From 3a4e46741749a8c6d7f702e015285653bc1acdb0 Mon Sep 17 00:00:00 2001 From: Minho Ryu Date: Tue, 21 Jan 2025 06:04:00 +0900 Subject: [PATCH] apply precommit (#2636) --- lm_eval/tasks/global_mmlu/README.md | 19 ++++- .../global_mmlu/{ => default}/_default_yaml | 0 .../{ => default}/_generate_configs.py | 0 .../{ => default}/global_mmlu_ar.yaml | 0 .../{ => default}/global_mmlu_bn.yaml | 0 .../{ => default}/global_mmlu_de.yaml | 0 .../{ => default}/global_mmlu_en.yaml | 0 .../{ => default}/global_mmlu_es.yaml | 0 .../{ => default}/global_mmlu_fr.yaml | 0 .../{ => default}/global_mmlu_hi.yaml | 0 .../{ => default}/global_mmlu_id.yaml | 0 .../{ => default}/global_mmlu_it.yaml | 0 .../{ => default}/global_mmlu_ja.yaml | 0 .../{ => default}/global_mmlu_ko.yaml | 0 .../{ => default}/global_mmlu_pt.yaml | 0 .../{ => default}/global_mmlu_sw.yaml | 0 .../{ => default}/global_mmlu_yo.yaml | 0 .../{ => default}/global_mmlu_zh.yaml | 0 .../global_mmlu/full/am/_am_template_yaml | 16 ++++ .../full/am/_global_mmlu_full_am.yaml | 11 +++ .../am/_global_mmlu_full_am_humanities.yaml | 8 ++ .../full/am/_global_mmlu_full_am_other.yaml | 8 ++ .../_global_mmlu_full_am_social_sciences.yaml | 8 ++ .../full/am/_global_mmlu_full_am_stem.yaml | 8 ++ .../global_mmlu_full_am_abstract_algebra.yaml | 5 ++ .../full/am/global_mmlu_full_am_anatomy.yaml | 5 ++ .../am/global_mmlu_full_am_astronomy.yaml | 5 ++ .../global_mmlu_full_am_business_ethics.yaml | 5 ++ ...lobal_mmlu_full_am_clinical_knowledge.yaml | 5 ++ .../global_mmlu_full_am_college_biology.yaml | 5 ++ ...global_mmlu_full_am_college_chemistry.yaml | 5 ++ ...mmlu_full_am_college_computer_science.yaml | 5 ++ ...obal_mmlu_full_am_college_mathematics.yaml | 5 ++ .../global_mmlu_full_am_college_medicine.yaml | 5 ++ .../global_mmlu_full_am_college_physics.yaml | 5 ++ ...global_mmlu_full_am_computer_security.yaml | 5 ++ ...lobal_mmlu_full_am_conceptual_physics.yaml | 5 ++ .../am/global_mmlu_full_am_econometrics.yaml | 5 ++ ...l_mmlu_full_am_electrical_engineering.yaml | 5 ++ ...l_mmlu_full_am_elementary_mathematics.yaml | 5 ++ .../am/global_mmlu_full_am_formal_logic.yaml | 5 ++ .../am/global_mmlu_full_am_global_facts.yaml | 5 ++ ...obal_mmlu_full_am_high_school_biology.yaml | 5 ++ ...al_mmlu_full_am_high_school_chemistry.yaml | 5 ++ ..._full_am_high_school_computer_science.yaml | 5 ++ ..._full_am_high_school_european_history.yaml | 5 ++ ...al_mmlu_full_am_high_school_geography.yaml | 5 ++ ...m_high_school_government_and_politics.yaml | 5 ++ ...lu_full_am_high_school_macroeconomics.yaml | 5 ++ ..._mmlu_full_am_high_school_mathematics.yaml | 5 ++ ...lu_full_am_high_school_microeconomics.yaml | 5 ++ ...obal_mmlu_full_am_high_school_physics.yaml | 5 ++ ...l_mmlu_full_am_high_school_psychology.yaml | 5 ++ ...l_mmlu_full_am_high_school_statistics.yaml | 5 ++ ...l_mmlu_full_am_high_school_us_history.yaml | 5 ++ ...mlu_full_am_high_school_world_history.yaml | 5 ++ .../am/global_mmlu_full_am_human_aging.yaml | 5 ++ .../global_mmlu_full_am_human_sexuality.yaml | 5 ++ ...global_mmlu_full_am_international_law.yaml | 5 ++ .../am/global_mmlu_full_am_jurisprudence.yaml | 5 ++ ...global_mmlu_full_am_logical_fallacies.yaml | 5 ++ .../global_mmlu_full_am_machine_learning.yaml | 5 ++ .../am/global_mmlu_full_am_management.yaml | 5 ++ .../am/global_mmlu_full_am_marketing.yaml | 5 ++ .../global_mmlu_full_am_medical_genetics.yaml | 5 ++ .../am/global_mmlu_full_am_miscellaneous.yaml | 5 ++ .../global_mmlu_full_am_moral_disputes.yaml | 5 ++ .../global_mmlu_full_am_moral_scenarios.yaml | 5 ++ .../am/global_mmlu_full_am_nutrition.yaml | 5 ++ .../am/global_mmlu_full_am_philosophy.yaml | 5 ++ .../am/global_mmlu_full_am_prehistory.yaml | 5 ++ ..._mmlu_full_am_professional_accounting.yaml | 5 ++ .../global_mmlu_full_am_professional_law.yaml | 5 ++ ...al_mmlu_full_am_professional_medicine.yaml | 5 ++ ..._mmlu_full_am_professional_psychology.yaml | 5 ++ .../global_mmlu_full_am_public_relations.yaml | 5 ++ .../global_mmlu_full_am_security_studies.yaml | 5 ++ .../am/global_mmlu_full_am_sociology.yaml | 5 ++ ...global_mmlu_full_am_us_foreign_policy.yaml | 5 ++ .../full/am/global_mmlu_full_am_virology.yaml | 5 ++ .../global_mmlu_full_am_world_religions.yaml | 5 ++ lm_eval/tasks/global_mmlu/full/am/utils.py | 73 +++++++++++++++++++ .../global_mmlu/full/ar/_ar_template_yaml | 16 ++++ .../full/ar/_global_mmlu_full_ar.yaml | 11 +++ .../ar/_global_mmlu_full_ar_humanities.yaml | 8 ++ .../full/ar/_global_mmlu_full_ar_other.yaml | 8 ++ .../_global_mmlu_full_ar_social_sciences.yaml | 8 ++ .../full/ar/_global_mmlu_full_ar_stem.yaml | 8 ++ .../global_mmlu_full_ar_abstract_algebra.yaml | 5 ++ .../full/ar/global_mmlu_full_ar_anatomy.yaml | 5 ++ .../ar/global_mmlu_full_ar_astronomy.yaml | 5 ++ .../global_mmlu_full_ar_business_ethics.yaml | 5 ++ ...lobal_mmlu_full_ar_clinical_knowledge.yaml | 5 ++ .../global_mmlu_full_ar_college_biology.yaml | 5 ++ ...global_mmlu_full_ar_college_chemistry.yaml | 5 ++ ...mmlu_full_ar_college_computer_science.yaml | 5 ++ ...obal_mmlu_full_ar_college_mathematics.yaml | 5 ++ .../global_mmlu_full_ar_college_medicine.yaml | 5 ++ .../global_mmlu_full_ar_college_physics.yaml | 5 ++ ...global_mmlu_full_ar_computer_security.yaml | 5 ++ ...lobal_mmlu_full_ar_conceptual_physics.yaml | 5 ++ .../ar/global_mmlu_full_ar_econometrics.yaml | 5 ++ ...l_mmlu_full_ar_electrical_engineering.yaml | 5 ++ ...l_mmlu_full_ar_elementary_mathematics.yaml | 5 ++ .../ar/global_mmlu_full_ar_formal_logic.yaml | 5 ++ .../ar/global_mmlu_full_ar_global_facts.yaml | 5 ++ ...obal_mmlu_full_ar_high_school_biology.yaml | 5 ++ ...al_mmlu_full_ar_high_school_chemistry.yaml | 5 ++ ..._full_ar_high_school_computer_science.yaml | 5 ++ ..._full_ar_high_school_european_history.yaml | 5 ++ ...al_mmlu_full_ar_high_school_geography.yaml | 5 ++ ...r_high_school_government_and_politics.yaml | 5 ++ ...lu_full_ar_high_school_macroeconomics.yaml | 5 ++ ..._mmlu_full_ar_high_school_mathematics.yaml | 5 ++ ...lu_full_ar_high_school_microeconomics.yaml | 5 ++ ...obal_mmlu_full_ar_high_school_physics.yaml | 5 ++ ...l_mmlu_full_ar_high_school_psychology.yaml | 5 ++ ...l_mmlu_full_ar_high_school_statistics.yaml | 5 ++ ...l_mmlu_full_ar_high_school_us_history.yaml | 5 ++ ...mlu_full_ar_high_school_world_history.yaml | 5 ++ .../ar/global_mmlu_full_ar_human_aging.yaml | 5 ++ .../global_mmlu_full_ar_human_sexuality.yaml | 5 ++ ...global_mmlu_full_ar_international_law.yaml | 5 ++ .../ar/global_mmlu_full_ar_jurisprudence.yaml | 5 ++ ...global_mmlu_full_ar_logical_fallacies.yaml | 5 ++ .../global_mmlu_full_ar_machine_learning.yaml | 5 ++ .../ar/global_mmlu_full_ar_management.yaml | 5 ++ .../ar/global_mmlu_full_ar_marketing.yaml | 5 ++ .../global_mmlu_full_ar_medical_genetics.yaml | 5 ++ .../ar/global_mmlu_full_ar_miscellaneous.yaml | 5 ++ .../global_mmlu_full_ar_moral_disputes.yaml | 5 ++ .../global_mmlu_full_ar_moral_scenarios.yaml | 5 ++ .../ar/global_mmlu_full_ar_nutrition.yaml | 5 ++ .../ar/global_mmlu_full_ar_philosophy.yaml | 5 ++ .../ar/global_mmlu_full_ar_prehistory.yaml | 5 ++ ..._mmlu_full_ar_professional_accounting.yaml | 5 ++ .../global_mmlu_full_ar_professional_law.yaml | 5 ++ ...al_mmlu_full_ar_professional_medicine.yaml | 5 ++ ..._mmlu_full_ar_professional_psychology.yaml | 5 ++ .../global_mmlu_full_ar_public_relations.yaml | 5 ++ .../global_mmlu_full_ar_security_studies.yaml | 5 ++ .../ar/global_mmlu_full_ar_sociology.yaml | 5 ++ ...global_mmlu_full_ar_us_foreign_policy.yaml | 5 ++ .../full/ar/global_mmlu_full_ar_virology.yaml | 5 ++ .../global_mmlu_full_ar_world_religions.yaml | 5 ++ lm_eval/tasks/global_mmlu/full/ar/utils.py | 73 +++++++++++++++++++ .../global_mmlu/full/bn/_bn_template_yaml | 16 ++++ .../full/bn/_global_mmlu_full_bn.yaml | 11 +++ .../bn/_global_mmlu_full_bn_humanities.yaml | 8 ++ .../full/bn/_global_mmlu_full_bn_other.yaml | 8 ++ .../_global_mmlu_full_bn_social_sciences.yaml | 8 ++ .../full/bn/_global_mmlu_full_bn_stem.yaml | 8 ++ .../global_mmlu_full_bn_abstract_algebra.yaml | 5 ++ .../full/bn/global_mmlu_full_bn_anatomy.yaml | 5 ++ .../bn/global_mmlu_full_bn_astronomy.yaml | 5 ++ .../global_mmlu_full_bn_business_ethics.yaml | 5 ++ ...lobal_mmlu_full_bn_clinical_knowledge.yaml | 5 ++ .../global_mmlu_full_bn_college_biology.yaml | 5 ++ ...global_mmlu_full_bn_college_chemistry.yaml | 5 ++ ...mmlu_full_bn_college_computer_science.yaml | 5 ++ ...obal_mmlu_full_bn_college_mathematics.yaml | 5 ++ .../global_mmlu_full_bn_college_medicine.yaml | 5 ++ .../global_mmlu_full_bn_college_physics.yaml | 5 ++ ...global_mmlu_full_bn_computer_security.yaml | 5 ++ ...lobal_mmlu_full_bn_conceptual_physics.yaml | 5 ++ .../bn/global_mmlu_full_bn_econometrics.yaml | 5 ++ ...l_mmlu_full_bn_electrical_engineering.yaml | 5 ++ ...l_mmlu_full_bn_elementary_mathematics.yaml | 5 ++ .../bn/global_mmlu_full_bn_formal_logic.yaml | 5 ++ .../bn/global_mmlu_full_bn_global_facts.yaml | 5 ++ ...obal_mmlu_full_bn_high_school_biology.yaml | 5 ++ ...al_mmlu_full_bn_high_school_chemistry.yaml | 5 ++ ..._full_bn_high_school_computer_science.yaml | 5 ++ ..._full_bn_high_school_european_history.yaml | 5 ++ ...al_mmlu_full_bn_high_school_geography.yaml | 5 ++ ...n_high_school_government_and_politics.yaml | 5 ++ ...lu_full_bn_high_school_macroeconomics.yaml | 5 ++ ..._mmlu_full_bn_high_school_mathematics.yaml | 5 ++ ...lu_full_bn_high_school_microeconomics.yaml | 5 ++ ...obal_mmlu_full_bn_high_school_physics.yaml | 5 ++ ...l_mmlu_full_bn_high_school_psychology.yaml | 5 ++ ...l_mmlu_full_bn_high_school_statistics.yaml | 5 ++ ...l_mmlu_full_bn_high_school_us_history.yaml | 5 ++ ...mlu_full_bn_high_school_world_history.yaml | 5 ++ .../bn/global_mmlu_full_bn_human_aging.yaml | 5 ++ .../global_mmlu_full_bn_human_sexuality.yaml | 5 ++ ...global_mmlu_full_bn_international_law.yaml | 5 ++ .../bn/global_mmlu_full_bn_jurisprudence.yaml | 5 ++ ...global_mmlu_full_bn_logical_fallacies.yaml | 5 ++ .../global_mmlu_full_bn_machine_learning.yaml | 5 ++ .../bn/global_mmlu_full_bn_management.yaml | 5 ++ .../bn/global_mmlu_full_bn_marketing.yaml | 5 ++ .../global_mmlu_full_bn_medical_genetics.yaml | 5 ++ .../bn/global_mmlu_full_bn_miscellaneous.yaml | 5 ++ .../global_mmlu_full_bn_moral_disputes.yaml | 5 ++ .../global_mmlu_full_bn_moral_scenarios.yaml | 5 ++ .../bn/global_mmlu_full_bn_nutrition.yaml | 5 ++ .../bn/global_mmlu_full_bn_philosophy.yaml | 5 ++ .../bn/global_mmlu_full_bn_prehistory.yaml | 5 ++ ..._mmlu_full_bn_professional_accounting.yaml | 5 ++ .../global_mmlu_full_bn_professional_law.yaml | 5 ++ ...al_mmlu_full_bn_professional_medicine.yaml | 5 ++ ..._mmlu_full_bn_professional_psychology.yaml | 5 ++ .../global_mmlu_full_bn_public_relations.yaml | 5 ++ .../global_mmlu_full_bn_security_studies.yaml | 5 ++ .../bn/global_mmlu_full_bn_sociology.yaml | 5 ++ ...global_mmlu_full_bn_us_foreign_policy.yaml | 5 ++ .../full/bn/global_mmlu_full_bn_virology.yaml | 5 ++ .../global_mmlu_full_bn_world_religions.yaml | 5 ++ lm_eval/tasks/global_mmlu/full/bn/utils.py | 73 +++++++++++++++++++ .../global_mmlu/full/cs/_cs_template_yaml | 16 ++++ .../full/cs/_global_mmlu_full_cs.yaml | 11 +++ .../cs/_global_mmlu_full_cs_humanities.yaml | 8 ++ .../full/cs/_global_mmlu_full_cs_other.yaml | 8 ++ .../_global_mmlu_full_cs_social_sciences.yaml | 8 ++ .../full/cs/_global_mmlu_full_cs_stem.yaml | 8 ++ .../global_mmlu_full_cs_abstract_algebra.yaml | 5 ++ .../full/cs/global_mmlu_full_cs_anatomy.yaml | 5 ++ .../cs/global_mmlu_full_cs_astronomy.yaml | 5 ++ .../global_mmlu_full_cs_business_ethics.yaml | 5 ++ ...lobal_mmlu_full_cs_clinical_knowledge.yaml | 5 ++ .../global_mmlu_full_cs_college_biology.yaml | 5 ++ ...global_mmlu_full_cs_college_chemistry.yaml | 5 ++ ...mmlu_full_cs_college_computer_science.yaml | 5 ++ ...obal_mmlu_full_cs_college_mathematics.yaml | 5 ++ .../global_mmlu_full_cs_college_medicine.yaml | 5 ++ .../global_mmlu_full_cs_college_physics.yaml | 5 ++ ...global_mmlu_full_cs_computer_security.yaml | 5 ++ ...lobal_mmlu_full_cs_conceptual_physics.yaml | 5 ++ .../cs/global_mmlu_full_cs_econometrics.yaml | 5 ++ ...l_mmlu_full_cs_electrical_engineering.yaml | 5 ++ ...l_mmlu_full_cs_elementary_mathematics.yaml | 5 ++ .../cs/global_mmlu_full_cs_formal_logic.yaml | 5 ++ .../cs/global_mmlu_full_cs_global_facts.yaml | 5 ++ ...obal_mmlu_full_cs_high_school_biology.yaml | 5 ++ ...al_mmlu_full_cs_high_school_chemistry.yaml | 5 ++ ..._full_cs_high_school_computer_science.yaml | 5 ++ ..._full_cs_high_school_european_history.yaml | 5 ++ ...al_mmlu_full_cs_high_school_geography.yaml | 5 ++ ...s_high_school_government_and_politics.yaml | 5 ++ ...lu_full_cs_high_school_macroeconomics.yaml | 5 ++ ..._mmlu_full_cs_high_school_mathematics.yaml | 5 ++ ...lu_full_cs_high_school_microeconomics.yaml | 5 ++ ...obal_mmlu_full_cs_high_school_physics.yaml | 5 ++ ...l_mmlu_full_cs_high_school_psychology.yaml | 5 ++ ...l_mmlu_full_cs_high_school_statistics.yaml | 5 ++ ...l_mmlu_full_cs_high_school_us_history.yaml | 5 ++ ...mlu_full_cs_high_school_world_history.yaml | 5 ++ .../cs/global_mmlu_full_cs_human_aging.yaml | 5 ++ .../global_mmlu_full_cs_human_sexuality.yaml | 5 ++ ...global_mmlu_full_cs_international_law.yaml | 5 ++ .../cs/global_mmlu_full_cs_jurisprudence.yaml | 5 ++ ...global_mmlu_full_cs_logical_fallacies.yaml | 5 ++ .../global_mmlu_full_cs_machine_learning.yaml | 5 ++ .../cs/global_mmlu_full_cs_management.yaml | 5 ++ .../cs/global_mmlu_full_cs_marketing.yaml | 5 ++ .../global_mmlu_full_cs_medical_genetics.yaml | 5 ++ .../cs/global_mmlu_full_cs_miscellaneous.yaml | 5 ++ .../global_mmlu_full_cs_moral_disputes.yaml | 5 ++ .../global_mmlu_full_cs_moral_scenarios.yaml | 5 ++ .../cs/global_mmlu_full_cs_nutrition.yaml | 5 ++ .../cs/global_mmlu_full_cs_philosophy.yaml | 5 ++ .../cs/global_mmlu_full_cs_prehistory.yaml | 5 ++ ..._mmlu_full_cs_professional_accounting.yaml | 5 ++ .../global_mmlu_full_cs_professional_law.yaml | 5 ++ ...al_mmlu_full_cs_professional_medicine.yaml | 5 ++ ..._mmlu_full_cs_professional_psychology.yaml | 5 ++ .../global_mmlu_full_cs_public_relations.yaml | 5 ++ .../global_mmlu_full_cs_security_studies.yaml | 5 ++ .../cs/global_mmlu_full_cs_sociology.yaml | 5 ++ ...global_mmlu_full_cs_us_foreign_policy.yaml | 5 ++ .../full/cs/global_mmlu_full_cs_virology.yaml | 5 ++ .../global_mmlu_full_cs_world_religions.yaml | 5 ++ lm_eval/tasks/global_mmlu/full/cs/utils.py | 73 +++++++++++++++++++ .../global_mmlu/full/de/_de_template_yaml | 16 ++++ .../full/de/_global_mmlu_full_de.yaml | 11 +++ .../de/_global_mmlu_full_de_humanities.yaml | 8 ++ .../full/de/_global_mmlu_full_de_other.yaml | 8 ++ .../_global_mmlu_full_de_social_sciences.yaml | 8 ++ .../full/de/_global_mmlu_full_de_stem.yaml | 8 ++ .../global_mmlu_full_de_abstract_algebra.yaml | 5 ++ .../full/de/global_mmlu_full_de_anatomy.yaml | 5 ++ .../de/global_mmlu_full_de_astronomy.yaml | 5 ++ .../global_mmlu_full_de_business_ethics.yaml | 5 ++ ...lobal_mmlu_full_de_clinical_knowledge.yaml | 5 ++ .../global_mmlu_full_de_college_biology.yaml | 5 ++ ...global_mmlu_full_de_college_chemistry.yaml | 5 ++ ...mmlu_full_de_college_computer_science.yaml | 5 ++ ...obal_mmlu_full_de_college_mathematics.yaml | 5 ++ .../global_mmlu_full_de_college_medicine.yaml | 5 ++ .../global_mmlu_full_de_college_physics.yaml | 5 ++ ...global_mmlu_full_de_computer_security.yaml | 5 ++ ...lobal_mmlu_full_de_conceptual_physics.yaml | 5 ++ .../de/global_mmlu_full_de_econometrics.yaml | 5 ++ ...l_mmlu_full_de_electrical_engineering.yaml | 5 ++ ...l_mmlu_full_de_elementary_mathematics.yaml | 5 ++ .../de/global_mmlu_full_de_formal_logic.yaml | 5 ++ .../de/global_mmlu_full_de_global_facts.yaml | 5 ++ ...obal_mmlu_full_de_high_school_biology.yaml | 5 ++ ...al_mmlu_full_de_high_school_chemistry.yaml | 5 ++ ..._full_de_high_school_computer_science.yaml | 5 ++ ..._full_de_high_school_european_history.yaml | 5 ++ ...al_mmlu_full_de_high_school_geography.yaml | 5 ++ ...e_high_school_government_and_politics.yaml | 5 ++ ...lu_full_de_high_school_macroeconomics.yaml | 5 ++ ..._mmlu_full_de_high_school_mathematics.yaml | 5 ++ ...lu_full_de_high_school_microeconomics.yaml | 5 ++ ...obal_mmlu_full_de_high_school_physics.yaml | 5 ++ ...l_mmlu_full_de_high_school_psychology.yaml | 5 ++ ...l_mmlu_full_de_high_school_statistics.yaml | 5 ++ ...l_mmlu_full_de_high_school_us_history.yaml | 5 ++ ...mlu_full_de_high_school_world_history.yaml | 5 ++ .../de/global_mmlu_full_de_human_aging.yaml | 5 ++ .../global_mmlu_full_de_human_sexuality.yaml | 5 ++ ...global_mmlu_full_de_international_law.yaml | 5 ++ .../de/global_mmlu_full_de_jurisprudence.yaml | 5 ++ ...global_mmlu_full_de_logical_fallacies.yaml | 5 ++ .../global_mmlu_full_de_machine_learning.yaml | 5 ++ .../de/global_mmlu_full_de_management.yaml | 5 ++ .../de/global_mmlu_full_de_marketing.yaml | 5 ++ .../global_mmlu_full_de_medical_genetics.yaml | 5 ++ .../de/global_mmlu_full_de_miscellaneous.yaml | 5 ++ .../global_mmlu_full_de_moral_disputes.yaml | 5 ++ .../global_mmlu_full_de_moral_scenarios.yaml | 5 ++ .../de/global_mmlu_full_de_nutrition.yaml | 5 ++ .../de/global_mmlu_full_de_philosophy.yaml | 5 ++ .../de/global_mmlu_full_de_prehistory.yaml | 5 ++ ..._mmlu_full_de_professional_accounting.yaml | 5 ++ .../global_mmlu_full_de_professional_law.yaml | 5 ++ ...al_mmlu_full_de_professional_medicine.yaml | 5 ++ ..._mmlu_full_de_professional_psychology.yaml | 5 ++ .../global_mmlu_full_de_public_relations.yaml | 5 ++ .../global_mmlu_full_de_security_studies.yaml | 5 ++ .../de/global_mmlu_full_de_sociology.yaml | 5 ++ ...global_mmlu_full_de_us_foreign_policy.yaml | 5 ++ .../full/de/global_mmlu_full_de_virology.yaml | 5 ++ .../global_mmlu_full_de_world_religions.yaml | 5 ++ lm_eval/tasks/global_mmlu/full/de/utils.py | 73 +++++++++++++++++++ .../global_mmlu/full/el/_el_template_yaml | 16 ++++ .../full/el/_global_mmlu_full_el.yaml | 11 +++ .../el/_global_mmlu_full_el_humanities.yaml | 8 ++ .../full/el/_global_mmlu_full_el_other.yaml | 8 ++ .../_global_mmlu_full_el_social_sciences.yaml | 8 ++ .../full/el/_global_mmlu_full_el_stem.yaml | 8 ++ .../global_mmlu_full_el_abstract_algebra.yaml | 5 ++ .../full/el/global_mmlu_full_el_anatomy.yaml | 5 ++ .../el/global_mmlu_full_el_astronomy.yaml | 5 ++ .../global_mmlu_full_el_business_ethics.yaml | 5 ++ ...lobal_mmlu_full_el_clinical_knowledge.yaml | 5 ++ .../global_mmlu_full_el_college_biology.yaml | 5 ++ ...global_mmlu_full_el_college_chemistry.yaml | 5 ++ ...mmlu_full_el_college_computer_science.yaml | 5 ++ ...obal_mmlu_full_el_college_mathematics.yaml | 5 ++ .../global_mmlu_full_el_college_medicine.yaml | 5 ++ .../global_mmlu_full_el_college_physics.yaml | 5 ++ ...global_mmlu_full_el_computer_security.yaml | 5 ++ ...lobal_mmlu_full_el_conceptual_physics.yaml | 5 ++ .../el/global_mmlu_full_el_econometrics.yaml | 5 ++ ...l_mmlu_full_el_electrical_engineering.yaml | 5 ++ ...l_mmlu_full_el_elementary_mathematics.yaml | 5 ++ .../el/global_mmlu_full_el_formal_logic.yaml | 5 ++ .../el/global_mmlu_full_el_global_facts.yaml | 5 ++ ...obal_mmlu_full_el_high_school_biology.yaml | 5 ++ ...al_mmlu_full_el_high_school_chemistry.yaml | 5 ++ ..._full_el_high_school_computer_science.yaml | 5 ++ ..._full_el_high_school_european_history.yaml | 5 ++ ...al_mmlu_full_el_high_school_geography.yaml | 5 ++ ...l_high_school_government_and_politics.yaml | 5 ++ ...lu_full_el_high_school_macroeconomics.yaml | 5 ++ ..._mmlu_full_el_high_school_mathematics.yaml | 5 ++ ...lu_full_el_high_school_microeconomics.yaml | 5 ++ ...obal_mmlu_full_el_high_school_physics.yaml | 5 ++ ...l_mmlu_full_el_high_school_psychology.yaml | 5 ++ ...l_mmlu_full_el_high_school_statistics.yaml | 5 ++ ...l_mmlu_full_el_high_school_us_history.yaml | 5 ++ ...mlu_full_el_high_school_world_history.yaml | 5 ++ .../el/global_mmlu_full_el_human_aging.yaml | 5 ++ .../global_mmlu_full_el_human_sexuality.yaml | 5 ++ ...global_mmlu_full_el_international_law.yaml | 5 ++ .../el/global_mmlu_full_el_jurisprudence.yaml | 5 ++ ...global_mmlu_full_el_logical_fallacies.yaml | 5 ++ .../global_mmlu_full_el_machine_learning.yaml | 5 ++ .../el/global_mmlu_full_el_management.yaml | 5 ++ .../el/global_mmlu_full_el_marketing.yaml | 5 ++ .../global_mmlu_full_el_medical_genetics.yaml | 5 ++ .../el/global_mmlu_full_el_miscellaneous.yaml | 5 ++ .../global_mmlu_full_el_moral_disputes.yaml | 5 ++ .../global_mmlu_full_el_moral_scenarios.yaml | 5 ++ .../el/global_mmlu_full_el_nutrition.yaml | 5 ++ .../el/global_mmlu_full_el_philosophy.yaml | 5 ++ .../el/global_mmlu_full_el_prehistory.yaml | 5 ++ ..._mmlu_full_el_professional_accounting.yaml | 5 ++ .../global_mmlu_full_el_professional_law.yaml | 5 ++ ...al_mmlu_full_el_professional_medicine.yaml | 5 ++ ..._mmlu_full_el_professional_psychology.yaml | 5 ++ .../global_mmlu_full_el_public_relations.yaml | 5 ++ .../global_mmlu_full_el_security_studies.yaml | 5 ++ .../el/global_mmlu_full_el_sociology.yaml | 5 ++ ...global_mmlu_full_el_us_foreign_policy.yaml | 5 ++ .../full/el/global_mmlu_full_el_virology.yaml | 5 ++ .../global_mmlu_full_el_world_religions.yaml | 5 ++ lm_eval/tasks/global_mmlu/full/el/utils.py | 73 +++++++++++++++++++ .../global_mmlu/full/en/_en_template_yaml | 16 ++++ .../full/en/_global_mmlu_full_en.yaml | 11 +++ .../en/_global_mmlu_full_en_humanities.yaml | 8 ++ .../full/en/_global_mmlu_full_en_other.yaml | 8 ++ .../_global_mmlu_full_en_social_sciences.yaml | 8 ++ .../full/en/_global_mmlu_full_en_stem.yaml | 8 ++ .../global_mmlu_full_en_abstract_algebra.yaml | 5 ++ .../full/en/global_mmlu_full_en_anatomy.yaml | 5 ++ .../en/global_mmlu_full_en_astronomy.yaml | 5 ++ .../global_mmlu_full_en_business_ethics.yaml | 5 ++ ...lobal_mmlu_full_en_clinical_knowledge.yaml | 5 ++ .../global_mmlu_full_en_college_biology.yaml | 5 ++ ...global_mmlu_full_en_college_chemistry.yaml | 5 ++ ...mmlu_full_en_college_computer_science.yaml | 5 ++ ...obal_mmlu_full_en_college_mathematics.yaml | 5 ++ .../global_mmlu_full_en_college_medicine.yaml | 5 ++ .../global_mmlu_full_en_college_physics.yaml | 5 ++ ...global_mmlu_full_en_computer_security.yaml | 5 ++ ...lobal_mmlu_full_en_conceptual_physics.yaml | 5 ++ .../en/global_mmlu_full_en_econometrics.yaml | 5 ++ ...l_mmlu_full_en_electrical_engineering.yaml | 5 ++ ...l_mmlu_full_en_elementary_mathematics.yaml | 5 ++ .../en/global_mmlu_full_en_formal_logic.yaml | 5 ++ .../en/global_mmlu_full_en_global_facts.yaml | 5 ++ ...obal_mmlu_full_en_high_school_biology.yaml | 5 ++ ...al_mmlu_full_en_high_school_chemistry.yaml | 5 ++ ..._full_en_high_school_computer_science.yaml | 5 ++ ..._full_en_high_school_european_history.yaml | 5 ++ ...al_mmlu_full_en_high_school_geography.yaml | 5 ++ ...n_high_school_government_and_politics.yaml | 5 ++ ...lu_full_en_high_school_macroeconomics.yaml | 5 ++ ..._mmlu_full_en_high_school_mathematics.yaml | 5 ++ ...lu_full_en_high_school_microeconomics.yaml | 5 ++ ...obal_mmlu_full_en_high_school_physics.yaml | 5 ++ ...l_mmlu_full_en_high_school_psychology.yaml | 5 ++ ...l_mmlu_full_en_high_school_statistics.yaml | 5 ++ ...l_mmlu_full_en_high_school_us_history.yaml | 5 ++ ...mlu_full_en_high_school_world_history.yaml | 5 ++ .../en/global_mmlu_full_en_human_aging.yaml | 5 ++ .../global_mmlu_full_en_human_sexuality.yaml | 5 ++ ...global_mmlu_full_en_international_law.yaml | 5 ++ .../en/global_mmlu_full_en_jurisprudence.yaml | 5 ++ ...global_mmlu_full_en_logical_fallacies.yaml | 5 ++ .../global_mmlu_full_en_machine_learning.yaml | 5 ++ .../en/global_mmlu_full_en_management.yaml | 5 ++ .../en/global_mmlu_full_en_marketing.yaml | 5 ++ .../global_mmlu_full_en_medical_genetics.yaml | 5 ++ .../en/global_mmlu_full_en_miscellaneous.yaml | 5 ++ .../global_mmlu_full_en_moral_disputes.yaml | 5 ++ .../global_mmlu_full_en_moral_scenarios.yaml | 5 ++ .../en/global_mmlu_full_en_nutrition.yaml | 5 ++ .../en/global_mmlu_full_en_philosophy.yaml | 5 ++ .../en/global_mmlu_full_en_prehistory.yaml | 5 ++ ..._mmlu_full_en_professional_accounting.yaml | 5 ++ .../global_mmlu_full_en_professional_law.yaml | 5 ++ ...al_mmlu_full_en_professional_medicine.yaml | 5 ++ ..._mmlu_full_en_professional_psychology.yaml | 5 ++ .../global_mmlu_full_en_public_relations.yaml | 5 ++ .../global_mmlu_full_en_security_studies.yaml | 5 ++ .../en/global_mmlu_full_en_sociology.yaml | 5 ++ ...global_mmlu_full_en_us_foreign_policy.yaml | 5 ++ .../full/en/global_mmlu_full_en_virology.yaml | 5 ++ .../global_mmlu_full_en_world_religions.yaml | 5 ++ lm_eval/tasks/global_mmlu/full/en/utils.py | 73 +++++++++++++++++++ .../global_mmlu/full/es/_es_template_yaml | 16 ++++ .../full/es/_global_mmlu_full_es.yaml | 11 +++ .../es/_global_mmlu_full_es_humanities.yaml | 8 ++ .../full/es/_global_mmlu_full_es_other.yaml | 8 ++ .../_global_mmlu_full_es_social_sciences.yaml | 8 ++ .../full/es/_global_mmlu_full_es_stem.yaml | 8 ++ .../global_mmlu_full_es_abstract_algebra.yaml | 5 ++ .../full/es/global_mmlu_full_es_anatomy.yaml | 5 ++ .../es/global_mmlu_full_es_astronomy.yaml | 5 ++ .../global_mmlu_full_es_business_ethics.yaml | 5 ++ ...lobal_mmlu_full_es_clinical_knowledge.yaml | 5 ++ .../global_mmlu_full_es_college_biology.yaml | 5 ++ ...global_mmlu_full_es_college_chemistry.yaml | 5 ++ ...mmlu_full_es_college_computer_science.yaml | 5 ++ ...obal_mmlu_full_es_college_mathematics.yaml | 5 ++ .../global_mmlu_full_es_college_medicine.yaml | 5 ++ .../global_mmlu_full_es_college_physics.yaml | 5 ++ ...global_mmlu_full_es_computer_security.yaml | 5 ++ ...lobal_mmlu_full_es_conceptual_physics.yaml | 5 ++ .../es/global_mmlu_full_es_econometrics.yaml | 5 ++ ...l_mmlu_full_es_electrical_engineering.yaml | 5 ++ ...l_mmlu_full_es_elementary_mathematics.yaml | 5 ++ .../es/global_mmlu_full_es_formal_logic.yaml | 5 ++ .../es/global_mmlu_full_es_global_facts.yaml | 5 ++ ...obal_mmlu_full_es_high_school_biology.yaml | 5 ++ ...al_mmlu_full_es_high_school_chemistry.yaml | 5 ++ ..._full_es_high_school_computer_science.yaml | 5 ++ ..._full_es_high_school_european_history.yaml | 5 ++ ...al_mmlu_full_es_high_school_geography.yaml | 5 ++ ...s_high_school_government_and_politics.yaml | 5 ++ ...lu_full_es_high_school_macroeconomics.yaml | 5 ++ ..._mmlu_full_es_high_school_mathematics.yaml | 5 ++ ...lu_full_es_high_school_microeconomics.yaml | 5 ++ ...obal_mmlu_full_es_high_school_physics.yaml | 5 ++ ...l_mmlu_full_es_high_school_psychology.yaml | 5 ++ ...l_mmlu_full_es_high_school_statistics.yaml | 5 ++ ...l_mmlu_full_es_high_school_us_history.yaml | 5 ++ ...mlu_full_es_high_school_world_history.yaml | 5 ++ .../es/global_mmlu_full_es_human_aging.yaml | 5 ++ .../global_mmlu_full_es_human_sexuality.yaml | 5 ++ ...global_mmlu_full_es_international_law.yaml | 5 ++ .../es/global_mmlu_full_es_jurisprudence.yaml | 5 ++ ...global_mmlu_full_es_logical_fallacies.yaml | 5 ++ .../global_mmlu_full_es_machine_learning.yaml | 5 ++ .../es/global_mmlu_full_es_management.yaml | 5 ++ .../es/global_mmlu_full_es_marketing.yaml | 5 ++ .../global_mmlu_full_es_medical_genetics.yaml | 5 ++ .../es/global_mmlu_full_es_miscellaneous.yaml | 5 ++ .../global_mmlu_full_es_moral_disputes.yaml | 5 ++ .../global_mmlu_full_es_moral_scenarios.yaml | 5 ++ .../es/global_mmlu_full_es_nutrition.yaml | 5 ++ .../es/global_mmlu_full_es_philosophy.yaml | 5 ++ .../es/global_mmlu_full_es_prehistory.yaml | 5 ++ ..._mmlu_full_es_professional_accounting.yaml | 5 ++ .../global_mmlu_full_es_professional_law.yaml | 5 ++ ...al_mmlu_full_es_professional_medicine.yaml | 5 ++ ..._mmlu_full_es_professional_psychology.yaml | 5 ++ .../global_mmlu_full_es_public_relations.yaml | 5 ++ .../global_mmlu_full_es_security_studies.yaml | 5 ++ .../es/global_mmlu_full_es_sociology.yaml | 5 ++ ...global_mmlu_full_es_us_foreign_policy.yaml | 5 ++ .../full/es/global_mmlu_full_es_virology.yaml | 5 ++ .../global_mmlu_full_es_world_religions.yaml | 5 ++ lm_eval/tasks/global_mmlu/full/es/utils.py | 73 +++++++++++++++++++ .../global_mmlu/full/fa/_fa_template_yaml | 16 ++++ .../full/fa/_global_mmlu_full_fa.yaml | 11 +++ .../fa/_global_mmlu_full_fa_humanities.yaml | 8 ++ .../full/fa/_global_mmlu_full_fa_other.yaml | 8 ++ .../_global_mmlu_full_fa_social_sciences.yaml | 8 ++ .../full/fa/_global_mmlu_full_fa_stem.yaml | 8 ++ .../global_mmlu_full_fa_abstract_algebra.yaml | 5 ++ .../full/fa/global_mmlu_full_fa_anatomy.yaml | 5 ++ .../fa/global_mmlu_full_fa_astronomy.yaml | 5 ++ .../global_mmlu_full_fa_business_ethics.yaml | 5 ++ ...lobal_mmlu_full_fa_clinical_knowledge.yaml | 5 ++ .../global_mmlu_full_fa_college_biology.yaml | 5 ++ ...global_mmlu_full_fa_college_chemistry.yaml | 5 ++ ...mmlu_full_fa_college_computer_science.yaml | 5 ++ ...obal_mmlu_full_fa_college_mathematics.yaml | 5 ++ .../global_mmlu_full_fa_college_medicine.yaml | 5 ++ .../global_mmlu_full_fa_college_physics.yaml | 5 ++ ...global_mmlu_full_fa_computer_security.yaml | 5 ++ ...lobal_mmlu_full_fa_conceptual_physics.yaml | 5 ++ .../fa/global_mmlu_full_fa_econometrics.yaml | 5 ++ ...l_mmlu_full_fa_electrical_engineering.yaml | 5 ++ ...l_mmlu_full_fa_elementary_mathematics.yaml | 5 ++ .../fa/global_mmlu_full_fa_formal_logic.yaml | 5 ++ .../fa/global_mmlu_full_fa_global_facts.yaml | 5 ++ ...obal_mmlu_full_fa_high_school_biology.yaml | 5 ++ ...al_mmlu_full_fa_high_school_chemistry.yaml | 5 ++ ..._full_fa_high_school_computer_science.yaml | 5 ++ ..._full_fa_high_school_european_history.yaml | 5 ++ ...al_mmlu_full_fa_high_school_geography.yaml | 5 ++ ...a_high_school_government_and_politics.yaml | 5 ++ ...lu_full_fa_high_school_macroeconomics.yaml | 5 ++ ..._mmlu_full_fa_high_school_mathematics.yaml | 5 ++ ...lu_full_fa_high_school_microeconomics.yaml | 5 ++ ...obal_mmlu_full_fa_high_school_physics.yaml | 5 ++ ...l_mmlu_full_fa_high_school_psychology.yaml | 5 ++ ...l_mmlu_full_fa_high_school_statistics.yaml | 5 ++ ...l_mmlu_full_fa_high_school_us_history.yaml | 5 ++ ...mlu_full_fa_high_school_world_history.yaml | 5 ++ .../fa/global_mmlu_full_fa_human_aging.yaml | 5 ++ .../global_mmlu_full_fa_human_sexuality.yaml | 5 ++ ...global_mmlu_full_fa_international_law.yaml | 5 ++ .../fa/global_mmlu_full_fa_jurisprudence.yaml | 5 ++ ...global_mmlu_full_fa_logical_fallacies.yaml | 5 ++ .../global_mmlu_full_fa_machine_learning.yaml | 5 ++ .../fa/global_mmlu_full_fa_management.yaml | 5 ++ .../fa/global_mmlu_full_fa_marketing.yaml | 5 ++ .../global_mmlu_full_fa_medical_genetics.yaml | 5 ++ .../fa/global_mmlu_full_fa_miscellaneous.yaml | 5 ++ .../global_mmlu_full_fa_moral_disputes.yaml | 5 ++ .../global_mmlu_full_fa_moral_scenarios.yaml | 5 ++ .../fa/global_mmlu_full_fa_nutrition.yaml | 5 ++ .../fa/global_mmlu_full_fa_philosophy.yaml | 5 ++ .../fa/global_mmlu_full_fa_prehistory.yaml | 5 ++ ..._mmlu_full_fa_professional_accounting.yaml | 5 ++ .../global_mmlu_full_fa_professional_law.yaml | 5 ++ ...al_mmlu_full_fa_professional_medicine.yaml | 5 ++ ..._mmlu_full_fa_professional_psychology.yaml | 5 ++ .../global_mmlu_full_fa_public_relations.yaml | 5 ++ .../global_mmlu_full_fa_security_studies.yaml | 5 ++ .../fa/global_mmlu_full_fa_sociology.yaml | 5 ++ ...global_mmlu_full_fa_us_foreign_policy.yaml | 5 ++ .../full/fa/global_mmlu_full_fa_virology.yaml | 5 ++ .../global_mmlu_full_fa_world_religions.yaml | 5 ++ lm_eval/tasks/global_mmlu/full/fa/utils.py | 73 +++++++++++++++++++ .../global_mmlu/full/fil/_fil_template_yaml | 16 ++++ .../full/fil/_global_mmlu_full_fil.yaml | 11 +++ .../fil/_global_mmlu_full_fil_humanities.yaml | 8 ++ .../full/fil/_global_mmlu_full_fil_other.yaml | 8 ++ ..._global_mmlu_full_fil_social_sciences.yaml | 8 ++ .../full/fil/_global_mmlu_full_fil_stem.yaml | 8 ++ ...global_mmlu_full_fil_abstract_algebra.yaml | 5 ++ .../fil/global_mmlu_full_fil_anatomy.yaml | 5 ++ .../fil/global_mmlu_full_fil_astronomy.yaml | 5 ++ .../global_mmlu_full_fil_business_ethics.yaml | 5 ++ ...obal_mmlu_full_fil_clinical_knowledge.yaml | 5 ++ .../global_mmlu_full_fil_college_biology.yaml | 5 ++ ...lobal_mmlu_full_fil_college_chemistry.yaml | 5 ++ ...mlu_full_fil_college_computer_science.yaml | 5 ++ ...bal_mmlu_full_fil_college_mathematics.yaml | 5 ++ ...global_mmlu_full_fil_college_medicine.yaml | 5 ++ .../global_mmlu_full_fil_college_physics.yaml | 5 ++ ...lobal_mmlu_full_fil_computer_security.yaml | 5 ++ ...obal_mmlu_full_fil_conceptual_physics.yaml | 5 ++ .../global_mmlu_full_fil_econometrics.yaml | 5 ++ ..._mmlu_full_fil_electrical_engineering.yaml | 5 ++ ..._mmlu_full_fil_elementary_mathematics.yaml | 5 ++ .../global_mmlu_full_fil_formal_logic.yaml | 5 ++ .../global_mmlu_full_fil_global_facts.yaml | 5 ++ ...bal_mmlu_full_fil_high_school_biology.yaml | 5 ++ ...l_mmlu_full_fil_high_school_chemistry.yaml | 5 ++ ...full_fil_high_school_computer_science.yaml | 5 ++ ...full_fil_high_school_european_history.yaml | 5 ++ ...l_mmlu_full_fil_high_school_geography.yaml | 5 ++ ...l_high_school_government_and_politics.yaml | 5 ++ ...u_full_fil_high_school_macroeconomics.yaml | 5 ++ ...mmlu_full_fil_high_school_mathematics.yaml | 5 ++ ...u_full_fil_high_school_microeconomics.yaml | 5 ++ ...bal_mmlu_full_fil_high_school_physics.yaml | 5 ++ ..._mmlu_full_fil_high_school_psychology.yaml | 5 ++ ..._mmlu_full_fil_high_school_statistics.yaml | 5 ++ ..._mmlu_full_fil_high_school_us_history.yaml | 5 ++ ...lu_full_fil_high_school_world_history.yaml | 5 ++ .../fil/global_mmlu_full_fil_human_aging.yaml | 5 ++ .../global_mmlu_full_fil_human_sexuality.yaml | 5 ++ ...lobal_mmlu_full_fil_international_law.yaml | 5 ++ .../global_mmlu_full_fil_jurisprudence.yaml | 5 ++ ...lobal_mmlu_full_fil_logical_fallacies.yaml | 5 ++ ...global_mmlu_full_fil_machine_learning.yaml | 5 ++ .../fil/global_mmlu_full_fil_management.yaml | 5 ++ .../fil/global_mmlu_full_fil_marketing.yaml | 5 ++ ...global_mmlu_full_fil_medical_genetics.yaml | 5 ++ .../global_mmlu_full_fil_miscellaneous.yaml | 5 ++ .../global_mmlu_full_fil_moral_disputes.yaml | 5 ++ .../global_mmlu_full_fil_moral_scenarios.yaml | 5 ++ .../fil/global_mmlu_full_fil_nutrition.yaml | 5 ++ .../fil/global_mmlu_full_fil_philosophy.yaml | 5 ++ .../fil/global_mmlu_full_fil_prehistory.yaml | 5 ++ ...mmlu_full_fil_professional_accounting.yaml | 5 ++ ...global_mmlu_full_fil_professional_law.yaml | 5 ++ ...l_mmlu_full_fil_professional_medicine.yaml | 5 ++ ...mmlu_full_fil_professional_psychology.yaml | 5 ++ ...global_mmlu_full_fil_public_relations.yaml | 5 ++ ...global_mmlu_full_fil_security_studies.yaml | 5 ++ .../fil/global_mmlu_full_fil_sociology.yaml | 5 ++ ...lobal_mmlu_full_fil_us_foreign_policy.yaml | 5 ++ .../fil/global_mmlu_full_fil_virology.yaml | 5 ++ .../global_mmlu_full_fil_world_religions.yaml | 5 ++ lm_eval/tasks/global_mmlu/full/fil/utils.py | 73 +++++++++++++++++++ .../global_mmlu/full/fr/_fr_template_yaml | 16 ++++ .../full/fr/_global_mmlu_full_fr.yaml | 11 +++ .../fr/_global_mmlu_full_fr_humanities.yaml | 8 ++ .../full/fr/_global_mmlu_full_fr_other.yaml | 8 ++ .../_global_mmlu_full_fr_social_sciences.yaml | 8 ++ .../full/fr/_global_mmlu_full_fr_stem.yaml | 8 ++ .../global_mmlu_full_fr_abstract_algebra.yaml | 5 ++ .../full/fr/global_mmlu_full_fr_anatomy.yaml | 5 ++ .../fr/global_mmlu_full_fr_astronomy.yaml | 5 ++ .../global_mmlu_full_fr_business_ethics.yaml | 5 ++ ...lobal_mmlu_full_fr_clinical_knowledge.yaml | 5 ++ .../global_mmlu_full_fr_college_biology.yaml | 5 ++ ...global_mmlu_full_fr_college_chemistry.yaml | 5 ++ ...mmlu_full_fr_college_computer_science.yaml | 5 ++ ...obal_mmlu_full_fr_college_mathematics.yaml | 5 ++ .../global_mmlu_full_fr_college_medicine.yaml | 5 ++ .../global_mmlu_full_fr_college_physics.yaml | 5 ++ ...global_mmlu_full_fr_computer_security.yaml | 5 ++ ...lobal_mmlu_full_fr_conceptual_physics.yaml | 5 ++ .../fr/global_mmlu_full_fr_econometrics.yaml | 5 ++ ...l_mmlu_full_fr_electrical_engineering.yaml | 5 ++ ...l_mmlu_full_fr_elementary_mathematics.yaml | 5 ++ .../fr/global_mmlu_full_fr_formal_logic.yaml | 5 ++ .../fr/global_mmlu_full_fr_global_facts.yaml | 5 ++ ...obal_mmlu_full_fr_high_school_biology.yaml | 5 ++ ...al_mmlu_full_fr_high_school_chemistry.yaml | 5 ++ ..._full_fr_high_school_computer_science.yaml | 5 ++ ..._full_fr_high_school_european_history.yaml | 5 ++ ...al_mmlu_full_fr_high_school_geography.yaml | 5 ++ ...r_high_school_government_and_politics.yaml | 5 ++ ...lu_full_fr_high_school_macroeconomics.yaml | 5 ++ ..._mmlu_full_fr_high_school_mathematics.yaml | 5 ++ ...lu_full_fr_high_school_microeconomics.yaml | 5 ++ ...obal_mmlu_full_fr_high_school_physics.yaml | 5 ++ ...l_mmlu_full_fr_high_school_psychology.yaml | 5 ++ ...l_mmlu_full_fr_high_school_statistics.yaml | 5 ++ ...l_mmlu_full_fr_high_school_us_history.yaml | 5 ++ ...mlu_full_fr_high_school_world_history.yaml | 5 ++ .../fr/global_mmlu_full_fr_human_aging.yaml | 5 ++ .../global_mmlu_full_fr_human_sexuality.yaml | 5 ++ ...global_mmlu_full_fr_international_law.yaml | 5 ++ .../fr/global_mmlu_full_fr_jurisprudence.yaml | 5 ++ ...global_mmlu_full_fr_logical_fallacies.yaml | 5 ++ .../global_mmlu_full_fr_machine_learning.yaml | 5 ++ .../fr/global_mmlu_full_fr_management.yaml | 5 ++ .../fr/global_mmlu_full_fr_marketing.yaml | 5 ++ .../global_mmlu_full_fr_medical_genetics.yaml | 5 ++ .../fr/global_mmlu_full_fr_miscellaneous.yaml | 5 ++ .../global_mmlu_full_fr_moral_disputes.yaml | 5 ++ .../global_mmlu_full_fr_moral_scenarios.yaml | 5 ++ .../fr/global_mmlu_full_fr_nutrition.yaml | 5 ++ .../fr/global_mmlu_full_fr_philosophy.yaml | 5 ++ .../fr/global_mmlu_full_fr_prehistory.yaml | 5 ++ ..._mmlu_full_fr_professional_accounting.yaml | 5 ++ .../global_mmlu_full_fr_professional_law.yaml | 5 ++ ...al_mmlu_full_fr_professional_medicine.yaml | 5 ++ ..._mmlu_full_fr_professional_psychology.yaml | 5 ++ .../global_mmlu_full_fr_public_relations.yaml | 5 ++ .../global_mmlu_full_fr_security_studies.yaml | 5 ++ .../fr/global_mmlu_full_fr_sociology.yaml | 5 ++ ...global_mmlu_full_fr_us_foreign_policy.yaml | 5 ++ .../full/fr/global_mmlu_full_fr_virology.yaml | 5 ++ .../global_mmlu_full_fr_world_religions.yaml | 5 ++ lm_eval/tasks/global_mmlu/full/fr/utils.py | 73 +++++++++++++++++++ .../full/ha/_global_mmlu_full_ha.yaml | 11 +++ .../ha/_global_mmlu_full_ha_humanities.yaml | 8 ++ .../full/ha/_global_mmlu_full_ha_other.yaml | 8 ++ .../_global_mmlu_full_ha_social_sciences.yaml | 8 ++ .../full/ha/_global_mmlu_full_ha_stem.yaml | 8 ++ .../global_mmlu/full/ha/_ha_template_yaml | 16 ++++ .../global_mmlu_full_ha_abstract_algebra.yaml | 5 ++ .../full/ha/global_mmlu_full_ha_anatomy.yaml | 5 ++ .../ha/global_mmlu_full_ha_astronomy.yaml | 5 ++ .../global_mmlu_full_ha_business_ethics.yaml | 5 ++ ...lobal_mmlu_full_ha_clinical_knowledge.yaml | 5 ++ .../global_mmlu_full_ha_college_biology.yaml | 5 ++ ...global_mmlu_full_ha_college_chemistry.yaml | 5 ++ ...mmlu_full_ha_college_computer_science.yaml | 5 ++ ...obal_mmlu_full_ha_college_mathematics.yaml | 5 ++ .../global_mmlu_full_ha_college_medicine.yaml | 5 ++ .../global_mmlu_full_ha_college_physics.yaml | 5 ++ ...global_mmlu_full_ha_computer_security.yaml | 5 ++ ...lobal_mmlu_full_ha_conceptual_physics.yaml | 5 ++ .../ha/global_mmlu_full_ha_econometrics.yaml | 5 ++ ...l_mmlu_full_ha_electrical_engineering.yaml | 5 ++ ...l_mmlu_full_ha_elementary_mathematics.yaml | 5 ++ .../ha/global_mmlu_full_ha_formal_logic.yaml | 5 ++ .../ha/global_mmlu_full_ha_global_facts.yaml | 5 ++ ...obal_mmlu_full_ha_high_school_biology.yaml | 5 ++ ...al_mmlu_full_ha_high_school_chemistry.yaml | 5 ++ ..._full_ha_high_school_computer_science.yaml | 5 ++ ..._full_ha_high_school_european_history.yaml | 5 ++ ...al_mmlu_full_ha_high_school_geography.yaml | 5 ++ ...a_high_school_government_and_politics.yaml | 5 ++ ...lu_full_ha_high_school_macroeconomics.yaml | 5 ++ ..._mmlu_full_ha_high_school_mathematics.yaml | 5 ++ ...lu_full_ha_high_school_microeconomics.yaml | 5 ++ ...obal_mmlu_full_ha_high_school_physics.yaml | 5 ++ ...l_mmlu_full_ha_high_school_psychology.yaml | 5 ++ ...l_mmlu_full_ha_high_school_statistics.yaml | 5 ++ ...l_mmlu_full_ha_high_school_us_history.yaml | 5 ++ ...mlu_full_ha_high_school_world_history.yaml | 5 ++ .../ha/global_mmlu_full_ha_human_aging.yaml | 5 ++ .../global_mmlu_full_ha_human_sexuality.yaml | 5 ++ ...global_mmlu_full_ha_international_law.yaml | 5 ++ .../ha/global_mmlu_full_ha_jurisprudence.yaml | 5 ++ ...global_mmlu_full_ha_logical_fallacies.yaml | 5 ++ .../global_mmlu_full_ha_machine_learning.yaml | 5 ++ .../ha/global_mmlu_full_ha_management.yaml | 5 ++ .../ha/global_mmlu_full_ha_marketing.yaml | 5 ++ .../global_mmlu_full_ha_medical_genetics.yaml | 5 ++ .../ha/global_mmlu_full_ha_miscellaneous.yaml | 5 ++ .../global_mmlu_full_ha_moral_disputes.yaml | 5 ++ .../global_mmlu_full_ha_moral_scenarios.yaml | 5 ++ .../ha/global_mmlu_full_ha_nutrition.yaml | 5 ++ .../ha/global_mmlu_full_ha_philosophy.yaml | 5 ++ .../ha/global_mmlu_full_ha_prehistory.yaml | 5 ++ ..._mmlu_full_ha_professional_accounting.yaml | 5 ++ .../global_mmlu_full_ha_professional_law.yaml | 5 ++ ...al_mmlu_full_ha_professional_medicine.yaml | 5 ++ ..._mmlu_full_ha_professional_psychology.yaml | 5 ++ .../global_mmlu_full_ha_public_relations.yaml | 5 ++ .../global_mmlu_full_ha_security_studies.yaml | 5 ++ .../ha/global_mmlu_full_ha_sociology.yaml | 5 ++ ...global_mmlu_full_ha_us_foreign_policy.yaml | 5 ++ .../full/ha/global_mmlu_full_ha_virology.yaml | 5 ++ .../global_mmlu_full_ha_world_religions.yaml | 5 ++ lm_eval/tasks/global_mmlu/full/ha/utils.py | 73 +++++++++++++++++++ .../full/he/_global_mmlu_full_he.yaml | 11 +++ .../he/_global_mmlu_full_he_humanities.yaml | 8 ++ .../full/he/_global_mmlu_full_he_other.yaml | 8 ++ .../_global_mmlu_full_he_social_sciences.yaml | 8 ++ .../full/he/_global_mmlu_full_he_stem.yaml | 8 ++ .../global_mmlu/full/he/_he_template_yaml | 16 ++++ .../global_mmlu_full_he_abstract_algebra.yaml | 5 ++ .../full/he/global_mmlu_full_he_anatomy.yaml | 5 ++ .../he/global_mmlu_full_he_astronomy.yaml | 5 ++ .../global_mmlu_full_he_business_ethics.yaml | 5 ++ ...lobal_mmlu_full_he_clinical_knowledge.yaml | 5 ++ .../global_mmlu_full_he_college_biology.yaml | 5 ++ ...global_mmlu_full_he_college_chemistry.yaml | 5 ++ ...mmlu_full_he_college_computer_science.yaml | 5 ++ ...obal_mmlu_full_he_college_mathematics.yaml | 5 ++ .../global_mmlu_full_he_college_medicine.yaml | 5 ++ .../global_mmlu_full_he_college_physics.yaml | 5 ++ ...global_mmlu_full_he_computer_security.yaml | 5 ++ ...lobal_mmlu_full_he_conceptual_physics.yaml | 5 ++ .../he/global_mmlu_full_he_econometrics.yaml | 5 ++ ...l_mmlu_full_he_electrical_engineering.yaml | 5 ++ ...l_mmlu_full_he_elementary_mathematics.yaml | 5 ++ .../he/global_mmlu_full_he_formal_logic.yaml | 5 ++ .../he/global_mmlu_full_he_global_facts.yaml | 5 ++ ...obal_mmlu_full_he_high_school_biology.yaml | 5 ++ ...al_mmlu_full_he_high_school_chemistry.yaml | 5 ++ ..._full_he_high_school_computer_science.yaml | 5 ++ ..._full_he_high_school_european_history.yaml | 5 ++ ...al_mmlu_full_he_high_school_geography.yaml | 5 ++ ...e_high_school_government_and_politics.yaml | 5 ++ ...lu_full_he_high_school_macroeconomics.yaml | 5 ++ ..._mmlu_full_he_high_school_mathematics.yaml | 5 ++ ...lu_full_he_high_school_microeconomics.yaml | 5 ++ ...obal_mmlu_full_he_high_school_physics.yaml | 5 ++ ...l_mmlu_full_he_high_school_psychology.yaml | 5 ++ ...l_mmlu_full_he_high_school_statistics.yaml | 5 ++ ...l_mmlu_full_he_high_school_us_history.yaml | 5 ++ ...mlu_full_he_high_school_world_history.yaml | 5 ++ .../he/global_mmlu_full_he_human_aging.yaml | 5 ++ .../global_mmlu_full_he_human_sexuality.yaml | 5 ++ ...global_mmlu_full_he_international_law.yaml | 5 ++ .../he/global_mmlu_full_he_jurisprudence.yaml | 5 ++ ...global_mmlu_full_he_logical_fallacies.yaml | 5 ++ .../global_mmlu_full_he_machine_learning.yaml | 5 ++ .../he/global_mmlu_full_he_management.yaml | 5 ++ .../he/global_mmlu_full_he_marketing.yaml | 5 ++ .../global_mmlu_full_he_medical_genetics.yaml | 5 ++ .../he/global_mmlu_full_he_miscellaneous.yaml | 5 ++ .../global_mmlu_full_he_moral_disputes.yaml | 5 ++ .../global_mmlu_full_he_moral_scenarios.yaml | 5 ++ .../he/global_mmlu_full_he_nutrition.yaml | 5 ++ .../he/global_mmlu_full_he_philosophy.yaml | 5 ++ .../he/global_mmlu_full_he_prehistory.yaml | 5 ++ ..._mmlu_full_he_professional_accounting.yaml | 5 ++ .../global_mmlu_full_he_professional_law.yaml | 5 ++ ...al_mmlu_full_he_professional_medicine.yaml | 5 ++ ..._mmlu_full_he_professional_psychology.yaml | 5 ++ .../global_mmlu_full_he_public_relations.yaml | 5 ++ .../global_mmlu_full_he_security_studies.yaml | 5 ++ .../he/global_mmlu_full_he_sociology.yaml | 5 ++ ...global_mmlu_full_he_us_foreign_policy.yaml | 5 ++ .../full/he/global_mmlu_full_he_virology.yaml | 5 ++ .../global_mmlu_full_he_world_religions.yaml | 5 ++ lm_eval/tasks/global_mmlu/full/he/utils.py | 73 +++++++++++++++++++ .../full/hi/_global_mmlu_full_hi.yaml | 11 +++ .../hi/_global_mmlu_full_hi_humanities.yaml | 8 ++ .../full/hi/_global_mmlu_full_hi_other.yaml | 8 ++ .../_global_mmlu_full_hi_social_sciences.yaml | 8 ++ .../full/hi/_global_mmlu_full_hi_stem.yaml | 8 ++ .../global_mmlu/full/hi/_hi_template_yaml | 16 ++++ .../global_mmlu_full_hi_abstract_algebra.yaml | 5 ++ .../full/hi/global_mmlu_full_hi_anatomy.yaml | 5 ++ .../hi/global_mmlu_full_hi_astronomy.yaml | 5 ++ .../global_mmlu_full_hi_business_ethics.yaml | 5 ++ ...lobal_mmlu_full_hi_clinical_knowledge.yaml | 5 ++ .../global_mmlu_full_hi_college_biology.yaml | 5 ++ ...global_mmlu_full_hi_college_chemistry.yaml | 5 ++ ...mmlu_full_hi_college_computer_science.yaml | 5 ++ ...obal_mmlu_full_hi_college_mathematics.yaml | 5 ++ .../global_mmlu_full_hi_college_medicine.yaml | 5 ++ .../global_mmlu_full_hi_college_physics.yaml | 5 ++ ...global_mmlu_full_hi_computer_security.yaml | 5 ++ ...lobal_mmlu_full_hi_conceptual_physics.yaml | 5 ++ .../hi/global_mmlu_full_hi_econometrics.yaml | 5 ++ ...l_mmlu_full_hi_electrical_engineering.yaml | 5 ++ ...l_mmlu_full_hi_elementary_mathematics.yaml | 5 ++ .../hi/global_mmlu_full_hi_formal_logic.yaml | 5 ++ .../hi/global_mmlu_full_hi_global_facts.yaml | 5 ++ ...obal_mmlu_full_hi_high_school_biology.yaml | 5 ++ ...al_mmlu_full_hi_high_school_chemistry.yaml | 5 ++ ..._full_hi_high_school_computer_science.yaml | 5 ++ ..._full_hi_high_school_european_history.yaml | 5 ++ ...al_mmlu_full_hi_high_school_geography.yaml | 5 ++ ...i_high_school_government_and_politics.yaml | 5 ++ ...lu_full_hi_high_school_macroeconomics.yaml | 5 ++ ..._mmlu_full_hi_high_school_mathematics.yaml | 5 ++ ...lu_full_hi_high_school_microeconomics.yaml | 5 ++ ...obal_mmlu_full_hi_high_school_physics.yaml | 5 ++ ...l_mmlu_full_hi_high_school_psychology.yaml | 5 ++ ...l_mmlu_full_hi_high_school_statistics.yaml | 5 ++ ...l_mmlu_full_hi_high_school_us_history.yaml | 5 ++ ...mlu_full_hi_high_school_world_history.yaml | 5 ++ .../hi/global_mmlu_full_hi_human_aging.yaml | 5 ++ .../global_mmlu_full_hi_human_sexuality.yaml | 5 ++ ...global_mmlu_full_hi_international_law.yaml | 5 ++ .../hi/global_mmlu_full_hi_jurisprudence.yaml | 5 ++ ...global_mmlu_full_hi_logical_fallacies.yaml | 5 ++ .../global_mmlu_full_hi_machine_learning.yaml | 5 ++ .../hi/global_mmlu_full_hi_management.yaml | 5 ++ .../hi/global_mmlu_full_hi_marketing.yaml | 5 ++ .../global_mmlu_full_hi_medical_genetics.yaml | 5 ++ .../hi/global_mmlu_full_hi_miscellaneous.yaml | 5 ++ .../global_mmlu_full_hi_moral_disputes.yaml | 5 ++ .../global_mmlu_full_hi_moral_scenarios.yaml | 5 ++ .../hi/global_mmlu_full_hi_nutrition.yaml | 5 ++ .../hi/global_mmlu_full_hi_philosophy.yaml | 5 ++ .../hi/global_mmlu_full_hi_prehistory.yaml | 5 ++ ..._mmlu_full_hi_professional_accounting.yaml | 5 ++ .../global_mmlu_full_hi_professional_law.yaml | 5 ++ ...al_mmlu_full_hi_professional_medicine.yaml | 5 ++ ..._mmlu_full_hi_professional_psychology.yaml | 5 ++ .../global_mmlu_full_hi_public_relations.yaml | 5 ++ .../global_mmlu_full_hi_security_studies.yaml | 5 ++ .../hi/global_mmlu_full_hi_sociology.yaml | 5 ++ ...global_mmlu_full_hi_us_foreign_policy.yaml | 5 ++ .../full/hi/global_mmlu_full_hi_virology.yaml | 5 ++ .../global_mmlu_full_hi_world_religions.yaml | 5 ++ lm_eval/tasks/global_mmlu/full/hi/utils.py | 73 +++++++++++++++++++ .../full/id/_global_mmlu_full_id.yaml | 11 +++ .../id/_global_mmlu_full_id_humanities.yaml | 8 ++ .../full/id/_global_mmlu_full_id_other.yaml | 8 ++ .../_global_mmlu_full_id_social_sciences.yaml | 8 ++ .../full/id/_global_mmlu_full_id_stem.yaml | 8 ++ .../global_mmlu/full/id/_id_template_yaml | 16 ++++ .../global_mmlu_full_id_abstract_algebra.yaml | 5 ++ .../full/id/global_mmlu_full_id_anatomy.yaml | 5 ++ .../id/global_mmlu_full_id_astronomy.yaml | 5 ++ .../global_mmlu_full_id_business_ethics.yaml | 5 ++ ...lobal_mmlu_full_id_clinical_knowledge.yaml | 5 ++ .../global_mmlu_full_id_college_biology.yaml | 5 ++ ...global_mmlu_full_id_college_chemistry.yaml | 5 ++ ...mmlu_full_id_college_computer_science.yaml | 5 ++ ...obal_mmlu_full_id_college_mathematics.yaml | 5 ++ .../global_mmlu_full_id_college_medicine.yaml | 5 ++ .../global_mmlu_full_id_college_physics.yaml | 5 ++ ...global_mmlu_full_id_computer_security.yaml | 5 ++ ...lobal_mmlu_full_id_conceptual_physics.yaml | 5 ++ .../id/global_mmlu_full_id_econometrics.yaml | 5 ++ ...l_mmlu_full_id_electrical_engineering.yaml | 5 ++ ...l_mmlu_full_id_elementary_mathematics.yaml | 5 ++ .../id/global_mmlu_full_id_formal_logic.yaml | 5 ++ .../id/global_mmlu_full_id_global_facts.yaml | 5 ++ ...obal_mmlu_full_id_high_school_biology.yaml | 5 ++ ...al_mmlu_full_id_high_school_chemistry.yaml | 5 ++ ..._full_id_high_school_computer_science.yaml | 5 ++ ..._full_id_high_school_european_history.yaml | 5 ++ ...al_mmlu_full_id_high_school_geography.yaml | 5 ++ ...d_high_school_government_and_politics.yaml | 5 ++ ...lu_full_id_high_school_macroeconomics.yaml | 5 ++ ..._mmlu_full_id_high_school_mathematics.yaml | 5 ++ ...lu_full_id_high_school_microeconomics.yaml | 5 ++ ...obal_mmlu_full_id_high_school_physics.yaml | 5 ++ ...l_mmlu_full_id_high_school_psychology.yaml | 5 ++ ...l_mmlu_full_id_high_school_statistics.yaml | 5 ++ ...l_mmlu_full_id_high_school_us_history.yaml | 5 ++ ...mlu_full_id_high_school_world_history.yaml | 5 ++ .../id/global_mmlu_full_id_human_aging.yaml | 5 ++ .../global_mmlu_full_id_human_sexuality.yaml | 5 ++ ...global_mmlu_full_id_international_law.yaml | 5 ++ .../id/global_mmlu_full_id_jurisprudence.yaml | 5 ++ ...global_mmlu_full_id_logical_fallacies.yaml | 5 ++ .../global_mmlu_full_id_machine_learning.yaml | 5 ++ .../id/global_mmlu_full_id_management.yaml | 5 ++ .../id/global_mmlu_full_id_marketing.yaml | 5 ++ .../global_mmlu_full_id_medical_genetics.yaml | 5 ++ .../id/global_mmlu_full_id_miscellaneous.yaml | 5 ++ .../global_mmlu_full_id_moral_disputes.yaml | 5 ++ .../global_mmlu_full_id_moral_scenarios.yaml | 5 ++ .../id/global_mmlu_full_id_nutrition.yaml | 5 ++ .../id/global_mmlu_full_id_philosophy.yaml | 5 ++ .../id/global_mmlu_full_id_prehistory.yaml | 5 ++ ..._mmlu_full_id_professional_accounting.yaml | 5 ++ .../global_mmlu_full_id_professional_law.yaml | 5 ++ ...al_mmlu_full_id_professional_medicine.yaml | 5 ++ ..._mmlu_full_id_professional_psychology.yaml | 5 ++ .../global_mmlu_full_id_public_relations.yaml | 5 ++ .../global_mmlu_full_id_security_studies.yaml | 5 ++ .../id/global_mmlu_full_id_sociology.yaml | 5 ++ ...global_mmlu_full_id_us_foreign_policy.yaml | 5 ++ .../full/id/global_mmlu_full_id_virology.yaml | 5 ++ .../global_mmlu_full_id_world_religions.yaml | 5 ++ lm_eval/tasks/global_mmlu/full/id/utils.py | 73 +++++++++++++++++++ .../full/ig/_global_mmlu_full_ig.yaml | 11 +++ .../ig/_global_mmlu_full_ig_humanities.yaml | 8 ++ .../full/ig/_global_mmlu_full_ig_other.yaml | 8 ++ .../_global_mmlu_full_ig_social_sciences.yaml | 8 ++ .../full/ig/_global_mmlu_full_ig_stem.yaml | 8 ++ .../global_mmlu/full/ig/_ig_template_yaml | 16 ++++ .../global_mmlu_full_ig_abstract_algebra.yaml | 5 ++ .../full/ig/global_mmlu_full_ig_anatomy.yaml | 5 ++ .../ig/global_mmlu_full_ig_astronomy.yaml | 5 ++ .../global_mmlu_full_ig_business_ethics.yaml | 5 ++ ...lobal_mmlu_full_ig_clinical_knowledge.yaml | 5 ++ .../global_mmlu_full_ig_college_biology.yaml | 5 ++ ...global_mmlu_full_ig_college_chemistry.yaml | 5 ++ ...mmlu_full_ig_college_computer_science.yaml | 5 ++ ...obal_mmlu_full_ig_college_mathematics.yaml | 5 ++ .../global_mmlu_full_ig_college_medicine.yaml | 5 ++ .../global_mmlu_full_ig_college_physics.yaml | 5 ++ ...global_mmlu_full_ig_computer_security.yaml | 5 ++ ...lobal_mmlu_full_ig_conceptual_physics.yaml | 5 ++ .../ig/global_mmlu_full_ig_econometrics.yaml | 5 ++ ...l_mmlu_full_ig_electrical_engineering.yaml | 5 ++ ...l_mmlu_full_ig_elementary_mathematics.yaml | 5 ++ .../ig/global_mmlu_full_ig_formal_logic.yaml | 5 ++ .../ig/global_mmlu_full_ig_global_facts.yaml | 5 ++ ...obal_mmlu_full_ig_high_school_biology.yaml | 5 ++ ...al_mmlu_full_ig_high_school_chemistry.yaml | 5 ++ ..._full_ig_high_school_computer_science.yaml | 5 ++ ..._full_ig_high_school_european_history.yaml | 5 ++ ...al_mmlu_full_ig_high_school_geography.yaml | 5 ++ ...g_high_school_government_and_politics.yaml | 5 ++ ...lu_full_ig_high_school_macroeconomics.yaml | 5 ++ ..._mmlu_full_ig_high_school_mathematics.yaml | 5 ++ ...lu_full_ig_high_school_microeconomics.yaml | 5 ++ ...obal_mmlu_full_ig_high_school_physics.yaml | 5 ++ ...l_mmlu_full_ig_high_school_psychology.yaml | 5 ++ ...l_mmlu_full_ig_high_school_statistics.yaml | 5 ++ ...l_mmlu_full_ig_high_school_us_history.yaml | 5 ++ ...mlu_full_ig_high_school_world_history.yaml | 5 ++ .../ig/global_mmlu_full_ig_human_aging.yaml | 5 ++ .../global_mmlu_full_ig_human_sexuality.yaml | 5 ++ ...global_mmlu_full_ig_international_law.yaml | 5 ++ .../ig/global_mmlu_full_ig_jurisprudence.yaml | 5 ++ ...global_mmlu_full_ig_logical_fallacies.yaml | 5 ++ .../global_mmlu_full_ig_machine_learning.yaml | 5 ++ .../ig/global_mmlu_full_ig_management.yaml | 5 ++ .../ig/global_mmlu_full_ig_marketing.yaml | 5 ++ .../global_mmlu_full_ig_medical_genetics.yaml | 5 ++ .../ig/global_mmlu_full_ig_miscellaneous.yaml | 5 ++ .../global_mmlu_full_ig_moral_disputes.yaml | 5 ++ .../global_mmlu_full_ig_moral_scenarios.yaml | 5 ++ .../ig/global_mmlu_full_ig_nutrition.yaml | 5 ++ .../ig/global_mmlu_full_ig_philosophy.yaml | 5 ++ .../ig/global_mmlu_full_ig_prehistory.yaml | 5 ++ ..._mmlu_full_ig_professional_accounting.yaml | 5 ++ .../global_mmlu_full_ig_professional_law.yaml | 5 ++ ...al_mmlu_full_ig_professional_medicine.yaml | 5 ++ ..._mmlu_full_ig_professional_psychology.yaml | 5 ++ .../global_mmlu_full_ig_public_relations.yaml | 5 ++ .../global_mmlu_full_ig_security_studies.yaml | 5 ++ .../ig/global_mmlu_full_ig_sociology.yaml | 5 ++ ...global_mmlu_full_ig_us_foreign_policy.yaml | 5 ++ .../full/ig/global_mmlu_full_ig_virology.yaml | 5 ++ .../global_mmlu_full_ig_world_religions.yaml | 5 ++ lm_eval/tasks/global_mmlu/full/ig/utils.py | 73 +++++++++++++++++++ .../full/it/_global_mmlu_full_it.yaml | 11 +++ .../it/_global_mmlu_full_it_humanities.yaml | 8 ++ .../full/it/_global_mmlu_full_it_other.yaml | 8 ++ .../_global_mmlu_full_it_social_sciences.yaml | 8 ++ .../full/it/_global_mmlu_full_it_stem.yaml | 8 ++ .../global_mmlu/full/it/_it_template_yaml | 16 ++++ .../global_mmlu_full_it_abstract_algebra.yaml | 5 ++ .../full/it/global_mmlu_full_it_anatomy.yaml | 5 ++ .../it/global_mmlu_full_it_astronomy.yaml | 5 ++ .../global_mmlu_full_it_business_ethics.yaml | 5 ++ ...lobal_mmlu_full_it_clinical_knowledge.yaml | 5 ++ .../global_mmlu_full_it_college_biology.yaml | 5 ++ ...global_mmlu_full_it_college_chemistry.yaml | 5 ++ ...mmlu_full_it_college_computer_science.yaml | 5 ++ ...obal_mmlu_full_it_college_mathematics.yaml | 5 ++ .../global_mmlu_full_it_college_medicine.yaml | 5 ++ .../global_mmlu_full_it_college_physics.yaml | 5 ++ ...global_mmlu_full_it_computer_security.yaml | 5 ++ ...lobal_mmlu_full_it_conceptual_physics.yaml | 5 ++ .../it/global_mmlu_full_it_econometrics.yaml | 5 ++ ...l_mmlu_full_it_electrical_engineering.yaml | 5 ++ ...l_mmlu_full_it_elementary_mathematics.yaml | 5 ++ .../it/global_mmlu_full_it_formal_logic.yaml | 5 ++ .../it/global_mmlu_full_it_global_facts.yaml | 5 ++ ...obal_mmlu_full_it_high_school_biology.yaml | 5 ++ ...al_mmlu_full_it_high_school_chemistry.yaml | 5 ++ ..._full_it_high_school_computer_science.yaml | 5 ++ ..._full_it_high_school_european_history.yaml | 5 ++ ...al_mmlu_full_it_high_school_geography.yaml | 5 ++ ...t_high_school_government_and_politics.yaml | 5 ++ ...lu_full_it_high_school_macroeconomics.yaml | 5 ++ ..._mmlu_full_it_high_school_mathematics.yaml | 5 ++ ...lu_full_it_high_school_microeconomics.yaml | 5 ++ ...obal_mmlu_full_it_high_school_physics.yaml | 5 ++ ...l_mmlu_full_it_high_school_psychology.yaml | 5 ++ ...l_mmlu_full_it_high_school_statistics.yaml | 5 ++ ...l_mmlu_full_it_high_school_us_history.yaml | 5 ++ ...mlu_full_it_high_school_world_history.yaml | 5 ++ .../it/global_mmlu_full_it_human_aging.yaml | 5 ++ .../global_mmlu_full_it_human_sexuality.yaml | 5 ++ ...global_mmlu_full_it_international_law.yaml | 5 ++ .../it/global_mmlu_full_it_jurisprudence.yaml | 5 ++ ...global_mmlu_full_it_logical_fallacies.yaml | 5 ++ .../global_mmlu_full_it_machine_learning.yaml | 5 ++ .../it/global_mmlu_full_it_management.yaml | 5 ++ .../it/global_mmlu_full_it_marketing.yaml | 5 ++ .../global_mmlu_full_it_medical_genetics.yaml | 5 ++ .../it/global_mmlu_full_it_miscellaneous.yaml | 5 ++ .../global_mmlu_full_it_moral_disputes.yaml | 5 ++ .../global_mmlu_full_it_moral_scenarios.yaml | 5 ++ .../it/global_mmlu_full_it_nutrition.yaml | 5 ++ .../it/global_mmlu_full_it_philosophy.yaml | 5 ++ .../it/global_mmlu_full_it_prehistory.yaml | 5 ++ ..._mmlu_full_it_professional_accounting.yaml | 5 ++ .../global_mmlu_full_it_professional_law.yaml | 5 ++ ...al_mmlu_full_it_professional_medicine.yaml | 5 ++ ..._mmlu_full_it_professional_psychology.yaml | 5 ++ .../global_mmlu_full_it_public_relations.yaml | 5 ++ .../global_mmlu_full_it_security_studies.yaml | 5 ++ .../it/global_mmlu_full_it_sociology.yaml | 5 ++ ...global_mmlu_full_it_us_foreign_policy.yaml | 5 ++ .../full/it/global_mmlu_full_it_virology.yaml | 5 ++ .../global_mmlu_full_it_world_religions.yaml | 5 ++ lm_eval/tasks/global_mmlu/full/it/utils.py | 73 +++++++++++++++++++ .../full/ja/_global_mmlu_full_ja.yaml | 11 +++ .../ja/_global_mmlu_full_ja_humanities.yaml | 8 ++ .../full/ja/_global_mmlu_full_ja_other.yaml | 8 ++ .../_global_mmlu_full_ja_social_sciences.yaml | 8 ++ .../full/ja/_global_mmlu_full_ja_stem.yaml | 8 ++ .../global_mmlu/full/ja/_ja_template_yaml | 16 ++++ .../global_mmlu_full_ja_abstract_algebra.yaml | 5 ++ .../full/ja/global_mmlu_full_ja_anatomy.yaml | 5 ++ .../ja/global_mmlu_full_ja_astronomy.yaml | 5 ++ .../global_mmlu_full_ja_business_ethics.yaml | 5 ++ ...lobal_mmlu_full_ja_clinical_knowledge.yaml | 5 ++ .../global_mmlu_full_ja_college_biology.yaml | 5 ++ ...global_mmlu_full_ja_college_chemistry.yaml | 5 ++ ...mmlu_full_ja_college_computer_science.yaml | 5 ++ ...obal_mmlu_full_ja_college_mathematics.yaml | 5 ++ .../global_mmlu_full_ja_college_medicine.yaml | 5 ++ .../global_mmlu_full_ja_college_physics.yaml | 5 ++ ...global_mmlu_full_ja_computer_security.yaml | 5 ++ ...lobal_mmlu_full_ja_conceptual_physics.yaml | 5 ++ .../ja/global_mmlu_full_ja_econometrics.yaml | 5 ++ ...l_mmlu_full_ja_electrical_engineering.yaml | 5 ++ ...l_mmlu_full_ja_elementary_mathematics.yaml | 5 ++ .../ja/global_mmlu_full_ja_formal_logic.yaml | 5 ++ .../ja/global_mmlu_full_ja_global_facts.yaml | 5 ++ ...obal_mmlu_full_ja_high_school_biology.yaml | 5 ++ ...al_mmlu_full_ja_high_school_chemistry.yaml | 5 ++ ..._full_ja_high_school_computer_science.yaml | 5 ++ ..._full_ja_high_school_european_history.yaml | 5 ++ ...al_mmlu_full_ja_high_school_geography.yaml | 5 ++ ...a_high_school_government_and_politics.yaml | 5 ++ ...lu_full_ja_high_school_macroeconomics.yaml | 5 ++ ..._mmlu_full_ja_high_school_mathematics.yaml | 5 ++ ...lu_full_ja_high_school_microeconomics.yaml | 5 ++ ...obal_mmlu_full_ja_high_school_physics.yaml | 5 ++ ...l_mmlu_full_ja_high_school_psychology.yaml | 5 ++ ...l_mmlu_full_ja_high_school_statistics.yaml | 5 ++ ...l_mmlu_full_ja_high_school_us_history.yaml | 5 ++ ...mlu_full_ja_high_school_world_history.yaml | 5 ++ .../ja/global_mmlu_full_ja_human_aging.yaml | 5 ++ .../global_mmlu_full_ja_human_sexuality.yaml | 5 ++ ...global_mmlu_full_ja_international_law.yaml | 5 ++ .../ja/global_mmlu_full_ja_jurisprudence.yaml | 5 ++ ...global_mmlu_full_ja_logical_fallacies.yaml | 5 ++ .../global_mmlu_full_ja_machine_learning.yaml | 5 ++ .../ja/global_mmlu_full_ja_management.yaml | 5 ++ .../ja/global_mmlu_full_ja_marketing.yaml | 5 ++ .../global_mmlu_full_ja_medical_genetics.yaml | 5 ++ .../ja/global_mmlu_full_ja_miscellaneous.yaml | 5 ++ .../global_mmlu_full_ja_moral_disputes.yaml | 5 ++ .../global_mmlu_full_ja_moral_scenarios.yaml | 5 ++ .../ja/global_mmlu_full_ja_nutrition.yaml | 5 ++ .../ja/global_mmlu_full_ja_philosophy.yaml | 5 ++ .../ja/global_mmlu_full_ja_prehistory.yaml | 5 ++ ..._mmlu_full_ja_professional_accounting.yaml | 5 ++ .../global_mmlu_full_ja_professional_law.yaml | 5 ++ ...al_mmlu_full_ja_professional_medicine.yaml | 5 ++ ..._mmlu_full_ja_professional_psychology.yaml | 5 ++ .../global_mmlu_full_ja_public_relations.yaml | 5 ++ .../global_mmlu_full_ja_security_studies.yaml | 5 ++ .../ja/global_mmlu_full_ja_sociology.yaml | 5 ++ ...global_mmlu_full_ja_us_foreign_policy.yaml | 5 ++ .../full/ja/global_mmlu_full_ja_virology.yaml | 5 ++ .../global_mmlu_full_ja_world_religions.yaml | 5 ++ lm_eval/tasks/global_mmlu/full/ja/utils.py | 73 +++++++++++++++++++ .../full/ko/_global_mmlu_full_ko.yaml | 11 +++ .../ko/_global_mmlu_full_ko_humanities.yaml | 8 ++ .../full/ko/_global_mmlu_full_ko_other.yaml | 8 ++ .../_global_mmlu_full_ko_social_sciences.yaml | 8 ++ .../full/ko/_global_mmlu_full_ko_stem.yaml | 8 ++ .../global_mmlu/full/ko/_ko_template_yaml | 16 ++++ .../global_mmlu_full_ko_abstract_algebra.yaml | 5 ++ .../full/ko/global_mmlu_full_ko_anatomy.yaml | 5 ++ .../ko/global_mmlu_full_ko_astronomy.yaml | 5 ++ .../global_mmlu_full_ko_business_ethics.yaml | 5 ++ ...lobal_mmlu_full_ko_clinical_knowledge.yaml | 5 ++ .../global_mmlu_full_ko_college_biology.yaml | 5 ++ ...global_mmlu_full_ko_college_chemistry.yaml | 5 ++ ...mmlu_full_ko_college_computer_science.yaml | 5 ++ ...obal_mmlu_full_ko_college_mathematics.yaml | 5 ++ .../global_mmlu_full_ko_college_medicine.yaml | 5 ++ .../global_mmlu_full_ko_college_physics.yaml | 5 ++ ...global_mmlu_full_ko_computer_security.yaml | 5 ++ ...lobal_mmlu_full_ko_conceptual_physics.yaml | 5 ++ .../ko/global_mmlu_full_ko_econometrics.yaml | 5 ++ ...l_mmlu_full_ko_electrical_engineering.yaml | 5 ++ ...l_mmlu_full_ko_elementary_mathematics.yaml | 5 ++ .../ko/global_mmlu_full_ko_formal_logic.yaml | 5 ++ .../ko/global_mmlu_full_ko_global_facts.yaml | 5 ++ ...obal_mmlu_full_ko_high_school_biology.yaml | 5 ++ ...al_mmlu_full_ko_high_school_chemistry.yaml | 5 ++ ..._full_ko_high_school_computer_science.yaml | 5 ++ ..._full_ko_high_school_european_history.yaml | 5 ++ ...al_mmlu_full_ko_high_school_geography.yaml | 5 ++ ...o_high_school_government_and_politics.yaml | 5 ++ ...lu_full_ko_high_school_macroeconomics.yaml | 5 ++ ..._mmlu_full_ko_high_school_mathematics.yaml | 5 ++ ...lu_full_ko_high_school_microeconomics.yaml | 5 ++ ...obal_mmlu_full_ko_high_school_physics.yaml | 5 ++ ...l_mmlu_full_ko_high_school_psychology.yaml | 5 ++ ...l_mmlu_full_ko_high_school_statistics.yaml | 5 ++ ...l_mmlu_full_ko_high_school_us_history.yaml | 5 ++ ...mlu_full_ko_high_school_world_history.yaml | 5 ++ .../ko/global_mmlu_full_ko_human_aging.yaml | 5 ++ .../global_mmlu_full_ko_human_sexuality.yaml | 5 ++ ...global_mmlu_full_ko_international_law.yaml | 5 ++ .../ko/global_mmlu_full_ko_jurisprudence.yaml | 5 ++ ...global_mmlu_full_ko_logical_fallacies.yaml | 5 ++ .../global_mmlu_full_ko_machine_learning.yaml | 5 ++ .../ko/global_mmlu_full_ko_management.yaml | 5 ++ .../ko/global_mmlu_full_ko_marketing.yaml | 5 ++ .../global_mmlu_full_ko_medical_genetics.yaml | 5 ++ .../ko/global_mmlu_full_ko_miscellaneous.yaml | 5 ++ .../global_mmlu_full_ko_moral_disputes.yaml | 5 ++ .../global_mmlu_full_ko_moral_scenarios.yaml | 5 ++ .../ko/global_mmlu_full_ko_nutrition.yaml | 5 ++ .../ko/global_mmlu_full_ko_philosophy.yaml | 5 ++ .../ko/global_mmlu_full_ko_prehistory.yaml | 5 ++ ..._mmlu_full_ko_professional_accounting.yaml | 5 ++ .../global_mmlu_full_ko_professional_law.yaml | 5 ++ ...al_mmlu_full_ko_professional_medicine.yaml | 5 ++ ..._mmlu_full_ko_professional_psychology.yaml | 5 ++ .../global_mmlu_full_ko_public_relations.yaml | 5 ++ .../global_mmlu_full_ko_security_studies.yaml | 5 ++ .../ko/global_mmlu_full_ko_sociology.yaml | 5 ++ ...global_mmlu_full_ko_us_foreign_policy.yaml | 5 ++ .../full/ko/global_mmlu_full_ko_virology.yaml | 5 ++ .../global_mmlu_full_ko_world_religions.yaml | 5 ++ lm_eval/tasks/global_mmlu/full/ko/utils.py | 73 +++++++++++++++++++ .../full/ky/_global_mmlu_full_ky.yaml | 11 +++ .../ky/_global_mmlu_full_ky_humanities.yaml | 8 ++ .../full/ky/_global_mmlu_full_ky_other.yaml | 8 ++ .../_global_mmlu_full_ky_social_sciences.yaml | 8 ++ .../full/ky/_global_mmlu_full_ky_stem.yaml | 8 ++ .../global_mmlu/full/ky/_ky_template_yaml | 16 ++++ .../global_mmlu_full_ky_abstract_algebra.yaml | 5 ++ .../full/ky/global_mmlu_full_ky_anatomy.yaml | 5 ++ .../ky/global_mmlu_full_ky_astronomy.yaml | 5 ++ .../global_mmlu_full_ky_business_ethics.yaml | 5 ++ ...lobal_mmlu_full_ky_clinical_knowledge.yaml | 5 ++ .../global_mmlu_full_ky_college_biology.yaml | 5 ++ ...global_mmlu_full_ky_college_chemistry.yaml | 5 ++ ...mmlu_full_ky_college_computer_science.yaml | 5 ++ ...obal_mmlu_full_ky_college_mathematics.yaml | 5 ++ .../global_mmlu_full_ky_college_medicine.yaml | 5 ++ .../global_mmlu_full_ky_college_physics.yaml | 5 ++ ...global_mmlu_full_ky_computer_security.yaml | 5 ++ ...lobal_mmlu_full_ky_conceptual_physics.yaml | 5 ++ .../ky/global_mmlu_full_ky_econometrics.yaml | 5 ++ ...l_mmlu_full_ky_electrical_engineering.yaml | 5 ++ ...l_mmlu_full_ky_elementary_mathematics.yaml | 5 ++ .../ky/global_mmlu_full_ky_formal_logic.yaml | 5 ++ .../ky/global_mmlu_full_ky_global_facts.yaml | 5 ++ ...obal_mmlu_full_ky_high_school_biology.yaml | 5 ++ ...al_mmlu_full_ky_high_school_chemistry.yaml | 5 ++ ..._full_ky_high_school_computer_science.yaml | 5 ++ ..._full_ky_high_school_european_history.yaml | 5 ++ ...al_mmlu_full_ky_high_school_geography.yaml | 5 ++ ...y_high_school_government_and_politics.yaml | 5 ++ ...lu_full_ky_high_school_macroeconomics.yaml | 5 ++ ..._mmlu_full_ky_high_school_mathematics.yaml | 5 ++ ...lu_full_ky_high_school_microeconomics.yaml | 5 ++ ...obal_mmlu_full_ky_high_school_physics.yaml | 5 ++ ...l_mmlu_full_ky_high_school_psychology.yaml | 5 ++ ...l_mmlu_full_ky_high_school_statistics.yaml | 5 ++ ...l_mmlu_full_ky_high_school_us_history.yaml | 5 ++ ...mlu_full_ky_high_school_world_history.yaml | 5 ++ .../ky/global_mmlu_full_ky_human_aging.yaml | 5 ++ .../global_mmlu_full_ky_human_sexuality.yaml | 5 ++ ...global_mmlu_full_ky_international_law.yaml | 5 ++ .../ky/global_mmlu_full_ky_jurisprudence.yaml | 5 ++ ...global_mmlu_full_ky_logical_fallacies.yaml | 5 ++ .../global_mmlu_full_ky_machine_learning.yaml | 5 ++ .../ky/global_mmlu_full_ky_management.yaml | 5 ++ .../ky/global_mmlu_full_ky_marketing.yaml | 5 ++ .../global_mmlu_full_ky_medical_genetics.yaml | 5 ++ .../ky/global_mmlu_full_ky_miscellaneous.yaml | 5 ++ .../global_mmlu_full_ky_moral_disputes.yaml | 5 ++ .../global_mmlu_full_ky_moral_scenarios.yaml | 5 ++ .../ky/global_mmlu_full_ky_nutrition.yaml | 5 ++ .../ky/global_mmlu_full_ky_philosophy.yaml | 5 ++ .../ky/global_mmlu_full_ky_prehistory.yaml | 5 ++ ..._mmlu_full_ky_professional_accounting.yaml | 5 ++ .../global_mmlu_full_ky_professional_law.yaml | 5 ++ ...al_mmlu_full_ky_professional_medicine.yaml | 5 ++ ..._mmlu_full_ky_professional_psychology.yaml | 5 ++ .../global_mmlu_full_ky_public_relations.yaml | 5 ++ .../global_mmlu_full_ky_security_studies.yaml | 5 ++ .../ky/global_mmlu_full_ky_sociology.yaml | 5 ++ ...global_mmlu_full_ky_us_foreign_policy.yaml | 5 ++ .../full/ky/global_mmlu_full_ky_virology.yaml | 5 ++ .../global_mmlu_full_ky_world_religions.yaml | 5 ++ lm_eval/tasks/global_mmlu/full/ky/utils.py | 73 +++++++++++++++++++ .../full/lt/_global_mmlu_full_lt.yaml | 11 +++ .../lt/_global_mmlu_full_lt_humanities.yaml | 8 ++ .../full/lt/_global_mmlu_full_lt_other.yaml | 8 ++ .../_global_mmlu_full_lt_social_sciences.yaml | 8 ++ .../full/lt/_global_mmlu_full_lt_stem.yaml | 8 ++ .../global_mmlu/full/lt/_lt_template_yaml | 16 ++++ .../global_mmlu_full_lt_abstract_algebra.yaml | 5 ++ .../full/lt/global_mmlu_full_lt_anatomy.yaml | 5 ++ .../lt/global_mmlu_full_lt_astronomy.yaml | 5 ++ .../global_mmlu_full_lt_business_ethics.yaml | 5 ++ ...lobal_mmlu_full_lt_clinical_knowledge.yaml | 5 ++ .../global_mmlu_full_lt_college_biology.yaml | 5 ++ ...global_mmlu_full_lt_college_chemistry.yaml | 5 ++ ...mmlu_full_lt_college_computer_science.yaml | 5 ++ ...obal_mmlu_full_lt_college_mathematics.yaml | 5 ++ .../global_mmlu_full_lt_college_medicine.yaml | 5 ++ .../global_mmlu_full_lt_college_physics.yaml | 5 ++ ...global_mmlu_full_lt_computer_security.yaml | 5 ++ ...lobal_mmlu_full_lt_conceptual_physics.yaml | 5 ++ .../lt/global_mmlu_full_lt_econometrics.yaml | 5 ++ ...l_mmlu_full_lt_electrical_engineering.yaml | 5 ++ ...l_mmlu_full_lt_elementary_mathematics.yaml | 5 ++ .../lt/global_mmlu_full_lt_formal_logic.yaml | 5 ++ .../lt/global_mmlu_full_lt_global_facts.yaml | 5 ++ ...obal_mmlu_full_lt_high_school_biology.yaml | 5 ++ ...al_mmlu_full_lt_high_school_chemistry.yaml | 5 ++ ..._full_lt_high_school_computer_science.yaml | 5 ++ ..._full_lt_high_school_european_history.yaml | 5 ++ ...al_mmlu_full_lt_high_school_geography.yaml | 5 ++ ...t_high_school_government_and_politics.yaml | 5 ++ ...lu_full_lt_high_school_macroeconomics.yaml | 5 ++ ..._mmlu_full_lt_high_school_mathematics.yaml | 5 ++ ...lu_full_lt_high_school_microeconomics.yaml | 5 ++ ...obal_mmlu_full_lt_high_school_physics.yaml | 5 ++ ...l_mmlu_full_lt_high_school_psychology.yaml | 5 ++ ...l_mmlu_full_lt_high_school_statistics.yaml | 5 ++ ...l_mmlu_full_lt_high_school_us_history.yaml | 5 ++ ...mlu_full_lt_high_school_world_history.yaml | 5 ++ .../lt/global_mmlu_full_lt_human_aging.yaml | 5 ++ .../global_mmlu_full_lt_human_sexuality.yaml | 5 ++ ...global_mmlu_full_lt_international_law.yaml | 5 ++ .../lt/global_mmlu_full_lt_jurisprudence.yaml | 5 ++ ...global_mmlu_full_lt_logical_fallacies.yaml | 5 ++ .../global_mmlu_full_lt_machine_learning.yaml | 5 ++ .../lt/global_mmlu_full_lt_management.yaml | 5 ++ .../lt/global_mmlu_full_lt_marketing.yaml | 5 ++ .../global_mmlu_full_lt_medical_genetics.yaml | 5 ++ .../lt/global_mmlu_full_lt_miscellaneous.yaml | 5 ++ .../global_mmlu_full_lt_moral_disputes.yaml | 5 ++ .../global_mmlu_full_lt_moral_scenarios.yaml | 5 ++ .../lt/global_mmlu_full_lt_nutrition.yaml | 5 ++ .../lt/global_mmlu_full_lt_philosophy.yaml | 5 ++ .../lt/global_mmlu_full_lt_prehistory.yaml | 5 ++ ..._mmlu_full_lt_professional_accounting.yaml | 5 ++ .../global_mmlu_full_lt_professional_law.yaml | 5 ++ ...al_mmlu_full_lt_professional_medicine.yaml | 5 ++ ..._mmlu_full_lt_professional_psychology.yaml | 5 ++ .../global_mmlu_full_lt_public_relations.yaml | 5 ++ .../global_mmlu_full_lt_security_studies.yaml | 5 ++ .../lt/global_mmlu_full_lt_sociology.yaml | 5 ++ ...global_mmlu_full_lt_us_foreign_policy.yaml | 5 ++ .../full/lt/global_mmlu_full_lt_virology.yaml | 5 ++ .../global_mmlu_full_lt_world_religions.yaml | 5 ++ lm_eval/tasks/global_mmlu/full/lt/utils.py | 73 +++++++++++++++++++ .../full/mg/_global_mmlu_full_mg.yaml | 11 +++ .../mg/_global_mmlu_full_mg_humanities.yaml | 8 ++ .../full/mg/_global_mmlu_full_mg_other.yaml | 8 ++ .../_global_mmlu_full_mg_social_sciences.yaml | 8 ++ .../full/mg/_global_mmlu_full_mg_stem.yaml | 8 ++ .../global_mmlu/full/mg/_mg_template_yaml | 16 ++++ .../global_mmlu_full_mg_abstract_algebra.yaml | 5 ++ .../full/mg/global_mmlu_full_mg_anatomy.yaml | 5 ++ .../mg/global_mmlu_full_mg_astronomy.yaml | 5 ++ .../global_mmlu_full_mg_business_ethics.yaml | 5 ++ ...lobal_mmlu_full_mg_clinical_knowledge.yaml | 5 ++ .../global_mmlu_full_mg_college_biology.yaml | 5 ++ ...global_mmlu_full_mg_college_chemistry.yaml | 5 ++ ...mmlu_full_mg_college_computer_science.yaml | 5 ++ ...obal_mmlu_full_mg_college_mathematics.yaml | 5 ++ .../global_mmlu_full_mg_college_medicine.yaml | 5 ++ .../global_mmlu_full_mg_college_physics.yaml | 5 ++ ...global_mmlu_full_mg_computer_security.yaml | 5 ++ ...lobal_mmlu_full_mg_conceptual_physics.yaml | 5 ++ .../mg/global_mmlu_full_mg_econometrics.yaml | 5 ++ ...l_mmlu_full_mg_electrical_engineering.yaml | 5 ++ ...l_mmlu_full_mg_elementary_mathematics.yaml | 5 ++ .../mg/global_mmlu_full_mg_formal_logic.yaml | 5 ++ .../mg/global_mmlu_full_mg_global_facts.yaml | 5 ++ ...obal_mmlu_full_mg_high_school_biology.yaml | 5 ++ ...al_mmlu_full_mg_high_school_chemistry.yaml | 5 ++ ..._full_mg_high_school_computer_science.yaml | 5 ++ ..._full_mg_high_school_european_history.yaml | 5 ++ ...al_mmlu_full_mg_high_school_geography.yaml | 5 ++ ...g_high_school_government_and_politics.yaml | 5 ++ ...lu_full_mg_high_school_macroeconomics.yaml | 5 ++ ..._mmlu_full_mg_high_school_mathematics.yaml | 5 ++ ...lu_full_mg_high_school_microeconomics.yaml | 5 ++ ...obal_mmlu_full_mg_high_school_physics.yaml | 5 ++ ...l_mmlu_full_mg_high_school_psychology.yaml | 5 ++ ...l_mmlu_full_mg_high_school_statistics.yaml | 5 ++ ...l_mmlu_full_mg_high_school_us_history.yaml | 5 ++ ...mlu_full_mg_high_school_world_history.yaml | 5 ++ .../mg/global_mmlu_full_mg_human_aging.yaml | 5 ++ .../global_mmlu_full_mg_human_sexuality.yaml | 5 ++ ...global_mmlu_full_mg_international_law.yaml | 5 ++ .../mg/global_mmlu_full_mg_jurisprudence.yaml | 5 ++ ...global_mmlu_full_mg_logical_fallacies.yaml | 5 ++ .../global_mmlu_full_mg_machine_learning.yaml | 5 ++ .../mg/global_mmlu_full_mg_management.yaml | 5 ++ .../mg/global_mmlu_full_mg_marketing.yaml | 5 ++ .../global_mmlu_full_mg_medical_genetics.yaml | 5 ++ .../mg/global_mmlu_full_mg_miscellaneous.yaml | 5 ++ .../global_mmlu_full_mg_moral_disputes.yaml | 5 ++ .../global_mmlu_full_mg_moral_scenarios.yaml | 5 ++ .../mg/global_mmlu_full_mg_nutrition.yaml | 5 ++ .../mg/global_mmlu_full_mg_philosophy.yaml | 5 ++ .../mg/global_mmlu_full_mg_prehistory.yaml | 5 ++ ..._mmlu_full_mg_professional_accounting.yaml | 5 ++ .../global_mmlu_full_mg_professional_law.yaml | 5 ++ ...al_mmlu_full_mg_professional_medicine.yaml | 5 ++ ..._mmlu_full_mg_professional_psychology.yaml | 5 ++ .../global_mmlu_full_mg_public_relations.yaml | 5 ++ .../global_mmlu_full_mg_security_studies.yaml | 5 ++ .../mg/global_mmlu_full_mg_sociology.yaml | 5 ++ ...global_mmlu_full_mg_us_foreign_policy.yaml | 5 ++ .../full/mg/global_mmlu_full_mg_virology.yaml | 5 ++ .../global_mmlu_full_mg_world_religions.yaml | 5 ++ lm_eval/tasks/global_mmlu/full/mg/utils.py | 73 +++++++++++++++++++ .../full/ms/_global_mmlu_full_ms.yaml | 11 +++ .../ms/_global_mmlu_full_ms_humanities.yaml | 8 ++ .../full/ms/_global_mmlu_full_ms_other.yaml | 8 ++ .../_global_mmlu_full_ms_social_sciences.yaml | 8 ++ .../full/ms/_global_mmlu_full_ms_stem.yaml | 8 ++ .../global_mmlu/full/ms/_ms_template_yaml | 16 ++++ .../global_mmlu_full_ms_abstract_algebra.yaml | 5 ++ .../full/ms/global_mmlu_full_ms_anatomy.yaml | 5 ++ .../ms/global_mmlu_full_ms_astronomy.yaml | 5 ++ .../global_mmlu_full_ms_business_ethics.yaml | 5 ++ ...lobal_mmlu_full_ms_clinical_knowledge.yaml | 5 ++ .../global_mmlu_full_ms_college_biology.yaml | 5 ++ ...global_mmlu_full_ms_college_chemistry.yaml | 5 ++ ...mmlu_full_ms_college_computer_science.yaml | 5 ++ ...obal_mmlu_full_ms_college_mathematics.yaml | 5 ++ .../global_mmlu_full_ms_college_medicine.yaml | 5 ++ .../global_mmlu_full_ms_college_physics.yaml | 5 ++ ...global_mmlu_full_ms_computer_security.yaml | 5 ++ ...lobal_mmlu_full_ms_conceptual_physics.yaml | 5 ++ .../ms/global_mmlu_full_ms_econometrics.yaml | 5 ++ ...l_mmlu_full_ms_electrical_engineering.yaml | 5 ++ ...l_mmlu_full_ms_elementary_mathematics.yaml | 5 ++ .../ms/global_mmlu_full_ms_formal_logic.yaml | 5 ++ .../ms/global_mmlu_full_ms_global_facts.yaml | 5 ++ ...obal_mmlu_full_ms_high_school_biology.yaml | 5 ++ ...al_mmlu_full_ms_high_school_chemistry.yaml | 5 ++ ..._full_ms_high_school_computer_science.yaml | 5 ++ ..._full_ms_high_school_european_history.yaml | 5 ++ ...al_mmlu_full_ms_high_school_geography.yaml | 5 ++ ...s_high_school_government_and_politics.yaml | 5 ++ ...lu_full_ms_high_school_macroeconomics.yaml | 5 ++ ..._mmlu_full_ms_high_school_mathematics.yaml | 5 ++ ...lu_full_ms_high_school_microeconomics.yaml | 5 ++ ...obal_mmlu_full_ms_high_school_physics.yaml | 5 ++ ...l_mmlu_full_ms_high_school_psychology.yaml | 5 ++ ...l_mmlu_full_ms_high_school_statistics.yaml | 5 ++ ...l_mmlu_full_ms_high_school_us_history.yaml | 5 ++ ...mlu_full_ms_high_school_world_history.yaml | 5 ++ .../ms/global_mmlu_full_ms_human_aging.yaml | 5 ++ .../global_mmlu_full_ms_human_sexuality.yaml | 5 ++ ...global_mmlu_full_ms_international_law.yaml | 5 ++ .../ms/global_mmlu_full_ms_jurisprudence.yaml | 5 ++ ...global_mmlu_full_ms_logical_fallacies.yaml | 5 ++ .../global_mmlu_full_ms_machine_learning.yaml | 5 ++ .../ms/global_mmlu_full_ms_management.yaml | 5 ++ .../ms/global_mmlu_full_ms_marketing.yaml | 5 ++ .../global_mmlu_full_ms_medical_genetics.yaml | 5 ++ .../ms/global_mmlu_full_ms_miscellaneous.yaml | 5 ++ .../global_mmlu_full_ms_moral_disputes.yaml | 5 ++ .../global_mmlu_full_ms_moral_scenarios.yaml | 5 ++ .../ms/global_mmlu_full_ms_nutrition.yaml | 5 ++ .../ms/global_mmlu_full_ms_philosophy.yaml | 5 ++ .../ms/global_mmlu_full_ms_prehistory.yaml | 5 ++ ..._mmlu_full_ms_professional_accounting.yaml | 5 ++ .../global_mmlu_full_ms_professional_law.yaml | 5 ++ ...al_mmlu_full_ms_professional_medicine.yaml | 5 ++ ..._mmlu_full_ms_professional_psychology.yaml | 5 ++ .../global_mmlu_full_ms_public_relations.yaml | 5 ++ .../global_mmlu_full_ms_security_studies.yaml | 5 ++ .../ms/global_mmlu_full_ms_sociology.yaml | 5 ++ ...global_mmlu_full_ms_us_foreign_policy.yaml | 5 ++ .../full/ms/global_mmlu_full_ms_virology.yaml | 5 ++ .../global_mmlu_full_ms_world_religions.yaml | 5 ++ lm_eval/tasks/global_mmlu/full/ms/utils.py | 73 +++++++++++++++++++ .../full/ne/_global_mmlu_full_ne.yaml | 11 +++ .../ne/_global_mmlu_full_ne_humanities.yaml | 8 ++ .../full/ne/_global_mmlu_full_ne_other.yaml | 8 ++ .../_global_mmlu_full_ne_social_sciences.yaml | 8 ++ .../full/ne/_global_mmlu_full_ne_stem.yaml | 8 ++ .../global_mmlu/full/ne/_ne_template_yaml | 16 ++++ .../global_mmlu_full_ne_abstract_algebra.yaml | 5 ++ .../full/ne/global_mmlu_full_ne_anatomy.yaml | 5 ++ .../ne/global_mmlu_full_ne_astronomy.yaml | 5 ++ .../global_mmlu_full_ne_business_ethics.yaml | 5 ++ ...lobal_mmlu_full_ne_clinical_knowledge.yaml | 5 ++ .../global_mmlu_full_ne_college_biology.yaml | 5 ++ ...global_mmlu_full_ne_college_chemistry.yaml | 5 ++ ...mmlu_full_ne_college_computer_science.yaml | 5 ++ ...obal_mmlu_full_ne_college_mathematics.yaml | 5 ++ .../global_mmlu_full_ne_college_medicine.yaml | 5 ++ .../global_mmlu_full_ne_college_physics.yaml | 5 ++ ...global_mmlu_full_ne_computer_security.yaml | 5 ++ ...lobal_mmlu_full_ne_conceptual_physics.yaml | 5 ++ .../ne/global_mmlu_full_ne_econometrics.yaml | 5 ++ ...l_mmlu_full_ne_electrical_engineering.yaml | 5 ++ ...l_mmlu_full_ne_elementary_mathematics.yaml | 5 ++ .../ne/global_mmlu_full_ne_formal_logic.yaml | 5 ++ .../ne/global_mmlu_full_ne_global_facts.yaml | 5 ++ ...obal_mmlu_full_ne_high_school_biology.yaml | 5 ++ ...al_mmlu_full_ne_high_school_chemistry.yaml | 5 ++ ..._full_ne_high_school_computer_science.yaml | 5 ++ ..._full_ne_high_school_european_history.yaml | 5 ++ ...al_mmlu_full_ne_high_school_geography.yaml | 5 ++ ...e_high_school_government_and_politics.yaml | 5 ++ ...lu_full_ne_high_school_macroeconomics.yaml | 5 ++ ..._mmlu_full_ne_high_school_mathematics.yaml | 5 ++ ...lu_full_ne_high_school_microeconomics.yaml | 5 ++ ...obal_mmlu_full_ne_high_school_physics.yaml | 5 ++ ...l_mmlu_full_ne_high_school_psychology.yaml | 5 ++ ...l_mmlu_full_ne_high_school_statistics.yaml | 5 ++ ...l_mmlu_full_ne_high_school_us_history.yaml | 5 ++ ...mlu_full_ne_high_school_world_history.yaml | 5 ++ .../ne/global_mmlu_full_ne_human_aging.yaml | 5 ++ .../global_mmlu_full_ne_human_sexuality.yaml | 5 ++ ...global_mmlu_full_ne_international_law.yaml | 5 ++ .../ne/global_mmlu_full_ne_jurisprudence.yaml | 5 ++ ...global_mmlu_full_ne_logical_fallacies.yaml | 5 ++ .../global_mmlu_full_ne_machine_learning.yaml | 5 ++ .../ne/global_mmlu_full_ne_management.yaml | 5 ++ .../ne/global_mmlu_full_ne_marketing.yaml | 5 ++ .../global_mmlu_full_ne_medical_genetics.yaml | 5 ++ .../ne/global_mmlu_full_ne_miscellaneous.yaml | 5 ++ .../global_mmlu_full_ne_moral_disputes.yaml | 5 ++ .../global_mmlu_full_ne_moral_scenarios.yaml | 5 ++ .../ne/global_mmlu_full_ne_nutrition.yaml | 5 ++ .../ne/global_mmlu_full_ne_philosophy.yaml | 5 ++ .../ne/global_mmlu_full_ne_prehistory.yaml | 5 ++ ..._mmlu_full_ne_professional_accounting.yaml | 5 ++ .../global_mmlu_full_ne_professional_law.yaml | 5 ++ ...al_mmlu_full_ne_professional_medicine.yaml | 5 ++ ..._mmlu_full_ne_professional_psychology.yaml | 5 ++ .../global_mmlu_full_ne_public_relations.yaml | 5 ++ .../global_mmlu_full_ne_security_studies.yaml | 5 ++ .../ne/global_mmlu_full_ne_sociology.yaml | 5 ++ ...global_mmlu_full_ne_us_foreign_policy.yaml | 5 ++ .../full/ne/global_mmlu_full_ne_virology.yaml | 5 ++ .../global_mmlu_full_ne_world_religions.yaml | 5 ++ lm_eval/tasks/global_mmlu/full/ne/utils.py | 73 +++++++++++++++++++ .../full/nl/_global_mmlu_full_nl.yaml | 11 +++ .../nl/_global_mmlu_full_nl_humanities.yaml | 8 ++ .../full/nl/_global_mmlu_full_nl_other.yaml | 8 ++ .../_global_mmlu_full_nl_social_sciences.yaml | 8 ++ .../full/nl/_global_mmlu_full_nl_stem.yaml | 8 ++ .../global_mmlu/full/nl/_nl_template_yaml | 16 ++++ .../global_mmlu_full_nl_abstract_algebra.yaml | 5 ++ .../full/nl/global_mmlu_full_nl_anatomy.yaml | 5 ++ .../nl/global_mmlu_full_nl_astronomy.yaml | 5 ++ .../global_mmlu_full_nl_business_ethics.yaml | 5 ++ ...lobal_mmlu_full_nl_clinical_knowledge.yaml | 5 ++ .../global_mmlu_full_nl_college_biology.yaml | 5 ++ ...global_mmlu_full_nl_college_chemistry.yaml | 5 ++ ...mmlu_full_nl_college_computer_science.yaml | 5 ++ ...obal_mmlu_full_nl_college_mathematics.yaml | 5 ++ .../global_mmlu_full_nl_college_medicine.yaml | 5 ++ .../global_mmlu_full_nl_college_physics.yaml | 5 ++ ...global_mmlu_full_nl_computer_security.yaml | 5 ++ ...lobal_mmlu_full_nl_conceptual_physics.yaml | 5 ++ .../nl/global_mmlu_full_nl_econometrics.yaml | 5 ++ ...l_mmlu_full_nl_electrical_engineering.yaml | 5 ++ ...l_mmlu_full_nl_elementary_mathematics.yaml | 5 ++ .../nl/global_mmlu_full_nl_formal_logic.yaml | 5 ++ .../nl/global_mmlu_full_nl_global_facts.yaml | 5 ++ ...obal_mmlu_full_nl_high_school_biology.yaml | 5 ++ ...al_mmlu_full_nl_high_school_chemistry.yaml | 5 ++ ..._full_nl_high_school_computer_science.yaml | 5 ++ ..._full_nl_high_school_european_history.yaml | 5 ++ ...al_mmlu_full_nl_high_school_geography.yaml | 5 ++ ...l_high_school_government_and_politics.yaml | 5 ++ ...lu_full_nl_high_school_macroeconomics.yaml | 5 ++ ..._mmlu_full_nl_high_school_mathematics.yaml | 5 ++ ...lu_full_nl_high_school_microeconomics.yaml | 5 ++ ...obal_mmlu_full_nl_high_school_physics.yaml | 5 ++ ...l_mmlu_full_nl_high_school_psychology.yaml | 5 ++ ...l_mmlu_full_nl_high_school_statistics.yaml | 5 ++ ...l_mmlu_full_nl_high_school_us_history.yaml | 5 ++ ...mlu_full_nl_high_school_world_history.yaml | 5 ++ .../nl/global_mmlu_full_nl_human_aging.yaml | 5 ++ .../global_mmlu_full_nl_human_sexuality.yaml | 5 ++ ...global_mmlu_full_nl_international_law.yaml | 5 ++ .../nl/global_mmlu_full_nl_jurisprudence.yaml | 5 ++ ...global_mmlu_full_nl_logical_fallacies.yaml | 5 ++ .../global_mmlu_full_nl_machine_learning.yaml | 5 ++ .../nl/global_mmlu_full_nl_management.yaml | 5 ++ .../nl/global_mmlu_full_nl_marketing.yaml | 5 ++ .../global_mmlu_full_nl_medical_genetics.yaml | 5 ++ .../nl/global_mmlu_full_nl_miscellaneous.yaml | 5 ++ .../global_mmlu_full_nl_moral_disputes.yaml | 5 ++ .../global_mmlu_full_nl_moral_scenarios.yaml | 5 ++ .../nl/global_mmlu_full_nl_nutrition.yaml | 5 ++ .../nl/global_mmlu_full_nl_philosophy.yaml | 5 ++ .../nl/global_mmlu_full_nl_prehistory.yaml | 5 ++ ..._mmlu_full_nl_professional_accounting.yaml | 5 ++ .../global_mmlu_full_nl_professional_law.yaml | 5 ++ ...al_mmlu_full_nl_professional_medicine.yaml | 5 ++ ..._mmlu_full_nl_professional_psychology.yaml | 5 ++ .../global_mmlu_full_nl_public_relations.yaml | 5 ++ .../global_mmlu_full_nl_security_studies.yaml | 5 ++ .../nl/global_mmlu_full_nl_sociology.yaml | 5 ++ ...global_mmlu_full_nl_us_foreign_policy.yaml | 5 ++ .../full/nl/global_mmlu_full_nl_virology.yaml | 5 ++ .../global_mmlu_full_nl_world_religions.yaml | 5 ++ lm_eval/tasks/global_mmlu/full/nl/utils.py | 73 +++++++++++++++++++ .../full/ny/_global_mmlu_full_ny.yaml | 11 +++ .../ny/_global_mmlu_full_ny_humanities.yaml | 8 ++ .../full/ny/_global_mmlu_full_ny_other.yaml | 8 ++ .../_global_mmlu_full_ny_social_sciences.yaml | 8 ++ .../full/ny/_global_mmlu_full_ny_stem.yaml | 8 ++ .../global_mmlu/full/ny/_ny_template_yaml | 16 ++++ .../global_mmlu_full_ny_abstract_algebra.yaml | 5 ++ .../full/ny/global_mmlu_full_ny_anatomy.yaml | 5 ++ .../ny/global_mmlu_full_ny_astronomy.yaml | 5 ++ .../global_mmlu_full_ny_business_ethics.yaml | 5 ++ ...lobal_mmlu_full_ny_clinical_knowledge.yaml | 5 ++ .../global_mmlu_full_ny_college_biology.yaml | 5 ++ ...global_mmlu_full_ny_college_chemistry.yaml | 5 ++ ...mmlu_full_ny_college_computer_science.yaml | 5 ++ ...obal_mmlu_full_ny_college_mathematics.yaml | 5 ++ .../global_mmlu_full_ny_college_medicine.yaml | 5 ++ .../global_mmlu_full_ny_college_physics.yaml | 5 ++ ...global_mmlu_full_ny_computer_security.yaml | 5 ++ ...lobal_mmlu_full_ny_conceptual_physics.yaml | 5 ++ .../ny/global_mmlu_full_ny_econometrics.yaml | 5 ++ ...l_mmlu_full_ny_electrical_engineering.yaml | 5 ++ ...l_mmlu_full_ny_elementary_mathematics.yaml | 5 ++ .../ny/global_mmlu_full_ny_formal_logic.yaml | 5 ++ .../ny/global_mmlu_full_ny_global_facts.yaml | 5 ++ ...obal_mmlu_full_ny_high_school_biology.yaml | 5 ++ ...al_mmlu_full_ny_high_school_chemistry.yaml | 5 ++ ..._full_ny_high_school_computer_science.yaml | 5 ++ ..._full_ny_high_school_european_history.yaml | 5 ++ ...al_mmlu_full_ny_high_school_geography.yaml | 5 ++ ...y_high_school_government_and_politics.yaml | 5 ++ ...lu_full_ny_high_school_macroeconomics.yaml | 5 ++ ..._mmlu_full_ny_high_school_mathematics.yaml | 5 ++ ...lu_full_ny_high_school_microeconomics.yaml | 5 ++ ...obal_mmlu_full_ny_high_school_physics.yaml | 5 ++ ...l_mmlu_full_ny_high_school_psychology.yaml | 5 ++ ...l_mmlu_full_ny_high_school_statistics.yaml | 5 ++ ...l_mmlu_full_ny_high_school_us_history.yaml | 5 ++ ...mlu_full_ny_high_school_world_history.yaml | 5 ++ .../ny/global_mmlu_full_ny_human_aging.yaml | 5 ++ .../global_mmlu_full_ny_human_sexuality.yaml | 5 ++ ...global_mmlu_full_ny_international_law.yaml | 5 ++ .../ny/global_mmlu_full_ny_jurisprudence.yaml | 5 ++ ...global_mmlu_full_ny_logical_fallacies.yaml | 5 ++ .../global_mmlu_full_ny_machine_learning.yaml | 5 ++ .../ny/global_mmlu_full_ny_management.yaml | 5 ++ .../ny/global_mmlu_full_ny_marketing.yaml | 5 ++ .../global_mmlu_full_ny_medical_genetics.yaml | 5 ++ .../ny/global_mmlu_full_ny_miscellaneous.yaml | 5 ++ .../global_mmlu_full_ny_moral_disputes.yaml | 5 ++ .../global_mmlu_full_ny_moral_scenarios.yaml | 5 ++ .../ny/global_mmlu_full_ny_nutrition.yaml | 5 ++ .../ny/global_mmlu_full_ny_philosophy.yaml | 5 ++ .../ny/global_mmlu_full_ny_prehistory.yaml | 5 ++ ..._mmlu_full_ny_professional_accounting.yaml | 5 ++ .../global_mmlu_full_ny_professional_law.yaml | 5 ++ ...al_mmlu_full_ny_professional_medicine.yaml | 5 ++ ..._mmlu_full_ny_professional_psychology.yaml | 5 ++ .../global_mmlu_full_ny_public_relations.yaml | 5 ++ .../global_mmlu_full_ny_security_studies.yaml | 5 ++ .../ny/global_mmlu_full_ny_sociology.yaml | 5 ++ ...global_mmlu_full_ny_us_foreign_policy.yaml | 5 ++ .../full/ny/global_mmlu_full_ny_virology.yaml | 5 ++ .../global_mmlu_full_ny_world_religions.yaml | 5 ++ lm_eval/tasks/global_mmlu/full/ny/utils.py | 73 +++++++++++++++++++ .../full/pl/_global_mmlu_full_pl.yaml | 11 +++ .../pl/_global_mmlu_full_pl_humanities.yaml | 8 ++ .../full/pl/_global_mmlu_full_pl_other.yaml | 8 ++ .../_global_mmlu_full_pl_social_sciences.yaml | 8 ++ .../full/pl/_global_mmlu_full_pl_stem.yaml | 8 ++ .../global_mmlu/full/pl/_pl_template_yaml | 16 ++++ .../global_mmlu_full_pl_abstract_algebra.yaml | 5 ++ .../full/pl/global_mmlu_full_pl_anatomy.yaml | 5 ++ .../pl/global_mmlu_full_pl_astronomy.yaml | 5 ++ .../global_mmlu_full_pl_business_ethics.yaml | 5 ++ ...lobal_mmlu_full_pl_clinical_knowledge.yaml | 5 ++ .../global_mmlu_full_pl_college_biology.yaml | 5 ++ ...global_mmlu_full_pl_college_chemistry.yaml | 5 ++ ...mmlu_full_pl_college_computer_science.yaml | 5 ++ ...obal_mmlu_full_pl_college_mathematics.yaml | 5 ++ .../global_mmlu_full_pl_college_medicine.yaml | 5 ++ .../global_mmlu_full_pl_college_physics.yaml | 5 ++ ...global_mmlu_full_pl_computer_security.yaml | 5 ++ ...lobal_mmlu_full_pl_conceptual_physics.yaml | 5 ++ .../pl/global_mmlu_full_pl_econometrics.yaml | 5 ++ ...l_mmlu_full_pl_electrical_engineering.yaml | 5 ++ ...l_mmlu_full_pl_elementary_mathematics.yaml | 5 ++ .../pl/global_mmlu_full_pl_formal_logic.yaml | 5 ++ .../pl/global_mmlu_full_pl_global_facts.yaml | 5 ++ ...obal_mmlu_full_pl_high_school_biology.yaml | 5 ++ ...al_mmlu_full_pl_high_school_chemistry.yaml | 5 ++ ..._full_pl_high_school_computer_science.yaml | 5 ++ ..._full_pl_high_school_european_history.yaml | 5 ++ ...al_mmlu_full_pl_high_school_geography.yaml | 5 ++ ...l_high_school_government_and_politics.yaml | 5 ++ ...lu_full_pl_high_school_macroeconomics.yaml | 5 ++ ..._mmlu_full_pl_high_school_mathematics.yaml | 5 ++ ...lu_full_pl_high_school_microeconomics.yaml | 5 ++ ...obal_mmlu_full_pl_high_school_physics.yaml | 5 ++ ...l_mmlu_full_pl_high_school_psychology.yaml | 5 ++ ...l_mmlu_full_pl_high_school_statistics.yaml | 5 ++ ...l_mmlu_full_pl_high_school_us_history.yaml | 5 ++ ...mlu_full_pl_high_school_world_history.yaml | 5 ++ .../pl/global_mmlu_full_pl_human_aging.yaml | 5 ++ .../global_mmlu_full_pl_human_sexuality.yaml | 5 ++ ...global_mmlu_full_pl_international_law.yaml | 5 ++ .../pl/global_mmlu_full_pl_jurisprudence.yaml | 5 ++ ...global_mmlu_full_pl_logical_fallacies.yaml | 5 ++ .../global_mmlu_full_pl_machine_learning.yaml | 5 ++ .../pl/global_mmlu_full_pl_management.yaml | 5 ++ .../pl/global_mmlu_full_pl_marketing.yaml | 5 ++ .../global_mmlu_full_pl_medical_genetics.yaml | 5 ++ .../pl/global_mmlu_full_pl_miscellaneous.yaml | 5 ++ .../global_mmlu_full_pl_moral_disputes.yaml | 5 ++ .../global_mmlu_full_pl_moral_scenarios.yaml | 5 ++ .../pl/global_mmlu_full_pl_nutrition.yaml | 5 ++ .../pl/global_mmlu_full_pl_philosophy.yaml | 5 ++ .../pl/global_mmlu_full_pl_prehistory.yaml | 5 ++ ..._mmlu_full_pl_professional_accounting.yaml | 5 ++ .../global_mmlu_full_pl_professional_law.yaml | 5 ++ ...al_mmlu_full_pl_professional_medicine.yaml | 5 ++ ..._mmlu_full_pl_professional_psychology.yaml | 5 ++ .../global_mmlu_full_pl_public_relations.yaml | 5 ++ .../global_mmlu_full_pl_security_studies.yaml | 5 ++ .../pl/global_mmlu_full_pl_sociology.yaml | 5 ++ ...global_mmlu_full_pl_us_foreign_policy.yaml | 5 ++ .../full/pl/global_mmlu_full_pl_virology.yaml | 5 ++ .../global_mmlu_full_pl_world_religions.yaml | 5 ++ lm_eval/tasks/global_mmlu/full/pl/utils.py | 73 +++++++++++++++++++ .../full/pt/_global_mmlu_full_pt.yaml | 11 +++ .../pt/_global_mmlu_full_pt_humanities.yaml | 8 ++ .../full/pt/_global_mmlu_full_pt_other.yaml | 8 ++ .../_global_mmlu_full_pt_social_sciences.yaml | 8 ++ .../full/pt/_global_mmlu_full_pt_stem.yaml | 8 ++ .../global_mmlu/full/pt/_pt_template_yaml | 16 ++++ .../global_mmlu_full_pt_abstract_algebra.yaml | 5 ++ .../full/pt/global_mmlu_full_pt_anatomy.yaml | 5 ++ .../pt/global_mmlu_full_pt_astronomy.yaml | 5 ++ .../global_mmlu_full_pt_business_ethics.yaml | 5 ++ ...lobal_mmlu_full_pt_clinical_knowledge.yaml | 5 ++ .../global_mmlu_full_pt_college_biology.yaml | 5 ++ ...global_mmlu_full_pt_college_chemistry.yaml | 5 ++ ...mmlu_full_pt_college_computer_science.yaml | 5 ++ ...obal_mmlu_full_pt_college_mathematics.yaml | 5 ++ .../global_mmlu_full_pt_college_medicine.yaml | 5 ++ .../global_mmlu_full_pt_college_physics.yaml | 5 ++ ...global_mmlu_full_pt_computer_security.yaml | 5 ++ ...lobal_mmlu_full_pt_conceptual_physics.yaml | 5 ++ .../pt/global_mmlu_full_pt_econometrics.yaml | 5 ++ ...l_mmlu_full_pt_electrical_engineering.yaml | 5 ++ ...l_mmlu_full_pt_elementary_mathematics.yaml | 5 ++ .../pt/global_mmlu_full_pt_formal_logic.yaml | 5 ++ .../pt/global_mmlu_full_pt_global_facts.yaml | 5 ++ ...obal_mmlu_full_pt_high_school_biology.yaml | 5 ++ ...al_mmlu_full_pt_high_school_chemistry.yaml | 5 ++ ..._full_pt_high_school_computer_science.yaml | 5 ++ ..._full_pt_high_school_european_history.yaml | 5 ++ ...al_mmlu_full_pt_high_school_geography.yaml | 5 ++ ...t_high_school_government_and_politics.yaml | 5 ++ ...lu_full_pt_high_school_macroeconomics.yaml | 5 ++ ..._mmlu_full_pt_high_school_mathematics.yaml | 5 ++ ...lu_full_pt_high_school_microeconomics.yaml | 5 ++ ...obal_mmlu_full_pt_high_school_physics.yaml | 5 ++ ...l_mmlu_full_pt_high_school_psychology.yaml | 5 ++ ...l_mmlu_full_pt_high_school_statistics.yaml | 5 ++ ...l_mmlu_full_pt_high_school_us_history.yaml | 5 ++ ...mlu_full_pt_high_school_world_history.yaml | 5 ++ .../pt/global_mmlu_full_pt_human_aging.yaml | 5 ++ .../global_mmlu_full_pt_human_sexuality.yaml | 5 ++ ...global_mmlu_full_pt_international_law.yaml | 5 ++ .../pt/global_mmlu_full_pt_jurisprudence.yaml | 5 ++ ...global_mmlu_full_pt_logical_fallacies.yaml | 5 ++ .../global_mmlu_full_pt_machine_learning.yaml | 5 ++ .../pt/global_mmlu_full_pt_management.yaml | 5 ++ .../pt/global_mmlu_full_pt_marketing.yaml | 5 ++ .../global_mmlu_full_pt_medical_genetics.yaml | 5 ++ .../pt/global_mmlu_full_pt_miscellaneous.yaml | 5 ++ .../global_mmlu_full_pt_moral_disputes.yaml | 5 ++ .../global_mmlu_full_pt_moral_scenarios.yaml | 5 ++ .../pt/global_mmlu_full_pt_nutrition.yaml | 5 ++ .../pt/global_mmlu_full_pt_philosophy.yaml | 5 ++ .../pt/global_mmlu_full_pt_prehistory.yaml | 5 ++ ..._mmlu_full_pt_professional_accounting.yaml | 5 ++ .../global_mmlu_full_pt_professional_law.yaml | 5 ++ ...al_mmlu_full_pt_professional_medicine.yaml | 5 ++ ..._mmlu_full_pt_professional_psychology.yaml | 5 ++ .../global_mmlu_full_pt_public_relations.yaml | 5 ++ .../global_mmlu_full_pt_security_studies.yaml | 5 ++ .../pt/global_mmlu_full_pt_sociology.yaml | 5 ++ ...global_mmlu_full_pt_us_foreign_policy.yaml | 5 ++ .../full/pt/global_mmlu_full_pt_virology.yaml | 5 ++ .../global_mmlu_full_pt_world_religions.yaml | 5 ++ lm_eval/tasks/global_mmlu/full/pt/utils.py | 73 +++++++++++++++++++ .../full/ro/_global_mmlu_full_ro.yaml | 11 +++ .../ro/_global_mmlu_full_ro_humanities.yaml | 8 ++ .../full/ro/_global_mmlu_full_ro_other.yaml | 8 ++ .../_global_mmlu_full_ro_social_sciences.yaml | 8 ++ .../full/ro/_global_mmlu_full_ro_stem.yaml | 8 ++ .../global_mmlu/full/ro/_ro_template_yaml | 16 ++++ .../global_mmlu_full_ro_abstract_algebra.yaml | 5 ++ .../full/ro/global_mmlu_full_ro_anatomy.yaml | 5 ++ .../ro/global_mmlu_full_ro_astronomy.yaml | 5 ++ .../global_mmlu_full_ro_business_ethics.yaml | 5 ++ ...lobal_mmlu_full_ro_clinical_knowledge.yaml | 5 ++ .../global_mmlu_full_ro_college_biology.yaml | 5 ++ ...global_mmlu_full_ro_college_chemistry.yaml | 5 ++ ...mmlu_full_ro_college_computer_science.yaml | 5 ++ ...obal_mmlu_full_ro_college_mathematics.yaml | 5 ++ .../global_mmlu_full_ro_college_medicine.yaml | 5 ++ .../global_mmlu_full_ro_college_physics.yaml | 5 ++ ...global_mmlu_full_ro_computer_security.yaml | 5 ++ ...lobal_mmlu_full_ro_conceptual_physics.yaml | 5 ++ .../ro/global_mmlu_full_ro_econometrics.yaml | 5 ++ ...l_mmlu_full_ro_electrical_engineering.yaml | 5 ++ ...l_mmlu_full_ro_elementary_mathematics.yaml | 5 ++ .../ro/global_mmlu_full_ro_formal_logic.yaml | 5 ++ .../ro/global_mmlu_full_ro_global_facts.yaml | 5 ++ ...obal_mmlu_full_ro_high_school_biology.yaml | 5 ++ ...al_mmlu_full_ro_high_school_chemistry.yaml | 5 ++ ..._full_ro_high_school_computer_science.yaml | 5 ++ ..._full_ro_high_school_european_history.yaml | 5 ++ ...al_mmlu_full_ro_high_school_geography.yaml | 5 ++ ...o_high_school_government_and_politics.yaml | 5 ++ ...lu_full_ro_high_school_macroeconomics.yaml | 5 ++ ..._mmlu_full_ro_high_school_mathematics.yaml | 5 ++ ...lu_full_ro_high_school_microeconomics.yaml | 5 ++ ...obal_mmlu_full_ro_high_school_physics.yaml | 5 ++ ...l_mmlu_full_ro_high_school_psychology.yaml | 5 ++ ...l_mmlu_full_ro_high_school_statistics.yaml | 5 ++ ...l_mmlu_full_ro_high_school_us_history.yaml | 5 ++ ...mlu_full_ro_high_school_world_history.yaml | 5 ++ .../ro/global_mmlu_full_ro_human_aging.yaml | 5 ++ .../global_mmlu_full_ro_human_sexuality.yaml | 5 ++ ...global_mmlu_full_ro_international_law.yaml | 5 ++ .../ro/global_mmlu_full_ro_jurisprudence.yaml | 5 ++ ...global_mmlu_full_ro_logical_fallacies.yaml | 5 ++ .../global_mmlu_full_ro_machine_learning.yaml | 5 ++ .../ro/global_mmlu_full_ro_management.yaml | 5 ++ .../ro/global_mmlu_full_ro_marketing.yaml | 5 ++ .../global_mmlu_full_ro_medical_genetics.yaml | 5 ++ .../ro/global_mmlu_full_ro_miscellaneous.yaml | 5 ++ .../global_mmlu_full_ro_moral_disputes.yaml | 5 ++ .../global_mmlu_full_ro_moral_scenarios.yaml | 5 ++ .../ro/global_mmlu_full_ro_nutrition.yaml | 5 ++ .../ro/global_mmlu_full_ro_philosophy.yaml | 5 ++ .../ro/global_mmlu_full_ro_prehistory.yaml | 5 ++ ..._mmlu_full_ro_professional_accounting.yaml | 5 ++ .../global_mmlu_full_ro_professional_law.yaml | 5 ++ ...al_mmlu_full_ro_professional_medicine.yaml | 5 ++ ..._mmlu_full_ro_professional_psychology.yaml | 5 ++ .../global_mmlu_full_ro_public_relations.yaml | 5 ++ .../global_mmlu_full_ro_security_studies.yaml | 5 ++ .../ro/global_mmlu_full_ro_sociology.yaml | 5 ++ ...global_mmlu_full_ro_us_foreign_policy.yaml | 5 ++ .../full/ro/global_mmlu_full_ro_virology.yaml | 5 ++ .../global_mmlu_full_ro_world_religions.yaml | 5 ++ lm_eval/tasks/global_mmlu/full/ro/utils.py | 73 +++++++++++++++++++ .../full/ru/_global_mmlu_full_ru.yaml | 11 +++ .../ru/_global_mmlu_full_ru_humanities.yaml | 8 ++ .../full/ru/_global_mmlu_full_ru_other.yaml | 8 ++ .../_global_mmlu_full_ru_social_sciences.yaml | 8 ++ .../full/ru/_global_mmlu_full_ru_stem.yaml | 8 ++ .../global_mmlu/full/ru/_ru_template_yaml | 16 ++++ .../global_mmlu_full_ru_abstract_algebra.yaml | 5 ++ .../full/ru/global_mmlu_full_ru_anatomy.yaml | 5 ++ .../ru/global_mmlu_full_ru_astronomy.yaml | 5 ++ .../global_mmlu_full_ru_business_ethics.yaml | 5 ++ ...lobal_mmlu_full_ru_clinical_knowledge.yaml | 5 ++ .../global_mmlu_full_ru_college_biology.yaml | 5 ++ ...global_mmlu_full_ru_college_chemistry.yaml | 5 ++ ...mmlu_full_ru_college_computer_science.yaml | 5 ++ ...obal_mmlu_full_ru_college_mathematics.yaml | 5 ++ .../global_mmlu_full_ru_college_medicine.yaml | 5 ++ .../global_mmlu_full_ru_college_physics.yaml | 5 ++ ...global_mmlu_full_ru_computer_security.yaml | 5 ++ ...lobal_mmlu_full_ru_conceptual_physics.yaml | 5 ++ .../ru/global_mmlu_full_ru_econometrics.yaml | 5 ++ ...l_mmlu_full_ru_electrical_engineering.yaml | 5 ++ ...l_mmlu_full_ru_elementary_mathematics.yaml | 5 ++ .../ru/global_mmlu_full_ru_formal_logic.yaml | 5 ++ .../ru/global_mmlu_full_ru_global_facts.yaml | 5 ++ ...obal_mmlu_full_ru_high_school_biology.yaml | 5 ++ ...al_mmlu_full_ru_high_school_chemistry.yaml | 5 ++ ..._full_ru_high_school_computer_science.yaml | 5 ++ ..._full_ru_high_school_european_history.yaml | 5 ++ ...al_mmlu_full_ru_high_school_geography.yaml | 5 ++ ...u_high_school_government_and_politics.yaml | 5 ++ ...lu_full_ru_high_school_macroeconomics.yaml | 5 ++ ..._mmlu_full_ru_high_school_mathematics.yaml | 5 ++ ...lu_full_ru_high_school_microeconomics.yaml | 5 ++ ...obal_mmlu_full_ru_high_school_physics.yaml | 5 ++ ...l_mmlu_full_ru_high_school_psychology.yaml | 5 ++ ...l_mmlu_full_ru_high_school_statistics.yaml | 5 ++ ...l_mmlu_full_ru_high_school_us_history.yaml | 5 ++ ...mlu_full_ru_high_school_world_history.yaml | 5 ++ .../ru/global_mmlu_full_ru_human_aging.yaml | 5 ++ .../global_mmlu_full_ru_human_sexuality.yaml | 5 ++ ...global_mmlu_full_ru_international_law.yaml | 5 ++ .../ru/global_mmlu_full_ru_jurisprudence.yaml | 5 ++ ...global_mmlu_full_ru_logical_fallacies.yaml | 5 ++ .../global_mmlu_full_ru_machine_learning.yaml | 5 ++ .../ru/global_mmlu_full_ru_management.yaml | 5 ++ .../ru/global_mmlu_full_ru_marketing.yaml | 5 ++ .../global_mmlu_full_ru_medical_genetics.yaml | 5 ++ .../ru/global_mmlu_full_ru_miscellaneous.yaml | 5 ++ .../global_mmlu_full_ru_moral_disputes.yaml | 5 ++ .../global_mmlu_full_ru_moral_scenarios.yaml | 5 ++ .../ru/global_mmlu_full_ru_nutrition.yaml | 5 ++ .../ru/global_mmlu_full_ru_philosophy.yaml | 5 ++ .../ru/global_mmlu_full_ru_prehistory.yaml | 5 ++ ..._mmlu_full_ru_professional_accounting.yaml | 5 ++ .../global_mmlu_full_ru_professional_law.yaml | 5 ++ ...al_mmlu_full_ru_professional_medicine.yaml | 5 ++ ..._mmlu_full_ru_professional_psychology.yaml | 5 ++ .../global_mmlu_full_ru_public_relations.yaml | 5 ++ .../global_mmlu_full_ru_security_studies.yaml | 5 ++ .../ru/global_mmlu_full_ru_sociology.yaml | 5 ++ ...global_mmlu_full_ru_us_foreign_policy.yaml | 5 ++ .../full/ru/global_mmlu_full_ru_virology.yaml | 5 ++ .../global_mmlu_full_ru_world_religions.yaml | 5 ++ lm_eval/tasks/global_mmlu/full/ru/utils.py | 73 +++++++++++++++++++ .../full/si/_global_mmlu_full_si.yaml | 11 +++ .../si/_global_mmlu_full_si_humanities.yaml | 8 ++ .../full/si/_global_mmlu_full_si_other.yaml | 8 ++ .../_global_mmlu_full_si_social_sciences.yaml | 8 ++ .../full/si/_global_mmlu_full_si_stem.yaml | 8 ++ .../global_mmlu/full/si/_si_template_yaml | 16 ++++ .../global_mmlu_full_si_abstract_algebra.yaml | 5 ++ .../full/si/global_mmlu_full_si_anatomy.yaml | 5 ++ .../si/global_mmlu_full_si_astronomy.yaml | 5 ++ .../global_mmlu_full_si_business_ethics.yaml | 5 ++ ...lobal_mmlu_full_si_clinical_knowledge.yaml | 5 ++ .../global_mmlu_full_si_college_biology.yaml | 5 ++ ...global_mmlu_full_si_college_chemistry.yaml | 5 ++ ...mmlu_full_si_college_computer_science.yaml | 5 ++ ...obal_mmlu_full_si_college_mathematics.yaml | 5 ++ .../global_mmlu_full_si_college_medicine.yaml | 5 ++ .../global_mmlu_full_si_college_physics.yaml | 5 ++ ...global_mmlu_full_si_computer_security.yaml | 5 ++ ...lobal_mmlu_full_si_conceptual_physics.yaml | 5 ++ .../si/global_mmlu_full_si_econometrics.yaml | 5 ++ ...l_mmlu_full_si_electrical_engineering.yaml | 5 ++ ...l_mmlu_full_si_elementary_mathematics.yaml | 5 ++ .../si/global_mmlu_full_si_formal_logic.yaml | 5 ++ .../si/global_mmlu_full_si_global_facts.yaml | 5 ++ ...obal_mmlu_full_si_high_school_biology.yaml | 5 ++ ...al_mmlu_full_si_high_school_chemistry.yaml | 5 ++ ..._full_si_high_school_computer_science.yaml | 5 ++ ..._full_si_high_school_european_history.yaml | 5 ++ ...al_mmlu_full_si_high_school_geography.yaml | 5 ++ ...i_high_school_government_and_politics.yaml | 5 ++ ...lu_full_si_high_school_macroeconomics.yaml | 5 ++ ..._mmlu_full_si_high_school_mathematics.yaml | 5 ++ ...lu_full_si_high_school_microeconomics.yaml | 5 ++ ...obal_mmlu_full_si_high_school_physics.yaml | 5 ++ ...l_mmlu_full_si_high_school_psychology.yaml | 5 ++ ...l_mmlu_full_si_high_school_statistics.yaml | 5 ++ ...l_mmlu_full_si_high_school_us_history.yaml | 5 ++ ...mlu_full_si_high_school_world_history.yaml | 5 ++ .../si/global_mmlu_full_si_human_aging.yaml | 5 ++ .../global_mmlu_full_si_human_sexuality.yaml | 5 ++ ...global_mmlu_full_si_international_law.yaml | 5 ++ .../si/global_mmlu_full_si_jurisprudence.yaml | 5 ++ ...global_mmlu_full_si_logical_fallacies.yaml | 5 ++ .../global_mmlu_full_si_machine_learning.yaml | 5 ++ .../si/global_mmlu_full_si_management.yaml | 5 ++ .../si/global_mmlu_full_si_marketing.yaml | 5 ++ .../global_mmlu_full_si_medical_genetics.yaml | 5 ++ .../si/global_mmlu_full_si_miscellaneous.yaml | 5 ++ .../global_mmlu_full_si_moral_disputes.yaml | 5 ++ .../global_mmlu_full_si_moral_scenarios.yaml | 5 ++ .../si/global_mmlu_full_si_nutrition.yaml | 5 ++ .../si/global_mmlu_full_si_philosophy.yaml | 5 ++ .../si/global_mmlu_full_si_prehistory.yaml | 5 ++ ..._mmlu_full_si_professional_accounting.yaml | 5 ++ .../global_mmlu_full_si_professional_law.yaml | 5 ++ ...al_mmlu_full_si_professional_medicine.yaml | 5 ++ ..._mmlu_full_si_professional_psychology.yaml | 5 ++ .../global_mmlu_full_si_public_relations.yaml | 5 ++ .../global_mmlu_full_si_security_studies.yaml | 5 ++ .../si/global_mmlu_full_si_sociology.yaml | 5 ++ ...global_mmlu_full_si_us_foreign_policy.yaml | 5 ++ .../full/si/global_mmlu_full_si_virology.yaml | 5 ++ .../global_mmlu_full_si_world_religions.yaml | 5 ++ lm_eval/tasks/global_mmlu/full/si/utils.py | 73 +++++++++++++++++++ .../full/sn/_global_mmlu_full_sn.yaml | 11 +++ .../sn/_global_mmlu_full_sn_humanities.yaml | 8 ++ .../full/sn/_global_mmlu_full_sn_other.yaml | 8 ++ .../_global_mmlu_full_sn_social_sciences.yaml | 8 ++ .../full/sn/_global_mmlu_full_sn_stem.yaml | 8 ++ .../global_mmlu/full/sn/_sn_template_yaml | 16 ++++ .../global_mmlu_full_sn_abstract_algebra.yaml | 5 ++ .../full/sn/global_mmlu_full_sn_anatomy.yaml | 5 ++ .../sn/global_mmlu_full_sn_astronomy.yaml | 5 ++ .../global_mmlu_full_sn_business_ethics.yaml | 5 ++ ...lobal_mmlu_full_sn_clinical_knowledge.yaml | 5 ++ .../global_mmlu_full_sn_college_biology.yaml | 5 ++ ...global_mmlu_full_sn_college_chemistry.yaml | 5 ++ ...mmlu_full_sn_college_computer_science.yaml | 5 ++ ...obal_mmlu_full_sn_college_mathematics.yaml | 5 ++ .../global_mmlu_full_sn_college_medicine.yaml | 5 ++ .../global_mmlu_full_sn_college_physics.yaml | 5 ++ ...global_mmlu_full_sn_computer_security.yaml | 5 ++ ...lobal_mmlu_full_sn_conceptual_physics.yaml | 5 ++ .../sn/global_mmlu_full_sn_econometrics.yaml | 5 ++ ...l_mmlu_full_sn_electrical_engineering.yaml | 5 ++ ...l_mmlu_full_sn_elementary_mathematics.yaml | 5 ++ .../sn/global_mmlu_full_sn_formal_logic.yaml | 5 ++ .../sn/global_mmlu_full_sn_global_facts.yaml | 5 ++ ...obal_mmlu_full_sn_high_school_biology.yaml | 5 ++ ...al_mmlu_full_sn_high_school_chemistry.yaml | 5 ++ ..._full_sn_high_school_computer_science.yaml | 5 ++ ..._full_sn_high_school_european_history.yaml | 5 ++ ...al_mmlu_full_sn_high_school_geography.yaml | 5 ++ ...n_high_school_government_and_politics.yaml | 5 ++ ...lu_full_sn_high_school_macroeconomics.yaml | 5 ++ ..._mmlu_full_sn_high_school_mathematics.yaml | 5 ++ ...lu_full_sn_high_school_microeconomics.yaml | 5 ++ ...obal_mmlu_full_sn_high_school_physics.yaml | 5 ++ ...l_mmlu_full_sn_high_school_psychology.yaml | 5 ++ ...l_mmlu_full_sn_high_school_statistics.yaml | 5 ++ ...l_mmlu_full_sn_high_school_us_history.yaml | 5 ++ ...mlu_full_sn_high_school_world_history.yaml | 5 ++ .../sn/global_mmlu_full_sn_human_aging.yaml | 5 ++ .../global_mmlu_full_sn_human_sexuality.yaml | 5 ++ ...global_mmlu_full_sn_international_law.yaml | 5 ++ .../sn/global_mmlu_full_sn_jurisprudence.yaml | 5 ++ ...global_mmlu_full_sn_logical_fallacies.yaml | 5 ++ .../global_mmlu_full_sn_machine_learning.yaml | 5 ++ .../sn/global_mmlu_full_sn_management.yaml | 5 ++ .../sn/global_mmlu_full_sn_marketing.yaml | 5 ++ .../global_mmlu_full_sn_medical_genetics.yaml | 5 ++ .../sn/global_mmlu_full_sn_miscellaneous.yaml | 5 ++ .../global_mmlu_full_sn_moral_disputes.yaml | 5 ++ .../global_mmlu_full_sn_moral_scenarios.yaml | 5 ++ .../sn/global_mmlu_full_sn_nutrition.yaml | 5 ++ .../sn/global_mmlu_full_sn_philosophy.yaml | 5 ++ .../sn/global_mmlu_full_sn_prehistory.yaml | 5 ++ ..._mmlu_full_sn_professional_accounting.yaml | 5 ++ .../global_mmlu_full_sn_professional_law.yaml | 5 ++ ...al_mmlu_full_sn_professional_medicine.yaml | 5 ++ ..._mmlu_full_sn_professional_psychology.yaml | 5 ++ .../global_mmlu_full_sn_public_relations.yaml | 5 ++ .../global_mmlu_full_sn_security_studies.yaml | 5 ++ .../sn/global_mmlu_full_sn_sociology.yaml | 5 ++ ...global_mmlu_full_sn_us_foreign_policy.yaml | 5 ++ .../full/sn/global_mmlu_full_sn_virology.yaml | 5 ++ .../global_mmlu_full_sn_world_religions.yaml | 5 ++ lm_eval/tasks/global_mmlu/full/sn/utils.py | 73 +++++++++++++++++++ .../full/so/_global_mmlu_full_so.yaml | 11 +++ .../so/_global_mmlu_full_so_humanities.yaml | 8 ++ .../full/so/_global_mmlu_full_so_other.yaml | 8 ++ .../_global_mmlu_full_so_social_sciences.yaml | 8 ++ .../full/so/_global_mmlu_full_so_stem.yaml | 8 ++ .../global_mmlu/full/so/_so_template_yaml | 16 ++++ .../global_mmlu_full_so_abstract_algebra.yaml | 5 ++ .../full/so/global_mmlu_full_so_anatomy.yaml | 5 ++ .../so/global_mmlu_full_so_astronomy.yaml | 5 ++ .../global_mmlu_full_so_business_ethics.yaml | 5 ++ ...lobal_mmlu_full_so_clinical_knowledge.yaml | 5 ++ .../global_mmlu_full_so_college_biology.yaml | 5 ++ ...global_mmlu_full_so_college_chemistry.yaml | 5 ++ ...mmlu_full_so_college_computer_science.yaml | 5 ++ ...obal_mmlu_full_so_college_mathematics.yaml | 5 ++ .../global_mmlu_full_so_college_medicine.yaml | 5 ++ .../global_mmlu_full_so_college_physics.yaml | 5 ++ ...global_mmlu_full_so_computer_security.yaml | 5 ++ ...lobal_mmlu_full_so_conceptual_physics.yaml | 5 ++ .../so/global_mmlu_full_so_econometrics.yaml | 5 ++ ...l_mmlu_full_so_electrical_engineering.yaml | 5 ++ ...l_mmlu_full_so_elementary_mathematics.yaml | 5 ++ .../so/global_mmlu_full_so_formal_logic.yaml | 5 ++ .../so/global_mmlu_full_so_global_facts.yaml | 5 ++ ...obal_mmlu_full_so_high_school_biology.yaml | 5 ++ ...al_mmlu_full_so_high_school_chemistry.yaml | 5 ++ ..._full_so_high_school_computer_science.yaml | 5 ++ ..._full_so_high_school_european_history.yaml | 5 ++ ...al_mmlu_full_so_high_school_geography.yaml | 5 ++ ...o_high_school_government_and_politics.yaml | 5 ++ ...lu_full_so_high_school_macroeconomics.yaml | 5 ++ ..._mmlu_full_so_high_school_mathematics.yaml | 5 ++ ...lu_full_so_high_school_microeconomics.yaml | 5 ++ ...obal_mmlu_full_so_high_school_physics.yaml | 5 ++ ...l_mmlu_full_so_high_school_psychology.yaml | 5 ++ ...l_mmlu_full_so_high_school_statistics.yaml | 5 ++ ...l_mmlu_full_so_high_school_us_history.yaml | 5 ++ ...mlu_full_so_high_school_world_history.yaml | 5 ++ .../so/global_mmlu_full_so_human_aging.yaml | 5 ++ .../global_mmlu_full_so_human_sexuality.yaml | 5 ++ ...global_mmlu_full_so_international_law.yaml | 5 ++ .../so/global_mmlu_full_so_jurisprudence.yaml | 5 ++ ...global_mmlu_full_so_logical_fallacies.yaml | 5 ++ .../global_mmlu_full_so_machine_learning.yaml | 5 ++ .../so/global_mmlu_full_so_management.yaml | 5 ++ .../so/global_mmlu_full_so_marketing.yaml | 5 ++ .../global_mmlu_full_so_medical_genetics.yaml | 5 ++ .../so/global_mmlu_full_so_miscellaneous.yaml | 5 ++ .../global_mmlu_full_so_moral_disputes.yaml | 5 ++ .../global_mmlu_full_so_moral_scenarios.yaml | 5 ++ .../so/global_mmlu_full_so_nutrition.yaml | 5 ++ .../so/global_mmlu_full_so_philosophy.yaml | 5 ++ .../so/global_mmlu_full_so_prehistory.yaml | 5 ++ ..._mmlu_full_so_professional_accounting.yaml | 5 ++ .../global_mmlu_full_so_professional_law.yaml | 5 ++ ...al_mmlu_full_so_professional_medicine.yaml | 5 ++ ..._mmlu_full_so_professional_psychology.yaml | 5 ++ .../global_mmlu_full_so_public_relations.yaml | 5 ++ .../global_mmlu_full_so_security_studies.yaml | 5 ++ .../so/global_mmlu_full_so_sociology.yaml | 5 ++ ...global_mmlu_full_so_us_foreign_policy.yaml | 5 ++ .../full/so/global_mmlu_full_so_virology.yaml | 5 ++ .../global_mmlu_full_so_world_religions.yaml | 5 ++ lm_eval/tasks/global_mmlu/full/so/utils.py | 73 +++++++++++++++++++ .../full/sr/_global_mmlu_full_sr.yaml | 11 +++ .../sr/_global_mmlu_full_sr_humanities.yaml | 8 ++ .../full/sr/_global_mmlu_full_sr_other.yaml | 8 ++ .../_global_mmlu_full_sr_social_sciences.yaml | 8 ++ .../full/sr/_global_mmlu_full_sr_stem.yaml | 8 ++ .../global_mmlu/full/sr/_sr_template_yaml | 16 ++++ .../global_mmlu_full_sr_abstract_algebra.yaml | 5 ++ .../full/sr/global_mmlu_full_sr_anatomy.yaml | 5 ++ .../sr/global_mmlu_full_sr_astronomy.yaml | 5 ++ .../global_mmlu_full_sr_business_ethics.yaml | 5 ++ ...lobal_mmlu_full_sr_clinical_knowledge.yaml | 5 ++ .../global_mmlu_full_sr_college_biology.yaml | 5 ++ ...global_mmlu_full_sr_college_chemistry.yaml | 5 ++ ...mmlu_full_sr_college_computer_science.yaml | 5 ++ ...obal_mmlu_full_sr_college_mathematics.yaml | 5 ++ .../global_mmlu_full_sr_college_medicine.yaml | 5 ++ .../global_mmlu_full_sr_college_physics.yaml | 5 ++ ...global_mmlu_full_sr_computer_security.yaml | 5 ++ ...lobal_mmlu_full_sr_conceptual_physics.yaml | 5 ++ .../sr/global_mmlu_full_sr_econometrics.yaml | 5 ++ ...l_mmlu_full_sr_electrical_engineering.yaml | 5 ++ ...l_mmlu_full_sr_elementary_mathematics.yaml | 5 ++ .../sr/global_mmlu_full_sr_formal_logic.yaml | 5 ++ .../sr/global_mmlu_full_sr_global_facts.yaml | 5 ++ ...obal_mmlu_full_sr_high_school_biology.yaml | 5 ++ ...al_mmlu_full_sr_high_school_chemistry.yaml | 5 ++ ..._full_sr_high_school_computer_science.yaml | 5 ++ ..._full_sr_high_school_european_history.yaml | 5 ++ ...al_mmlu_full_sr_high_school_geography.yaml | 5 ++ ...r_high_school_government_and_politics.yaml | 5 ++ ...lu_full_sr_high_school_macroeconomics.yaml | 5 ++ ..._mmlu_full_sr_high_school_mathematics.yaml | 5 ++ ...lu_full_sr_high_school_microeconomics.yaml | 5 ++ ...obal_mmlu_full_sr_high_school_physics.yaml | 5 ++ ...l_mmlu_full_sr_high_school_psychology.yaml | 5 ++ ...l_mmlu_full_sr_high_school_statistics.yaml | 5 ++ ...l_mmlu_full_sr_high_school_us_history.yaml | 5 ++ ...mlu_full_sr_high_school_world_history.yaml | 5 ++ .../sr/global_mmlu_full_sr_human_aging.yaml | 5 ++ .../global_mmlu_full_sr_human_sexuality.yaml | 5 ++ ...global_mmlu_full_sr_international_law.yaml | 5 ++ .../sr/global_mmlu_full_sr_jurisprudence.yaml | 5 ++ ...global_mmlu_full_sr_logical_fallacies.yaml | 5 ++ .../global_mmlu_full_sr_machine_learning.yaml | 5 ++ .../sr/global_mmlu_full_sr_management.yaml | 5 ++ .../sr/global_mmlu_full_sr_marketing.yaml | 5 ++ .../global_mmlu_full_sr_medical_genetics.yaml | 5 ++ .../sr/global_mmlu_full_sr_miscellaneous.yaml | 5 ++ .../global_mmlu_full_sr_moral_disputes.yaml | 5 ++ .../global_mmlu_full_sr_moral_scenarios.yaml | 5 ++ .../sr/global_mmlu_full_sr_nutrition.yaml | 5 ++ .../sr/global_mmlu_full_sr_philosophy.yaml | 5 ++ .../sr/global_mmlu_full_sr_prehistory.yaml | 5 ++ ..._mmlu_full_sr_professional_accounting.yaml | 5 ++ .../global_mmlu_full_sr_professional_law.yaml | 5 ++ ...al_mmlu_full_sr_professional_medicine.yaml | 5 ++ ..._mmlu_full_sr_professional_psychology.yaml | 5 ++ .../global_mmlu_full_sr_public_relations.yaml | 5 ++ .../global_mmlu_full_sr_security_studies.yaml | 5 ++ .../sr/global_mmlu_full_sr_sociology.yaml | 5 ++ ...global_mmlu_full_sr_us_foreign_policy.yaml | 5 ++ .../full/sr/global_mmlu_full_sr_virology.yaml | 5 ++ .../global_mmlu_full_sr_world_religions.yaml | 5 ++ lm_eval/tasks/global_mmlu/full/sr/utils.py | 73 +++++++++++++++++++ .../full/sv/_global_mmlu_full_sv.yaml | 11 +++ .../sv/_global_mmlu_full_sv_humanities.yaml | 8 ++ .../full/sv/_global_mmlu_full_sv_other.yaml | 8 ++ .../_global_mmlu_full_sv_social_sciences.yaml | 8 ++ .../full/sv/_global_mmlu_full_sv_stem.yaml | 8 ++ .../global_mmlu/full/sv/_sv_template_yaml | 16 ++++ .../global_mmlu_full_sv_abstract_algebra.yaml | 5 ++ .../full/sv/global_mmlu_full_sv_anatomy.yaml | 5 ++ .../sv/global_mmlu_full_sv_astronomy.yaml | 5 ++ .../global_mmlu_full_sv_business_ethics.yaml | 5 ++ ...lobal_mmlu_full_sv_clinical_knowledge.yaml | 5 ++ .../global_mmlu_full_sv_college_biology.yaml | 5 ++ ...global_mmlu_full_sv_college_chemistry.yaml | 5 ++ ...mmlu_full_sv_college_computer_science.yaml | 5 ++ ...obal_mmlu_full_sv_college_mathematics.yaml | 5 ++ .../global_mmlu_full_sv_college_medicine.yaml | 5 ++ .../global_mmlu_full_sv_college_physics.yaml | 5 ++ ...global_mmlu_full_sv_computer_security.yaml | 5 ++ ...lobal_mmlu_full_sv_conceptual_physics.yaml | 5 ++ .../sv/global_mmlu_full_sv_econometrics.yaml | 5 ++ ...l_mmlu_full_sv_electrical_engineering.yaml | 5 ++ ...l_mmlu_full_sv_elementary_mathematics.yaml | 5 ++ .../sv/global_mmlu_full_sv_formal_logic.yaml | 5 ++ .../sv/global_mmlu_full_sv_global_facts.yaml | 5 ++ ...obal_mmlu_full_sv_high_school_biology.yaml | 5 ++ ...al_mmlu_full_sv_high_school_chemistry.yaml | 5 ++ ..._full_sv_high_school_computer_science.yaml | 5 ++ ..._full_sv_high_school_european_history.yaml | 5 ++ ...al_mmlu_full_sv_high_school_geography.yaml | 5 ++ ...v_high_school_government_and_politics.yaml | 5 ++ ...lu_full_sv_high_school_macroeconomics.yaml | 5 ++ ..._mmlu_full_sv_high_school_mathematics.yaml | 5 ++ ...lu_full_sv_high_school_microeconomics.yaml | 5 ++ ...obal_mmlu_full_sv_high_school_physics.yaml | 5 ++ ...l_mmlu_full_sv_high_school_psychology.yaml | 5 ++ ...l_mmlu_full_sv_high_school_statistics.yaml | 5 ++ ...l_mmlu_full_sv_high_school_us_history.yaml | 5 ++ ...mlu_full_sv_high_school_world_history.yaml | 5 ++ .../sv/global_mmlu_full_sv_human_aging.yaml | 5 ++ .../global_mmlu_full_sv_human_sexuality.yaml | 5 ++ ...global_mmlu_full_sv_international_law.yaml | 5 ++ .../sv/global_mmlu_full_sv_jurisprudence.yaml | 5 ++ ...global_mmlu_full_sv_logical_fallacies.yaml | 5 ++ .../global_mmlu_full_sv_machine_learning.yaml | 5 ++ .../sv/global_mmlu_full_sv_management.yaml | 5 ++ .../sv/global_mmlu_full_sv_marketing.yaml | 5 ++ .../global_mmlu_full_sv_medical_genetics.yaml | 5 ++ .../sv/global_mmlu_full_sv_miscellaneous.yaml | 5 ++ .../global_mmlu_full_sv_moral_disputes.yaml | 5 ++ .../global_mmlu_full_sv_moral_scenarios.yaml | 5 ++ .../sv/global_mmlu_full_sv_nutrition.yaml | 5 ++ .../sv/global_mmlu_full_sv_philosophy.yaml | 5 ++ .../sv/global_mmlu_full_sv_prehistory.yaml | 5 ++ ..._mmlu_full_sv_professional_accounting.yaml | 5 ++ .../global_mmlu_full_sv_professional_law.yaml | 5 ++ ...al_mmlu_full_sv_professional_medicine.yaml | 5 ++ ..._mmlu_full_sv_professional_psychology.yaml | 5 ++ .../global_mmlu_full_sv_public_relations.yaml | 5 ++ .../global_mmlu_full_sv_security_studies.yaml | 5 ++ .../sv/global_mmlu_full_sv_sociology.yaml | 5 ++ ...global_mmlu_full_sv_us_foreign_policy.yaml | 5 ++ .../full/sv/global_mmlu_full_sv_virology.yaml | 5 ++ .../global_mmlu_full_sv_world_religions.yaml | 5 ++ lm_eval/tasks/global_mmlu/full/sv/utils.py | 73 +++++++++++++++++++ .../full/sw/_global_mmlu_full_sw.yaml | 11 +++ .../sw/_global_mmlu_full_sw_humanities.yaml | 8 ++ .../full/sw/_global_mmlu_full_sw_other.yaml | 8 ++ .../_global_mmlu_full_sw_social_sciences.yaml | 8 ++ .../full/sw/_global_mmlu_full_sw_stem.yaml | 8 ++ .../global_mmlu/full/sw/_sw_template_yaml | 16 ++++ .../global_mmlu_full_sw_abstract_algebra.yaml | 5 ++ .../full/sw/global_mmlu_full_sw_anatomy.yaml | 5 ++ .../sw/global_mmlu_full_sw_astronomy.yaml | 5 ++ .../global_mmlu_full_sw_business_ethics.yaml | 5 ++ ...lobal_mmlu_full_sw_clinical_knowledge.yaml | 5 ++ .../global_mmlu_full_sw_college_biology.yaml | 5 ++ ...global_mmlu_full_sw_college_chemistry.yaml | 5 ++ ...mmlu_full_sw_college_computer_science.yaml | 5 ++ ...obal_mmlu_full_sw_college_mathematics.yaml | 5 ++ .../global_mmlu_full_sw_college_medicine.yaml | 5 ++ .../global_mmlu_full_sw_college_physics.yaml | 5 ++ ...global_mmlu_full_sw_computer_security.yaml | 5 ++ ...lobal_mmlu_full_sw_conceptual_physics.yaml | 5 ++ .../sw/global_mmlu_full_sw_econometrics.yaml | 5 ++ ...l_mmlu_full_sw_electrical_engineering.yaml | 5 ++ ...l_mmlu_full_sw_elementary_mathematics.yaml | 5 ++ .../sw/global_mmlu_full_sw_formal_logic.yaml | 5 ++ .../sw/global_mmlu_full_sw_global_facts.yaml | 5 ++ ...obal_mmlu_full_sw_high_school_biology.yaml | 5 ++ ...al_mmlu_full_sw_high_school_chemistry.yaml | 5 ++ ..._full_sw_high_school_computer_science.yaml | 5 ++ ..._full_sw_high_school_european_history.yaml | 5 ++ ...al_mmlu_full_sw_high_school_geography.yaml | 5 ++ ...w_high_school_government_and_politics.yaml | 5 ++ ...lu_full_sw_high_school_macroeconomics.yaml | 5 ++ ..._mmlu_full_sw_high_school_mathematics.yaml | 5 ++ ...lu_full_sw_high_school_microeconomics.yaml | 5 ++ ...obal_mmlu_full_sw_high_school_physics.yaml | 5 ++ ...l_mmlu_full_sw_high_school_psychology.yaml | 5 ++ ...l_mmlu_full_sw_high_school_statistics.yaml | 5 ++ ...l_mmlu_full_sw_high_school_us_history.yaml | 5 ++ ...mlu_full_sw_high_school_world_history.yaml | 5 ++ .../sw/global_mmlu_full_sw_human_aging.yaml | 5 ++ .../global_mmlu_full_sw_human_sexuality.yaml | 5 ++ ...global_mmlu_full_sw_international_law.yaml | 5 ++ .../sw/global_mmlu_full_sw_jurisprudence.yaml | 5 ++ ...global_mmlu_full_sw_logical_fallacies.yaml | 5 ++ .../global_mmlu_full_sw_machine_learning.yaml | 5 ++ .../sw/global_mmlu_full_sw_management.yaml | 5 ++ .../sw/global_mmlu_full_sw_marketing.yaml | 5 ++ .../global_mmlu_full_sw_medical_genetics.yaml | 5 ++ .../sw/global_mmlu_full_sw_miscellaneous.yaml | 5 ++ .../global_mmlu_full_sw_moral_disputes.yaml | 5 ++ .../global_mmlu_full_sw_moral_scenarios.yaml | 5 ++ .../sw/global_mmlu_full_sw_nutrition.yaml | 5 ++ .../sw/global_mmlu_full_sw_philosophy.yaml | 5 ++ .../sw/global_mmlu_full_sw_prehistory.yaml | 5 ++ ..._mmlu_full_sw_professional_accounting.yaml | 5 ++ .../global_mmlu_full_sw_professional_law.yaml | 5 ++ ...al_mmlu_full_sw_professional_medicine.yaml | 5 ++ ..._mmlu_full_sw_professional_psychology.yaml | 5 ++ .../global_mmlu_full_sw_public_relations.yaml | 5 ++ .../global_mmlu_full_sw_security_studies.yaml | 5 ++ .../sw/global_mmlu_full_sw_sociology.yaml | 5 ++ ...global_mmlu_full_sw_us_foreign_policy.yaml | 5 ++ .../full/sw/global_mmlu_full_sw_virology.yaml | 5 ++ .../global_mmlu_full_sw_world_religions.yaml | 5 ++ lm_eval/tasks/global_mmlu/full/sw/utils.py | 73 +++++++++++++++++++ .../full/te/_global_mmlu_full_te.yaml | 11 +++ .../te/_global_mmlu_full_te_humanities.yaml | 8 ++ .../full/te/_global_mmlu_full_te_other.yaml | 8 ++ .../_global_mmlu_full_te_social_sciences.yaml | 8 ++ .../full/te/_global_mmlu_full_te_stem.yaml | 8 ++ .../global_mmlu/full/te/_te_template_yaml | 16 ++++ .../global_mmlu_full_te_abstract_algebra.yaml | 5 ++ .../full/te/global_mmlu_full_te_anatomy.yaml | 5 ++ .../te/global_mmlu_full_te_astronomy.yaml | 5 ++ .../global_mmlu_full_te_business_ethics.yaml | 5 ++ ...lobal_mmlu_full_te_clinical_knowledge.yaml | 5 ++ .../global_mmlu_full_te_college_biology.yaml | 5 ++ ...global_mmlu_full_te_college_chemistry.yaml | 5 ++ ...mmlu_full_te_college_computer_science.yaml | 5 ++ ...obal_mmlu_full_te_college_mathematics.yaml | 5 ++ .../global_mmlu_full_te_college_medicine.yaml | 5 ++ .../global_mmlu_full_te_college_physics.yaml | 5 ++ ...global_mmlu_full_te_computer_security.yaml | 5 ++ ...lobal_mmlu_full_te_conceptual_physics.yaml | 5 ++ .../te/global_mmlu_full_te_econometrics.yaml | 5 ++ ...l_mmlu_full_te_electrical_engineering.yaml | 5 ++ ...l_mmlu_full_te_elementary_mathematics.yaml | 5 ++ .../te/global_mmlu_full_te_formal_logic.yaml | 5 ++ .../te/global_mmlu_full_te_global_facts.yaml | 5 ++ ...obal_mmlu_full_te_high_school_biology.yaml | 5 ++ ...al_mmlu_full_te_high_school_chemistry.yaml | 5 ++ ..._full_te_high_school_computer_science.yaml | 5 ++ ..._full_te_high_school_european_history.yaml | 5 ++ ...al_mmlu_full_te_high_school_geography.yaml | 5 ++ ...e_high_school_government_and_politics.yaml | 5 ++ ...lu_full_te_high_school_macroeconomics.yaml | 5 ++ ..._mmlu_full_te_high_school_mathematics.yaml | 5 ++ ...lu_full_te_high_school_microeconomics.yaml | 5 ++ ...obal_mmlu_full_te_high_school_physics.yaml | 5 ++ ...l_mmlu_full_te_high_school_psychology.yaml | 5 ++ ...l_mmlu_full_te_high_school_statistics.yaml | 5 ++ ...l_mmlu_full_te_high_school_us_history.yaml | 5 ++ ...mlu_full_te_high_school_world_history.yaml | 5 ++ .../te/global_mmlu_full_te_human_aging.yaml | 5 ++ .../global_mmlu_full_te_human_sexuality.yaml | 5 ++ ...global_mmlu_full_te_international_law.yaml | 5 ++ .../te/global_mmlu_full_te_jurisprudence.yaml | 5 ++ ...global_mmlu_full_te_logical_fallacies.yaml | 5 ++ .../global_mmlu_full_te_machine_learning.yaml | 5 ++ .../te/global_mmlu_full_te_management.yaml | 5 ++ .../te/global_mmlu_full_te_marketing.yaml | 5 ++ .../global_mmlu_full_te_medical_genetics.yaml | 5 ++ .../te/global_mmlu_full_te_miscellaneous.yaml | 5 ++ .../global_mmlu_full_te_moral_disputes.yaml | 5 ++ .../global_mmlu_full_te_moral_scenarios.yaml | 5 ++ .../te/global_mmlu_full_te_nutrition.yaml | 5 ++ .../te/global_mmlu_full_te_philosophy.yaml | 5 ++ .../te/global_mmlu_full_te_prehistory.yaml | 5 ++ ..._mmlu_full_te_professional_accounting.yaml | 5 ++ .../global_mmlu_full_te_professional_law.yaml | 5 ++ ...al_mmlu_full_te_professional_medicine.yaml | 5 ++ ..._mmlu_full_te_professional_psychology.yaml | 5 ++ .../global_mmlu_full_te_public_relations.yaml | 5 ++ .../global_mmlu_full_te_security_studies.yaml | 5 ++ .../te/global_mmlu_full_te_sociology.yaml | 5 ++ ...global_mmlu_full_te_us_foreign_policy.yaml | 5 ++ .../full/te/global_mmlu_full_te_virology.yaml | 5 ++ .../global_mmlu_full_te_world_religions.yaml | 5 ++ lm_eval/tasks/global_mmlu/full/te/utils.py | 73 +++++++++++++++++++ .../full/tr/_global_mmlu_full_tr.yaml | 11 +++ .../tr/_global_mmlu_full_tr_humanities.yaml | 8 ++ .../full/tr/_global_mmlu_full_tr_other.yaml | 8 ++ .../_global_mmlu_full_tr_social_sciences.yaml | 8 ++ .../full/tr/_global_mmlu_full_tr_stem.yaml | 8 ++ .../global_mmlu/full/tr/_tr_template_yaml | 16 ++++ .../global_mmlu_full_tr_abstract_algebra.yaml | 5 ++ .../full/tr/global_mmlu_full_tr_anatomy.yaml | 5 ++ .../tr/global_mmlu_full_tr_astronomy.yaml | 5 ++ .../global_mmlu_full_tr_business_ethics.yaml | 5 ++ ...lobal_mmlu_full_tr_clinical_knowledge.yaml | 5 ++ .../global_mmlu_full_tr_college_biology.yaml | 5 ++ ...global_mmlu_full_tr_college_chemistry.yaml | 5 ++ ...mmlu_full_tr_college_computer_science.yaml | 5 ++ ...obal_mmlu_full_tr_college_mathematics.yaml | 5 ++ .../global_mmlu_full_tr_college_medicine.yaml | 5 ++ .../global_mmlu_full_tr_college_physics.yaml | 5 ++ ...global_mmlu_full_tr_computer_security.yaml | 5 ++ ...lobal_mmlu_full_tr_conceptual_physics.yaml | 5 ++ .../tr/global_mmlu_full_tr_econometrics.yaml | 5 ++ ...l_mmlu_full_tr_electrical_engineering.yaml | 5 ++ ...l_mmlu_full_tr_elementary_mathematics.yaml | 5 ++ .../tr/global_mmlu_full_tr_formal_logic.yaml | 5 ++ .../tr/global_mmlu_full_tr_global_facts.yaml | 5 ++ ...obal_mmlu_full_tr_high_school_biology.yaml | 5 ++ ...al_mmlu_full_tr_high_school_chemistry.yaml | 5 ++ ..._full_tr_high_school_computer_science.yaml | 5 ++ ..._full_tr_high_school_european_history.yaml | 5 ++ ...al_mmlu_full_tr_high_school_geography.yaml | 5 ++ ...r_high_school_government_and_politics.yaml | 5 ++ ...lu_full_tr_high_school_macroeconomics.yaml | 5 ++ ..._mmlu_full_tr_high_school_mathematics.yaml | 5 ++ ...lu_full_tr_high_school_microeconomics.yaml | 5 ++ ...obal_mmlu_full_tr_high_school_physics.yaml | 5 ++ ...l_mmlu_full_tr_high_school_psychology.yaml | 5 ++ ...l_mmlu_full_tr_high_school_statistics.yaml | 5 ++ ...l_mmlu_full_tr_high_school_us_history.yaml | 5 ++ ...mlu_full_tr_high_school_world_history.yaml | 5 ++ .../tr/global_mmlu_full_tr_human_aging.yaml | 5 ++ .../global_mmlu_full_tr_human_sexuality.yaml | 5 ++ ...global_mmlu_full_tr_international_law.yaml | 5 ++ .../tr/global_mmlu_full_tr_jurisprudence.yaml | 5 ++ ...global_mmlu_full_tr_logical_fallacies.yaml | 5 ++ .../global_mmlu_full_tr_machine_learning.yaml | 5 ++ .../tr/global_mmlu_full_tr_management.yaml | 5 ++ .../tr/global_mmlu_full_tr_marketing.yaml | 5 ++ .../global_mmlu_full_tr_medical_genetics.yaml | 5 ++ .../tr/global_mmlu_full_tr_miscellaneous.yaml | 5 ++ .../global_mmlu_full_tr_moral_disputes.yaml | 5 ++ .../global_mmlu_full_tr_moral_scenarios.yaml | 5 ++ .../tr/global_mmlu_full_tr_nutrition.yaml | 5 ++ .../tr/global_mmlu_full_tr_philosophy.yaml | 5 ++ .../tr/global_mmlu_full_tr_prehistory.yaml | 5 ++ ..._mmlu_full_tr_professional_accounting.yaml | 5 ++ .../global_mmlu_full_tr_professional_law.yaml | 5 ++ ...al_mmlu_full_tr_professional_medicine.yaml | 5 ++ ..._mmlu_full_tr_professional_psychology.yaml | 5 ++ .../global_mmlu_full_tr_public_relations.yaml | 5 ++ .../global_mmlu_full_tr_security_studies.yaml | 5 ++ .../tr/global_mmlu_full_tr_sociology.yaml | 5 ++ ...global_mmlu_full_tr_us_foreign_policy.yaml | 5 ++ .../full/tr/global_mmlu_full_tr_virology.yaml | 5 ++ .../global_mmlu_full_tr_world_religions.yaml | 5 ++ lm_eval/tasks/global_mmlu/full/tr/utils.py | 73 +++++++++++++++++++ .../full/uk/_global_mmlu_full_uk.yaml | 11 +++ .../uk/_global_mmlu_full_uk_humanities.yaml | 8 ++ .../full/uk/_global_mmlu_full_uk_other.yaml | 8 ++ .../_global_mmlu_full_uk_social_sciences.yaml | 8 ++ .../full/uk/_global_mmlu_full_uk_stem.yaml | 8 ++ .../global_mmlu/full/uk/_uk_template_yaml | 16 ++++ .../global_mmlu_full_uk_abstract_algebra.yaml | 5 ++ .../full/uk/global_mmlu_full_uk_anatomy.yaml | 5 ++ .../uk/global_mmlu_full_uk_astronomy.yaml | 5 ++ .../global_mmlu_full_uk_business_ethics.yaml | 5 ++ ...lobal_mmlu_full_uk_clinical_knowledge.yaml | 5 ++ .../global_mmlu_full_uk_college_biology.yaml | 5 ++ ...global_mmlu_full_uk_college_chemistry.yaml | 5 ++ ...mmlu_full_uk_college_computer_science.yaml | 5 ++ ...obal_mmlu_full_uk_college_mathematics.yaml | 5 ++ .../global_mmlu_full_uk_college_medicine.yaml | 5 ++ .../global_mmlu_full_uk_college_physics.yaml | 5 ++ ...global_mmlu_full_uk_computer_security.yaml | 5 ++ ...lobal_mmlu_full_uk_conceptual_physics.yaml | 5 ++ .../uk/global_mmlu_full_uk_econometrics.yaml | 5 ++ ...l_mmlu_full_uk_electrical_engineering.yaml | 5 ++ ...l_mmlu_full_uk_elementary_mathematics.yaml | 5 ++ .../uk/global_mmlu_full_uk_formal_logic.yaml | 5 ++ .../uk/global_mmlu_full_uk_global_facts.yaml | 5 ++ ...obal_mmlu_full_uk_high_school_biology.yaml | 5 ++ ...al_mmlu_full_uk_high_school_chemistry.yaml | 5 ++ ..._full_uk_high_school_computer_science.yaml | 5 ++ ..._full_uk_high_school_european_history.yaml | 5 ++ ...al_mmlu_full_uk_high_school_geography.yaml | 5 ++ ...k_high_school_government_and_politics.yaml | 5 ++ ...lu_full_uk_high_school_macroeconomics.yaml | 5 ++ ..._mmlu_full_uk_high_school_mathematics.yaml | 5 ++ ...lu_full_uk_high_school_microeconomics.yaml | 5 ++ ...obal_mmlu_full_uk_high_school_physics.yaml | 5 ++ ...l_mmlu_full_uk_high_school_psychology.yaml | 5 ++ ...l_mmlu_full_uk_high_school_statistics.yaml | 5 ++ ...l_mmlu_full_uk_high_school_us_history.yaml | 5 ++ ...mlu_full_uk_high_school_world_history.yaml | 5 ++ .../uk/global_mmlu_full_uk_human_aging.yaml | 5 ++ .../global_mmlu_full_uk_human_sexuality.yaml | 5 ++ ...global_mmlu_full_uk_international_law.yaml | 5 ++ .../uk/global_mmlu_full_uk_jurisprudence.yaml | 5 ++ ...global_mmlu_full_uk_logical_fallacies.yaml | 5 ++ .../global_mmlu_full_uk_machine_learning.yaml | 5 ++ .../uk/global_mmlu_full_uk_management.yaml | 5 ++ .../uk/global_mmlu_full_uk_marketing.yaml | 5 ++ .../global_mmlu_full_uk_medical_genetics.yaml | 5 ++ .../uk/global_mmlu_full_uk_miscellaneous.yaml | 5 ++ .../global_mmlu_full_uk_moral_disputes.yaml | 5 ++ .../global_mmlu_full_uk_moral_scenarios.yaml | 5 ++ .../uk/global_mmlu_full_uk_nutrition.yaml | 5 ++ .../uk/global_mmlu_full_uk_philosophy.yaml | 5 ++ .../uk/global_mmlu_full_uk_prehistory.yaml | 5 ++ ..._mmlu_full_uk_professional_accounting.yaml | 5 ++ .../global_mmlu_full_uk_professional_law.yaml | 5 ++ ...al_mmlu_full_uk_professional_medicine.yaml | 5 ++ ..._mmlu_full_uk_professional_psychology.yaml | 5 ++ .../global_mmlu_full_uk_public_relations.yaml | 5 ++ .../global_mmlu_full_uk_security_studies.yaml | 5 ++ .../uk/global_mmlu_full_uk_sociology.yaml | 5 ++ ...global_mmlu_full_uk_us_foreign_policy.yaml | 5 ++ .../full/uk/global_mmlu_full_uk_virology.yaml | 5 ++ .../global_mmlu_full_uk_world_religions.yaml | 5 ++ lm_eval/tasks/global_mmlu/full/uk/utils.py | 73 +++++++++++++++++++ .../full/vi/_global_mmlu_full_vi.yaml | 11 +++ .../vi/_global_mmlu_full_vi_humanities.yaml | 8 ++ .../full/vi/_global_mmlu_full_vi_other.yaml | 8 ++ .../_global_mmlu_full_vi_social_sciences.yaml | 8 ++ .../full/vi/_global_mmlu_full_vi_stem.yaml | 8 ++ .../global_mmlu/full/vi/_vi_template_yaml | 16 ++++ .../global_mmlu_full_vi_abstract_algebra.yaml | 5 ++ .../full/vi/global_mmlu_full_vi_anatomy.yaml | 5 ++ .../vi/global_mmlu_full_vi_astronomy.yaml | 5 ++ .../global_mmlu_full_vi_business_ethics.yaml | 5 ++ ...lobal_mmlu_full_vi_clinical_knowledge.yaml | 5 ++ .../global_mmlu_full_vi_college_biology.yaml | 5 ++ ...global_mmlu_full_vi_college_chemistry.yaml | 5 ++ ...mmlu_full_vi_college_computer_science.yaml | 5 ++ ...obal_mmlu_full_vi_college_mathematics.yaml | 5 ++ .../global_mmlu_full_vi_college_medicine.yaml | 5 ++ .../global_mmlu_full_vi_college_physics.yaml | 5 ++ ...global_mmlu_full_vi_computer_security.yaml | 5 ++ ...lobal_mmlu_full_vi_conceptual_physics.yaml | 5 ++ .../vi/global_mmlu_full_vi_econometrics.yaml | 5 ++ ...l_mmlu_full_vi_electrical_engineering.yaml | 5 ++ ...l_mmlu_full_vi_elementary_mathematics.yaml | 5 ++ .../vi/global_mmlu_full_vi_formal_logic.yaml | 5 ++ .../vi/global_mmlu_full_vi_global_facts.yaml | 5 ++ ...obal_mmlu_full_vi_high_school_biology.yaml | 5 ++ ...al_mmlu_full_vi_high_school_chemistry.yaml | 5 ++ ..._full_vi_high_school_computer_science.yaml | 5 ++ ..._full_vi_high_school_european_history.yaml | 5 ++ ...al_mmlu_full_vi_high_school_geography.yaml | 5 ++ ...i_high_school_government_and_politics.yaml | 5 ++ ...lu_full_vi_high_school_macroeconomics.yaml | 5 ++ ..._mmlu_full_vi_high_school_mathematics.yaml | 5 ++ ...lu_full_vi_high_school_microeconomics.yaml | 5 ++ ...obal_mmlu_full_vi_high_school_physics.yaml | 5 ++ ...l_mmlu_full_vi_high_school_psychology.yaml | 5 ++ ...l_mmlu_full_vi_high_school_statistics.yaml | 5 ++ ...l_mmlu_full_vi_high_school_us_history.yaml | 5 ++ ...mlu_full_vi_high_school_world_history.yaml | 5 ++ .../vi/global_mmlu_full_vi_human_aging.yaml | 5 ++ .../global_mmlu_full_vi_human_sexuality.yaml | 5 ++ ...global_mmlu_full_vi_international_law.yaml | 5 ++ .../vi/global_mmlu_full_vi_jurisprudence.yaml | 5 ++ ...global_mmlu_full_vi_logical_fallacies.yaml | 5 ++ .../global_mmlu_full_vi_machine_learning.yaml | 5 ++ .../vi/global_mmlu_full_vi_management.yaml | 5 ++ .../vi/global_mmlu_full_vi_marketing.yaml | 5 ++ .../global_mmlu_full_vi_medical_genetics.yaml | 5 ++ .../vi/global_mmlu_full_vi_miscellaneous.yaml | 5 ++ .../global_mmlu_full_vi_moral_disputes.yaml | 5 ++ .../global_mmlu_full_vi_moral_scenarios.yaml | 5 ++ .../vi/global_mmlu_full_vi_nutrition.yaml | 5 ++ .../vi/global_mmlu_full_vi_philosophy.yaml | 5 ++ .../vi/global_mmlu_full_vi_prehistory.yaml | 5 ++ ..._mmlu_full_vi_professional_accounting.yaml | 5 ++ .../global_mmlu_full_vi_professional_law.yaml | 5 ++ ...al_mmlu_full_vi_professional_medicine.yaml | 5 ++ ..._mmlu_full_vi_professional_psychology.yaml | 5 ++ .../global_mmlu_full_vi_public_relations.yaml | 5 ++ .../global_mmlu_full_vi_security_studies.yaml | 5 ++ .../vi/global_mmlu_full_vi_sociology.yaml | 5 ++ ...global_mmlu_full_vi_us_foreign_policy.yaml | 5 ++ .../full/vi/global_mmlu_full_vi_virology.yaml | 5 ++ .../global_mmlu_full_vi_world_religions.yaml | 5 ++ lm_eval/tasks/global_mmlu/full/vi/utils.py | 73 +++++++++++++++++++ .../full/yo/_global_mmlu_full_yo.yaml | 11 +++ .../yo/_global_mmlu_full_yo_humanities.yaml | 8 ++ .../full/yo/_global_mmlu_full_yo_other.yaml | 8 ++ .../_global_mmlu_full_yo_social_sciences.yaml | 8 ++ .../full/yo/_global_mmlu_full_yo_stem.yaml | 8 ++ .../global_mmlu/full/yo/_yo_template_yaml | 16 ++++ .../global_mmlu_full_yo_abstract_algebra.yaml | 5 ++ .../full/yo/global_mmlu_full_yo_anatomy.yaml | 5 ++ .../yo/global_mmlu_full_yo_astronomy.yaml | 5 ++ .../global_mmlu_full_yo_business_ethics.yaml | 5 ++ ...lobal_mmlu_full_yo_clinical_knowledge.yaml | 5 ++ .../global_mmlu_full_yo_college_biology.yaml | 5 ++ ...global_mmlu_full_yo_college_chemistry.yaml | 5 ++ ...mmlu_full_yo_college_computer_science.yaml | 5 ++ ...obal_mmlu_full_yo_college_mathematics.yaml | 5 ++ .../global_mmlu_full_yo_college_medicine.yaml | 5 ++ .../global_mmlu_full_yo_college_physics.yaml | 5 ++ ...global_mmlu_full_yo_computer_security.yaml | 5 ++ ...lobal_mmlu_full_yo_conceptual_physics.yaml | 5 ++ .../yo/global_mmlu_full_yo_econometrics.yaml | 5 ++ ...l_mmlu_full_yo_electrical_engineering.yaml | 5 ++ ...l_mmlu_full_yo_elementary_mathematics.yaml | 5 ++ .../yo/global_mmlu_full_yo_formal_logic.yaml | 5 ++ .../yo/global_mmlu_full_yo_global_facts.yaml | 5 ++ ...obal_mmlu_full_yo_high_school_biology.yaml | 5 ++ ...al_mmlu_full_yo_high_school_chemistry.yaml | 5 ++ ..._full_yo_high_school_computer_science.yaml | 5 ++ ..._full_yo_high_school_european_history.yaml | 5 ++ ...al_mmlu_full_yo_high_school_geography.yaml | 5 ++ ...o_high_school_government_and_politics.yaml | 5 ++ ...lu_full_yo_high_school_macroeconomics.yaml | 5 ++ ..._mmlu_full_yo_high_school_mathematics.yaml | 5 ++ ...lu_full_yo_high_school_microeconomics.yaml | 5 ++ ...obal_mmlu_full_yo_high_school_physics.yaml | 5 ++ ...l_mmlu_full_yo_high_school_psychology.yaml | 5 ++ ...l_mmlu_full_yo_high_school_statistics.yaml | 5 ++ ...l_mmlu_full_yo_high_school_us_history.yaml | 5 ++ ...mlu_full_yo_high_school_world_history.yaml | 5 ++ .../yo/global_mmlu_full_yo_human_aging.yaml | 5 ++ .../global_mmlu_full_yo_human_sexuality.yaml | 5 ++ ...global_mmlu_full_yo_international_law.yaml | 5 ++ .../yo/global_mmlu_full_yo_jurisprudence.yaml | 5 ++ ...global_mmlu_full_yo_logical_fallacies.yaml | 5 ++ .../global_mmlu_full_yo_machine_learning.yaml | 5 ++ .../yo/global_mmlu_full_yo_management.yaml | 5 ++ .../yo/global_mmlu_full_yo_marketing.yaml | 5 ++ .../global_mmlu_full_yo_medical_genetics.yaml | 5 ++ .../yo/global_mmlu_full_yo_miscellaneous.yaml | 5 ++ .../global_mmlu_full_yo_moral_disputes.yaml | 5 ++ .../global_mmlu_full_yo_moral_scenarios.yaml | 5 ++ .../yo/global_mmlu_full_yo_nutrition.yaml | 5 ++ .../yo/global_mmlu_full_yo_philosophy.yaml | 5 ++ .../yo/global_mmlu_full_yo_prehistory.yaml | 5 ++ ..._mmlu_full_yo_professional_accounting.yaml | 5 ++ .../global_mmlu_full_yo_professional_law.yaml | 5 ++ ...al_mmlu_full_yo_professional_medicine.yaml | 5 ++ ..._mmlu_full_yo_professional_psychology.yaml | 5 ++ .../global_mmlu_full_yo_public_relations.yaml | 5 ++ .../global_mmlu_full_yo_security_studies.yaml | 5 ++ .../yo/global_mmlu_full_yo_sociology.yaml | 5 ++ ...global_mmlu_full_yo_us_foreign_policy.yaml | 5 ++ .../full/yo/global_mmlu_full_yo_virology.yaml | 5 ++ .../global_mmlu_full_yo_world_religions.yaml | 5 ++ lm_eval/tasks/global_mmlu/full/yo/utils.py | 73 +++++++++++++++++++ .../full/zh/_global_mmlu_full_zh.yaml | 11 +++ .../zh/_global_mmlu_full_zh_humanities.yaml | 8 ++ .../full/zh/_global_mmlu_full_zh_other.yaml | 8 ++ .../_global_mmlu_full_zh_social_sciences.yaml | 8 ++ .../full/zh/_global_mmlu_full_zh_stem.yaml | 8 ++ .../global_mmlu/full/zh/_zh_template_yaml | 16 ++++ .../global_mmlu_full_zh_abstract_algebra.yaml | 5 ++ .../full/zh/global_mmlu_full_zh_anatomy.yaml | 5 ++ .../zh/global_mmlu_full_zh_astronomy.yaml | 5 ++ .../global_mmlu_full_zh_business_ethics.yaml | 5 ++ ...lobal_mmlu_full_zh_clinical_knowledge.yaml | 5 ++ .../global_mmlu_full_zh_college_biology.yaml | 5 ++ ...global_mmlu_full_zh_college_chemistry.yaml | 5 ++ ...mmlu_full_zh_college_computer_science.yaml | 5 ++ ...obal_mmlu_full_zh_college_mathematics.yaml | 5 ++ .../global_mmlu_full_zh_college_medicine.yaml | 5 ++ .../global_mmlu_full_zh_college_physics.yaml | 5 ++ ...global_mmlu_full_zh_computer_security.yaml | 5 ++ ...lobal_mmlu_full_zh_conceptual_physics.yaml | 5 ++ .../zh/global_mmlu_full_zh_econometrics.yaml | 5 ++ ...l_mmlu_full_zh_electrical_engineering.yaml | 5 ++ ...l_mmlu_full_zh_elementary_mathematics.yaml | 5 ++ .../zh/global_mmlu_full_zh_formal_logic.yaml | 5 ++ .../zh/global_mmlu_full_zh_global_facts.yaml | 5 ++ ...obal_mmlu_full_zh_high_school_biology.yaml | 5 ++ ...al_mmlu_full_zh_high_school_chemistry.yaml | 5 ++ ..._full_zh_high_school_computer_science.yaml | 5 ++ ..._full_zh_high_school_european_history.yaml | 5 ++ ...al_mmlu_full_zh_high_school_geography.yaml | 5 ++ ...h_high_school_government_and_politics.yaml | 5 ++ ...lu_full_zh_high_school_macroeconomics.yaml | 5 ++ ..._mmlu_full_zh_high_school_mathematics.yaml | 5 ++ ...lu_full_zh_high_school_microeconomics.yaml | 5 ++ ...obal_mmlu_full_zh_high_school_physics.yaml | 5 ++ ...l_mmlu_full_zh_high_school_psychology.yaml | 5 ++ ...l_mmlu_full_zh_high_school_statistics.yaml | 5 ++ ...l_mmlu_full_zh_high_school_us_history.yaml | 5 ++ ...mlu_full_zh_high_school_world_history.yaml | 5 ++ .../zh/global_mmlu_full_zh_human_aging.yaml | 5 ++ .../global_mmlu_full_zh_human_sexuality.yaml | 5 ++ ...global_mmlu_full_zh_international_law.yaml | 5 ++ .../zh/global_mmlu_full_zh_jurisprudence.yaml | 5 ++ ...global_mmlu_full_zh_logical_fallacies.yaml | 5 ++ .../global_mmlu_full_zh_machine_learning.yaml | 5 ++ .../zh/global_mmlu_full_zh_management.yaml | 5 ++ .../zh/global_mmlu_full_zh_marketing.yaml | 5 ++ .../global_mmlu_full_zh_medical_genetics.yaml | 5 ++ .../zh/global_mmlu_full_zh_miscellaneous.yaml | 5 ++ .../global_mmlu_full_zh_moral_disputes.yaml | 5 ++ .../global_mmlu_full_zh_moral_scenarios.yaml | 5 ++ .../zh/global_mmlu_full_zh_nutrition.yaml | 5 ++ .../zh/global_mmlu_full_zh_philosophy.yaml | 5 ++ .../zh/global_mmlu_full_zh_prehistory.yaml | 5 ++ ..._mmlu_full_zh_professional_accounting.yaml | 5 ++ .../global_mmlu_full_zh_professional_law.yaml | 5 ++ ...al_mmlu_full_zh_professional_medicine.yaml | 5 ++ ..._mmlu_full_zh_professional_psychology.yaml | 5 ++ .../global_mmlu_full_zh_public_relations.yaml | 5 ++ .../global_mmlu_full_zh_security_studies.yaml | 5 ++ .../zh/global_mmlu_full_zh_sociology.yaml | 5 ++ ...global_mmlu_full_zh_us_foreign_policy.yaml | 5 ++ .../full/zh/global_mmlu_full_zh_virology.yaml | 5 ++ .../global_mmlu_full_zh_world_religions.yaml | 5 ++ lm_eval/tasks/global_mmlu/full/zh/utils.py | 73 +++++++++++++++++++ 2706 files changed, 17532 insertions(+), 1 deletion(-) rename lm_eval/tasks/global_mmlu/{ => default}/_default_yaml (100%) rename lm_eval/tasks/global_mmlu/{ => default}/_generate_configs.py (100%) rename lm_eval/tasks/global_mmlu/{ => default}/global_mmlu_ar.yaml (100%) rename lm_eval/tasks/global_mmlu/{ => default}/global_mmlu_bn.yaml (100%) rename lm_eval/tasks/global_mmlu/{ => default}/global_mmlu_de.yaml (100%) rename lm_eval/tasks/global_mmlu/{ => default}/global_mmlu_en.yaml (100%) rename lm_eval/tasks/global_mmlu/{ => default}/global_mmlu_es.yaml (100%) rename lm_eval/tasks/global_mmlu/{ => default}/global_mmlu_fr.yaml (100%) rename lm_eval/tasks/global_mmlu/{ => default}/global_mmlu_hi.yaml (100%) rename lm_eval/tasks/global_mmlu/{ => default}/global_mmlu_id.yaml (100%) rename lm_eval/tasks/global_mmlu/{ => default}/global_mmlu_it.yaml (100%) rename lm_eval/tasks/global_mmlu/{ => default}/global_mmlu_ja.yaml (100%) rename lm_eval/tasks/global_mmlu/{ => default}/global_mmlu_ko.yaml (100%) rename lm_eval/tasks/global_mmlu/{ => default}/global_mmlu_pt.yaml (100%) rename lm_eval/tasks/global_mmlu/{ => default}/global_mmlu_sw.yaml (100%) rename lm_eval/tasks/global_mmlu/{ => default}/global_mmlu_yo.yaml (100%) rename lm_eval/tasks/global_mmlu/{ => default}/global_mmlu_zh.yaml (100%) create mode 100644 lm_eval/tasks/global_mmlu/full/am/_am_template_yaml create mode 100644 lm_eval/tasks/global_mmlu/full/am/_global_mmlu_full_am.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/am/_global_mmlu_full_am_humanities.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/am/_global_mmlu_full_am_other.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/am/_global_mmlu_full_am_social_sciences.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/am/_global_mmlu_full_am_stem.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_abstract_algebra.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_anatomy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_astronomy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_business_ethics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_clinical_knowledge.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_college_biology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_college_chemistry.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_college_computer_science.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_college_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_college_medicine.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_college_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_computer_security.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_conceptual_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_econometrics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_electrical_engineering.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_elementary_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_formal_logic.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_global_facts.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_high_school_biology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_high_school_chemistry.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_high_school_computer_science.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_high_school_european_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_high_school_geography.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_high_school_government_and_politics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_high_school_macroeconomics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_high_school_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_high_school_microeconomics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_high_school_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_high_school_psychology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_high_school_statistics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_high_school_us_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_high_school_world_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_human_aging.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_human_sexuality.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_international_law.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_jurisprudence.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_logical_fallacies.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_machine_learning.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_management.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_marketing.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_medical_genetics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_miscellaneous.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_moral_disputes.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_moral_scenarios.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_nutrition.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_philosophy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_prehistory.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_professional_accounting.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_professional_law.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_professional_medicine.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_professional_psychology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_public_relations.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_security_studies.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_sociology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_us_foreign_policy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_virology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_world_religions.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/am/utils.py create mode 100644 lm_eval/tasks/global_mmlu/full/ar/_ar_template_yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ar/_global_mmlu_full_ar.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ar/_global_mmlu_full_ar_humanities.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ar/_global_mmlu_full_ar_other.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ar/_global_mmlu_full_ar_social_sciences.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ar/_global_mmlu_full_ar_stem.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_abstract_algebra.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_anatomy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_astronomy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_business_ethics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_clinical_knowledge.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_college_biology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_college_chemistry.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_college_computer_science.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_college_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_college_medicine.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_college_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_computer_security.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_conceptual_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_econometrics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_electrical_engineering.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_elementary_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_formal_logic.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_global_facts.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_high_school_biology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_high_school_chemistry.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_high_school_computer_science.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_high_school_european_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_high_school_geography.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_high_school_government_and_politics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_high_school_macroeconomics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_high_school_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_high_school_microeconomics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_high_school_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_high_school_psychology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_high_school_statistics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_high_school_us_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_high_school_world_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_human_aging.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_human_sexuality.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_international_law.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_jurisprudence.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_logical_fallacies.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_machine_learning.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_management.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_marketing.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_medical_genetics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_miscellaneous.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_moral_disputes.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_moral_scenarios.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_nutrition.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_philosophy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_prehistory.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_professional_accounting.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_professional_law.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_professional_medicine.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_professional_psychology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_public_relations.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_security_studies.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_sociology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_us_foreign_policy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_virology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_world_religions.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ar/utils.py create mode 100644 lm_eval/tasks/global_mmlu/full/bn/_bn_template_yaml create mode 100644 lm_eval/tasks/global_mmlu/full/bn/_global_mmlu_full_bn.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/bn/_global_mmlu_full_bn_humanities.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/bn/_global_mmlu_full_bn_other.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/bn/_global_mmlu_full_bn_social_sciences.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/bn/_global_mmlu_full_bn_stem.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_abstract_algebra.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_anatomy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_astronomy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_business_ethics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_clinical_knowledge.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_college_biology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_college_chemistry.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_college_computer_science.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_college_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_college_medicine.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_college_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_computer_security.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_conceptual_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_econometrics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_electrical_engineering.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_elementary_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_formal_logic.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_global_facts.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_high_school_biology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_high_school_chemistry.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_high_school_computer_science.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_high_school_european_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_high_school_geography.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_high_school_government_and_politics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_high_school_macroeconomics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_high_school_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_high_school_microeconomics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_high_school_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_high_school_psychology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_high_school_statistics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_high_school_us_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_high_school_world_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_human_aging.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_human_sexuality.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_international_law.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_jurisprudence.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_logical_fallacies.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_machine_learning.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_management.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_marketing.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_medical_genetics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_miscellaneous.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_moral_disputes.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_moral_scenarios.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_nutrition.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_philosophy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_prehistory.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_professional_accounting.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_professional_law.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_professional_medicine.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_professional_psychology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_public_relations.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_security_studies.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_sociology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_us_foreign_policy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_virology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_world_religions.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/bn/utils.py create mode 100644 lm_eval/tasks/global_mmlu/full/cs/_cs_template_yaml create mode 100644 lm_eval/tasks/global_mmlu/full/cs/_global_mmlu_full_cs.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/cs/_global_mmlu_full_cs_humanities.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/cs/_global_mmlu_full_cs_other.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/cs/_global_mmlu_full_cs_social_sciences.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/cs/_global_mmlu_full_cs_stem.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_abstract_algebra.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_anatomy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_astronomy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_business_ethics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_clinical_knowledge.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_college_biology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_college_chemistry.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_college_computer_science.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_college_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_college_medicine.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_college_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_computer_security.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_conceptual_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_econometrics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_electrical_engineering.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_elementary_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_formal_logic.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_global_facts.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_high_school_biology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_high_school_chemistry.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_high_school_computer_science.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_high_school_european_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_high_school_geography.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_high_school_government_and_politics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_high_school_macroeconomics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_high_school_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_high_school_microeconomics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_high_school_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_high_school_psychology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_high_school_statistics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_high_school_us_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_high_school_world_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_human_aging.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_human_sexuality.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_international_law.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_jurisprudence.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_logical_fallacies.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_machine_learning.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_management.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_marketing.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_medical_genetics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_miscellaneous.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_moral_disputes.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_moral_scenarios.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_nutrition.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_philosophy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_prehistory.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_professional_accounting.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_professional_law.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_professional_medicine.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_professional_psychology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_public_relations.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_security_studies.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_sociology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_us_foreign_policy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_virology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_world_religions.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/cs/utils.py create mode 100644 lm_eval/tasks/global_mmlu/full/de/_de_template_yaml create mode 100644 lm_eval/tasks/global_mmlu/full/de/_global_mmlu_full_de.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/de/_global_mmlu_full_de_humanities.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/de/_global_mmlu_full_de_other.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/de/_global_mmlu_full_de_social_sciences.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/de/_global_mmlu_full_de_stem.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_abstract_algebra.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_anatomy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_astronomy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_business_ethics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_clinical_knowledge.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_college_biology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_college_chemistry.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_college_computer_science.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_college_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_college_medicine.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_college_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_computer_security.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_conceptual_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_econometrics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_electrical_engineering.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_elementary_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_formal_logic.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_global_facts.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_high_school_biology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_high_school_chemistry.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_high_school_computer_science.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_high_school_european_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_high_school_geography.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_high_school_government_and_politics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_high_school_macroeconomics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_high_school_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_high_school_microeconomics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_high_school_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_high_school_psychology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_high_school_statistics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_high_school_us_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_high_school_world_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_human_aging.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_human_sexuality.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_international_law.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_jurisprudence.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_logical_fallacies.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_machine_learning.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_management.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_marketing.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_medical_genetics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_miscellaneous.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_moral_disputes.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_moral_scenarios.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_nutrition.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_philosophy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_prehistory.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_professional_accounting.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_professional_law.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_professional_medicine.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_professional_psychology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_public_relations.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_security_studies.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_sociology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_us_foreign_policy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_virology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_world_religions.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/de/utils.py create mode 100644 lm_eval/tasks/global_mmlu/full/el/_el_template_yaml create mode 100644 lm_eval/tasks/global_mmlu/full/el/_global_mmlu_full_el.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/el/_global_mmlu_full_el_humanities.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/el/_global_mmlu_full_el_other.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/el/_global_mmlu_full_el_social_sciences.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/el/_global_mmlu_full_el_stem.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_abstract_algebra.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_anatomy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_astronomy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_business_ethics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_clinical_knowledge.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_college_biology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_college_chemistry.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_college_computer_science.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_college_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_college_medicine.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_college_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_computer_security.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_conceptual_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_econometrics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_electrical_engineering.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_elementary_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_formal_logic.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_global_facts.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_high_school_biology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_high_school_chemistry.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_high_school_computer_science.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_high_school_european_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_high_school_geography.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_high_school_government_and_politics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_high_school_macroeconomics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_high_school_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_high_school_microeconomics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_high_school_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_high_school_psychology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_high_school_statistics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_high_school_us_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_high_school_world_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_human_aging.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_human_sexuality.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_international_law.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_jurisprudence.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_logical_fallacies.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_machine_learning.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_management.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_marketing.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_medical_genetics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_miscellaneous.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_moral_disputes.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_moral_scenarios.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_nutrition.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_philosophy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_prehistory.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_professional_accounting.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_professional_law.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_professional_medicine.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_professional_psychology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_public_relations.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_security_studies.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_sociology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_us_foreign_policy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_virology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_world_religions.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/el/utils.py create mode 100644 lm_eval/tasks/global_mmlu/full/en/_en_template_yaml create mode 100644 lm_eval/tasks/global_mmlu/full/en/_global_mmlu_full_en.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/en/_global_mmlu_full_en_humanities.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/en/_global_mmlu_full_en_other.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/en/_global_mmlu_full_en_social_sciences.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/en/_global_mmlu_full_en_stem.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_abstract_algebra.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_anatomy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_astronomy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_business_ethics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_clinical_knowledge.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_college_biology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_college_chemistry.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_college_computer_science.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_college_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_college_medicine.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_college_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_computer_security.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_conceptual_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_econometrics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_electrical_engineering.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_elementary_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_formal_logic.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_global_facts.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_high_school_biology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_high_school_chemistry.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_high_school_computer_science.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_high_school_european_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_high_school_geography.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_high_school_government_and_politics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_high_school_macroeconomics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_high_school_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_high_school_microeconomics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_high_school_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_high_school_psychology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_high_school_statistics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_high_school_us_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_high_school_world_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_human_aging.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_human_sexuality.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_international_law.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_jurisprudence.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_logical_fallacies.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_machine_learning.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_management.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_marketing.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_medical_genetics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_miscellaneous.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_moral_disputes.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_moral_scenarios.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_nutrition.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_philosophy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_prehistory.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_professional_accounting.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_professional_law.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_professional_medicine.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_professional_psychology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_public_relations.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_security_studies.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_sociology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_us_foreign_policy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_virology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_world_religions.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/en/utils.py create mode 100644 lm_eval/tasks/global_mmlu/full/es/_es_template_yaml create mode 100644 lm_eval/tasks/global_mmlu/full/es/_global_mmlu_full_es.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/es/_global_mmlu_full_es_humanities.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/es/_global_mmlu_full_es_other.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/es/_global_mmlu_full_es_social_sciences.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/es/_global_mmlu_full_es_stem.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_abstract_algebra.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_anatomy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_astronomy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_business_ethics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_clinical_knowledge.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_college_biology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_college_chemistry.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_college_computer_science.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_college_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_college_medicine.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_college_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_computer_security.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_conceptual_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_econometrics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_electrical_engineering.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_elementary_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_formal_logic.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_global_facts.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_high_school_biology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_high_school_chemistry.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_high_school_computer_science.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_high_school_european_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_high_school_geography.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_high_school_government_and_politics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_high_school_macroeconomics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_high_school_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_high_school_microeconomics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_high_school_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_high_school_psychology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_high_school_statistics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_high_school_us_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_high_school_world_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_human_aging.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_human_sexuality.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_international_law.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_jurisprudence.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_logical_fallacies.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_machine_learning.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_management.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_marketing.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_medical_genetics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_miscellaneous.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_moral_disputes.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_moral_scenarios.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_nutrition.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_philosophy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_prehistory.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_professional_accounting.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_professional_law.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_professional_medicine.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_professional_psychology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_public_relations.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_security_studies.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_sociology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_us_foreign_policy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_virology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_world_religions.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/es/utils.py create mode 100644 lm_eval/tasks/global_mmlu/full/fa/_fa_template_yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fa/_global_mmlu_full_fa.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fa/_global_mmlu_full_fa_humanities.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fa/_global_mmlu_full_fa_other.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fa/_global_mmlu_full_fa_social_sciences.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fa/_global_mmlu_full_fa_stem.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_abstract_algebra.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_anatomy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_astronomy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_business_ethics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_clinical_knowledge.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_college_biology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_college_chemistry.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_college_computer_science.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_college_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_college_medicine.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_college_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_computer_security.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_conceptual_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_econometrics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_electrical_engineering.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_elementary_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_formal_logic.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_global_facts.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_high_school_biology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_high_school_chemistry.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_high_school_computer_science.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_high_school_european_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_high_school_geography.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_high_school_government_and_politics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_high_school_macroeconomics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_high_school_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_high_school_microeconomics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_high_school_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_high_school_psychology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_high_school_statistics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_high_school_us_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_high_school_world_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_human_aging.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_human_sexuality.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_international_law.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_jurisprudence.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_logical_fallacies.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_machine_learning.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_management.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_marketing.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_medical_genetics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_miscellaneous.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_moral_disputes.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_moral_scenarios.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_nutrition.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_philosophy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_prehistory.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_professional_accounting.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_professional_law.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_professional_medicine.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_professional_psychology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_public_relations.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_security_studies.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_sociology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_us_foreign_policy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_virology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_world_religions.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fa/utils.py create mode 100644 lm_eval/tasks/global_mmlu/full/fil/_fil_template_yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fil/_global_mmlu_full_fil.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fil/_global_mmlu_full_fil_humanities.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fil/_global_mmlu_full_fil_other.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fil/_global_mmlu_full_fil_social_sciences.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fil/_global_mmlu_full_fil_stem.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_abstract_algebra.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_anatomy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_astronomy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_business_ethics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_clinical_knowledge.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_college_biology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_college_chemistry.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_college_computer_science.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_college_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_college_medicine.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_college_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_computer_security.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_conceptual_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_econometrics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_electrical_engineering.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_elementary_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_formal_logic.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_global_facts.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_high_school_biology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_high_school_chemistry.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_high_school_computer_science.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_high_school_european_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_high_school_geography.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_high_school_government_and_politics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_high_school_macroeconomics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_high_school_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_high_school_microeconomics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_high_school_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_high_school_psychology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_high_school_statistics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_high_school_us_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_high_school_world_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_human_aging.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_human_sexuality.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_international_law.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_jurisprudence.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_logical_fallacies.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_machine_learning.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_management.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_marketing.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_medical_genetics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_miscellaneous.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_moral_disputes.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_moral_scenarios.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_nutrition.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_philosophy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_prehistory.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_professional_accounting.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_professional_law.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_professional_medicine.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_professional_psychology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_public_relations.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_security_studies.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_sociology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_us_foreign_policy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_virology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_world_religions.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fil/utils.py create mode 100644 lm_eval/tasks/global_mmlu/full/fr/_fr_template_yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fr/_global_mmlu_full_fr.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fr/_global_mmlu_full_fr_humanities.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fr/_global_mmlu_full_fr_other.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fr/_global_mmlu_full_fr_social_sciences.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fr/_global_mmlu_full_fr_stem.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_abstract_algebra.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_anatomy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_astronomy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_business_ethics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_clinical_knowledge.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_college_biology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_college_chemistry.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_college_computer_science.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_college_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_college_medicine.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_college_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_computer_security.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_conceptual_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_econometrics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_electrical_engineering.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_elementary_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_formal_logic.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_global_facts.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_high_school_biology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_high_school_chemistry.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_high_school_computer_science.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_high_school_european_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_high_school_geography.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_high_school_government_and_politics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_high_school_macroeconomics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_high_school_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_high_school_microeconomics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_high_school_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_high_school_psychology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_high_school_statistics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_high_school_us_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_high_school_world_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_human_aging.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_human_sexuality.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_international_law.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_jurisprudence.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_logical_fallacies.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_machine_learning.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_management.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_marketing.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_medical_genetics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_miscellaneous.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_moral_disputes.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_moral_scenarios.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_nutrition.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_philosophy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_prehistory.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_professional_accounting.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_professional_law.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_professional_medicine.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_professional_psychology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_public_relations.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_security_studies.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_sociology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_us_foreign_policy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_virology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_world_religions.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/fr/utils.py create mode 100644 lm_eval/tasks/global_mmlu/full/ha/_global_mmlu_full_ha.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ha/_global_mmlu_full_ha_humanities.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ha/_global_mmlu_full_ha_other.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ha/_global_mmlu_full_ha_social_sciences.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ha/_global_mmlu_full_ha_stem.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ha/_ha_template_yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_abstract_algebra.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_anatomy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_astronomy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_business_ethics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_clinical_knowledge.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_college_biology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_college_chemistry.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_college_computer_science.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_college_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_college_medicine.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_college_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_computer_security.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_conceptual_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_econometrics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_electrical_engineering.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_elementary_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_formal_logic.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_global_facts.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_high_school_biology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_high_school_chemistry.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_high_school_computer_science.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_high_school_european_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_high_school_geography.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_high_school_government_and_politics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_high_school_macroeconomics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_high_school_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_high_school_microeconomics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_high_school_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_high_school_psychology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_high_school_statistics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_high_school_us_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_high_school_world_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_human_aging.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_human_sexuality.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_international_law.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_jurisprudence.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_logical_fallacies.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_machine_learning.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_management.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_marketing.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_medical_genetics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_miscellaneous.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_moral_disputes.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_moral_scenarios.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_nutrition.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_philosophy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_prehistory.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_professional_accounting.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_professional_law.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_professional_medicine.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_professional_psychology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_public_relations.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_security_studies.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_sociology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_us_foreign_policy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_virology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_world_religions.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ha/utils.py create mode 100644 lm_eval/tasks/global_mmlu/full/he/_global_mmlu_full_he.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/he/_global_mmlu_full_he_humanities.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/he/_global_mmlu_full_he_other.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/he/_global_mmlu_full_he_social_sciences.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/he/_global_mmlu_full_he_stem.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/he/_he_template_yaml create mode 100644 lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_abstract_algebra.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_anatomy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_astronomy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_business_ethics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_clinical_knowledge.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_college_biology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_college_chemistry.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_college_computer_science.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_college_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_college_medicine.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_college_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_computer_security.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_conceptual_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_econometrics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_electrical_engineering.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_elementary_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_formal_logic.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_global_facts.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_high_school_biology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_high_school_chemistry.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_high_school_computer_science.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_high_school_european_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_high_school_geography.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_high_school_government_and_politics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_high_school_macroeconomics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_high_school_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_high_school_microeconomics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_high_school_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_high_school_psychology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_high_school_statistics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_high_school_us_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_high_school_world_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_human_aging.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_human_sexuality.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_international_law.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_jurisprudence.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_logical_fallacies.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_machine_learning.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_management.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_marketing.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_medical_genetics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_miscellaneous.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_moral_disputes.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_moral_scenarios.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_nutrition.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_philosophy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_prehistory.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_professional_accounting.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_professional_law.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_professional_medicine.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_professional_psychology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_public_relations.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_security_studies.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_sociology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_us_foreign_policy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_virology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_world_religions.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/he/utils.py create mode 100644 lm_eval/tasks/global_mmlu/full/hi/_global_mmlu_full_hi.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/hi/_global_mmlu_full_hi_humanities.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/hi/_global_mmlu_full_hi_other.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/hi/_global_mmlu_full_hi_social_sciences.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/hi/_global_mmlu_full_hi_stem.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/hi/_hi_template_yaml create mode 100644 lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_abstract_algebra.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_anatomy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_astronomy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_business_ethics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_clinical_knowledge.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_college_biology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_college_chemistry.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_college_computer_science.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_college_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_college_medicine.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_college_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_computer_security.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_conceptual_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_econometrics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_electrical_engineering.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_elementary_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_formal_logic.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_global_facts.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_high_school_biology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_high_school_chemistry.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_high_school_computer_science.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_high_school_european_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_high_school_geography.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_high_school_government_and_politics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_high_school_macroeconomics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_high_school_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_high_school_microeconomics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_high_school_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_high_school_psychology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_high_school_statistics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_high_school_us_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_high_school_world_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_human_aging.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_human_sexuality.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_international_law.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_jurisprudence.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_logical_fallacies.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_machine_learning.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_management.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_marketing.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_medical_genetics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_miscellaneous.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_moral_disputes.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_moral_scenarios.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_nutrition.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_philosophy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_prehistory.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_professional_accounting.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_professional_law.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_professional_medicine.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_professional_psychology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_public_relations.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_security_studies.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_sociology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_us_foreign_policy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_virology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_world_religions.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/hi/utils.py create mode 100644 lm_eval/tasks/global_mmlu/full/id/_global_mmlu_full_id.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/id/_global_mmlu_full_id_humanities.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/id/_global_mmlu_full_id_other.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/id/_global_mmlu_full_id_social_sciences.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/id/_global_mmlu_full_id_stem.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/id/_id_template_yaml create mode 100644 lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_abstract_algebra.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_anatomy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_astronomy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_business_ethics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_clinical_knowledge.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_college_biology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_college_chemistry.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_college_computer_science.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_college_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_college_medicine.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_college_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_computer_security.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_conceptual_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_econometrics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_electrical_engineering.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_elementary_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_formal_logic.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_global_facts.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_high_school_biology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_high_school_chemistry.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_high_school_computer_science.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_high_school_european_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_high_school_geography.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_high_school_government_and_politics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_high_school_macroeconomics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_high_school_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_high_school_microeconomics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_high_school_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_high_school_psychology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_high_school_statistics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_high_school_us_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_high_school_world_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_human_aging.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_human_sexuality.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_international_law.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_jurisprudence.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_logical_fallacies.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_machine_learning.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_management.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_marketing.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_medical_genetics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_miscellaneous.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_moral_disputes.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_moral_scenarios.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_nutrition.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_philosophy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_prehistory.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_professional_accounting.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_professional_law.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_professional_medicine.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_professional_psychology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_public_relations.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_security_studies.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_sociology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_us_foreign_policy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_virology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_world_religions.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/id/utils.py create mode 100644 lm_eval/tasks/global_mmlu/full/ig/_global_mmlu_full_ig.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ig/_global_mmlu_full_ig_humanities.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ig/_global_mmlu_full_ig_other.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ig/_global_mmlu_full_ig_social_sciences.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ig/_global_mmlu_full_ig_stem.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ig/_ig_template_yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_abstract_algebra.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_anatomy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_astronomy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_business_ethics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_clinical_knowledge.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_college_biology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_college_chemistry.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_college_computer_science.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_college_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_college_medicine.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_college_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_computer_security.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_conceptual_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_econometrics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_electrical_engineering.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_elementary_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_formal_logic.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_global_facts.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_high_school_biology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_high_school_chemistry.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_high_school_computer_science.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_high_school_european_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_high_school_geography.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_high_school_government_and_politics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_high_school_macroeconomics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_high_school_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_high_school_microeconomics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_high_school_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_high_school_psychology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_high_school_statistics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_high_school_us_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_high_school_world_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_human_aging.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_human_sexuality.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_international_law.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_jurisprudence.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_logical_fallacies.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_machine_learning.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_management.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_marketing.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_medical_genetics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_miscellaneous.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_moral_disputes.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_moral_scenarios.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_nutrition.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_philosophy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_prehistory.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_professional_accounting.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_professional_law.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_professional_medicine.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_professional_psychology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_public_relations.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_security_studies.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_sociology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_us_foreign_policy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_virology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_world_religions.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ig/utils.py create mode 100644 lm_eval/tasks/global_mmlu/full/it/_global_mmlu_full_it.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/it/_global_mmlu_full_it_humanities.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/it/_global_mmlu_full_it_other.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/it/_global_mmlu_full_it_social_sciences.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/it/_global_mmlu_full_it_stem.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/it/_it_template_yaml create mode 100644 lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_abstract_algebra.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_anatomy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_astronomy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_business_ethics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_clinical_knowledge.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_college_biology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_college_chemistry.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_college_computer_science.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_college_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_college_medicine.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_college_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_computer_security.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_conceptual_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_econometrics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_electrical_engineering.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_elementary_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_formal_logic.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_global_facts.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_high_school_biology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_high_school_chemistry.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_high_school_computer_science.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_high_school_european_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_high_school_geography.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_high_school_government_and_politics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_high_school_macroeconomics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_high_school_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_high_school_microeconomics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_high_school_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_high_school_psychology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_high_school_statistics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_high_school_us_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_high_school_world_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_human_aging.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_human_sexuality.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_international_law.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_jurisprudence.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_logical_fallacies.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_machine_learning.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_management.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_marketing.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_medical_genetics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_miscellaneous.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_moral_disputes.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_moral_scenarios.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_nutrition.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_philosophy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_prehistory.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_professional_accounting.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_professional_law.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_professional_medicine.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_professional_psychology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_public_relations.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_security_studies.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_sociology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_us_foreign_policy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_virology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_world_religions.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/it/utils.py create mode 100644 lm_eval/tasks/global_mmlu/full/ja/_global_mmlu_full_ja.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ja/_global_mmlu_full_ja_humanities.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ja/_global_mmlu_full_ja_other.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ja/_global_mmlu_full_ja_social_sciences.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ja/_global_mmlu_full_ja_stem.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ja/_ja_template_yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_abstract_algebra.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_anatomy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_astronomy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_business_ethics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_clinical_knowledge.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_college_biology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_college_chemistry.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_college_computer_science.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_college_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_college_medicine.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_college_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_computer_security.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_conceptual_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_econometrics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_electrical_engineering.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_elementary_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_formal_logic.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_global_facts.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_high_school_biology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_high_school_chemistry.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_high_school_computer_science.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_high_school_european_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_high_school_geography.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_high_school_government_and_politics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_high_school_macroeconomics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_high_school_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_high_school_microeconomics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_high_school_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_high_school_psychology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_high_school_statistics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_high_school_us_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_high_school_world_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_human_aging.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_human_sexuality.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_international_law.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_jurisprudence.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_logical_fallacies.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_machine_learning.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_management.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_marketing.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_medical_genetics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_miscellaneous.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_moral_disputes.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_moral_scenarios.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_nutrition.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_philosophy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_prehistory.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_professional_accounting.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_professional_law.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_professional_medicine.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_professional_psychology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_public_relations.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_security_studies.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_sociology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_us_foreign_policy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_virology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_world_religions.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ja/utils.py create mode 100644 lm_eval/tasks/global_mmlu/full/ko/_global_mmlu_full_ko.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ko/_global_mmlu_full_ko_humanities.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ko/_global_mmlu_full_ko_other.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ko/_global_mmlu_full_ko_social_sciences.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ko/_global_mmlu_full_ko_stem.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ko/_ko_template_yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_abstract_algebra.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_anatomy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_astronomy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_business_ethics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_clinical_knowledge.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_college_biology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_college_chemistry.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_college_computer_science.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_college_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_college_medicine.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_college_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_computer_security.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_conceptual_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_econometrics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_electrical_engineering.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_elementary_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_formal_logic.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_global_facts.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_high_school_biology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_high_school_chemistry.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_high_school_computer_science.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_high_school_european_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_high_school_geography.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_high_school_government_and_politics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_high_school_macroeconomics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_high_school_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_high_school_microeconomics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_high_school_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_high_school_psychology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_high_school_statistics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_high_school_us_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_high_school_world_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_human_aging.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_human_sexuality.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_international_law.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_jurisprudence.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_logical_fallacies.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_machine_learning.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_management.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_marketing.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_medical_genetics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_miscellaneous.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_moral_disputes.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_moral_scenarios.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_nutrition.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_philosophy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_prehistory.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_professional_accounting.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_professional_law.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_professional_medicine.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_professional_psychology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_public_relations.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_security_studies.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_sociology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_us_foreign_policy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_virology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_world_religions.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ko/utils.py create mode 100644 lm_eval/tasks/global_mmlu/full/ky/_global_mmlu_full_ky.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ky/_global_mmlu_full_ky_humanities.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ky/_global_mmlu_full_ky_other.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ky/_global_mmlu_full_ky_social_sciences.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ky/_global_mmlu_full_ky_stem.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ky/_ky_template_yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_abstract_algebra.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_anatomy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_astronomy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_business_ethics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_clinical_knowledge.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_college_biology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_college_chemistry.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_college_computer_science.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_college_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_college_medicine.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_college_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_computer_security.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_conceptual_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_econometrics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_electrical_engineering.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_elementary_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_formal_logic.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_global_facts.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_high_school_biology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_high_school_chemistry.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_high_school_computer_science.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_high_school_european_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_high_school_geography.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_high_school_government_and_politics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_high_school_macroeconomics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_high_school_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_high_school_microeconomics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_high_school_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_high_school_psychology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_high_school_statistics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_high_school_us_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_high_school_world_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_human_aging.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_human_sexuality.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_international_law.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_jurisprudence.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_logical_fallacies.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_machine_learning.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_management.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_marketing.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_medical_genetics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_miscellaneous.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_moral_disputes.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_moral_scenarios.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_nutrition.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_philosophy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_prehistory.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_professional_accounting.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_professional_law.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_professional_medicine.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_professional_psychology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_public_relations.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_security_studies.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_sociology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_us_foreign_policy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_virology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_world_religions.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ky/utils.py create mode 100644 lm_eval/tasks/global_mmlu/full/lt/_global_mmlu_full_lt.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/lt/_global_mmlu_full_lt_humanities.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/lt/_global_mmlu_full_lt_other.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/lt/_global_mmlu_full_lt_social_sciences.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/lt/_global_mmlu_full_lt_stem.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/lt/_lt_template_yaml create mode 100644 lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_abstract_algebra.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_anatomy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_astronomy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_business_ethics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_clinical_knowledge.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_college_biology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_college_chemistry.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_college_computer_science.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_college_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_college_medicine.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_college_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_computer_security.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_conceptual_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_econometrics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_electrical_engineering.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_elementary_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_formal_logic.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_global_facts.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_high_school_biology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_high_school_chemistry.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_high_school_computer_science.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_high_school_european_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_high_school_geography.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_high_school_government_and_politics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_high_school_macroeconomics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_high_school_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_high_school_microeconomics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_high_school_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_high_school_psychology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_high_school_statistics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_high_school_us_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_high_school_world_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_human_aging.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_human_sexuality.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_international_law.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_jurisprudence.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_logical_fallacies.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_machine_learning.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_management.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_marketing.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_medical_genetics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_miscellaneous.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_moral_disputes.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_moral_scenarios.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_nutrition.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_philosophy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_prehistory.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_professional_accounting.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_professional_law.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_professional_medicine.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_professional_psychology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_public_relations.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_security_studies.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_sociology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_us_foreign_policy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_virology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_world_religions.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/lt/utils.py create mode 100644 lm_eval/tasks/global_mmlu/full/mg/_global_mmlu_full_mg.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/mg/_global_mmlu_full_mg_humanities.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/mg/_global_mmlu_full_mg_other.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/mg/_global_mmlu_full_mg_social_sciences.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/mg/_global_mmlu_full_mg_stem.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/mg/_mg_template_yaml create mode 100644 lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_abstract_algebra.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_anatomy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_astronomy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_business_ethics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_clinical_knowledge.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_college_biology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_college_chemistry.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_college_computer_science.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_college_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_college_medicine.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_college_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_computer_security.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_conceptual_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_econometrics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_electrical_engineering.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_elementary_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_formal_logic.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_global_facts.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_high_school_biology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_high_school_chemistry.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_high_school_computer_science.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_high_school_european_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_high_school_geography.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_high_school_government_and_politics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_high_school_macroeconomics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_high_school_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_high_school_microeconomics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_high_school_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_high_school_psychology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_high_school_statistics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_high_school_us_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_high_school_world_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_human_aging.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_human_sexuality.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_international_law.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_jurisprudence.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_logical_fallacies.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_machine_learning.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_management.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_marketing.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_medical_genetics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_miscellaneous.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_moral_disputes.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_moral_scenarios.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_nutrition.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_philosophy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_prehistory.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_professional_accounting.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_professional_law.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_professional_medicine.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_professional_psychology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_public_relations.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_security_studies.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_sociology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_us_foreign_policy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_virology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_world_religions.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/mg/utils.py create mode 100644 lm_eval/tasks/global_mmlu/full/ms/_global_mmlu_full_ms.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ms/_global_mmlu_full_ms_humanities.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ms/_global_mmlu_full_ms_other.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ms/_global_mmlu_full_ms_social_sciences.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ms/_global_mmlu_full_ms_stem.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ms/_ms_template_yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_abstract_algebra.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_anatomy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_astronomy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_business_ethics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_clinical_knowledge.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_college_biology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_college_chemistry.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_college_computer_science.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_college_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_college_medicine.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_college_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_computer_security.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_conceptual_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_econometrics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_electrical_engineering.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_elementary_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_formal_logic.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_global_facts.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_high_school_biology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_high_school_chemistry.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_high_school_computer_science.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_high_school_european_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_high_school_geography.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_high_school_government_and_politics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_high_school_macroeconomics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_high_school_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_high_school_microeconomics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_high_school_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_high_school_psychology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_high_school_statistics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_high_school_us_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_high_school_world_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_human_aging.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_human_sexuality.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_international_law.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_jurisprudence.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_logical_fallacies.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_machine_learning.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_management.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_marketing.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_medical_genetics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_miscellaneous.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_moral_disputes.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_moral_scenarios.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_nutrition.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_philosophy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_prehistory.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_professional_accounting.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_professional_law.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_professional_medicine.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_professional_psychology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_public_relations.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_security_studies.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_sociology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_us_foreign_policy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_virology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_world_religions.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ms/utils.py create mode 100644 lm_eval/tasks/global_mmlu/full/ne/_global_mmlu_full_ne.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ne/_global_mmlu_full_ne_humanities.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ne/_global_mmlu_full_ne_other.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ne/_global_mmlu_full_ne_social_sciences.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ne/_global_mmlu_full_ne_stem.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ne/_ne_template_yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_abstract_algebra.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_anatomy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_astronomy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_business_ethics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_clinical_knowledge.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_college_biology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_college_chemistry.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_college_computer_science.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_college_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_college_medicine.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_college_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_computer_security.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_conceptual_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_econometrics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_electrical_engineering.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_elementary_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_formal_logic.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_global_facts.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_high_school_biology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_high_school_chemistry.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_high_school_computer_science.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_high_school_european_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_high_school_geography.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_high_school_government_and_politics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_high_school_macroeconomics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_high_school_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_high_school_microeconomics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_high_school_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_high_school_psychology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_high_school_statistics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_high_school_us_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_high_school_world_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_human_aging.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_human_sexuality.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_international_law.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_jurisprudence.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_logical_fallacies.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_machine_learning.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_management.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_marketing.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_medical_genetics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_miscellaneous.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_moral_disputes.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_moral_scenarios.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_nutrition.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_philosophy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_prehistory.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_professional_accounting.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_professional_law.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_professional_medicine.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_professional_psychology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_public_relations.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_security_studies.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_sociology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_us_foreign_policy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_virology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_world_religions.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ne/utils.py create mode 100644 lm_eval/tasks/global_mmlu/full/nl/_global_mmlu_full_nl.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/nl/_global_mmlu_full_nl_humanities.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/nl/_global_mmlu_full_nl_other.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/nl/_global_mmlu_full_nl_social_sciences.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/nl/_global_mmlu_full_nl_stem.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/nl/_nl_template_yaml create mode 100644 lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_abstract_algebra.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_anatomy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_astronomy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_business_ethics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_clinical_knowledge.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_college_biology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_college_chemistry.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_college_computer_science.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_college_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_college_medicine.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_college_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_computer_security.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_conceptual_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_econometrics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_electrical_engineering.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_elementary_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_formal_logic.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_global_facts.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_high_school_biology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_high_school_chemistry.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_high_school_computer_science.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_high_school_european_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_high_school_geography.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_high_school_government_and_politics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_high_school_macroeconomics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_high_school_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_high_school_microeconomics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_high_school_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_high_school_psychology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_high_school_statistics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_high_school_us_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_high_school_world_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_human_aging.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_human_sexuality.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_international_law.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_jurisprudence.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_logical_fallacies.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_machine_learning.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_management.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_marketing.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_medical_genetics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_miscellaneous.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_moral_disputes.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_moral_scenarios.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_nutrition.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_philosophy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_prehistory.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_professional_accounting.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_professional_law.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_professional_medicine.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_professional_psychology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_public_relations.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_security_studies.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_sociology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_us_foreign_policy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_virology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_world_religions.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/nl/utils.py create mode 100644 lm_eval/tasks/global_mmlu/full/ny/_global_mmlu_full_ny.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ny/_global_mmlu_full_ny_humanities.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ny/_global_mmlu_full_ny_other.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ny/_global_mmlu_full_ny_social_sciences.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ny/_global_mmlu_full_ny_stem.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ny/_ny_template_yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_abstract_algebra.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_anatomy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_astronomy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_business_ethics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_clinical_knowledge.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_college_biology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_college_chemistry.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_college_computer_science.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_college_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_college_medicine.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_college_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_computer_security.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_conceptual_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_econometrics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_electrical_engineering.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_elementary_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_formal_logic.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_global_facts.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_high_school_biology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_high_school_chemistry.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_high_school_computer_science.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_high_school_european_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_high_school_geography.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_high_school_government_and_politics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_high_school_macroeconomics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_high_school_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_high_school_microeconomics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_high_school_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_high_school_psychology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_high_school_statistics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_high_school_us_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_high_school_world_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_human_aging.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_human_sexuality.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_international_law.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_jurisprudence.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_logical_fallacies.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_machine_learning.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_management.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_marketing.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_medical_genetics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_miscellaneous.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_moral_disputes.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_moral_scenarios.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_nutrition.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_philosophy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_prehistory.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_professional_accounting.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_professional_law.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_professional_medicine.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_professional_psychology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_public_relations.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_security_studies.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_sociology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_us_foreign_policy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_virology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_world_religions.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ny/utils.py create mode 100644 lm_eval/tasks/global_mmlu/full/pl/_global_mmlu_full_pl.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pl/_global_mmlu_full_pl_humanities.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pl/_global_mmlu_full_pl_other.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pl/_global_mmlu_full_pl_social_sciences.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pl/_global_mmlu_full_pl_stem.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pl/_pl_template_yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_abstract_algebra.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_anatomy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_astronomy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_business_ethics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_clinical_knowledge.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_college_biology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_college_chemistry.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_college_computer_science.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_college_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_college_medicine.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_college_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_computer_security.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_conceptual_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_econometrics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_electrical_engineering.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_elementary_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_formal_logic.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_global_facts.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_high_school_biology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_high_school_chemistry.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_high_school_computer_science.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_high_school_european_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_high_school_geography.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_high_school_government_and_politics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_high_school_macroeconomics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_high_school_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_high_school_microeconomics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_high_school_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_high_school_psychology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_high_school_statistics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_high_school_us_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_high_school_world_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_human_aging.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_human_sexuality.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_international_law.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_jurisprudence.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_logical_fallacies.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_machine_learning.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_management.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_marketing.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_medical_genetics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_miscellaneous.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_moral_disputes.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_moral_scenarios.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_nutrition.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_philosophy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_prehistory.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_professional_accounting.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_professional_law.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_professional_medicine.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_professional_psychology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_public_relations.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_security_studies.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_sociology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_us_foreign_policy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_virology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_world_religions.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pl/utils.py create mode 100644 lm_eval/tasks/global_mmlu/full/pt/_global_mmlu_full_pt.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pt/_global_mmlu_full_pt_humanities.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pt/_global_mmlu_full_pt_other.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pt/_global_mmlu_full_pt_social_sciences.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pt/_global_mmlu_full_pt_stem.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pt/_pt_template_yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_abstract_algebra.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_anatomy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_astronomy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_business_ethics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_clinical_knowledge.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_college_biology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_college_chemistry.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_college_computer_science.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_college_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_college_medicine.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_college_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_computer_security.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_conceptual_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_econometrics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_electrical_engineering.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_elementary_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_formal_logic.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_global_facts.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_high_school_biology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_high_school_chemistry.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_high_school_computer_science.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_high_school_european_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_high_school_geography.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_high_school_government_and_politics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_high_school_macroeconomics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_high_school_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_high_school_microeconomics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_high_school_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_high_school_psychology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_high_school_statistics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_high_school_us_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_high_school_world_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_human_aging.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_human_sexuality.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_international_law.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_jurisprudence.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_logical_fallacies.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_machine_learning.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_management.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_marketing.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_medical_genetics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_miscellaneous.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_moral_disputes.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_moral_scenarios.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_nutrition.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_philosophy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_prehistory.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_professional_accounting.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_professional_law.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_professional_medicine.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_professional_psychology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_public_relations.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_security_studies.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_sociology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_us_foreign_policy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_virology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_world_religions.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/pt/utils.py create mode 100644 lm_eval/tasks/global_mmlu/full/ro/_global_mmlu_full_ro.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ro/_global_mmlu_full_ro_humanities.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ro/_global_mmlu_full_ro_other.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ro/_global_mmlu_full_ro_social_sciences.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ro/_global_mmlu_full_ro_stem.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ro/_ro_template_yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_abstract_algebra.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_anatomy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_astronomy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_business_ethics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_clinical_knowledge.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_college_biology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_college_chemistry.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_college_computer_science.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_college_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_college_medicine.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_college_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_computer_security.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_conceptual_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_econometrics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_electrical_engineering.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_elementary_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_formal_logic.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_global_facts.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_high_school_biology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_high_school_chemistry.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_high_school_computer_science.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_high_school_european_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_high_school_geography.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_high_school_government_and_politics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_high_school_macroeconomics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_high_school_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_high_school_microeconomics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_high_school_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_high_school_psychology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_high_school_statistics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_high_school_us_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_high_school_world_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_human_aging.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_human_sexuality.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_international_law.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_jurisprudence.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_logical_fallacies.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_machine_learning.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_management.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_marketing.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_medical_genetics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_miscellaneous.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_moral_disputes.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_moral_scenarios.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_nutrition.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_philosophy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_prehistory.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_professional_accounting.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_professional_law.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_professional_medicine.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_professional_psychology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_public_relations.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_security_studies.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_sociology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_us_foreign_policy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_virology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_world_religions.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ro/utils.py create mode 100644 lm_eval/tasks/global_mmlu/full/ru/_global_mmlu_full_ru.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ru/_global_mmlu_full_ru_humanities.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ru/_global_mmlu_full_ru_other.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ru/_global_mmlu_full_ru_social_sciences.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ru/_global_mmlu_full_ru_stem.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ru/_ru_template_yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_abstract_algebra.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_anatomy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_astronomy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_business_ethics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_clinical_knowledge.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_college_biology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_college_chemistry.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_college_computer_science.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_college_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_college_medicine.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_college_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_computer_security.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_conceptual_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_econometrics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_electrical_engineering.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_elementary_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_formal_logic.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_global_facts.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_high_school_biology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_high_school_chemistry.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_high_school_computer_science.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_high_school_european_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_high_school_geography.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_high_school_government_and_politics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_high_school_macroeconomics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_high_school_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_high_school_microeconomics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_high_school_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_high_school_psychology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_high_school_statistics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_high_school_us_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_high_school_world_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_human_aging.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_human_sexuality.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_international_law.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_jurisprudence.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_logical_fallacies.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_machine_learning.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_management.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_marketing.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_medical_genetics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_miscellaneous.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_moral_disputes.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_moral_scenarios.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_nutrition.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_philosophy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_prehistory.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_professional_accounting.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_professional_law.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_professional_medicine.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_professional_psychology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_public_relations.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_security_studies.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_sociology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_us_foreign_policy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_virology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_world_religions.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/ru/utils.py create mode 100644 lm_eval/tasks/global_mmlu/full/si/_global_mmlu_full_si.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/si/_global_mmlu_full_si_humanities.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/si/_global_mmlu_full_si_other.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/si/_global_mmlu_full_si_social_sciences.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/si/_global_mmlu_full_si_stem.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/si/_si_template_yaml create mode 100644 lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_abstract_algebra.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_anatomy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_astronomy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_business_ethics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_clinical_knowledge.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_college_biology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_college_chemistry.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_college_computer_science.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_college_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_college_medicine.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_college_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_computer_security.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_conceptual_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_econometrics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_electrical_engineering.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_elementary_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_formal_logic.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_global_facts.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_high_school_biology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_high_school_chemistry.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_high_school_computer_science.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_high_school_european_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_high_school_geography.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_high_school_government_and_politics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_high_school_macroeconomics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_high_school_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_high_school_microeconomics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_high_school_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_high_school_psychology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_high_school_statistics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_high_school_us_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_high_school_world_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_human_aging.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_human_sexuality.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_international_law.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_jurisprudence.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_logical_fallacies.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_machine_learning.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_management.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_marketing.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_medical_genetics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_miscellaneous.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_moral_disputes.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_moral_scenarios.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_nutrition.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_philosophy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_prehistory.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_professional_accounting.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_professional_law.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_professional_medicine.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_professional_psychology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_public_relations.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_security_studies.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_sociology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_us_foreign_policy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_virology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_world_religions.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/si/utils.py create mode 100644 lm_eval/tasks/global_mmlu/full/sn/_global_mmlu_full_sn.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sn/_global_mmlu_full_sn_humanities.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sn/_global_mmlu_full_sn_other.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sn/_global_mmlu_full_sn_social_sciences.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sn/_global_mmlu_full_sn_stem.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sn/_sn_template_yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_abstract_algebra.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_anatomy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_astronomy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_business_ethics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_clinical_knowledge.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_college_biology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_college_chemistry.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_college_computer_science.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_college_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_college_medicine.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_college_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_computer_security.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_conceptual_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_econometrics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_electrical_engineering.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_elementary_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_formal_logic.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_global_facts.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_high_school_biology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_high_school_chemistry.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_high_school_computer_science.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_high_school_european_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_high_school_geography.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_high_school_government_and_politics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_high_school_macroeconomics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_high_school_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_high_school_microeconomics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_high_school_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_high_school_psychology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_high_school_statistics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_high_school_us_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_high_school_world_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_human_aging.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_human_sexuality.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_international_law.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_jurisprudence.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_logical_fallacies.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_machine_learning.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_management.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_marketing.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_medical_genetics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_miscellaneous.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_moral_disputes.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_moral_scenarios.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_nutrition.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_philosophy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_prehistory.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_professional_accounting.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_professional_law.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_professional_medicine.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_professional_psychology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_public_relations.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_security_studies.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_sociology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_us_foreign_policy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_virology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_world_religions.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sn/utils.py create mode 100644 lm_eval/tasks/global_mmlu/full/so/_global_mmlu_full_so.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/so/_global_mmlu_full_so_humanities.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/so/_global_mmlu_full_so_other.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/so/_global_mmlu_full_so_social_sciences.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/so/_global_mmlu_full_so_stem.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/so/_so_template_yaml create mode 100644 lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_abstract_algebra.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_anatomy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_astronomy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_business_ethics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_clinical_knowledge.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_college_biology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_college_chemistry.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_college_computer_science.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_college_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_college_medicine.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_college_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_computer_security.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_conceptual_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_econometrics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_electrical_engineering.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_elementary_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_formal_logic.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_global_facts.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_high_school_biology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_high_school_chemistry.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_high_school_computer_science.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_high_school_european_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_high_school_geography.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_high_school_government_and_politics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_high_school_macroeconomics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_high_school_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_high_school_microeconomics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_high_school_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_high_school_psychology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_high_school_statistics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_high_school_us_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_high_school_world_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_human_aging.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_human_sexuality.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_international_law.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_jurisprudence.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_logical_fallacies.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_machine_learning.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_management.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_marketing.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_medical_genetics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_miscellaneous.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_moral_disputes.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_moral_scenarios.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_nutrition.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_philosophy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_prehistory.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_professional_accounting.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_professional_law.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_professional_medicine.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_professional_psychology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_public_relations.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_security_studies.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_sociology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_us_foreign_policy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_virology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_world_religions.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/so/utils.py create mode 100644 lm_eval/tasks/global_mmlu/full/sr/_global_mmlu_full_sr.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sr/_global_mmlu_full_sr_humanities.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sr/_global_mmlu_full_sr_other.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sr/_global_mmlu_full_sr_social_sciences.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sr/_global_mmlu_full_sr_stem.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sr/_sr_template_yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_abstract_algebra.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_anatomy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_astronomy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_business_ethics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_clinical_knowledge.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_college_biology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_college_chemistry.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_college_computer_science.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_college_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_college_medicine.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_college_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_computer_security.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_conceptual_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_econometrics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_electrical_engineering.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_elementary_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_formal_logic.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_global_facts.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_high_school_biology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_high_school_chemistry.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_high_school_computer_science.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_high_school_european_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_high_school_geography.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_high_school_government_and_politics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_high_school_macroeconomics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_high_school_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_high_school_microeconomics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_high_school_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_high_school_psychology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_high_school_statistics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_high_school_us_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_high_school_world_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_human_aging.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_human_sexuality.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_international_law.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_jurisprudence.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_logical_fallacies.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_machine_learning.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_management.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_marketing.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_medical_genetics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_miscellaneous.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_moral_disputes.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_moral_scenarios.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_nutrition.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_philosophy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_prehistory.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_professional_accounting.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_professional_law.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_professional_medicine.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_professional_psychology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_public_relations.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_security_studies.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_sociology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_us_foreign_policy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_virology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_world_religions.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sr/utils.py create mode 100644 lm_eval/tasks/global_mmlu/full/sv/_global_mmlu_full_sv.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sv/_global_mmlu_full_sv_humanities.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sv/_global_mmlu_full_sv_other.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sv/_global_mmlu_full_sv_social_sciences.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sv/_global_mmlu_full_sv_stem.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sv/_sv_template_yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_abstract_algebra.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_anatomy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_astronomy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_business_ethics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_clinical_knowledge.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_college_biology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_college_chemistry.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_college_computer_science.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_college_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_college_medicine.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_college_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_computer_security.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_conceptual_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_econometrics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_electrical_engineering.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_elementary_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_formal_logic.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_global_facts.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_high_school_biology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_high_school_chemistry.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_high_school_computer_science.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_high_school_european_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_high_school_geography.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_high_school_government_and_politics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_high_school_macroeconomics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_high_school_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_high_school_microeconomics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_high_school_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_high_school_psychology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_high_school_statistics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_high_school_us_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_high_school_world_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_human_aging.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_human_sexuality.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_international_law.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_jurisprudence.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_logical_fallacies.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_machine_learning.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_management.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_marketing.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_medical_genetics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_miscellaneous.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_moral_disputes.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_moral_scenarios.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_nutrition.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_philosophy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_prehistory.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_professional_accounting.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_professional_law.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_professional_medicine.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_professional_psychology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_public_relations.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_security_studies.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_sociology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_us_foreign_policy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_virology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_world_religions.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sv/utils.py create mode 100644 lm_eval/tasks/global_mmlu/full/sw/_global_mmlu_full_sw.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sw/_global_mmlu_full_sw_humanities.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sw/_global_mmlu_full_sw_other.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sw/_global_mmlu_full_sw_social_sciences.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sw/_global_mmlu_full_sw_stem.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sw/_sw_template_yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_abstract_algebra.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_anatomy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_astronomy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_business_ethics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_clinical_knowledge.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_college_biology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_college_chemistry.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_college_computer_science.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_college_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_college_medicine.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_college_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_computer_security.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_conceptual_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_econometrics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_electrical_engineering.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_elementary_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_formal_logic.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_global_facts.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_high_school_biology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_high_school_chemistry.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_high_school_computer_science.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_high_school_european_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_high_school_geography.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_high_school_government_and_politics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_high_school_macroeconomics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_high_school_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_high_school_microeconomics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_high_school_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_high_school_psychology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_high_school_statistics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_high_school_us_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_high_school_world_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_human_aging.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_human_sexuality.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_international_law.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_jurisprudence.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_logical_fallacies.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_machine_learning.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_management.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_marketing.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_medical_genetics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_miscellaneous.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_moral_disputes.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_moral_scenarios.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_nutrition.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_philosophy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_prehistory.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_professional_accounting.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_professional_law.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_professional_medicine.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_professional_psychology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_public_relations.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_security_studies.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_sociology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_us_foreign_policy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_virology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_world_religions.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/sw/utils.py create mode 100644 lm_eval/tasks/global_mmlu/full/te/_global_mmlu_full_te.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/te/_global_mmlu_full_te_humanities.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/te/_global_mmlu_full_te_other.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/te/_global_mmlu_full_te_social_sciences.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/te/_global_mmlu_full_te_stem.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/te/_te_template_yaml create mode 100644 lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_abstract_algebra.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_anatomy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_astronomy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_business_ethics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_clinical_knowledge.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_college_biology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_college_chemistry.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_college_computer_science.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_college_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_college_medicine.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_college_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_computer_security.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_conceptual_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_econometrics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_electrical_engineering.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_elementary_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_formal_logic.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_global_facts.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_high_school_biology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_high_school_chemistry.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_high_school_computer_science.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_high_school_european_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_high_school_geography.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_high_school_government_and_politics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_high_school_macroeconomics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_high_school_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_high_school_microeconomics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_high_school_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_high_school_psychology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_high_school_statistics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_high_school_us_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_high_school_world_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_human_aging.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_human_sexuality.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_international_law.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_jurisprudence.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_logical_fallacies.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_machine_learning.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_management.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_marketing.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_medical_genetics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_miscellaneous.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_moral_disputes.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_moral_scenarios.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_nutrition.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_philosophy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_prehistory.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_professional_accounting.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_professional_law.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_professional_medicine.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_professional_psychology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_public_relations.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_security_studies.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_sociology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_us_foreign_policy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_virology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_world_religions.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/te/utils.py create mode 100644 lm_eval/tasks/global_mmlu/full/tr/_global_mmlu_full_tr.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/tr/_global_mmlu_full_tr_humanities.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/tr/_global_mmlu_full_tr_other.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/tr/_global_mmlu_full_tr_social_sciences.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/tr/_global_mmlu_full_tr_stem.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/tr/_tr_template_yaml create mode 100644 lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_abstract_algebra.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_anatomy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_astronomy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_business_ethics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_clinical_knowledge.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_college_biology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_college_chemistry.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_college_computer_science.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_college_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_college_medicine.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_college_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_computer_security.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_conceptual_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_econometrics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_electrical_engineering.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_elementary_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_formal_logic.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_global_facts.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_high_school_biology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_high_school_chemistry.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_high_school_computer_science.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_high_school_european_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_high_school_geography.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_high_school_government_and_politics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_high_school_macroeconomics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_high_school_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_high_school_microeconomics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_high_school_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_high_school_psychology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_high_school_statistics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_high_school_us_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_high_school_world_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_human_aging.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_human_sexuality.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_international_law.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_jurisprudence.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_logical_fallacies.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_machine_learning.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_management.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_marketing.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_medical_genetics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_miscellaneous.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_moral_disputes.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_moral_scenarios.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_nutrition.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_philosophy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_prehistory.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_professional_accounting.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_professional_law.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_professional_medicine.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_professional_psychology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_public_relations.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_security_studies.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_sociology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_us_foreign_policy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_virology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_world_religions.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/tr/utils.py create mode 100644 lm_eval/tasks/global_mmlu/full/uk/_global_mmlu_full_uk.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/uk/_global_mmlu_full_uk_humanities.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/uk/_global_mmlu_full_uk_other.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/uk/_global_mmlu_full_uk_social_sciences.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/uk/_global_mmlu_full_uk_stem.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/uk/_uk_template_yaml create mode 100644 lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_abstract_algebra.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_anatomy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_astronomy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_business_ethics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_clinical_knowledge.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_college_biology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_college_chemistry.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_college_computer_science.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_college_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_college_medicine.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_college_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_computer_security.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_conceptual_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_econometrics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_electrical_engineering.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_elementary_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_formal_logic.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_global_facts.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_high_school_biology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_high_school_chemistry.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_high_school_computer_science.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_high_school_european_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_high_school_geography.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_high_school_government_and_politics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_high_school_macroeconomics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_high_school_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_high_school_microeconomics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_high_school_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_high_school_psychology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_high_school_statistics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_high_school_us_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_high_school_world_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_human_aging.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_human_sexuality.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_international_law.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_jurisprudence.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_logical_fallacies.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_machine_learning.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_management.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_marketing.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_medical_genetics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_miscellaneous.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_moral_disputes.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_moral_scenarios.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_nutrition.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_philosophy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_prehistory.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_professional_accounting.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_professional_law.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_professional_medicine.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_professional_psychology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_public_relations.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_security_studies.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_sociology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_us_foreign_policy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_virology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_world_religions.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/uk/utils.py create mode 100644 lm_eval/tasks/global_mmlu/full/vi/_global_mmlu_full_vi.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/vi/_global_mmlu_full_vi_humanities.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/vi/_global_mmlu_full_vi_other.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/vi/_global_mmlu_full_vi_social_sciences.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/vi/_global_mmlu_full_vi_stem.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/vi/_vi_template_yaml create mode 100644 lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_abstract_algebra.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_anatomy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_astronomy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_business_ethics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_clinical_knowledge.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_college_biology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_college_chemistry.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_college_computer_science.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_college_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_college_medicine.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_college_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_computer_security.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_conceptual_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_econometrics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_electrical_engineering.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_elementary_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_formal_logic.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_global_facts.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_high_school_biology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_high_school_chemistry.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_high_school_computer_science.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_high_school_european_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_high_school_geography.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_high_school_government_and_politics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_high_school_macroeconomics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_high_school_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_high_school_microeconomics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_high_school_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_high_school_psychology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_high_school_statistics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_high_school_us_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_high_school_world_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_human_aging.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_human_sexuality.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_international_law.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_jurisprudence.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_logical_fallacies.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_machine_learning.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_management.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_marketing.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_medical_genetics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_miscellaneous.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_moral_disputes.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_moral_scenarios.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_nutrition.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_philosophy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_prehistory.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_professional_accounting.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_professional_law.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_professional_medicine.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_professional_psychology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_public_relations.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_security_studies.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_sociology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_us_foreign_policy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_virology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_world_religions.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/vi/utils.py create mode 100644 lm_eval/tasks/global_mmlu/full/yo/_global_mmlu_full_yo.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/yo/_global_mmlu_full_yo_humanities.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/yo/_global_mmlu_full_yo_other.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/yo/_global_mmlu_full_yo_social_sciences.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/yo/_global_mmlu_full_yo_stem.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/yo/_yo_template_yaml create mode 100644 lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_abstract_algebra.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_anatomy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_astronomy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_business_ethics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_clinical_knowledge.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_college_biology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_college_chemistry.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_college_computer_science.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_college_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_college_medicine.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_college_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_computer_security.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_conceptual_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_econometrics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_electrical_engineering.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_elementary_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_formal_logic.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_global_facts.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_high_school_biology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_high_school_chemistry.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_high_school_computer_science.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_high_school_european_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_high_school_geography.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_high_school_government_and_politics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_high_school_macroeconomics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_high_school_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_high_school_microeconomics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_high_school_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_high_school_psychology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_high_school_statistics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_high_school_us_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_high_school_world_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_human_aging.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_human_sexuality.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_international_law.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_jurisprudence.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_logical_fallacies.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_machine_learning.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_management.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_marketing.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_medical_genetics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_miscellaneous.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_moral_disputes.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_moral_scenarios.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_nutrition.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_philosophy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_prehistory.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_professional_accounting.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_professional_law.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_professional_medicine.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_professional_psychology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_public_relations.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_security_studies.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_sociology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_us_foreign_policy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_virology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_world_religions.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/yo/utils.py create mode 100644 lm_eval/tasks/global_mmlu/full/zh/_global_mmlu_full_zh.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/zh/_global_mmlu_full_zh_humanities.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/zh/_global_mmlu_full_zh_other.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/zh/_global_mmlu_full_zh_social_sciences.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/zh/_global_mmlu_full_zh_stem.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/zh/_zh_template_yaml create mode 100644 lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_abstract_algebra.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_anatomy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_astronomy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_business_ethics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_clinical_knowledge.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_college_biology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_college_chemistry.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_college_computer_science.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_college_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_college_medicine.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_college_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_computer_security.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_conceptual_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_econometrics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_electrical_engineering.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_elementary_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_formal_logic.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_global_facts.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_high_school_biology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_high_school_chemistry.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_high_school_computer_science.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_high_school_european_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_high_school_geography.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_high_school_government_and_politics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_high_school_macroeconomics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_high_school_mathematics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_high_school_microeconomics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_high_school_physics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_high_school_psychology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_high_school_statistics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_high_school_us_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_high_school_world_history.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_human_aging.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_human_sexuality.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_international_law.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_jurisprudence.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_logical_fallacies.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_machine_learning.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_management.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_marketing.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_medical_genetics.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_miscellaneous.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_moral_disputes.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_moral_scenarios.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_nutrition.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_philosophy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_prehistory.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_professional_accounting.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_professional_law.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_professional_medicine.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_professional_psychology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_public_relations.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_security_studies.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_sociology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_us_foreign_policy.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_virology.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_world_religions.yaml create mode 100644 lm_eval/tasks/global_mmlu/full/zh/utils.py diff --git a/lm_eval/tasks/global_mmlu/README.md b/lm_eval/tasks/global_mmlu/README.md index 838a7c9d..d1514102 100644 --- a/lm_eval/tasks/global_mmlu/README.md +++ b/lm_eval/tasks/global_mmlu/README.md @@ -6,9 +6,26 @@ Title: `Global MMLU: Understanding and Addressing Cultural and Linguistic Biases Abstract: [https://arxiv.org/abs/2412.03304](https://arxiv.org/abs/2412.03304) +Global-MMLU 🌍 is a multilingual evaluation set spanning 42 languages, including English. This dataset combines machine translations for MMLU questions along with professional translations and crowd-sourced post-edits. It also includes cultural sensitivity annotations for a subset of the questions (2850 questions per language) and classifies them as Culturally Sensitive (CS) 🗽 or Culturally Agnostic (CA) ⚖️. These annotations were collected as part of an open science initiative led by Cohere For AI in collaboration with many external collaborators from both industry and academia. + Global-MMLU-Lite is a balanced collection of culturally sensitive and culturally agnostic MMLU tasks. It is designed for efficient evaluation of multilingual models in 15 languages (including English). Only languages with human translations and post-edits in the original [Global-MMLU](https://huggingface.co/datasets/CohereForAI/Global-MMLU) 🌍 dataset have been included in the lite version. -Homepage: [https://huggingface.co/datasets/CohereForAI/Global-MMLU-Lite](https://huggingface.co/datasets/CohereForAI/Global-MMLU-Lite) +Homepage: \ +[https://huggingface.co/datasets/CohereForAI/Global-MMLU](https://huggingface.co/datasets/CohereForAI/Global-MMLU) \ +[https://huggingface.co/datasets/CohereForAI/Global-MMLU-Lite](https://huggingface.co/datasets/CohereForAI/Global-MMLU-Lite) + + +#### Groups + +* `global_mmlu_{lang}`: This group uses `Global-MMLU-Lite` benchmark which supports 14 languages. +* `global_mmlu_full_{lang}`: This group uses `Global-MMLU` benchmark which supports 42 languages. + +#### Subgroups (support only for `full` version) + +* `global_mmlu_full_stem` +* `global_mmlu_full_humanities` +* `global_mmlu_full_social_sciences` +* `global_mmlu_full_other` ### Citation diff --git a/lm_eval/tasks/global_mmlu/_default_yaml b/lm_eval/tasks/global_mmlu/default/_default_yaml similarity index 100% rename from lm_eval/tasks/global_mmlu/_default_yaml rename to lm_eval/tasks/global_mmlu/default/_default_yaml diff --git a/lm_eval/tasks/global_mmlu/_generate_configs.py b/lm_eval/tasks/global_mmlu/default/_generate_configs.py similarity index 100% rename from lm_eval/tasks/global_mmlu/_generate_configs.py rename to lm_eval/tasks/global_mmlu/default/_generate_configs.py diff --git a/lm_eval/tasks/global_mmlu/global_mmlu_ar.yaml b/lm_eval/tasks/global_mmlu/default/global_mmlu_ar.yaml similarity index 100% rename from lm_eval/tasks/global_mmlu/global_mmlu_ar.yaml rename to lm_eval/tasks/global_mmlu/default/global_mmlu_ar.yaml diff --git a/lm_eval/tasks/global_mmlu/global_mmlu_bn.yaml b/lm_eval/tasks/global_mmlu/default/global_mmlu_bn.yaml similarity index 100% rename from lm_eval/tasks/global_mmlu/global_mmlu_bn.yaml rename to lm_eval/tasks/global_mmlu/default/global_mmlu_bn.yaml diff --git a/lm_eval/tasks/global_mmlu/global_mmlu_de.yaml b/lm_eval/tasks/global_mmlu/default/global_mmlu_de.yaml similarity index 100% rename from lm_eval/tasks/global_mmlu/global_mmlu_de.yaml rename to lm_eval/tasks/global_mmlu/default/global_mmlu_de.yaml diff --git a/lm_eval/tasks/global_mmlu/global_mmlu_en.yaml b/lm_eval/tasks/global_mmlu/default/global_mmlu_en.yaml similarity index 100% rename from lm_eval/tasks/global_mmlu/global_mmlu_en.yaml rename to lm_eval/tasks/global_mmlu/default/global_mmlu_en.yaml diff --git a/lm_eval/tasks/global_mmlu/global_mmlu_es.yaml b/lm_eval/tasks/global_mmlu/default/global_mmlu_es.yaml similarity index 100% rename from lm_eval/tasks/global_mmlu/global_mmlu_es.yaml rename to lm_eval/tasks/global_mmlu/default/global_mmlu_es.yaml diff --git a/lm_eval/tasks/global_mmlu/global_mmlu_fr.yaml b/lm_eval/tasks/global_mmlu/default/global_mmlu_fr.yaml similarity index 100% rename from lm_eval/tasks/global_mmlu/global_mmlu_fr.yaml rename to lm_eval/tasks/global_mmlu/default/global_mmlu_fr.yaml diff --git a/lm_eval/tasks/global_mmlu/global_mmlu_hi.yaml b/lm_eval/tasks/global_mmlu/default/global_mmlu_hi.yaml similarity index 100% rename from lm_eval/tasks/global_mmlu/global_mmlu_hi.yaml rename to lm_eval/tasks/global_mmlu/default/global_mmlu_hi.yaml diff --git a/lm_eval/tasks/global_mmlu/global_mmlu_id.yaml b/lm_eval/tasks/global_mmlu/default/global_mmlu_id.yaml similarity index 100% rename from lm_eval/tasks/global_mmlu/global_mmlu_id.yaml rename to lm_eval/tasks/global_mmlu/default/global_mmlu_id.yaml diff --git a/lm_eval/tasks/global_mmlu/global_mmlu_it.yaml b/lm_eval/tasks/global_mmlu/default/global_mmlu_it.yaml similarity index 100% rename from lm_eval/tasks/global_mmlu/global_mmlu_it.yaml rename to lm_eval/tasks/global_mmlu/default/global_mmlu_it.yaml diff --git a/lm_eval/tasks/global_mmlu/global_mmlu_ja.yaml b/lm_eval/tasks/global_mmlu/default/global_mmlu_ja.yaml similarity index 100% rename from lm_eval/tasks/global_mmlu/global_mmlu_ja.yaml rename to lm_eval/tasks/global_mmlu/default/global_mmlu_ja.yaml diff --git a/lm_eval/tasks/global_mmlu/global_mmlu_ko.yaml b/lm_eval/tasks/global_mmlu/default/global_mmlu_ko.yaml similarity index 100% rename from lm_eval/tasks/global_mmlu/global_mmlu_ko.yaml rename to lm_eval/tasks/global_mmlu/default/global_mmlu_ko.yaml diff --git a/lm_eval/tasks/global_mmlu/global_mmlu_pt.yaml b/lm_eval/tasks/global_mmlu/default/global_mmlu_pt.yaml similarity index 100% rename from lm_eval/tasks/global_mmlu/global_mmlu_pt.yaml rename to lm_eval/tasks/global_mmlu/default/global_mmlu_pt.yaml diff --git a/lm_eval/tasks/global_mmlu/global_mmlu_sw.yaml b/lm_eval/tasks/global_mmlu/default/global_mmlu_sw.yaml similarity index 100% rename from lm_eval/tasks/global_mmlu/global_mmlu_sw.yaml rename to lm_eval/tasks/global_mmlu/default/global_mmlu_sw.yaml diff --git a/lm_eval/tasks/global_mmlu/global_mmlu_yo.yaml b/lm_eval/tasks/global_mmlu/default/global_mmlu_yo.yaml similarity index 100% rename from lm_eval/tasks/global_mmlu/global_mmlu_yo.yaml rename to lm_eval/tasks/global_mmlu/default/global_mmlu_yo.yaml diff --git a/lm_eval/tasks/global_mmlu/global_mmlu_zh.yaml b/lm_eval/tasks/global_mmlu/default/global_mmlu_zh.yaml similarity index 100% rename from lm_eval/tasks/global_mmlu/global_mmlu_zh.yaml rename to lm_eval/tasks/global_mmlu/default/global_mmlu_zh.yaml diff --git a/lm_eval/tasks/global_mmlu/full/am/_am_template_yaml b/lm_eval/tasks/global_mmlu/full/am/_am_template_yaml new file mode 100644 index 00000000..f52152bb --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/am/_am_template_yaml @@ -0,0 +1,16 @@ +dataset_path: CohereForAI/Global-MMLU +dataset_name: am +test_split: test +fewshot_split: dev +fewshot_config: + sampler: first_n +output_type: multiple_choice +doc_to_text: "{{question.strip()}}\nA. {{option_a}}\nB. {{option_b}}\nC. {{option_c}}\nD. {{option_d}}\nAnswer:" +doc_to_choice: ["A", "B", "C", "D"] +doc_to_target: answer +metric_list: + - metric: acc + aggregation: mean + higher_is_better: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/am/_global_mmlu_full_am.yaml b/lm_eval/tasks/global_mmlu/full/am/_global_mmlu_full_am.yaml new file mode 100644 index 00000000..48fc270a --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/am/_global_mmlu_full_am.yaml @@ -0,0 +1,11 @@ +group: global_mmlu_full_am +task: + - global_mmlu_full_am_stem + - global_mmlu_full_am_other + - global_mmlu_full_am_social_sciences + - global_mmlu_full_am_humanities +aggregate_metric_list: + - metric: acc + weight_by_size: True +metadata: + version: 1.0 diff --git a/lm_eval/tasks/global_mmlu/full/am/_global_mmlu_full_am_humanities.yaml b/lm_eval/tasks/global_mmlu/full/am/_global_mmlu_full_am_humanities.yaml new file mode 100644 index 00000000..e250d14c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/am/_global_mmlu_full_am_humanities.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_am_humanities +task: + - global_mmlu_full_am_humanities_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/am/_global_mmlu_full_am_other.yaml b/lm_eval/tasks/global_mmlu/full/am/_global_mmlu_full_am_other.yaml new file mode 100644 index 00000000..4b5151ce --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/am/_global_mmlu_full_am_other.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_am_other +task: + - global_mmlu_full_am_other_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/am/_global_mmlu_full_am_social_sciences.yaml b/lm_eval/tasks/global_mmlu/full/am/_global_mmlu_full_am_social_sciences.yaml new file mode 100644 index 00000000..f0fbcc1b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/am/_global_mmlu_full_am_social_sciences.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_am_social_sciences +task: + - global_mmlu_full_am_social_sciences_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/am/_global_mmlu_full_am_stem.yaml b/lm_eval/tasks/global_mmlu/full/am/_global_mmlu_full_am_stem.yaml new file mode 100644 index 00000000..b67dfdb7 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/am/_global_mmlu_full_am_stem.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_am_stem +task: + - global_mmlu_full_am_stem_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_abstract_algebra.yaml b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_abstract_algebra.yaml new file mode 100644 index 00000000..06a70dd8 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_abstract_algebra.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _am_template_yaml +process_docs: !function utils.process_abstract_algebra +tag: global_mmlu_full_am_stem_tasks +task: global_mmlu_full_am_abstract_algebra diff --git a/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_anatomy.yaml b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_anatomy.yaml new file mode 100644 index 00000000..7914c3b0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_anatomy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _am_template_yaml +process_docs: !function utils.process_anatomy +tag: global_mmlu_full_am_stem_tasks +task: global_mmlu_full_am_anatomy diff --git a/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_astronomy.yaml b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_astronomy.yaml new file mode 100644 index 00000000..4e7e2a04 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_astronomy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _am_template_yaml +process_docs: !function utils.process_astronomy +tag: global_mmlu_full_am_stem_tasks +task: global_mmlu_full_am_astronomy diff --git a/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_business_ethics.yaml b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_business_ethics.yaml new file mode 100644 index 00000000..a98a9597 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_business_ethics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _am_template_yaml +process_docs: !function utils.process_business_ethics +tag: global_mmlu_full_am_other_tasks +task: global_mmlu_full_am_business_ethics diff --git a/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_clinical_knowledge.yaml b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_clinical_knowledge.yaml new file mode 100644 index 00000000..4c25627f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_clinical_knowledge.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _am_template_yaml +process_docs: !function utils.process_clinical_knowledge +tag: global_mmlu_full_am_other_tasks +task: global_mmlu_full_am_clinical_knowledge diff --git a/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_college_biology.yaml b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_college_biology.yaml new file mode 100644 index 00000000..a8b6661b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_college_biology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _am_template_yaml +process_docs: !function utils.process_college_biology +tag: global_mmlu_full_am_stem_tasks +task: global_mmlu_full_am_college_biology diff --git a/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_college_chemistry.yaml b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_college_chemistry.yaml new file mode 100644 index 00000000..b0d2d2a8 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_college_chemistry.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _am_template_yaml +process_docs: !function utils.process_college_chemistry +tag: global_mmlu_full_am_stem_tasks +task: global_mmlu_full_am_college_chemistry diff --git a/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_college_computer_science.yaml b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_college_computer_science.yaml new file mode 100644 index 00000000..b5c52a82 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_college_computer_science.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _am_template_yaml +process_docs: !function utils.process_college_computer_science +tag: global_mmlu_full_am_stem_tasks +task: global_mmlu_full_am_college_computer_science diff --git a/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_college_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_college_mathematics.yaml new file mode 100644 index 00000000..0b73422e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_college_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _am_template_yaml +process_docs: !function utils.process_college_mathematics +tag: global_mmlu_full_am_stem_tasks +task: global_mmlu_full_am_college_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_college_medicine.yaml b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_college_medicine.yaml new file mode 100644 index 00000000..bd36f40f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_college_medicine.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _am_template_yaml +process_docs: !function utils.process_college_medicine +tag: global_mmlu_full_am_other_tasks +task: global_mmlu_full_am_college_medicine diff --git a/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_college_physics.yaml b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_college_physics.yaml new file mode 100644 index 00000000..009fdc1a --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_college_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _am_template_yaml +process_docs: !function utils.process_college_physics +tag: global_mmlu_full_am_stem_tasks +task: global_mmlu_full_am_college_physics diff --git a/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_computer_security.yaml b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_computer_security.yaml new file mode 100644 index 00000000..3df6247b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_computer_security.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _am_template_yaml +process_docs: !function utils.process_computer_security +tag: global_mmlu_full_am_stem_tasks +task: global_mmlu_full_am_computer_security diff --git a/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_conceptual_physics.yaml b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_conceptual_physics.yaml new file mode 100644 index 00000000..4115ea02 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_conceptual_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _am_template_yaml +process_docs: !function utils.process_conceptual_physics +tag: global_mmlu_full_am_stem_tasks +task: global_mmlu_full_am_conceptual_physics diff --git a/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_econometrics.yaml b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_econometrics.yaml new file mode 100644 index 00000000..87dd12ca --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_econometrics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _am_template_yaml +process_docs: !function utils.process_econometrics +tag: global_mmlu_full_am_social_sciences_tasks +task: global_mmlu_full_am_econometrics diff --git a/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_electrical_engineering.yaml b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_electrical_engineering.yaml new file mode 100644 index 00000000..d8f72619 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_electrical_engineering.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _am_template_yaml +process_docs: !function utils.process_electrical_engineering +tag: global_mmlu_full_am_stem_tasks +task: global_mmlu_full_am_electrical_engineering diff --git a/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_elementary_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_elementary_mathematics.yaml new file mode 100644 index 00000000..455563f1 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_elementary_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _am_template_yaml +process_docs: !function utils.process_elementary_mathematics +tag: global_mmlu_full_am_stem_tasks +task: global_mmlu_full_am_elementary_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_formal_logic.yaml b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_formal_logic.yaml new file mode 100644 index 00000000..5c5babd4 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_formal_logic.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _am_template_yaml +process_docs: !function utils.process_formal_logic +tag: global_mmlu_full_am_humanities_tasks +task: global_mmlu_full_am_formal_logic diff --git a/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_global_facts.yaml b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_global_facts.yaml new file mode 100644 index 00000000..b59d47e4 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_global_facts.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _am_template_yaml +process_docs: !function utils.process_global_facts +tag: global_mmlu_full_am_other_tasks +task: global_mmlu_full_am_global_facts diff --git a/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_high_school_biology.yaml b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_high_school_biology.yaml new file mode 100644 index 00000000..680d4eca --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_high_school_biology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _am_template_yaml +process_docs: !function utils.process_high_school_biology +tag: global_mmlu_full_am_stem_tasks +task: global_mmlu_full_am_high_school_biology diff --git a/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_high_school_chemistry.yaml b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_high_school_chemistry.yaml new file mode 100644 index 00000000..96af7940 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_high_school_chemistry.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _am_template_yaml +process_docs: !function utils.process_high_school_chemistry +tag: global_mmlu_full_am_stem_tasks +task: global_mmlu_full_am_high_school_chemistry diff --git a/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_high_school_computer_science.yaml b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_high_school_computer_science.yaml new file mode 100644 index 00000000..6cd19227 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_high_school_computer_science.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _am_template_yaml +process_docs: !function utils.process_high_school_computer_science +tag: global_mmlu_full_am_stem_tasks +task: global_mmlu_full_am_high_school_computer_science diff --git a/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_high_school_european_history.yaml b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_high_school_european_history.yaml new file mode 100644 index 00000000..e0249142 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_high_school_european_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _am_template_yaml +process_docs: !function utils.process_high_school_european_history +tag: global_mmlu_full_am_humanities_tasks +task: global_mmlu_full_am_high_school_european_history diff --git a/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_high_school_geography.yaml b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_high_school_geography.yaml new file mode 100644 index 00000000..b4925a54 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_high_school_geography.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _am_template_yaml +process_docs: !function utils.process_high_school_geography +tag: global_mmlu_full_am_social_sciences_tasks +task: global_mmlu_full_am_high_school_geography diff --git a/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_high_school_government_and_politics.yaml b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_high_school_government_and_politics.yaml new file mode 100644 index 00000000..d63f1d35 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_high_school_government_and_politics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _am_template_yaml +process_docs: !function utils.process_high_school_government_and_politics +tag: global_mmlu_full_am_social_sciences_tasks +task: global_mmlu_full_am_high_school_government_and_politics diff --git a/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_high_school_macroeconomics.yaml b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_high_school_macroeconomics.yaml new file mode 100644 index 00000000..3c8a0ea6 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_high_school_macroeconomics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _am_template_yaml +process_docs: !function utils.process_high_school_macroeconomics +tag: global_mmlu_full_am_social_sciences_tasks +task: global_mmlu_full_am_high_school_macroeconomics diff --git a/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_high_school_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_high_school_mathematics.yaml new file mode 100644 index 00000000..76a8c3d3 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_high_school_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _am_template_yaml +process_docs: !function utils.process_high_school_mathematics +tag: global_mmlu_full_am_stem_tasks +task: global_mmlu_full_am_high_school_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_high_school_microeconomics.yaml b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_high_school_microeconomics.yaml new file mode 100644 index 00000000..1acbf4e1 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_high_school_microeconomics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _am_template_yaml +process_docs: !function utils.process_high_school_microeconomics +tag: global_mmlu_full_am_social_sciences_tasks +task: global_mmlu_full_am_high_school_microeconomics diff --git a/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_high_school_physics.yaml b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_high_school_physics.yaml new file mode 100644 index 00000000..dcfd9bb9 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_high_school_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _am_template_yaml +process_docs: !function utils.process_high_school_physics +tag: global_mmlu_full_am_stem_tasks +task: global_mmlu_full_am_high_school_physics diff --git a/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_high_school_psychology.yaml b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_high_school_psychology.yaml new file mode 100644 index 00000000..2dd64dc1 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_high_school_psychology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _am_template_yaml +process_docs: !function utils.process_high_school_psychology +tag: global_mmlu_full_am_social_sciences_tasks +task: global_mmlu_full_am_high_school_psychology diff --git a/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_high_school_statistics.yaml b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_high_school_statistics.yaml new file mode 100644 index 00000000..a523f443 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_high_school_statistics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _am_template_yaml +process_docs: !function utils.process_high_school_statistics +tag: global_mmlu_full_am_stem_tasks +task: global_mmlu_full_am_high_school_statistics diff --git a/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_high_school_us_history.yaml b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_high_school_us_history.yaml new file mode 100644 index 00000000..ce233f44 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_high_school_us_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _am_template_yaml +process_docs: !function utils.process_high_school_us_history +tag: global_mmlu_full_am_humanities_tasks +task: global_mmlu_full_am_high_school_us_history diff --git a/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_high_school_world_history.yaml b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_high_school_world_history.yaml new file mode 100644 index 00000000..20aeca5e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_high_school_world_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _am_template_yaml +process_docs: !function utils.process_high_school_world_history +tag: global_mmlu_full_am_humanities_tasks +task: global_mmlu_full_am_high_school_world_history diff --git a/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_human_aging.yaml b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_human_aging.yaml new file mode 100644 index 00000000..18e95e40 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_human_aging.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _am_template_yaml +process_docs: !function utils.process_human_aging +tag: global_mmlu_full_am_other_tasks +task: global_mmlu_full_am_human_aging diff --git a/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_human_sexuality.yaml b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_human_sexuality.yaml new file mode 100644 index 00000000..140f2329 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_human_sexuality.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _am_template_yaml +process_docs: !function utils.process_human_sexuality +tag: global_mmlu_full_am_social_sciences_tasks +task: global_mmlu_full_am_human_sexuality diff --git a/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_international_law.yaml b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_international_law.yaml new file mode 100644 index 00000000..10a2d638 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_international_law.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _am_template_yaml +process_docs: !function utils.process_international_law +tag: global_mmlu_full_am_humanities_tasks +task: global_mmlu_full_am_international_law diff --git a/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_jurisprudence.yaml b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_jurisprudence.yaml new file mode 100644 index 00000000..cd982742 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_jurisprudence.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _am_template_yaml +process_docs: !function utils.process_jurisprudence +tag: global_mmlu_full_am_humanities_tasks +task: global_mmlu_full_am_jurisprudence diff --git a/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_logical_fallacies.yaml b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_logical_fallacies.yaml new file mode 100644 index 00000000..2faf735c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_logical_fallacies.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _am_template_yaml +process_docs: !function utils.process_logical_fallacies +tag: global_mmlu_full_am_humanities_tasks +task: global_mmlu_full_am_logical_fallacies diff --git a/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_machine_learning.yaml b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_machine_learning.yaml new file mode 100644 index 00000000..7f5c8e9b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_machine_learning.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _am_template_yaml +process_docs: !function utils.process_machine_learning +tag: global_mmlu_full_am_stem_tasks +task: global_mmlu_full_am_machine_learning diff --git a/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_management.yaml b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_management.yaml new file mode 100644 index 00000000..08d080a8 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_management.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _am_template_yaml +process_docs: !function utils.process_management +tag: global_mmlu_full_am_other_tasks +task: global_mmlu_full_am_management diff --git a/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_marketing.yaml b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_marketing.yaml new file mode 100644 index 00000000..52b4f7c6 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_marketing.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _am_template_yaml +process_docs: !function utils.process_marketing +tag: global_mmlu_full_am_other_tasks +task: global_mmlu_full_am_marketing diff --git a/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_medical_genetics.yaml b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_medical_genetics.yaml new file mode 100644 index 00000000..32bd2432 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_medical_genetics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _am_template_yaml +process_docs: !function utils.process_medical_genetics +tag: global_mmlu_full_am_other_tasks +task: global_mmlu_full_am_medical_genetics diff --git a/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_miscellaneous.yaml b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_miscellaneous.yaml new file mode 100644 index 00000000..ed5d610d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_miscellaneous.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _am_template_yaml +process_docs: !function utils.process_miscellaneous +tag: global_mmlu_full_am_other_tasks +task: global_mmlu_full_am_miscellaneous diff --git a/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_moral_disputes.yaml b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_moral_disputes.yaml new file mode 100644 index 00000000..bddaebc7 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_moral_disputes.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _am_template_yaml +process_docs: !function utils.process_moral_disputes +tag: global_mmlu_full_am_humanities_tasks +task: global_mmlu_full_am_moral_disputes diff --git a/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_moral_scenarios.yaml b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_moral_scenarios.yaml new file mode 100644 index 00000000..fda69f31 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_moral_scenarios.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _am_template_yaml +process_docs: !function utils.process_moral_scenarios +tag: global_mmlu_full_am_humanities_tasks +task: global_mmlu_full_am_moral_scenarios diff --git a/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_nutrition.yaml b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_nutrition.yaml new file mode 100644 index 00000000..bb0cb08b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_nutrition.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _am_template_yaml +process_docs: !function utils.process_nutrition +tag: global_mmlu_full_am_other_tasks +task: global_mmlu_full_am_nutrition diff --git a/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_philosophy.yaml b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_philosophy.yaml new file mode 100644 index 00000000..484c015e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_philosophy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _am_template_yaml +process_docs: !function utils.process_philosophy +tag: global_mmlu_full_am_humanities_tasks +task: global_mmlu_full_am_philosophy diff --git a/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_prehistory.yaml b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_prehistory.yaml new file mode 100644 index 00000000..6e104f48 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_prehistory.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _am_template_yaml +process_docs: !function utils.process_prehistory +tag: global_mmlu_full_am_humanities_tasks +task: global_mmlu_full_am_prehistory diff --git a/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_professional_accounting.yaml b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_professional_accounting.yaml new file mode 100644 index 00000000..50c9fe50 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_professional_accounting.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _am_template_yaml +process_docs: !function utils.process_professional_accounting +tag: global_mmlu_full_am_other_tasks +task: global_mmlu_full_am_professional_accounting diff --git a/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_professional_law.yaml b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_professional_law.yaml new file mode 100644 index 00000000..df2cf26c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_professional_law.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _am_template_yaml +process_docs: !function utils.process_professional_law +tag: global_mmlu_full_am_humanities_tasks +task: global_mmlu_full_am_professional_law diff --git a/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_professional_medicine.yaml b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_professional_medicine.yaml new file mode 100644 index 00000000..c2860528 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_professional_medicine.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _am_template_yaml +process_docs: !function utils.process_professional_medicine +tag: global_mmlu_full_am_other_tasks +task: global_mmlu_full_am_professional_medicine diff --git a/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_professional_psychology.yaml b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_professional_psychology.yaml new file mode 100644 index 00000000..8562a28d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_professional_psychology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _am_template_yaml +process_docs: !function utils.process_professional_psychology +tag: global_mmlu_full_am_social_sciences_tasks +task: global_mmlu_full_am_professional_psychology diff --git a/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_public_relations.yaml b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_public_relations.yaml new file mode 100644 index 00000000..5cb3186c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_public_relations.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _am_template_yaml +process_docs: !function utils.process_public_relations +tag: global_mmlu_full_am_social_sciences_tasks +task: global_mmlu_full_am_public_relations diff --git a/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_security_studies.yaml b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_security_studies.yaml new file mode 100644 index 00000000..6aa8575e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_security_studies.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _am_template_yaml +process_docs: !function utils.process_security_studies +tag: global_mmlu_full_am_social_sciences_tasks +task: global_mmlu_full_am_security_studies diff --git a/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_sociology.yaml b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_sociology.yaml new file mode 100644 index 00000000..60005bab --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_sociology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _am_template_yaml +process_docs: !function utils.process_sociology +tag: global_mmlu_full_am_social_sciences_tasks +task: global_mmlu_full_am_sociology diff --git a/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_us_foreign_policy.yaml b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_us_foreign_policy.yaml new file mode 100644 index 00000000..374fb14a --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_us_foreign_policy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _am_template_yaml +process_docs: !function utils.process_us_foreign_policy +tag: global_mmlu_full_am_social_sciences_tasks +task: global_mmlu_full_am_us_foreign_policy diff --git a/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_virology.yaml b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_virology.yaml new file mode 100644 index 00000000..9f235299 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_virology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _am_template_yaml +process_docs: !function utils.process_virology +tag: global_mmlu_full_am_other_tasks +task: global_mmlu_full_am_virology diff --git a/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_world_religions.yaml b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_world_religions.yaml new file mode 100644 index 00000000..c169a048 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/am/global_mmlu_full_am_world_religions.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _am_template_yaml +process_docs: !function utils.process_world_religions +tag: global_mmlu_full_am_humanities_tasks +task: global_mmlu_full_am_world_religions diff --git a/lm_eval/tasks/global_mmlu/full/am/utils.py b/lm_eval/tasks/global_mmlu/full/am/utils.py new file mode 100644 index 00000000..7df72cb0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/am/utils.py @@ -0,0 +1,73 @@ +from functools import partial + + +SUBJECTS = [ + "abstract_algebra", + "anatomy", + "astronomy", + "business_ethics", + "clinical_knowledge", + "college_biology", + "college_chemistry", + "college_computer_science", + "college_mathematics", + "college_medicine", + "college_physics", + "computer_security", + "conceptual_physics", + "econometrics", + "electrical_engineering", + "elementary_mathematics", + "formal_logic", + "global_facts", + "high_school_biology", + "high_school_chemistry", + "high_school_computer_science", + "high_school_european_history", + "high_school_geography", + "high_school_government_and_politics", + "high_school_macroeconomics", + "high_school_mathematics", + "high_school_microeconomics", + "high_school_physics", + "high_school_psychology", + "high_school_statistics", + "high_school_us_history", + "high_school_world_history", + "human_aging", + "human_sexuality", + "international_law", + "jurisprudence", + "logical_fallacies", + "machine_learning", + "management", + "marketing", + "medical_genetics", + "miscellaneous", + "moral_disputes", + "moral_scenarios", + "nutrition", + "philosophy", + "prehistory", + "professional_accounting", + "professional_law", + "professional_medicine", + "professional_psychology", + "public_relations", + "security_studies", + "sociology", + "us_foreign_policy", + "virology", + "world_religions", +] + + +def process_docs(dataset, subject): + return dataset.filter(lambda x: x["subject"] == subject) + + +process_functions = { + f"process_{subject}": partial(process_docs, subject=subject) for subject in SUBJECTS +} + +globals().update(process_functions) diff --git a/lm_eval/tasks/global_mmlu/full/ar/_ar_template_yaml b/lm_eval/tasks/global_mmlu/full/ar/_ar_template_yaml new file mode 100644 index 00000000..768bb7f9 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ar/_ar_template_yaml @@ -0,0 +1,16 @@ +dataset_path: CohereForAI/Global-MMLU +dataset_name: ar +test_split: test +fewshot_split: dev +fewshot_config: + sampler: first_n +output_type: multiple_choice +doc_to_text: "{{question.strip()}}\nA. {{option_a}}\nB. {{option_b}}\nC. {{option_c}}\nD. {{option_d}}\nAnswer:" +doc_to_choice: ["A", "B", "C", "D"] +doc_to_target: answer +metric_list: + - metric: acc + aggregation: mean + higher_is_better: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/ar/_global_mmlu_full_ar.yaml b/lm_eval/tasks/global_mmlu/full/ar/_global_mmlu_full_ar.yaml new file mode 100644 index 00000000..61f60b9b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ar/_global_mmlu_full_ar.yaml @@ -0,0 +1,11 @@ +group: global_mmlu_full_ar +task: + - global_mmlu_full_ar_stem + - global_mmlu_full_ar_other + - global_mmlu_full_ar_social_sciences + - global_mmlu_full_ar_humanities +aggregate_metric_list: + - metric: acc + weight_by_size: True +metadata: + version: 1.0 diff --git a/lm_eval/tasks/global_mmlu/full/ar/_global_mmlu_full_ar_humanities.yaml b/lm_eval/tasks/global_mmlu/full/ar/_global_mmlu_full_ar_humanities.yaml new file mode 100644 index 00000000..cfa6d80a --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ar/_global_mmlu_full_ar_humanities.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_ar_humanities +task: + - global_mmlu_full_ar_humanities_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/ar/_global_mmlu_full_ar_other.yaml b/lm_eval/tasks/global_mmlu/full/ar/_global_mmlu_full_ar_other.yaml new file mode 100644 index 00000000..26603f33 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ar/_global_mmlu_full_ar_other.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_ar_other +task: + - global_mmlu_full_ar_other_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/ar/_global_mmlu_full_ar_social_sciences.yaml b/lm_eval/tasks/global_mmlu/full/ar/_global_mmlu_full_ar_social_sciences.yaml new file mode 100644 index 00000000..aca95bc2 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ar/_global_mmlu_full_ar_social_sciences.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_ar_social_sciences +task: + - global_mmlu_full_ar_social_sciences_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/ar/_global_mmlu_full_ar_stem.yaml b/lm_eval/tasks/global_mmlu/full/ar/_global_mmlu_full_ar_stem.yaml new file mode 100644 index 00000000..b91e6c9b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ar/_global_mmlu_full_ar_stem.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_ar_stem +task: + - global_mmlu_full_ar_stem_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_abstract_algebra.yaml b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_abstract_algebra.yaml new file mode 100644 index 00000000..1f044b04 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_abstract_algebra.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ar_template_yaml +process_docs: !function utils.process_abstract_algebra +tag: global_mmlu_full_ar_stem_tasks +task: global_mmlu_full_ar_abstract_algebra diff --git a/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_anatomy.yaml b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_anatomy.yaml new file mode 100644 index 00000000..cd5d0963 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_anatomy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ar_template_yaml +process_docs: !function utils.process_anatomy +tag: global_mmlu_full_ar_stem_tasks +task: global_mmlu_full_ar_anatomy diff --git a/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_astronomy.yaml b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_astronomy.yaml new file mode 100644 index 00000000..d21c00b7 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_astronomy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ar_template_yaml +process_docs: !function utils.process_astronomy +tag: global_mmlu_full_ar_stem_tasks +task: global_mmlu_full_ar_astronomy diff --git a/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_business_ethics.yaml b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_business_ethics.yaml new file mode 100644 index 00000000..a73f5f2d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_business_ethics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ar_template_yaml +process_docs: !function utils.process_business_ethics +tag: global_mmlu_full_ar_other_tasks +task: global_mmlu_full_ar_business_ethics diff --git a/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_clinical_knowledge.yaml b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_clinical_knowledge.yaml new file mode 100644 index 00000000..a9c3d078 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_clinical_knowledge.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ar_template_yaml +process_docs: !function utils.process_clinical_knowledge +tag: global_mmlu_full_ar_other_tasks +task: global_mmlu_full_ar_clinical_knowledge diff --git a/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_college_biology.yaml b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_college_biology.yaml new file mode 100644 index 00000000..6fba6a1b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_college_biology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ar_template_yaml +process_docs: !function utils.process_college_biology +tag: global_mmlu_full_ar_stem_tasks +task: global_mmlu_full_ar_college_biology diff --git a/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_college_chemistry.yaml b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_college_chemistry.yaml new file mode 100644 index 00000000..386ba52d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_college_chemistry.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ar_template_yaml +process_docs: !function utils.process_college_chemistry +tag: global_mmlu_full_ar_stem_tasks +task: global_mmlu_full_ar_college_chemistry diff --git a/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_college_computer_science.yaml b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_college_computer_science.yaml new file mode 100644 index 00000000..9b846715 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_college_computer_science.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ar_template_yaml +process_docs: !function utils.process_college_computer_science +tag: global_mmlu_full_ar_stem_tasks +task: global_mmlu_full_ar_college_computer_science diff --git a/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_college_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_college_mathematics.yaml new file mode 100644 index 00000000..c8d8d090 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_college_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ar_template_yaml +process_docs: !function utils.process_college_mathematics +tag: global_mmlu_full_ar_stem_tasks +task: global_mmlu_full_ar_college_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_college_medicine.yaml b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_college_medicine.yaml new file mode 100644 index 00000000..b988cfee --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_college_medicine.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ar_template_yaml +process_docs: !function utils.process_college_medicine +tag: global_mmlu_full_ar_other_tasks +task: global_mmlu_full_ar_college_medicine diff --git a/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_college_physics.yaml b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_college_physics.yaml new file mode 100644 index 00000000..008a39dc --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_college_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ar_template_yaml +process_docs: !function utils.process_college_physics +tag: global_mmlu_full_ar_stem_tasks +task: global_mmlu_full_ar_college_physics diff --git a/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_computer_security.yaml b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_computer_security.yaml new file mode 100644 index 00000000..34a93535 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_computer_security.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ar_template_yaml +process_docs: !function utils.process_computer_security +tag: global_mmlu_full_ar_stem_tasks +task: global_mmlu_full_ar_computer_security diff --git a/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_conceptual_physics.yaml b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_conceptual_physics.yaml new file mode 100644 index 00000000..ea20efa5 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_conceptual_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ar_template_yaml +process_docs: !function utils.process_conceptual_physics +tag: global_mmlu_full_ar_stem_tasks +task: global_mmlu_full_ar_conceptual_physics diff --git a/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_econometrics.yaml b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_econometrics.yaml new file mode 100644 index 00000000..3a757901 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_econometrics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ar_template_yaml +process_docs: !function utils.process_econometrics +tag: global_mmlu_full_ar_social_sciences_tasks +task: global_mmlu_full_ar_econometrics diff --git a/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_electrical_engineering.yaml b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_electrical_engineering.yaml new file mode 100644 index 00000000..31a4e22e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_electrical_engineering.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ar_template_yaml +process_docs: !function utils.process_electrical_engineering +tag: global_mmlu_full_ar_stem_tasks +task: global_mmlu_full_ar_electrical_engineering diff --git a/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_elementary_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_elementary_mathematics.yaml new file mode 100644 index 00000000..25f4adb9 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_elementary_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ar_template_yaml +process_docs: !function utils.process_elementary_mathematics +tag: global_mmlu_full_ar_stem_tasks +task: global_mmlu_full_ar_elementary_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_formal_logic.yaml b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_formal_logic.yaml new file mode 100644 index 00000000..b2792d56 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_formal_logic.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ar_template_yaml +process_docs: !function utils.process_formal_logic +tag: global_mmlu_full_ar_humanities_tasks +task: global_mmlu_full_ar_formal_logic diff --git a/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_global_facts.yaml b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_global_facts.yaml new file mode 100644 index 00000000..af1bf60b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_global_facts.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ar_template_yaml +process_docs: !function utils.process_global_facts +tag: global_mmlu_full_ar_other_tasks +task: global_mmlu_full_ar_global_facts diff --git a/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_high_school_biology.yaml b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_high_school_biology.yaml new file mode 100644 index 00000000..8f7eaff7 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_high_school_biology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ar_template_yaml +process_docs: !function utils.process_high_school_biology +tag: global_mmlu_full_ar_stem_tasks +task: global_mmlu_full_ar_high_school_biology diff --git a/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_high_school_chemistry.yaml b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_high_school_chemistry.yaml new file mode 100644 index 00000000..8f56395b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_high_school_chemistry.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ar_template_yaml +process_docs: !function utils.process_high_school_chemistry +tag: global_mmlu_full_ar_stem_tasks +task: global_mmlu_full_ar_high_school_chemistry diff --git a/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_high_school_computer_science.yaml b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_high_school_computer_science.yaml new file mode 100644 index 00000000..6e388aed --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_high_school_computer_science.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ar_template_yaml +process_docs: !function utils.process_high_school_computer_science +tag: global_mmlu_full_ar_stem_tasks +task: global_mmlu_full_ar_high_school_computer_science diff --git a/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_high_school_european_history.yaml b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_high_school_european_history.yaml new file mode 100644 index 00000000..741584c5 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_high_school_european_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ar_template_yaml +process_docs: !function utils.process_high_school_european_history +tag: global_mmlu_full_ar_humanities_tasks +task: global_mmlu_full_ar_high_school_european_history diff --git a/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_high_school_geography.yaml b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_high_school_geography.yaml new file mode 100644 index 00000000..3c376967 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_high_school_geography.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ar_template_yaml +process_docs: !function utils.process_high_school_geography +tag: global_mmlu_full_ar_social_sciences_tasks +task: global_mmlu_full_ar_high_school_geography diff --git a/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_high_school_government_and_politics.yaml b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_high_school_government_and_politics.yaml new file mode 100644 index 00000000..c71ada9b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_high_school_government_and_politics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ar_template_yaml +process_docs: !function utils.process_high_school_government_and_politics +tag: global_mmlu_full_ar_social_sciences_tasks +task: global_mmlu_full_ar_high_school_government_and_politics diff --git a/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_high_school_macroeconomics.yaml b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_high_school_macroeconomics.yaml new file mode 100644 index 00000000..0b5f3267 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_high_school_macroeconomics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ar_template_yaml +process_docs: !function utils.process_high_school_macroeconomics +tag: global_mmlu_full_ar_social_sciences_tasks +task: global_mmlu_full_ar_high_school_macroeconomics diff --git a/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_high_school_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_high_school_mathematics.yaml new file mode 100644 index 00000000..cb259ac2 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_high_school_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ar_template_yaml +process_docs: !function utils.process_high_school_mathematics +tag: global_mmlu_full_ar_stem_tasks +task: global_mmlu_full_ar_high_school_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_high_school_microeconomics.yaml b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_high_school_microeconomics.yaml new file mode 100644 index 00000000..c4ab308b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_high_school_microeconomics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ar_template_yaml +process_docs: !function utils.process_high_school_microeconomics +tag: global_mmlu_full_ar_social_sciences_tasks +task: global_mmlu_full_ar_high_school_microeconomics diff --git a/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_high_school_physics.yaml b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_high_school_physics.yaml new file mode 100644 index 00000000..68180e5d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_high_school_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ar_template_yaml +process_docs: !function utils.process_high_school_physics +tag: global_mmlu_full_ar_stem_tasks +task: global_mmlu_full_ar_high_school_physics diff --git a/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_high_school_psychology.yaml b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_high_school_psychology.yaml new file mode 100644 index 00000000..e727ad09 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_high_school_psychology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ar_template_yaml +process_docs: !function utils.process_high_school_psychology +tag: global_mmlu_full_ar_social_sciences_tasks +task: global_mmlu_full_ar_high_school_psychology diff --git a/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_high_school_statistics.yaml b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_high_school_statistics.yaml new file mode 100644 index 00000000..8ff9dd0b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_high_school_statistics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ar_template_yaml +process_docs: !function utils.process_high_school_statistics +tag: global_mmlu_full_ar_stem_tasks +task: global_mmlu_full_ar_high_school_statistics diff --git a/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_high_school_us_history.yaml b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_high_school_us_history.yaml new file mode 100644 index 00000000..668991cf --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_high_school_us_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ar_template_yaml +process_docs: !function utils.process_high_school_us_history +tag: global_mmlu_full_ar_humanities_tasks +task: global_mmlu_full_ar_high_school_us_history diff --git a/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_high_school_world_history.yaml b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_high_school_world_history.yaml new file mode 100644 index 00000000..1df9a553 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_high_school_world_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ar_template_yaml +process_docs: !function utils.process_high_school_world_history +tag: global_mmlu_full_ar_humanities_tasks +task: global_mmlu_full_ar_high_school_world_history diff --git a/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_human_aging.yaml b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_human_aging.yaml new file mode 100644 index 00000000..515a40f0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_human_aging.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ar_template_yaml +process_docs: !function utils.process_human_aging +tag: global_mmlu_full_ar_other_tasks +task: global_mmlu_full_ar_human_aging diff --git a/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_human_sexuality.yaml b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_human_sexuality.yaml new file mode 100644 index 00000000..24caceac --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_human_sexuality.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ar_template_yaml +process_docs: !function utils.process_human_sexuality +tag: global_mmlu_full_ar_social_sciences_tasks +task: global_mmlu_full_ar_human_sexuality diff --git a/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_international_law.yaml b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_international_law.yaml new file mode 100644 index 00000000..a5aee4b2 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_international_law.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ar_template_yaml +process_docs: !function utils.process_international_law +tag: global_mmlu_full_ar_humanities_tasks +task: global_mmlu_full_ar_international_law diff --git a/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_jurisprudence.yaml b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_jurisprudence.yaml new file mode 100644 index 00000000..37781208 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_jurisprudence.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ar_template_yaml +process_docs: !function utils.process_jurisprudence +tag: global_mmlu_full_ar_humanities_tasks +task: global_mmlu_full_ar_jurisprudence diff --git a/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_logical_fallacies.yaml b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_logical_fallacies.yaml new file mode 100644 index 00000000..4365730e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_logical_fallacies.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ar_template_yaml +process_docs: !function utils.process_logical_fallacies +tag: global_mmlu_full_ar_humanities_tasks +task: global_mmlu_full_ar_logical_fallacies diff --git a/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_machine_learning.yaml b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_machine_learning.yaml new file mode 100644 index 00000000..e1fc86e2 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_machine_learning.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ar_template_yaml +process_docs: !function utils.process_machine_learning +tag: global_mmlu_full_ar_stem_tasks +task: global_mmlu_full_ar_machine_learning diff --git a/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_management.yaml b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_management.yaml new file mode 100644 index 00000000..4dc7c8c0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_management.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ar_template_yaml +process_docs: !function utils.process_management +tag: global_mmlu_full_ar_other_tasks +task: global_mmlu_full_ar_management diff --git a/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_marketing.yaml b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_marketing.yaml new file mode 100644 index 00000000..371fb521 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_marketing.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ar_template_yaml +process_docs: !function utils.process_marketing +tag: global_mmlu_full_ar_other_tasks +task: global_mmlu_full_ar_marketing diff --git a/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_medical_genetics.yaml b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_medical_genetics.yaml new file mode 100644 index 00000000..c080b645 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_medical_genetics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ar_template_yaml +process_docs: !function utils.process_medical_genetics +tag: global_mmlu_full_ar_other_tasks +task: global_mmlu_full_ar_medical_genetics diff --git a/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_miscellaneous.yaml b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_miscellaneous.yaml new file mode 100644 index 00000000..7d593ecb --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_miscellaneous.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ar_template_yaml +process_docs: !function utils.process_miscellaneous +tag: global_mmlu_full_ar_other_tasks +task: global_mmlu_full_ar_miscellaneous diff --git a/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_moral_disputes.yaml b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_moral_disputes.yaml new file mode 100644 index 00000000..4021a93e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_moral_disputes.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ar_template_yaml +process_docs: !function utils.process_moral_disputes +tag: global_mmlu_full_ar_humanities_tasks +task: global_mmlu_full_ar_moral_disputes diff --git a/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_moral_scenarios.yaml b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_moral_scenarios.yaml new file mode 100644 index 00000000..f09edd00 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_moral_scenarios.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ar_template_yaml +process_docs: !function utils.process_moral_scenarios +tag: global_mmlu_full_ar_humanities_tasks +task: global_mmlu_full_ar_moral_scenarios diff --git a/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_nutrition.yaml b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_nutrition.yaml new file mode 100644 index 00000000..8d8577cb --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_nutrition.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ar_template_yaml +process_docs: !function utils.process_nutrition +tag: global_mmlu_full_ar_other_tasks +task: global_mmlu_full_ar_nutrition diff --git a/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_philosophy.yaml b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_philosophy.yaml new file mode 100644 index 00000000..733b77ce --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_philosophy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ar_template_yaml +process_docs: !function utils.process_philosophy +tag: global_mmlu_full_ar_humanities_tasks +task: global_mmlu_full_ar_philosophy diff --git a/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_prehistory.yaml b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_prehistory.yaml new file mode 100644 index 00000000..4d1bf141 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_prehistory.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ar_template_yaml +process_docs: !function utils.process_prehistory +tag: global_mmlu_full_ar_humanities_tasks +task: global_mmlu_full_ar_prehistory diff --git a/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_professional_accounting.yaml b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_professional_accounting.yaml new file mode 100644 index 00000000..45b07299 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_professional_accounting.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ar_template_yaml +process_docs: !function utils.process_professional_accounting +tag: global_mmlu_full_ar_other_tasks +task: global_mmlu_full_ar_professional_accounting diff --git a/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_professional_law.yaml b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_professional_law.yaml new file mode 100644 index 00000000..6e33b583 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_professional_law.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ar_template_yaml +process_docs: !function utils.process_professional_law +tag: global_mmlu_full_ar_humanities_tasks +task: global_mmlu_full_ar_professional_law diff --git a/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_professional_medicine.yaml b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_professional_medicine.yaml new file mode 100644 index 00000000..4cd0a17a --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_professional_medicine.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ar_template_yaml +process_docs: !function utils.process_professional_medicine +tag: global_mmlu_full_ar_other_tasks +task: global_mmlu_full_ar_professional_medicine diff --git a/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_professional_psychology.yaml b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_professional_psychology.yaml new file mode 100644 index 00000000..f035162d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_professional_psychology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ar_template_yaml +process_docs: !function utils.process_professional_psychology +tag: global_mmlu_full_ar_social_sciences_tasks +task: global_mmlu_full_ar_professional_psychology diff --git a/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_public_relations.yaml b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_public_relations.yaml new file mode 100644 index 00000000..3d4dd34f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_public_relations.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ar_template_yaml +process_docs: !function utils.process_public_relations +tag: global_mmlu_full_ar_social_sciences_tasks +task: global_mmlu_full_ar_public_relations diff --git a/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_security_studies.yaml b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_security_studies.yaml new file mode 100644 index 00000000..f2245b52 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_security_studies.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ar_template_yaml +process_docs: !function utils.process_security_studies +tag: global_mmlu_full_ar_social_sciences_tasks +task: global_mmlu_full_ar_security_studies diff --git a/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_sociology.yaml b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_sociology.yaml new file mode 100644 index 00000000..dd920305 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_sociology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ar_template_yaml +process_docs: !function utils.process_sociology +tag: global_mmlu_full_ar_social_sciences_tasks +task: global_mmlu_full_ar_sociology diff --git a/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_us_foreign_policy.yaml b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_us_foreign_policy.yaml new file mode 100644 index 00000000..0f38b855 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_us_foreign_policy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ar_template_yaml +process_docs: !function utils.process_us_foreign_policy +tag: global_mmlu_full_ar_social_sciences_tasks +task: global_mmlu_full_ar_us_foreign_policy diff --git a/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_virology.yaml b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_virology.yaml new file mode 100644 index 00000000..f3be1f8f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_virology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ar_template_yaml +process_docs: !function utils.process_virology +tag: global_mmlu_full_ar_other_tasks +task: global_mmlu_full_ar_virology diff --git a/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_world_religions.yaml b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_world_religions.yaml new file mode 100644 index 00000000..7c7f01a5 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ar/global_mmlu_full_ar_world_religions.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ar_template_yaml +process_docs: !function utils.process_world_religions +tag: global_mmlu_full_ar_humanities_tasks +task: global_mmlu_full_ar_world_religions diff --git a/lm_eval/tasks/global_mmlu/full/ar/utils.py b/lm_eval/tasks/global_mmlu/full/ar/utils.py new file mode 100644 index 00000000..7df72cb0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ar/utils.py @@ -0,0 +1,73 @@ +from functools import partial + + +SUBJECTS = [ + "abstract_algebra", + "anatomy", + "astronomy", + "business_ethics", + "clinical_knowledge", + "college_biology", + "college_chemistry", + "college_computer_science", + "college_mathematics", + "college_medicine", + "college_physics", + "computer_security", + "conceptual_physics", + "econometrics", + "electrical_engineering", + "elementary_mathematics", + "formal_logic", + "global_facts", + "high_school_biology", + "high_school_chemistry", + "high_school_computer_science", + "high_school_european_history", + "high_school_geography", + "high_school_government_and_politics", + "high_school_macroeconomics", + "high_school_mathematics", + "high_school_microeconomics", + "high_school_physics", + "high_school_psychology", + "high_school_statistics", + "high_school_us_history", + "high_school_world_history", + "human_aging", + "human_sexuality", + "international_law", + "jurisprudence", + "logical_fallacies", + "machine_learning", + "management", + "marketing", + "medical_genetics", + "miscellaneous", + "moral_disputes", + "moral_scenarios", + "nutrition", + "philosophy", + "prehistory", + "professional_accounting", + "professional_law", + "professional_medicine", + "professional_psychology", + "public_relations", + "security_studies", + "sociology", + "us_foreign_policy", + "virology", + "world_religions", +] + + +def process_docs(dataset, subject): + return dataset.filter(lambda x: x["subject"] == subject) + + +process_functions = { + f"process_{subject}": partial(process_docs, subject=subject) for subject in SUBJECTS +} + +globals().update(process_functions) diff --git a/lm_eval/tasks/global_mmlu/full/bn/_bn_template_yaml b/lm_eval/tasks/global_mmlu/full/bn/_bn_template_yaml new file mode 100644 index 00000000..f388063d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/bn/_bn_template_yaml @@ -0,0 +1,16 @@ +dataset_path: CohereForAI/Global-MMLU +dataset_name: bn +test_split: test +fewshot_split: dev +fewshot_config: + sampler: first_n +output_type: multiple_choice +doc_to_text: "{{question.strip()}}\nA. {{option_a}}\nB. {{option_b}}\nC. {{option_c}}\nD. {{option_d}}\nAnswer:" +doc_to_choice: ["A", "B", "C", "D"] +doc_to_target: answer +metric_list: + - metric: acc + aggregation: mean + higher_is_better: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/bn/_global_mmlu_full_bn.yaml b/lm_eval/tasks/global_mmlu/full/bn/_global_mmlu_full_bn.yaml new file mode 100644 index 00000000..f1c91f09 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/bn/_global_mmlu_full_bn.yaml @@ -0,0 +1,11 @@ +group: global_mmlu_full_bn +task: + - global_mmlu_full_bn_stem + - global_mmlu_full_bn_other + - global_mmlu_full_bn_social_sciences + - global_mmlu_full_bn_humanities +aggregate_metric_list: + - metric: acc + weight_by_size: True +metadata: + version: 1.0 diff --git a/lm_eval/tasks/global_mmlu/full/bn/_global_mmlu_full_bn_humanities.yaml b/lm_eval/tasks/global_mmlu/full/bn/_global_mmlu_full_bn_humanities.yaml new file mode 100644 index 00000000..acd1ab01 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/bn/_global_mmlu_full_bn_humanities.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_bn_humanities +task: + - global_mmlu_full_bn_humanities_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/bn/_global_mmlu_full_bn_other.yaml b/lm_eval/tasks/global_mmlu/full/bn/_global_mmlu_full_bn_other.yaml new file mode 100644 index 00000000..d2160298 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/bn/_global_mmlu_full_bn_other.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_bn_other +task: + - global_mmlu_full_bn_other_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/bn/_global_mmlu_full_bn_social_sciences.yaml b/lm_eval/tasks/global_mmlu/full/bn/_global_mmlu_full_bn_social_sciences.yaml new file mode 100644 index 00000000..c359b359 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/bn/_global_mmlu_full_bn_social_sciences.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_bn_social_sciences +task: + - global_mmlu_full_bn_social_sciences_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/bn/_global_mmlu_full_bn_stem.yaml b/lm_eval/tasks/global_mmlu/full/bn/_global_mmlu_full_bn_stem.yaml new file mode 100644 index 00000000..2c78c4ce --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/bn/_global_mmlu_full_bn_stem.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_bn_stem +task: + - global_mmlu_full_bn_stem_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_abstract_algebra.yaml b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_abstract_algebra.yaml new file mode 100644 index 00000000..5bb7bb61 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_abstract_algebra.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _bn_template_yaml +process_docs: !function utils.process_abstract_algebra +tag: global_mmlu_full_bn_stem_tasks +task: global_mmlu_full_bn_abstract_algebra diff --git a/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_anatomy.yaml b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_anatomy.yaml new file mode 100644 index 00000000..d49070f1 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_anatomy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _bn_template_yaml +process_docs: !function utils.process_anatomy +tag: global_mmlu_full_bn_stem_tasks +task: global_mmlu_full_bn_anatomy diff --git a/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_astronomy.yaml b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_astronomy.yaml new file mode 100644 index 00000000..2e6dbc97 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_astronomy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _bn_template_yaml +process_docs: !function utils.process_astronomy +tag: global_mmlu_full_bn_stem_tasks +task: global_mmlu_full_bn_astronomy diff --git a/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_business_ethics.yaml b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_business_ethics.yaml new file mode 100644 index 00000000..8c45a0e2 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_business_ethics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _bn_template_yaml +process_docs: !function utils.process_business_ethics +tag: global_mmlu_full_bn_other_tasks +task: global_mmlu_full_bn_business_ethics diff --git a/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_clinical_knowledge.yaml b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_clinical_knowledge.yaml new file mode 100644 index 00000000..97e17570 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_clinical_knowledge.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _bn_template_yaml +process_docs: !function utils.process_clinical_knowledge +tag: global_mmlu_full_bn_other_tasks +task: global_mmlu_full_bn_clinical_knowledge diff --git a/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_college_biology.yaml b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_college_biology.yaml new file mode 100644 index 00000000..9bf0b34c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_college_biology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _bn_template_yaml +process_docs: !function utils.process_college_biology +tag: global_mmlu_full_bn_stem_tasks +task: global_mmlu_full_bn_college_biology diff --git a/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_college_chemistry.yaml b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_college_chemistry.yaml new file mode 100644 index 00000000..cb5a2600 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_college_chemistry.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _bn_template_yaml +process_docs: !function utils.process_college_chemistry +tag: global_mmlu_full_bn_stem_tasks +task: global_mmlu_full_bn_college_chemistry diff --git a/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_college_computer_science.yaml b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_college_computer_science.yaml new file mode 100644 index 00000000..ecd60e54 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_college_computer_science.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _bn_template_yaml +process_docs: !function utils.process_college_computer_science +tag: global_mmlu_full_bn_stem_tasks +task: global_mmlu_full_bn_college_computer_science diff --git a/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_college_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_college_mathematics.yaml new file mode 100644 index 00000000..5fb69d57 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_college_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _bn_template_yaml +process_docs: !function utils.process_college_mathematics +tag: global_mmlu_full_bn_stem_tasks +task: global_mmlu_full_bn_college_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_college_medicine.yaml b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_college_medicine.yaml new file mode 100644 index 00000000..442045f9 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_college_medicine.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _bn_template_yaml +process_docs: !function utils.process_college_medicine +tag: global_mmlu_full_bn_other_tasks +task: global_mmlu_full_bn_college_medicine diff --git a/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_college_physics.yaml b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_college_physics.yaml new file mode 100644 index 00000000..6849ffbb --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_college_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _bn_template_yaml +process_docs: !function utils.process_college_physics +tag: global_mmlu_full_bn_stem_tasks +task: global_mmlu_full_bn_college_physics diff --git a/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_computer_security.yaml b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_computer_security.yaml new file mode 100644 index 00000000..184097f8 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_computer_security.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _bn_template_yaml +process_docs: !function utils.process_computer_security +tag: global_mmlu_full_bn_stem_tasks +task: global_mmlu_full_bn_computer_security diff --git a/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_conceptual_physics.yaml b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_conceptual_physics.yaml new file mode 100644 index 00000000..4dc8a2c2 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_conceptual_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _bn_template_yaml +process_docs: !function utils.process_conceptual_physics +tag: global_mmlu_full_bn_stem_tasks +task: global_mmlu_full_bn_conceptual_physics diff --git a/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_econometrics.yaml b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_econometrics.yaml new file mode 100644 index 00000000..941f6355 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_econometrics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _bn_template_yaml +process_docs: !function utils.process_econometrics +tag: global_mmlu_full_bn_social_sciences_tasks +task: global_mmlu_full_bn_econometrics diff --git a/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_electrical_engineering.yaml b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_electrical_engineering.yaml new file mode 100644 index 00000000..5918b08a --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_electrical_engineering.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _bn_template_yaml +process_docs: !function utils.process_electrical_engineering +tag: global_mmlu_full_bn_stem_tasks +task: global_mmlu_full_bn_electrical_engineering diff --git a/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_elementary_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_elementary_mathematics.yaml new file mode 100644 index 00000000..8f7d1f10 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_elementary_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _bn_template_yaml +process_docs: !function utils.process_elementary_mathematics +tag: global_mmlu_full_bn_stem_tasks +task: global_mmlu_full_bn_elementary_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_formal_logic.yaml b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_formal_logic.yaml new file mode 100644 index 00000000..b54c80db --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_formal_logic.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _bn_template_yaml +process_docs: !function utils.process_formal_logic +tag: global_mmlu_full_bn_humanities_tasks +task: global_mmlu_full_bn_formal_logic diff --git a/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_global_facts.yaml b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_global_facts.yaml new file mode 100644 index 00000000..371d61cd --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_global_facts.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _bn_template_yaml +process_docs: !function utils.process_global_facts +tag: global_mmlu_full_bn_other_tasks +task: global_mmlu_full_bn_global_facts diff --git a/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_high_school_biology.yaml b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_high_school_biology.yaml new file mode 100644 index 00000000..4f2c8731 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_high_school_biology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _bn_template_yaml +process_docs: !function utils.process_high_school_biology +tag: global_mmlu_full_bn_stem_tasks +task: global_mmlu_full_bn_high_school_biology diff --git a/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_high_school_chemistry.yaml b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_high_school_chemistry.yaml new file mode 100644 index 00000000..0022c824 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_high_school_chemistry.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _bn_template_yaml +process_docs: !function utils.process_high_school_chemistry +tag: global_mmlu_full_bn_stem_tasks +task: global_mmlu_full_bn_high_school_chemistry diff --git a/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_high_school_computer_science.yaml b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_high_school_computer_science.yaml new file mode 100644 index 00000000..62ed6c6c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_high_school_computer_science.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _bn_template_yaml +process_docs: !function utils.process_high_school_computer_science +tag: global_mmlu_full_bn_stem_tasks +task: global_mmlu_full_bn_high_school_computer_science diff --git a/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_high_school_european_history.yaml b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_high_school_european_history.yaml new file mode 100644 index 00000000..b9118a11 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_high_school_european_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _bn_template_yaml +process_docs: !function utils.process_high_school_european_history +tag: global_mmlu_full_bn_humanities_tasks +task: global_mmlu_full_bn_high_school_european_history diff --git a/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_high_school_geography.yaml b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_high_school_geography.yaml new file mode 100644 index 00000000..a7fa3c1b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_high_school_geography.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _bn_template_yaml +process_docs: !function utils.process_high_school_geography +tag: global_mmlu_full_bn_social_sciences_tasks +task: global_mmlu_full_bn_high_school_geography diff --git a/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_high_school_government_and_politics.yaml b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_high_school_government_and_politics.yaml new file mode 100644 index 00000000..067ec0ea --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_high_school_government_and_politics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _bn_template_yaml +process_docs: !function utils.process_high_school_government_and_politics +tag: global_mmlu_full_bn_social_sciences_tasks +task: global_mmlu_full_bn_high_school_government_and_politics diff --git a/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_high_school_macroeconomics.yaml b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_high_school_macroeconomics.yaml new file mode 100644 index 00000000..12c775ab --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_high_school_macroeconomics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _bn_template_yaml +process_docs: !function utils.process_high_school_macroeconomics +tag: global_mmlu_full_bn_social_sciences_tasks +task: global_mmlu_full_bn_high_school_macroeconomics diff --git a/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_high_school_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_high_school_mathematics.yaml new file mode 100644 index 00000000..82809b15 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_high_school_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _bn_template_yaml +process_docs: !function utils.process_high_school_mathematics +tag: global_mmlu_full_bn_stem_tasks +task: global_mmlu_full_bn_high_school_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_high_school_microeconomics.yaml b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_high_school_microeconomics.yaml new file mode 100644 index 00000000..a14eb703 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_high_school_microeconomics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _bn_template_yaml +process_docs: !function utils.process_high_school_microeconomics +tag: global_mmlu_full_bn_social_sciences_tasks +task: global_mmlu_full_bn_high_school_microeconomics diff --git a/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_high_school_physics.yaml b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_high_school_physics.yaml new file mode 100644 index 00000000..a84f85fd --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_high_school_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _bn_template_yaml +process_docs: !function utils.process_high_school_physics +tag: global_mmlu_full_bn_stem_tasks +task: global_mmlu_full_bn_high_school_physics diff --git a/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_high_school_psychology.yaml b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_high_school_psychology.yaml new file mode 100644 index 00000000..5b10c59d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_high_school_psychology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _bn_template_yaml +process_docs: !function utils.process_high_school_psychology +tag: global_mmlu_full_bn_social_sciences_tasks +task: global_mmlu_full_bn_high_school_psychology diff --git a/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_high_school_statistics.yaml b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_high_school_statistics.yaml new file mode 100644 index 00000000..f4231ea2 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_high_school_statistics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _bn_template_yaml +process_docs: !function utils.process_high_school_statistics +tag: global_mmlu_full_bn_stem_tasks +task: global_mmlu_full_bn_high_school_statistics diff --git a/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_high_school_us_history.yaml b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_high_school_us_history.yaml new file mode 100644 index 00000000..28dbddf7 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_high_school_us_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _bn_template_yaml +process_docs: !function utils.process_high_school_us_history +tag: global_mmlu_full_bn_humanities_tasks +task: global_mmlu_full_bn_high_school_us_history diff --git a/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_high_school_world_history.yaml b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_high_school_world_history.yaml new file mode 100644 index 00000000..fc8aec7d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_high_school_world_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _bn_template_yaml +process_docs: !function utils.process_high_school_world_history +tag: global_mmlu_full_bn_humanities_tasks +task: global_mmlu_full_bn_high_school_world_history diff --git a/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_human_aging.yaml b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_human_aging.yaml new file mode 100644 index 00000000..16a3c204 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_human_aging.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _bn_template_yaml +process_docs: !function utils.process_human_aging +tag: global_mmlu_full_bn_other_tasks +task: global_mmlu_full_bn_human_aging diff --git a/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_human_sexuality.yaml b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_human_sexuality.yaml new file mode 100644 index 00000000..a25244a5 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_human_sexuality.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _bn_template_yaml +process_docs: !function utils.process_human_sexuality +tag: global_mmlu_full_bn_social_sciences_tasks +task: global_mmlu_full_bn_human_sexuality diff --git a/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_international_law.yaml b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_international_law.yaml new file mode 100644 index 00000000..b47f516d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_international_law.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _bn_template_yaml +process_docs: !function utils.process_international_law +tag: global_mmlu_full_bn_humanities_tasks +task: global_mmlu_full_bn_international_law diff --git a/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_jurisprudence.yaml b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_jurisprudence.yaml new file mode 100644 index 00000000..08ab51e2 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_jurisprudence.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _bn_template_yaml +process_docs: !function utils.process_jurisprudence +tag: global_mmlu_full_bn_humanities_tasks +task: global_mmlu_full_bn_jurisprudence diff --git a/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_logical_fallacies.yaml b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_logical_fallacies.yaml new file mode 100644 index 00000000..0885a1a9 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_logical_fallacies.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _bn_template_yaml +process_docs: !function utils.process_logical_fallacies +tag: global_mmlu_full_bn_humanities_tasks +task: global_mmlu_full_bn_logical_fallacies diff --git a/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_machine_learning.yaml b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_machine_learning.yaml new file mode 100644 index 00000000..f0eb0997 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_machine_learning.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _bn_template_yaml +process_docs: !function utils.process_machine_learning +tag: global_mmlu_full_bn_stem_tasks +task: global_mmlu_full_bn_machine_learning diff --git a/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_management.yaml b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_management.yaml new file mode 100644 index 00000000..d006b411 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_management.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _bn_template_yaml +process_docs: !function utils.process_management +tag: global_mmlu_full_bn_other_tasks +task: global_mmlu_full_bn_management diff --git a/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_marketing.yaml b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_marketing.yaml new file mode 100644 index 00000000..520f9469 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_marketing.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _bn_template_yaml +process_docs: !function utils.process_marketing +tag: global_mmlu_full_bn_other_tasks +task: global_mmlu_full_bn_marketing diff --git a/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_medical_genetics.yaml b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_medical_genetics.yaml new file mode 100644 index 00000000..88caa977 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_medical_genetics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _bn_template_yaml +process_docs: !function utils.process_medical_genetics +tag: global_mmlu_full_bn_other_tasks +task: global_mmlu_full_bn_medical_genetics diff --git a/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_miscellaneous.yaml b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_miscellaneous.yaml new file mode 100644 index 00000000..9ce31f7b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_miscellaneous.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _bn_template_yaml +process_docs: !function utils.process_miscellaneous +tag: global_mmlu_full_bn_other_tasks +task: global_mmlu_full_bn_miscellaneous diff --git a/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_moral_disputes.yaml b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_moral_disputes.yaml new file mode 100644 index 00000000..44403216 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_moral_disputes.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _bn_template_yaml +process_docs: !function utils.process_moral_disputes +tag: global_mmlu_full_bn_humanities_tasks +task: global_mmlu_full_bn_moral_disputes diff --git a/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_moral_scenarios.yaml b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_moral_scenarios.yaml new file mode 100644 index 00000000..e5f59e15 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_moral_scenarios.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _bn_template_yaml +process_docs: !function utils.process_moral_scenarios +tag: global_mmlu_full_bn_humanities_tasks +task: global_mmlu_full_bn_moral_scenarios diff --git a/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_nutrition.yaml b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_nutrition.yaml new file mode 100644 index 00000000..422bba55 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_nutrition.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _bn_template_yaml +process_docs: !function utils.process_nutrition +tag: global_mmlu_full_bn_other_tasks +task: global_mmlu_full_bn_nutrition diff --git a/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_philosophy.yaml b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_philosophy.yaml new file mode 100644 index 00000000..62af532b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_philosophy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _bn_template_yaml +process_docs: !function utils.process_philosophy +tag: global_mmlu_full_bn_humanities_tasks +task: global_mmlu_full_bn_philosophy diff --git a/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_prehistory.yaml b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_prehistory.yaml new file mode 100644 index 00000000..dc49d36c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_prehistory.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _bn_template_yaml +process_docs: !function utils.process_prehistory +tag: global_mmlu_full_bn_humanities_tasks +task: global_mmlu_full_bn_prehistory diff --git a/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_professional_accounting.yaml b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_professional_accounting.yaml new file mode 100644 index 00000000..bf72a6a4 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_professional_accounting.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _bn_template_yaml +process_docs: !function utils.process_professional_accounting +tag: global_mmlu_full_bn_other_tasks +task: global_mmlu_full_bn_professional_accounting diff --git a/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_professional_law.yaml b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_professional_law.yaml new file mode 100644 index 00000000..f49fb142 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_professional_law.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _bn_template_yaml +process_docs: !function utils.process_professional_law +tag: global_mmlu_full_bn_humanities_tasks +task: global_mmlu_full_bn_professional_law diff --git a/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_professional_medicine.yaml b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_professional_medicine.yaml new file mode 100644 index 00000000..3c53d77a --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_professional_medicine.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _bn_template_yaml +process_docs: !function utils.process_professional_medicine +tag: global_mmlu_full_bn_other_tasks +task: global_mmlu_full_bn_professional_medicine diff --git a/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_professional_psychology.yaml b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_professional_psychology.yaml new file mode 100644 index 00000000..a50c5cbf --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_professional_psychology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _bn_template_yaml +process_docs: !function utils.process_professional_psychology +tag: global_mmlu_full_bn_social_sciences_tasks +task: global_mmlu_full_bn_professional_psychology diff --git a/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_public_relations.yaml b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_public_relations.yaml new file mode 100644 index 00000000..00e2742a --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_public_relations.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _bn_template_yaml +process_docs: !function utils.process_public_relations +tag: global_mmlu_full_bn_social_sciences_tasks +task: global_mmlu_full_bn_public_relations diff --git a/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_security_studies.yaml b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_security_studies.yaml new file mode 100644 index 00000000..5a0e7612 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_security_studies.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _bn_template_yaml +process_docs: !function utils.process_security_studies +tag: global_mmlu_full_bn_social_sciences_tasks +task: global_mmlu_full_bn_security_studies diff --git a/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_sociology.yaml b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_sociology.yaml new file mode 100644 index 00000000..e8820319 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_sociology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _bn_template_yaml +process_docs: !function utils.process_sociology +tag: global_mmlu_full_bn_social_sciences_tasks +task: global_mmlu_full_bn_sociology diff --git a/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_us_foreign_policy.yaml b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_us_foreign_policy.yaml new file mode 100644 index 00000000..42be796a --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_us_foreign_policy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _bn_template_yaml +process_docs: !function utils.process_us_foreign_policy +tag: global_mmlu_full_bn_social_sciences_tasks +task: global_mmlu_full_bn_us_foreign_policy diff --git a/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_virology.yaml b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_virology.yaml new file mode 100644 index 00000000..3959f006 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_virology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _bn_template_yaml +process_docs: !function utils.process_virology +tag: global_mmlu_full_bn_other_tasks +task: global_mmlu_full_bn_virology diff --git a/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_world_religions.yaml b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_world_religions.yaml new file mode 100644 index 00000000..15ee9efc --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_world_religions.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _bn_template_yaml +process_docs: !function utils.process_world_religions +tag: global_mmlu_full_bn_humanities_tasks +task: global_mmlu_full_bn_world_religions diff --git a/lm_eval/tasks/global_mmlu/full/bn/utils.py b/lm_eval/tasks/global_mmlu/full/bn/utils.py new file mode 100644 index 00000000..7df72cb0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/bn/utils.py @@ -0,0 +1,73 @@ +from functools import partial + + +SUBJECTS = [ + "abstract_algebra", + "anatomy", + "astronomy", + "business_ethics", + "clinical_knowledge", + "college_biology", + "college_chemistry", + "college_computer_science", + "college_mathematics", + "college_medicine", + "college_physics", + "computer_security", + "conceptual_physics", + "econometrics", + "electrical_engineering", + "elementary_mathematics", + "formal_logic", + "global_facts", + "high_school_biology", + "high_school_chemistry", + "high_school_computer_science", + "high_school_european_history", + "high_school_geography", + "high_school_government_and_politics", + "high_school_macroeconomics", + "high_school_mathematics", + "high_school_microeconomics", + "high_school_physics", + "high_school_psychology", + "high_school_statistics", + "high_school_us_history", + "high_school_world_history", + "human_aging", + "human_sexuality", + "international_law", + "jurisprudence", + "logical_fallacies", + "machine_learning", + "management", + "marketing", + "medical_genetics", + "miscellaneous", + "moral_disputes", + "moral_scenarios", + "nutrition", + "philosophy", + "prehistory", + "professional_accounting", + "professional_law", + "professional_medicine", + "professional_psychology", + "public_relations", + "security_studies", + "sociology", + "us_foreign_policy", + "virology", + "world_religions", +] + + +def process_docs(dataset, subject): + return dataset.filter(lambda x: x["subject"] == subject) + + +process_functions = { + f"process_{subject}": partial(process_docs, subject=subject) for subject in SUBJECTS +} + +globals().update(process_functions) diff --git a/lm_eval/tasks/global_mmlu/full/cs/_cs_template_yaml b/lm_eval/tasks/global_mmlu/full/cs/_cs_template_yaml new file mode 100644 index 00000000..ce2189a0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/cs/_cs_template_yaml @@ -0,0 +1,16 @@ +dataset_path: CohereForAI/Global-MMLU +dataset_name: cs +test_split: test +fewshot_split: dev +fewshot_config: + sampler: first_n +output_type: multiple_choice +doc_to_text: "{{question.strip()}}\nA. {{option_a}}\nB. {{option_b}}\nC. {{option_c}}\nD. {{option_d}}\nAnswer:" +doc_to_choice: ["A", "B", "C", "D"] +doc_to_target: answer +metric_list: + - metric: acc + aggregation: mean + higher_is_better: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/cs/_global_mmlu_full_cs.yaml b/lm_eval/tasks/global_mmlu/full/cs/_global_mmlu_full_cs.yaml new file mode 100644 index 00000000..977b0051 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/cs/_global_mmlu_full_cs.yaml @@ -0,0 +1,11 @@ +group: global_mmlu_full_cs +task: + - global_mmlu_full_cs_stem + - global_mmlu_full_cs_other + - global_mmlu_full_cs_social_sciences + - global_mmlu_full_cs_humanities +aggregate_metric_list: + - metric: acc + weight_by_size: True +metadata: + version: 1.0 diff --git a/lm_eval/tasks/global_mmlu/full/cs/_global_mmlu_full_cs_humanities.yaml b/lm_eval/tasks/global_mmlu/full/cs/_global_mmlu_full_cs_humanities.yaml new file mode 100644 index 00000000..b4b4aff3 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/cs/_global_mmlu_full_cs_humanities.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_cs_humanities +task: + - global_mmlu_full_cs_humanities_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/cs/_global_mmlu_full_cs_other.yaml b/lm_eval/tasks/global_mmlu/full/cs/_global_mmlu_full_cs_other.yaml new file mode 100644 index 00000000..302912e4 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/cs/_global_mmlu_full_cs_other.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_cs_other +task: + - global_mmlu_full_cs_other_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/cs/_global_mmlu_full_cs_social_sciences.yaml b/lm_eval/tasks/global_mmlu/full/cs/_global_mmlu_full_cs_social_sciences.yaml new file mode 100644 index 00000000..d3fed76e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/cs/_global_mmlu_full_cs_social_sciences.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_cs_social_sciences +task: + - global_mmlu_full_cs_social_sciences_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/cs/_global_mmlu_full_cs_stem.yaml b/lm_eval/tasks/global_mmlu/full/cs/_global_mmlu_full_cs_stem.yaml new file mode 100644 index 00000000..898bb092 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/cs/_global_mmlu_full_cs_stem.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_cs_stem +task: + - global_mmlu_full_cs_stem_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_abstract_algebra.yaml b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_abstract_algebra.yaml new file mode 100644 index 00000000..40431ec9 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_abstract_algebra.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _cs_template_yaml +process_docs: !function utils.process_abstract_algebra +tag: global_mmlu_full_cs_stem_tasks +task: global_mmlu_full_cs_abstract_algebra diff --git a/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_anatomy.yaml b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_anatomy.yaml new file mode 100644 index 00000000..97d7354d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_anatomy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _cs_template_yaml +process_docs: !function utils.process_anatomy +tag: global_mmlu_full_cs_stem_tasks +task: global_mmlu_full_cs_anatomy diff --git a/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_astronomy.yaml b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_astronomy.yaml new file mode 100644 index 00000000..5b5a5f99 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_astronomy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _cs_template_yaml +process_docs: !function utils.process_astronomy +tag: global_mmlu_full_cs_stem_tasks +task: global_mmlu_full_cs_astronomy diff --git a/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_business_ethics.yaml b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_business_ethics.yaml new file mode 100644 index 00000000..6db79c52 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_business_ethics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _cs_template_yaml +process_docs: !function utils.process_business_ethics +tag: global_mmlu_full_cs_other_tasks +task: global_mmlu_full_cs_business_ethics diff --git a/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_clinical_knowledge.yaml b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_clinical_knowledge.yaml new file mode 100644 index 00000000..3a17c605 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_clinical_knowledge.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _cs_template_yaml +process_docs: !function utils.process_clinical_knowledge +tag: global_mmlu_full_cs_other_tasks +task: global_mmlu_full_cs_clinical_knowledge diff --git a/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_college_biology.yaml b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_college_biology.yaml new file mode 100644 index 00000000..9c6597b4 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_college_biology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _cs_template_yaml +process_docs: !function utils.process_college_biology +tag: global_mmlu_full_cs_stem_tasks +task: global_mmlu_full_cs_college_biology diff --git a/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_college_chemistry.yaml b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_college_chemistry.yaml new file mode 100644 index 00000000..713af5c3 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_college_chemistry.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _cs_template_yaml +process_docs: !function utils.process_college_chemistry +tag: global_mmlu_full_cs_stem_tasks +task: global_mmlu_full_cs_college_chemistry diff --git a/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_college_computer_science.yaml b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_college_computer_science.yaml new file mode 100644 index 00000000..fd619d13 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_college_computer_science.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _cs_template_yaml +process_docs: !function utils.process_college_computer_science +tag: global_mmlu_full_cs_stem_tasks +task: global_mmlu_full_cs_college_computer_science diff --git a/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_college_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_college_mathematics.yaml new file mode 100644 index 00000000..e09563f9 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_college_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _cs_template_yaml +process_docs: !function utils.process_college_mathematics +tag: global_mmlu_full_cs_stem_tasks +task: global_mmlu_full_cs_college_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_college_medicine.yaml b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_college_medicine.yaml new file mode 100644 index 00000000..f7b868c9 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_college_medicine.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _cs_template_yaml +process_docs: !function utils.process_college_medicine +tag: global_mmlu_full_cs_other_tasks +task: global_mmlu_full_cs_college_medicine diff --git a/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_college_physics.yaml b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_college_physics.yaml new file mode 100644 index 00000000..e98df339 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_college_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _cs_template_yaml +process_docs: !function utils.process_college_physics +tag: global_mmlu_full_cs_stem_tasks +task: global_mmlu_full_cs_college_physics diff --git a/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_computer_security.yaml b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_computer_security.yaml new file mode 100644 index 00000000..7256ad67 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_computer_security.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _cs_template_yaml +process_docs: !function utils.process_computer_security +tag: global_mmlu_full_cs_stem_tasks +task: global_mmlu_full_cs_computer_security diff --git a/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_conceptual_physics.yaml b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_conceptual_physics.yaml new file mode 100644 index 00000000..9bd64498 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_conceptual_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _cs_template_yaml +process_docs: !function utils.process_conceptual_physics +tag: global_mmlu_full_cs_stem_tasks +task: global_mmlu_full_cs_conceptual_physics diff --git a/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_econometrics.yaml b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_econometrics.yaml new file mode 100644 index 00000000..c954d320 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_econometrics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _cs_template_yaml +process_docs: !function utils.process_econometrics +tag: global_mmlu_full_cs_social_sciences_tasks +task: global_mmlu_full_cs_econometrics diff --git a/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_electrical_engineering.yaml b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_electrical_engineering.yaml new file mode 100644 index 00000000..2f80e8ac --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_electrical_engineering.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _cs_template_yaml +process_docs: !function utils.process_electrical_engineering +tag: global_mmlu_full_cs_stem_tasks +task: global_mmlu_full_cs_electrical_engineering diff --git a/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_elementary_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_elementary_mathematics.yaml new file mode 100644 index 00000000..bfbc2c9d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_elementary_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _cs_template_yaml +process_docs: !function utils.process_elementary_mathematics +tag: global_mmlu_full_cs_stem_tasks +task: global_mmlu_full_cs_elementary_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_formal_logic.yaml b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_formal_logic.yaml new file mode 100644 index 00000000..0c2ec8bd --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_formal_logic.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _cs_template_yaml +process_docs: !function utils.process_formal_logic +tag: global_mmlu_full_cs_humanities_tasks +task: global_mmlu_full_cs_formal_logic diff --git a/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_global_facts.yaml b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_global_facts.yaml new file mode 100644 index 00000000..6302b417 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_global_facts.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _cs_template_yaml +process_docs: !function utils.process_global_facts +tag: global_mmlu_full_cs_other_tasks +task: global_mmlu_full_cs_global_facts diff --git a/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_high_school_biology.yaml b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_high_school_biology.yaml new file mode 100644 index 00000000..b69e9ac3 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_high_school_biology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _cs_template_yaml +process_docs: !function utils.process_high_school_biology +tag: global_mmlu_full_cs_stem_tasks +task: global_mmlu_full_cs_high_school_biology diff --git a/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_high_school_chemistry.yaml b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_high_school_chemistry.yaml new file mode 100644 index 00000000..67f53cf5 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_high_school_chemistry.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _cs_template_yaml +process_docs: !function utils.process_high_school_chemistry +tag: global_mmlu_full_cs_stem_tasks +task: global_mmlu_full_cs_high_school_chemistry diff --git a/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_high_school_computer_science.yaml b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_high_school_computer_science.yaml new file mode 100644 index 00000000..0be19221 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_high_school_computer_science.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _cs_template_yaml +process_docs: !function utils.process_high_school_computer_science +tag: global_mmlu_full_cs_stem_tasks +task: global_mmlu_full_cs_high_school_computer_science diff --git a/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_high_school_european_history.yaml b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_high_school_european_history.yaml new file mode 100644 index 00000000..7fa264c3 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_high_school_european_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _cs_template_yaml +process_docs: !function utils.process_high_school_european_history +tag: global_mmlu_full_cs_humanities_tasks +task: global_mmlu_full_cs_high_school_european_history diff --git a/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_high_school_geography.yaml b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_high_school_geography.yaml new file mode 100644 index 00000000..b9f903c2 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_high_school_geography.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _cs_template_yaml +process_docs: !function utils.process_high_school_geography +tag: global_mmlu_full_cs_social_sciences_tasks +task: global_mmlu_full_cs_high_school_geography diff --git a/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_high_school_government_and_politics.yaml b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_high_school_government_and_politics.yaml new file mode 100644 index 00000000..5bde4d69 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_high_school_government_and_politics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _cs_template_yaml +process_docs: !function utils.process_high_school_government_and_politics +tag: global_mmlu_full_cs_social_sciences_tasks +task: global_mmlu_full_cs_high_school_government_and_politics diff --git a/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_high_school_macroeconomics.yaml b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_high_school_macroeconomics.yaml new file mode 100644 index 00000000..bb5068ed --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_high_school_macroeconomics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _cs_template_yaml +process_docs: !function utils.process_high_school_macroeconomics +tag: global_mmlu_full_cs_social_sciences_tasks +task: global_mmlu_full_cs_high_school_macroeconomics diff --git a/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_high_school_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_high_school_mathematics.yaml new file mode 100644 index 00000000..87cb3e57 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_high_school_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _cs_template_yaml +process_docs: !function utils.process_high_school_mathematics +tag: global_mmlu_full_cs_stem_tasks +task: global_mmlu_full_cs_high_school_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_high_school_microeconomics.yaml b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_high_school_microeconomics.yaml new file mode 100644 index 00000000..33c2e18c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_high_school_microeconomics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _cs_template_yaml +process_docs: !function utils.process_high_school_microeconomics +tag: global_mmlu_full_cs_social_sciences_tasks +task: global_mmlu_full_cs_high_school_microeconomics diff --git a/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_high_school_physics.yaml b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_high_school_physics.yaml new file mode 100644 index 00000000..1ed095bf --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_high_school_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _cs_template_yaml +process_docs: !function utils.process_high_school_physics +tag: global_mmlu_full_cs_stem_tasks +task: global_mmlu_full_cs_high_school_physics diff --git a/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_high_school_psychology.yaml b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_high_school_psychology.yaml new file mode 100644 index 00000000..59b62305 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_high_school_psychology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _cs_template_yaml +process_docs: !function utils.process_high_school_psychology +tag: global_mmlu_full_cs_social_sciences_tasks +task: global_mmlu_full_cs_high_school_psychology diff --git a/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_high_school_statistics.yaml b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_high_school_statistics.yaml new file mode 100644 index 00000000..1a18ee25 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_high_school_statistics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _cs_template_yaml +process_docs: !function utils.process_high_school_statistics +tag: global_mmlu_full_cs_stem_tasks +task: global_mmlu_full_cs_high_school_statistics diff --git a/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_high_school_us_history.yaml b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_high_school_us_history.yaml new file mode 100644 index 00000000..d8d0a271 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_high_school_us_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _cs_template_yaml +process_docs: !function utils.process_high_school_us_history +tag: global_mmlu_full_cs_humanities_tasks +task: global_mmlu_full_cs_high_school_us_history diff --git a/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_high_school_world_history.yaml b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_high_school_world_history.yaml new file mode 100644 index 00000000..07012306 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_high_school_world_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _cs_template_yaml +process_docs: !function utils.process_high_school_world_history +tag: global_mmlu_full_cs_humanities_tasks +task: global_mmlu_full_cs_high_school_world_history diff --git a/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_human_aging.yaml b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_human_aging.yaml new file mode 100644 index 00000000..e3f5c7c3 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_human_aging.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _cs_template_yaml +process_docs: !function utils.process_human_aging +tag: global_mmlu_full_cs_other_tasks +task: global_mmlu_full_cs_human_aging diff --git a/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_human_sexuality.yaml b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_human_sexuality.yaml new file mode 100644 index 00000000..61d405c7 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_human_sexuality.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _cs_template_yaml +process_docs: !function utils.process_human_sexuality +tag: global_mmlu_full_cs_social_sciences_tasks +task: global_mmlu_full_cs_human_sexuality diff --git a/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_international_law.yaml b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_international_law.yaml new file mode 100644 index 00000000..509ebee4 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_international_law.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _cs_template_yaml +process_docs: !function utils.process_international_law +tag: global_mmlu_full_cs_humanities_tasks +task: global_mmlu_full_cs_international_law diff --git a/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_jurisprudence.yaml b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_jurisprudence.yaml new file mode 100644 index 00000000..c0e27957 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_jurisprudence.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _cs_template_yaml +process_docs: !function utils.process_jurisprudence +tag: global_mmlu_full_cs_humanities_tasks +task: global_mmlu_full_cs_jurisprudence diff --git a/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_logical_fallacies.yaml b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_logical_fallacies.yaml new file mode 100644 index 00000000..85010f3c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_logical_fallacies.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _cs_template_yaml +process_docs: !function utils.process_logical_fallacies +tag: global_mmlu_full_cs_humanities_tasks +task: global_mmlu_full_cs_logical_fallacies diff --git a/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_machine_learning.yaml b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_machine_learning.yaml new file mode 100644 index 00000000..32aaa1a6 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_machine_learning.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _cs_template_yaml +process_docs: !function utils.process_machine_learning +tag: global_mmlu_full_cs_stem_tasks +task: global_mmlu_full_cs_machine_learning diff --git a/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_management.yaml b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_management.yaml new file mode 100644 index 00000000..4e1a3a7c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_management.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _cs_template_yaml +process_docs: !function utils.process_management +tag: global_mmlu_full_cs_other_tasks +task: global_mmlu_full_cs_management diff --git a/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_marketing.yaml b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_marketing.yaml new file mode 100644 index 00000000..239e3c0c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_marketing.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _cs_template_yaml +process_docs: !function utils.process_marketing +tag: global_mmlu_full_cs_other_tasks +task: global_mmlu_full_cs_marketing diff --git a/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_medical_genetics.yaml b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_medical_genetics.yaml new file mode 100644 index 00000000..1c76fee7 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_medical_genetics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _cs_template_yaml +process_docs: !function utils.process_medical_genetics +tag: global_mmlu_full_cs_other_tasks +task: global_mmlu_full_cs_medical_genetics diff --git a/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_miscellaneous.yaml b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_miscellaneous.yaml new file mode 100644 index 00000000..4be6207a --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_miscellaneous.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _cs_template_yaml +process_docs: !function utils.process_miscellaneous +tag: global_mmlu_full_cs_other_tasks +task: global_mmlu_full_cs_miscellaneous diff --git a/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_moral_disputes.yaml b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_moral_disputes.yaml new file mode 100644 index 00000000..b263f67e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_moral_disputes.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _cs_template_yaml +process_docs: !function utils.process_moral_disputes +tag: global_mmlu_full_cs_humanities_tasks +task: global_mmlu_full_cs_moral_disputes diff --git a/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_moral_scenarios.yaml b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_moral_scenarios.yaml new file mode 100644 index 00000000..6532a43e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_moral_scenarios.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _cs_template_yaml +process_docs: !function utils.process_moral_scenarios +tag: global_mmlu_full_cs_humanities_tasks +task: global_mmlu_full_cs_moral_scenarios diff --git a/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_nutrition.yaml b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_nutrition.yaml new file mode 100644 index 00000000..3f04fbcd --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_nutrition.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _cs_template_yaml +process_docs: !function utils.process_nutrition +tag: global_mmlu_full_cs_other_tasks +task: global_mmlu_full_cs_nutrition diff --git a/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_philosophy.yaml b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_philosophy.yaml new file mode 100644 index 00000000..2f5093f9 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_philosophy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _cs_template_yaml +process_docs: !function utils.process_philosophy +tag: global_mmlu_full_cs_humanities_tasks +task: global_mmlu_full_cs_philosophy diff --git a/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_prehistory.yaml b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_prehistory.yaml new file mode 100644 index 00000000..a8f5f5a5 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_prehistory.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _cs_template_yaml +process_docs: !function utils.process_prehistory +tag: global_mmlu_full_cs_humanities_tasks +task: global_mmlu_full_cs_prehistory diff --git a/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_professional_accounting.yaml b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_professional_accounting.yaml new file mode 100644 index 00000000..bccb71b2 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_professional_accounting.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _cs_template_yaml +process_docs: !function utils.process_professional_accounting +tag: global_mmlu_full_cs_other_tasks +task: global_mmlu_full_cs_professional_accounting diff --git a/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_professional_law.yaml b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_professional_law.yaml new file mode 100644 index 00000000..ff50f50c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_professional_law.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _cs_template_yaml +process_docs: !function utils.process_professional_law +tag: global_mmlu_full_cs_humanities_tasks +task: global_mmlu_full_cs_professional_law diff --git a/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_professional_medicine.yaml b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_professional_medicine.yaml new file mode 100644 index 00000000..9b829379 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_professional_medicine.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _cs_template_yaml +process_docs: !function utils.process_professional_medicine +tag: global_mmlu_full_cs_other_tasks +task: global_mmlu_full_cs_professional_medicine diff --git a/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_professional_psychology.yaml b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_professional_psychology.yaml new file mode 100644 index 00000000..e41edb29 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_professional_psychology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _cs_template_yaml +process_docs: !function utils.process_professional_psychology +tag: global_mmlu_full_cs_social_sciences_tasks +task: global_mmlu_full_cs_professional_psychology diff --git a/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_public_relations.yaml b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_public_relations.yaml new file mode 100644 index 00000000..e8fb512d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_public_relations.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _cs_template_yaml +process_docs: !function utils.process_public_relations +tag: global_mmlu_full_cs_social_sciences_tasks +task: global_mmlu_full_cs_public_relations diff --git a/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_security_studies.yaml b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_security_studies.yaml new file mode 100644 index 00000000..64ec0b3f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_security_studies.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _cs_template_yaml +process_docs: !function utils.process_security_studies +tag: global_mmlu_full_cs_social_sciences_tasks +task: global_mmlu_full_cs_security_studies diff --git a/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_sociology.yaml b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_sociology.yaml new file mode 100644 index 00000000..18214f7c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_sociology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _cs_template_yaml +process_docs: !function utils.process_sociology +tag: global_mmlu_full_cs_social_sciences_tasks +task: global_mmlu_full_cs_sociology diff --git a/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_us_foreign_policy.yaml b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_us_foreign_policy.yaml new file mode 100644 index 00000000..ac42b097 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_us_foreign_policy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _cs_template_yaml +process_docs: !function utils.process_us_foreign_policy +tag: global_mmlu_full_cs_social_sciences_tasks +task: global_mmlu_full_cs_us_foreign_policy diff --git a/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_virology.yaml b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_virology.yaml new file mode 100644 index 00000000..a51b8aef --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_virology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _cs_template_yaml +process_docs: !function utils.process_virology +tag: global_mmlu_full_cs_other_tasks +task: global_mmlu_full_cs_virology diff --git a/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_world_religions.yaml b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_world_religions.yaml new file mode 100644 index 00000000..cf9af3e9 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/cs/global_mmlu_full_cs_world_religions.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _cs_template_yaml +process_docs: !function utils.process_world_religions +tag: global_mmlu_full_cs_humanities_tasks +task: global_mmlu_full_cs_world_religions diff --git a/lm_eval/tasks/global_mmlu/full/cs/utils.py b/lm_eval/tasks/global_mmlu/full/cs/utils.py new file mode 100644 index 00000000..7df72cb0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/cs/utils.py @@ -0,0 +1,73 @@ +from functools import partial + + +SUBJECTS = [ + "abstract_algebra", + "anatomy", + "astronomy", + "business_ethics", + "clinical_knowledge", + "college_biology", + "college_chemistry", + "college_computer_science", + "college_mathematics", + "college_medicine", + "college_physics", + "computer_security", + "conceptual_physics", + "econometrics", + "electrical_engineering", + "elementary_mathematics", + "formal_logic", + "global_facts", + "high_school_biology", + "high_school_chemistry", + "high_school_computer_science", + "high_school_european_history", + "high_school_geography", + "high_school_government_and_politics", + "high_school_macroeconomics", + "high_school_mathematics", + "high_school_microeconomics", + "high_school_physics", + "high_school_psychology", + "high_school_statistics", + "high_school_us_history", + "high_school_world_history", + "human_aging", + "human_sexuality", + "international_law", + "jurisprudence", + "logical_fallacies", + "machine_learning", + "management", + "marketing", + "medical_genetics", + "miscellaneous", + "moral_disputes", + "moral_scenarios", + "nutrition", + "philosophy", + "prehistory", + "professional_accounting", + "professional_law", + "professional_medicine", + "professional_psychology", + "public_relations", + "security_studies", + "sociology", + "us_foreign_policy", + "virology", + "world_religions", +] + + +def process_docs(dataset, subject): + return dataset.filter(lambda x: x["subject"] == subject) + + +process_functions = { + f"process_{subject}": partial(process_docs, subject=subject) for subject in SUBJECTS +} + +globals().update(process_functions) diff --git a/lm_eval/tasks/global_mmlu/full/de/_de_template_yaml b/lm_eval/tasks/global_mmlu/full/de/_de_template_yaml new file mode 100644 index 00000000..036b8619 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/de/_de_template_yaml @@ -0,0 +1,16 @@ +dataset_path: CohereForAI/Global-MMLU +dataset_name: de +test_split: test +fewshot_split: dev +fewshot_config: + sampler: first_n +output_type: multiple_choice +doc_to_text: "{{question.strip()}}\nA. {{option_a}}\nB. {{option_b}}\nC. {{option_c}}\nD. {{option_d}}\nAnswer:" +doc_to_choice: ["A", "B", "C", "D"] +doc_to_target: answer +metric_list: + - metric: acc + aggregation: mean + higher_is_better: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/de/_global_mmlu_full_de.yaml b/lm_eval/tasks/global_mmlu/full/de/_global_mmlu_full_de.yaml new file mode 100644 index 00000000..c09da268 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/de/_global_mmlu_full_de.yaml @@ -0,0 +1,11 @@ +group: global_mmlu_full_de +task: + - global_mmlu_full_de_stem + - global_mmlu_full_de_other + - global_mmlu_full_de_social_sciences + - global_mmlu_full_de_humanities +aggregate_metric_list: + - metric: acc + weight_by_size: True +metadata: + version: 1.0 diff --git a/lm_eval/tasks/global_mmlu/full/de/_global_mmlu_full_de_humanities.yaml b/lm_eval/tasks/global_mmlu/full/de/_global_mmlu_full_de_humanities.yaml new file mode 100644 index 00000000..df571c67 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/de/_global_mmlu_full_de_humanities.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_de_humanities +task: + - global_mmlu_full_de_humanities_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/de/_global_mmlu_full_de_other.yaml b/lm_eval/tasks/global_mmlu/full/de/_global_mmlu_full_de_other.yaml new file mode 100644 index 00000000..bfff864e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/de/_global_mmlu_full_de_other.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_de_other +task: + - global_mmlu_full_de_other_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/de/_global_mmlu_full_de_social_sciences.yaml b/lm_eval/tasks/global_mmlu/full/de/_global_mmlu_full_de_social_sciences.yaml new file mode 100644 index 00000000..8cf304a2 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/de/_global_mmlu_full_de_social_sciences.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_de_social_sciences +task: + - global_mmlu_full_de_social_sciences_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/de/_global_mmlu_full_de_stem.yaml b/lm_eval/tasks/global_mmlu/full/de/_global_mmlu_full_de_stem.yaml new file mode 100644 index 00000000..75d1aa5a --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/de/_global_mmlu_full_de_stem.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_de_stem +task: + - global_mmlu_full_de_stem_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_abstract_algebra.yaml b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_abstract_algebra.yaml new file mode 100644 index 00000000..07cd2356 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_abstract_algebra.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _de_template_yaml +process_docs: !function utils.process_abstract_algebra +tag: global_mmlu_full_de_stem_tasks +task: global_mmlu_full_de_abstract_algebra diff --git a/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_anatomy.yaml b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_anatomy.yaml new file mode 100644 index 00000000..9deb16a6 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_anatomy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _de_template_yaml +process_docs: !function utils.process_anatomy +tag: global_mmlu_full_de_stem_tasks +task: global_mmlu_full_de_anatomy diff --git a/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_astronomy.yaml b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_astronomy.yaml new file mode 100644 index 00000000..6a743d45 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_astronomy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _de_template_yaml +process_docs: !function utils.process_astronomy +tag: global_mmlu_full_de_stem_tasks +task: global_mmlu_full_de_astronomy diff --git a/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_business_ethics.yaml b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_business_ethics.yaml new file mode 100644 index 00000000..37bf9d45 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_business_ethics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _de_template_yaml +process_docs: !function utils.process_business_ethics +tag: global_mmlu_full_de_other_tasks +task: global_mmlu_full_de_business_ethics diff --git a/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_clinical_knowledge.yaml b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_clinical_knowledge.yaml new file mode 100644 index 00000000..c5ad878a --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_clinical_knowledge.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _de_template_yaml +process_docs: !function utils.process_clinical_knowledge +tag: global_mmlu_full_de_other_tasks +task: global_mmlu_full_de_clinical_knowledge diff --git a/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_college_biology.yaml b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_college_biology.yaml new file mode 100644 index 00000000..200f9239 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_college_biology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _de_template_yaml +process_docs: !function utils.process_college_biology +tag: global_mmlu_full_de_stem_tasks +task: global_mmlu_full_de_college_biology diff --git a/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_college_chemistry.yaml b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_college_chemistry.yaml new file mode 100644 index 00000000..2bbc4d46 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_college_chemistry.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _de_template_yaml +process_docs: !function utils.process_college_chemistry +tag: global_mmlu_full_de_stem_tasks +task: global_mmlu_full_de_college_chemistry diff --git a/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_college_computer_science.yaml b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_college_computer_science.yaml new file mode 100644 index 00000000..ac903e3a --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_college_computer_science.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _de_template_yaml +process_docs: !function utils.process_college_computer_science +tag: global_mmlu_full_de_stem_tasks +task: global_mmlu_full_de_college_computer_science diff --git a/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_college_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_college_mathematics.yaml new file mode 100644 index 00000000..616010ca --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_college_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _de_template_yaml +process_docs: !function utils.process_college_mathematics +tag: global_mmlu_full_de_stem_tasks +task: global_mmlu_full_de_college_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_college_medicine.yaml b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_college_medicine.yaml new file mode 100644 index 00000000..b9648ce8 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_college_medicine.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _de_template_yaml +process_docs: !function utils.process_college_medicine +tag: global_mmlu_full_de_other_tasks +task: global_mmlu_full_de_college_medicine diff --git a/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_college_physics.yaml b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_college_physics.yaml new file mode 100644 index 00000000..d3bc6892 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_college_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _de_template_yaml +process_docs: !function utils.process_college_physics +tag: global_mmlu_full_de_stem_tasks +task: global_mmlu_full_de_college_physics diff --git a/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_computer_security.yaml b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_computer_security.yaml new file mode 100644 index 00000000..fee01f9e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_computer_security.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _de_template_yaml +process_docs: !function utils.process_computer_security +tag: global_mmlu_full_de_stem_tasks +task: global_mmlu_full_de_computer_security diff --git a/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_conceptual_physics.yaml b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_conceptual_physics.yaml new file mode 100644 index 00000000..201c17d7 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_conceptual_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _de_template_yaml +process_docs: !function utils.process_conceptual_physics +tag: global_mmlu_full_de_stem_tasks +task: global_mmlu_full_de_conceptual_physics diff --git a/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_econometrics.yaml b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_econometrics.yaml new file mode 100644 index 00000000..1d902c3c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_econometrics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _de_template_yaml +process_docs: !function utils.process_econometrics +tag: global_mmlu_full_de_social_sciences_tasks +task: global_mmlu_full_de_econometrics diff --git a/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_electrical_engineering.yaml b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_electrical_engineering.yaml new file mode 100644 index 00000000..8dcb6c48 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_electrical_engineering.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _de_template_yaml +process_docs: !function utils.process_electrical_engineering +tag: global_mmlu_full_de_stem_tasks +task: global_mmlu_full_de_electrical_engineering diff --git a/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_elementary_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_elementary_mathematics.yaml new file mode 100644 index 00000000..a1ca41ce --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_elementary_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _de_template_yaml +process_docs: !function utils.process_elementary_mathematics +tag: global_mmlu_full_de_stem_tasks +task: global_mmlu_full_de_elementary_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_formal_logic.yaml b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_formal_logic.yaml new file mode 100644 index 00000000..6e16729e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_formal_logic.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _de_template_yaml +process_docs: !function utils.process_formal_logic +tag: global_mmlu_full_de_humanities_tasks +task: global_mmlu_full_de_formal_logic diff --git a/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_global_facts.yaml b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_global_facts.yaml new file mode 100644 index 00000000..a7b09289 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_global_facts.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _de_template_yaml +process_docs: !function utils.process_global_facts +tag: global_mmlu_full_de_other_tasks +task: global_mmlu_full_de_global_facts diff --git a/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_high_school_biology.yaml b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_high_school_biology.yaml new file mode 100644 index 00000000..0ad59551 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_high_school_biology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _de_template_yaml +process_docs: !function utils.process_high_school_biology +tag: global_mmlu_full_de_stem_tasks +task: global_mmlu_full_de_high_school_biology diff --git a/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_high_school_chemistry.yaml b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_high_school_chemistry.yaml new file mode 100644 index 00000000..6c0fbd55 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_high_school_chemistry.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _de_template_yaml +process_docs: !function utils.process_high_school_chemistry +tag: global_mmlu_full_de_stem_tasks +task: global_mmlu_full_de_high_school_chemistry diff --git a/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_high_school_computer_science.yaml b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_high_school_computer_science.yaml new file mode 100644 index 00000000..0aea5ada --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_high_school_computer_science.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _de_template_yaml +process_docs: !function utils.process_high_school_computer_science +tag: global_mmlu_full_de_stem_tasks +task: global_mmlu_full_de_high_school_computer_science diff --git a/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_high_school_european_history.yaml b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_high_school_european_history.yaml new file mode 100644 index 00000000..97293b49 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_high_school_european_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _de_template_yaml +process_docs: !function utils.process_high_school_european_history +tag: global_mmlu_full_de_humanities_tasks +task: global_mmlu_full_de_high_school_european_history diff --git a/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_high_school_geography.yaml b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_high_school_geography.yaml new file mode 100644 index 00000000..d26a65d9 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_high_school_geography.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _de_template_yaml +process_docs: !function utils.process_high_school_geography +tag: global_mmlu_full_de_social_sciences_tasks +task: global_mmlu_full_de_high_school_geography diff --git a/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_high_school_government_and_politics.yaml b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_high_school_government_and_politics.yaml new file mode 100644 index 00000000..b6ec78e6 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_high_school_government_and_politics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _de_template_yaml +process_docs: !function utils.process_high_school_government_and_politics +tag: global_mmlu_full_de_social_sciences_tasks +task: global_mmlu_full_de_high_school_government_and_politics diff --git a/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_high_school_macroeconomics.yaml b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_high_school_macroeconomics.yaml new file mode 100644 index 00000000..53489d85 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_high_school_macroeconomics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _de_template_yaml +process_docs: !function utils.process_high_school_macroeconomics +tag: global_mmlu_full_de_social_sciences_tasks +task: global_mmlu_full_de_high_school_macroeconomics diff --git a/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_high_school_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_high_school_mathematics.yaml new file mode 100644 index 00000000..44a5666f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_high_school_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _de_template_yaml +process_docs: !function utils.process_high_school_mathematics +tag: global_mmlu_full_de_stem_tasks +task: global_mmlu_full_de_high_school_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_high_school_microeconomics.yaml b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_high_school_microeconomics.yaml new file mode 100644 index 00000000..3b911297 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_high_school_microeconomics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _de_template_yaml +process_docs: !function utils.process_high_school_microeconomics +tag: global_mmlu_full_de_social_sciences_tasks +task: global_mmlu_full_de_high_school_microeconomics diff --git a/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_high_school_physics.yaml b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_high_school_physics.yaml new file mode 100644 index 00000000..8d17d047 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_high_school_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _de_template_yaml +process_docs: !function utils.process_high_school_physics +tag: global_mmlu_full_de_stem_tasks +task: global_mmlu_full_de_high_school_physics diff --git a/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_high_school_psychology.yaml b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_high_school_psychology.yaml new file mode 100644 index 00000000..ae768002 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_high_school_psychology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _de_template_yaml +process_docs: !function utils.process_high_school_psychology +tag: global_mmlu_full_de_social_sciences_tasks +task: global_mmlu_full_de_high_school_psychology diff --git a/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_high_school_statistics.yaml b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_high_school_statistics.yaml new file mode 100644 index 00000000..4c272287 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_high_school_statistics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _de_template_yaml +process_docs: !function utils.process_high_school_statistics +tag: global_mmlu_full_de_stem_tasks +task: global_mmlu_full_de_high_school_statistics diff --git a/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_high_school_us_history.yaml b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_high_school_us_history.yaml new file mode 100644 index 00000000..9c1eff81 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_high_school_us_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _de_template_yaml +process_docs: !function utils.process_high_school_us_history +tag: global_mmlu_full_de_humanities_tasks +task: global_mmlu_full_de_high_school_us_history diff --git a/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_high_school_world_history.yaml b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_high_school_world_history.yaml new file mode 100644 index 00000000..11f804a6 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_high_school_world_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _de_template_yaml +process_docs: !function utils.process_high_school_world_history +tag: global_mmlu_full_de_humanities_tasks +task: global_mmlu_full_de_high_school_world_history diff --git a/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_human_aging.yaml b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_human_aging.yaml new file mode 100644 index 00000000..7d5b4d77 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_human_aging.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _de_template_yaml +process_docs: !function utils.process_human_aging +tag: global_mmlu_full_de_other_tasks +task: global_mmlu_full_de_human_aging diff --git a/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_human_sexuality.yaml b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_human_sexuality.yaml new file mode 100644 index 00000000..b3f09c7f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_human_sexuality.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _de_template_yaml +process_docs: !function utils.process_human_sexuality +tag: global_mmlu_full_de_social_sciences_tasks +task: global_mmlu_full_de_human_sexuality diff --git a/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_international_law.yaml b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_international_law.yaml new file mode 100644 index 00000000..34bb5918 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_international_law.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _de_template_yaml +process_docs: !function utils.process_international_law +tag: global_mmlu_full_de_humanities_tasks +task: global_mmlu_full_de_international_law diff --git a/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_jurisprudence.yaml b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_jurisprudence.yaml new file mode 100644 index 00000000..585e99b3 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_jurisprudence.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _de_template_yaml +process_docs: !function utils.process_jurisprudence +tag: global_mmlu_full_de_humanities_tasks +task: global_mmlu_full_de_jurisprudence diff --git a/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_logical_fallacies.yaml b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_logical_fallacies.yaml new file mode 100644 index 00000000..dd09d6ad --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_logical_fallacies.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _de_template_yaml +process_docs: !function utils.process_logical_fallacies +tag: global_mmlu_full_de_humanities_tasks +task: global_mmlu_full_de_logical_fallacies diff --git a/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_machine_learning.yaml b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_machine_learning.yaml new file mode 100644 index 00000000..dfe82a9b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_machine_learning.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _de_template_yaml +process_docs: !function utils.process_machine_learning +tag: global_mmlu_full_de_stem_tasks +task: global_mmlu_full_de_machine_learning diff --git a/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_management.yaml b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_management.yaml new file mode 100644 index 00000000..7304da38 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_management.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _de_template_yaml +process_docs: !function utils.process_management +tag: global_mmlu_full_de_other_tasks +task: global_mmlu_full_de_management diff --git a/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_marketing.yaml b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_marketing.yaml new file mode 100644 index 00000000..2143e4f1 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_marketing.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _de_template_yaml +process_docs: !function utils.process_marketing +tag: global_mmlu_full_de_other_tasks +task: global_mmlu_full_de_marketing diff --git a/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_medical_genetics.yaml b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_medical_genetics.yaml new file mode 100644 index 00000000..01549868 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_medical_genetics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _de_template_yaml +process_docs: !function utils.process_medical_genetics +tag: global_mmlu_full_de_other_tasks +task: global_mmlu_full_de_medical_genetics diff --git a/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_miscellaneous.yaml b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_miscellaneous.yaml new file mode 100644 index 00000000..0c8bd533 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_miscellaneous.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _de_template_yaml +process_docs: !function utils.process_miscellaneous +tag: global_mmlu_full_de_other_tasks +task: global_mmlu_full_de_miscellaneous diff --git a/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_moral_disputes.yaml b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_moral_disputes.yaml new file mode 100644 index 00000000..f03361ae --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_moral_disputes.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _de_template_yaml +process_docs: !function utils.process_moral_disputes +tag: global_mmlu_full_de_humanities_tasks +task: global_mmlu_full_de_moral_disputes diff --git a/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_moral_scenarios.yaml b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_moral_scenarios.yaml new file mode 100644 index 00000000..a36519a7 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_moral_scenarios.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _de_template_yaml +process_docs: !function utils.process_moral_scenarios +tag: global_mmlu_full_de_humanities_tasks +task: global_mmlu_full_de_moral_scenarios diff --git a/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_nutrition.yaml b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_nutrition.yaml new file mode 100644 index 00000000..799065cb --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_nutrition.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _de_template_yaml +process_docs: !function utils.process_nutrition +tag: global_mmlu_full_de_other_tasks +task: global_mmlu_full_de_nutrition diff --git a/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_philosophy.yaml b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_philosophy.yaml new file mode 100644 index 00000000..a5f0372b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_philosophy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _de_template_yaml +process_docs: !function utils.process_philosophy +tag: global_mmlu_full_de_humanities_tasks +task: global_mmlu_full_de_philosophy diff --git a/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_prehistory.yaml b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_prehistory.yaml new file mode 100644 index 00000000..2145e87d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_prehistory.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _de_template_yaml +process_docs: !function utils.process_prehistory +tag: global_mmlu_full_de_humanities_tasks +task: global_mmlu_full_de_prehistory diff --git a/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_professional_accounting.yaml b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_professional_accounting.yaml new file mode 100644 index 00000000..7ad55e97 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_professional_accounting.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _de_template_yaml +process_docs: !function utils.process_professional_accounting +tag: global_mmlu_full_de_other_tasks +task: global_mmlu_full_de_professional_accounting diff --git a/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_professional_law.yaml b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_professional_law.yaml new file mode 100644 index 00000000..6f4e338f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_professional_law.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _de_template_yaml +process_docs: !function utils.process_professional_law +tag: global_mmlu_full_de_humanities_tasks +task: global_mmlu_full_de_professional_law diff --git a/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_professional_medicine.yaml b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_professional_medicine.yaml new file mode 100644 index 00000000..7a1214a6 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_professional_medicine.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _de_template_yaml +process_docs: !function utils.process_professional_medicine +tag: global_mmlu_full_de_other_tasks +task: global_mmlu_full_de_professional_medicine diff --git a/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_professional_psychology.yaml b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_professional_psychology.yaml new file mode 100644 index 00000000..a2d49ec8 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_professional_psychology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _de_template_yaml +process_docs: !function utils.process_professional_psychology +tag: global_mmlu_full_de_social_sciences_tasks +task: global_mmlu_full_de_professional_psychology diff --git a/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_public_relations.yaml b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_public_relations.yaml new file mode 100644 index 00000000..4b7d23a8 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_public_relations.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _de_template_yaml +process_docs: !function utils.process_public_relations +tag: global_mmlu_full_de_social_sciences_tasks +task: global_mmlu_full_de_public_relations diff --git a/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_security_studies.yaml b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_security_studies.yaml new file mode 100644 index 00000000..a1a3b22e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_security_studies.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _de_template_yaml +process_docs: !function utils.process_security_studies +tag: global_mmlu_full_de_social_sciences_tasks +task: global_mmlu_full_de_security_studies diff --git a/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_sociology.yaml b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_sociology.yaml new file mode 100644 index 00000000..fefef9d0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_sociology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _de_template_yaml +process_docs: !function utils.process_sociology +tag: global_mmlu_full_de_social_sciences_tasks +task: global_mmlu_full_de_sociology diff --git a/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_us_foreign_policy.yaml b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_us_foreign_policy.yaml new file mode 100644 index 00000000..35394ab5 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_us_foreign_policy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _de_template_yaml +process_docs: !function utils.process_us_foreign_policy +tag: global_mmlu_full_de_social_sciences_tasks +task: global_mmlu_full_de_us_foreign_policy diff --git a/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_virology.yaml b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_virology.yaml new file mode 100644 index 00000000..f0f2f595 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_virology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _de_template_yaml +process_docs: !function utils.process_virology +tag: global_mmlu_full_de_other_tasks +task: global_mmlu_full_de_virology diff --git a/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_world_religions.yaml b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_world_religions.yaml new file mode 100644 index 00000000..1a43e6fe --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/de/global_mmlu_full_de_world_religions.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _de_template_yaml +process_docs: !function utils.process_world_religions +tag: global_mmlu_full_de_humanities_tasks +task: global_mmlu_full_de_world_religions diff --git a/lm_eval/tasks/global_mmlu/full/de/utils.py b/lm_eval/tasks/global_mmlu/full/de/utils.py new file mode 100644 index 00000000..7df72cb0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/de/utils.py @@ -0,0 +1,73 @@ +from functools import partial + + +SUBJECTS = [ + "abstract_algebra", + "anatomy", + "astronomy", + "business_ethics", + "clinical_knowledge", + "college_biology", + "college_chemistry", + "college_computer_science", + "college_mathematics", + "college_medicine", + "college_physics", + "computer_security", + "conceptual_physics", + "econometrics", + "electrical_engineering", + "elementary_mathematics", + "formal_logic", + "global_facts", + "high_school_biology", + "high_school_chemistry", + "high_school_computer_science", + "high_school_european_history", + "high_school_geography", + "high_school_government_and_politics", + "high_school_macroeconomics", + "high_school_mathematics", + "high_school_microeconomics", + "high_school_physics", + "high_school_psychology", + "high_school_statistics", + "high_school_us_history", + "high_school_world_history", + "human_aging", + "human_sexuality", + "international_law", + "jurisprudence", + "logical_fallacies", + "machine_learning", + "management", + "marketing", + "medical_genetics", + "miscellaneous", + "moral_disputes", + "moral_scenarios", + "nutrition", + "philosophy", + "prehistory", + "professional_accounting", + "professional_law", + "professional_medicine", + "professional_psychology", + "public_relations", + "security_studies", + "sociology", + "us_foreign_policy", + "virology", + "world_religions", +] + + +def process_docs(dataset, subject): + return dataset.filter(lambda x: x["subject"] == subject) + + +process_functions = { + f"process_{subject}": partial(process_docs, subject=subject) for subject in SUBJECTS +} + +globals().update(process_functions) diff --git a/lm_eval/tasks/global_mmlu/full/el/_el_template_yaml b/lm_eval/tasks/global_mmlu/full/el/_el_template_yaml new file mode 100644 index 00000000..5fccad5e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/el/_el_template_yaml @@ -0,0 +1,16 @@ +dataset_path: CohereForAI/Global-MMLU +dataset_name: el +test_split: test +fewshot_split: dev +fewshot_config: + sampler: first_n +output_type: multiple_choice +doc_to_text: "{{question.strip()}}\nA. {{option_a}}\nB. {{option_b}}\nC. {{option_c}}\nD. {{option_d}}\nAnswer:" +doc_to_choice: ["A", "B", "C", "D"] +doc_to_target: answer +metric_list: + - metric: acc + aggregation: mean + higher_is_better: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/el/_global_mmlu_full_el.yaml b/lm_eval/tasks/global_mmlu/full/el/_global_mmlu_full_el.yaml new file mode 100644 index 00000000..a77feecb --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/el/_global_mmlu_full_el.yaml @@ -0,0 +1,11 @@ +group: global_mmlu_full_el +task: + - global_mmlu_full_el_stem + - global_mmlu_full_el_other + - global_mmlu_full_el_social_sciences + - global_mmlu_full_el_humanities +aggregate_metric_list: + - metric: acc + weight_by_size: True +metadata: + version: 1.0 diff --git a/lm_eval/tasks/global_mmlu/full/el/_global_mmlu_full_el_humanities.yaml b/lm_eval/tasks/global_mmlu/full/el/_global_mmlu_full_el_humanities.yaml new file mode 100644 index 00000000..f07f2b52 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/el/_global_mmlu_full_el_humanities.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_el_humanities +task: + - global_mmlu_full_el_humanities_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/el/_global_mmlu_full_el_other.yaml b/lm_eval/tasks/global_mmlu/full/el/_global_mmlu_full_el_other.yaml new file mode 100644 index 00000000..938292f0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/el/_global_mmlu_full_el_other.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_el_other +task: + - global_mmlu_full_el_other_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/el/_global_mmlu_full_el_social_sciences.yaml b/lm_eval/tasks/global_mmlu/full/el/_global_mmlu_full_el_social_sciences.yaml new file mode 100644 index 00000000..e72e1e9c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/el/_global_mmlu_full_el_social_sciences.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_el_social_sciences +task: + - global_mmlu_full_el_social_sciences_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/el/_global_mmlu_full_el_stem.yaml b/lm_eval/tasks/global_mmlu/full/el/_global_mmlu_full_el_stem.yaml new file mode 100644 index 00000000..2123be08 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/el/_global_mmlu_full_el_stem.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_el_stem +task: + - global_mmlu_full_el_stem_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_abstract_algebra.yaml b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_abstract_algebra.yaml new file mode 100644 index 00000000..bc56c069 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_abstract_algebra.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _el_template_yaml +process_docs: !function utils.process_abstract_algebra +tag: global_mmlu_full_el_stem_tasks +task: global_mmlu_full_el_abstract_algebra diff --git a/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_anatomy.yaml b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_anatomy.yaml new file mode 100644 index 00000000..0b2e0e7f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_anatomy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _el_template_yaml +process_docs: !function utils.process_anatomy +tag: global_mmlu_full_el_stem_tasks +task: global_mmlu_full_el_anatomy diff --git a/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_astronomy.yaml b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_astronomy.yaml new file mode 100644 index 00000000..7faf7389 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_astronomy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _el_template_yaml +process_docs: !function utils.process_astronomy +tag: global_mmlu_full_el_stem_tasks +task: global_mmlu_full_el_astronomy diff --git a/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_business_ethics.yaml b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_business_ethics.yaml new file mode 100644 index 00000000..0e8b5bb4 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_business_ethics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _el_template_yaml +process_docs: !function utils.process_business_ethics +tag: global_mmlu_full_el_other_tasks +task: global_mmlu_full_el_business_ethics diff --git a/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_clinical_knowledge.yaml b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_clinical_knowledge.yaml new file mode 100644 index 00000000..51ade421 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_clinical_knowledge.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _el_template_yaml +process_docs: !function utils.process_clinical_knowledge +tag: global_mmlu_full_el_other_tasks +task: global_mmlu_full_el_clinical_knowledge diff --git a/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_college_biology.yaml b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_college_biology.yaml new file mode 100644 index 00000000..cf3aa362 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_college_biology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _el_template_yaml +process_docs: !function utils.process_college_biology +tag: global_mmlu_full_el_stem_tasks +task: global_mmlu_full_el_college_biology diff --git a/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_college_chemistry.yaml b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_college_chemistry.yaml new file mode 100644 index 00000000..cd8e1dac --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_college_chemistry.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _el_template_yaml +process_docs: !function utils.process_college_chemistry +tag: global_mmlu_full_el_stem_tasks +task: global_mmlu_full_el_college_chemistry diff --git a/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_college_computer_science.yaml b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_college_computer_science.yaml new file mode 100644 index 00000000..f1ea0859 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_college_computer_science.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _el_template_yaml +process_docs: !function utils.process_college_computer_science +tag: global_mmlu_full_el_stem_tasks +task: global_mmlu_full_el_college_computer_science diff --git a/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_college_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_college_mathematics.yaml new file mode 100644 index 00000000..0ec055b7 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_college_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _el_template_yaml +process_docs: !function utils.process_college_mathematics +tag: global_mmlu_full_el_stem_tasks +task: global_mmlu_full_el_college_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_college_medicine.yaml b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_college_medicine.yaml new file mode 100644 index 00000000..b16b545b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_college_medicine.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _el_template_yaml +process_docs: !function utils.process_college_medicine +tag: global_mmlu_full_el_other_tasks +task: global_mmlu_full_el_college_medicine diff --git a/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_college_physics.yaml b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_college_physics.yaml new file mode 100644 index 00000000..a4630f7f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_college_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _el_template_yaml +process_docs: !function utils.process_college_physics +tag: global_mmlu_full_el_stem_tasks +task: global_mmlu_full_el_college_physics diff --git a/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_computer_security.yaml b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_computer_security.yaml new file mode 100644 index 00000000..a40228ea --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_computer_security.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _el_template_yaml +process_docs: !function utils.process_computer_security +tag: global_mmlu_full_el_stem_tasks +task: global_mmlu_full_el_computer_security diff --git a/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_conceptual_physics.yaml b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_conceptual_physics.yaml new file mode 100644 index 00000000..e7baf6e6 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_conceptual_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _el_template_yaml +process_docs: !function utils.process_conceptual_physics +tag: global_mmlu_full_el_stem_tasks +task: global_mmlu_full_el_conceptual_physics diff --git a/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_econometrics.yaml b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_econometrics.yaml new file mode 100644 index 00000000..48e59021 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_econometrics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _el_template_yaml +process_docs: !function utils.process_econometrics +tag: global_mmlu_full_el_social_sciences_tasks +task: global_mmlu_full_el_econometrics diff --git a/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_electrical_engineering.yaml b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_electrical_engineering.yaml new file mode 100644 index 00000000..294c3c5d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_electrical_engineering.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _el_template_yaml +process_docs: !function utils.process_electrical_engineering +tag: global_mmlu_full_el_stem_tasks +task: global_mmlu_full_el_electrical_engineering diff --git a/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_elementary_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_elementary_mathematics.yaml new file mode 100644 index 00000000..4373d82e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_elementary_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _el_template_yaml +process_docs: !function utils.process_elementary_mathematics +tag: global_mmlu_full_el_stem_tasks +task: global_mmlu_full_el_elementary_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_formal_logic.yaml b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_formal_logic.yaml new file mode 100644 index 00000000..81799a17 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_formal_logic.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _el_template_yaml +process_docs: !function utils.process_formal_logic +tag: global_mmlu_full_el_humanities_tasks +task: global_mmlu_full_el_formal_logic diff --git a/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_global_facts.yaml b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_global_facts.yaml new file mode 100644 index 00000000..6317eeec --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_global_facts.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _el_template_yaml +process_docs: !function utils.process_global_facts +tag: global_mmlu_full_el_other_tasks +task: global_mmlu_full_el_global_facts diff --git a/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_high_school_biology.yaml b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_high_school_biology.yaml new file mode 100644 index 00000000..fa5958aa --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_high_school_biology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _el_template_yaml +process_docs: !function utils.process_high_school_biology +tag: global_mmlu_full_el_stem_tasks +task: global_mmlu_full_el_high_school_biology diff --git a/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_high_school_chemistry.yaml b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_high_school_chemistry.yaml new file mode 100644 index 00000000..38053add --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_high_school_chemistry.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _el_template_yaml +process_docs: !function utils.process_high_school_chemistry +tag: global_mmlu_full_el_stem_tasks +task: global_mmlu_full_el_high_school_chemistry diff --git a/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_high_school_computer_science.yaml b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_high_school_computer_science.yaml new file mode 100644 index 00000000..4fe73214 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_high_school_computer_science.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _el_template_yaml +process_docs: !function utils.process_high_school_computer_science +tag: global_mmlu_full_el_stem_tasks +task: global_mmlu_full_el_high_school_computer_science diff --git a/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_high_school_european_history.yaml b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_high_school_european_history.yaml new file mode 100644 index 00000000..8beb1e3f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_high_school_european_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _el_template_yaml +process_docs: !function utils.process_high_school_european_history +tag: global_mmlu_full_el_humanities_tasks +task: global_mmlu_full_el_high_school_european_history diff --git a/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_high_school_geography.yaml b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_high_school_geography.yaml new file mode 100644 index 00000000..22c08321 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_high_school_geography.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _el_template_yaml +process_docs: !function utils.process_high_school_geography +tag: global_mmlu_full_el_social_sciences_tasks +task: global_mmlu_full_el_high_school_geography diff --git a/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_high_school_government_and_politics.yaml b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_high_school_government_and_politics.yaml new file mode 100644 index 00000000..e3b33041 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_high_school_government_and_politics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _el_template_yaml +process_docs: !function utils.process_high_school_government_and_politics +tag: global_mmlu_full_el_social_sciences_tasks +task: global_mmlu_full_el_high_school_government_and_politics diff --git a/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_high_school_macroeconomics.yaml b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_high_school_macroeconomics.yaml new file mode 100644 index 00000000..63ba6a05 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_high_school_macroeconomics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _el_template_yaml +process_docs: !function utils.process_high_school_macroeconomics +tag: global_mmlu_full_el_social_sciences_tasks +task: global_mmlu_full_el_high_school_macroeconomics diff --git a/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_high_school_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_high_school_mathematics.yaml new file mode 100644 index 00000000..f6ff6e2c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_high_school_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _el_template_yaml +process_docs: !function utils.process_high_school_mathematics +tag: global_mmlu_full_el_stem_tasks +task: global_mmlu_full_el_high_school_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_high_school_microeconomics.yaml b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_high_school_microeconomics.yaml new file mode 100644 index 00000000..5e4deeeb --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_high_school_microeconomics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _el_template_yaml +process_docs: !function utils.process_high_school_microeconomics +tag: global_mmlu_full_el_social_sciences_tasks +task: global_mmlu_full_el_high_school_microeconomics diff --git a/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_high_school_physics.yaml b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_high_school_physics.yaml new file mode 100644 index 00000000..cb875703 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_high_school_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _el_template_yaml +process_docs: !function utils.process_high_school_physics +tag: global_mmlu_full_el_stem_tasks +task: global_mmlu_full_el_high_school_physics diff --git a/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_high_school_psychology.yaml b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_high_school_psychology.yaml new file mode 100644 index 00000000..e82d1b53 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_high_school_psychology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _el_template_yaml +process_docs: !function utils.process_high_school_psychology +tag: global_mmlu_full_el_social_sciences_tasks +task: global_mmlu_full_el_high_school_psychology diff --git a/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_high_school_statistics.yaml b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_high_school_statistics.yaml new file mode 100644 index 00000000..0003184c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_high_school_statistics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _el_template_yaml +process_docs: !function utils.process_high_school_statistics +tag: global_mmlu_full_el_stem_tasks +task: global_mmlu_full_el_high_school_statistics diff --git a/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_high_school_us_history.yaml b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_high_school_us_history.yaml new file mode 100644 index 00000000..f5e0a367 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_high_school_us_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _el_template_yaml +process_docs: !function utils.process_high_school_us_history +tag: global_mmlu_full_el_humanities_tasks +task: global_mmlu_full_el_high_school_us_history diff --git a/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_high_school_world_history.yaml b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_high_school_world_history.yaml new file mode 100644 index 00000000..ac460ea8 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_high_school_world_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _el_template_yaml +process_docs: !function utils.process_high_school_world_history +tag: global_mmlu_full_el_humanities_tasks +task: global_mmlu_full_el_high_school_world_history diff --git a/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_human_aging.yaml b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_human_aging.yaml new file mode 100644 index 00000000..8a40e04f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_human_aging.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _el_template_yaml +process_docs: !function utils.process_human_aging +tag: global_mmlu_full_el_other_tasks +task: global_mmlu_full_el_human_aging diff --git a/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_human_sexuality.yaml b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_human_sexuality.yaml new file mode 100644 index 00000000..de5075bc --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_human_sexuality.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _el_template_yaml +process_docs: !function utils.process_human_sexuality +tag: global_mmlu_full_el_social_sciences_tasks +task: global_mmlu_full_el_human_sexuality diff --git a/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_international_law.yaml b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_international_law.yaml new file mode 100644 index 00000000..2fb93f2c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_international_law.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _el_template_yaml +process_docs: !function utils.process_international_law +tag: global_mmlu_full_el_humanities_tasks +task: global_mmlu_full_el_international_law diff --git a/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_jurisprudence.yaml b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_jurisprudence.yaml new file mode 100644 index 00000000..624e040a --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_jurisprudence.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _el_template_yaml +process_docs: !function utils.process_jurisprudence +tag: global_mmlu_full_el_humanities_tasks +task: global_mmlu_full_el_jurisprudence diff --git a/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_logical_fallacies.yaml b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_logical_fallacies.yaml new file mode 100644 index 00000000..7e5bdb4f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_logical_fallacies.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _el_template_yaml +process_docs: !function utils.process_logical_fallacies +tag: global_mmlu_full_el_humanities_tasks +task: global_mmlu_full_el_logical_fallacies diff --git a/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_machine_learning.yaml b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_machine_learning.yaml new file mode 100644 index 00000000..180f3b25 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_machine_learning.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _el_template_yaml +process_docs: !function utils.process_machine_learning +tag: global_mmlu_full_el_stem_tasks +task: global_mmlu_full_el_machine_learning diff --git a/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_management.yaml b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_management.yaml new file mode 100644 index 00000000..40487fb1 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_management.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _el_template_yaml +process_docs: !function utils.process_management +tag: global_mmlu_full_el_other_tasks +task: global_mmlu_full_el_management diff --git a/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_marketing.yaml b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_marketing.yaml new file mode 100644 index 00000000..781d4170 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_marketing.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _el_template_yaml +process_docs: !function utils.process_marketing +tag: global_mmlu_full_el_other_tasks +task: global_mmlu_full_el_marketing diff --git a/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_medical_genetics.yaml b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_medical_genetics.yaml new file mode 100644 index 00000000..2ca01146 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_medical_genetics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _el_template_yaml +process_docs: !function utils.process_medical_genetics +tag: global_mmlu_full_el_other_tasks +task: global_mmlu_full_el_medical_genetics diff --git a/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_miscellaneous.yaml b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_miscellaneous.yaml new file mode 100644 index 00000000..66114367 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_miscellaneous.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _el_template_yaml +process_docs: !function utils.process_miscellaneous +tag: global_mmlu_full_el_other_tasks +task: global_mmlu_full_el_miscellaneous diff --git a/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_moral_disputes.yaml b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_moral_disputes.yaml new file mode 100644 index 00000000..c553ab7b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_moral_disputes.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _el_template_yaml +process_docs: !function utils.process_moral_disputes +tag: global_mmlu_full_el_humanities_tasks +task: global_mmlu_full_el_moral_disputes diff --git a/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_moral_scenarios.yaml b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_moral_scenarios.yaml new file mode 100644 index 00000000..14a79a4a --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_moral_scenarios.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _el_template_yaml +process_docs: !function utils.process_moral_scenarios +tag: global_mmlu_full_el_humanities_tasks +task: global_mmlu_full_el_moral_scenarios diff --git a/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_nutrition.yaml b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_nutrition.yaml new file mode 100644 index 00000000..595daa39 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_nutrition.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _el_template_yaml +process_docs: !function utils.process_nutrition +tag: global_mmlu_full_el_other_tasks +task: global_mmlu_full_el_nutrition diff --git a/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_philosophy.yaml b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_philosophy.yaml new file mode 100644 index 00000000..25b121b6 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_philosophy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _el_template_yaml +process_docs: !function utils.process_philosophy +tag: global_mmlu_full_el_humanities_tasks +task: global_mmlu_full_el_philosophy diff --git a/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_prehistory.yaml b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_prehistory.yaml new file mode 100644 index 00000000..5938a174 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_prehistory.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _el_template_yaml +process_docs: !function utils.process_prehistory +tag: global_mmlu_full_el_humanities_tasks +task: global_mmlu_full_el_prehistory diff --git a/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_professional_accounting.yaml b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_professional_accounting.yaml new file mode 100644 index 00000000..002b02aa --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_professional_accounting.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _el_template_yaml +process_docs: !function utils.process_professional_accounting +tag: global_mmlu_full_el_other_tasks +task: global_mmlu_full_el_professional_accounting diff --git a/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_professional_law.yaml b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_professional_law.yaml new file mode 100644 index 00000000..7b457038 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_professional_law.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _el_template_yaml +process_docs: !function utils.process_professional_law +tag: global_mmlu_full_el_humanities_tasks +task: global_mmlu_full_el_professional_law diff --git a/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_professional_medicine.yaml b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_professional_medicine.yaml new file mode 100644 index 00000000..a31d4e3b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_professional_medicine.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _el_template_yaml +process_docs: !function utils.process_professional_medicine +tag: global_mmlu_full_el_other_tasks +task: global_mmlu_full_el_professional_medicine diff --git a/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_professional_psychology.yaml b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_professional_psychology.yaml new file mode 100644 index 00000000..6e048079 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_professional_psychology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _el_template_yaml +process_docs: !function utils.process_professional_psychology +tag: global_mmlu_full_el_social_sciences_tasks +task: global_mmlu_full_el_professional_psychology diff --git a/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_public_relations.yaml b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_public_relations.yaml new file mode 100644 index 00000000..264799d6 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_public_relations.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _el_template_yaml +process_docs: !function utils.process_public_relations +tag: global_mmlu_full_el_social_sciences_tasks +task: global_mmlu_full_el_public_relations diff --git a/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_security_studies.yaml b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_security_studies.yaml new file mode 100644 index 00000000..19ffae47 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_security_studies.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _el_template_yaml +process_docs: !function utils.process_security_studies +tag: global_mmlu_full_el_social_sciences_tasks +task: global_mmlu_full_el_security_studies diff --git a/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_sociology.yaml b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_sociology.yaml new file mode 100644 index 00000000..f57d3e0a --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_sociology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _el_template_yaml +process_docs: !function utils.process_sociology +tag: global_mmlu_full_el_social_sciences_tasks +task: global_mmlu_full_el_sociology diff --git a/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_us_foreign_policy.yaml b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_us_foreign_policy.yaml new file mode 100644 index 00000000..14c76440 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_us_foreign_policy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _el_template_yaml +process_docs: !function utils.process_us_foreign_policy +tag: global_mmlu_full_el_social_sciences_tasks +task: global_mmlu_full_el_us_foreign_policy diff --git a/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_virology.yaml b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_virology.yaml new file mode 100644 index 00000000..0e444358 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_virology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _el_template_yaml +process_docs: !function utils.process_virology +tag: global_mmlu_full_el_other_tasks +task: global_mmlu_full_el_virology diff --git a/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_world_religions.yaml b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_world_religions.yaml new file mode 100644 index 00000000..60f8e52e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/el/global_mmlu_full_el_world_religions.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _el_template_yaml +process_docs: !function utils.process_world_religions +tag: global_mmlu_full_el_humanities_tasks +task: global_mmlu_full_el_world_religions diff --git a/lm_eval/tasks/global_mmlu/full/el/utils.py b/lm_eval/tasks/global_mmlu/full/el/utils.py new file mode 100644 index 00000000..7df72cb0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/el/utils.py @@ -0,0 +1,73 @@ +from functools import partial + + +SUBJECTS = [ + "abstract_algebra", + "anatomy", + "astronomy", + "business_ethics", + "clinical_knowledge", + "college_biology", + "college_chemistry", + "college_computer_science", + "college_mathematics", + "college_medicine", + "college_physics", + "computer_security", + "conceptual_physics", + "econometrics", + "electrical_engineering", + "elementary_mathematics", + "formal_logic", + "global_facts", + "high_school_biology", + "high_school_chemistry", + "high_school_computer_science", + "high_school_european_history", + "high_school_geography", + "high_school_government_and_politics", + "high_school_macroeconomics", + "high_school_mathematics", + "high_school_microeconomics", + "high_school_physics", + "high_school_psychology", + "high_school_statistics", + "high_school_us_history", + "high_school_world_history", + "human_aging", + "human_sexuality", + "international_law", + "jurisprudence", + "logical_fallacies", + "machine_learning", + "management", + "marketing", + "medical_genetics", + "miscellaneous", + "moral_disputes", + "moral_scenarios", + "nutrition", + "philosophy", + "prehistory", + "professional_accounting", + "professional_law", + "professional_medicine", + "professional_psychology", + "public_relations", + "security_studies", + "sociology", + "us_foreign_policy", + "virology", + "world_religions", +] + + +def process_docs(dataset, subject): + return dataset.filter(lambda x: x["subject"] == subject) + + +process_functions = { + f"process_{subject}": partial(process_docs, subject=subject) for subject in SUBJECTS +} + +globals().update(process_functions) diff --git a/lm_eval/tasks/global_mmlu/full/en/_en_template_yaml b/lm_eval/tasks/global_mmlu/full/en/_en_template_yaml new file mode 100644 index 00000000..ae7da46b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/en/_en_template_yaml @@ -0,0 +1,16 @@ +dataset_path: CohereForAI/Global-MMLU +dataset_name: en +test_split: test +fewshot_split: dev +fewshot_config: + sampler: first_n +output_type: multiple_choice +doc_to_text: "{{question.strip()}}\nA. {{option_a}}\nB. {{option_b}}\nC. {{option_c}}\nD. {{option_d}}\nAnswer:" +doc_to_choice: ["A", "B", "C", "D"] +doc_to_target: answer +metric_list: + - metric: acc + aggregation: mean + higher_is_better: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/en/_global_mmlu_full_en.yaml b/lm_eval/tasks/global_mmlu/full/en/_global_mmlu_full_en.yaml new file mode 100644 index 00000000..648a10dd --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/en/_global_mmlu_full_en.yaml @@ -0,0 +1,11 @@ +group: global_mmlu_full_en +task: + - global_mmlu_full_en_stem + - global_mmlu_full_en_other + - global_mmlu_full_en_social_sciences + - global_mmlu_full_en_humanities +aggregate_metric_list: + - metric: acc + weight_by_size: True +metadata: + version: 1.0 diff --git a/lm_eval/tasks/global_mmlu/full/en/_global_mmlu_full_en_humanities.yaml b/lm_eval/tasks/global_mmlu/full/en/_global_mmlu_full_en_humanities.yaml new file mode 100644 index 00000000..4455fbcf --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/en/_global_mmlu_full_en_humanities.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_en_humanities +task: + - global_mmlu_full_en_humanities_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/en/_global_mmlu_full_en_other.yaml b/lm_eval/tasks/global_mmlu/full/en/_global_mmlu_full_en_other.yaml new file mode 100644 index 00000000..cca60e52 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/en/_global_mmlu_full_en_other.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_en_other +task: + - global_mmlu_full_en_other_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/en/_global_mmlu_full_en_social_sciences.yaml b/lm_eval/tasks/global_mmlu/full/en/_global_mmlu_full_en_social_sciences.yaml new file mode 100644 index 00000000..becac7a5 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/en/_global_mmlu_full_en_social_sciences.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_en_social_sciences +task: + - global_mmlu_full_en_social_sciences_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/en/_global_mmlu_full_en_stem.yaml b/lm_eval/tasks/global_mmlu/full/en/_global_mmlu_full_en_stem.yaml new file mode 100644 index 00000000..71aac061 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/en/_global_mmlu_full_en_stem.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_en_stem +task: + - global_mmlu_full_en_stem_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_abstract_algebra.yaml b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_abstract_algebra.yaml new file mode 100644 index 00000000..3d7a5ed8 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_abstract_algebra.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _en_template_yaml +process_docs: !function utils.process_abstract_algebra +tag: global_mmlu_full_en_stem_tasks +task: global_mmlu_full_en_abstract_algebra diff --git a/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_anatomy.yaml b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_anatomy.yaml new file mode 100644 index 00000000..f2267ad8 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_anatomy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _en_template_yaml +process_docs: !function utils.process_anatomy +tag: global_mmlu_full_en_stem_tasks +task: global_mmlu_full_en_anatomy diff --git a/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_astronomy.yaml b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_astronomy.yaml new file mode 100644 index 00000000..6999c30f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_astronomy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _en_template_yaml +process_docs: !function utils.process_astronomy +tag: global_mmlu_full_en_stem_tasks +task: global_mmlu_full_en_astronomy diff --git a/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_business_ethics.yaml b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_business_ethics.yaml new file mode 100644 index 00000000..56a6e490 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_business_ethics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _en_template_yaml +process_docs: !function utils.process_business_ethics +tag: global_mmlu_full_en_other_tasks +task: global_mmlu_full_en_business_ethics diff --git a/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_clinical_knowledge.yaml b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_clinical_knowledge.yaml new file mode 100644 index 00000000..60425fad --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_clinical_knowledge.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _en_template_yaml +process_docs: !function utils.process_clinical_knowledge +tag: global_mmlu_full_en_other_tasks +task: global_mmlu_full_en_clinical_knowledge diff --git a/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_college_biology.yaml b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_college_biology.yaml new file mode 100644 index 00000000..9b5f2f8c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_college_biology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _en_template_yaml +process_docs: !function utils.process_college_biology +tag: global_mmlu_full_en_stem_tasks +task: global_mmlu_full_en_college_biology diff --git a/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_college_chemistry.yaml b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_college_chemistry.yaml new file mode 100644 index 00000000..8e2ab91f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_college_chemistry.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _en_template_yaml +process_docs: !function utils.process_college_chemistry +tag: global_mmlu_full_en_stem_tasks +task: global_mmlu_full_en_college_chemistry diff --git a/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_college_computer_science.yaml b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_college_computer_science.yaml new file mode 100644 index 00000000..9abf38db --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_college_computer_science.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _en_template_yaml +process_docs: !function utils.process_college_computer_science +tag: global_mmlu_full_en_stem_tasks +task: global_mmlu_full_en_college_computer_science diff --git a/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_college_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_college_mathematics.yaml new file mode 100644 index 00000000..5da6199f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_college_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _en_template_yaml +process_docs: !function utils.process_college_mathematics +tag: global_mmlu_full_en_stem_tasks +task: global_mmlu_full_en_college_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_college_medicine.yaml b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_college_medicine.yaml new file mode 100644 index 00000000..c568f36b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_college_medicine.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _en_template_yaml +process_docs: !function utils.process_college_medicine +tag: global_mmlu_full_en_other_tasks +task: global_mmlu_full_en_college_medicine diff --git a/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_college_physics.yaml b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_college_physics.yaml new file mode 100644 index 00000000..ac044019 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_college_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _en_template_yaml +process_docs: !function utils.process_college_physics +tag: global_mmlu_full_en_stem_tasks +task: global_mmlu_full_en_college_physics diff --git a/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_computer_security.yaml b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_computer_security.yaml new file mode 100644 index 00000000..be47dbde --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_computer_security.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _en_template_yaml +process_docs: !function utils.process_computer_security +tag: global_mmlu_full_en_stem_tasks +task: global_mmlu_full_en_computer_security diff --git a/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_conceptual_physics.yaml b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_conceptual_physics.yaml new file mode 100644 index 00000000..86180924 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_conceptual_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _en_template_yaml +process_docs: !function utils.process_conceptual_physics +tag: global_mmlu_full_en_stem_tasks +task: global_mmlu_full_en_conceptual_physics diff --git a/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_econometrics.yaml b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_econometrics.yaml new file mode 100644 index 00000000..a75d329f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_econometrics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _en_template_yaml +process_docs: !function utils.process_econometrics +tag: global_mmlu_full_en_social_sciences_tasks +task: global_mmlu_full_en_econometrics diff --git a/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_electrical_engineering.yaml b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_electrical_engineering.yaml new file mode 100644 index 00000000..2568993f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_electrical_engineering.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _en_template_yaml +process_docs: !function utils.process_electrical_engineering +tag: global_mmlu_full_en_stem_tasks +task: global_mmlu_full_en_electrical_engineering diff --git a/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_elementary_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_elementary_mathematics.yaml new file mode 100644 index 00000000..622a99f8 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_elementary_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _en_template_yaml +process_docs: !function utils.process_elementary_mathematics +tag: global_mmlu_full_en_stem_tasks +task: global_mmlu_full_en_elementary_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_formal_logic.yaml b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_formal_logic.yaml new file mode 100644 index 00000000..109ca44a --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_formal_logic.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _en_template_yaml +process_docs: !function utils.process_formal_logic +tag: global_mmlu_full_en_humanities_tasks +task: global_mmlu_full_en_formal_logic diff --git a/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_global_facts.yaml b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_global_facts.yaml new file mode 100644 index 00000000..39daa506 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_global_facts.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _en_template_yaml +process_docs: !function utils.process_global_facts +tag: global_mmlu_full_en_other_tasks +task: global_mmlu_full_en_global_facts diff --git a/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_high_school_biology.yaml b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_high_school_biology.yaml new file mode 100644 index 00000000..063392eb --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_high_school_biology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _en_template_yaml +process_docs: !function utils.process_high_school_biology +tag: global_mmlu_full_en_stem_tasks +task: global_mmlu_full_en_high_school_biology diff --git a/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_high_school_chemistry.yaml b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_high_school_chemistry.yaml new file mode 100644 index 00000000..452e9445 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_high_school_chemistry.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _en_template_yaml +process_docs: !function utils.process_high_school_chemistry +tag: global_mmlu_full_en_stem_tasks +task: global_mmlu_full_en_high_school_chemistry diff --git a/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_high_school_computer_science.yaml b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_high_school_computer_science.yaml new file mode 100644 index 00000000..baf43136 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_high_school_computer_science.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _en_template_yaml +process_docs: !function utils.process_high_school_computer_science +tag: global_mmlu_full_en_stem_tasks +task: global_mmlu_full_en_high_school_computer_science diff --git a/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_high_school_european_history.yaml b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_high_school_european_history.yaml new file mode 100644 index 00000000..fceda5c2 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_high_school_european_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _en_template_yaml +process_docs: !function utils.process_high_school_european_history +tag: global_mmlu_full_en_humanities_tasks +task: global_mmlu_full_en_high_school_european_history diff --git a/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_high_school_geography.yaml b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_high_school_geography.yaml new file mode 100644 index 00000000..4fbb9ade --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_high_school_geography.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _en_template_yaml +process_docs: !function utils.process_high_school_geography +tag: global_mmlu_full_en_social_sciences_tasks +task: global_mmlu_full_en_high_school_geography diff --git a/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_high_school_government_and_politics.yaml b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_high_school_government_and_politics.yaml new file mode 100644 index 00000000..73ca9087 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_high_school_government_and_politics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _en_template_yaml +process_docs: !function utils.process_high_school_government_and_politics +tag: global_mmlu_full_en_social_sciences_tasks +task: global_mmlu_full_en_high_school_government_and_politics diff --git a/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_high_school_macroeconomics.yaml b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_high_school_macroeconomics.yaml new file mode 100644 index 00000000..1b9ca7a9 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_high_school_macroeconomics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _en_template_yaml +process_docs: !function utils.process_high_school_macroeconomics +tag: global_mmlu_full_en_social_sciences_tasks +task: global_mmlu_full_en_high_school_macroeconomics diff --git a/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_high_school_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_high_school_mathematics.yaml new file mode 100644 index 00000000..9be50ad2 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_high_school_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _en_template_yaml +process_docs: !function utils.process_high_school_mathematics +tag: global_mmlu_full_en_stem_tasks +task: global_mmlu_full_en_high_school_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_high_school_microeconomics.yaml b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_high_school_microeconomics.yaml new file mode 100644 index 00000000..d93285cb --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_high_school_microeconomics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _en_template_yaml +process_docs: !function utils.process_high_school_microeconomics +tag: global_mmlu_full_en_social_sciences_tasks +task: global_mmlu_full_en_high_school_microeconomics diff --git a/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_high_school_physics.yaml b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_high_school_physics.yaml new file mode 100644 index 00000000..2f74c609 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_high_school_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _en_template_yaml +process_docs: !function utils.process_high_school_physics +tag: global_mmlu_full_en_stem_tasks +task: global_mmlu_full_en_high_school_physics diff --git a/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_high_school_psychology.yaml b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_high_school_psychology.yaml new file mode 100644 index 00000000..365762ba --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_high_school_psychology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _en_template_yaml +process_docs: !function utils.process_high_school_psychology +tag: global_mmlu_full_en_social_sciences_tasks +task: global_mmlu_full_en_high_school_psychology diff --git a/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_high_school_statistics.yaml b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_high_school_statistics.yaml new file mode 100644 index 00000000..d6ca42ad --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_high_school_statistics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _en_template_yaml +process_docs: !function utils.process_high_school_statistics +tag: global_mmlu_full_en_stem_tasks +task: global_mmlu_full_en_high_school_statistics diff --git a/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_high_school_us_history.yaml b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_high_school_us_history.yaml new file mode 100644 index 00000000..4f20a4dd --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_high_school_us_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _en_template_yaml +process_docs: !function utils.process_high_school_us_history +tag: global_mmlu_full_en_humanities_tasks +task: global_mmlu_full_en_high_school_us_history diff --git a/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_high_school_world_history.yaml b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_high_school_world_history.yaml new file mode 100644 index 00000000..d0fce403 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_high_school_world_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _en_template_yaml +process_docs: !function utils.process_high_school_world_history +tag: global_mmlu_full_en_humanities_tasks +task: global_mmlu_full_en_high_school_world_history diff --git a/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_human_aging.yaml b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_human_aging.yaml new file mode 100644 index 00000000..35320a85 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_human_aging.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _en_template_yaml +process_docs: !function utils.process_human_aging +tag: global_mmlu_full_en_other_tasks +task: global_mmlu_full_en_human_aging diff --git a/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_human_sexuality.yaml b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_human_sexuality.yaml new file mode 100644 index 00000000..86096c5d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_human_sexuality.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _en_template_yaml +process_docs: !function utils.process_human_sexuality +tag: global_mmlu_full_en_social_sciences_tasks +task: global_mmlu_full_en_human_sexuality diff --git a/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_international_law.yaml b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_international_law.yaml new file mode 100644 index 00000000..8a41e9fc --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_international_law.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _en_template_yaml +process_docs: !function utils.process_international_law +tag: global_mmlu_full_en_humanities_tasks +task: global_mmlu_full_en_international_law diff --git a/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_jurisprudence.yaml b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_jurisprudence.yaml new file mode 100644 index 00000000..aa34c443 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_jurisprudence.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _en_template_yaml +process_docs: !function utils.process_jurisprudence +tag: global_mmlu_full_en_humanities_tasks +task: global_mmlu_full_en_jurisprudence diff --git a/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_logical_fallacies.yaml b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_logical_fallacies.yaml new file mode 100644 index 00000000..50c105b4 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_logical_fallacies.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _en_template_yaml +process_docs: !function utils.process_logical_fallacies +tag: global_mmlu_full_en_humanities_tasks +task: global_mmlu_full_en_logical_fallacies diff --git a/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_machine_learning.yaml b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_machine_learning.yaml new file mode 100644 index 00000000..35f496c1 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_machine_learning.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _en_template_yaml +process_docs: !function utils.process_machine_learning +tag: global_mmlu_full_en_stem_tasks +task: global_mmlu_full_en_machine_learning diff --git a/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_management.yaml b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_management.yaml new file mode 100644 index 00000000..d8499d9f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_management.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _en_template_yaml +process_docs: !function utils.process_management +tag: global_mmlu_full_en_other_tasks +task: global_mmlu_full_en_management diff --git a/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_marketing.yaml b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_marketing.yaml new file mode 100644 index 00000000..05f8f0ec --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_marketing.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _en_template_yaml +process_docs: !function utils.process_marketing +tag: global_mmlu_full_en_other_tasks +task: global_mmlu_full_en_marketing diff --git a/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_medical_genetics.yaml b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_medical_genetics.yaml new file mode 100644 index 00000000..8f272510 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_medical_genetics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _en_template_yaml +process_docs: !function utils.process_medical_genetics +tag: global_mmlu_full_en_other_tasks +task: global_mmlu_full_en_medical_genetics diff --git a/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_miscellaneous.yaml b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_miscellaneous.yaml new file mode 100644 index 00000000..a72fad22 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_miscellaneous.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _en_template_yaml +process_docs: !function utils.process_miscellaneous +tag: global_mmlu_full_en_other_tasks +task: global_mmlu_full_en_miscellaneous diff --git a/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_moral_disputes.yaml b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_moral_disputes.yaml new file mode 100644 index 00000000..2504abeb --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_moral_disputes.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _en_template_yaml +process_docs: !function utils.process_moral_disputes +tag: global_mmlu_full_en_humanities_tasks +task: global_mmlu_full_en_moral_disputes diff --git a/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_moral_scenarios.yaml b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_moral_scenarios.yaml new file mode 100644 index 00000000..4ae4c37a --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_moral_scenarios.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _en_template_yaml +process_docs: !function utils.process_moral_scenarios +tag: global_mmlu_full_en_humanities_tasks +task: global_mmlu_full_en_moral_scenarios diff --git a/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_nutrition.yaml b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_nutrition.yaml new file mode 100644 index 00000000..b5364f69 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_nutrition.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _en_template_yaml +process_docs: !function utils.process_nutrition +tag: global_mmlu_full_en_other_tasks +task: global_mmlu_full_en_nutrition diff --git a/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_philosophy.yaml b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_philosophy.yaml new file mode 100644 index 00000000..6e68d7e7 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_philosophy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _en_template_yaml +process_docs: !function utils.process_philosophy +tag: global_mmlu_full_en_humanities_tasks +task: global_mmlu_full_en_philosophy diff --git a/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_prehistory.yaml b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_prehistory.yaml new file mode 100644 index 00000000..72e93368 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_prehistory.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _en_template_yaml +process_docs: !function utils.process_prehistory +tag: global_mmlu_full_en_humanities_tasks +task: global_mmlu_full_en_prehistory diff --git a/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_professional_accounting.yaml b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_professional_accounting.yaml new file mode 100644 index 00000000..cdb66ead --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_professional_accounting.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _en_template_yaml +process_docs: !function utils.process_professional_accounting +tag: global_mmlu_full_en_other_tasks +task: global_mmlu_full_en_professional_accounting diff --git a/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_professional_law.yaml b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_professional_law.yaml new file mode 100644 index 00000000..67120278 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_professional_law.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _en_template_yaml +process_docs: !function utils.process_professional_law +tag: global_mmlu_full_en_humanities_tasks +task: global_mmlu_full_en_professional_law diff --git a/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_professional_medicine.yaml b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_professional_medicine.yaml new file mode 100644 index 00000000..ffbcb29b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_professional_medicine.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _en_template_yaml +process_docs: !function utils.process_professional_medicine +tag: global_mmlu_full_en_other_tasks +task: global_mmlu_full_en_professional_medicine diff --git a/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_professional_psychology.yaml b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_professional_psychology.yaml new file mode 100644 index 00000000..1abea59b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_professional_psychology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _en_template_yaml +process_docs: !function utils.process_professional_psychology +tag: global_mmlu_full_en_social_sciences_tasks +task: global_mmlu_full_en_professional_psychology diff --git a/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_public_relations.yaml b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_public_relations.yaml new file mode 100644 index 00000000..9df4f491 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_public_relations.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _en_template_yaml +process_docs: !function utils.process_public_relations +tag: global_mmlu_full_en_social_sciences_tasks +task: global_mmlu_full_en_public_relations diff --git a/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_security_studies.yaml b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_security_studies.yaml new file mode 100644 index 00000000..addb6934 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_security_studies.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _en_template_yaml +process_docs: !function utils.process_security_studies +tag: global_mmlu_full_en_social_sciences_tasks +task: global_mmlu_full_en_security_studies diff --git a/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_sociology.yaml b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_sociology.yaml new file mode 100644 index 00000000..a198cb84 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_sociology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _en_template_yaml +process_docs: !function utils.process_sociology +tag: global_mmlu_full_en_social_sciences_tasks +task: global_mmlu_full_en_sociology diff --git a/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_us_foreign_policy.yaml b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_us_foreign_policy.yaml new file mode 100644 index 00000000..047b61e0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_us_foreign_policy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _en_template_yaml +process_docs: !function utils.process_us_foreign_policy +tag: global_mmlu_full_en_social_sciences_tasks +task: global_mmlu_full_en_us_foreign_policy diff --git a/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_virology.yaml b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_virology.yaml new file mode 100644 index 00000000..bb74fefd --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_virology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _en_template_yaml +process_docs: !function utils.process_virology +tag: global_mmlu_full_en_other_tasks +task: global_mmlu_full_en_virology diff --git a/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_world_religions.yaml b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_world_religions.yaml new file mode 100644 index 00000000..2c453bf7 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/en/global_mmlu_full_en_world_religions.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _en_template_yaml +process_docs: !function utils.process_world_religions +tag: global_mmlu_full_en_humanities_tasks +task: global_mmlu_full_en_world_religions diff --git a/lm_eval/tasks/global_mmlu/full/en/utils.py b/lm_eval/tasks/global_mmlu/full/en/utils.py new file mode 100644 index 00000000..7df72cb0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/en/utils.py @@ -0,0 +1,73 @@ +from functools import partial + + +SUBJECTS = [ + "abstract_algebra", + "anatomy", + "astronomy", + "business_ethics", + "clinical_knowledge", + "college_biology", + "college_chemistry", + "college_computer_science", + "college_mathematics", + "college_medicine", + "college_physics", + "computer_security", + "conceptual_physics", + "econometrics", + "electrical_engineering", + "elementary_mathematics", + "formal_logic", + "global_facts", + "high_school_biology", + "high_school_chemistry", + "high_school_computer_science", + "high_school_european_history", + "high_school_geography", + "high_school_government_and_politics", + "high_school_macroeconomics", + "high_school_mathematics", + "high_school_microeconomics", + "high_school_physics", + "high_school_psychology", + "high_school_statistics", + "high_school_us_history", + "high_school_world_history", + "human_aging", + "human_sexuality", + "international_law", + "jurisprudence", + "logical_fallacies", + "machine_learning", + "management", + "marketing", + "medical_genetics", + "miscellaneous", + "moral_disputes", + "moral_scenarios", + "nutrition", + "philosophy", + "prehistory", + "professional_accounting", + "professional_law", + "professional_medicine", + "professional_psychology", + "public_relations", + "security_studies", + "sociology", + "us_foreign_policy", + "virology", + "world_religions", +] + + +def process_docs(dataset, subject): + return dataset.filter(lambda x: x["subject"] == subject) + + +process_functions = { + f"process_{subject}": partial(process_docs, subject=subject) for subject in SUBJECTS +} + +globals().update(process_functions) diff --git a/lm_eval/tasks/global_mmlu/full/es/_es_template_yaml b/lm_eval/tasks/global_mmlu/full/es/_es_template_yaml new file mode 100644 index 00000000..443af17c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/es/_es_template_yaml @@ -0,0 +1,16 @@ +dataset_path: CohereForAI/Global-MMLU +dataset_name: es +test_split: test +fewshot_split: dev +fewshot_config: + sampler: first_n +output_type: multiple_choice +doc_to_text: "{{question.strip()}}\nA. {{option_a}}\nB. {{option_b}}\nC. {{option_c}}\nD. {{option_d}}\nAnswer:" +doc_to_choice: ["A", "B", "C", "D"] +doc_to_target: answer +metric_list: + - metric: acc + aggregation: mean + higher_is_better: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/es/_global_mmlu_full_es.yaml b/lm_eval/tasks/global_mmlu/full/es/_global_mmlu_full_es.yaml new file mode 100644 index 00000000..832001c1 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/es/_global_mmlu_full_es.yaml @@ -0,0 +1,11 @@ +group: global_mmlu_full_es +task: + - global_mmlu_full_es_stem + - global_mmlu_full_es_other + - global_mmlu_full_es_social_sciences + - global_mmlu_full_es_humanities +aggregate_metric_list: + - metric: acc + weight_by_size: True +metadata: + version: 1.0 diff --git a/lm_eval/tasks/global_mmlu/full/es/_global_mmlu_full_es_humanities.yaml b/lm_eval/tasks/global_mmlu/full/es/_global_mmlu_full_es_humanities.yaml new file mode 100644 index 00000000..bda6944e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/es/_global_mmlu_full_es_humanities.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_es_humanities +task: + - global_mmlu_full_es_humanities_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/es/_global_mmlu_full_es_other.yaml b/lm_eval/tasks/global_mmlu/full/es/_global_mmlu_full_es_other.yaml new file mode 100644 index 00000000..610366ef --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/es/_global_mmlu_full_es_other.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_es_other +task: + - global_mmlu_full_es_other_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/es/_global_mmlu_full_es_social_sciences.yaml b/lm_eval/tasks/global_mmlu/full/es/_global_mmlu_full_es_social_sciences.yaml new file mode 100644 index 00000000..00948690 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/es/_global_mmlu_full_es_social_sciences.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_es_social_sciences +task: + - global_mmlu_full_es_social_sciences_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/es/_global_mmlu_full_es_stem.yaml b/lm_eval/tasks/global_mmlu/full/es/_global_mmlu_full_es_stem.yaml new file mode 100644 index 00000000..483a8fd6 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/es/_global_mmlu_full_es_stem.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_es_stem +task: + - global_mmlu_full_es_stem_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_abstract_algebra.yaml b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_abstract_algebra.yaml new file mode 100644 index 00000000..02fb7200 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_abstract_algebra.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _es_template_yaml +process_docs: !function utils.process_abstract_algebra +tag: global_mmlu_full_es_stem_tasks +task: global_mmlu_full_es_abstract_algebra diff --git a/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_anatomy.yaml b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_anatomy.yaml new file mode 100644 index 00000000..40f05e7b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_anatomy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _es_template_yaml +process_docs: !function utils.process_anatomy +tag: global_mmlu_full_es_stem_tasks +task: global_mmlu_full_es_anatomy diff --git a/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_astronomy.yaml b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_astronomy.yaml new file mode 100644 index 00000000..fb688c13 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_astronomy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _es_template_yaml +process_docs: !function utils.process_astronomy +tag: global_mmlu_full_es_stem_tasks +task: global_mmlu_full_es_astronomy diff --git a/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_business_ethics.yaml b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_business_ethics.yaml new file mode 100644 index 00000000..aab858f1 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_business_ethics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _es_template_yaml +process_docs: !function utils.process_business_ethics +tag: global_mmlu_full_es_other_tasks +task: global_mmlu_full_es_business_ethics diff --git a/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_clinical_knowledge.yaml b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_clinical_knowledge.yaml new file mode 100644 index 00000000..a3483f8d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_clinical_knowledge.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _es_template_yaml +process_docs: !function utils.process_clinical_knowledge +tag: global_mmlu_full_es_other_tasks +task: global_mmlu_full_es_clinical_knowledge diff --git a/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_college_biology.yaml b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_college_biology.yaml new file mode 100644 index 00000000..36658ab6 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_college_biology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _es_template_yaml +process_docs: !function utils.process_college_biology +tag: global_mmlu_full_es_stem_tasks +task: global_mmlu_full_es_college_biology diff --git a/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_college_chemistry.yaml b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_college_chemistry.yaml new file mode 100644 index 00000000..47a47444 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_college_chemistry.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _es_template_yaml +process_docs: !function utils.process_college_chemistry +tag: global_mmlu_full_es_stem_tasks +task: global_mmlu_full_es_college_chemistry diff --git a/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_college_computer_science.yaml b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_college_computer_science.yaml new file mode 100644 index 00000000..4154324e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_college_computer_science.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _es_template_yaml +process_docs: !function utils.process_college_computer_science +tag: global_mmlu_full_es_stem_tasks +task: global_mmlu_full_es_college_computer_science diff --git a/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_college_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_college_mathematics.yaml new file mode 100644 index 00000000..85bc6261 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_college_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _es_template_yaml +process_docs: !function utils.process_college_mathematics +tag: global_mmlu_full_es_stem_tasks +task: global_mmlu_full_es_college_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_college_medicine.yaml b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_college_medicine.yaml new file mode 100644 index 00000000..40e8d129 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_college_medicine.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _es_template_yaml +process_docs: !function utils.process_college_medicine +tag: global_mmlu_full_es_other_tasks +task: global_mmlu_full_es_college_medicine diff --git a/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_college_physics.yaml b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_college_physics.yaml new file mode 100644 index 00000000..7ebc5e95 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_college_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _es_template_yaml +process_docs: !function utils.process_college_physics +tag: global_mmlu_full_es_stem_tasks +task: global_mmlu_full_es_college_physics diff --git a/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_computer_security.yaml b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_computer_security.yaml new file mode 100644 index 00000000..b586eb2b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_computer_security.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _es_template_yaml +process_docs: !function utils.process_computer_security +tag: global_mmlu_full_es_stem_tasks +task: global_mmlu_full_es_computer_security diff --git a/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_conceptual_physics.yaml b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_conceptual_physics.yaml new file mode 100644 index 00000000..4186cec6 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_conceptual_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _es_template_yaml +process_docs: !function utils.process_conceptual_physics +tag: global_mmlu_full_es_stem_tasks +task: global_mmlu_full_es_conceptual_physics diff --git a/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_econometrics.yaml b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_econometrics.yaml new file mode 100644 index 00000000..3d61c8f9 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_econometrics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _es_template_yaml +process_docs: !function utils.process_econometrics +tag: global_mmlu_full_es_social_sciences_tasks +task: global_mmlu_full_es_econometrics diff --git a/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_electrical_engineering.yaml b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_electrical_engineering.yaml new file mode 100644 index 00000000..1a454d79 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_electrical_engineering.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _es_template_yaml +process_docs: !function utils.process_electrical_engineering +tag: global_mmlu_full_es_stem_tasks +task: global_mmlu_full_es_electrical_engineering diff --git a/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_elementary_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_elementary_mathematics.yaml new file mode 100644 index 00000000..772436e6 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_elementary_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _es_template_yaml +process_docs: !function utils.process_elementary_mathematics +tag: global_mmlu_full_es_stem_tasks +task: global_mmlu_full_es_elementary_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_formal_logic.yaml b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_formal_logic.yaml new file mode 100644 index 00000000..da6223fe --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_formal_logic.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _es_template_yaml +process_docs: !function utils.process_formal_logic +tag: global_mmlu_full_es_humanities_tasks +task: global_mmlu_full_es_formal_logic diff --git a/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_global_facts.yaml b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_global_facts.yaml new file mode 100644 index 00000000..ae3b5912 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_global_facts.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _es_template_yaml +process_docs: !function utils.process_global_facts +tag: global_mmlu_full_es_other_tasks +task: global_mmlu_full_es_global_facts diff --git a/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_high_school_biology.yaml b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_high_school_biology.yaml new file mode 100644 index 00000000..79a72140 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_high_school_biology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _es_template_yaml +process_docs: !function utils.process_high_school_biology +tag: global_mmlu_full_es_stem_tasks +task: global_mmlu_full_es_high_school_biology diff --git a/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_high_school_chemistry.yaml b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_high_school_chemistry.yaml new file mode 100644 index 00000000..27ba7570 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_high_school_chemistry.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _es_template_yaml +process_docs: !function utils.process_high_school_chemistry +tag: global_mmlu_full_es_stem_tasks +task: global_mmlu_full_es_high_school_chemistry diff --git a/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_high_school_computer_science.yaml b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_high_school_computer_science.yaml new file mode 100644 index 00000000..72ad4505 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_high_school_computer_science.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _es_template_yaml +process_docs: !function utils.process_high_school_computer_science +tag: global_mmlu_full_es_stem_tasks +task: global_mmlu_full_es_high_school_computer_science diff --git a/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_high_school_european_history.yaml b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_high_school_european_history.yaml new file mode 100644 index 00000000..2cec9d5f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_high_school_european_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _es_template_yaml +process_docs: !function utils.process_high_school_european_history +tag: global_mmlu_full_es_humanities_tasks +task: global_mmlu_full_es_high_school_european_history diff --git a/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_high_school_geography.yaml b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_high_school_geography.yaml new file mode 100644 index 00000000..5ee91f71 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_high_school_geography.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _es_template_yaml +process_docs: !function utils.process_high_school_geography +tag: global_mmlu_full_es_social_sciences_tasks +task: global_mmlu_full_es_high_school_geography diff --git a/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_high_school_government_and_politics.yaml b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_high_school_government_and_politics.yaml new file mode 100644 index 00000000..b3f10319 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_high_school_government_and_politics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _es_template_yaml +process_docs: !function utils.process_high_school_government_and_politics +tag: global_mmlu_full_es_social_sciences_tasks +task: global_mmlu_full_es_high_school_government_and_politics diff --git a/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_high_school_macroeconomics.yaml b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_high_school_macroeconomics.yaml new file mode 100644 index 00000000..d555129a --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_high_school_macroeconomics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _es_template_yaml +process_docs: !function utils.process_high_school_macroeconomics +tag: global_mmlu_full_es_social_sciences_tasks +task: global_mmlu_full_es_high_school_macroeconomics diff --git a/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_high_school_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_high_school_mathematics.yaml new file mode 100644 index 00000000..a1216336 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_high_school_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _es_template_yaml +process_docs: !function utils.process_high_school_mathematics +tag: global_mmlu_full_es_stem_tasks +task: global_mmlu_full_es_high_school_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_high_school_microeconomics.yaml b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_high_school_microeconomics.yaml new file mode 100644 index 00000000..d4c28844 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_high_school_microeconomics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _es_template_yaml +process_docs: !function utils.process_high_school_microeconomics +tag: global_mmlu_full_es_social_sciences_tasks +task: global_mmlu_full_es_high_school_microeconomics diff --git a/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_high_school_physics.yaml b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_high_school_physics.yaml new file mode 100644 index 00000000..fb83ad1e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_high_school_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _es_template_yaml +process_docs: !function utils.process_high_school_physics +tag: global_mmlu_full_es_stem_tasks +task: global_mmlu_full_es_high_school_physics diff --git a/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_high_school_psychology.yaml b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_high_school_psychology.yaml new file mode 100644 index 00000000..4bcd53e4 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_high_school_psychology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _es_template_yaml +process_docs: !function utils.process_high_school_psychology +tag: global_mmlu_full_es_social_sciences_tasks +task: global_mmlu_full_es_high_school_psychology diff --git a/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_high_school_statistics.yaml b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_high_school_statistics.yaml new file mode 100644 index 00000000..900936eb --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_high_school_statistics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _es_template_yaml +process_docs: !function utils.process_high_school_statistics +tag: global_mmlu_full_es_stem_tasks +task: global_mmlu_full_es_high_school_statistics diff --git a/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_high_school_us_history.yaml b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_high_school_us_history.yaml new file mode 100644 index 00000000..d54acd65 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_high_school_us_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _es_template_yaml +process_docs: !function utils.process_high_school_us_history +tag: global_mmlu_full_es_humanities_tasks +task: global_mmlu_full_es_high_school_us_history diff --git a/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_high_school_world_history.yaml b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_high_school_world_history.yaml new file mode 100644 index 00000000..2a654fe8 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_high_school_world_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _es_template_yaml +process_docs: !function utils.process_high_school_world_history +tag: global_mmlu_full_es_humanities_tasks +task: global_mmlu_full_es_high_school_world_history diff --git a/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_human_aging.yaml b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_human_aging.yaml new file mode 100644 index 00000000..47bd8900 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_human_aging.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _es_template_yaml +process_docs: !function utils.process_human_aging +tag: global_mmlu_full_es_other_tasks +task: global_mmlu_full_es_human_aging diff --git a/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_human_sexuality.yaml b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_human_sexuality.yaml new file mode 100644 index 00000000..29925c34 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_human_sexuality.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _es_template_yaml +process_docs: !function utils.process_human_sexuality +tag: global_mmlu_full_es_social_sciences_tasks +task: global_mmlu_full_es_human_sexuality diff --git a/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_international_law.yaml b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_international_law.yaml new file mode 100644 index 00000000..abe4ef94 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_international_law.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _es_template_yaml +process_docs: !function utils.process_international_law +tag: global_mmlu_full_es_humanities_tasks +task: global_mmlu_full_es_international_law diff --git a/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_jurisprudence.yaml b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_jurisprudence.yaml new file mode 100644 index 00000000..751878fe --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_jurisprudence.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _es_template_yaml +process_docs: !function utils.process_jurisprudence +tag: global_mmlu_full_es_humanities_tasks +task: global_mmlu_full_es_jurisprudence diff --git a/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_logical_fallacies.yaml b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_logical_fallacies.yaml new file mode 100644 index 00000000..55233f7f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_logical_fallacies.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _es_template_yaml +process_docs: !function utils.process_logical_fallacies +tag: global_mmlu_full_es_humanities_tasks +task: global_mmlu_full_es_logical_fallacies diff --git a/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_machine_learning.yaml b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_machine_learning.yaml new file mode 100644 index 00000000..9a11e310 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_machine_learning.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _es_template_yaml +process_docs: !function utils.process_machine_learning +tag: global_mmlu_full_es_stem_tasks +task: global_mmlu_full_es_machine_learning diff --git a/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_management.yaml b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_management.yaml new file mode 100644 index 00000000..a31b4c26 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_management.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _es_template_yaml +process_docs: !function utils.process_management +tag: global_mmlu_full_es_other_tasks +task: global_mmlu_full_es_management diff --git a/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_marketing.yaml b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_marketing.yaml new file mode 100644 index 00000000..22136569 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_marketing.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _es_template_yaml +process_docs: !function utils.process_marketing +tag: global_mmlu_full_es_other_tasks +task: global_mmlu_full_es_marketing diff --git a/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_medical_genetics.yaml b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_medical_genetics.yaml new file mode 100644 index 00000000..18fc7a23 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_medical_genetics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _es_template_yaml +process_docs: !function utils.process_medical_genetics +tag: global_mmlu_full_es_other_tasks +task: global_mmlu_full_es_medical_genetics diff --git a/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_miscellaneous.yaml b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_miscellaneous.yaml new file mode 100644 index 00000000..5b3955a9 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_miscellaneous.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _es_template_yaml +process_docs: !function utils.process_miscellaneous +tag: global_mmlu_full_es_other_tasks +task: global_mmlu_full_es_miscellaneous diff --git a/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_moral_disputes.yaml b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_moral_disputes.yaml new file mode 100644 index 00000000..57095856 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_moral_disputes.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _es_template_yaml +process_docs: !function utils.process_moral_disputes +tag: global_mmlu_full_es_humanities_tasks +task: global_mmlu_full_es_moral_disputes diff --git a/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_moral_scenarios.yaml b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_moral_scenarios.yaml new file mode 100644 index 00000000..ed31f8cc --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_moral_scenarios.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _es_template_yaml +process_docs: !function utils.process_moral_scenarios +tag: global_mmlu_full_es_humanities_tasks +task: global_mmlu_full_es_moral_scenarios diff --git a/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_nutrition.yaml b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_nutrition.yaml new file mode 100644 index 00000000..07746d09 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_nutrition.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _es_template_yaml +process_docs: !function utils.process_nutrition +tag: global_mmlu_full_es_other_tasks +task: global_mmlu_full_es_nutrition diff --git a/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_philosophy.yaml b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_philosophy.yaml new file mode 100644 index 00000000..3853e162 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_philosophy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _es_template_yaml +process_docs: !function utils.process_philosophy +tag: global_mmlu_full_es_humanities_tasks +task: global_mmlu_full_es_philosophy diff --git a/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_prehistory.yaml b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_prehistory.yaml new file mode 100644 index 00000000..b75ac9df --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_prehistory.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _es_template_yaml +process_docs: !function utils.process_prehistory +tag: global_mmlu_full_es_humanities_tasks +task: global_mmlu_full_es_prehistory diff --git a/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_professional_accounting.yaml b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_professional_accounting.yaml new file mode 100644 index 00000000..da8fd46f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_professional_accounting.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _es_template_yaml +process_docs: !function utils.process_professional_accounting +tag: global_mmlu_full_es_other_tasks +task: global_mmlu_full_es_professional_accounting diff --git a/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_professional_law.yaml b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_professional_law.yaml new file mode 100644 index 00000000..ddd0ab3d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_professional_law.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _es_template_yaml +process_docs: !function utils.process_professional_law +tag: global_mmlu_full_es_humanities_tasks +task: global_mmlu_full_es_professional_law diff --git a/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_professional_medicine.yaml b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_professional_medicine.yaml new file mode 100644 index 00000000..6be1ae81 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_professional_medicine.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _es_template_yaml +process_docs: !function utils.process_professional_medicine +tag: global_mmlu_full_es_other_tasks +task: global_mmlu_full_es_professional_medicine diff --git a/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_professional_psychology.yaml b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_professional_psychology.yaml new file mode 100644 index 00000000..cadc7f96 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_professional_psychology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _es_template_yaml +process_docs: !function utils.process_professional_psychology +tag: global_mmlu_full_es_social_sciences_tasks +task: global_mmlu_full_es_professional_psychology diff --git a/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_public_relations.yaml b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_public_relations.yaml new file mode 100644 index 00000000..72609ea9 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_public_relations.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _es_template_yaml +process_docs: !function utils.process_public_relations +tag: global_mmlu_full_es_social_sciences_tasks +task: global_mmlu_full_es_public_relations diff --git a/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_security_studies.yaml b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_security_studies.yaml new file mode 100644 index 00000000..319123c6 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_security_studies.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _es_template_yaml +process_docs: !function utils.process_security_studies +tag: global_mmlu_full_es_social_sciences_tasks +task: global_mmlu_full_es_security_studies diff --git a/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_sociology.yaml b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_sociology.yaml new file mode 100644 index 00000000..dec44c29 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_sociology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _es_template_yaml +process_docs: !function utils.process_sociology +tag: global_mmlu_full_es_social_sciences_tasks +task: global_mmlu_full_es_sociology diff --git a/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_us_foreign_policy.yaml b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_us_foreign_policy.yaml new file mode 100644 index 00000000..a18a3942 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_us_foreign_policy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _es_template_yaml +process_docs: !function utils.process_us_foreign_policy +tag: global_mmlu_full_es_social_sciences_tasks +task: global_mmlu_full_es_us_foreign_policy diff --git a/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_virology.yaml b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_virology.yaml new file mode 100644 index 00000000..b06431e2 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_virology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _es_template_yaml +process_docs: !function utils.process_virology +tag: global_mmlu_full_es_other_tasks +task: global_mmlu_full_es_virology diff --git a/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_world_religions.yaml b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_world_religions.yaml new file mode 100644 index 00000000..4d9d6b79 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/es/global_mmlu_full_es_world_religions.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _es_template_yaml +process_docs: !function utils.process_world_religions +tag: global_mmlu_full_es_humanities_tasks +task: global_mmlu_full_es_world_religions diff --git a/lm_eval/tasks/global_mmlu/full/es/utils.py b/lm_eval/tasks/global_mmlu/full/es/utils.py new file mode 100644 index 00000000..7df72cb0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/es/utils.py @@ -0,0 +1,73 @@ +from functools import partial + + +SUBJECTS = [ + "abstract_algebra", + "anatomy", + "astronomy", + "business_ethics", + "clinical_knowledge", + "college_biology", + "college_chemistry", + "college_computer_science", + "college_mathematics", + "college_medicine", + "college_physics", + "computer_security", + "conceptual_physics", + "econometrics", + "electrical_engineering", + "elementary_mathematics", + "formal_logic", + "global_facts", + "high_school_biology", + "high_school_chemistry", + "high_school_computer_science", + "high_school_european_history", + "high_school_geography", + "high_school_government_and_politics", + "high_school_macroeconomics", + "high_school_mathematics", + "high_school_microeconomics", + "high_school_physics", + "high_school_psychology", + "high_school_statistics", + "high_school_us_history", + "high_school_world_history", + "human_aging", + "human_sexuality", + "international_law", + "jurisprudence", + "logical_fallacies", + "machine_learning", + "management", + "marketing", + "medical_genetics", + "miscellaneous", + "moral_disputes", + "moral_scenarios", + "nutrition", + "philosophy", + "prehistory", + "professional_accounting", + "professional_law", + "professional_medicine", + "professional_psychology", + "public_relations", + "security_studies", + "sociology", + "us_foreign_policy", + "virology", + "world_religions", +] + + +def process_docs(dataset, subject): + return dataset.filter(lambda x: x["subject"] == subject) + + +process_functions = { + f"process_{subject}": partial(process_docs, subject=subject) for subject in SUBJECTS +} + +globals().update(process_functions) diff --git a/lm_eval/tasks/global_mmlu/full/fa/_fa_template_yaml b/lm_eval/tasks/global_mmlu/full/fa/_fa_template_yaml new file mode 100644 index 00000000..952259b2 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fa/_fa_template_yaml @@ -0,0 +1,16 @@ +dataset_path: CohereForAI/Global-MMLU +dataset_name: fa +test_split: test +fewshot_split: dev +fewshot_config: + sampler: first_n +output_type: multiple_choice +doc_to_text: "{{question.strip()}}\nA. {{option_a}}\nB. {{option_b}}\nC. {{option_c}}\nD. {{option_d}}\nAnswer:" +doc_to_choice: ["A", "B", "C", "D"] +doc_to_target: answer +metric_list: + - metric: acc + aggregation: mean + higher_is_better: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/fa/_global_mmlu_full_fa.yaml b/lm_eval/tasks/global_mmlu/full/fa/_global_mmlu_full_fa.yaml new file mode 100644 index 00000000..9edb8540 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fa/_global_mmlu_full_fa.yaml @@ -0,0 +1,11 @@ +group: global_mmlu_full_fa +task: + - global_mmlu_full_fa_stem + - global_mmlu_full_fa_other + - global_mmlu_full_fa_social_sciences + - global_mmlu_full_fa_humanities +aggregate_metric_list: + - metric: acc + weight_by_size: True +metadata: + version: 1.0 diff --git a/lm_eval/tasks/global_mmlu/full/fa/_global_mmlu_full_fa_humanities.yaml b/lm_eval/tasks/global_mmlu/full/fa/_global_mmlu_full_fa_humanities.yaml new file mode 100644 index 00000000..f36ecea5 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fa/_global_mmlu_full_fa_humanities.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_fa_humanities +task: + - global_mmlu_full_fa_humanities_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/fa/_global_mmlu_full_fa_other.yaml b/lm_eval/tasks/global_mmlu/full/fa/_global_mmlu_full_fa_other.yaml new file mode 100644 index 00000000..dd57bb86 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fa/_global_mmlu_full_fa_other.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_fa_other +task: + - global_mmlu_full_fa_other_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/fa/_global_mmlu_full_fa_social_sciences.yaml b/lm_eval/tasks/global_mmlu/full/fa/_global_mmlu_full_fa_social_sciences.yaml new file mode 100644 index 00000000..9e7da860 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fa/_global_mmlu_full_fa_social_sciences.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_fa_social_sciences +task: + - global_mmlu_full_fa_social_sciences_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/fa/_global_mmlu_full_fa_stem.yaml b/lm_eval/tasks/global_mmlu/full/fa/_global_mmlu_full_fa_stem.yaml new file mode 100644 index 00000000..5bf2eb01 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fa/_global_mmlu_full_fa_stem.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_fa_stem +task: + - global_mmlu_full_fa_stem_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_abstract_algebra.yaml b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_abstract_algebra.yaml new file mode 100644 index 00000000..1014795f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_abstract_algebra.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fa_template_yaml +process_docs: !function utils.process_abstract_algebra +tag: global_mmlu_full_fa_stem_tasks +task: global_mmlu_full_fa_abstract_algebra diff --git a/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_anatomy.yaml b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_anatomy.yaml new file mode 100644 index 00000000..317705c9 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_anatomy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fa_template_yaml +process_docs: !function utils.process_anatomy +tag: global_mmlu_full_fa_stem_tasks +task: global_mmlu_full_fa_anatomy diff --git a/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_astronomy.yaml b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_astronomy.yaml new file mode 100644 index 00000000..45475964 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_astronomy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fa_template_yaml +process_docs: !function utils.process_astronomy +tag: global_mmlu_full_fa_stem_tasks +task: global_mmlu_full_fa_astronomy diff --git a/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_business_ethics.yaml b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_business_ethics.yaml new file mode 100644 index 00000000..3c0dd60b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_business_ethics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fa_template_yaml +process_docs: !function utils.process_business_ethics +tag: global_mmlu_full_fa_other_tasks +task: global_mmlu_full_fa_business_ethics diff --git a/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_clinical_knowledge.yaml b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_clinical_knowledge.yaml new file mode 100644 index 00000000..a7af0e21 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_clinical_knowledge.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fa_template_yaml +process_docs: !function utils.process_clinical_knowledge +tag: global_mmlu_full_fa_other_tasks +task: global_mmlu_full_fa_clinical_knowledge diff --git a/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_college_biology.yaml b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_college_biology.yaml new file mode 100644 index 00000000..31ae6d71 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_college_biology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fa_template_yaml +process_docs: !function utils.process_college_biology +tag: global_mmlu_full_fa_stem_tasks +task: global_mmlu_full_fa_college_biology diff --git a/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_college_chemistry.yaml b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_college_chemistry.yaml new file mode 100644 index 00000000..8b099f41 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_college_chemistry.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fa_template_yaml +process_docs: !function utils.process_college_chemistry +tag: global_mmlu_full_fa_stem_tasks +task: global_mmlu_full_fa_college_chemistry diff --git a/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_college_computer_science.yaml b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_college_computer_science.yaml new file mode 100644 index 00000000..07491e5b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_college_computer_science.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fa_template_yaml +process_docs: !function utils.process_college_computer_science +tag: global_mmlu_full_fa_stem_tasks +task: global_mmlu_full_fa_college_computer_science diff --git a/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_college_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_college_mathematics.yaml new file mode 100644 index 00000000..774f6b97 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_college_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fa_template_yaml +process_docs: !function utils.process_college_mathematics +tag: global_mmlu_full_fa_stem_tasks +task: global_mmlu_full_fa_college_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_college_medicine.yaml b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_college_medicine.yaml new file mode 100644 index 00000000..13d6f5a2 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_college_medicine.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fa_template_yaml +process_docs: !function utils.process_college_medicine +tag: global_mmlu_full_fa_other_tasks +task: global_mmlu_full_fa_college_medicine diff --git a/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_college_physics.yaml b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_college_physics.yaml new file mode 100644 index 00000000..1e415b8c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_college_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fa_template_yaml +process_docs: !function utils.process_college_physics +tag: global_mmlu_full_fa_stem_tasks +task: global_mmlu_full_fa_college_physics diff --git a/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_computer_security.yaml b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_computer_security.yaml new file mode 100644 index 00000000..ae47213b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_computer_security.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fa_template_yaml +process_docs: !function utils.process_computer_security +tag: global_mmlu_full_fa_stem_tasks +task: global_mmlu_full_fa_computer_security diff --git a/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_conceptual_physics.yaml b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_conceptual_physics.yaml new file mode 100644 index 00000000..c3f2ba4c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_conceptual_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fa_template_yaml +process_docs: !function utils.process_conceptual_physics +tag: global_mmlu_full_fa_stem_tasks +task: global_mmlu_full_fa_conceptual_physics diff --git a/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_econometrics.yaml b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_econometrics.yaml new file mode 100644 index 00000000..6cf79a92 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_econometrics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fa_template_yaml +process_docs: !function utils.process_econometrics +tag: global_mmlu_full_fa_social_sciences_tasks +task: global_mmlu_full_fa_econometrics diff --git a/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_electrical_engineering.yaml b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_electrical_engineering.yaml new file mode 100644 index 00000000..ab7aa858 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_electrical_engineering.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fa_template_yaml +process_docs: !function utils.process_electrical_engineering +tag: global_mmlu_full_fa_stem_tasks +task: global_mmlu_full_fa_electrical_engineering diff --git a/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_elementary_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_elementary_mathematics.yaml new file mode 100644 index 00000000..b83f6ddc --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_elementary_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fa_template_yaml +process_docs: !function utils.process_elementary_mathematics +tag: global_mmlu_full_fa_stem_tasks +task: global_mmlu_full_fa_elementary_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_formal_logic.yaml b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_formal_logic.yaml new file mode 100644 index 00000000..cab2effa --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_formal_logic.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fa_template_yaml +process_docs: !function utils.process_formal_logic +tag: global_mmlu_full_fa_humanities_tasks +task: global_mmlu_full_fa_formal_logic diff --git a/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_global_facts.yaml b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_global_facts.yaml new file mode 100644 index 00000000..93d11b75 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_global_facts.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fa_template_yaml +process_docs: !function utils.process_global_facts +tag: global_mmlu_full_fa_other_tasks +task: global_mmlu_full_fa_global_facts diff --git a/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_high_school_biology.yaml b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_high_school_biology.yaml new file mode 100644 index 00000000..59b6869b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_high_school_biology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fa_template_yaml +process_docs: !function utils.process_high_school_biology +tag: global_mmlu_full_fa_stem_tasks +task: global_mmlu_full_fa_high_school_biology diff --git a/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_high_school_chemistry.yaml b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_high_school_chemistry.yaml new file mode 100644 index 00000000..8d15d4b4 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_high_school_chemistry.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fa_template_yaml +process_docs: !function utils.process_high_school_chemistry +tag: global_mmlu_full_fa_stem_tasks +task: global_mmlu_full_fa_high_school_chemistry diff --git a/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_high_school_computer_science.yaml b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_high_school_computer_science.yaml new file mode 100644 index 00000000..a02df4f1 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_high_school_computer_science.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fa_template_yaml +process_docs: !function utils.process_high_school_computer_science +tag: global_mmlu_full_fa_stem_tasks +task: global_mmlu_full_fa_high_school_computer_science diff --git a/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_high_school_european_history.yaml b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_high_school_european_history.yaml new file mode 100644 index 00000000..e18b2c7b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_high_school_european_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fa_template_yaml +process_docs: !function utils.process_high_school_european_history +tag: global_mmlu_full_fa_humanities_tasks +task: global_mmlu_full_fa_high_school_european_history diff --git a/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_high_school_geography.yaml b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_high_school_geography.yaml new file mode 100644 index 00000000..d94c7e89 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_high_school_geography.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fa_template_yaml +process_docs: !function utils.process_high_school_geography +tag: global_mmlu_full_fa_social_sciences_tasks +task: global_mmlu_full_fa_high_school_geography diff --git a/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_high_school_government_and_politics.yaml b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_high_school_government_and_politics.yaml new file mode 100644 index 00000000..e1007895 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_high_school_government_and_politics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fa_template_yaml +process_docs: !function utils.process_high_school_government_and_politics +tag: global_mmlu_full_fa_social_sciences_tasks +task: global_mmlu_full_fa_high_school_government_and_politics diff --git a/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_high_school_macroeconomics.yaml b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_high_school_macroeconomics.yaml new file mode 100644 index 00000000..a9ad0633 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_high_school_macroeconomics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fa_template_yaml +process_docs: !function utils.process_high_school_macroeconomics +tag: global_mmlu_full_fa_social_sciences_tasks +task: global_mmlu_full_fa_high_school_macroeconomics diff --git a/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_high_school_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_high_school_mathematics.yaml new file mode 100644 index 00000000..2c733b17 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_high_school_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fa_template_yaml +process_docs: !function utils.process_high_school_mathematics +tag: global_mmlu_full_fa_stem_tasks +task: global_mmlu_full_fa_high_school_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_high_school_microeconomics.yaml b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_high_school_microeconomics.yaml new file mode 100644 index 00000000..4f88f0aa --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_high_school_microeconomics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fa_template_yaml +process_docs: !function utils.process_high_school_microeconomics +tag: global_mmlu_full_fa_social_sciences_tasks +task: global_mmlu_full_fa_high_school_microeconomics diff --git a/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_high_school_physics.yaml b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_high_school_physics.yaml new file mode 100644 index 00000000..64fdef98 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_high_school_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fa_template_yaml +process_docs: !function utils.process_high_school_physics +tag: global_mmlu_full_fa_stem_tasks +task: global_mmlu_full_fa_high_school_physics diff --git a/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_high_school_psychology.yaml b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_high_school_psychology.yaml new file mode 100644 index 00000000..c43a115b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_high_school_psychology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fa_template_yaml +process_docs: !function utils.process_high_school_psychology +tag: global_mmlu_full_fa_social_sciences_tasks +task: global_mmlu_full_fa_high_school_psychology diff --git a/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_high_school_statistics.yaml b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_high_school_statistics.yaml new file mode 100644 index 00000000..ebb4e82d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_high_school_statistics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fa_template_yaml +process_docs: !function utils.process_high_school_statistics +tag: global_mmlu_full_fa_stem_tasks +task: global_mmlu_full_fa_high_school_statistics diff --git a/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_high_school_us_history.yaml b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_high_school_us_history.yaml new file mode 100644 index 00000000..a0041e33 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_high_school_us_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fa_template_yaml +process_docs: !function utils.process_high_school_us_history +tag: global_mmlu_full_fa_humanities_tasks +task: global_mmlu_full_fa_high_school_us_history diff --git a/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_high_school_world_history.yaml b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_high_school_world_history.yaml new file mode 100644 index 00000000..66f38f54 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_high_school_world_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fa_template_yaml +process_docs: !function utils.process_high_school_world_history +tag: global_mmlu_full_fa_humanities_tasks +task: global_mmlu_full_fa_high_school_world_history diff --git a/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_human_aging.yaml b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_human_aging.yaml new file mode 100644 index 00000000..95a2adde --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_human_aging.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fa_template_yaml +process_docs: !function utils.process_human_aging +tag: global_mmlu_full_fa_other_tasks +task: global_mmlu_full_fa_human_aging diff --git a/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_human_sexuality.yaml b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_human_sexuality.yaml new file mode 100644 index 00000000..475a71fd --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_human_sexuality.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fa_template_yaml +process_docs: !function utils.process_human_sexuality +tag: global_mmlu_full_fa_social_sciences_tasks +task: global_mmlu_full_fa_human_sexuality diff --git a/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_international_law.yaml b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_international_law.yaml new file mode 100644 index 00000000..c0d6aec2 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_international_law.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fa_template_yaml +process_docs: !function utils.process_international_law +tag: global_mmlu_full_fa_humanities_tasks +task: global_mmlu_full_fa_international_law diff --git a/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_jurisprudence.yaml b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_jurisprudence.yaml new file mode 100644 index 00000000..0d82bd5a --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_jurisprudence.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fa_template_yaml +process_docs: !function utils.process_jurisprudence +tag: global_mmlu_full_fa_humanities_tasks +task: global_mmlu_full_fa_jurisprudence diff --git a/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_logical_fallacies.yaml b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_logical_fallacies.yaml new file mode 100644 index 00000000..a8e89d3c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_logical_fallacies.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fa_template_yaml +process_docs: !function utils.process_logical_fallacies +tag: global_mmlu_full_fa_humanities_tasks +task: global_mmlu_full_fa_logical_fallacies diff --git a/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_machine_learning.yaml b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_machine_learning.yaml new file mode 100644 index 00000000..4e4d1a8a --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_machine_learning.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fa_template_yaml +process_docs: !function utils.process_machine_learning +tag: global_mmlu_full_fa_stem_tasks +task: global_mmlu_full_fa_machine_learning diff --git a/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_management.yaml b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_management.yaml new file mode 100644 index 00000000..e7e592ba --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_management.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fa_template_yaml +process_docs: !function utils.process_management +tag: global_mmlu_full_fa_other_tasks +task: global_mmlu_full_fa_management diff --git a/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_marketing.yaml b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_marketing.yaml new file mode 100644 index 00000000..c0e7ef1f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_marketing.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fa_template_yaml +process_docs: !function utils.process_marketing +tag: global_mmlu_full_fa_other_tasks +task: global_mmlu_full_fa_marketing diff --git a/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_medical_genetics.yaml b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_medical_genetics.yaml new file mode 100644 index 00000000..c31679ec --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_medical_genetics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fa_template_yaml +process_docs: !function utils.process_medical_genetics +tag: global_mmlu_full_fa_other_tasks +task: global_mmlu_full_fa_medical_genetics diff --git a/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_miscellaneous.yaml b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_miscellaneous.yaml new file mode 100644 index 00000000..652d5a33 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_miscellaneous.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fa_template_yaml +process_docs: !function utils.process_miscellaneous +tag: global_mmlu_full_fa_other_tasks +task: global_mmlu_full_fa_miscellaneous diff --git a/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_moral_disputes.yaml b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_moral_disputes.yaml new file mode 100644 index 00000000..16adcb26 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_moral_disputes.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fa_template_yaml +process_docs: !function utils.process_moral_disputes +tag: global_mmlu_full_fa_humanities_tasks +task: global_mmlu_full_fa_moral_disputes diff --git a/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_moral_scenarios.yaml b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_moral_scenarios.yaml new file mode 100644 index 00000000..92d018f2 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_moral_scenarios.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fa_template_yaml +process_docs: !function utils.process_moral_scenarios +tag: global_mmlu_full_fa_humanities_tasks +task: global_mmlu_full_fa_moral_scenarios diff --git a/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_nutrition.yaml b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_nutrition.yaml new file mode 100644 index 00000000..ae7e065e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_nutrition.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fa_template_yaml +process_docs: !function utils.process_nutrition +tag: global_mmlu_full_fa_other_tasks +task: global_mmlu_full_fa_nutrition diff --git a/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_philosophy.yaml b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_philosophy.yaml new file mode 100644 index 00000000..cd8513da --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_philosophy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fa_template_yaml +process_docs: !function utils.process_philosophy +tag: global_mmlu_full_fa_humanities_tasks +task: global_mmlu_full_fa_philosophy diff --git a/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_prehistory.yaml b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_prehistory.yaml new file mode 100644 index 00000000..9fd6bb3d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_prehistory.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fa_template_yaml +process_docs: !function utils.process_prehistory +tag: global_mmlu_full_fa_humanities_tasks +task: global_mmlu_full_fa_prehistory diff --git a/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_professional_accounting.yaml b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_professional_accounting.yaml new file mode 100644 index 00000000..99f6c316 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_professional_accounting.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fa_template_yaml +process_docs: !function utils.process_professional_accounting +tag: global_mmlu_full_fa_other_tasks +task: global_mmlu_full_fa_professional_accounting diff --git a/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_professional_law.yaml b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_professional_law.yaml new file mode 100644 index 00000000..9fee460a --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_professional_law.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fa_template_yaml +process_docs: !function utils.process_professional_law +tag: global_mmlu_full_fa_humanities_tasks +task: global_mmlu_full_fa_professional_law diff --git a/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_professional_medicine.yaml b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_professional_medicine.yaml new file mode 100644 index 00000000..13d67d45 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_professional_medicine.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fa_template_yaml +process_docs: !function utils.process_professional_medicine +tag: global_mmlu_full_fa_other_tasks +task: global_mmlu_full_fa_professional_medicine diff --git a/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_professional_psychology.yaml b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_professional_psychology.yaml new file mode 100644 index 00000000..3e821145 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_professional_psychology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fa_template_yaml +process_docs: !function utils.process_professional_psychology +tag: global_mmlu_full_fa_social_sciences_tasks +task: global_mmlu_full_fa_professional_psychology diff --git a/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_public_relations.yaml b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_public_relations.yaml new file mode 100644 index 00000000..de6cc311 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_public_relations.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fa_template_yaml +process_docs: !function utils.process_public_relations +tag: global_mmlu_full_fa_social_sciences_tasks +task: global_mmlu_full_fa_public_relations diff --git a/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_security_studies.yaml b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_security_studies.yaml new file mode 100644 index 00000000..64d5fd14 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_security_studies.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fa_template_yaml +process_docs: !function utils.process_security_studies +tag: global_mmlu_full_fa_social_sciences_tasks +task: global_mmlu_full_fa_security_studies diff --git a/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_sociology.yaml b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_sociology.yaml new file mode 100644 index 00000000..cf3d9564 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_sociology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fa_template_yaml +process_docs: !function utils.process_sociology +tag: global_mmlu_full_fa_social_sciences_tasks +task: global_mmlu_full_fa_sociology diff --git a/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_us_foreign_policy.yaml b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_us_foreign_policy.yaml new file mode 100644 index 00000000..38d51936 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_us_foreign_policy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fa_template_yaml +process_docs: !function utils.process_us_foreign_policy +tag: global_mmlu_full_fa_social_sciences_tasks +task: global_mmlu_full_fa_us_foreign_policy diff --git a/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_virology.yaml b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_virology.yaml new file mode 100644 index 00000000..39c5188d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_virology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fa_template_yaml +process_docs: !function utils.process_virology +tag: global_mmlu_full_fa_other_tasks +task: global_mmlu_full_fa_virology diff --git a/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_world_religions.yaml b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_world_religions.yaml new file mode 100644 index 00000000..44e6fc82 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fa/global_mmlu_full_fa_world_religions.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fa_template_yaml +process_docs: !function utils.process_world_religions +tag: global_mmlu_full_fa_humanities_tasks +task: global_mmlu_full_fa_world_religions diff --git a/lm_eval/tasks/global_mmlu/full/fa/utils.py b/lm_eval/tasks/global_mmlu/full/fa/utils.py new file mode 100644 index 00000000..7df72cb0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fa/utils.py @@ -0,0 +1,73 @@ +from functools import partial + + +SUBJECTS = [ + "abstract_algebra", + "anatomy", + "astronomy", + "business_ethics", + "clinical_knowledge", + "college_biology", + "college_chemistry", + "college_computer_science", + "college_mathematics", + "college_medicine", + "college_physics", + "computer_security", + "conceptual_physics", + "econometrics", + "electrical_engineering", + "elementary_mathematics", + "formal_logic", + "global_facts", + "high_school_biology", + "high_school_chemistry", + "high_school_computer_science", + "high_school_european_history", + "high_school_geography", + "high_school_government_and_politics", + "high_school_macroeconomics", + "high_school_mathematics", + "high_school_microeconomics", + "high_school_physics", + "high_school_psychology", + "high_school_statistics", + "high_school_us_history", + "high_school_world_history", + "human_aging", + "human_sexuality", + "international_law", + "jurisprudence", + "logical_fallacies", + "machine_learning", + "management", + "marketing", + "medical_genetics", + "miscellaneous", + "moral_disputes", + "moral_scenarios", + "nutrition", + "philosophy", + "prehistory", + "professional_accounting", + "professional_law", + "professional_medicine", + "professional_psychology", + "public_relations", + "security_studies", + "sociology", + "us_foreign_policy", + "virology", + "world_religions", +] + + +def process_docs(dataset, subject): + return dataset.filter(lambda x: x["subject"] == subject) + + +process_functions = { + f"process_{subject}": partial(process_docs, subject=subject) for subject in SUBJECTS +} + +globals().update(process_functions) diff --git a/lm_eval/tasks/global_mmlu/full/fil/_fil_template_yaml b/lm_eval/tasks/global_mmlu/full/fil/_fil_template_yaml new file mode 100644 index 00000000..32dc097a --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fil/_fil_template_yaml @@ -0,0 +1,16 @@ +dataset_path: CohereForAI/Global-MMLU +dataset_name: fil +test_split: test +fewshot_split: dev +fewshot_config: + sampler: first_n +output_type: multiple_choice +doc_to_text: "{{question.strip()}}\nA. {{option_a}}\nB. {{option_b}}\nC. {{option_c}}\nD. {{option_d}}\nAnswer:" +doc_to_choice: ["A", "B", "C", "D"] +doc_to_target: answer +metric_list: + - metric: acc + aggregation: mean + higher_is_better: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/fil/_global_mmlu_full_fil.yaml b/lm_eval/tasks/global_mmlu/full/fil/_global_mmlu_full_fil.yaml new file mode 100644 index 00000000..24fcb6d2 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fil/_global_mmlu_full_fil.yaml @@ -0,0 +1,11 @@ +group: global_mmlu_full_fil +task: + - global_mmlu_full_fil_stem + - global_mmlu_full_fil_other + - global_mmlu_full_fil_social_sciences + - global_mmlu_full_fil_humanities +aggregate_metric_list: + - metric: acc + weight_by_size: True +metadata: + version: 1.0 diff --git a/lm_eval/tasks/global_mmlu/full/fil/_global_mmlu_full_fil_humanities.yaml b/lm_eval/tasks/global_mmlu/full/fil/_global_mmlu_full_fil_humanities.yaml new file mode 100644 index 00000000..061eb818 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fil/_global_mmlu_full_fil_humanities.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_fil_humanities +task: + - global_mmlu_full_fil_humanities_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/fil/_global_mmlu_full_fil_other.yaml b/lm_eval/tasks/global_mmlu/full/fil/_global_mmlu_full_fil_other.yaml new file mode 100644 index 00000000..fea793ef --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fil/_global_mmlu_full_fil_other.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_fil_other +task: + - global_mmlu_full_fil_other_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/fil/_global_mmlu_full_fil_social_sciences.yaml b/lm_eval/tasks/global_mmlu/full/fil/_global_mmlu_full_fil_social_sciences.yaml new file mode 100644 index 00000000..e9f79330 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fil/_global_mmlu_full_fil_social_sciences.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_fil_social_sciences +task: + - global_mmlu_full_fil_social_sciences_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/fil/_global_mmlu_full_fil_stem.yaml b/lm_eval/tasks/global_mmlu/full/fil/_global_mmlu_full_fil_stem.yaml new file mode 100644 index 00000000..2e567c70 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fil/_global_mmlu_full_fil_stem.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_fil_stem +task: + - global_mmlu_full_fil_stem_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_abstract_algebra.yaml b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_abstract_algebra.yaml new file mode 100644 index 00000000..7eef19d6 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_abstract_algebra.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fil_template_yaml +process_docs: !function utils.process_abstract_algebra +tag: global_mmlu_full_fil_stem_tasks +task: global_mmlu_full_fil_abstract_algebra diff --git a/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_anatomy.yaml b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_anatomy.yaml new file mode 100644 index 00000000..e87d8d80 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_anatomy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fil_template_yaml +process_docs: !function utils.process_anatomy +tag: global_mmlu_full_fil_stem_tasks +task: global_mmlu_full_fil_anatomy diff --git a/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_astronomy.yaml b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_astronomy.yaml new file mode 100644 index 00000000..6c258877 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_astronomy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fil_template_yaml +process_docs: !function utils.process_astronomy +tag: global_mmlu_full_fil_stem_tasks +task: global_mmlu_full_fil_astronomy diff --git a/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_business_ethics.yaml b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_business_ethics.yaml new file mode 100644 index 00000000..139f3ccc --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_business_ethics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fil_template_yaml +process_docs: !function utils.process_business_ethics +tag: global_mmlu_full_fil_other_tasks +task: global_mmlu_full_fil_business_ethics diff --git a/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_clinical_knowledge.yaml b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_clinical_knowledge.yaml new file mode 100644 index 00000000..fc160a99 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_clinical_knowledge.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fil_template_yaml +process_docs: !function utils.process_clinical_knowledge +tag: global_mmlu_full_fil_other_tasks +task: global_mmlu_full_fil_clinical_knowledge diff --git a/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_college_biology.yaml b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_college_biology.yaml new file mode 100644 index 00000000..ff6fa3d8 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_college_biology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fil_template_yaml +process_docs: !function utils.process_college_biology +tag: global_mmlu_full_fil_stem_tasks +task: global_mmlu_full_fil_college_biology diff --git a/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_college_chemistry.yaml b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_college_chemistry.yaml new file mode 100644 index 00000000..61f0df50 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_college_chemistry.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fil_template_yaml +process_docs: !function utils.process_college_chemistry +tag: global_mmlu_full_fil_stem_tasks +task: global_mmlu_full_fil_college_chemistry diff --git a/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_college_computer_science.yaml b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_college_computer_science.yaml new file mode 100644 index 00000000..1385b934 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_college_computer_science.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fil_template_yaml +process_docs: !function utils.process_college_computer_science +tag: global_mmlu_full_fil_stem_tasks +task: global_mmlu_full_fil_college_computer_science diff --git a/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_college_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_college_mathematics.yaml new file mode 100644 index 00000000..afe15d7d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_college_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fil_template_yaml +process_docs: !function utils.process_college_mathematics +tag: global_mmlu_full_fil_stem_tasks +task: global_mmlu_full_fil_college_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_college_medicine.yaml b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_college_medicine.yaml new file mode 100644 index 00000000..221289f7 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_college_medicine.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fil_template_yaml +process_docs: !function utils.process_college_medicine +tag: global_mmlu_full_fil_other_tasks +task: global_mmlu_full_fil_college_medicine diff --git a/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_college_physics.yaml b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_college_physics.yaml new file mode 100644 index 00000000..863792b3 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_college_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fil_template_yaml +process_docs: !function utils.process_college_physics +tag: global_mmlu_full_fil_stem_tasks +task: global_mmlu_full_fil_college_physics diff --git a/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_computer_security.yaml b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_computer_security.yaml new file mode 100644 index 00000000..7971c606 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_computer_security.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fil_template_yaml +process_docs: !function utils.process_computer_security +tag: global_mmlu_full_fil_stem_tasks +task: global_mmlu_full_fil_computer_security diff --git a/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_conceptual_physics.yaml b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_conceptual_physics.yaml new file mode 100644 index 00000000..77a75ccf --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_conceptual_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fil_template_yaml +process_docs: !function utils.process_conceptual_physics +tag: global_mmlu_full_fil_stem_tasks +task: global_mmlu_full_fil_conceptual_physics diff --git a/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_econometrics.yaml b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_econometrics.yaml new file mode 100644 index 00000000..bd98fc8d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_econometrics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fil_template_yaml +process_docs: !function utils.process_econometrics +tag: global_mmlu_full_fil_social_sciences_tasks +task: global_mmlu_full_fil_econometrics diff --git a/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_electrical_engineering.yaml b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_electrical_engineering.yaml new file mode 100644 index 00000000..98e48a27 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_electrical_engineering.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fil_template_yaml +process_docs: !function utils.process_electrical_engineering +tag: global_mmlu_full_fil_stem_tasks +task: global_mmlu_full_fil_electrical_engineering diff --git a/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_elementary_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_elementary_mathematics.yaml new file mode 100644 index 00000000..eba4149c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_elementary_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fil_template_yaml +process_docs: !function utils.process_elementary_mathematics +tag: global_mmlu_full_fil_stem_tasks +task: global_mmlu_full_fil_elementary_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_formal_logic.yaml b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_formal_logic.yaml new file mode 100644 index 00000000..f1796059 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_formal_logic.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fil_template_yaml +process_docs: !function utils.process_formal_logic +tag: global_mmlu_full_fil_humanities_tasks +task: global_mmlu_full_fil_formal_logic diff --git a/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_global_facts.yaml b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_global_facts.yaml new file mode 100644 index 00000000..96886181 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_global_facts.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fil_template_yaml +process_docs: !function utils.process_global_facts +tag: global_mmlu_full_fil_other_tasks +task: global_mmlu_full_fil_global_facts diff --git a/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_high_school_biology.yaml b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_high_school_biology.yaml new file mode 100644 index 00000000..93d94120 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_high_school_biology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fil_template_yaml +process_docs: !function utils.process_high_school_biology +tag: global_mmlu_full_fil_stem_tasks +task: global_mmlu_full_fil_high_school_biology diff --git a/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_high_school_chemistry.yaml b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_high_school_chemistry.yaml new file mode 100644 index 00000000..9ec56d5b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_high_school_chemistry.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fil_template_yaml +process_docs: !function utils.process_high_school_chemistry +tag: global_mmlu_full_fil_stem_tasks +task: global_mmlu_full_fil_high_school_chemistry diff --git a/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_high_school_computer_science.yaml b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_high_school_computer_science.yaml new file mode 100644 index 00000000..82d86aed --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_high_school_computer_science.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fil_template_yaml +process_docs: !function utils.process_high_school_computer_science +tag: global_mmlu_full_fil_stem_tasks +task: global_mmlu_full_fil_high_school_computer_science diff --git a/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_high_school_european_history.yaml b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_high_school_european_history.yaml new file mode 100644 index 00000000..7fcdec0a --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_high_school_european_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fil_template_yaml +process_docs: !function utils.process_high_school_european_history +tag: global_mmlu_full_fil_humanities_tasks +task: global_mmlu_full_fil_high_school_european_history diff --git a/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_high_school_geography.yaml b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_high_school_geography.yaml new file mode 100644 index 00000000..96268192 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_high_school_geography.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fil_template_yaml +process_docs: !function utils.process_high_school_geography +tag: global_mmlu_full_fil_social_sciences_tasks +task: global_mmlu_full_fil_high_school_geography diff --git a/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_high_school_government_and_politics.yaml b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_high_school_government_and_politics.yaml new file mode 100644 index 00000000..f826de3d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_high_school_government_and_politics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fil_template_yaml +process_docs: !function utils.process_high_school_government_and_politics +tag: global_mmlu_full_fil_social_sciences_tasks +task: global_mmlu_full_fil_high_school_government_and_politics diff --git a/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_high_school_macroeconomics.yaml b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_high_school_macroeconomics.yaml new file mode 100644 index 00000000..104a7088 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_high_school_macroeconomics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fil_template_yaml +process_docs: !function utils.process_high_school_macroeconomics +tag: global_mmlu_full_fil_social_sciences_tasks +task: global_mmlu_full_fil_high_school_macroeconomics diff --git a/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_high_school_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_high_school_mathematics.yaml new file mode 100644 index 00000000..1d499b4d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_high_school_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fil_template_yaml +process_docs: !function utils.process_high_school_mathematics +tag: global_mmlu_full_fil_stem_tasks +task: global_mmlu_full_fil_high_school_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_high_school_microeconomics.yaml b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_high_school_microeconomics.yaml new file mode 100644 index 00000000..43fcc04d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_high_school_microeconomics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fil_template_yaml +process_docs: !function utils.process_high_school_microeconomics +tag: global_mmlu_full_fil_social_sciences_tasks +task: global_mmlu_full_fil_high_school_microeconomics diff --git a/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_high_school_physics.yaml b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_high_school_physics.yaml new file mode 100644 index 00000000..175f31ee --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_high_school_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fil_template_yaml +process_docs: !function utils.process_high_school_physics +tag: global_mmlu_full_fil_stem_tasks +task: global_mmlu_full_fil_high_school_physics diff --git a/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_high_school_psychology.yaml b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_high_school_psychology.yaml new file mode 100644 index 00000000..2fc2dd5c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_high_school_psychology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fil_template_yaml +process_docs: !function utils.process_high_school_psychology +tag: global_mmlu_full_fil_social_sciences_tasks +task: global_mmlu_full_fil_high_school_psychology diff --git a/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_high_school_statistics.yaml b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_high_school_statistics.yaml new file mode 100644 index 00000000..0540d57c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_high_school_statistics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fil_template_yaml +process_docs: !function utils.process_high_school_statistics +tag: global_mmlu_full_fil_stem_tasks +task: global_mmlu_full_fil_high_school_statistics diff --git a/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_high_school_us_history.yaml b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_high_school_us_history.yaml new file mode 100644 index 00000000..d0801af2 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_high_school_us_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fil_template_yaml +process_docs: !function utils.process_high_school_us_history +tag: global_mmlu_full_fil_humanities_tasks +task: global_mmlu_full_fil_high_school_us_history diff --git a/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_high_school_world_history.yaml b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_high_school_world_history.yaml new file mode 100644 index 00000000..724b7ce8 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_high_school_world_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fil_template_yaml +process_docs: !function utils.process_high_school_world_history +tag: global_mmlu_full_fil_humanities_tasks +task: global_mmlu_full_fil_high_school_world_history diff --git a/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_human_aging.yaml b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_human_aging.yaml new file mode 100644 index 00000000..6c2c1141 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_human_aging.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fil_template_yaml +process_docs: !function utils.process_human_aging +tag: global_mmlu_full_fil_other_tasks +task: global_mmlu_full_fil_human_aging diff --git a/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_human_sexuality.yaml b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_human_sexuality.yaml new file mode 100644 index 00000000..1672d5b2 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_human_sexuality.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fil_template_yaml +process_docs: !function utils.process_human_sexuality +tag: global_mmlu_full_fil_social_sciences_tasks +task: global_mmlu_full_fil_human_sexuality diff --git a/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_international_law.yaml b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_international_law.yaml new file mode 100644 index 00000000..4c5da91c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_international_law.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fil_template_yaml +process_docs: !function utils.process_international_law +tag: global_mmlu_full_fil_humanities_tasks +task: global_mmlu_full_fil_international_law diff --git a/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_jurisprudence.yaml b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_jurisprudence.yaml new file mode 100644 index 00000000..dea2b20b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_jurisprudence.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fil_template_yaml +process_docs: !function utils.process_jurisprudence +tag: global_mmlu_full_fil_humanities_tasks +task: global_mmlu_full_fil_jurisprudence diff --git a/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_logical_fallacies.yaml b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_logical_fallacies.yaml new file mode 100644 index 00000000..6a30c724 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_logical_fallacies.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fil_template_yaml +process_docs: !function utils.process_logical_fallacies +tag: global_mmlu_full_fil_humanities_tasks +task: global_mmlu_full_fil_logical_fallacies diff --git a/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_machine_learning.yaml b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_machine_learning.yaml new file mode 100644 index 00000000..d2a7062c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_machine_learning.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fil_template_yaml +process_docs: !function utils.process_machine_learning +tag: global_mmlu_full_fil_stem_tasks +task: global_mmlu_full_fil_machine_learning diff --git a/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_management.yaml b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_management.yaml new file mode 100644 index 00000000..1ea56835 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_management.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fil_template_yaml +process_docs: !function utils.process_management +tag: global_mmlu_full_fil_other_tasks +task: global_mmlu_full_fil_management diff --git a/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_marketing.yaml b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_marketing.yaml new file mode 100644 index 00000000..82d4490a --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_marketing.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fil_template_yaml +process_docs: !function utils.process_marketing +tag: global_mmlu_full_fil_other_tasks +task: global_mmlu_full_fil_marketing diff --git a/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_medical_genetics.yaml b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_medical_genetics.yaml new file mode 100644 index 00000000..bdeb0984 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_medical_genetics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fil_template_yaml +process_docs: !function utils.process_medical_genetics +tag: global_mmlu_full_fil_other_tasks +task: global_mmlu_full_fil_medical_genetics diff --git a/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_miscellaneous.yaml b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_miscellaneous.yaml new file mode 100644 index 00000000..51c56a3b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_miscellaneous.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fil_template_yaml +process_docs: !function utils.process_miscellaneous +tag: global_mmlu_full_fil_other_tasks +task: global_mmlu_full_fil_miscellaneous diff --git a/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_moral_disputes.yaml b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_moral_disputes.yaml new file mode 100644 index 00000000..53148a54 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_moral_disputes.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fil_template_yaml +process_docs: !function utils.process_moral_disputes +tag: global_mmlu_full_fil_humanities_tasks +task: global_mmlu_full_fil_moral_disputes diff --git a/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_moral_scenarios.yaml b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_moral_scenarios.yaml new file mode 100644 index 00000000..fb5fecf2 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_moral_scenarios.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fil_template_yaml +process_docs: !function utils.process_moral_scenarios +tag: global_mmlu_full_fil_humanities_tasks +task: global_mmlu_full_fil_moral_scenarios diff --git a/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_nutrition.yaml b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_nutrition.yaml new file mode 100644 index 00000000..35859dc2 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_nutrition.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fil_template_yaml +process_docs: !function utils.process_nutrition +tag: global_mmlu_full_fil_other_tasks +task: global_mmlu_full_fil_nutrition diff --git a/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_philosophy.yaml b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_philosophy.yaml new file mode 100644 index 00000000..dc2d414e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_philosophy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fil_template_yaml +process_docs: !function utils.process_philosophy +tag: global_mmlu_full_fil_humanities_tasks +task: global_mmlu_full_fil_philosophy diff --git a/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_prehistory.yaml b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_prehistory.yaml new file mode 100644 index 00000000..abf65fd2 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_prehistory.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fil_template_yaml +process_docs: !function utils.process_prehistory +tag: global_mmlu_full_fil_humanities_tasks +task: global_mmlu_full_fil_prehistory diff --git a/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_professional_accounting.yaml b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_professional_accounting.yaml new file mode 100644 index 00000000..04ce3436 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_professional_accounting.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fil_template_yaml +process_docs: !function utils.process_professional_accounting +tag: global_mmlu_full_fil_other_tasks +task: global_mmlu_full_fil_professional_accounting diff --git a/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_professional_law.yaml b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_professional_law.yaml new file mode 100644 index 00000000..e5694cf4 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_professional_law.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fil_template_yaml +process_docs: !function utils.process_professional_law +tag: global_mmlu_full_fil_humanities_tasks +task: global_mmlu_full_fil_professional_law diff --git a/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_professional_medicine.yaml b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_professional_medicine.yaml new file mode 100644 index 00000000..e7fd0446 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_professional_medicine.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fil_template_yaml +process_docs: !function utils.process_professional_medicine +tag: global_mmlu_full_fil_other_tasks +task: global_mmlu_full_fil_professional_medicine diff --git a/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_professional_psychology.yaml b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_professional_psychology.yaml new file mode 100644 index 00000000..b9ce14aa --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_professional_psychology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fil_template_yaml +process_docs: !function utils.process_professional_psychology +tag: global_mmlu_full_fil_social_sciences_tasks +task: global_mmlu_full_fil_professional_psychology diff --git a/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_public_relations.yaml b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_public_relations.yaml new file mode 100644 index 00000000..fdae5298 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_public_relations.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fil_template_yaml +process_docs: !function utils.process_public_relations +tag: global_mmlu_full_fil_social_sciences_tasks +task: global_mmlu_full_fil_public_relations diff --git a/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_security_studies.yaml b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_security_studies.yaml new file mode 100644 index 00000000..4a03eec1 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_security_studies.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fil_template_yaml +process_docs: !function utils.process_security_studies +tag: global_mmlu_full_fil_social_sciences_tasks +task: global_mmlu_full_fil_security_studies diff --git a/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_sociology.yaml b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_sociology.yaml new file mode 100644 index 00000000..bc0ed052 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_sociology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fil_template_yaml +process_docs: !function utils.process_sociology +tag: global_mmlu_full_fil_social_sciences_tasks +task: global_mmlu_full_fil_sociology diff --git a/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_us_foreign_policy.yaml b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_us_foreign_policy.yaml new file mode 100644 index 00000000..ed40afb6 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_us_foreign_policy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fil_template_yaml +process_docs: !function utils.process_us_foreign_policy +tag: global_mmlu_full_fil_social_sciences_tasks +task: global_mmlu_full_fil_us_foreign_policy diff --git a/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_virology.yaml b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_virology.yaml new file mode 100644 index 00000000..85ed4d42 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_virology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fil_template_yaml +process_docs: !function utils.process_virology +tag: global_mmlu_full_fil_other_tasks +task: global_mmlu_full_fil_virology diff --git a/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_world_religions.yaml b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_world_religions.yaml new file mode 100644 index 00000000..3ee6bce1 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fil/global_mmlu_full_fil_world_religions.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fil_template_yaml +process_docs: !function utils.process_world_religions +tag: global_mmlu_full_fil_humanities_tasks +task: global_mmlu_full_fil_world_religions diff --git a/lm_eval/tasks/global_mmlu/full/fil/utils.py b/lm_eval/tasks/global_mmlu/full/fil/utils.py new file mode 100644 index 00000000..7df72cb0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fil/utils.py @@ -0,0 +1,73 @@ +from functools import partial + + +SUBJECTS = [ + "abstract_algebra", + "anatomy", + "astronomy", + "business_ethics", + "clinical_knowledge", + "college_biology", + "college_chemistry", + "college_computer_science", + "college_mathematics", + "college_medicine", + "college_physics", + "computer_security", + "conceptual_physics", + "econometrics", + "electrical_engineering", + "elementary_mathematics", + "formal_logic", + "global_facts", + "high_school_biology", + "high_school_chemistry", + "high_school_computer_science", + "high_school_european_history", + "high_school_geography", + "high_school_government_and_politics", + "high_school_macroeconomics", + "high_school_mathematics", + "high_school_microeconomics", + "high_school_physics", + "high_school_psychology", + "high_school_statistics", + "high_school_us_history", + "high_school_world_history", + "human_aging", + "human_sexuality", + "international_law", + "jurisprudence", + "logical_fallacies", + "machine_learning", + "management", + "marketing", + "medical_genetics", + "miscellaneous", + "moral_disputes", + "moral_scenarios", + "nutrition", + "philosophy", + "prehistory", + "professional_accounting", + "professional_law", + "professional_medicine", + "professional_psychology", + "public_relations", + "security_studies", + "sociology", + "us_foreign_policy", + "virology", + "world_religions", +] + + +def process_docs(dataset, subject): + return dataset.filter(lambda x: x["subject"] == subject) + + +process_functions = { + f"process_{subject}": partial(process_docs, subject=subject) for subject in SUBJECTS +} + +globals().update(process_functions) diff --git a/lm_eval/tasks/global_mmlu/full/fr/_fr_template_yaml b/lm_eval/tasks/global_mmlu/full/fr/_fr_template_yaml new file mode 100644 index 00000000..47ca7972 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fr/_fr_template_yaml @@ -0,0 +1,16 @@ +dataset_path: CohereForAI/Global-MMLU +dataset_name: fr +test_split: test +fewshot_split: dev +fewshot_config: + sampler: first_n +output_type: multiple_choice +doc_to_text: "{{question.strip()}}\nA. {{option_a}}\nB. {{option_b}}\nC. {{option_c}}\nD. {{option_d}}\nAnswer:" +doc_to_choice: ["A", "B", "C", "D"] +doc_to_target: answer +metric_list: + - metric: acc + aggregation: mean + higher_is_better: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/fr/_global_mmlu_full_fr.yaml b/lm_eval/tasks/global_mmlu/full/fr/_global_mmlu_full_fr.yaml new file mode 100644 index 00000000..e85d6746 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fr/_global_mmlu_full_fr.yaml @@ -0,0 +1,11 @@ +group: global_mmlu_full_fr +task: + - global_mmlu_full_fr_stem + - global_mmlu_full_fr_other + - global_mmlu_full_fr_social_sciences + - global_mmlu_full_fr_humanities +aggregate_metric_list: + - metric: acc + weight_by_size: True +metadata: + version: 1.0 diff --git a/lm_eval/tasks/global_mmlu/full/fr/_global_mmlu_full_fr_humanities.yaml b/lm_eval/tasks/global_mmlu/full/fr/_global_mmlu_full_fr_humanities.yaml new file mode 100644 index 00000000..697e3a29 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fr/_global_mmlu_full_fr_humanities.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_fr_humanities +task: + - global_mmlu_full_fr_humanities_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/fr/_global_mmlu_full_fr_other.yaml b/lm_eval/tasks/global_mmlu/full/fr/_global_mmlu_full_fr_other.yaml new file mode 100644 index 00000000..9b2ada6b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fr/_global_mmlu_full_fr_other.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_fr_other +task: + - global_mmlu_full_fr_other_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/fr/_global_mmlu_full_fr_social_sciences.yaml b/lm_eval/tasks/global_mmlu/full/fr/_global_mmlu_full_fr_social_sciences.yaml new file mode 100644 index 00000000..ac7e4605 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fr/_global_mmlu_full_fr_social_sciences.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_fr_social_sciences +task: + - global_mmlu_full_fr_social_sciences_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/fr/_global_mmlu_full_fr_stem.yaml b/lm_eval/tasks/global_mmlu/full/fr/_global_mmlu_full_fr_stem.yaml new file mode 100644 index 00000000..c81d601f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fr/_global_mmlu_full_fr_stem.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_fr_stem +task: + - global_mmlu_full_fr_stem_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_abstract_algebra.yaml b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_abstract_algebra.yaml new file mode 100644 index 00000000..bf7d76c3 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_abstract_algebra.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fr_template_yaml +process_docs: !function utils.process_abstract_algebra +tag: global_mmlu_full_fr_stem_tasks +task: global_mmlu_full_fr_abstract_algebra diff --git a/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_anatomy.yaml b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_anatomy.yaml new file mode 100644 index 00000000..e9a96927 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_anatomy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fr_template_yaml +process_docs: !function utils.process_anatomy +tag: global_mmlu_full_fr_stem_tasks +task: global_mmlu_full_fr_anatomy diff --git a/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_astronomy.yaml b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_astronomy.yaml new file mode 100644 index 00000000..6e4ca5a7 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_astronomy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fr_template_yaml +process_docs: !function utils.process_astronomy +tag: global_mmlu_full_fr_stem_tasks +task: global_mmlu_full_fr_astronomy diff --git a/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_business_ethics.yaml b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_business_ethics.yaml new file mode 100644 index 00000000..df3c1fbd --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_business_ethics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fr_template_yaml +process_docs: !function utils.process_business_ethics +tag: global_mmlu_full_fr_other_tasks +task: global_mmlu_full_fr_business_ethics diff --git a/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_clinical_knowledge.yaml b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_clinical_knowledge.yaml new file mode 100644 index 00000000..b0daa2e6 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_clinical_knowledge.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fr_template_yaml +process_docs: !function utils.process_clinical_knowledge +tag: global_mmlu_full_fr_other_tasks +task: global_mmlu_full_fr_clinical_knowledge diff --git a/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_college_biology.yaml b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_college_biology.yaml new file mode 100644 index 00000000..1e997578 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_college_biology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fr_template_yaml +process_docs: !function utils.process_college_biology +tag: global_mmlu_full_fr_stem_tasks +task: global_mmlu_full_fr_college_biology diff --git a/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_college_chemistry.yaml b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_college_chemistry.yaml new file mode 100644 index 00000000..9c1c3189 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_college_chemistry.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fr_template_yaml +process_docs: !function utils.process_college_chemistry +tag: global_mmlu_full_fr_stem_tasks +task: global_mmlu_full_fr_college_chemistry diff --git a/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_college_computer_science.yaml b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_college_computer_science.yaml new file mode 100644 index 00000000..078108f8 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_college_computer_science.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fr_template_yaml +process_docs: !function utils.process_college_computer_science +tag: global_mmlu_full_fr_stem_tasks +task: global_mmlu_full_fr_college_computer_science diff --git a/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_college_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_college_mathematics.yaml new file mode 100644 index 00000000..bf2f2940 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_college_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fr_template_yaml +process_docs: !function utils.process_college_mathematics +tag: global_mmlu_full_fr_stem_tasks +task: global_mmlu_full_fr_college_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_college_medicine.yaml b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_college_medicine.yaml new file mode 100644 index 00000000..8c9ccc80 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_college_medicine.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fr_template_yaml +process_docs: !function utils.process_college_medicine +tag: global_mmlu_full_fr_other_tasks +task: global_mmlu_full_fr_college_medicine diff --git a/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_college_physics.yaml b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_college_physics.yaml new file mode 100644 index 00000000..01dcea37 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_college_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fr_template_yaml +process_docs: !function utils.process_college_physics +tag: global_mmlu_full_fr_stem_tasks +task: global_mmlu_full_fr_college_physics diff --git a/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_computer_security.yaml b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_computer_security.yaml new file mode 100644 index 00000000..794f64be --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_computer_security.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fr_template_yaml +process_docs: !function utils.process_computer_security +tag: global_mmlu_full_fr_stem_tasks +task: global_mmlu_full_fr_computer_security diff --git a/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_conceptual_physics.yaml b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_conceptual_physics.yaml new file mode 100644 index 00000000..12c6afc2 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_conceptual_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fr_template_yaml +process_docs: !function utils.process_conceptual_physics +tag: global_mmlu_full_fr_stem_tasks +task: global_mmlu_full_fr_conceptual_physics diff --git a/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_econometrics.yaml b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_econometrics.yaml new file mode 100644 index 00000000..1f33ddab --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_econometrics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fr_template_yaml +process_docs: !function utils.process_econometrics +tag: global_mmlu_full_fr_social_sciences_tasks +task: global_mmlu_full_fr_econometrics diff --git a/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_electrical_engineering.yaml b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_electrical_engineering.yaml new file mode 100644 index 00000000..8dcb0585 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_electrical_engineering.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fr_template_yaml +process_docs: !function utils.process_electrical_engineering +tag: global_mmlu_full_fr_stem_tasks +task: global_mmlu_full_fr_electrical_engineering diff --git a/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_elementary_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_elementary_mathematics.yaml new file mode 100644 index 00000000..2658ce96 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_elementary_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fr_template_yaml +process_docs: !function utils.process_elementary_mathematics +tag: global_mmlu_full_fr_stem_tasks +task: global_mmlu_full_fr_elementary_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_formal_logic.yaml b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_formal_logic.yaml new file mode 100644 index 00000000..5239cb1c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_formal_logic.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fr_template_yaml +process_docs: !function utils.process_formal_logic +tag: global_mmlu_full_fr_humanities_tasks +task: global_mmlu_full_fr_formal_logic diff --git a/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_global_facts.yaml b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_global_facts.yaml new file mode 100644 index 00000000..2763dcb5 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_global_facts.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fr_template_yaml +process_docs: !function utils.process_global_facts +tag: global_mmlu_full_fr_other_tasks +task: global_mmlu_full_fr_global_facts diff --git a/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_high_school_biology.yaml b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_high_school_biology.yaml new file mode 100644 index 00000000..2a6a26c9 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_high_school_biology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fr_template_yaml +process_docs: !function utils.process_high_school_biology +tag: global_mmlu_full_fr_stem_tasks +task: global_mmlu_full_fr_high_school_biology diff --git a/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_high_school_chemistry.yaml b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_high_school_chemistry.yaml new file mode 100644 index 00000000..6ffacc29 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_high_school_chemistry.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fr_template_yaml +process_docs: !function utils.process_high_school_chemistry +tag: global_mmlu_full_fr_stem_tasks +task: global_mmlu_full_fr_high_school_chemistry diff --git a/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_high_school_computer_science.yaml b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_high_school_computer_science.yaml new file mode 100644 index 00000000..d1720422 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_high_school_computer_science.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fr_template_yaml +process_docs: !function utils.process_high_school_computer_science +tag: global_mmlu_full_fr_stem_tasks +task: global_mmlu_full_fr_high_school_computer_science diff --git a/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_high_school_european_history.yaml b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_high_school_european_history.yaml new file mode 100644 index 00000000..9788e7be --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_high_school_european_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fr_template_yaml +process_docs: !function utils.process_high_school_european_history +tag: global_mmlu_full_fr_humanities_tasks +task: global_mmlu_full_fr_high_school_european_history diff --git a/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_high_school_geography.yaml b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_high_school_geography.yaml new file mode 100644 index 00000000..3e2ff22e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_high_school_geography.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fr_template_yaml +process_docs: !function utils.process_high_school_geography +tag: global_mmlu_full_fr_social_sciences_tasks +task: global_mmlu_full_fr_high_school_geography diff --git a/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_high_school_government_and_politics.yaml b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_high_school_government_and_politics.yaml new file mode 100644 index 00000000..2aba3b61 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_high_school_government_and_politics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fr_template_yaml +process_docs: !function utils.process_high_school_government_and_politics +tag: global_mmlu_full_fr_social_sciences_tasks +task: global_mmlu_full_fr_high_school_government_and_politics diff --git a/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_high_school_macroeconomics.yaml b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_high_school_macroeconomics.yaml new file mode 100644 index 00000000..21fb1df5 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_high_school_macroeconomics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fr_template_yaml +process_docs: !function utils.process_high_school_macroeconomics +tag: global_mmlu_full_fr_social_sciences_tasks +task: global_mmlu_full_fr_high_school_macroeconomics diff --git a/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_high_school_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_high_school_mathematics.yaml new file mode 100644 index 00000000..a975d1fc --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_high_school_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fr_template_yaml +process_docs: !function utils.process_high_school_mathematics +tag: global_mmlu_full_fr_stem_tasks +task: global_mmlu_full_fr_high_school_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_high_school_microeconomics.yaml b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_high_school_microeconomics.yaml new file mode 100644 index 00000000..ff654ff3 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_high_school_microeconomics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fr_template_yaml +process_docs: !function utils.process_high_school_microeconomics +tag: global_mmlu_full_fr_social_sciences_tasks +task: global_mmlu_full_fr_high_school_microeconomics diff --git a/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_high_school_physics.yaml b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_high_school_physics.yaml new file mode 100644 index 00000000..4038c956 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_high_school_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fr_template_yaml +process_docs: !function utils.process_high_school_physics +tag: global_mmlu_full_fr_stem_tasks +task: global_mmlu_full_fr_high_school_physics diff --git a/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_high_school_psychology.yaml b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_high_school_psychology.yaml new file mode 100644 index 00000000..a65da780 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_high_school_psychology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fr_template_yaml +process_docs: !function utils.process_high_school_psychology +tag: global_mmlu_full_fr_social_sciences_tasks +task: global_mmlu_full_fr_high_school_psychology diff --git a/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_high_school_statistics.yaml b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_high_school_statistics.yaml new file mode 100644 index 00000000..37c75136 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_high_school_statistics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fr_template_yaml +process_docs: !function utils.process_high_school_statistics +tag: global_mmlu_full_fr_stem_tasks +task: global_mmlu_full_fr_high_school_statistics diff --git a/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_high_school_us_history.yaml b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_high_school_us_history.yaml new file mode 100644 index 00000000..a0e123f2 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_high_school_us_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fr_template_yaml +process_docs: !function utils.process_high_school_us_history +tag: global_mmlu_full_fr_humanities_tasks +task: global_mmlu_full_fr_high_school_us_history diff --git a/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_high_school_world_history.yaml b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_high_school_world_history.yaml new file mode 100644 index 00000000..e2a9cf6b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_high_school_world_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fr_template_yaml +process_docs: !function utils.process_high_school_world_history +tag: global_mmlu_full_fr_humanities_tasks +task: global_mmlu_full_fr_high_school_world_history diff --git a/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_human_aging.yaml b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_human_aging.yaml new file mode 100644 index 00000000..b9e9ece9 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_human_aging.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fr_template_yaml +process_docs: !function utils.process_human_aging +tag: global_mmlu_full_fr_other_tasks +task: global_mmlu_full_fr_human_aging diff --git a/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_human_sexuality.yaml b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_human_sexuality.yaml new file mode 100644 index 00000000..eac30d27 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_human_sexuality.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fr_template_yaml +process_docs: !function utils.process_human_sexuality +tag: global_mmlu_full_fr_social_sciences_tasks +task: global_mmlu_full_fr_human_sexuality diff --git a/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_international_law.yaml b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_international_law.yaml new file mode 100644 index 00000000..2e15b0fb --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_international_law.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fr_template_yaml +process_docs: !function utils.process_international_law +tag: global_mmlu_full_fr_humanities_tasks +task: global_mmlu_full_fr_international_law diff --git a/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_jurisprudence.yaml b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_jurisprudence.yaml new file mode 100644 index 00000000..f42079c9 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_jurisprudence.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fr_template_yaml +process_docs: !function utils.process_jurisprudence +tag: global_mmlu_full_fr_humanities_tasks +task: global_mmlu_full_fr_jurisprudence diff --git a/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_logical_fallacies.yaml b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_logical_fallacies.yaml new file mode 100644 index 00000000..68ebdb71 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_logical_fallacies.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fr_template_yaml +process_docs: !function utils.process_logical_fallacies +tag: global_mmlu_full_fr_humanities_tasks +task: global_mmlu_full_fr_logical_fallacies diff --git a/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_machine_learning.yaml b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_machine_learning.yaml new file mode 100644 index 00000000..25a8df3a --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_machine_learning.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fr_template_yaml +process_docs: !function utils.process_machine_learning +tag: global_mmlu_full_fr_stem_tasks +task: global_mmlu_full_fr_machine_learning diff --git a/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_management.yaml b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_management.yaml new file mode 100644 index 00000000..73f7d869 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_management.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fr_template_yaml +process_docs: !function utils.process_management +tag: global_mmlu_full_fr_other_tasks +task: global_mmlu_full_fr_management diff --git a/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_marketing.yaml b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_marketing.yaml new file mode 100644 index 00000000..8a19b83e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_marketing.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fr_template_yaml +process_docs: !function utils.process_marketing +tag: global_mmlu_full_fr_other_tasks +task: global_mmlu_full_fr_marketing diff --git a/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_medical_genetics.yaml b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_medical_genetics.yaml new file mode 100644 index 00000000..d15774f1 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_medical_genetics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fr_template_yaml +process_docs: !function utils.process_medical_genetics +tag: global_mmlu_full_fr_other_tasks +task: global_mmlu_full_fr_medical_genetics diff --git a/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_miscellaneous.yaml b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_miscellaneous.yaml new file mode 100644 index 00000000..d7519709 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_miscellaneous.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fr_template_yaml +process_docs: !function utils.process_miscellaneous +tag: global_mmlu_full_fr_other_tasks +task: global_mmlu_full_fr_miscellaneous diff --git a/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_moral_disputes.yaml b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_moral_disputes.yaml new file mode 100644 index 00000000..f625921e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_moral_disputes.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fr_template_yaml +process_docs: !function utils.process_moral_disputes +tag: global_mmlu_full_fr_humanities_tasks +task: global_mmlu_full_fr_moral_disputes diff --git a/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_moral_scenarios.yaml b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_moral_scenarios.yaml new file mode 100644 index 00000000..4575ca04 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_moral_scenarios.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fr_template_yaml +process_docs: !function utils.process_moral_scenarios +tag: global_mmlu_full_fr_humanities_tasks +task: global_mmlu_full_fr_moral_scenarios diff --git a/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_nutrition.yaml b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_nutrition.yaml new file mode 100644 index 00000000..61521c91 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_nutrition.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fr_template_yaml +process_docs: !function utils.process_nutrition +tag: global_mmlu_full_fr_other_tasks +task: global_mmlu_full_fr_nutrition diff --git a/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_philosophy.yaml b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_philosophy.yaml new file mode 100644 index 00000000..7f771c34 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_philosophy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fr_template_yaml +process_docs: !function utils.process_philosophy +tag: global_mmlu_full_fr_humanities_tasks +task: global_mmlu_full_fr_philosophy diff --git a/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_prehistory.yaml b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_prehistory.yaml new file mode 100644 index 00000000..3bcac0f5 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_prehistory.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fr_template_yaml +process_docs: !function utils.process_prehistory +tag: global_mmlu_full_fr_humanities_tasks +task: global_mmlu_full_fr_prehistory diff --git a/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_professional_accounting.yaml b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_professional_accounting.yaml new file mode 100644 index 00000000..a06a7af5 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_professional_accounting.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fr_template_yaml +process_docs: !function utils.process_professional_accounting +tag: global_mmlu_full_fr_other_tasks +task: global_mmlu_full_fr_professional_accounting diff --git a/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_professional_law.yaml b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_professional_law.yaml new file mode 100644 index 00000000..2ecf2e8e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_professional_law.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fr_template_yaml +process_docs: !function utils.process_professional_law +tag: global_mmlu_full_fr_humanities_tasks +task: global_mmlu_full_fr_professional_law diff --git a/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_professional_medicine.yaml b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_professional_medicine.yaml new file mode 100644 index 00000000..983a2d38 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_professional_medicine.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fr_template_yaml +process_docs: !function utils.process_professional_medicine +tag: global_mmlu_full_fr_other_tasks +task: global_mmlu_full_fr_professional_medicine diff --git a/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_professional_psychology.yaml b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_professional_psychology.yaml new file mode 100644 index 00000000..59d9aa30 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_professional_psychology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fr_template_yaml +process_docs: !function utils.process_professional_psychology +tag: global_mmlu_full_fr_social_sciences_tasks +task: global_mmlu_full_fr_professional_psychology diff --git a/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_public_relations.yaml b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_public_relations.yaml new file mode 100644 index 00000000..d84b7ad0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_public_relations.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fr_template_yaml +process_docs: !function utils.process_public_relations +tag: global_mmlu_full_fr_social_sciences_tasks +task: global_mmlu_full_fr_public_relations diff --git a/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_security_studies.yaml b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_security_studies.yaml new file mode 100644 index 00000000..fcd82b7d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_security_studies.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fr_template_yaml +process_docs: !function utils.process_security_studies +tag: global_mmlu_full_fr_social_sciences_tasks +task: global_mmlu_full_fr_security_studies diff --git a/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_sociology.yaml b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_sociology.yaml new file mode 100644 index 00000000..ff7b8fd3 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_sociology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fr_template_yaml +process_docs: !function utils.process_sociology +tag: global_mmlu_full_fr_social_sciences_tasks +task: global_mmlu_full_fr_sociology diff --git a/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_us_foreign_policy.yaml b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_us_foreign_policy.yaml new file mode 100644 index 00000000..d92c2095 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_us_foreign_policy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fr_template_yaml +process_docs: !function utils.process_us_foreign_policy +tag: global_mmlu_full_fr_social_sciences_tasks +task: global_mmlu_full_fr_us_foreign_policy diff --git a/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_virology.yaml b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_virology.yaml new file mode 100644 index 00000000..211c96a7 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_virology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fr_template_yaml +process_docs: !function utils.process_virology +tag: global_mmlu_full_fr_other_tasks +task: global_mmlu_full_fr_virology diff --git a/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_world_religions.yaml b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_world_religions.yaml new file mode 100644 index 00000000..f1f168ae --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fr/global_mmlu_full_fr_world_religions.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _fr_template_yaml +process_docs: !function utils.process_world_religions +tag: global_mmlu_full_fr_humanities_tasks +task: global_mmlu_full_fr_world_religions diff --git a/lm_eval/tasks/global_mmlu/full/fr/utils.py b/lm_eval/tasks/global_mmlu/full/fr/utils.py new file mode 100644 index 00000000..7df72cb0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/fr/utils.py @@ -0,0 +1,73 @@ +from functools import partial + + +SUBJECTS = [ + "abstract_algebra", + "anatomy", + "astronomy", + "business_ethics", + "clinical_knowledge", + "college_biology", + "college_chemistry", + "college_computer_science", + "college_mathematics", + "college_medicine", + "college_physics", + "computer_security", + "conceptual_physics", + "econometrics", + "electrical_engineering", + "elementary_mathematics", + "formal_logic", + "global_facts", + "high_school_biology", + "high_school_chemistry", + "high_school_computer_science", + "high_school_european_history", + "high_school_geography", + "high_school_government_and_politics", + "high_school_macroeconomics", + "high_school_mathematics", + "high_school_microeconomics", + "high_school_physics", + "high_school_psychology", + "high_school_statistics", + "high_school_us_history", + "high_school_world_history", + "human_aging", + "human_sexuality", + "international_law", + "jurisprudence", + "logical_fallacies", + "machine_learning", + "management", + "marketing", + "medical_genetics", + "miscellaneous", + "moral_disputes", + "moral_scenarios", + "nutrition", + "philosophy", + "prehistory", + "professional_accounting", + "professional_law", + "professional_medicine", + "professional_psychology", + "public_relations", + "security_studies", + "sociology", + "us_foreign_policy", + "virology", + "world_religions", +] + + +def process_docs(dataset, subject): + return dataset.filter(lambda x: x["subject"] == subject) + + +process_functions = { + f"process_{subject}": partial(process_docs, subject=subject) for subject in SUBJECTS +} + +globals().update(process_functions) diff --git a/lm_eval/tasks/global_mmlu/full/ha/_global_mmlu_full_ha.yaml b/lm_eval/tasks/global_mmlu/full/ha/_global_mmlu_full_ha.yaml new file mode 100644 index 00000000..08a958bb --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ha/_global_mmlu_full_ha.yaml @@ -0,0 +1,11 @@ +group: global_mmlu_full_ha +task: + - global_mmlu_full_ha_stem + - global_mmlu_full_ha_other + - global_mmlu_full_ha_social_sciences + - global_mmlu_full_ha_humanities +aggregate_metric_list: + - metric: acc + weight_by_size: True +metadata: + version: 1.0 diff --git a/lm_eval/tasks/global_mmlu/full/ha/_global_mmlu_full_ha_humanities.yaml b/lm_eval/tasks/global_mmlu/full/ha/_global_mmlu_full_ha_humanities.yaml new file mode 100644 index 00000000..84cce38d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ha/_global_mmlu_full_ha_humanities.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_ha_humanities +task: + - global_mmlu_full_ha_humanities_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/ha/_global_mmlu_full_ha_other.yaml b/lm_eval/tasks/global_mmlu/full/ha/_global_mmlu_full_ha_other.yaml new file mode 100644 index 00000000..73a6ea0d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ha/_global_mmlu_full_ha_other.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_ha_other +task: + - global_mmlu_full_ha_other_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/ha/_global_mmlu_full_ha_social_sciences.yaml b/lm_eval/tasks/global_mmlu/full/ha/_global_mmlu_full_ha_social_sciences.yaml new file mode 100644 index 00000000..8b520a5d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ha/_global_mmlu_full_ha_social_sciences.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_ha_social_sciences +task: + - global_mmlu_full_ha_social_sciences_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/ha/_global_mmlu_full_ha_stem.yaml b/lm_eval/tasks/global_mmlu/full/ha/_global_mmlu_full_ha_stem.yaml new file mode 100644 index 00000000..6213d280 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ha/_global_mmlu_full_ha_stem.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_ha_stem +task: + - global_mmlu_full_ha_stem_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/ha/_ha_template_yaml b/lm_eval/tasks/global_mmlu/full/ha/_ha_template_yaml new file mode 100644 index 00000000..8521fe50 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ha/_ha_template_yaml @@ -0,0 +1,16 @@ +dataset_path: CohereForAI/Global-MMLU +dataset_name: ha +test_split: test +fewshot_split: dev +fewshot_config: + sampler: first_n +output_type: multiple_choice +doc_to_text: "{{question.strip()}}\nA. {{option_a}}\nB. {{option_b}}\nC. {{option_c}}\nD. {{option_d}}\nAnswer:" +doc_to_choice: ["A", "B", "C", "D"] +doc_to_target: answer +metric_list: + - metric: acc + aggregation: mean + higher_is_better: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_abstract_algebra.yaml b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_abstract_algebra.yaml new file mode 100644 index 00000000..62ad5e7d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_abstract_algebra.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ha_template_yaml +process_docs: !function utils.process_abstract_algebra +tag: global_mmlu_full_ha_stem_tasks +task: global_mmlu_full_ha_abstract_algebra diff --git a/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_anatomy.yaml b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_anatomy.yaml new file mode 100644 index 00000000..2ead0f6c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_anatomy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ha_template_yaml +process_docs: !function utils.process_anatomy +tag: global_mmlu_full_ha_stem_tasks +task: global_mmlu_full_ha_anatomy diff --git a/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_astronomy.yaml b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_astronomy.yaml new file mode 100644 index 00000000..1616398f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_astronomy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ha_template_yaml +process_docs: !function utils.process_astronomy +tag: global_mmlu_full_ha_stem_tasks +task: global_mmlu_full_ha_astronomy diff --git a/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_business_ethics.yaml b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_business_ethics.yaml new file mode 100644 index 00000000..c1719b0e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_business_ethics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ha_template_yaml +process_docs: !function utils.process_business_ethics +tag: global_mmlu_full_ha_other_tasks +task: global_mmlu_full_ha_business_ethics diff --git a/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_clinical_knowledge.yaml b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_clinical_knowledge.yaml new file mode 100644 index 00000000..dcef5e27 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_clinical_knowledge.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ha_template_yaml +process_docs: !function utils.process_clinical_knowledge +tag: global_mmlu_full_ha_other_tasks +task: global_mmlu_full_ha_clinical_knowledge diff --git a/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_college_biology.yaml b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_college_biology.yaml new file mode 100644 index 00000000..f2825694 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_college_biology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ha_template_yaml +process_docs: !function utils.process_college_biology +tag: global_mmlu_full_ha_stem_tasks +task: global_mmlu_full_ha_college_biology diff --git a/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_college_chemistry.yaml b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_college_chemistry.yaml new file mode 100644 index 00000000..73a422e3 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_college_chemistry.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ha_template_yaml +process_docs: !function utils.process_college_chemistry +tag: global_mmlu_full_ha_stem_tasks +task: global_mmlu_full_ha_college_chemistry diff --git a/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_college_computer_science.yaml b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_college_computer_science.yaml new file mode 100644 index 00000000..7bdb65c9 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_college_computer_science.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ha_template_yaml +process_docs: !function utils.process_college_computer_science +tag: global_mmlu_full_ha_stem_tasks +task: global_mmlu_full_ha_college_computer_science diff --git a/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_college_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_college_mathematics.yaml new file mode 100644 index 00000000..47e5326c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_college_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ha_template_yaml +process_docs: !function utils.process_college_mathematics +tag: global_mmlu_full_ha_stem_tasks +task: global_mmlu_full_ha_college_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_college_medicine.yaml b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_college_medicine.yaml new file mode 100644 index 00000000..9065f085 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_college_medicine.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ha_template_yaml +process_docs: !function utils.process_college_medicine +tag: global_mmlu_full_ha_other_tasks +task: global_mmlu_full_ha_college_medicine diff --git a/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_college_physics.yaml b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_college_physics.yaml new file mode 100644 index 00000000..40aa11c5 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_college_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ha_template_yaml +process_docs: !function utils.process_college_physics +tag: global_mmlu_full_ha_stem_tasks +task: global_mmlu_full_ha_college_physics diff --git a/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_computer_security.yaml b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_computer_security.yaml new file mode 100644 index 00000000..38d1e9c2 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_computer_security.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ha_template_yaml +process_docs: !function utils.process_computer_security +tag: global_mmlu_full_ha_stem_tasks +task: global_mmlu_full_ha_computer_security diff --git a/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_conceptual_physics.yaml b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_conceptual_physics.yaml new file mode 100644 index 00000000..7326514a --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_conceptual_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ha_template_yaml +process_docs: !function utils.process_conceptual_physics +tag: global_mmlu_full_ha_stem_tasks +task: global_mmlu_full_ha_conceptual_physics diff --git a/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_econometrics.yaml b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_econometrics.yaml new file mode 100644 index 00000000..e865b6bc --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_econometrics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ha_template_yaml +process_docs: !function utils.process_econometrics +tag: global_mmlu_full_ha_social_sciences_tasks +task: global_mmlu_full_ha_econometrics diff --git a/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_electrical_engineering.yaml b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_electrical_engineering.yaml new file mode 100644 index 00000000..9457d1bb --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_electrical_engineering.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ha_template_yaml +process_docs: !function utils.process_electrical_engineering +tag: global_mmlu_full_ha_stem_tasks +task: global_mmlu_full_ha_electrical_engineering diff --git a/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_elementary_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_elementary_mathematics.yaml new file mode 100644 index 00000000..e04fb1ff --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_elementary_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ha_template_yaml +process_docs: !function utils.process_elementary_mathematics +tag: global_mmlu_full_ha_stem_tasks +task: global_mmlu_full_ha_elementary_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_formal_logic.yaml b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_formal_logic.yaml new file mode 100644 index 00000000..03c9cbac --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_formal_logic.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ha_template_yaml +process_docs: !function utils.process_formal_logic +tag: global_mmlu_full_ha_humanities_tasks +task: global_mmlu_full_ha_formal_logic diff --git a/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_global_facts.yaml b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_global_facts.yaml new file mode 100644 index 00000000..db104be5 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_global_facts.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ha_template_yaml +process_docs: !function utils.process_global_facts +tag: global_mmlu_full_ha_other_tasks +task: global_mmlu_full_ha_global_facts diff --git a/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_high_school_biology.yaml b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_high_school_biology.yaml new file mode 100644 index 00000000..729fed2b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_high_school_biology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ha_template_yaml +process_docs: !function utils.process_high_school_biology +tag: global_mmlu_full_ha_stem_tasks +task: global_mmlu_full_ha_high_school_biology diff --git a/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_high_school_chemistry.yaml b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_high_school_chemistry.yaml new file mode 100644 index 00000000..13f5621b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_high_school_chemistry.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ha_template_yaml +process_docs: !function utils.process_high_school_chemistry +tag: global_mmlu_full_ha_stem_tasks +task: global_mmlu_full_ha_high_school_chemistry diff --git a/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_high_school_computer_science.yaml b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_high_school_computer_science.yaml new file mode 100644 index 00000000..1914e1fb --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_high_school_computer_science.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ha_template_yaml +process_docs: !function utils.process_high_school_computer_science +tag: global_mmlu_full_ha_stem_tasks +task: global_mmlu_full_ha_high_school_computer_science diff --git a/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_high_school_european_history.yaml b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_high_school_european_history.yaml new file mode 100644 index 00000000..fa878b03 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_high_school_european_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ha_template_yaml +process_docs: !function utils.process_high_school_european_history +tag: global_mmlu_full_ha_humanities_tasks +task: global_mmlu_full_ha_high_school_european_history diff --git a/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_high_school_geography.yaml b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_high_school_geography.yaml new file mode 100644 index 00000000..10a13674 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_high_school_geography.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ha_template_yaml +process_docs: !function utils.process_high_school_geography +tag: global_mmlu_full_ha_social_sciences_tasks +task: global_mmlu_full_ha_high_school_geography diff --git a/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_high_school_government_and_politics.yaml b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_high_school_government_and_politics.yaml new file mode 100644 index 00000000..eebac409 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_high_school_government_and_politics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ha_template_yaml +process_docs: !function utils.process_high_school_government_and_politics +tag: global_mmlu_full_ha_social_sciences_tasks +task: global_mmlu_full_ha_high_school_government_and_politics diff --git a/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_high_school_macroeconomics.yaml b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_high_school_macroeconomics.yaml new file mode 100644 index 00000000..0a22ab84 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_high_school_macroeconomics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ha_template_yaml +process_docs: !function utils.process_high_school_macroeconomics +tag: global_mmlu_full_ha_social_sciences_tasks +task: global_mmlu_full_ha_high_school_macroeconomics diff --git a/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_high_school_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_high_school_mathematics.yaml new file mode 100644 index 00000000..fc681f90 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_high_school_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ha_template_yaml +process_docs: !function utils.process_high_school_mathematics +tag: global_mmlu_full_ha_stem_tasks +task: global_mmlu_full_ha_high_school_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_high_school_microeconomics.yaml b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_high_school_microeconomics.yaml new file mode 100644 index 00000000..81bb343c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_high_school_microeconomics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ha_template_yaml +process_docs: !function utils.process_high_school_microeconomics +tag: global_mmlu_full_ha_social_sciences_tasks +task: global_mmlu_full_ha_high_school_microeconomics diff --git a/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_high_school_physics.yaml b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_high_school_physics.yaml new file mode 100644 index 00000000..2bc4cc4d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_high_school_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ha_template_yaml +process_docs: !function utils.process_high_school_physics +tag: global_mmlu_full_ha_stem_tasks +task: global_mmlu_full_ha_high_school_physics diff --git a/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_high_school_psychology.yaml b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_high_school_psychology.yaml new file mode 100644 index 00000000..c5d46e5e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_high_school_psychology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ha_template_yaml +process_docs: !function utils.process_high_school_psychology +tag: global_mmlu_full_ha_social_sciences_tasks +task: global_mmlu_full_ha_high_school_psychology diff --git a/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_high_school_statistics.yaml b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_high_school_statistics.yaml new file mode 100644 index 00000000..4848cc31 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_high_school_statistics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ha_template_yaml +process_docs: !function utils.process_high_school_statistics +tag: global_mmlu_full_ha_stem_tasks +task: global_mmlu_full_ha_high_school_statistics diff --git a/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_high_school_us_history.yaml b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_high_school_us_history.yaml new file mode 100644 index 00000000..7a22c79a --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_high_school_us_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ha_template_yaml +process_docs: !function utils.process_high_school_us_history +tag: global_mmlu_full_ha_humanities_tasks +task: global_mmlu_full_ha_high_school_us_history diff --git a/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_high_school_world_history.yaml b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_high_school_world_history.yaml new file mode 100644 index 00000000..13882279 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_high_school_world_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ha_template_yaml +process_docs: !function utils.process_high_school_world_history +tag: global_mmlu_full_ha_humanities_tasks +task: global_mmlu_full_ha_high_school_world_history diff --git a/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_human_aging.yaml b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_human_aging.yaml new file mode 100644 index 00000000..51ff436b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_human_aging.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ha_template_yaml +process_docs: !function utils.process_human_aging +tag: global_mmlu_full_ha_other_tasks +task: global_mmlu_full_ha_human_aging diff --git a/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_human_sexuality.yaml b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_human_sexuality.yaml new file mode 100644 index 00000000..1a36fb86 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_human_sexuality.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ha_template_yaml +process_docs: !function utils.process_human_sexuality +tag: global_mmlu_full_ha_social_sciences_tasks +task: global_mmlu_full_ha_human_sexuality diff --git a/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_international_law.yaml b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_international_law.yaml new file mode 100644 index 00000000..f1c9cc1c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_international_law.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ha_template_yaml +process_docs: !function utils.process_international_law +tag: global_mmlu_full_ha_humanities_tasks +task: global_mmlu_full_ha_international_law diff --git a/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_jurisprudence.yaml b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_jurisprudence.yaml new file mode 100644 index 00000000..4bc1314b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_jurisprudence.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ha_template_yaml +process_docs: !function utils.process_jurisprudence +tag: global_mmlu_full_ha_humanities_tasks +task: global_mmlu_full_ha_jurisprudence diff --git a/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_logical_fallacies.yaml b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_logical_fallacies.yaml new file mode 100644 index 00000000..259534b9 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_logical_fallacies.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ha_template_yaml +process_docs: !function utils.process_logical_fallacies +tag: global_mmlu_full_ha_humanities_tasks +task: global_mmlu_full_ha_logical_fallacies diff --git a/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_machine_learning.yaml b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_machine_learning.yaml new file mode 100644 index 00000000..c94a073b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_machine_learning.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ha_template_yaml +process_docs: !function utils.process_machine_learning +tag: global_mmlu_full_ha_stem_tasks +task: global_mmlu_full_ha_machine_learning diff --git a/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_management.yaml b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_management.yaml new file mode 100644 index 00000000..666d4720 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_management.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ha_template_yaml +process_docs: !function utils.process_management +tag: global_mmlu_full_ha_other_tasks +task: global_mmlu_full_ha_management diff --git a/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_marketing.yaml b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_marketing.yaml new file mode 100644 index 00000000..9528a1f3 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_marketing.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ha_template_yaml +process_docs: !function utils.process_marketing +tag: global_mmlu_full_ha_other_tasks +task: global_mmlu_full_ha_marketing diff --git a/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_medical_genetics.yaml b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_medical_genetics.yaml new file mode 100644 index 00000000..92f0a408 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_medical_genetics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ha_template_yaml +process_docs: !function utils.process_medical_genetics +tag: global_mmlu_full_ha_other_tasks +task: global_mmlu_full_ha_medical_genetics diff --git a/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_miscellaneous.yaml b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_miscellaneous.yaml new file mode 100644 index 00000000..fc97a8dc --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_miscellaneous.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ha_template_yaml +process_docs: !function utils.process_miscellaneous +tag: global_mmlu_full_ha_other_tasks +task: global_mmlu_full_ha_miscellaneous diff --git a/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_moral_disputes.yaml b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_moral_disputes.yaml new file mode 100644 index 00000000..dbcf96c2 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_moral_disputes.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ha_template_yaml +process_docs: !function utils.process_moral_disputes +tag: global_mmlu_full_ha_humanities_tasks +task: global_mmlu_full_ha_moral_disputes diff --git a/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_moral_scenarios.yaml b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_moral_scenarios.yaml new file mode 100644 index 00000000..aa7b4266 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_moral_scenarios.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ha_template_yaml +process_docs: !function utils.process_moral_scenarios +tag: global_mmlu_full_ha_humanities_tasks +task: global_mmlu_full_ha_moral_scenarios diff --git a/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_nutrition.yaml b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_nutrition.yaml new file mode 100644 index 00000000..b413e4be --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_nutrition.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ha_template_yaml +process_docs: !function utils.process_nutrition +tag: global_mmlu_full_ha_other_tasks +task: global_mmlu_full_ha_nutrition diff --git a/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_philosophy.yaml b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_philosophy.yaml new file mode 100644 index 00000000..118e4801 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_philosophy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ha_template_yaml +process_docs: !function utils.process_philosophy +tag: global_mmlu_full_ha_humanities_tasks +task: global_mmlu_full_ha_philosophy diff --git a/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_prehistory.yaml b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_prehistory.yaml new file mode 100644 index 00000000..a310d023 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_prehistory.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ha_template_yaml +process_docs: !function utils.process_prehistory +tag: global_mmlu_full_ha_humanities_tasks +task: global_mmlu_full_ha_prehistory diff --git a/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_professional_accounting.yaml b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_professional_accounting.yaml new file mode 100644 index 00000000..79536ddc --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_professional_accounting.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ha_template_yaml +process_docs: !function utils.process_professional_accounting +tag: global_mmlu_full_ha_other_tasks +task: global_mmlu_full_ha_professional_accounting diff --git a/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_professional_law.yaml b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_professional_law.yaml new file mode 100644 index 00000000..613170da --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_professional_law.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ha_template_yaml +process_docs: !function utils.process_professional_law +tag: global_mmlu_full_ha_humanities_tasks +task: global_mmlu_full_ha_professional_law diff --git a/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_professional_medicine.yaml b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_professional_medicine.yaml new file mode 100644 index 00000000..bd65c233 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_professional_medicine.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ha_template_yaml +process_docs: !function utils.process_professional_medicine +tag: global_mmlu_full_ha_other_tasks +task: global_mmlu_full_ha_professional_medicine diff --git a/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_professional_psychology.yaml b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_professional_psychology.yaml new file mode 100644 index 00000000..cf7ecb1f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_professional_psychology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ha_template_yaml +process_docs: !function utils.process_professional_psychology +tag: global_mmlu_full_ha_social_sciences_tasks +task: global_mmlu_full_ha_professional_psychology diff --git a/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_public_relations.yaml b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_public_relations.yaml new file mode 100644 index 00000000..c9cba53f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_public_relations.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ha_template_yaml +process_docs: !function utils.process_public_relations +tag: global_mmlu_full_ha_social_sciences_tasks +task: global_mmlu_full_ha_public_relations diff --git a/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_security_studies.yaml b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_security_studies.yaml new file mode 100644 index 00000000..fe767686 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_security_studies.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ha_template_yaml +process_docs: !function utils.process_security_studies +tag: global_mmlu_full_ha_social_sciences_tasks +task: global_mmlu_full_ha_security_studies diff --git a/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_sociology.yaml b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_sociology.yaml new file mode 100644 index 00000000..94f8e311 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_sociology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ha_template_yaml +process_docs: !function utils.process_sociology +tag: global_mmlu_full_ha_social_sciences_tasks +task: global_mmlu_full_ha_sociology diff --git a/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_us_foreign_policy.yaml b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_us_foreign_policy.yaml new file mode 100644 index 00000000..54f82b3f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_us_foreign_policy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ha_template_yaml +process_docs: !function utils.process_us_foreign_policy +tag: global_mmlu_full_ha_social_sciences_tasks +task: global_mmlu_full_ha_us_foreign_policy diff --git a/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_virology.yaml b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_virology.yaml new file mode 100644 index 00000000..ce7d224d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_virology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ha_template_yaml +process_docs: !function utils.process_virology +tag: global_mmlu_full_ha_other_tasks +task: global_mmlu_full_ha_virology diff --git a/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_world_religions.yaml b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_world_religions.yaml new file mode 100644 index 00000000..67a6d33d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ha/global_mmlu_full_ha_world_religions.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ha_template_yaml +process_docs: !function utils.process_world_religions +tag: global_mmlu_full_ha_humanities_tasks +task: global_mmlu_full_ha_world_religions diff --git a/lm_eval/tasks/global_mmlu/full/ha/utils.py b/lm_eval/tasks/global_mmlu/full/ha/utils.py new file mode 100644 index 00000000..7df72cb0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ha/utils.py @@ -0,0 +1,73 @@ +from functools import partial + + +SUBJECTS = [ + "abstract_algebra", + "anatomy", + "astronomy", + "business_ethics", + "clinical_knowledge", + "college_biology", + "college_chemistry", + "college_computer_science", + "college_mathematics", + "college_medicine", + "college_physics", + "computer_security", + "conceptual_physics", + "econometrics", + "electrical_engineering", + "elementary_mathematics", + "formal_logic", + "global_facts", + "high_school_biology", + "high_school_chemistry", + "high_school_computer_science", + "high_school_european_history", + "high_school_geography", + "high_school_government_and_politics", + "high_school_macroeconomics", + "high_school_mathematics", + "high_school_microeconomics", + "high_school_physics", + "high_school_psychology", + "high_school_statistics", + "high_school_us_history", + "high_school_world_history", + "human_aging", + "human_sexuality", + "international_law", + "jurisprudence", + "logical_fallacies", + "machine_learning", + "management", + "marketing", + "medical_genetics", + "miscellaneous", + "moral_disputes", + "moral_scenarios", + "nutrition", + "philosophy", + "prehistory", + "professional_accounting", + "professional_law", + "professional_medicine", + "professional_psychology", + "public_relations", + "security_studies", + "sociology", + "us_foreign_policy", + "virology", + "world_religions", +] + + +def process_docs(dataset, subject): + return dataset.filter(lambda x: x["subject"] == subject) + + +process_functions = { + f"process_{subject}": partial(process_docs, subject=subject) for subject in SUBJECTS +} + +globals().update(process_functions) diff --git a/lm_eval/tasks/global_mmlu/full/he/_global_mmlu_full_he.yaml b/lm_eval/tasks/global_mmlu/full/he/_global_mmlu_full_he.yaml new file mode 100644 index 00000000..ff0a5e8f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/he/_global_mmlu_full_he.yaml @@ -0,0 +1,11 @@ +group: global_mmlu_full_he +task: + - global_mmlu_full_he_stem + - global_mmlu_full_he_other + - global_mmlu_full_he_social_sciences + - global_mmlu_full_he_humanities +aggregate_metric_list: + - metric: acc + weight_by_size: True +metadata: + version: 1.0 diff --git a/lm_eval/tasks/global_mmlu/full/he/_global_mmlu_full_he_humanities.yaml b/lm_eval/tasks/global_mmlu/full/he/_global_mmlu_full_he_humanities.yaml new file mode 100644 index 00000000..678ee0d4 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/he/_global_mmlu_full_he_humanities.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_he_humanities +task: + - global_mmlu_full_he_humanities_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/he/_global_mmlu_full_he_other.yaml b/lm_eval/tasks/global_mmlu/full/he/_global_mmlu_full_he_other.yaml new file mode 100644 index 00000000..c99b4806 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/he/_global_mmlu_full_he_other.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_he_other +task: + - global_mmlu_full_he_other_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/he/_global_mmlu_full_he_social_sciences.yaml b/lm_eval/tasks/global_mmlu/full/he/_global_mmlu_full_he_social_sciences.yaml new file mode 100644 index 00000000..12906895 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/he/_global_mmlu_full_he_social_sciences.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_he_social_sciences +task: + - global_mmlu_full_he_social_sciences_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/he/_global_mmlu_full_he_stem.yaml b/lm_eval/tasks/global_mmlu/full/he/_global_mmlu_full_he_stem.yaml new file mode 100644 index 00000000..f6e76e7a --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/he/_global_mmlu_full_he_stem.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_he_stem +task: + - global_mmlu_full_he_stem_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/he/_he_template_yaml b/lm_eval/tasks/global_mmlu/full/he/_he_template_yaml new file mode 100644 index 00000000..b6ec9fc8 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/he/_he_template_yaml @@ -0,0 +1,16 @@ +dataset_path: CohereForAI/Global-MMLU +dataset_name: he +test_split: test +fewshot_split: dev +fewshot_config: + sampler: first_n +output_type: multiple_choice +doc_to_text: "{{question.strip()}}\nA. {{option_a}}\nB. {{option_b}}\nC. {{option_c}}\nD. {{option_d}}\nAnswer:" +doc_to_choice: ["A", "B", "C", "D"] +doc_to_target: answer +metric_list: + - metric: acc + aggregation: mean + higher_is_better: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_abstract_algebra.yaml b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_abstract_algebra.yaml new file mode 100644 index 00000000..fb197c3d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_abstract_algebra.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _he_template_yaml +process_docs: !function utils.process_abstract_algebra +tag: global_mmlu_full_he_stem_tasks +task: global_mmlu_full_he_abstract_algebra diff --git a/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_anatomy.yaml b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_anatomy.yaml new file mode 100644 index 00000000..3ab9ee20 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_anatomy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _he_template_yaml +process_docs: !function utils.process_anatomy +tag: global_mmlu_full_he_stem_tasks +task: global_mmlu_full_he_anatomy diff --git a/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_astronomy.yaml b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_astronomy.yaml new file mode 100644 index 00000000..8950b1e0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_astronomy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _he_template_yaml +process_docs: !function utils.process_astronomy +tag: global_mmlu_full_he_stem_tasks +task: global_mmlu_full_he_astronomy diff --git a/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_business_ethics.yaml b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_business_ethics.yaml new file mode 100644 index 00000000..8c114348 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_business_ethics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _he_template_yaml +process_docs: !function utils.process_business_ethics +tag: global_mmlu_full_he_other_tasks +task: global_mmlu_full_he_business_ethics diff --git a/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_clinical_knowledge.yaml b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_clinical_knowledge.yaml new file mode 100644 index 00000000..1324a04d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_clinical_knowledge.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _he_template_yaml +process_docs: !function utils.process_clinical_knowledge +tag: global_mmlu_full_he_other_tasks +task: global_mmlu_full_he_clinical_knowledge diff --git a/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_college_biology.yaml b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_college_biology.yaml new file mode 100644 index 00000000..cecddc60 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_college_biology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _he_template_yaml +process_docs: !function utils.process_college_biology +tag: global_mmlu_full_he_stem_tasks +task: global_mmlu_full_he_college_biology diff --git a/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_college_chemistry.yaml b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_college_chemistry.yaml new file mode 100644 index 00000000..2c0f8b5d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_college_chemistry.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _he_template_yaml +process_docs: !function utils.process_college_chemistry +tag: global_mmlu_full_he_stem_tasks +task: global_mmlu_full_he_college_chemistry diff --git a/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_college_computer_science.yaml b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_college_computer_science.yaml new file mode 100644 index 00000000..b4c36a41 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_college_computer_science.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _he_template_yaml +process_docs: !function utils.process_college_computer_science +tag: global_mmlu_full_he_stem_tasks +task: global_mmlu_full_he_college_computer_science diff --git a/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_college_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_college_mathematics.yaml new file mode 100644 index 00000000..3633d537 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_college_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _he_template_yaml +process_docs: !function utils.process_college_mathematics +tag: global_mmlu_full_he_stem_tasks +task: global_mmlu_full_he_college_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_college_medicine.yaml b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_college_medicine.yaml new file mode 100644 index 00000000..a28c592e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_college_medicine.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _he_template_yaml +process_docs: !function utils.process_college_medicine +tag: global_mmlu_full_he_other_tasks +task: global_mmlu_full_he_college_medicine diff --git a/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_college_physics.yaml b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_college_physics.yaml new file mode 100644 index 00000000..3893b9aa --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_college_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _he_template_yaml +process_docs: !function utils.process_college_physics +tag: global_mmlu_full_he_stem_tasks +task: global_mmlu_full_he_college_physics diff --git a/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_computer_security.yaml b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_computer_security.yaml new file mode 100644 index 00000000..4167874e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_computer_security.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _he_template_yaml +process_docs: !function utils.process_computer_security +tag: global_mmlu_full_he_stem_tasks +task: global_mmlu_full_he_computer_security diff --git a/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_conceptual_physics.yaml b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_conceptual_physics.yaml new file mode 100644 index 00000000..2ee92851 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_conceptual_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _he_template_yaml +process_docs: !function utils.process_conceptual_physics +tag: global_mmlu_full_he_stem_tasks +task: global_mmlu_full_he_conceptual_physics diff --git a/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_econometrics.yaml b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_econometrics.yaml new file mode 100644 index 00000000..9ceb3277 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_econometrics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _he_template_yaml +process_docs: !function utils.process_econometrics +tag: global_mmlu_full_he_social_sciences_tasks +task: global_mmlu_full_he_econometrics diff --git a/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_electrical_engineering.yaml b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_electrical_engineering.yaml new file mode 100644 index 00000000..00658e28 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_electrical_engineering.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _he_template_yaml +process_docs: !function utils.process_electrical_engineering +tag: global_mmlu_full_he_stem_tasks +task: global_mmlu_full_he_electrical_engineering diff --git a/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_elementary_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_elementary_mathematics.yaml new file mode 100644 index 00000000..10f2ac18 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_elementary_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _he_template_yaml +process_docs: !function utils.process_elementary_mathematics +tag: global_mmlu_full_he_stem_tasks +task: global_mmlu_full_he_elementary_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_formal_logic.yaml b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_formal_logic.yaml new file mode 100644 index 00000000..aac3f8da --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_formal_logic.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _he_template_yaml +process_docs: !function utils.process_formal_logic +tag: global_mmlu_full_he_humanities_tasks +task: global_mmlu_full_he_formal_logic diff --git a/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_global_facts.yaml b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_global_facts.yaml new file mode 100644 index 00000000..299a73ef --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_global_facts.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _he_template_yaml +process_docs: !function utils.process_global_facts +tag: global_mmlu_full_he_other_tasks +task: global_mmlu_full_he_global_facts diff --git a/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_high_school_biology.yaml b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_high_school_biology.yaml new file mode 100644 index 00000000..9d3ba893 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_high_school_biology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _he_template_yaml +process_docs: !function utils.process_high_school_biology +tag: global_mmlu_full_he_stem_tasks +task: global_mmlu_full_he_high_school_biology diff --git a/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_high_school_chemistry.yaml b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_high_school_chemistry.yaml new file mode 100644 index 00000000..f67f8ef3 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_high_school_chemistry.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _he_template_yaml +process_docs: !function utils.process_high_school_chemistry +tag: global_mmlu_full_he_stem_tasks +task: global_mmlu_full_he_high_school_chemistry diff --git a/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_high_school_computer_science.yaml b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_high_school_computer_science.yaml new file mode 100644 index 00000000..7ca8b6f8 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_high_school_computer_science.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _he_template_yaml +process_docs: !function utils.process_high_school_computer_science +tag: global_mmlu_full_he_stem_tasks +task: global_mmlu_full_he_high_school_computer_science diff --git a/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_high_school_european_history.yaml b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_high_school_european_history.yaml new file mode 100644 index 00000000..58e4081a --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_high_school_european_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _he_template_yaml +process_docs: !function utils.process_high_school_european_history +tag: global_mmlu_full_he_humanities_tasks +task: global_mmlu_full_he_high_school_european_history diff --git a/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_high_school_geography.yaml b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_high_school_geography.yaml new file mode 100644 index 00000000..2d76e387 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_high_school_geography.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _he_template_yaml +process_docs: !function utils.process_high_school_geography +tag: global_mmlu_full_he_social_sciences_tasks +task: global_mmlu_full_he_high_school_geography diff --git a/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_high_school_government_and_politics.yaml b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_high_school_government_and_politics.yaml new file mode 100644 index 00000000..e3745110 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_high_school_government_and_politics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _he_template_yaml +process_docs: !function utils.process_high_school_government_and_politics +tag: global_mmlu_full_he_social_sciences_tasks +task: global_mmlu_full_he_high_school_government_and_politics diff --git a/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_high_school_macroeconomics.yaml b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_high_school_macroeconomics.yaml new file mode 100644 index 00000000..fa0b7c71 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_high_school_macroeconomics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _he_template_yaml +process_docs: !function utils.process_high_school_macroeconomics +tag: global_mmlu_full_he_social_sciences_tasks +task: global_mmlu_full_he_high_school_macroeconomics diff --git a/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_high_school_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_high_school_mathematics.yaml new file mode 100644 index 00000000..7f78a5c5 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_high_school_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _he_template_yaml +process_docs: !function utils.process_high_school_mathematics +tag: global_mmlu_full_he_stem_tasks +task: global_mmlu_full_he_high_school_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_high_school_microeconomics.yaml b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_high_school_microeconomics.yaml new file mode 100644 index 00000000..15be9243 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_high_school_microeconomics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _he_template_yaml +process_docs: !function utils.process_high_school_microeconomics +tag: global_mmlu_full_he_social_sciences_tasks +task: global_mmlu_full_he_high_school_microeconomics diff --git a/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_high_school_physics.yaml b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_high_school_physics.yaml new file mode 100644 index 00000000..6f309c0b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_high_school_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _he_template_yaml +process_docs: !function utils.process_high_school_physics +tag: global_mmlu_full_he_stem_tasks +task: global_mmlu_full_he_high_school_physics diff --git a/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_high_school_psychology.yaml b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_high_school_psychology.yaml new file mode 100644 index 00000000..1ae831c6 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_high_school_psychology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _he_template_yaml +process_docs: !function utils.process_high_school_psychology +tag: global_mmlu_full_he_social_sciences_tasks +task: global_mmlu_full_he_high_school_psychology diff --git a/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_high_school_statistics.yaml b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_high_school_statistics.yaml new file mode 100644 index 00000000..3a2e8170 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_high_school_statistics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _he_template_yaml +process_docs: !function utils.process_high_school_statistics +tag: global_mmlu_full_he_stem_tasks +task: global_mmlu_full_he_high_school_statistics diff --git a/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_high_school_us_history.yaml b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_high_school_us_history.yaml new file mode 100644 index 00000000..c05da45a --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_high_school_us_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _he_template_yaml +process_docs: !function utils.process_high_school_us_history +tag: global_mmlu_full_he_humanities_tasks +task: global_mmlu_full_he_high_school_us_history diff --git a/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_high_school_world_history.yaml b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_high_school_world_history.yaml new file mode 100644 index 00000000..b818e4fe --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_high_school_world_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _he_template_yaml +process_docs: !function utils.process_high_school_world_history +tag: global_mmlu_full_he_humanities_tasks +task: global_mmlu_full_he_high_school_world_history diff --git a/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_human_aging.yaml b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_human_aging.yaml new file mode 100644 index 00000000..49f7ce5d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_human_aging.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _he_template_yaml +process_docs: !function utils.process_human_aging +tag: global_mmlu_full_he_other_tasks +task: global_mmlu_full_he_human_aging diff --git a/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_human_sexuality.yaml b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_human_sexuality.yaml new file mode 100644 index 00000000..91d08567 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_human_sexuality.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _he_template_yaml +process_docs: !function utils.process_human_sexuality +tag: global_mmlu_full_he_social_sciences_tasks +task: global_mmlu_full_he_human_sexuality diff --git a/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_international_law.yaml b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_international_law.yaml new file mode 100644 index 00000000..1bedb4f4 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_international_law.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _he_template_yaml +process_docs: !function utils.process_international_law +tag: global_mmlu_full_he_humanities_tasks +task: global_mmlu_full_he_international_law diff --git a/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_jurisprudence.yaml b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_jurisprudence.yaml new file mode 100644 index 00000000..39fe15a2 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_jurisprudence.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _he_template_yaml +process_docs: !function utils.process_jurisprudence +tag: global_mmlu_full_he_humanities_tasks +task: global_mmlu_full_he_jurisprudence diff --git a/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_logical_fallacies.yaml b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_logical_fallacies.yaml new file mode 100644 index 00000000..e54b58b3 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_logical_fallacies.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _he_template_yaml +process_docs: !function utils.process_logical_fallacies +tag: global_mmlu_full_he_humanities_tasks +task: global_mmlu_full_he_logical_fallacies diff --git a/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_machine_learning.yaml b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_machine_learning.yaml new file mode 100644 index 00000000..8190e96a --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_machine_learning.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _he_template_yaml +process_docs: !function utils.process_machine_learning +tag: global_mmlu_full_he_stem_tasks +task: global_mmlu_full_he_machine_learning diff --git a/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_management.yaml b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_management.yaml new file mode 100644 index 00000000..d5811f80 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_management.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _he_template_yaml +process_docs: !function utils.process_management +tag: global_mmlu_full_he_other_tasks +task: global_mmlu_full_he_management diff --git a/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_marketing.yaml b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_marketing.yaml new file mode 100644 index 00000000..7fe44232 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_marketing.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _he_template_yaml +process_docs: !function utils.process_marketing +tag: global_mmlu_full_he_other_tasks +task: global_mmlu_full_he_marketing diff --git a/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_medical_genetics.yaml b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_medical_genetics.yaml new file mode 100644 index 00000000..8c9082c5 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_medical_genetics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _he_template_yaml +process_docs: !function utils.process_medical_genetics +tag: global_mmlu_full_he_other_tasks +task: global_mmlu_full_he_medical_genetics diff --git a/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_miscellaneous.yaml b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_miscellaneous.yaml new file mode 100644 index 00000000..bc419dee --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_miscellaneous.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _he_template_yaml +process_docs: !function utils.process_miscellaneous +tag: global_mmlu_full_he_other_tasks +task: global_mmlu_full_he_miscellaneous diff --git a/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_moral_disputes.yaml b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_moral_disputes.yaml new file mode 100644 index 00000000..d889642b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_moral_disputes.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _he_template_yaml +process_docs: !function utils.process_moral_disputes +tag: global_mmlu_full_he_humanities_tasks +task: global_mmlu_full_he_moral_disputes diff --git a/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_moral_scenarios.yaml b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_moral_scenarios.yaml new file mode 100644 index 00000000..11554823 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_moral_scenarios.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _he_template_yaml +process_docs: !function utils.process_moral_scenarios +tag: global_mmlu_full_he_humanities_tasks +task: global_mmlu_full_he_moral_scenarios diff --git a/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_nutrition.yaml b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_nutrition.yaml new file mode 100644 index 00000000..30d49701 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_nutrition.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _he_template_yaml +process_docs: !function utils.process_nutrition +tag: global_mmlu_full_he_other_tasks +task: global_mmlu_full_he_nutrition diff --git a/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_philosophy.yaml b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_philosophy.yaml new file mode 100644 index 00000000..458632de --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_philosophy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _he_template_yaml +process_docs: !function utils.process_philosophy +tag: global_mmlu_full_he_humanities_tasks +task: global_mmlu_full_he_philosophy diff --git a/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_prehistory.yaml b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_prehistory.yaml new file mode 100644 index 00000000..93835673 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_prehistory.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _he_template_yaml +process_docs: !function utils.process_prehistory +tag: global_mmlu_full_he_humanities_tasks +task: global_mmlu_full_he_prehistory diff --git a/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_professional_accounting.yaml b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_professional_accounting.yaml new file mode 100644 index 00000000..aed28636 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_professional_accounting.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _he_template_yaml +process_docs: !function utils.process_professional_accounting +tag: global_mmlu_full_he_other_tasks +task: global_mmlu_full_he_professional_accounting diff --git a/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_professional_law.yaml b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_professional_law.yaml new file mode 100644 index 00000000..38a9e3cc --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_professional_law.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _he_template_yaml +process_docs: !function utils.process_professional_law +tag: global_mmlu_full_he_humanities_tasks +task: global_mmlu_full_he_professional_law diff --git a/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_professional_medicine.yaml b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_professional_medicine.yaml new file mode 100644 index 00000000..e8ca950c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_professional_medicine.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _he_template_yaml +process_docs: !function utils.process_professional_medicine +tag: global_mmlu_full_he_other_tasks +task: global_mmlu_full_he_professional_medicine diff --git a/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_professional_psychology.yaml b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_professional_psychology.yaml new file mode 100644 index 00000000..f82c2892 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_professional_psychology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _he_template_yaml +process_docs: !function utils.process_professional_psychology +tag: global_mmlu_full_he_social_sciences_tasks +task: global_mmlu_full_he_professional_psychology diff --git a/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_public_relations.yaml b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_public_relations.yaml new file mode 100644 index 00000000..e3aff661 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_public_relations.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _he_template_yaml +process_docs: !function utils.process_public_relations +tag: global_mmlu_full_he_social_sciences_tasks +task: global_mmlu_full_he_public_relations diff --git a/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_security_studies.yaml b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_security_studies.yaml new file mode 100644 index 00000000..e99aa015 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_security_studies.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _he_template_yaml +process_docs: !function utils.process_security_studies +tag: global_mmlu_full_he_social_sciences_tasks +task: global_mmlu_full_he_security_studies diff --git a/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_sociology.yaml b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_sociology.yaml new file mode 100644 index 00000000..de81b92c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_sociology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _he_template_yaml +process_docs: !function utils.process_sociology +tag: global_mmlu_full_he_social_sciences_tasks +task: global_mmlu_full_he_sociology diff --git a/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_us_foreign_policy.yaml b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_us_foreign_policy.yaml new file mode 100644 index 00000000..7be65044 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_us_foreign_policy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _he_template_yaml +process_docs: !function utils.process_us_foreign_policy +tag: global_mmlu_full_he_social_sciences_tasks +task: global_mmlu_full_he_us_foreign_policy diff --git a/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_virology.yaml b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_virology.yaml new file mode 100644 index 00000000..b6f51e1b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_virology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _he_template_yaml +process_docs: !function utils.process_virology +tag: global_mmlu_full_he_other_tasks +task: global_mmlu_full_he_virology diff --git a/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_world_religions.yaml b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_world_religions.yaml new file mode 100644 index 00000000..e3d10a0d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/he/global_mmlu_full_he_world_religions.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _he_template_yaml +process_docs: !function utils.process_world_religions +tag: global_mmlu_full_he_humanities_tasks +task: global_mmlu_full_he_world_religions diff --git a/lm_eval/tasks/global_mmlu/full/he/utils.py b/lm_eval/tasks/global_mmlu/full/he/utils.py new file mode 100644 index 00000000..7df72cb0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/he/utils.py @@ -0,0 +1,73 @@ +from functools import partial + + +SUBJECTS = [ + "abstract_algebra", + "anatomy", + "astronomy", + "business_ethics", + "clinical_knowledge", + "college_biology", + "college_chemistry", + "college_computer_science", + "college_mathematics", + "college_medicine", + "college_physics", + "computer_security", + "conceptual_physics", + "econometrics", + "electrical_engineering", + "elementary_mathematics", + "formal_logic", + "global_facts", + "high_school_biology", + "high_school_chemistry", + "high_school_computer_science", + "high_school_european_history", + "high_school_geography", + "high_school_government_and_politics", + "high_school_macroeconomics", + "high_school_mathematics", + "high_school_microeconomics", + "high_school_physics", + "high_school_psychology", + "high_school_statistics", + "high_school_us_history", + "high_school_world_history", + "human_aging", + "human_sexuality", + "international_law", + "jurisprudence", + "logical_fallacies", + "machine_learning", + "management", + "marketing", + "medical_genetics", + "miscellaneous", + "moral_disputes", + "moral_scenarios", + "nutrition", + "philosophy", + "prehistory", + "professional_accounting", + "professional_law", + "professional_medicine", + "professional_psychology", + "public_relations", + "security_studies", + "sociology", + "us_foreign_policy", + "virology", + "world_religions", +] + + +def process_docs(dataset, subject): + return dataset.filter(lambda x: x["subject"] == subject) + + +process_functions = { + f"process_{subject}": partial(process_docs, subject=subject) for subject in SUBJECTS +} + +globals().update(process_functions) diff --git a/lm_eval/tasks/global_mmlu/full/hi/_global_mmlu_full_hi.yaml b/lm_eval/tasks/global_mmlu/full/hi/_global_mmlu_full_hi.yaml new file mode 100644 index 00000000..ed54a6ad --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/hi/_global_mmlu_full_hi.yaml @@ -0,0 +1,11 @@ +group: global_mmlu_full_hi +task: + - global_mmlu_full_hi_stem + - global_mmlu_full_hi_other + - global_mmlu_full_hi_social_sciences + - global_mmlu_full_hi_humanities +aggregate_metric_list: + - metric: acc + weight_by_size: True +metadata: + version: 1.0 diff --git a/lm_eval/tasks/global_mmlu/full/hi/_global_mmlu_full_hi_humanities.yaml b/lm_eval/tasks/global_mmlu/full/hi/_global_mmlu_full_hi_humanities.yaml new file mode 100644 index 00000000..36492fa3 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/hi/_global_mmlu_full_hi_humanities.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_hi_humanities +task: + - global_mmlu_full_hi_humanities_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/hi/_global_mmlu_full_hi_other.yaml b/lm_eval/tasks/global_mmlu/full/hi/_global_mmlu_full_hi_other.yaml new file mode 100644 index 00000000..08dc16b0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/hi/_global_mmlu_full_hi_other.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_hi_other +task: + - global_mmlu_full_hi_other_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/hi/_global_mmlu_full_hi_social_sciences.yaml b/lm_eval/tasks/global_mmlu/full/hi/_global_mmlu_full_hi_social_sciences.yaml new file mode 100644 index 00000000..0a4dfdd7 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/hi/_global_mmlu_full_hi_social_sciences.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_hi_social_sciences +task: + - global_mmlu_full_hi_social_sciences_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/hi/_global_mmlu_full_hi_stem.yaml b/lm_eval/tasks/global_mmlu/full/hi/_global_mmlu_full_hi_stem.yaml new file mode 100644 index 00000000..7a0123ae --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/hi/_global_mmlu_full_hi_stem.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_hi_stem +task: + - global_mmlu_full_hi_stem_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/hi/_hi_template_yaml b/lm_eval/tasks/global_mmlu/full/hi/_hi_template_yaml new file mode 100644 index 00000000..18c6286e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/hi/_hi_template_yaml @@ -0,0 +1,16 @@ +dataset_path: CohereForAI/Global-MMLU +dataset_name: hi +test_split: test +fewshot_split: dev +fewshot_config: + sampler: first_n +output_type: multiple_choice +doc_to_text: "{{question.strip()}}\nA. {{option_a}}\nB. {{option_b}}\nC. {{option_c}}\nD. {{option_d}}\nAnswer:" +doc_to_choice: ["A", "B", "C", "D"] +doc_to_target: answer +metric_list: + - metric: acc + aggregation: mean + higher_is_better: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_abstract_algebra.yaml b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_abstract_algebra.yaml new file mode 100644 index 00000000..f239f067 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_abstract_algebra.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _hi_template_yaml +process_docs: !function utils.process_abstract_algebra +tag: global_mmlu_full_hi_stem_tasks +task: global_mmlu_full_hi_abstract_algebra diff --git a/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_anatomy.yaml b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_anatomy.yaml new file mode 100644 index 00000000..dfcd776e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_anatomy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _hi_template_yaml +process_docs: !function utils.process_anatomy +tag: global_mmlu_full_hi_stem_tasks +task: global_mmlu_full_hi_anatomy diff --git a/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_astronomy.yaml b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_astronomy.yaml new file mode 100644 index 00000000..dbb6763d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_astronomy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _hi_template_yaml +process_docs: !function utils.process_astronomy +tag: global_mmlu_full_hi_stem_tasks +task: global_mmlu_full_hi_astronomy diff --git a/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_business_ethics.yaml b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_business_ethics.yaml new file mode 100644 index 00000000..5882427e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_business_ethics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _hi_template_yaml +process_docs: !function utils.process_business_ethics +tag: global_mmlu_full_hi_other_tasks +task: global_mmlu_full_hi_business_ethics diff --git a/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_clinical_knowledge.yaml b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_clinical_knowledge.yaml new file mode 100644 index 00000000..7b0c6c3b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_clinical_knowledge.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _hi_template_yaml +process_docs: !function utils.process_clinical_knowledge +tag: global_mmlu_full_hi_other_tasks +task: global_mmlu_full_hi_clinical_knowledge diff --git a/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_college_biology.yaml b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_college_biology.yaml new file mode 100644 index 00000000..d5326c8d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_college_biology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _hi_template_yaml +process_docs: !function utils.process_college_biology +tag: global_mmlu_full_hi_stem_tasks +task: global_mmlu_full_hi_college_biology diff --git a/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_college_chemistry.yaml b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_college_chemistry.yaml new file mode 100644 index 00000000..bf9e2130 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_college_chemistry.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _hi_template_yaml +process_docs: !function utils.process_college_chemistry +tag: global_mmlu_full_hi_stem_tasks +task: global_mmlu_full_hi_college_chemistry diff --git a/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_college_computer_science.yaml b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_college_computer_science.yaml new file mode 100644 index 00000000..c79f4250 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_college_computer_science.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _hi_template_yaml +process_docs: !function utils.process_college_computer_science +tag: global_mmlu_full_hi_stem_tasks +task: global_mmlu_full_hi_college_computer_science diff --git a/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_college_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_college_mathematics.yaml new file mode 100644 index 00000000..4e8b0427 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_college_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _hi_template_yaml +process_docs: !function utils.process_college_mathematics +tag: global_mmlu_full_hi_stem_tasks +task: global_mmlu_full_hi_college_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_college_medicine.yaml b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_college_medicine.yaml new file mode 100644 index 00000000..7e8c0df2 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_college_medicine.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _hi_template_yaml +process_docs: !function utils.process_college_medicine +tag: global_mmlu_full_hi_other_tasks +task: global_mmlu_full_hi_college_medicine diff --git a/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_college_physics.yaml b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_college_physics.yaml new file mode 100644 index 00000000..5fe337ee --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_college_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _hi_template_yaml +process_docs: !function utils.process_college_physics +tag: global_mmlu_full_hi_stem_tasks +task: global_mmlu_full_hi_college_physics diff --git a/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_computer_security.yaml b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_computer_security.yaml new file mode 100644 index 00000000..029a02e0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_computer_security.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _hi_template_yaml +process_docs: !function utils.process_computer_security +tag: global_mmlu_full_hi_stem_tasks +task: global_mmlu_full_hi_computer_security diff --git a/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_conceptual_physics.yaml b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_conceptual_physics.yaml new file mode 100644 index 00000000..a6748974 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_conceptual_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _hi_template_yaml +process_docs: !function utils.process_conceptual_physics +tag: global_mmlu_full_hi_stem_tasks +task: global_mmlu_full_hi_conceptual_physics diff --git a/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_econometrics.yaml b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_econometrics.yaml new file mode 100644 index 00000000..355053b2 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_econometrics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _hi_template_yaml +process_docs: !function utils.process_econometrics +tag: global_mmlu_full_hi_social_sciences_tasks +task: global_mmlu_full_hi_econometrics diff --git a/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_electrical_engineering.yaml b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_electrical_engineering.yaml new file mode 100644 index 00000000..04dca10d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_electrical_engineering.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _hi_template_yaml +process_docs: !function utils.process_electrical_engineering +tag: global_mmlu_full_hi_stem_tasks +task: global_mmlu_full_hi_electrical_engineering diff --git a/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_elementary_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_elementary_mathematics.yaml new file mode 100644 index 00000000..ca7a3083 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_elementary_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _hi_template_yaml +process_docs: !function utils.process_elementary_mathematics +tag: global_mmlu_full_hi_stem_tasks +task: global_mmlu_full_hi_elementary_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_formal_logic.yaml b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_formal_logic.yaml new file mode 100644 index 00000000..ae534fa6 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_formal_logic.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _hi_template_yaml +process_docs: !function utils.process_formal_logic +tag: global_mmlu_full_hi_humanities_tasks +task: global_mmlu_full_hi_formal_logic diff --git a/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_global_facts.yaml b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_global_facts.yaml new file mode 100644 index 00000000..096fd58b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_global_facts.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _hi_template_yaml +process_docs: !function utils.process_global_facts +tag: global_mmlu_full_hi_other_tasks +task: global_mmlu_full_hi_global_facts diff --git a/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_high_school_biology.yaml b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_high_school_biology.yaml new file mode 100644 index 00000000..9ef04ee5 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_high_school_biology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _hi_template_yaml +process_docs: !function utils.process_high_school_biology +tag: global_mmlu_full_hi_stem_tasks +task: global_mmlu_full_hi_high_school_biology diff --git a/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_high_school_chemistry.yaml b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_high_school_chemistry.yaml new file mode 100644 index 00000000..4e8913e5 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_high_school_chemistry.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _hi_template_yaml +process_docs: !function utils.process_high_school_chemistry +tag: global_mmlu_full_hi_stem_tasks +task: global_mmlu_full_hi_high_school_chemistry diff --git a/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_high_school_computer_science.yaml b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_high_school_computer_science.yaml new file mode 100644 index 00000000..180eef75 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_high_school_computer_science.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _hi_template_yaml +process_docs: !function utils.process_high_school_computer_science +tag: global_mmlu_full_hi_stem_tasks +task: global_mmlu_full_hi_high_school_computer_science diff --git a/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_high_school_european_history.yaml b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_high_school_european_history.yaml new file mode 100644 index 00000000..32abd63b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_high_school_european_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _hi_template_yaml +process_docs: !function utils.process_high_school_european_history +tag: global_mmlu_full_hi_humanities_tasks +task: global_mmlu_full_hi_high_school_european_history diff --git a/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_high_school_geography.yaml b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_high_school_geography.yaml new file mode 100644 index 00000000..1089908b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_high_school_geography.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _hi_template_yaml +process_docs: !function utils.process_high_school_geography +tag: global_mmlu_full_hi_social_sciences_tasks +task: global_mmlu_full_hi_high_school_geography diff --git a/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_high_school_government_and_politics.yaml b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_high_school_government_and_politics.yaml new file mode 100644 index 00000000..fb22bb51 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_high_school_government_and_politics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _hi_template_yaml +process_docs: !function utils.process_high_school_government_and_politics +tag: global_mmlu_full_hi_social_sciences_tasks +task: global_mmlu_full_hi_high_school_government_and_politics diff --git a/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_high_school_macroeconomics.yaml b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_high_school_macroeconomics.yaml new file mode 100644 index 00000000..affc27c0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_high_school_macroeconomics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _hi_template_yaml +process_docs: !function utils.process_high_school_macroeconomics +tag: global_mmlu_full_hi_social_sciences_tasks +task: global_mmlu_full_hi_high_school_macroeconomics diff --git a/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_high_school_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_high_school_mathematics.yaml new file mode 100644 index 00000000..59f97c94 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_high_school_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _hi_template_yaml +process_docs: !function utils.process_high_school_mathematics +tag: global_mmlu_full_hi_stem_tasks +task: global_mmlu_full_hi_high_school_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_high_school_microeconomics.yaml b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_high_school_microeconomics.yaml new file mode 100644 index 00000000..a7506a4c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_high_school_microeconomics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _hi_template_yaml +process_docs: !function utils.process_high_school_microeconomics +tag: global_mmlu_full_hi_social_sciences_tasks +task: global_mmlu_full_hi_high_school_microeconomics diff --git a/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_high_school_physics.yaml b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_high_school_physics.yaml new file mode 100644 index 00000000..406035bd --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_high_school_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _hi_template_yaml +process_docs: !function utils.process_high_school_physics +tag: global_mmlu_full_hi_stem_tasks +task: global_mmlu_full_hi_high_school_physics diff --git a/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_high_school_psychology.yaml b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_high_school_psychology.yaml new file mode 100644 index 00000000..f5c2be37 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_high_school_psychology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _hi_template_yaml +process_docs: !function utils.process_high_school_psychology +tag: global_mmlu_full_hi_social_sciences_tasks +task: global_mmlu_full_hi_high_school_psychology diff --git a/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_high_school_statistics.yaml b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_high_school_statistics.yaml new file mode 100644 index 00000000..a955febe --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_high_school_statistics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _hi_template_yaml +process_docs: !function utils.process_high_school_statistics +tag: global_mmlu_full_hi_stem_tasks +task: global_mmlu_full_hi_high_school_statistics diff --git a/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_high_school_us_history.yaml b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_high_school_us_history.yaml new file mode 100644 index 00000000..6a5573f8 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_high_school_us_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _hi_template_yaml +process_docs: !function utils.process_high_school_us_history +tag: global_mmlu_full_hi_humanities_tasks +task: global_mmlu_full_hi_high_school_us_history diff --git a/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_high_school_world_history.yaml b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_high_school_world_history.yaml new file mode 100644 index 00000000..38ce4680 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_high_school_world_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _hi_template_yaml +process_docs: !function utils.process_high_school_world_history +tag: global_mmlu_full_hi_humanities_tasks +task: global_mmlu_full_hi_high_school_world_history diff --git a/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_human_aging.yaml b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_human_aging.yaml new file mode 100644 index 00000000..2486301f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_human_aging.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _hi_template_yaml +process_docs: !function utils.process_human_aging +tag: global_mmlu_full_hi_other_tasks +task: global_mmlu_full_hi_human_aging diff --git a/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_human_sexuality.yaml b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_human_sexuality.yaml new file mode 100644 index 00000000..8f889885 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_human_sexuality.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _hi_template_yaml +process_docs: !function utils.process_human_sexuality +tag: global_mmlu_full_hi_social_sciences_tasks +task: global_mmlu_full_hi_human_sexuality diff --git a/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_international_law.yaml b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_international_law.yaml new file mode 100644 index 00000000..2cb0d834 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_international_law.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _hi_template_yaml +process_docs: !function utils.process_international_law +tag: global_mmlu_full_hi_humanities_tasks +task: global_mmlu_full_hi_international_law diff --git a/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_jurisprudence.yaml b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_jurisprudence.yaml new file mode 100644 index 00000000..11329130 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_jurisprudence.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _hi_template_yaml +process_docs: !function utils.process_jurisprudence +tag: global_mmlu_full_hi_humanities_tasks +task: global_mmlu_full_hi_jurisprudence diff --git a/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_logical_fallacies.yaml b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_logical_fallacies.yaml new file mode 100644 index 00000000..e22cedbe --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_logical_fallacies.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _hi_template_yaml +process_docs: !function utils.process_logical_fallacies +tag: global_mmlu_full_hi_humanities_tasks +task: global_mmlu_full_hi_logical_fallacies diff --git a/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_machine_learning.yaml b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_machine_learning.yaml new file mode 100644 index 00000000..134ab080 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_machine_learning.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _hi_template_yaml +process_docs: !function utils.process_machine_learning +tag: global_mmlu_full_hi_stem_tasks +task: global_mmlu_full_hi_machine_learning diff --git a/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_management.yaml b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_management.yaml new file mode 100644 index 00000000..e523b5d1 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_management.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _hi_template_yaml +process_docs: !function utils.process_management +tag: global_mmlu_full_hi_other_tasks +task: global_mmlu_full_hi_management diff --git a/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_marketing.yaml b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_marketing.yaml new file mode 100644 index 00000000..11d8930b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_marketing.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _hi_template_yaml +process_docs: !function utils.process_marketing +tag: global_mmlu_full_hi_other_tasks +task: global_mmlu_full_hi_marketing diff --git a/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_medical_genetics.yaml b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_medical_genetics.yaml new file mode 100644 index 00000000..ad38e3e6 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_medical_genetics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _hi_template_yaml +process_docs: !function utils.process_medical_genetics +tag: global_mmlu_full_hi_other_tasks +task: global_mmlu_full_hi_medical_genetics diff --git a/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_miscellaneous.yaml b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_miscellaneous.yaml new file mode 100644 index 00000000..c31f8883 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_miscellaneous.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _hi_template_yaml +process_docs: !function utils.process_miscellaneous +tag: global_mmlu_full_hi_other_tasks +task: global_mmlu_full_hi_miscellaneous diff --git a/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_moral_disputes.yaml b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_moral_disputes.yaml new file mode 100644 index 00000000..01145f6f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_moral_disputes.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _hi_template_yaml +process_docs: !function utils.process_moral_disputes +tag: global_mmlu_full_hi_humanities_tasks +task: global_mmlu_full_hi_moral_disputes diff --git a/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_moral_scenarios.yaml b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_moral_scenarios.yaml new file mode 100644 index 00000000..4acbb127 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_moral_scenarios.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _hi_template_yaml +process_docs: !function utils.process_moral_scenarios +tag: global_mmlu_full_hi_humanities_tasks +task: global_mmlu_full_hi_moral_scenarios diff --git a/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_nutrition.yaml b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_nutrition.yaml new file mode 100644 index 00000000..889c0018 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_nutrition.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _hi_template_yaml +process_docs: !function utils.process_nutrition +tag: global_mmlu_full_hi_other_tasks +task: global_mmlu_full_hi_nutrition diff --git a/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_philosophy.yaml b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_philosophy.yaml new file mode 100644 index 00000000..2a8aeb4d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_philosophy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _hi_template_yaml +process_docs: !function utils.process_philosophy +tag: global_mmlu_full_hi_humanities_tasks +task: global_mmlu_full_hi_philosophy diff --git a/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_prehistory.yaml b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_prehistory.yaml new file mode 100644 index 00000000..ad80a3c0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_prehistory.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _hi_template_yaml +process_docs: !function utils.process_prehistory +tag: global_mmlu_full_hi_humanities_tasks +task: global_mmlu_full_hi_prehistory diff --git a/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_professional_accounting.yaml b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_professional_accounting.yaml new file mode 100644 index 00000000..1f547789 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_professional_accounting.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _hi_template_yaml +process_docs: !function utils.process_professional_accounting +tag: global_mmlu_full_hi_other_tasks +task: global_mmlu_full_hi_professional_accounting diff --git a/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_professional_law.yaml b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_professional_law.yaml new file mode 100644 index 00000000..836d577d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_professional_law.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _hi_template_yaml +process_docs: !function utils.process_professional_law +tag: global_mmlu_full_hi_humanities_tasks +task: global_mmlu_full_hi_professional_law diff --git a/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_professional_medicine.yaml b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_professional_medicine.yaml new file mode 100644 index 00000000..7a8e7db9 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_professional_medicine.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _hi_template_yaml +process_docs: !function utils.process_professional_medicine +tag: global_mmlu_full_hi_other_tasks +task: global_mmlu_full_hi_professional_medicine diff --git a/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_professional_psychology.yaml b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_professional_psychology.yaml new file mode 100644 index 00000000..b4ebc1a5 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_professional_psychology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _hi_template_yaml +process_docs: !function utils.process_professional_psychology +tag: global_mmlu_full_hi_social_sciences_tasks +task: global_mmlu_full_hi_professional_psychology diff --git a/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_public_relations.yaml b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_public_relations.yaml new file mode 100644 index 00000000..7bbf959c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_public_relations.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _hi_template_yaml +process_docs: !function utils.process_public_relations +tag: global_mmlu_full_hi_social_sciences_tasks +task: global_mmlu_full_hi_public_relations diff --git a/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_security_studies.yaml b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_security_studies.yaml new file mode 100644 index 00000000..7faa9d43 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_security_studies.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _hi_template_yaml +process_docs: !function utils.process_security_studies +tag: global_mmlu_full_hi_social_sciences_tasks +task: global_mmlu_full_hi_security_studies diff --git a/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_sociology.yaml b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_sociology.yaml new file mode 100644 index 00000000..b0ca49ae --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_sociology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _hi_template_yaml +process_docs: !function utils.process_sociology +tag: global_mmlu_full_hi_social_sciences_tasks +task: global_mmlu_full_hi_sociology diff --git a/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_us_foreign_policy.yaml b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_us_foreign_policy.yaml new file mode 100644 index 00000000..d5fd9f0f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_us_foreign_policy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _hi_template_yaml +process_docs: !function utils.process_us_foreign_policy +tag: global_mmlu_full_hi_social_sciences_tasks +task: global_mmlu_full_hi_us_foreign_policy diff --git a/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_virology.yaml b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_virology.yaml new file mode 100644 index 00000000..843ea254 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_virology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _hi_template_yaml +process_docs: !function utils.process_virology +tag: global_mmlu_full_hi_other_tasks +task: global_mmlu_full_hi_virology diff --git a/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_world_religions.yaml b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_world_religions.yaml new file mode 100644 index 00000000..f5e56ce0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/hi/global_mmlu_full_hi_world_religions.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _hi_template_yaml +process_docs: !function utils.process_world_religions +tag: global_mmlu_full_hi_humanities_tasks +task: global_mmlu_full_hi_world_religions diff --git a/lm_eval/tasks/global_mmlu/full/hi/utils.py b/lm_eval/tasks/global_mmlu/full/hi/utils.py new file mode 100644 index 00000000..7df72cb0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/hi/utils.py @@ -0,0 +1,73 @@ +from functools import partial + + +SUBJECTS = [ + "abstract_algebra", + "anatomy", + "astronomy", + "business_ethics", + "clinical_knowledge", + "college_biology", + "college_chemistry", + "college_computer_science", + "college_mathematics", + "college_medicine", + "college_physics", + "computer_security", + "conceptual_physics", + "econometrics", + "electrical_engineering", + "elementary_mathematics", + "formal_logic", + "global_facts", + "high_school_biology", + "high_school_chemistry", + "high_school_computer_science", + "high_school_european_history", + "high_school_geography", + "high_school_government_and_politics", + "high_school_macroeconomics", + "high_school_mathematics", + "high_school_microeconomics", + "high_school_physics", + "high_school_psychology", + "high_school_statistics", + "high_school_us_history", + "high_school_world_history", + "human_aging", + "human_sexuality", + "international_law", + "jurisprudence", + "logical_fallacies", + "machine_learning", + "management", + "marketing", + "medical_genetics", + "miscellaneous", + "moral_disputes", + "moral_scenarios", + "nutrition", + "philosophy", + "prehistory", + "professional_accounting", + "professional_law", + "professional_medicine", + "professional_psychology", + "public_relations", + "security_studies", + "sociology", + "us_foreign_policy", + "virology", + "world_religions", +] + + +def process_docs(dataset, subject): + return dataset.filter(lambda x: x["subject"] == subject) + + +process_functions = { + f"process_{subject}": partial(process_docs, subject=subject) for subject in SUBJECTS +} + +globals().update(process_functions) diff --git a/lm_eval/tasks/global_mmlu/full/id/_global_mmlu_full_id.yaml b/lm_eval/tasks/global_mmlu/full/id/_global_mmlu_full_id.yaml new file mode 100644 index 00000000..f678660e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/id/_global_mmlu_full_id.yaml @@ -0,0 +1,11 @@ +group: global_mmlu_full_id +task: + - global_mmlu_full_id_stem + - global_mmlu_full_id_other + - global_mmlu_full_id_social_sciences + - global_mmlu_full_id_humanities +aggregate_metric_list: + - metric: acc + weight_by_size: True +metadata: + version: 1.0 diff --git a/lm_eval/tasks/global_mmlu/full/id/_global_mmlu_full_id_humanities.yaml b/lm_eval/tasks/global_mmlu/full/id/_global_mmlu_full_id_humanities.yaml new file mode 100644 index 00000000..b9283f55 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/id/_global_mmlu_full_id_humanities.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_id_humanities +task: + - global_mmlu_full_id_humanities_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/id/_global_mmlu_full_id_other.yaml b/lm_eval/tasks/global_mmlu/full/id/_global_mmlu_full_id_other.yaml new file mode 100644 index 00000000..74de0f36 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/id/_global_mmlu_full_id_other.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_id_other +task: + - global_mmlu_full_id_other_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/id/_global_mmlu_full_id_social_sciences.yaml b/lm_eval/tasks/global_mmlu/full/id/_global_mmlu_full_id_social_sciences.yaml new file mode 100644 index 00000000..b8656b6b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/id/_global_mmlu_full_id_social_sciences.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_id_social_sciences +task: + - global_mmlu_full_id_social_sciences_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/id/_global_mmlu_full_id_stem.yaml b/lm_eval/tasks/global_mmlu/full/id/_global_mmlu_full_id_stem.yaml new file mode 100644 index 00000000..d0e47276 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/id/_global_mmlu_full_id_stem.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_id_stem +task: + - global_mmlu_full_id_stem_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/id/_id_template_yaml b/lm_eval/tasks/global_mmlu/full/id/_id_template_yaml new file mode 100644 index 00000000..32d9dc92 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/id/_id_template_yaml @@ -0,0 +1,16 @@ +dataset_path: CohereForAI/Global-MMLU +dataset_name: id +test_split: test +fewshot_split: dev +fewshot_config: + sampler: first_n +output_type: multiple_choice +doc_to_text: "{{question.strip()}}\nA. {{option_a}}\nB. {{option_b}}\nC. {{option_c}}\nD. {{option_d}}\nAnswer:" +doc_to_choice: ["A", "B", "C", "D"] +doc_to_target: answer +metric_list: + - metric: acc + aggregation: mean + higher_is_better: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_abstract_algebra.yaml b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_abstract_algebra.yaml new file mode 100644 index 00000000..b18c1cd7 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_abstract_algebra.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _id_template_yaml +process_docs: !function utils.process_abstract_algebra +tag: global_mmlu_full_id_stem_tasks +task: global_mmlu_full_id_abstract_algebra diff --git a/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_anatomy.yaml b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_anatomy.yaml new file mode 100644 index 00000000..65b83d9d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_anatomy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _id_template_yaml +process_docs: !function utils.process_anatomy +tag: global_mmlu_full_id_stem_tasks +task: global_mmlu_full_id_anatomy diff --git a/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_astronomy.yaml b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_astronomy.yaml new file mode 100644 index 00000000..11f1047c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_astronomy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _id_template_yaml +process_docs: !function utils.process_astronomy +tag: global_mmlu_full_id_stem_tasks +task: global_mmlu_full_id_astronomy diff --git a/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_business_ethics.yaml b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_business_ethics.yaml new file mode 100644 index 00000000..9ed992f2 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_business_ethics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _id_template_yaml +process_docs: !function utils.process_business_ethics +tag: global_mmlu_full_id_other_tasks +task: global_mmlu_full_id_business_ethics diff --git a/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_clinical_knowledge.yaml b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_clinical_knowledge.yaml new file mode 100644 index 00000000..8baa424f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_clinical_knowledge.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _id_template_yaml +process_docs: !function utils.process_clinical_knowledge +tag: global_mmlu_full_id_other_tasks +task: global_mmlu_full_id_clinical_knowledge diff --git a/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_college_biology.yaml b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_college_biology.yaml new file mode 100644 index 00000000..67b9c935 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_college_biology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _id_template_yaml +process_docs: !function utils.process_college_biology +tag: global_mmlu_full_id_stem_tasks +task: global_mmlu_full_id_college_biology diff --git a/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_college_chemistry.yaml b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_college_chemistry.yaml new file mode 100644 index 00000000..3eb5d228 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_college_chemistry.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _id_template_yaml +process_docs: !function utils.process_college_chemistry +tag: global_mmlu_full_id_stem_tasks +task: global_mmlu_full_id_college_chemistry diff --git a/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_college_computer_science.yaml b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_college_computer_science.yaml new file mode 100644 index 00000000..1462945b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_college_computer_science.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _id_template_yaml +process_docs: !function utils.process_college_computer_science +tag: global_mmlu_full_id_stem_tasks +task: global_mmlu_full_id_college_computer_science diff --git a/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_college_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_college_mathematics.yaml new file mode 100644 index 00000000..98062792 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_college_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _id_template_yaml +process_docs: !function utils.process_college_mathematics +tag: global_mmlu_full_id_stem_tasks +task: global_mmlu_full_id_college_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_college_medicine.yaml b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_college_medicine.yaml new file mode 100644 index 00000000..1a2736e8 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_college_medicine.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _id_template_yaml +process_docs: !function utils.process_college_medicine +tag: global_mmlu_full_id_other_tasks +task: global_mmlu_full_id_college_medicine diff --git a/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_college_physics.yaml b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_college_physics.yaml new file mode 100644 index 00000000..bb88c3f8 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_college_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _id_template_yaml +process_docs: !function utils.process_college_physics +tag: global_mmlu_full_id_stem_tasks +task: global_mmlu_full_id_college_physics diff --git a/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_computer_security.yaml b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_computer_security.yaml new file mode 100644 index 00000000..9764ac3e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_computer_security.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _id_template_yaml +process_docs: !function utils.process_computer_security +tag: global_mmlu_full_id_stem_tasks +task: global_mmlu_full_id_computer_security diff --git a/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_conceptual_physics.yaml b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_conceptual_physics.yaml new file mode 100644 index 00000000..c70c111c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_conceptual_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _id_template_yaml +process_docs: !function utils.process_conceptual_physics +tag: global_mmlu_full_id_stem_tasks +task: global_mmlu_full_id_conceptual_physics diff --git a/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_econometrics.yaml b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_econometrics.yaml new file mode 100644 index 00000000..7f82a74b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_econometrics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _id_template_yaml +process_docs: !function utils.process_econometrics +tag: global_mmlu_full_id_social_sciences_tasks +task: global_mmlu_full_id_econometrics diff --git a/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_electrical_engineering.yaml b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_electrical_engineering.yaml new file mode 100644 index 00000000..3cc2dfba --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_electrical_engineering.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _id_template_yaml +process_docs: !function utils.process_electrical_engineering +tag: global_mmlu_full_id_stem_tasks +task: global_mmlu_full_id_electrical_engineering diff --git a/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_elementary_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_elementary_mathematics.yaml new file mode 100644 index 00000000..1d511b4b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_elementary_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _id_template_yaml +process_docs: !function utils.process_elementary_mathematics +tag: global_mmlu_full_id_stem_tasks +task: global_mmlu_full_id_elementary_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_formal_logic.yaml b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_formal_logic.yaml new file mode 100644 index 00000000..7c6cef13 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_formal_logic.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _id_template_yaml +process_docs: !function utils.process_formal_logic +tag: global_mmlu_full_id_humanities_tasks +task: global_mmlu_full_id_formal_logic diff --git a/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_global_facts.yaml b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_global_facts.yaml new file mode 100644 index 00000000..5e7a44da --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_global_facts.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _id_template_yaml +process_docs: !function utils.process_global_facts +tag: global_mmlu_full_id_other_tasks +task: global_mmlu_full_id_global_facts diff --git a/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_high_school_biology.yaml b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_high_school_biology.yaml new file mode 100644 index 00000000..d39c31ab --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_high_school_biology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _id_template_yaml +process_docs: !function utils.process_high_school_biology +tag: global_mmlu_full_id_stem_tasks +task: global_mmlu_full_id_high_school_biology diff --git a/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_high_school_chemistry.yaml b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_high_school_chemistry.yaml new file mode 100644 index 00000000..d92d827a --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_high_school_chemistry.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _id_template_yaml +process_docs: !function utils.process_high_school_chemistry +tag: global_mmlu_full_id_stem_tasks +task: global_mmlu_full_id_high_school_chemistry diff --git a/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_high_school_computer_science.yaml b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_high_school_computer_science.yaml new file mode 100644 index 00000000..ff714ac8 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_high_school_computer_science.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _id_template_yaml +process_docs: !function utils.process_high_school_computer_science +tag: global_mmlu_full_id_stem_tasks +task: global_mmlu_full_id_high_school_computer_science diff --git a/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_high_school_european_history.yaml b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_high_school_european_history.yaml new file mode 100644 index 00000000..0d5c8141 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_high_school_european_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _id_template_yaml +process_docs: !function utils.process_high_school_european_history +tag: global_mmlu_full_id_humanities_tasks +task: global_mmlu_full_id_high_school_european_history diff --git a/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_high_school_geography.yaml b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_high_school_geography.yaml new file mode 100644 index 00000000..1ad392b3 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_high_school_geography.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _id_template_yaml +process_docs: !function utils.process_high_school_geography +tag: global_mmlu_full_id_social_sciences_tasks +task: global_mmlu_full_id_high_school_geography diff --git a/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_high_school_government_and_politics.yaml b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_high_school_government_and_politics.yaml new file mode 100644 index 00000000..850d6d82 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_high_school_government_and_politics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _id_template_yaml +process_docs: !function utils.process_high_school_government_and_politics +tag: global_mmlu_full_id_social_sciences_tasks +task: global_mmlu_full_id_high_school_government_and_politics diff --git a/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_high_school_macroeconomics.yaml b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_high_school_macroeconomics.yaml new file mode 100644 index 00000000..c1fda5c6 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_high_school_macroeconomics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _id_template_yaml +process_docs: !function utils.process_high_school_macroeconomics +tag: global_mmlu_full_id_social_sciences_tasks +task: global_mmlu_full_id_high_school_macroeconomics diff --git a/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_high_school_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_high_school_mathematics.yaml new file mode 100644 index 00000000..8a628ed9 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_high_school_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _id_template_yaml +process_docs: !function utils.process_high_school_mathematics +tag: global_mmlu_full_id_stem_tasks +task: global_mmlu_full_id_high_school_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_high_school_microeconomics.yaml b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_high_school_microeconomics.yaml new file mode 100644 index 00000000..f2c44707 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_high_school_microeconomics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _id_template_yaml +process_docs: !function utils.process_high_school_microeconomics +tag: global_mmlu_full_id_social_sciences_tasks +task: global_mmlu_full_id_high_school_microeconomics diff --git a/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_high_school_physics.yaml b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_high_school_physics.yaml new file mode 100644 index 00000000..75888a3d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_high_school_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _id_template_yaml +process_docs: !function utils.process_high_school_physics +tag: global_mmlu_full_id_stem_tasks +task: global_mmlu_full_id_high_school_physics diff --git a/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_high_school_psychology.yaml b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_high_school_psychology.yaml new file mode 100644 index 00000000..8a6ff54b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_high_school_psychology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _id_template_yaml +process_docs: !function utils.process_high_school_psychology +tag: global_mmlu_full_id_social_sciences_tasks +task: global_mmlu_full_id_high_school_psychology diff --git a/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_high_school_statistics.yaml b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_high_school_statistics.yaml new file mode 100644 index 00000000..ab205802 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_high_school_statistics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _id_template_yaml +process_docs: !function utils.process_high_school_statistics +tag: global_mmlu_full_id_stem_tasks +task: global_mmlu_full_id_high_school_statistics diff --git a/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_high_school_us_history.yaml b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_high_school_us_history.yaml new file mode 100644 index 00000000..8dee8c31 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_high_school_us_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _id_template_yaml +process_docs: !function utils.process_high_school_us_history +tag: global_mmlu_full_id_humanities_tasks +task: global_mmlu_full_id_high_school_us_history diff --git a/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_high_school_world_history.yaml b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_high_school_world_history.yaml new file mode 100644 index 00000000..5474c8ba --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_high_school_world_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _id_template_yaml +process_docs: !function utils.process_high_school_world_history +tag: global_mmlu_full_id_humanities_tasks +task: global_mmlu_full_id_high_school_world_history diff --git a/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_human_aging.yaml b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_human_aging.yaml new file mode 100644 index 00000000..464ac67f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_human_aging.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _id_template_yaml +process_docs: !function utils.process_human_aging +tag: global_mmlu_full_id_other_tasks +task: global_mmlu_full_id_human_aging diff --git a/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_human_sexuality.yaml b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_human_sexuality.yaml new file mode 100644 index 00000000..518cb30c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_human_sexuality.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _id_template_yaml +process_docs: !function utils.process_human_sexuality +tag: global_mmlu_full_id_social_sciences_tasks +task: global_mmlu_full_id_human_sexuality diff --git a/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_international_law.yaml b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_international_law.yaml new file mode 100644 index 00000000..90262ada --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_international_law.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _id_template_yaml +process_docs: !function utils.process_international_law +tag: global_mmlu_full_id_humanities_tasks +task: global_mmlu_full_id_international_law diff --git a/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_jurisprudence.yaml b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_jurisprudence.yaml new file mode 100644 index 00000000..8727ab49 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_jurisprudence.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _id_template_yaml +process_docs: !function utils.process_jurisprudence +tag: global_mmlu_full_id_humanities_tasks +task: global_mmlu_full_id_jurisprudence diff --git a/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_logical_fallacies.yaml b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_logical_fallacies.yaml new file mode 100644 index 00000000..da2c8e6c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_logical_fallacies.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _id_template_yaml +process_docs: !function utils.process_logical_fallacies +tag: global_mmlu_full_id_humanities_tasks +task: global_mmlu_full_id_logical_fallacies diff --git a/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_machine_learning.yaml b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_machine_learning.yaml new file mode 100644 index 00000000..84a30d9d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_machine_learning.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _id_template_yaml +process_docs: !function utils.process_machine_learning +tag: global_mmlu_full_id_stem_tasks +task: global_mmlu_full_id_machine_learning diff --git a/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_management.yaml b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_management.yaml new file mode 100644 index 00000000..fdd340bd --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_management.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _id_template_yaml +process_docs: !function utils.process_management +tag: global_mmlu_full_id_other_tasks +task: global_mmlu_full_id_management diff --git a/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_marketing.yaml b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_marketing.yaml new file mode 100644 index 00000000..caf3eb0f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_marketing.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _id_template_yaml +process_docs: !function utils.process_marketing +tag: global_mmlu_full_id_other_tasks +task: global_mmlu_full_id_marketing diff --git a/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_medical_genetics.yaml b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_medical_genetics.yaml new file mode 100644 index 00000000..0d649fd3 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_medical_genetics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _id_template_yaml +process_docs: !function utils.process_medical_genetics +tag: global_mmlu_full_id_other_tasks +task: global_mmlu_full_id_medical_genetics diff --git a/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_miscellaneous.yaml b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_miscellaneous.yaml new file mode 100644 index 00000000..0811f1b0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_miscellaneous.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _id_template_yaml +process_docs: !function utils.process_miscellaneous +tag: global_mmlu_full_id_other_tasks +task: global_mmlu_full_id_miscellaneous diff --git a/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_moral_disputes.yaml b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_moral_disputes.yaml new file mode 100644 index 00000000..0a124ded --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_moral_disputes.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _id_template_yaml +process_docs: !function utils.process_moral_disputes +tag: global_mmlu_full_id_humanities_tasks +task: global_mmlu_full_id_moral_disputes diff --git a/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_moral_scenarios.yaml b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_moral_scenarios.yaml new file mode 100644 index 00000000..65dfaea7 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_moral_scenarios.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _id_template_yaml +process_docs: !function utils.process_moral_scenarios +tag: global_mmlu_full_id_humanities_tasks +task: global_mmlu_full_id_moral_scenarios diff --git a/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_nutrition.yaml b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_nutrition.yaml new file mode 100644 index 00000000..804ffc60 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_nutrition.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _id_template_yaml +process_docs: !function utils.process_nutrition +tag: global_mmlu_full_id_other_tasks +task: global_mmlu_full_id_nutrition diff --git a/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_philosophy.yaml b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_philosophy.yaml new file mode 100644 index 00000000..88b37de8 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_philosophy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _id_template_yaml +process_docs: !function utils.process_philosophy +tag: global_mmlu_full_id_humanities_tasks +task: global_mmlu_full_id_philosophy diff --git a/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_prehistory.yaml b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_prehistory.yaml new file mode 100644 index 00000000..1e851c49 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_prehistory.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _id_template_yaml +process_docs: !function utils.process_prehistory +tag: global_mmlu_full_id_humanities_tasks +task: global_mmlu_full_id_prehistory diff --git a/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_professional_accounting.yaml b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_professional_accounting.yaml new file mode 100644 index 00000000..d45c9517 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_professional_accounting.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _id_template_yaml +process_docs: !function utils.process_professional_accounting +tag: global_mmlu_full_id_other_tasks +task: global_mmlu_full_id_professional_accounting diff --git a/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_professional_law.yaml b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_professional_law.yaml new file mode 100644 index 00000000..965cbad6 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_professional_law.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _id_template_yaml +process_docs: !function utils.process_professional_law +tag: global_mmlu_full_id_humanities_tasks +task: global_mmlu_full_id_professional_law diff --git a/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_professional_medicine.yaml b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_professional_medicine.yaml new file mode 100644 index 00000000..fdd02d53 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_professional_medicine.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _id_template_yaml +process_docs: !function utils.process_professional_medicine +tag: global_mmlu_full_id_other_tasks +task: global_mmlu_full_id_professional_medicine diff --git a/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_professional_psychology.yaml b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_professional_psychology.yaml new file mode 100644 index 00000000..b8d294b2 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_professional_psychology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _id_template_yaml +process_docs: !function utils.process_professional_psychology +tag: global_mmlu_full_id_social_sciences_tasks +task: global_mmlu_full_id_professional_psychology diff --git a/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_public_relations.yaml b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_public_relations.yaml new file mode 100644 index 00000000..8f772b0c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_public_relations.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _id_template_yaml +process_docs: !function utils.process_public_relations +tag: global_mmlu_full_id_social_sciences_tasks +task: global_mmlu_full_id_public_relations diff --git a/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_security_studies.yaml b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_security_studies.yaml new file mode 100644 index 00000000..1a73d36b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_security_studies.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _id_template_yaml +process_docs: !function utils.process_security_studies +tag: global_mmlu_full_id_social_sciences_tasks +task: global_mmlu_full_id_security_studies diff --git a/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_sociology.yaml b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_sociology.yaml new file mode 100644 index 00000000..715e5c31 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_sociology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _id_template_yaml +process_docs: !function utils.process_sociology +tag: global_mmlu_full_id_social_sciences_tasks +task: global_mmlu_full_id_sociology diff --git a/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_us_foreign_policy.yaml b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_us_foreign_policy.yaml new file mode 100644 index 00000000..59e147ae --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_us_foreign_policy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _id_template_yaml +process_docs: !function utils.process_us_foreign_policy +tag: global_mmlu_full_id_social_sciences_tasks +task: global_mmlu_full_id_us_foreign_policy diff --git a/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_virology.yaml b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_virology.yaml new file mode 100644 index 00000000..50225ab5 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_virology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _id_template_yaml +process_docs: !function utils.process_virology +tag: global_mmlu_full_id_other_tasks +task: global_mmlu_full_id_virology diff --git a/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_world_religions.yaml b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_world_religions.yaml new file mode 100644 index 00000000..0193d12d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_world_religions.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _id_template_yaml +process_docs: !function utils.process_world_religions +tag: global_mmlu_full_id_humanities_tasks +task: global_mmlu_full_id_world_religions diff --git a/lm_eval/tasks/global_mmlu/full/id/utils.py b/lm_eval/tasks/global_mmlu/full/id/utils.py new file mode 100644 index 00000000..7df72cb0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/id/utils.py @@ -0,0 +1,73 @@ +from functools import partial + + +SUBJECTS = [ + "abstract_algebra", + "anatomy", + "astronomy", + "business_ethics", + "clinical_knowledge", + "college_biology", + "college_chemistry", + "college_computer_science", + "college_mathematics", + "college_medicine", + "college_physics", + "computer_security", + "conceptual_physics", + "econometrics", + "electrical_engineering", + "elementary_mathematics", + "formal_logic", + "global_facts", + "high_school_biology", + "high_school_chemistry", + "high_school_computer_science", + "high_school_european_history", + "high_school_geography", + "high_school_government_and_politics", + "high_school_macroeconomics", + "high_school_mathematics", + "high_school_microeconomics", + "high_school_physics", + "high_school_psychology", + "high_school_statistics", + "high_school_us_history", + "high_school_world_history", + "human_aging", + "human_sexuality", + "international_law", + "jurisprudence", + "logical_fallacies", + "machine_learning", + "management", + "marketing", + "medical_genetics", + "miscellaneous", + "moral_disputes", + "moral_scenarios", + "nutrition", + "philosophy", + "prehistory", + "professional_accounting", + "professional_law", + "professional_medicine", + "professional_psychology", + "public_relations", + "security_studies", + "sociology", + "us_foreign_policy", + "virology", + "world_religions", +] + + +def process_docs(dataset, subject): + return dataset.filter(lambda x: x["subject"] == subject) + + +process_functions = { + f"process_{subject}": partial(process_docs, subject=subject) for subject in SUBJECTS +} + +globals().update(process_functions) diff --git a/lm_eval/tasks/global_mmlu/full/ig/_global_mmlu_full_ig.yaml b/lm_eval/tasks/global_mmlu/full/ig/_global_mmlu_full_ig.yaml new file mode 100644 index 00000000..a263e295 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ig/_global_mmlu_full_ig.yaml @@ -0,0 +1,11 @@ +group: global_mmlu_full_ig +task: + - global_mmlu_full_ig_stem + - global_mmlu_full_ig_other + - global_mmlu_full_ig_social_sciences + - global_mmlu_full_ig_humanities +aggregate_metric_list: + - metric: acc + weight_by_size: True +metadata: + version: 1.0 diff --git a/lm_eval/tasks/global_mmlu/full/ig/_global_mmlu_full_ig_humanities.yaml b/lm_eval/tasks/global_mmlu/full/ig/_global_mmlu_full_ig_humanities.yaml new file mode 100644 index 00000000..6c6ffb61 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ig/_global_mmlu_full_ig_humanities.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_ig_humanities +task: + - global_mmlu_full_ig_humanities_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/ig/_global_mmlu_full_ig_other.yaml b/lm_eval/tasks/global_mmlu/full/ig/_global_mmlu_full_ig_other.yaml new file mode 100644 index 00000000..214efed2 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ig/_global_mmlu_full_ig_other.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_ig_other +task: + - global_mmlu_full_ig_other_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/ig/_global_mmlu_full_ig_social_sciences.yaml b/lm_eval/tasks/global_mmlu/full/ig/_global_mmlu_full_ig_social_sciences.yaml new file mode 100644 index 00000000..e27fe1fa --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ig/_global_mmlu_full_ig_social_sciences.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_ig_social_sciences +task: + - global_mmlu_full_ig_social_sciences_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/ig/_global_mmlu_full_ig_stem.yaml b/lm_eval/tasks/global_mmlu/full/ig/_global_mmlu_full_ig_stem.yaml new file mode 100644 index 00000000..5dd33b62 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ig/_global_mmlu_full_ig_stem.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_ig_stem +task: + - global_mmlu_full_ig_stem_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/ig/_ig_template_yaml b/lm_eval/tasks/global_mmlu/full/ig/_ig_template_yaml new file mode 100644 index 00000000..0832c633 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ig/_ig_template_yaml @@ -0,0 +1,16 @@ +dataset_path: CohereForAI/Global-MMLU +dataset_name: ig +test_split: test +fewshot_split: dev +fewshot_config: + sampler: first_n +output_type: multiple_choice +doc_to_text: "{{question.strip()}}\nA. {{option_a}}\nB. {{option_b}}\nC. {{option_c}}\nD. {{option_d}}\nAnswer:" +doc_to_choice: ["A", "B", "C", "D"] +doc_to_target: answer +metric_list: + - metric: acc + aggregation: mean + higher_is_better: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_abstract_algebra.yaml b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_abstract_algebra.yaml new file mode 100644 index 00000000..1dbf6c83 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_abstract_algebra.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ig_template_yaml +process_docs: !function utils.process_abstract_algebra +tag: global_mmlu_full_ig_stem_tasks +task: global_mmlu_full_ig_abstract_algebra diff --git a/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_anatomy.yaml b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_anatomy.yaml new file mode 100644 index 00000000..8dc198c2 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_anatomy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ig_template_yaml +process_docs: !function utils.process_anatomy +tag: global_mmlu_full_ig_stem_tasks +task: global_mmlu_full_ig_anatomy diff --git a/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_astronomy.yaml b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_astronomy.yaml new file mode 100644 index 00000000..078069eb --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_astronomy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ig_template_yaml +process_docs: !function utils.process_astronomy +tag: global_mmlu_full_ig_stem_tasks +task: global_mmlu_full_ig_astronomy diff --git a/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_business_ethics.yaml b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_business_ethics.yaml new file mode 100644 index 00000000..f075e740 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_business_ethics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ig_template_yaml +process_docs: !function utils.process_business_ethics +tag: global_mmlu_full_ig_other_tasks +task: global_mmlu_full_ig_business_ethics diff --git a/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_clinical_knowledge.yaml b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_clinical_knowledge.yaml new file mode 100644 index 00000000..d41779ad --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_clinical_knowledge.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ig_template_yaml +process_docs: !function utils.process_clinical_knowledge +tag: global_mmlu_full_ig_other_tasks +task: global_mmlu_full_ig_clinical_knowledge diff --git a/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_college_biology.yaml b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_college_biology.yaml new file mode 100644 index 00000000..5f0e5705 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_college_biology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ig_template_yaml +process_docs: !function utils.process_college_biology +tag: global_mmlu_full_ig_stem_tasks +task: global_mmlu_full_ig_college_biology diff --git a/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_college_chemistry.yaml b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_college_chemistry.yaml new file mode 100644 index 00000000..78e25dc8 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_college_chemistry.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ig_template_yaml +process_docs: !function utils.process_college_chemistry +tag: global_mmlu_full_ig_stem_tasks +task: global_mmlu_full_ig_college_chemistry diff --git a/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_college_computer_science.yaml b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_college_computer_science.yaml new file mode 100644 index 00000000..d9894a45 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_college_computer_science.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ig_template_yaml +process_docs: !function utils.process_college_computer_science +tag: global_mmlu_full_ig_stem_tasks +task: global_mmlu_full_ig_college_computer_science diff --git a/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_college_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_college_mathematics.yaml new file mode 100644 index 00000000..8976041f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_college_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ig_template_yaml +process_docs: !function utils.process_college_mathematics +tag: global_mmlu_full_ig_stem_tasks +task: global_mmlu_full_ig_college_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_college_medicine.yaml b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_college_medicine.yaml new file mode 100644 index 00000000..5edaf0d5 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_college_medicine.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ig_template_yaml +process_docs: !function utils.process_college_medicine +tag: global_mmlu_full_ig_other_tasks +task: global_mmlu_full_ig_college_medicine diff --git a/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_college_physics.yaml b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_college_physics.yaml new file mode 100644 index 00000000..e55c01cb --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_college_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ig_template_yaml +process_docs: !function utils.process_college_physics +tag: global_mmlu_full_ig_stem_tasks +task: global_mmlu_full_ig_college_physics diff --git a/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_computer_security.yaml b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_computer_security.yaml new file mode 100644 index 00000000..5ee7564c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_computer_security.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ig_template_yaml +process_docs: !function utils.process_computer_security +tag: global_mmlu_full_ig_stem_tasks +task: global_mmlu_full_ig_computer_security diff --git a/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_conceptual_physics.yaml b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_conceptual_physics.yaml new file mode 100644 index 00000000..555d4fa8 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_conceptual_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ig_template_yaml +process_docs: !function utils.process_conceptual_physics +tag: global_mmlu_full_ig_stem_tasks +task: global_mmlu_full_ig_conceptual_physics diff --git a/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_econometrics.yaml b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_econometrics.yaml new file mode 100644 index 00000000..783804b8 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_econometrics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ig_template_yaml +process_docs: !function utils.process_econometrics +tag: global_mmlu_full_ig_social_sciences_tasks +task: global_mmlu_full_ig_econometrics diff --git a/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_electrical_engineering.yaml b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_electrical_engineering.yaml new file mode 100644 index 00000000..789f95d2 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_electrical_engineering.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ig_template_yaml +process_docs: !function utils.process_electrical_engineering +tag: global_mmlu_full_ig_stem_tasks +task: global_mmlu_full_ig_electrical_engineering diff --git a/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_elementary_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_elementary_mathematics.yaml new file mode 100644 index 00000000..7a5c9d2c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_elementary_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ig_template_yaml +process_docs: !function utils.process_elementary_mathematics +tag: global_mmlu_full_ig_stem_tasks +task: global_mmlu_full_ig_elementary_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_formal_logic.yaml b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_formal_logic.yaml new file mode 100644 index 00000000..8f9e426c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_formal_logic.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ig_template_yaml +process_docs: !function utils.process_formal_logic +tag: global_mmlu_full_ig_humanities_tasks +task: global_mmlu_full_ig_formal_logic diff --git a/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_global_facts.yaml b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_global_facts.yaml new file mode 100644 index 00000000..d9b7955c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_global_facts.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ig_template_yaml +process_docs: !function utils.process_global_facts +tag: global_mmlu_full_ig_other_tasks +task: global_mmlu_full_ig_global_facts diff --git a/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_high_school_biology.yaml b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_high_school_biology.yaml new file mode 100644 index 00000000..368bc71d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_high_school_biology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ig_template_yaml +process_docs: !function utils.process_high_school_biology +tag: global_mmlu_full_ig_stem_tasks +task: global_mmlu_full_ig_high_school_biology diff --git a/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_high_school_chemistry.yaml b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_high_school_chemistry.yaml new file mode 100644 index 00000000..1ce77e10 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_high_school_chemistry.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ig_template_yaml +process_docs: !function utils.process_high_school_chemistry +tag: global_mmlu_full_ig_stem_tasks +task: global_mmlu_full_ig_high_school_chemistry diff --git a/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_high_school_computer_science.yaml b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_high_school_computer_science.yaml new file mode 100644 index 00000000..d859f390 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_high_school_computer_science.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ig_template_yaml +process_docs: !function utils.process_high_school_computer_science +tag: global_mmlu_full_ig_stem_tasks +task: global_mmlu_full_ig_high_school_computer_science diff --git a/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_high_school_european_history.yaml b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_high_school_european_history.yaml new file mode 100644 index 00000000..29a93f46 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_high_school_european_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ig_template_yaml +process_docs: !function utils.process_high_school_european_history +tag: global_mmlu_full_ig_humanities_tasks +task: global_mmlu_full_ig_high_school_european_history diff --git a/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_high_school_geography.yaml b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_high_school_geography.yaml new file mode 100644 index 00000000..74194a44 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_high_school_geography.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ig_template_yaml +process_docs: !function utils.process_high_school_geography +tag: global_mmlu_full_ig_social_sciences_tasks +task: global_mmlu_full_ig_high_school_geography diff --git a/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_high_school_government_and_politics.yaml b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_high_school_government_and_politics.yaml new file mode 100644 index 00000000..cd53504d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_high_school_government_and_politics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ig_template_yaml +process_docs: !function utils.process_high_school_government_and_politics +tag: global_mmlu_full_ig_social_sciences_tasks +task: global_mmlu_full_ig_high_school_government_and_politics diff --git a/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_high_school_macroeconomics.yaml b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_high_school_macroeconomics.yaml new file mode 100644 index 00000000..30244a64 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_high_school_macroeconomics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ig_template_yaml +process_docs: !function utils.process_high_school_macroeconomics +tag: global_mmlu_full_ig_social_sciences_tasks +task: global_mmlu_full_ig_high_school_macroeconomics diff --git a/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_high_school_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_high_school_mathematics.yaml new file mode 100644 index 00000000..737c0a56 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_high_school_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ig_template_yaml +process_docs: !function utils.process_high_school_mathematics +tag: global_mmlu_full_ig_stem_tasks +task: global_mmlu_full_ig_high_school_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_high_school_microeconomics.yaml b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_high_school_microeconomics.yaml new file mode 100644 index 00000000..c5a2220c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_high_school_microeconomics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ig_template_yaml +process_docs: !function utils.process_high_school_microeconomics +tag: global_mmlu_full_ig_social_sciences_tasks +task: global_mmlu_full_ig_high_school_microeconomics diff --git a/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_high_school_physics.yaml b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_high_school_physics.yaml new file mode 100644 index 00000000..a7d4c537 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_high_school_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ig_template_yaml +process_docs: !function utils.process_high_school_physics +tag: global_mmlu_full_ig_stem_tasks +task: global_mmlu_full_ig_high_school_physics diff --git a/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_high_school_psychology.yaml b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_high_school_psychology.yaml new file mode 100644 index 00000000..d3051f01 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_high_school_psychology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ig_template_yaml +process_docs: !function utils.process_high_school_psychology +tag: global_mmlu_full_ig_social_sciences_tasks +task: global_mmlu_full_ig_high_school_psychology diff --git a/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_high_school_statistics.yaml b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_high_school_statistics.yaml new file mode 100644 index 00000000..d4841032 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_high_school_statistics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ig_template_yaml +process_docs: !function utils.process_high_school_statistics +tag: global_mmlu_full_ig_stem_tasks +task: global_mmlu_full_ig_high_school_statistics diff --git a/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_high_school_us_history.yaml b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_high_school_us_history.yaml new file mode 100644 index 00000000..61e124fc --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_high_school_us_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ig_template_yaml +process_docs: !function utils.process_high_school_us_history +tag: global_mmlu_full_ig_humanities_tasks +task: global_mmlu_full_ig_high_school_us_history diff --git a/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_high_school_world_history.yaml b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_high_school_world_history.yaml new file mode 100644 index 00000000..3d83a63d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_high_school_world_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ig_template_yaml +process_docs: !function utils.process_high_school_world_history +tag: global_mmlu_full_ig_humanities_tasks +task: global_mmlu_full_ig_high_school_world_history diff --git a/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_human_aging.yaml b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_human_aging.yaml new file mode 100644 index 00000000..787e3151 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_human_aging.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ig_template_yaml +process_docs: !function utils.process_human_aging +tag: global_mmlu_full_ig_other_tasks +task: global_mmlu_full_ig_human_aging diff --git a/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_human_sexuality.yaml b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_human_sexuality.yaml new file mode 100644 index 00000000..5c618459 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_human_sexuality.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ig_template_yaml +process_docs: !function utils.process_human_sexuality +tag: global_mmlu_full_ig_social_sciences_tasks +task: global_mmlu_full_ig_human_sexuality diff --git a/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_international_law.yaml b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_international_law.yaml new file mode 100644 index 00000000..3a8511d2 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_international_law.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ig_template_yaml +process_docs: !function utils.process_international_law +tag: global_mmlu_full_ig_humanities_tasks +task: global_mmlu_full_ig_international_law diff --git a/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_jurisprudence.yaml b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_jurisprudence.yaml new file mode 100644 index 00000000..46254ea1 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_jurisprudence.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ig_template_yaml +process_docs: !function utils.process_jurisprudence +tag: global_mmlu_full_ig_humanities_tasks +task: global_mmlu_full_ig_jurisprudence diff --git a/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_logical_fallacies.yaml b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_logical_fallacies.yaml new file mode 100644 index 00000000..2bce7502 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_logical_fallacies.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ig_template_yaml +process_docs: !function utils.process_logical_fallacies +tag: global_mmlu_full_ig_humanities_tasks +task: global_mmlu_full_ig_logical_fallacies diff --git a/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_machine_learning.yaml b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_machine_learning.yaml new file mode 100644 index 00000000..93c87fbe --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_machine_learning.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ig_template_yaml +process_docs: !function utils.process_machine_learning +tag: global_mmlu_full_ig_stem_tasks +task: global_mmlu_full_ig_machine_learning diff --git a/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_management.yaml b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_management.yaml new file mode 100644 index 00000000..780e1c89 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_management.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ig_template_yaml +process_docs: !function utils.process_management +tag: global_mmlu_full_ig_other_tasks +task: global_mmlu_full_ig_management diff --git a/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_marketing.yaml b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_marketing.yaml new file mode 100644 index 00000000..2d30ece9 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_marketing.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ig_template_yaml +process_docs: !function utils.process_marketing +tag: global_mmlu_full_ig_other_tasks +task: global_mmlu_full_ig_marketing diff --git a/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_medical_genetics.yaml b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_medical_genetics.yaml new file mode 100644 index 00000000..cac197c7 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_medical_genetics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ig_template_yaml +process_docs: !function utils.process_medical_genetics +tag: global_mmlu_full_ig_other_tasks +task: global_mmlu_full_ig_medical_genetics diff --git a/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_miscellaneous.yaml b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_miscellaneous.yaml new file mode 100644 index 00000000..a3824510 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_miscellaneous.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ig_template_yaml +process_docs: !function utils.process_miscellaneous +tag: global_mmlu_full_ig_other_tasks +task: global_mmlu_full_ig_miscellaneous diff --git a/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_moral_disputes.yaml b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_moral_disputes.yaml new file mode 100644 index 00000000..cc545d84 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_moral_disputes.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ig_template_yaml +process_docs: !function utils.process_moral_disputes +tag: global_mmlu_full_ig_humanities_tasks +task: global_mmlu_full_ig_moral_disputes diff --git a/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_moral_scenarios.yaml b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_moral_scenarios.yaml new file mode 100644 index 00000000..60ad22fe --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_moral_scenarios.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ig_template_yaml +process_docs: !function utils.process_moral_scenarios +tag: global_mmlu_full_ig_humanities_tasks +task: global_mmlu_full_ig_moral_scenarios diff --git a/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_nutrition.yaml b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_nutrition.yaml new file mode 100644 index 00000000..3cc55607 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_nutrition.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ig_template_yaml +process_docs: !function utils.process_nutrition +tag: global_mmlu_full_ig_other_tasks +task: global_mmlu_full_ig_nutrition diff --git a/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_philosophy.yaml b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_philosophy.yaml new file mode 100644 index 00000000..3f655632 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_philosophy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ig_template_yaml +process_docs: !function utils.process_philosophy +tag: global_mmlu_full_ig_humanities_tasks +task: global_mmlu_full_ig_philosophy diff --git a/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_prehistory.yaml b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_prehistory.yaml new file mode 100644 index 00000000..db4affcf --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_prehistory.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ig_template_yaml +process_docs: !function utils.process_prehistory +tag: global_mmlu_full_ig_humanities_tasks +task: global_mmlu_full_ig_prehistory diff --git a/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_professional_accounting.yaml b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_professional_accounting.yaml new file mode 100644 index 00000000..18d35773 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_professional_accounting.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ig_template_yaml +process_docs: !function utils.process_professional_accounting +tag: global_mmlu_full_ig_other_tasks +task: global_mmlu_full_ig_professional_accounting diff --git a/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_professional_law.yaml b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_professional_law.yaml new file mode 100644 index 00000000..e9db41d0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_professional_law.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ig_template_yaml +process_docs: !function utils.process_professional_law +tag: global_mmlu_full_ig_humanities_tasks +task: global_mmlu_full_ig_professional_law diff --git a/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_professional_medicine.yaml b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_professional_medicine.yaml new file mode 100644 index 00000000..7fa28b60 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_professional_medicine.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ig_template_yaml +process_docs: !function utils.process_professional_medicine +tag: global_mmlu_full_ig_other_tasks +task: global_mmlu_full_ig_professional_medicine diff --git a/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_professional_psychology.yaml b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_professional_psychology.yaml new file mode 100644 index 00000000..639be381 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_professional_psychology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ig_template_yaml +process_docs: !function utils.process_professional_psychology +tag: global_mmlu_full_ig_social_sciences_tasks +task: global_mmlu_full_ig_professional_psychology diff --git a/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_public_relations.yaml b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_public_relations.yaml new file mode 100644 index 00000000..d31af09f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_public_relations.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ig_template_yaml +process_docs: !function utils.process_public_relations +tag: global_mmlu_full_ig_social_sciences_tasks +task: global_mmlu_full_ig_public_relations diff --git a/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_security_studies.yaml b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_security_studies.yaml new file mode 100644 index 00000000..200db46b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_security_studies.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ig_template_yaml +process_docs: !function utils.process_security_studies +tag: global_mmlu_full_ig_social_sciences_tasks +task: global_mmlu_full_ig_security_studies diff --git a/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_sociology.yaml b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_sociology.yaml new file mode 100644 index 00000000..65a3e4e1 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_sociology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ig_template_yaml +process_docs: !function utils.process_sociology +tag: global_mmlu_full_ig_social_sciences_tasks +task: global_mmlu_full_ig_sociology diff --git a/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_us_foreign_policy.yaml b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_us_foreign_policy.yaml new file mode 100644 index 00000000..ff0b0505 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_us_foreign_policy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ig_template_yaml +process_docs: !function utils.process_us_foreign_policy +tag: global_mmlu_full_ig_social_sciences_tasks +task: global_mmlu_full_ig_us_foreign_policy diff --git a/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_virology.yaml b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_virology.yaml new file mode 100644 index 00000000..b437c82f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_virology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ig_template_yaml +process_docs: !function utils.process_virology +tag: global_mmlu_full_ig_other_tasks +task: global_mmlu_full_ig_virology diff --git a/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_world_religions.yaml b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_world_religions.yaml new file mode 100644 index 00000000..6fbc7cfd --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ig/global_mmlu_full_ig_world_religions.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ig_template_yaml +process_docs: !function utils.process_world_religions +tag: global_mmlu_full_ig_humanities_tasks +task: global_mmlu_full_ig_world_religions diff --git a/lm_eval/tasks/global_mmlu/full/ig/utils.py b/lm_eval/tasks/global_mmlu/full/ig/utils.py new file mode 100644 index 00000000..7df72cb0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ig/utils.py @@ -0,0 +1,73 @@ +from functools import partial + + +SUBJECTS = [ + "abstract_algebra", + "anatomy", + "astronomy", + "business_ethics", + "clinical_knowledge", + "college_biology", + "college_chemistry", + "college_computer_science", + "college_mathematics", + "college_medicine", + "college_physics", + "computer_security", + "conceptual_physics", + "econometrics", + "electrical_engineering", + "elementary_mathematics", + "formal_logic", + "global_facts", + "high_school_biology", + "high_school_chemistry", + "high_school_computer_science", + "high_school_european_history", + "high_school_geography", + "high_school_government_and_politics", + "high_school_macroeconomics", + "high_school_mathematics", + "high_school_microeconomics", + "high_school_physics", + "high_school_psychology", + "high_school_statistics", + "high_school_us_history", + "high_school_world_history", + "human_aging", + "human_sexuality", + "international_law", + "jurisprudence", + "logical_fallacies", + "machine_learning", + "management", + "marketing", + "medical_genetics", + "miscellaneous", + "moral_disputes", + "moral_scenarios", + "nutrition", + "philosophy", + "prehistory", + "professional_accounting", + "professional_law", + "professional_medicine", + "professional_psychology", + "public_relations", + "security_studies", + "sociology", + "us_foreign_policy", + "virology", + "world_religions", +] + + +def process_docs(dataset, subject): + return dataset.filter(lambda x: x["subject"] == subject) + + +process_functions = { + f"process_{subject}": partial(process_docs, subject=subject) for subject in SUBJECTS +} + +globals().update(process_functions) diff --git a/lm_eval/tasks/global_mmlu/full/it/_global_mmlu_full_it.yaml b/lm_eval/tasks/global_mmlu/full/it/_global_mmlu_full_it.yaml new file mode 100644 index 00000000..dabb8987 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/it/_global_mmlu_full_it.yaml @@ -0,0 +1,11 @@ +group: global_mmlu_full_it +task: + - global_mmlu_full_it_stem + - global_mmlu_full_it_other + - global_mmlu_full_it_social_sciences + - global_mmlu_full_it_humanities +aggregate_metric_list: + - metric: acc + weight_by_size: True +metadata: + version: 1.0 diff --git a/lm_eval/tasks/global_mmlu/full/it/_global_mmlu_full_it_humanities.yaml b/lm_eval/tasks/global_mmlu/full/it/_global_mmlu_full_it_humanities.yaml new file mode 100644 index 00000000..3d072ccc --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/it/_global_mmlu_full_it_humanities.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_it_humanities +task: + - global_mmlu_full_it_humanities_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/it/_global_mmlu_full_it_other.yaml b/lm_eval/tasks/global_mmlu/full/it/_global_mmlu_full_it_other.yaml new file mode 100644 index 00000000..99fe18cd --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/it/_global_mmlu_full_it_other.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_it_other +task: + - global_mmlu_full_it_other_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/it/_global_mmlu_full_it_social_sciences.yaml b/lm_eval/tasks/global_mmlu/full/it/_global_mmlu_full_it_social_sciences.yaml new file mode 100644 index 00000000..15a457a5 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/it/_global_mmlu_full_it_social_sciences.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_it_social_sciences +task: + - global_mmlu_full_it_social_sciences_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/it/_global_mmlu_full_it_stem.yaml b/lm_eval/tasks/global_mmlu/full/it/_global_mmlu_full_it_stem.yaml new file mode 100644 index 00000000..cf7a555d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/it/_global_mmlu_full_it_stem.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_it_stem +task: + - global_mmlu_full_it_stem_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/it/_it_template_yaml b/lm_eval/tasks/global_mmlu/full/it/_it_template_yaml new file mode 100644 index 00000000..4798e10a --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/it/_it_template_yaml @@ -0,0 +1,16 @@ +dataset_path: CohereForAI/Global-MMLU +dataset_name: it +test_split: test +fewshot_split: dev +fewshot_config: + sampler: first_n +output_type: multiple_choice +doc_to_text: "{{question.strip()}}\nA. {{option_a}}\nB. {{option_b}}\nC. {{option_c}}\nD. {{option_d}}\nAnswer:" +doc_to_choice: ["A", "B", "C", "D"] +doc_to_target: answer +metric_list: + - metric: acc + aggregation: mean + higher_is_better: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_abstract_algebra.yaml b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_abstract_algebra.yaml new file mode 100644 index 00000000..f7351c1e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_abstract_algebra.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _it_template_yaml +process_docs: !function utils.process_abstract_algebra +tag: global_mmlu_full_it_stem_tasks +task: global_mmlu_full_it_abstract_algebra diff --git a/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_anatomy.yaml b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_anatomy.yaml new file mode 100644 index 00000000..436cd3f6 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_anatomy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _it_template_yaml +process_docs: !function utils.process_anatomy +tag: global_mmlu_full_it_stem_tasks +task: global_mmlu_full_it_anatomy diff --git a/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_astronomy.yaml b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_astronomy.yaml new file mode 100644 index 00000000..f98f0f20 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_astronomy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _it_template_yaml +process_docs: !function utils.process_astronomy +tag: global_mmlu_full_it_stem_tasks +task: global_mmlu_full_it_astronomy diff --git a/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_business_ethics.yaml b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_business_ethics.yaml new file mode 100644 index 00000000..d9d931fe --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_business_ethics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _it_template_yaml +process_docs: !function utils.process_business_ethics +tag: global_mmlu_full_it_other_tasks +task: global_mmlu_full_it_business_ethics diff --git a/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_clinical_knowledge.yaml b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_clinical_knowledge.yaml new file mode 100644 index 00000000..fe429024 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_clinical_knowledge.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _it_template_yaml +process_docs: !function utils.process_clinical_knowledge +tag: global_mmlu_full_it_other_tasks +task: global_mmlu_full_it_clinical_knowledge diff --git a/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_college_biology.yaml b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_college_biology.yaml new file mode 100644 index 00000000..71b8f45e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_college_biology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _it_template_yaml +process_docs: !function utils.process_college_biology +tag: global_mmlu_full_it_stem_tasks +task: global_mmlu_full_it_college_biology diff --git a/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_college_chemistry.yaml b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_college_chemistry.yaml new file mode 100644 index 00000000..d29bd758 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_college_chemistry.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _it_template_yaml +process_docs: !function utils.process_college_chemistry +tag: global_mmlu_full_it_stem_tasks +task: global_mmlu_full_it_college_chemistry diff --git a/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_college_computer_science.yaml b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_college_computer_science.yaml new file mode 100644 index 00000000..f740d259 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_college_computer_science.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _it_template_yaml +process_docs: !function utils.process_college_computer_science +tag: global_mmlu_full_it_stem_tasks +task: global_mmlu_full_it_college_computer_science diff --git a/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_college_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_college_mathematics.yaml new file mode 100644 index 00000000..7568fb7e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_college_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _it_template_yaml +process_docs: !function utils.process_college_mathematics +tag: global_mmlu_full_it_stem_tasks +task: global_mmlu_full_it_college_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_college_medicine.yaml b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_college_medicine.yaml new file mode 100644 index 00000000..9bfc5ac1 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_college_medicine.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _it_template_yaml +process_docs: !function utils.process_college_medicine +tag: global_mmlu_full_it_other_tasks +task: global_mmlu_full_it_college_medicine diff --git a/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_college_physics.yaml b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_college_physics.yaml new file mode 100644 index 00000000..2101847e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_college_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _it_template_yaml +process_docs: !function utils.process_college_physics +tag: global_mmlu_full_it_stem_tasks +task: global_mmlu_full_it_college_physics diff --git a/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_computer_security.yaml b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_computer_security.yaml new file mode 100644 index 00000000..70b31f9a --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_computer_security.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _it_template_yaml +process_docs: !function utils.process_computer_security +tag: global_mmlu_full_it_stem_tasks +task: global_mmlu_full_it_computer_security diff --git a/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_conceptual_physics.yaml b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_conceptual_physics.yaml new file mode 100644 index 00000000..d8917d40 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_conceptual_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _it_template_yaml +process_docs: !function utils.process_conceptual_physics +tag: global_mmlu_full_it_stem_tasks +task: global_mmlu_full_it_conceptual_physics diff --git a/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_econometrics.yaml b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_econometrics.yaml new file mode 100644 index 00000000..a49352fb --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_econometrics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _it_template_yaml +process_docs: !function utils.process_econometrics +tag: global_mmlu_full_it_social_sciences_tasks +task: global_mmlu_full_it_econometrics diff --git a/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_electrical_engineering.yaml b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_electrical_engineering.yaml new file mode 100644 index 00000000..27f0c6c3 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_electrical_engineering.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _it_template_yaml +process_docs: !function utils.process_electrical_engineering +tag: global_mmlu_full_it_stem_tasks +task: global_mmlu_full_it_electrical_engineering diff --git a/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_elementary_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_elementary_mathematics.yaml new file mode 100644 index 00000000..fd78a52e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_elementary_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _it_template_yaml +process_docs: !function utils.process_elementary_mathematics +tag: global_mmlu_full_it_stem_tasks +task: global_mmlu_full_it_elementary_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_formal_logic.yaml b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_formal_logic.yaml new file mode 100644 index 00000000..8171fcf1 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_formal_logic.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _it_template_yaml +process_docs: !function utils.process_formal_logic +tag: global_mmlu_full_it_humanities_tasks +task: global_mmlu_full_it_formal_logic diff --git a/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_global_facts.yaml b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_global_facts.yaml new file mode 100644 index 00000000..a952ed44 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_global_facts.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _it_template_yaml +process_docs: !function utils.process_global_facts +tag: global_mmlu_full_it_other_tasks +task: global_mmlu_full_it_global_facts diff --git a/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_high_school_biology.yaml b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_high_school_biology.yaml new file mode 100644 index 00000000..939ba752 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_high_school_biology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _it_template_yaml +process_docs: !function utils.process_high_school_biology +tag: global_mmlu_full_it_stem_tasks +task: global_mmlu_full_it_high_school_biology diff --git a/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_high_school_chemistry.yaml b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_high_school_chemistry.yaml new file mode 100644 index 00000000..4524d4dc --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_high_school_chemistry.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _it_template_yaml +process_docs: !function utils.process_high_school_chemistry +tag: global_mmlu_full_it_stem_tasks +task: global_mmlu_full_it_high_school_chemistry diff --git a/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_high_school_computer_science.yaml b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_high_school_computer_science.yaml new file mode 100644 index 00000000..2dfb1649 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_high_school_computer_science.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _it_template_yaml +process_docs: !function utils.process_high_school_computer_science +tag: global_mmlu_full_it_stem_tasks +task: global_mmlu_full_it_high_school_computer_science diff --git a/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_high_school_european_history.yaml b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_high_school_european_history.yaml new file mode 100644 index 00000000..556aaf20 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_high_school_european_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _it_template_yaml +process_docs: !function utils.process_high_school_european_history +tag: global_mmlu_full_it_humanities_tasks +task: global_mmlu_full_it_high_school_european_history diff --git a/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_high_school_geography.yaml b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_high_school_geography.yaml new file mode 100644 index 00000000..3c1d5b60 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_high_school_geography.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _it_template_yaml +process_docs: !function utils.process_high_school_geography +tag: global_mmlu_full_it_social_sciences_tasks +task: global_mmlu_full_it_high_school_geography diff --git a/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_high_school_government_and_politics.yaml b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_high_school_government_and_politics.yaml new file mode 100644 index 00000000..a35b6bac --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_high_school_government_and_politics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _it_template_yaml +process_docs: !function utils.process_high_school_government_and_politics +tag: global_mmlu_full_it_social_sciences_tasks +task: global_mmlu_full_it_high_school_government_and_politics diff --git a/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_high_school_macroeconomics.yaml b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_high_school_macroeconomics.yaml new file mode 100644 index 00000000..74c01ccd --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_high_school_macroeconomics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _it_template_yaml +process_docs: !function utils.process_high_school_macroeconomics +tag: global_mmlu_full_it_social_sciences_tasks +task: global_mmlu_full_it_high_school_macroeconomics diff --git a/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_high_school_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_high_school_mathematics.yaml new file mode 100644 index 00000000..6bec02c4 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_high_school_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _it_template_yaml +process_docs: !function utils.process_high_school_mathematics +tag: global_mmlu_full_it_stem_tasks +task: global_mmlu_full_it_high_school_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_high_school_microeconomics.yaml b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_high_school_microeconomics.yaml new file mode 100644 index 00000000..551a0f8d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_high_school_microeconomics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _it_template_yaml +process_docs: !function utils.process_high_school_microeconomics +tag: global_mmlu_full_it_social_sciences_tasks +task: global_mmlu_full_it_high_school_microeconomics diff --git a/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_high_school_physics.yaml b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_high_school_physics.yaml new file mode 100644 index 00000000..3cf7144b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_high_school_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _it_template_yaml +process_docs: !function utils.process_high_school_physics +tag: global_mmlu_full_it_stem_tasks +task: global_mmlu_full_it_high_school_physics diff --git a/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_high_school_psychology.yaml b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_high_school_psychology.yaml new file mode 100644 index 00000000..17088e51 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_high_school_psychology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _it_template_yaml +process_docs: !function utils.process_high_school_psychology +tag: global_mmlu_full_it_social_sciences_tasks +task: global_mmlu_full_it_high_school_psychology diff --git a/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_high_school_statistics.yaml b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_high_school_statistics.yaml new file mode 100644 index 00000000..f3f35f99 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_high_school_statistics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _it_template_yaml +process_docs: !function utils.process_high_school_statistics +tag: global_mmlu_full_it_stem_tasks +task: global_mmlu_full_it_high_school_statistics diff --git a/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_high_school_us_history.yaml b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_high_school_us_history.yaml new file mode 100644 index 00000000..af222877 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_high_school_us_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _it_template_yaml +process_docs: !function utils.process_high_school_us_history +tag: global_mmlu_full_it_humanities_tasks +task: global_mmlu_full_it_high_school_us_history diff --git a/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_high_school_world_history.yaml b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_high_school_world_history.yaml new file mode 100644 index 00000000..698ddb5f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_high_school_world_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _it_template_yaml +process_docs: !function utils.process_high_school_world_history +tag: global_mmlu_full_it_humanities_tasks +task: global_mmlu_full_it_high_school_world_history diff --git a/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_human_aging.yaml b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_human_aging.yaml new file mode 100644 index 00000000..6ff49730 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_human_aging.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _it_template_yaml +process_docs: !function utils.process_human_aging +tag: global_mmlu_full_it_other_tasks +task: global_mmlu_full_it_human_aging diff --git a/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_human_sexuality.yaml b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_human_sexuality.yaml new file mode 100644 index 00000000..58d32fa4 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_human_sexuality.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _it_template_yaml +process_docs: !function utils.process_human_sexuality +tag: global_mmlu_full_it_social_sciences_tasks +task: global_mmlu_full_it_human_sexuality diff --git a/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_international_law.yaml b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_international_law.yaml new file mode 100644 index 00000000..d7c47e55 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_international_law.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _it_template_yaml +process_docs: !function utils.process_international_law +tag: global_mmlu_full_it_humanities_tasks +task: global_mmlu_full_it_international_law diff --git a/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_jurisprudence.yaml b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_jurisprudence.yaml new file mode 100644 index 00000000..e100c0e9 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_jurisprudence.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _it_template_yaml +process_docs: !function utils.process_jurisprudence +tag: global_mmlu_full_it_humanities_tasks +task: global_mmlu_full_it_jurisprudence diff --git a/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_logical_fallacies.yaml b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_logical_fallacies.yaml new file mode 100644 index 00000000..a07444a8 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_logical_fallacies.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _it_template_yaml +process_docs: !function utils.process_logical_fallacies +tag: global_mmlu_full_it_humanities_tasks +task: global_mmlu_full_it_logical_fallacies diff --git a/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_machine_learning.yaml b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_machine_learning.yaml new file mode 100644 index 00000000..bfd3b7a5 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_machine_learning.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _it_template_yaml +process_docs: !function utils.process_machine_learning +tag: global_mmlu_full_it_stem_tasks +task: global_mmlu_full_it_machine_learning diff --git a/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_management.yaml b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_management.yaml new file mode 100644 index 00000000..5b5feeac --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_management.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _it_template_yaml +process_docs: !function utils.process_management +tag: global_mmlu_full_it_other_tasks +task: global_mmlu_full_it_management diff --git a/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_marketing.yaml b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_marketing.yaml new file mode 100644 index 00000000..d50b46f4 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_marketing.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _it_template_yaml +process_docs: !function utils.process_marketing +tag: global_mmlu_full_it_other_tasks +task: global_mmlu_full_it_marketing diff --git a/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_medical_genetics.yaml b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_medical_genetics.yaml new file mode 100644 index 00000000..1b02316c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_medical_genetics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _it_template_yaml +process_docs: !function utils.process_medical_genetics +tag: global_mmlu_full_it_other_tasks +task: global_mmlu_full_it_medical_genetics diff --git a/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_miscellaneous.yaml b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_miscellaneous.yaml new file mode 100644 index 00000000..b638b50d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_miscellaneous.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _it_template_yaml +process_docs: !function utils.process_miscellaneous +tag: global_mmlu_full_it_other_tasks +task: global_mmlu_full_it_miscellaneous diff --git a/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_moral_disputes.yaml b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_moral_disputes.yaml new file mode 100644 index 00000000..520a8bea --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_moral_disputes.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _it_template_yaml +process_docs: !function utils.process_moral_disputes +tag: global_mmlu_full_it_humanities_tasks +task: global_mmlu_full_it_moral_disputes diff --git a/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_moral_scenarios.yaml b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_moral_scenarios.yaml new file mode 100644 index 00000000..abfc7395 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_moral_scenarios.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _it_template_yaml +process_docs: !function utils.process_moral_scenarios +tag: global_mmlu_full_it_humanities_tasks +task: global_mmlu_full_it_moral_scenarios diff --git a/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_nutrition.yaml b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_nutrition.yaml new file mode 100644 index 00000000..cac74152 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_nutrition.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _it_template_yaml +process_docs: !function utils.process_nutrition +tag: global_mmlu_full_it_other_tasks +task: global_mmlu_full_it_nutrition diff --git a/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_philosophy.yaml b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_philosophy.yaml new file mode 100644 index 00000000..a1d94976 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_philosophy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _it_template_yaml +process_docs: !function utils.process_philosophy +tag: global_mmlu_full_it_humanities_tasks +task: global_mmlu_full_it_philosophy diff --git a/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_prehistory.yaml b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_prehistory.yaml new file mode 100644 index 00000000..74bdec82 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_prehistory.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _it_template_yaml +process_docs: !function utils.process_prehistory +tag: global_mmlu_full_it_humanities_tasks +task: global_mmlu_full_it_prehistory diff --git a/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_professional_accounting.yaml b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_professional_accounting.yaml new file mode 100644 index 00000000..acf999a2 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_professional_accounting.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _it_template_yaml +process_docs: !function utils.process_professional_accounting +tag: global_mmlu_full_it_other_tasks +task: global_mmlu_full_it_professional_accounting diff --git a/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_professional_law.yaml b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_professional_law.yaml new file mode 100644 index 00000000..1ec4f58e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_professional_law.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _it_template_yaml +process_docs: !function utils.process_professional_law +tag: global_mmlu_full_it_humanities_tasks +task: global_mmlu_full_it_professional_law diff --git a/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_professional_medicine.yaml b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_professional_medicine.yaml new file mode 100644 index 00000000..8b53cdac --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_professional_medicine.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _it_template_yaml +process_docs: !function utils.process_professional_medicine +tag: global_mmlu_full_it_other_tasks +task: global_mmlu_full_it_professional_medicine diff --git a/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_professional_psychology.yaml b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_professional_psychology.yaml new file mode 100644 index 00000000..9b7a24f3 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_professional_psychology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _it_template_yaml +process_docs: !function utils.process_professional_psychology +tag: global_mmlu_full_it_social_sciences_tasks +task: global_mmlu_full_it_professional_psychology diff --git a/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_public_relations.yaml b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_public_relations.yaml new file mode 100644 index 00000000..727cf4b6 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_public_relations.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _it_template_yaml +process_docs: !function utils.process_public_relations +tag: global_mmlu_full_it_social_sciences_tasks +task: global_mmlu_full_it_public_relations diff --git a/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_security_studies.yaml b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_security_studies.yaml new file mode 100644 index 00000000..90fd186c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_security_studies.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _it_template_yaml +process_docs: !function utils.process_security_studies +tag: global_mmlu_full_it_social_sciences_tasks +task: global_mmlu_full_it_security_studies diff --git a/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_sociology.yaml b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_sociology.yaml new file mode 100644 index 00000000..dbc77935 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_sociology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _it_template_yaml +process_docs: !function utils.process_sociology +tag: global_mmlu_full_it_social_sciences_tasks +task: global_mmlu_full_it_sociology diff --git a/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_us_foreign_policy.yaml b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_us_foreign_policy.yaml new file mode 100644 index 00000000..e2a923b6 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_us_foreign_policy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _it_template_yaml +process_docs: !function utils.process_us_foreign_policy +tag: global_mmlu_full_it_social_sciences_tasks +task: global_mmlu_full_it_us_foreign_policy diff --git a/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_virology.yaml b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_virology.yaml new file mode 100644 index 00000000..72758a56 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_virology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _it_template_yaml +process_docs: !function utils.process_virology +tag: global_mmlu_full_it_other_tasks +task: global_mmlu_full_it_virology diff --git a/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_world_religions.yaml b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_world_religions.yaml new file mode 100644 index 00000000..e4491c51 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/it/global_mmlu_full_it_world_religions.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _it_template_yaml +process_docs: !function utils.process_world_religions +tag: global_mmlu_full_it_humanities_tasks +task: global_mmlu_full_it_world_religions diff --git a/lm_eval/tasks/global_mmlu/full/it/utils.py b/lm_eval/tasks/global_mmlu/full/it/utils.py new file mode 100644 index 00000000..7df72cb0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/it/utils.py @@ -0,0 +1,73 @@ +from functools import partial + + +SUBJECTS = [ + "abstract_algebra", + "anatomy", + "astronomy", + "business_ethics", + "clinical_knowledge", + "college_biology", + "college_chemistry", + "college_computer_science", + "college_mathematics", + "college_medicine", + "college_physics", + "computer_security", + "conceptual_physics", + "econometrics", + "electrical_engineering", + "elementary_mathematics", + "formal_logic", + "global_facts", + "high_school_biology", + "high_school_chemistry", + "high_school_computer_science", + "high_school_european_history", + "high_school_geography", + "high_school_government_and_politics", + "high_school_macroeconomics", + "high_school_mathematics", + "high_school_microeconomics", + "high_school_physics", + "high_school_psychology", + "high_school_statistics", + "high_school_us_history", + "high_school_world_history", + "human_aging", + "human_sexuality", + "international_law", + "jurisprudence", + "logical_fallacies", + "machine_learning", + "management", + "marketing", + "medical_genetics", + "miscellaneous", + "moral_disputes", + "moral_scenarios", + "nutrition", + "philosophy", + "prehistory", + "professional_accounting", + "professional_law", + "professional_medicine", + "professional_psychology", + "public_relations", + "security_studies", + "sociology", + "us_foreign_policy", + "virology", + "world_religions", +] + + +def process_docs(dataset, subject): + return dataset.filter(lambda x: x["subject"] == subject) + + +process_functions = { + f"process_{subject}": partial(process_docs, subject=subject) for subject in SUBJECTS +} + +globals().update(process_functions) diff --git a/lm_eval/tasks/global_mmlu/full/ja/_global_mmlu_full_ja.yaml b/lm_eval/tasks/global_mmlu/full/ja/_global_mmlu_full_ja.yaml new file mode 100644 index 00000000..103460d7 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ja/_global_mmlu_full_ja.yaml @@ -0,0 +1,11 @@ +group: global_mmlu_full_ja +task: + - global_mmlu_full_ja_stem + - global_mmlu_full_ja_other + - global_mmlu_full_ja_social_sciences + - global_mmlu_full_ja_humanities +aggregate_metric_list: + - metric: acc + weight_by_size: True +metadata: + version: 1.0 diff --git a/lm_eval/tasks/global_mmlu/full/ja/_global_mmlu_full_ja_humanities.yaml b/lm_eval/tasks/global_mmlu/full/ja/_global_mmlu_full_ja_humanities.yaml new file mode 100644 index 00000000..a063eb0b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ja/_global_mmlu_full_ja_humanities.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_ja_humanities +task: + - global_mmlu_full_ja_humanities_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/ja/_global_mmlu_full_ja_other.yaml b/lm_eval/tasks/global_mmlu/full/ja/_global_mmlu_full_ja_other.yaml new file mode 100644 index 00000000..1f9b95ed --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ja/_global_mmlu_full_ja_other.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_ja_other +task: + - global_mmlu_full_ja_other_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/ja/_global_mmlu_full_ja_social_sciences.yaml b/lm_eval/tasks/global_mmlu/full/ja/_global_mmlu_full_ja_social_sciences.yaml new file mode 100644 index 00000000..4207fea4 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ja/_global_mmlu_full_ja_social_sciences.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_ja_social_sciences +task: + - global_mmlu_full_ja_social_sciences_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/ja/_global_mmlu_full_ja_stem.yaml b/lm_eval/tasks/global_mmlu/full/ja/_global_mmlu_full_ja_stem.yaml new file mode 100644 index 00000000..7ca6ed1c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ja/_global_mmlu_full_ja_stem.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_ja_stem +task: + - global_mmlu_full_ja_stem_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/ja/_ja_template_yaml b/lm_eval/tasks/global_mmlu/full/ja/_ja_template_yaml new file mode 100644 index 00000000..591725e3 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ja/_ja_template_yaml @@ -0,0 +1,16 @@ +dataset_path: CohereForAI/Global-MMLU +dataset_name: ja +test_split: test +fewshot_split: dev +fewshot_config: + sampler: first_n +output_type: multiple_choice +doc_to_text: "{{question.strip()}}\nA. {{option_a}}\nB. {{option_b}}\nC. {{option_c}}\nD. {{option_d}}\nAnswer:" +doc_to_choice: ["A", "B", "C", "D"] +doc_to_target: answer +metric_list: + - metric: acc + aggregation: mean + higher_is_better: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_abstract_algebra.yaml b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_abstract_algebra.yaml new file mode 100644 index 00000000..4b65a75b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_abstract_algebra.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ja_template_yaml +process_docs: !function utils.process_abstract_algebra +tag: global_mmlu_full_ja_stem_tasks +task: global_mmlu_full_ja_abstract_algebra diff --git a/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_anatomy.yaml b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_anatomy.yaml new file mode 100644 index 00000000..e735aa34 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_anatomy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ja_template_yaml +process_docs: !function utils.process_anatomy +tag: global_mmlu_full_ja_stem_tasks +task: global_mmlu_full_ja_anatomy diff --git a/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_astronomy.yaml b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_astronomy.yaml new file mode 100644 index 00000000..a0ba8947 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_astronomy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ja_template_yaml +process_docs: !function utils.process_astronomy +tag: global_mmlu_full_ja_stem_tasks +task: global_mmlu_full_ja_astronomy diff --git a/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_business_ethics.yaml b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_business_ethics.yaml new file mode 100644 index 00000000..c39d286c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_business_ethics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ja_template_yaml +process_docs: !function utils.process_business_ethics +tag: global_mmlu_full_ja_other_tasks +task: global_mmlu_full_ja_business_ethics diff --git a/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_clinical_knowledge.yaml b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_clinical_knowledge.yaml new file mode 100644 index 00000000..27d09b88 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_clinical_knowledge.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ja_template_yaml +process_docs: !function utils.process_clinical_knowledge +tag: global_mmlu_full_ja_other_tasks +task: global_mmlu_full_ja_clinical_knowledge diff --git a/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_college_biology.yaml b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_college_biology.yaml new file mode 100644 index 00000000..15e26a51 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_college_biology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ja_template_yaml +process_docs: !function utils.process_college_biology +tag: global_mmlu_full_ja_stem_tasks +task: global_mmlu_full_ja_college_biology diff --git a/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_college_chemistry.yaml b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_college_chemistry.yaml new file mode 100644 index 00000000..52c92423 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_college_chemistry.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ja_template_yaml +process_docs: !function utils.process_college_chemistry +tag: global_mmlu_full_ja_stem_tasks +task: global_mmlu_full_ja_college_chemistry diff --git a/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_college_computer_science.yaml b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_college_computer_science.yaml new file mode 100644 index 00000000..a91a7d61 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_college_computer_science.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ja_template_yaml +process_docs: !function utils.process_college_computer_science +tag: global_mmlu_full_ja_stem_tasks +task: global_mmlu_full_ja_college_computer_science diff --git a/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_college_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_college_mathematics.yaml new file mode 100644 index 00000000..67dcd2a0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_college_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ja_template_yaml +process_docs: !function utils.process_college_mathematics +tag: global_mmlu_full_ja_stem_tasks +task: global_mmlu_full_ja_college_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_college_medicine.yaml b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_college_medicine.yaml new file mode 100644 index 00000000..c55ab2a2 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_college_medicine.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ja_template_yaml +process_docs: !function utils.process_college_medicine +tag: global_mmlu_full_ja_other_tasks +task: global_mmlu_full_ja_college_medicine diff --git a/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_college_physics.yaml b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_college_physics.yaml new file mode 100644 index 00000000..5413c86d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_college_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ja_template_yaml +process_docs: !function utils.process_college_physics +tag: global_mmlu_full_ja_stem_tasks +task: global_mmlu_full_ja_college_physics diff --git a/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_computer_security.yaml b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_computer_security.yaml new file mode 100644 index 00000000..276f214e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_computer_security.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ja_template_yaml +process_docs: !function utils.process_computer_security +tag: global_mmlu_full_ja_stem_tasks +task: global_mmlu_full_ja_computer_security diff --git a/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_conceptual_physics.yaml b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_conceptual_physics.yaml new file mode 100644 index 00000000..f823ac44 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_conceptual_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ja_template_yaml +process_docs: !function utils.process_conceptual_physics +tag: global_mmlu_full_ja_stem_tasks +task: global_mmlu_full_ja_conceptual_physics diff --git a/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_econometrics.yaml b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_econometrics.yaml new file mode 100644 index 00000000..dbc6846a --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_econometrics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ja_template_yaml +process_docs: !function utils.process_econometrics +tag: global_mmlu_full_ja_social_sciences_tasks +task: global_mmlu_full_ja_econometrics diff --git a/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_electrical_engineering.yaml b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_electrical_engineering.yaml new file mode 100644 index 00000000..ba729575 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_electrical_engineering.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ja_template_yaml +process_docs: !function utils.process_electrical_engineering +tag: global_mmlu_full_ja_stem_tasks +task: global_mmlu_full_ja_electrical_engineering diff --git a/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_elementary_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_elementary_mathematics.yaml new file mode 100644 index 00000000..13807104 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_elementary_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ja_template_yaml +process_docs: !function utils.process_elementary_mathematics +tag: global_mmlu_full_ja_stem_tasks +task: global_mmlu_full_ja_elementary_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_formal_logic.yaml b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_formal_logic.yaml new file mode 100644 index 00000000..d88d5685 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_formal_logic.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ja_template_yaml +process_docs: !function utils.process_formal_logic +tag: global_mmlu_full_ja_humanities_tasks +task: global_mmlu_full_ja_formal_logic diff --git a/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_global_facts.yaml b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_global_facts.yaml new file mode 100644 index 00000000..64cb2b9e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_global_facts.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ja_template_yaml +process_docs: !function utils.process_global_facts +tag: global_mmlu_full_ja_other_tasks +task: global_mmlu_full_ja_global_facts diff --git a/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_high_school_biology.yaml b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_high_school_biology.yaml new file mode 100644 index 00000000..b88adf90 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_high_school_biology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ja_template_yaml +process_docs: !function utils.process_high_school_biology +tag: global_mmlu_full_ja_stem_tasks +task: global_mmlu_full_ja_high_school_biology diff --git a/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_high_school_chemistry.yaml b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_high_school_chemistry.yaml new file mode 100644 index 00000000..eef67cc7 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_high_school_chemistry.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ja_template_yaml +process_docs: !function utils.process_high_school_chemistry +tag: global_mmlu_full_ja_stem_tasks +task: global_mmlu_full_ja_high_school_chemistry diff --git a/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_high_school_computer_science.yaml b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_high_school_computer_science.yaml new file mode 100644 index 00000000..c90e5fb7 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_high_school_computer_science.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ja_template_yaml +process_docs: !function utils.process_high_school_computer_science +tag: global_mmlu_full_ja_stem_tasks +task: global_mmlu_full_ja_high_school_computer_science diff --git a/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_high_school_european_history.yaml b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_high_school_european_history.yaml new file mode 100644 index 00000000..8318099a --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_high_school_european_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ja_template_yaml +process_docs: !function utils.process_high_school_european_history +tag: global_mmlu_full_ja_humanities_tasks +task: global_mmlu_full_ja_high_school_european_history diff --git a/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_high_school_geography.yaml b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_high_school_geography.yaml new file mode 100644 index 00000000..4ed5a620 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_high_school_geography.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ja_template_yaml +process_docs: !function utils.process_high_school_geography +tag: global_mmlu_full_ja_social_sciences_tasks +task: global_mmlu_full_ja_high_school_geography diff --git a/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_high_school_government_and_politics.yaml b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_high_school_government_and_politics.yaml new file mode 100644 index 00000000..6ec0ab84 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_high_school_government_and_politics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ja_template_yaml +process_docs: !function utils.process_high_school_government_and_politics +tag: global_mmlu_full_ja_social_sciences_tasks +task: global_mmlu_full_ja_high_school_government_and_politics diff --git a/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_high_school_macroeconomics.yaml b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_high_school_macroeconomics.yaml new file mode 100644 index 00000000..4bdd9555 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_high_school_macroeconomics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ja_template_yaml +process_docs: !function utils.process_high_school_macroeconomics +tag: global_mmlu_full_ja_social_sciences_tasks +task: global_mmlu_full_ja_high_school_macroeconomics diff --git a/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_high_school_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_high_school_mathematics.yaml new file mode 100644 index 00000000..3abfd81b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_high_school_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ja_template_yaml +process_docs: !function utils.process_high_school_mathematics +tag: global_mmlu_full_ja_stem_tasks +task: global_mmlu_full_ja_high_school_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_high_school_microeconomics.yaml b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_high_school_microeconomics.yaml new file mode 100644 index 00000000..483161a6 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_high_school_microeconomics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ja_template_yaml +process_docs: !function utils.process_high_school_microeconomics +tag: global_mmlu_full_ja_social_sciences_tasks +task: global_mmlu_full_ja_high_school_microeconomics diff --git a/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_high_school_physics.yaml b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_high_school_physics.yaml new file mode 100644 index 00000000..702092af --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_high_school_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ja_template_yaml +process_docs: !function utils.process_high_school_physics +tag: global_mmlu_full_ja_stem_tasks +task: global_mmlu_full_ja_high_school_physics diff --git a/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_high_school_psychology.yaml b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_high_school_psychology.yaml new file mode 100644 index 00000000..1b7ce92e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_high_school_psychology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ja_template_yaml +process_docs: !function utils.process_high_school_psychology +tag: global_mmlu_full_ja_social_sciences_tasks +task: global_mmlu_full_ja_high_school_psychology diff --git a/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_high_school_statistics.yaml b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_high_school_statistics.yaml new file mode 100644 index 00000000..c68acb8e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_high_school_statistics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ja_template_yaml +process_docs: !function utils.process_high_school_statistics +tag: global_mmlu_full_ja_stem_tasks +task: global_mmlu_full_ja_high_school_statistics diff --git a/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_high_school_us_history.yaml b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_high_school_us_history.yaml new file mode 100644 index 00000000..b1b91833 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_high_school_us_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ja_template_yaml +process_docs: !function utils.process_high_school_us_history +tag: global_mmlu_full_ja_humanities_tasks +task: global_mmlu_full_ja_high_school_us_history diff --git a/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_high_school_world_history.yaml b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_high_school_world_history.yaml new file mode 100644 index 00000000..2dee1f89 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_high_school_world_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ja_template_yaml +process_docs: !function utils.process_high_school_world_history +tag: global_mmlu_full_ja_humanities_tasks +task: global_mmlu_full_ja_high_school_world_history diff --git a/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_human_aging.yaml b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_human_aging.yaml new file mode 100644 index 00000000..3612a7ee --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_human_aging.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ja_template_yaml +process_docs: !function utils.process_human_aging +tag: global_mmlu_full_ja_other_tasks +task: global_mmlu_full_ja_human_aging diff --git a/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_human_sexuality.yaml b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_human_sexuality.yaml new file mode 100644 index 00000000..b70204fb --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_human_sexuality.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ja_template_yaml +process_docs: !function utils.process_human_sexuality +tag: global_mmlu_full_ja_social_sciences_tasks +task: global_mmlu_full_ja_human_sexuality diff --git a/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_international_law.yaml b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_international_law.yaml new file mode 100644 index 00000000..77ed3c97 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_international_law.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ja_template_yaml +process_docs: !function utils.process_international_law +tag: global_mmlu_full_ja_humanities_tasks +task: global_mmlu_full_ja_international_law diff --git a/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_jurisprudence.yaml b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_jurisprudence.yaml new file mode 100644 index 00000000..f8fbb261 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_jurisprudence.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ja_template_yaml +process_docs: !function utils.process_jurisprudence +tag: global_mmlu_full_ja_humanities_tasks +task: global_mmlu_full_ja_jurisprudence diff --git a/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_logical_fallacies.yaml b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_logical_fallacies.yaml new file mode 100644 index 00000000..58d4afcc --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_logical_fallacies.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ja_template_yaml +process_docs: !function utils.process_logical_fallacies +tag: global_mmlu_full_ja_humanities_tasks +task: global_mmlu_full_ja_logical_fallacies diff --git a/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_machine_learning.yaml b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_machine_learning.yaml new file mode 100644 index 00000000..e664390f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_machine_learning.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ja_template_yaml +process_docs: !function utils.process_machine_learning +tag: global_mmlu_full_ja_stem_tasks +task: global_mmlu_full_ja_machine_learning diff --git a/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_management.yaml b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_management.yaml new file mode 100644 index 00000000..cf495ae2 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_management.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ja_template_yaml +process_docs: !function utils.process_management +tag: global_mmlu_full_ja_other_tasks +task: global_mmlu_full_ja_management diff --git a/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_marketing.yaml b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_marketing.yaml new file mode 100644 index 00000000..1349771e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_marketing.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ja_template_yaml +process_docs: !function utils.process_marketing +tag: global_mmlu_full_ja_other_tasks +task: global_mmlu_full_ja_marketing diff --git a/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_medical_genetics.yaml b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_medical_genetics.yaml new file mode 100644 index 00000000..1b513ac4 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_medical_genetics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ja_template_yaml +process_docs: !function utils.process_medical_genetics +tag: global_mmlu_full_ja_other_tasks +task: global_mmlu_full_ja_medical_genetics diff --git a/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_miscellaneous.yaml b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_miscellaneous.yaml new file mode 100644 index 00000000..81659bf7 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_miscellaneous.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ja_template_yaml +process_docs: !function utils.process_miscellaneous +tag: global_mmlu_full_ja_other_tasks +task: global_mmlu_full_ja_miscellaneous diff --git a/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_moral_disputes.yaml b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_moral_disputes.yaml new file mode 100644 index 00000000..2e77694b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_moral_disputes.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ja_template_yaml +process_docs: !function utils.process_moral_disputes +tag: global_mmlu_full_ja_humanities_tasks +task: global_mmlu_full_ja_moral_disputes diff --git a/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_moral_scenarios.yaml b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_moral_scenarios.yaml new file mode 100644 index 00000000..f322376d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_moral_scenarios.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ja_template_yaml +process_docs: !function utils.process_moral_scenarios +tag: global_mmlu_full_ja_humanities_tasks +task: global_mmlu_full_ja_moral_scenarios diff --git a/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_nutrition.yaml b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_nutrition.yaml new file mode 100644 index 00000000..1d58fb0e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_nutrition.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ja_template_yaml +process_docs: !function utils.process_nutrition +tag: global_mmlu_full_ja_other_tasks +task: global_mmlu_full_ja_nutrition diff --git a/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_philosophy.yaml b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_philosophy.yaml new file mode 100644 index 00000000..23865361 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_philosophy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ja_template_yaml +process_docs: !function utils.process_philosophy +tag: global_mmlu_full_ja_humanities_tasks +task: global_mmlu_full_ja_philosophy diff --git a/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_prehistory.yaml b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_prehistory.yaml new file mode 100644 index 00000000..a044bf99 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_prehistory.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ja_template_yaml +process_docs: !function utils.process_prehistory +tag: global_mmlu_full_ja_humanities_tasks +task: global_mmlu_full_ja_prehistory diff --git a/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_professional_accounting.yaml b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_professional_accounting.yaml new file mode 100644 index 00000000..b828e0e2 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_professional_accounting.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ja_template_yaml +process_docs: !function utils.process_professional_accounting +tag: global_mmlu_full_ja_other_tasks +task: global_mmlu_full_ja_professional_accounting diff --git a/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_professional_law.yaml b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_professional_law.yaml new file mode 100644 index 00000000..7aafb6c4 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_professional_law.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ja_template_yaml +process_docs: !function utils.process_professional_law +tag: global_mmlu_full_ja_humanities_tasks +task: global_mmlu_full_ja_professional_law diff --git a/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_professional_medicine.yaml b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_professional_medicine.yaml new file mode 100644 index 00000000..b0cf9905 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_professional_medicine.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ja_template_yaml +process_docs: !function utils.process_professional_medicine +tag: global_mmlu_full_ja_other_tasks +task: global_mmlu_full_ja_professional_medicine diff --git a/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_professional_psychology.yaml b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_professional_psychology.yaml new file mode 100644 index 00000000..e5ef36c1 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_professional_psychology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ja_template_yaml +process_docs: !function utils.process_professional_psychology +tag: global_mmlu_full_ja_social_sciences_tasks +task: global_mmlu_full_ja_professional_psychology diff --git a/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_public_relations.yaml b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_public_relations.yaml new file mode 100644 index 00000000..565439e6 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_public_relations.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ja_template_yaml +process_docs: !function utils.process_public_relations +tag: global_mmlu_full_ja_social_sciences_tasks +task: global_mmlu_full_ja_public_relations diff --git a/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_security_studies.yaml b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_security_studies.yaml new file mode 100644 index 00000000..f7d21bd6 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_security_studies.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ja_template_yaml +process_docs: !function utils.process_security_studies +tag: global_mmlu_full_ja_social_sciences_tasks +task: global_mmlu_full_ja_security_studies diff --git a/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_sociology.yaml b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_sociology.yaml new file mode 100644 index 00000000..5cc44c1c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_sociology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ja_template_yaml +process_docs: !function utils.process_sociology +tag: global_mmlu_full_ja_social_sciences_tasks +task: global_mmlu_full_ja_sociology diff --git a/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_us_foreign_policy.yaml b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_us_foreign_policy.yaml new file mode 100644 index 00000000..8ebdb14a --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_us_foreign_policy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ja_template_yaml +process_docs: !function utils.process_us_foreign_policy +tag: global_mmlu_full_ja_social_sciences_tasks +task: global_mmlu_full_ja_us_foreign_policy diff --git a/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_virology.yaml b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_virology.yaml new file mode 100644 index 00000000..d6f83367 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_virology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ja_template_yaml +process_docs: !function utils.process_virology +tag: global_mmlu_full_ja_other_tasks +task: global_mmlu_full_ja_virology diff --git a/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_world_religions.yaml b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_world_religions.yaml new file mode 100644 index 00000000..23e66e06 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ja/global_mmlu_full_ja_world_religions.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ja_template_yaml +process_docs: !function utils.process_world_religions +tag: global_mmlu_full_ja_humanities_tasks +task: global_mmlu_full_ja_world_religions diff --git a/lm_eval/tasks/global_mmlu/full/ja/utils.py b/lm_eval/tasks/global_mmlu/full/ja/utils.py new file mode 100644 index 00000000..7df72cb0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ja/utils.py @@ -0,0 +1,73 @@ +from functools import partial + + +SUBJECTS = [ + "abstract_algebra", + "anatomy", + "astronomy", + "business_ethics", + "clinical_knowledge", + "college_biology", + "college_chemistry", + "college_computer_science", + "college_mathematics", + "college_medicine", + "college_physics", + "computer_security", + "conceptual_physics", + "econometrics", + "electrical_engineering", + "elementary_mathematics", + "formal_logic", + "global_facts", + "high_school_biology", + "high_school_chemistry", + "high_school_computer_science", + "high_school_european_history", + "high_school_geography", + "high_school_government_and_politics", + "high_school_macroeconomics", + "high_school_mathematics", + "high_school_microeconomics", + "high_school_physics", + "high_school_psychology", + "high_school_statistics", + "high_school_us_history", + "high_school_world_history", + "human_aging", + "human_sexuality", + "international_law", + "jurisprudence", + "logical_fallacies", + "machine_learning", + "management", + "marketing", + "medical_genetics", + "miscellaneous", + "moral_disputes", + "moral_scenarios", + "nutrition", + "philosophy", + "prehistory", + "professional_accounting", + "professional_law", + "professional_medicine", + "professional_psychology", + "public_relations", + "security_studies", + "sociology", + "us_foreign_policy", + "virology", + "world_religions", +] + + +def process_docs(dataset, subject): + return dataset.filter(lambda x: x["subject"] == subject) + + +process_functions = { + f"process_{subject}": partial(process_docs, subject=subject) for subject in SUBJECTS +} + +globals().update(process_functions) diff --git a/lm_eval/tasks/global_mmlu/full/ko/_global_mmlu_full_ko.yaml b/lm_eval/tasks/global_mmlu/full/ko/_global_mmlu_full_ko.yaml new file mode 100644 index 00000000..d2225e23 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ko/_global_mmlu_full_ko.yaml @@ -0,0 +1,11 @@ +group: global_mmlu_full_ko +task: + - global_mmlu_full_ko_stem + - global_mmlu_full_ko_other + - global_mmlu_full_ko_social_sciences + - global_mmlu_full_ko_humanities +aggregate_metric_list: + - metric: acc + weight_by_size: True +metadata: + version: 1.0 diff --git a/lm_eval/tasks/global_mmlu/full/ko/_global_mmlu_full_ko_humanities.yaml b/lm_eval/tasks/global_mmlu/full/ko/_global_mmlu_full_ko_humanities.yaml new file mode 100644 index 00000000..c7690643 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ko/_global_mmlu_full_ko_humanities.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_ko_humanities +task: + - global_mmlu_full_ko_humanities_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/ko/_global_mmlu_full_ko_other.yaml b/lm_eval/tasks/global_mmlu/full/ko/_global_mmlu_full_ko_other.yaml new file mode 100644 index 00000000..8990ae95 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ko/_global_mmlu_full_ko_other.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_ko_other +task: + - global_mmlu_full_ko_other_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/ko/_global_mmlu_full_ko_social_sciences.yaml b/lm_eval/tasks/global_mmlu/full/ko/_global_mmlu_full_ko_social_sciences.yaml new file mode 100644 index 00000000..0bbfad7f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ko/_global_mmlu_full_ko_social_sciences.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_ko_social_sciences +task: + - global_mmlu_full_ko_social_sciences_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/ko/_global_mmlu_full_ko_stem.yaml b/lm_eval/tasks/global_mmlu/full/ko/_global_mmlu_full_ko_stem.yaml new file mode 100644 index 00000000..18b7f17b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ko/_global_mmlu_full_ko_stem.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_ko_stem +task: + - global_mmlu_full_ko_stem_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/ko/_ko_template_yaml b/lm_eval/tasks/global_mmlu/full/ko/_ko_template_yaml new file mode 100644 index 00000000..11700a26 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ko/_ko_template_yaml @@ -0,0 +1,16 @@ +dataset_path: CohereForAI/Global-MMLU +dataset_name: ko +test_split: test +fewshot_split: dev +fewshot_config: + sampler: first_n +output_type: multiple_choice +doc_to_text: "{{question.strip()}}\nA. {{option_a}}\nB. {{option_b}}\nC. {{option_c}}\nD. {{option_d}}\nAnswer:" +doc_to_choice: ["A", "B", "C", "D"] +doc_to_target: answer +metric_list: + - metric: acc + aggregation: mean + higher_is_better: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_abstract_algebra.yaml b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_abstract_algebra.yaml new file mode 100644 index 00000000..5959d788 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_abstract_algebra.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ko_template_yaml +process_docs: !function utils.process_abstract_algebra +tag: global_mmlu_full_ko_stem_tasks +task: global_mmlu_full_ko_abstract_algebra diff --git a/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_anatomy.yaml b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_anatomy.yaml new file mode 100644 index 00000000..ebb90860 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_anatomy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ko_template_yaml +process_docs: !function utils.process_anatomy +tag: global_mmlu_full_ko_stem_tasks +task: global_mmlu_full_ko_anatomy diff --git a/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_astronomy.yaml b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_astronomy.yaml new file mode 100644 index 00000000..670846b3 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_astronomy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ko_template_yaml +process_docs: !function utils.process_astronomy +tag: global_mmlu_full_ko_stem_tasks +task: global_mmlu_full_ko_astronomy diff --git a/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_business_ethics.yaml b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_business_ethics.yaml new file mode 100644 index 00000000..1a44e430 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_business_ethics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ko_template_yaml +process_docs: !function utils.process_business_ethics +tag: global_mmlu_full_ko_other_tasks +task: global_mmlu_full_ko_business_ethics diff --git a/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_clinical_knowledge.yaml b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_clinical_knowledge.yaml new file mode 100644 index 00000000..e9e29697 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_clinical_knowledge.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ko_template_yaml +process_docs: !function utils.process_clinical_knowledge +tag: global_mmlu_full_ko_other_tasks +task: global_mmlu_full_ko_clinical_knowledge diff --git a/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_college_biology.yaml b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_college_biology.yaml new file mode 100644 index 00000000..fc364468 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_college_biology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ko_template_yaml +process_docs: !function utils.process_college_biology +tag: global_mmlu_full_ko_stem_tasks +task: global_mmlu_full_ko_college_biology diff --git a/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_college_chemistry.yaml b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_college_chemistry.yaml new file mode 100644 index 00000000..2eb0f416 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_college_chemistry.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ko_template_yaml +process_docs: !function utils.process_college_chemistry +tag: global_mmlu_full_ko_stem_tasks +task: global_mmlu_full_ko_college_chemistry diff --git a/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_college_computer_science.yaml b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_college_computer_science.yaml new file mode 100644 index 00000000..044f1eff --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_college_computer_science.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ko_template_yaml +process_docs: !function utils.process_college_computer_science +tag: global_mmlu_full_ko_stem_tasks +task: global_mmlu_full_ko_college_computer_science diff --git a/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_college_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_college_mathematics.yaml new file mode 100644 index 00000000..9929097c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_college_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ko_template_yaml +process_docs: !function utils.process_college_mathematics +tag: global_mmlu_full_ko_stem_tasks +task: global_mmlu_full_ko_college_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_college_medicine.yaml b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_college_medicine.yaml new file mode 100644 index 00000000..b78c24e6 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_college_medicine.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ko_template_yaml +process_docs: !function utils.process_college_medicine +tag: global_mmlu_full_ko_other_tasks +task: global_mmlu_full_ko_college_medicine diff --git a/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_college_physics.yaml b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_college_physics.yaml new file mode 100644 index 00000000..20c3fb20 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_college_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ko_template_yaml +process_docs: !function utils.process_college_physics +tag: global_mmlu_full_ko_stem_tasks +task: global_mmlu_full_ko_college_physics diff --git a/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_computer_security.yaml b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_computer_security.yaml new file mode 100644 index 00000000..1f954572 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_computer_security.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ko_template_yaml +process_docs: !function utils.process_computer_security +tag: global_mmlu_full_ko_stem_tasks +task: global_mmlu_full_ko_computer_security diff --git a/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_conceptual_physics.yaml b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_conceptual_physics.yaml new file mode 100644 index 00000000..f7998975 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_conceptual_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ko_template_yaml +process_docs: !function utils.process_conceptual_physics +tag: global_mmlu_full_ko_stem_tasks +task: global_mmlu_full_ko_conceptual_physics diff --git a/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_econometrics.yaml b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_econometrics.yaml new file mode 100644 index 00000000..79c35ed7 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_econometrics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ko_template_yaml +process_docs: !function utils.process_econometrics +tag: global_mmlu_full_ko_social_sciences_tasks +task: global_mmlu_full_ko_econometrics diff --git a/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_electrical_engineering.yaml b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_electrical_engineering.yaml new file mode 100644 index 00000000..1444a249 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_electrical_engineering.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ko_template_yaml +process_docs: !function utils.process_electrical_engineering +tag: global_mmlu_full_ko_stem_tasks +task: global_mmlu_full_ko_electrical_engineering diff --git a/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_elementary_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_elementary_mathematics.yaml new file mode 100644 index 00000000..8bec91b9 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_elementary_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ko_template_yaml +process_docs: !function utils.process_elementary_mathematics +tag: global_mmlu_full_ko_stem_tasks +task: global_mmlu_full_ko_elementary_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_formal_logic.yaml b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_formal_logic.yaml new file mode 100644 index 00000000..1cf31092 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_formal_logic.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ko_template_yaml +process_docs: !function utils.process_formal_logic +tag: global_mmlu_full_ko_humanities_tasks +task: global_mmlu_full_ko_formal_logic diff --git a/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_global_facts.yaml b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_global_facts.yaml new file mode 100644 index 00000000..2a5f7bd5 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_global_facts.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ko_template_yaml +process_docs: !function utils.process_global_facts +tag: global_mmlu_full_ko_other_tasks +task: global_mmlu_full_ko_global_facts diff --git a/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_high_school_biology.yaml b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_high_school_biology.yaml new file mode 100644 index 00000000..bdaed574 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_high_school_biology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ko_template_yaml +process_docs: !function utils.process_high_school_biology +tag: global_mmlu_full_ko_stem_tasks +task: global_mmlu_full_ko_high_school_biology diff --git a/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_high_school_chemistry.yaml b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_high_school_chemistry.yaml new file mode 100644 index 00000000..193a064c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_high_school_chemistry.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ko_template_yaml +process_docs: !function utils.process_high_school_chemistry +tag: global_mmlu_full_ko_stem_tasks +task: global_mmlu_full_ko_high_school_chemistry diff --git a/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_high_school_computer_science.yaml b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_high_school_computer_science.yaml new file mode 100644 index 00000000..2d2ad648 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_high_school_computer_science.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ko_template_yaml +process_docs: !function utils.process_high_school_computer_science +tag: global_mmlu_full_ko_stem_tasks +task: global_mmlu_full_ko_high_school_computer_science diff --git a/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_high_school_european_history.yaml b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_high_school_european_history.yaml new file mode 100644 index 00000000..a48b602d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_high_school_european_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ko_template_yaml +process_docs: !function utils.process_high_school_european_history +tag: global_mmlu_full_ko_humanities_tasks +task: global_mmlu_full_ko_high_school_european_history diff --git a/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_high_school_geography.yaml b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_high_school_geography.yaml new file mode 100644 index 00000000..cc9c20eb --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_high_school_geography.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ko_template_yaml +process_docs: !function utils.process_high_school_geography +tag: global_mmlu_full_ko_social_sciences_tasks +task: global_mmlu_full_ko_high_school_geography diff --git a/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_high_school_government_and_politics.yaml b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_high_school_government_and_politics.yaml new file mode 100644 index 00000000..e86a27fa --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_high_school_government_and_politics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ko_template_yaml +process_docs: !function utils.process_high_school_government_and_politics +tag: global_mmlu_full_ko_social_sciences_tasks +task: global_mmlu_full_ko_high_school_government_and_politics diff --git a/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_high_school_macroeconomics.yaml b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_high_school_macroeconomics.yaml new file mode 100644 index 00000000..4b947f7f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_high_school_macroeconomics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ko_template_yaml +process_docs: !function utils.process_high_school_macroeconomics +tag: global_mmlu_full_ko_social_sciences_tasks +task: global_mmlu_full_ko_high_school_macroeconomics diff --git a/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_high_school_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_high_school_mathematics.yaml new file mode 100644 index 00000000..9184ad9c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_high_school_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ko_template_yaml +process_docs: !function utils.process_high_school_mathematics +tag: global_mmlu_full_ko_stem_tasks +task: global_mmlu_full_ko_high_school_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_high_school_microeconomics.yaml b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_high_school_microeconomics.yaml new file mode 100644 index 00000000..50b6a150 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_high_school_microeconomics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ko_template_yaml +process_docs: !function utils.process_high_school_microeconomics +tag: global_mmlu_full_ko_social_sciences_tasks +task: global_mmlu_full_ko_high_school_microeconomics diff --git a/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_high_school_physics.yaml b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_high_school_physics.yaml new file mode 100644 index 00000000..974e3b03 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_high_school_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ko_template_yaml +process_docs: !function utils.process_high_school_physics +tag: global_mmlu_full_ko_stem_tasks +task: global_mmlu_full_ko_high_school_physics diff --git a/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_high_school_psychology.yaml b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_high_school_psychology.yaml new file mode 100644 index 00000000..e617e8cd --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_high_school_psychology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ko_template_yaml +process_docs: !function utils.process_high_school_psychology +tag: global_mmlu_full_ko_social_sciences_tasks +task: global_mmlu_full_ko_high_school_psychology diff --git a/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_high_school_statistics.yaml b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_high_school_statistics.yaml new file mode 100644 index 00000000..1a010596 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_high_school_statistics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ko_template_yaml +process_docs: !function utils.process_high_school_statistics +tag: global_mmlu_full_ko_stem_tasks +task: global_mmlu_full_ko_high_school_statistics diff --git a/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_high_school_us_history.yaml b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_high_school_us_history.yaml new file mode 100644 index 00000000..a696675d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_high_school_us_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ko_template_yaml +process_docs: !function utils.process_high_school_us_history +tag: global_mmlu_full_ko_humanities_tasks +task: global_mmlu_full_ko_high_school_us_history diff --git a/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_high_school_world_history.yaml b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_high_school_world_history.yaml new file mode 100644 index 00000000..eca86cbe --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_high_school_world_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ko_template_yaml +process_docs: !function utils.process_high_school_world_history +tag: global_mmlu_full_ko_humanities_tasks +task: global_mmlu_full_ko_high_school_world_history diff --git a/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_human_aging.yaml b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_human_aging.yaml new file mode 100644 index 00000000..69e3a2df --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_human_aging.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ko_template_yaml +process_docs: !function utils.process_human_aging +tag: global_mmlu_full_ko_other_tasks +task: global_mmlu_full_ko_human_aging diff --git a/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_human_sexuality.yaml b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_human_sexuality.yaml new file mode 100644 index 00000000..ed3e99fc --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_human_sexuality.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ko_template_yaml +process_docs: !function utils.process_human_sexuality +tag: global_mmlu_full_ko_social_sciences_tasks +task: global_mmlu_full_ko_human_sexuality diff --git a/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_international_law.yaml b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_international_law.yaml new file mode 100644 index 00000000..651f389c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_international_law.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ko_template_yaml +process_docs: !function utils.process_international_law +tag: global_mmlu_full_ko_humanities_tasks +task: global_mmlu_full_ko_international_law diff --git a/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_jurisprudence.yaml b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_jurisprudence.yaml new file mode 100644 index 00000000..001807eb --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_jurisprudence.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ko_template_yaml +process_docs: !function utils.process_jurisprudence +tag: global_mmlu_full_ko_humanities_tasks +task: global_mmlu_full_ko_jurisprudence diff --git a/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_logical_fallacies.yaml b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_logical_fallacies.yaml new file mode 100644 index 00000000..01eec477 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_logical_fallacies.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ko_template_yaml +process_docs: !function utils.process_logical_fallacies +tag: global_mmlu_full_ko_humanities_tasks +task: global_mmlu_full_ko_logical_fallacies diff --git a/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_machine_learning.yaml b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_machine_learning.yaml new file mode 100644 index 00000000..c1126c6b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_machine_learning.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ko_template_yaml +process_docs: !function utils.process_machine_learning +tag: global_mmlu_full_ko_stem_tasks +task: global_mmlu_full_ko_machine_learning diff --git a/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_management.yaml b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_management.yaml new file mode 100644 index 00000000..3b833270 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_management.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ko_template_yaml +process_docs: !function utils.process_management +tag: global_mmlu_full_ko_other_tasks +task: global_mmlu_full_ko_management diff --git a/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_marketing.yaml b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_marketing.yaml new file mode 100644 index 00000000..3cce25c0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_marketing.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ko_template_yaml +process_docs: !function utils.process_marketing +tag: global_mmlu_full_ko_other_tasks +task: global_mmlu_full_ko_marketing diff --git a/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_medical_genetics.yaml b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_medical_genetics.yaml new file mode 100644 index 00000000..65df1786 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_medical_genetics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ko_template_yaml +process_docs: !function utils.process_medical_genetics +tag: global_mmlu_full_ko_other_tasks +task: global_mmlu_full_ko_medical_genetics diff --git a/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_miscellaneous.yaml b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_miscellaneous.yaml new file mode 100644 index 00000000..04b71e2a --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_miscellaneous.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ko_template_yaml +process_docs: !function utils.process_miscellaneous +tag: global_mmlu_full_ko_other_tasks +task: global_mmlu_full_ko_miscellaneous diff --git a/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_moral_disputes.yaml b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_moral_disputes.yaml new file mode 100644 index 00000000..3f1e7fa1 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_moral_disputes.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ko_template_yaml +process_docs: !function utils.process_moral_disputes +tag: global_mmlu_full_ko_humanities_tasks +task: global_mmlu_full_ko_moral_disputes diff --git a/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_moral_scenarios.yaml b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_moral_scenarios.yaml new file mode 100644 index 00000000..c657543a --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_moral_scenarios.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ko_template_yaml +process_docs: !function utils.process_moral_scenarios +tag: global_mmlu_full_ko_humanities_tasks +task: global_mmlu_full_ko_moral_scenarios diff --git a/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_nutrition.yaml b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_nutrition.yaml new file mode 100644 index 00000000..dff6450f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_nutrition.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ko_template_yaml +process_docs: !function utils.process_nutrition +tag: global_mmlu_full_ko_other_tasks +task: global_mmlu_full_ko_nutrition diff --git a/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_philosophy.yaml b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_philosophy.yaml new file mode 100644 index 00000000..21f058af --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_philosophy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ko_template_yaml +process_docs: !function utils.process_philosophy +tag: global_mmlu_full_ko_humanities_tasks +task: global_mmlu_full_ko_philosophy diff --git a/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_prehistory.yaml b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_prehistory.yaml new file mode 100644 index 00000000..56aedae9 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_prehistory.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ko_template_yaml +process_docs: !function utils.process_prehistory +tag: global_mmlu_full_ko_humanities_tasks +task: global_mmlu_full_ko_prehistory diff --git a/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_professional_accounting.yaml b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_professional_accounting.yaml new file mode 100644 index 00000000..24f83b23 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_professional_accounting.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ko_template_yaml +process_docs: !function utils.process_professional_accounting +tag: global_mmlu_full_ko_other_tasks +task: global_mmlu_full_ko_professional_accounting diff --git a/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_professional_law.yaml b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_professional_law.yaml new file mode 100644 index 00000000..ece9dc5c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_professional_law.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ko_template_yaml +process_docs: !function utils.process_professional_law +tag: global_mmlu_full_ko_humanities_tasks +task: global_mmlu_full_ko_professional_law diff --git a/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_professional_medicine.yaml b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_professional_medicine.yaml new file mode 100644 index 00000000..43930957 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_professional_medicine.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ko_template_yaml +process_docs: !function utils.process_professional_medicine +tag: global_mmlu_full_ko_other_tasks +task: global_mmlu_full_ko_professional_medicine diff --git a/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_professional_psychology.yaml b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_professional_psychology.yaml new file mode 100644 index 00000000..98ff6520 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_professional_psychology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ko_template_yaml +process_docs: !function utils.process_professional_psychology +tag: global_mmlu_full_ko_social_sciences_tasks +task: global_mmlu_full_ko_professional_psychology diff --git a/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_public_relations.yaml b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_public_relations.yaml new file mode 100644 index 00000000..1a5b07f7 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_public_relations.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ko_template_yaml +process_docs: !function utils.process_public_relations +tag: global_mmlu_full_ko_social_sciences_tasks +task: global_mmlu_full_ko_public_relations diff --git a/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_security_studies.yaml b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_security_studies.yaml new file mode 100644 index 00000000..3663391a --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_security_studies.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ko_template_yaml +process_docs: !function utils.process_security_studies +tag: global_mmlu_full_ko_social_sciences_tasks +task: global_mmlu_full_ko_security_studies diff --git a/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_sociology.yaml b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_sociology.yaml new file mode 100644 index 00000000..902b4443 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_sociology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ko_template_yaml +process_docs: !function utils.process_sociology +tag: global_mmlu_full_ko_social_sciences_tasks +task: global_mmlu_full_ko_sociology diff --git a/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_us_foreign_policy.yaml b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_us_foreign_policy.yaml new file mode 100644 index 00000000..36e1794c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_us_foreign_policy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ko_template_yaml +process_docs: !function utils.process_us_foreign_policy +tag: global_mmlu_full_ko_social_sciences_tasks +task: global_mmlu_full_ko_us_foreign_policy diff --git a/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_virology.yaml b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_virology.yaml new file mode 100644 index 00000000..64b58d6a --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_virology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ko_template_yaml +process_docs: !function utils.process_virology +tag: global_mmlu_full_ko_other_tasks +task: global_mmlu_full_ko_virology diff --git a/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_world_religions.yaml b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_world_religions.yaml new file mode 100644 index 00000000..7289671f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ko/global_mmlu_full_ko_world_religions.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ko_template_yaml +process_docs: !function utils.process_world_religions +tag: global_mmlu_full_ko_humanities_tasks +task: global_mmlu_full_ko_world_religions diff --git a/lm_eval/tasks/global_mmlu/full/ko/utils.py b/lm_eval/tasks/global_mmlu/full/ko/utils.py new file mode 100644 index 00000000..7df72cb0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ko/utils.py @@ -0,0 +1,73 @@ +from functools import partial + + +SUBJECTS = [ + "abstract_algebra", + "anatomy", + "astronomy", + "business_ethics", + "clinical_knowledge", + "college_biology", + "college_chemistry", + "college_computer_science", + "college_mathematics", + "college_medicine", + "college_physics", + "computer_security", + "conceptual_physics", + "econometrics", + "electrical_engineering", + "elementary_mathematics", + "formal_logic", + "global_facts", + "high_school_biology", + "high_school_chemistry", + "high_school_computer_science", + "high_school_european_history", + "high_school_geography", + "high_school_government_and_politics", + "high_school_macroeconomics", + "high_school_mathematics", + "high_school_microeconomics", + "high_school_physics", + "high_school_psychology", + "high_school_statistics", + "high_school_us_history", + "high_school_world_history", + "human_aging", + "human_sexuality", + "international_law", + "jurisprudence", + "logical_fallacies", + "machine_learning", + "management", + "marketing", + "medical_genetics", + "miscellaneous", + "moral_disputes", + "moral_scenarios", + "nutrition", + "philosophy", + "prehistory", + "professional_accounting", + "professional_law", + "professional_medicine", + "professional_psychology", + "public_relations", + "security_studies", + "sociology", + "us_foreign_policy", + "virology", + "world_religions", +] + + +def process_docs(dataset, subject): + return dataset.filter(lambda x: x["subject"] == subject) + + +process_functions = { + f"process_{subject}": partial(process_docs, subject=subject) for subject in SUBJECTS +} + +globals().update(process_functions) diff --git a/lm_eval/tasks/global_mmlu/full/ky/_global_mmlu_full_ky.yaml b/lm_eval/tasks/global_mmlu/full/ky/_global_mmlu_full_ky.yaml new file mode 100644 index 00000000..4774599a --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ky/_global_mmlu_full_ky.yaml @@ -0,0 +1,11 @@ +group: global_mmlu_full_ky +task: + - global_mmlu_full_ky_stem + - global_mmlu_full_ky_other + - global_mmlu_full_ky_social_sciences + - global_mmlu_full_ky_humanities +aggregate_metric_list: + - metric: acc + weight_by_size: True +metadata: + version: 1.0 diff --git a/lm_eval/tasks/global_mmlu/full/ky/_global_mmlu_full_ky_humanities.yaml b/lm_eval/tasks/global_mmlu/full/ky/_global_mmlu_full_ky_humanities.yaml new file mode 100644 index 00000000..1e0368c2 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ky/_global_mmlu_full_ky_humanities.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_ky_humanities +task: + - global_mmlu_full_ky_humanities_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/ky/_global_mmlu_full_ky_other.yaml b/lm_eval/tasks/global_mmlu/full/ky/_global_mmlu_full_ky_other.yaml new file mode 100644 index 00000000..1bfc89ab --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ky/_global_mmlu_full_ky_other.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_ky_other +task: + - global_mmlu_full_ky_other_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/ky/_global_mmlu_full_ky_social_sciences.yaml b/lm_eval/tasks/global_mmlu/full/ky/_global_mmlu_full_ky_social_sciences.yaml new file mode 100644 index 00000000..3ae756c4 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ky/_global_mmlu_full_ky_social_sciences.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_ky_social_sciences +task: + - global_mmlu_full_ky_social_sciences_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/ky/_global_mmlu_full_ky_stem.yaml b/lm_eval/tasks/global_mmlu/full/ky/_global_mmlu_full_ky_stem.yaml new file mode 100644 index 00000000..817456fc --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ky/_global_mmlu_full_ky_stem.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_ky_stem +task: + - global_mmlu_full_ky_stem_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/ky/_ky_template_yaml b/lm_eval/tasks/global_mmlu/full/ky/_ky_template_yaml new file mode 100644 index 00000000..63f88823 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ky/_ky_template_yaml @@ -0,0 +1,16 @@ +dataset_path: CohereForAI/Global-MMLU +dataset_name: ky +test_split: test +fewshot_split: dev +fewshot_config: + sampler: first_n +output_type: multiple_choice +doc_to_text: "{{question.strip()}}\nA. {{option_a}}\nB. {{option_b}}\nC. {{option_c}}\nD. {{option_d}}\nAnswer:" +doc_to_choice: ["A", "B", "C", "D"] +doc_to_target: answer +metric_list: + - metric: acc + aggregation: mean + higher_is_better: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_abstract_algebra.yaml b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_abstract_algebra.yaml new file mode 100644 index 00000000..21338a56 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_abstract_algebra.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ky_template_yaml +process_docs: !function utils.process_abstract_algebra +tag: global_mmlu_full_ky_stem_tasks +task: global_mmlu_full_ky_abstract_algebra diff --git a/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_anatomy.yaml b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_anatomy.yaml new file mode 100644 index 00000000..df263548 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_anatomy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ky_template_yaml +process_docs: !function utils.process_anatomy +tag: global_mmlu_full_ky_stem_tasks +task: global_mmlu_full_ky_anatomy diff --git a/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_astronomy.yaml b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_astronomy.yaml new file mode 100644 index 00000000..5e0f6aba --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_astronomy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ky_template_yaml +process_docs: !function utils.process_astronomy +tag: global_mmlu_full_ky_stem_tasks +task: global_mmlu_full_ky_astronomy diff --git a/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_business_ethics.yaml b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_business_ethics.yaml new file mode 100644 index 00000000..17656dc6 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_business_ethics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ky_template_yaml +process_docs: !function utils.process_business_ethics +tag: global_mmlu_full_ky_other_tasks +task: global_mmlu_full_ky_business_ethics diff --git a/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_clinical_knowledge.yaml b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_clinical_knowledge.yaml new file mode 100644 index 00000000..8c053b88 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_clinical_knowledge.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ky_template_yaml +process_docs: !function utils.process_clinical_knowledge +tag: global_mmlu_full_ky_other_tasks +task: global_mmlu_full_ky_clinical_knowledge diff --git a/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_college_biology.yaml b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_college_biology.yaml new file mode 100644 index 00000000..36492106 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_college_biology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ky_template_yaml +process_docs: !function utils.process_college_biology +tag: global_mmlu_full_ky_stem_tasks +task: global_mmlu_full_ky_college_biology diff --git a/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_college_chemistry.yaml b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_college_chemistry.yaml new file mode 100644 index 00000000..cb9f8586 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_college_chemistry.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ky_template_yaml +process_docs: !function utils.process_college_chemistry +tag: global_mmlu_full_ky_stem_tasks +task: global_mmlu_full_ky_college_chemistry diff --git a/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_college_computer_science.yaml b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_college_computer_science.yaml new file mode 100644 index 00000000..e4b15b54 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_college_computer_science.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ky_template_yaml +process_docs: !function utils.process_college_computer_science +tag: global_mmlu_full_ky_stem_tasks +task: global_mmlu_full_ky_college_computer_science diff --git a/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_college_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_college_mathematics.yaml new file mode 100644 index 00000000..f5657b66 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_college_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ky_template_yaml +process_docs: !function utils.process_college_mathematics +tag: global_mmlu_full_ky_stem_tasks +task: global_mmlu_full_ky_college_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_college_medicine.yaml b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_college_medicine.yaml new file mode 100644 index 00000000..f1e0c25e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_college_medicine.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ky_template_yaml +process_docs: !function utils.process_college_medicine +tag: global_mmlu_full_ky_other_tasks +task: global_mmlu_full_ky_college_medicine diff --git a/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_college_physics.yaml b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_college_physics.yaml new file mode 100644 index 00000000..fac1d80f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_college_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ky_template_yaml +process_docs: !function utils.process_college_physics +tag: global_mmlu_full_ky_stem_tasks +task: global_mmlu_full_ky_college_physics diff --git a/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_computer_security.yaml b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_computer_security.yaml new file mode 100644 index 00000000..e35718d0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_computer_security.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ky_template_yaml +process_docs: !function utils.process_computer_security +tag: global_mmlu_full_ky_stem_tasks +task: global_mmlu_full_ky_computer_security diff --git a/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_conceptual_physics.yaml b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_conceptual_physics.yaml new file mode 100644 index 00000000..f165ec61 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_conceptual_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ky_template_yaml +process_docs: !function utils.process_conceptual_physics +tag: global_mmlu_full_ky_stem_tasks +task: global_mmlu_full_ky_conceptual_physics diff --git a/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_econometrics.yaml b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_econometrics.yaml new file mode 100644 index 00000000..48670c7f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_econometrics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ky_template_yaml +process_docs: !function utils.process_econometrics +tag: global_mmlu_full_ky_social_sciences_tasks +task: global_mmlu_full_ky_econometrics diff --git a/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_electrical_engineering.yaml b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_electrical_engineering.yaml new file mode 100644 index 00000000..29d24142 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_electrical_engineering.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ky_template_yaml +process_docs: !function utils.process_electrical_engineering +tag: global_mmlu_full_ky_stem_tasks +task: global_mmlu_full_ky_electrical_engineering diff --git a/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_elementary_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_elementary_mathematics.yaml new file mode 100644 index 00000000..9aa7f81b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_elementary_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ky_template_yaml +process_docs: !function utils.process_elementary_mathematics +tag: global_mmlu_full_ky_stem_tasks +task: global_mmlu_full_ky_elementary_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_formal_logic.yaml b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_formal_logic.yaml new file mode 100644 index 00000000..70a5bd86 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_formal_logic.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ky_template_yaml +process_docs: !function utils.process_formal_logic +tag: global_mmlu_full_ky_humanities_tasks +task: global_mmlu_full_ky_formal_logic diff --git a/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_global_facts.yaml b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_global_facts.yaml new file mode 100644 index 00000000..f678c0d1 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_global_facts.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ky_template_yaml +process_docs: !function utils.process_global_facts +tag: global_mmlu_full_ky_other_tasks +task: global_mmlu_full_ky_global_facts diff --git a/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_high_school_biology.yaml b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_high_school_biology.yaml new file mode 100644 index 00000000..750bc68b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_high_school_biology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ky_template_yaml +process_docs: !function utils.process_high_school_biology +tag: global_mmlu_full_ky_stem_tasks +task: global_mmlu_full_ky_high_school_biology diff --git a/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_high_school_chemistry.yaml b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_high_school_chemistry.yaml new file mode 100644 index 00000000..7700e37f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_high_school_chemistry.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ky_template_yaml +process_docs: !function utils.process_high_school_chemistry +tag: global_mmlu_full_ky_stem_tasks +task: global_mmlu_full_ky_high_school_chemistry diff --git a/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_high_school_computer_science.yaml b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_high_school_computer_science.yaml new file mode 100644 index 00000000..c805fc4e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_high_school_computer_science.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ky_template_yaml +process_docs: !function utils.process_high_school_computer_science +tag: global_mmlu_full_ky_stem_tasks +task: global_mmlu_full_ky_high_school_computer_science diff --git a/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_high_school_european_history.yaml b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_high_school_european_history.yaml new file mode 100644 index 00000000..01c67f8e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_high_school_european_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ky_template_yaml +process_docs: !function utils.process_high_school_european_history +tag: global_mmlu_full_ky_humanities_tasks +task: global_mmlu_full_ky_high_school_european_history diff --git a/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_high_school_geography.yaml b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_high_school_geography.yaml new file mode 100644 index 00000000..ccc5c8b7 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_high_school_geography.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ky_template_yaml +process_docs: !function utils.process_high_school_geography +tag: global_mmlu_full_ky_social_sciences_tasks +task: global_mmlu_full_ky_high_school_geography diff --git a/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_high_school_government_and_politics.yaml b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_high_school_government_and_politics.yaml new file mode 100644 index 00000000..02ea66ef --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_high_school_government_and_politics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ky_template_yaml +process_docs: !function utils.process_high_school_government_and_politics +tag: global_mmlu_full_ky_social_sciences_tasks +task: global_mmlu_full_ky_high_school_government_and_politics diff --git a/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_high_school_macroeconomics.yaml b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_high_school_macroeconomics.yaml new file mode 100644 index 00000000..f693296d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_high_school_macroeconomics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ky_template_yaml +process_docs: !function utils.process_high_school_macroeconomics +tag: global_mmlu_full_ky_social_sciences_tasks +task: global_mmlu_full_ky_high_school_macroeconomics diff --git a/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_high_school_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_high_school_mathematics.yaml new file mode 100644 index 00000000..b05e2799 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_high_school_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ky_template_yaml +process_docs: !function utils.process_high_school_mathematics +tag: global_mmlu_full_ky_stem_tasks +task: global_mmlu_full_ky_high_school_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_high_school_microeconomics.yaml b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_high_school_microeconomics.yaml new file mode 100644 index 00000000..d596290f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_high_school_microeconomics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ky_template_yaml +process_docs: !function utils.process_high_school_microeconomics +tag: global_mmlu_full_ky_social_sciences_tasks +task: global_mmlu_full_ky_high_school_microeconomics diff --git a/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_high_school_physics.yaml b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_high_school_physics.yaml new file mode 100644 index 00000000..3f71865c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_high_school_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ky_template_yaml +process_docs: !function utils.process_high_school_physics +tag: global_mmlu_full_ky_stem_tasks +task: global_mmlu_full_ky_high_school_physics diff --git a/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_high_school_psychology.yaml b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_high_school_psychology.yaml new file mode 100644 index 00000000..635873a1 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_high_school_psychology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ky_template_yaml +process_docs: !function utils.process_high_school_psychology +tag: global_mmlu_full_ky_social_sciences_tasks +task: global_mmlu_full_ky_high_school_psychology diff --git a/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_high_school_statistics.yaml b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_high_school_statistics.yaml new file mode 100644 index 00000000..df8cfefb --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_high_school_statistics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ky_template_yaml +process_docs: !function utils.process_high_school_statistics +tag: global_mmlu_full_ky_stem_tasks +task: global_mmlu_full_ky_high_school_statistics diff --git a/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_high_school_us_history.yaml b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_high_school_us_history.yaml new file mode 100644 index 00000000..3c75f534 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_high_school_us_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ky_template_yaml +process_docs: !function utils.process_high_school_us_history +tag: global_mmlu_full_ky_humanities_tasks +task: global_mmlu_full_ky_high_school_us_history diff --git a/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_high_school_world_history.yaml b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_high_school_world_history.yaml new file mode 100644 index 00000000..e73edcbe --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_high_school_world_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ky_template_yaml +process_docs: !function utils.process_high_school_world_history +tag: global_mmlu_full_ky_humanities_tasks +task: global_mmlu_full_ky_high_school_world_history diff --git a/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_human_aging.yaml b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_human_aging.yaml new file mode 100644 index 00000000..f4e662a5 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_human_aging.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ky_template_yaml +process_docs: !function utils.process_human_aging +tag: global_mmlu_full_ky_other_tasks +task: global_mmlu_full_ky_human_aging diff --git a/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_human_sexuality.yaml b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_human_sexuality.yaml new file mode 100644 index 00000000..8c2556da --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_human_sexuality.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ky_template_yaml +process_docs: !function utils.process_human_sexuality +tag: global_mmlu_full_ky_social_sciences_tasks +task: global_mmlu_full_ky_human_sexuality diff --git a/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_international_law.yaml b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_international_law.yaml new file mode 100644 index 00000000..2af16190 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_international_law.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ky_template_yaml +process_docs: !function utils.process_international_law +tag: global_mmlu_full_ky_humanities_tasks +task: global_mmlu_full_ky_international_law diff --git a/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_jurisprudence.yaml b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_jurisprudence.yaml new file mode 100644 index 00000000..f0994cc2 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_jurisprudence.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ky_template_yaml +process_docs: !function utils.process_jurisprudence +tag: global_mmlu_full_ky_humanities_tasks +task: global_mmlu_full_ky_jurisprudence diff --git a/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_logical_fallacies.yaml b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_logical_fallacies.yaml new file mode 100644 index 00000000..f7933a77 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_logical_fallacies.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ky_template_yaml +process_docs: !function utils.process_logical_fallacies +tag: global_mmlu_full_ky_humanities_tasks +task: global_mmlu_full_ky_logical_fallacies diff --git a/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_machine_learning.yaml b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_machine_learning.yaml new file mode 100644 index 00000000..f6e525a1 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_machine_learning.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ky_template_yaml +process_docs: !function utils.process_machine_learning +tag: global_mmlu_full_ky_stem_tasks +task: global_mmlu_full_ky_machine_learning diff --git a/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_management.yaml b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_management.yaml new file mode 100644 index 00000000..03f70aa0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_management.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ky_template_yaml +process_docs: !function utils.process_management +tag: global_mmlu_full_ky_other_tasks +task: global_mmlu_full_ky_management diff --git a/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_marketing.yaml b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_marketing.yaml new file mode 100644 index 00000000..72ced798 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_marketing.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ky_template_yaml +process_docs: !function utils.process_marketing +tag: global_mmlu_full_ky_other_tasks +task: global_mmlu_full_ky_marketing diff --git a/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_medical_genetics.yaml b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_medical_genetics.yaml new file mode 100644 index 00000000..371e4b21 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_medical_genetics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ky_template_yaml +process_docs: !function utils.process_medical_genetics +tag: global_mmlu_full_ky_other_tasks +task: global_mmlu_full_ky_medical_genetics diff --git a/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_miscellaneous.yaml b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_miscellaneous.yaml new file mode 100644 index 00000000..e693ab8b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_miscellaneous.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ky_template_yaml +process_docs: !function utils.process_miscellaneous +tag: global_mmlu_full_ky_other_tasks +task: global_mmlu_full_ky_miscellaneous diff --git a/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_moral_disputes.yaml b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_moral_disputes.yaml new file mode 100644 index 00000000..ccafcb1e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_moral_disputes.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ky_template_yaml +process_docs: !function utils.process_moral_disputes +tag: global_mmlu_full_ky_humanities_tasks +task: global_mmlu_full_ky_moral_disputes diff --git a/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_moral_scenarios.yaml b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_moral_scenarios.yaml new file mode 100644 index 00000000..16c19b29 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_moral_scenarios.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ky_template_yaml +process_docs: !function utils.process_moral_scenarios +tag: global_mmlu_full_ky_humanities_tasks +task: global_mmlu_full_ky_moral_scenarios diff --git a/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_nutrition.yaml b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_nutrition.yaml new file mode 100644 index 00000000..f6c00cb0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_nutrition.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ky_template_yaml +process_docs: !function utils.process_nutrition +tag: global_mmlu_full_ky_other_tasks +task: global_mmlu_full_ky_nutrition diff --git a/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_philosophy.yaml b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_philosophy.yaml new file mode 100644 index 00000000..6d6d242b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_philosophy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ky_template_yaml +process_docs: !function utils.process_philosophy +tag: global_mmlu_full_ky_humanities_tasks +task: global_mmlu_full_ky_philosophy diff --git a/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_prehistory.yaml b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_prehistory.yaml new file mode 100644 index 00000000..4ff2e08d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_prehistory.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ky_template_yaml +process_docs: !function utils.process_prehistory +tag: global_mmlu_full_ky_humanities_tasks +task: global_mmlu_full_ky_prehistory diff --git a/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_professional_accounting.yaml b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_professional_accounting.yaml new file mode 100644 index 00000000..37c6a892 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_professional_accounting.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ky_template_yaml +process_docs: !function utils.process_professional_accounting +tag: global_mmlu_full_ky_other_tasks +task: global_mmlu_full_ky_professional_accounting diff --git a/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_professional_law.yaml b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_professional_law.yaml new file mode 100644 index 00000000..9b4fea0e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_professional_law.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ky_template_yaml +process_docs: !function utils.process_professional_law +tag: global_mmlu_full_ky_humanities_tasks +task: global_mmlu_full_ky_professional_law diff --git a/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_professional_medicine.yaml b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_professional_medicine.yaml new file mode 100644 index 00000000..8a6ef0b5 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_professional_medicine.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ky_template_yaml +process_docs: !function utils.process_professional_medicine +tag: global_mmlu_full_ky_other_tasks +task: global_mmlu_full_ky_professional_medicine diff --git a/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_professional_psychology.yaml b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_professional_psychology.yaml new file mode 100644 index 00000000..dce1b6d2 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_professional_psychology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ky_template_yaml +process_docs: !function utils.process_professional_psychology +tag: global_mmlu_full_ky_social_sciences_tasks +task: global_mmlu_full_ky_professional_psychology diff --git a/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_public_relations.yaml b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_public_relations.yaml new file mode 100644 index 00000000..168cae74 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_public_relations.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ky_template_yaml +process_docs: !function utils.process_public_relations +tag: global_mmlu_full_ky_social_sciences_tasks +task: global_mmlu_full_ky_public_relations diff --git a/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_security_studies.yaml b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_security_studies.yaml new file mode 100644 index 00000000..1e24b816 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_security_studies.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ky_template_yaml +process_docs: !function utils.process_security_studies +tag: global_mmlu_full_ky_social_sciences_tasks +task: global_mmlu_full_ky_security_studies diff --git a/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_sociology.yaml b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_sociology.yaml new file mode 100644 index 00000000..7d1ad959 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_sociology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ky_template_yaml +process_docs: !function utils.process_sociology +tag: global_mmlu_full_ky_social_sciences_tasks +task: global_mmlu_full_ky_sociology diff --git a/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_us_foreign_policy.yaml b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_us_foreign_policy.yaml new file mode 100644 index 00000000..36cd7e20 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_us_foreign_policy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ky_template_yaml +process_docs: !function utils.process_us_foreign_policy +tag: global_mmlu_full_ky_social_sciences_tasks +task: global_mmlu_full_ky_us_foreign_policy diff --git a/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_virology.yaml b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_virology.yaml new file mode 100644 index 00000000..e2a77915 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_virology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ky_template_yaml +process_docs: !function utils.process_virology +tag: global_mmlu_full_ky_other_tasks +task: global_mmlu_full_ky_virology diff --git a/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_world_religions.yaml b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_world_religions.yaml new file mode 100644 index 00000000..563c1397 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ky/global_mmlu_full_ky_world_religions.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ky_template_yaml +process_docs: !function utils.process_world_religions +tag: global_mmlu_full_ky_humanities_tasks +task: global_mmlu_full_ky_world_religions diff --git a/lm_eval/tasks/global_mmlu/full/ky/utils.py b/lm_eval/tasks/global_mmlu/full/ky/utils.py new file mode 100644 index 00000000..7df72cb0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ky/utils.py @@ -0,0 +1,73 @@ +from functools import partial + + +SUBJECTS = [ + "abstract_algebra", + "anatomy", + "astronomy", + "business_ethics", + "clinical_knowledge", + "college_biology", + "college_chemistry", + "college_computer_science", + "college_mathematics", + "college_medicine", + "college_physics", + "computer_security", + "conceptual_physics", + "econometrics", + "electrical_engineering", + "elementary_mathematics", + "formal_logic", + "global_facts", + "high_school_biology", + "high_school_chemistry", + "high_school_computer_science", + "high_school_european_history", + "high_school_geography", + "high_school_government_and_politics", + "high_school_macroeconomics", + "high_school_mathematics", + "high_school_microeconomics", + "high_school_physics", + "high_school_psychology", + "high_school_statistics", + "high_school_us_history", + "high_school_world_history", + "human_aging", + "human_sexuality", + "international_law", + "jurisprudence", + "logical_fallacies", + "machine_learning", + "management", + "marketing", + "medical_genetics", + "miscellaneous", + "moral_disputes", + "moral_scenarios", + "nutrition", + "philosophy", + "prehistory", + "professional_accounting", + "professional_law", + "professional_medicine", + "professional_psychology", + "public_relations", + "security_studies", + "sociology", + "us_foreign_policy", + "virology", + "world_religions", +] + + +def process_docs(dataset, subject): + return dataset.filter(lambda x: x["subject"] == subject) + + +process_functions = { + f"process_{subject}": partial(process_docs, subject=subject) for subject in SUBJECTS +} + +globals().update(process_functions) diff --git a/lm_eval/tasks/global_mmlu/full/lt/_global_mmlu_full_lt.yaml b/lm_eval/tasks/global_mmlu/full/lt/_global_mmlu_full_lt.yaml new file mode 100644 index 00000000..93929d42 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/lt/_global_mmlu_full_lt.yaml @@ -0,0 +1,11 @@ +group: global_mmlu_full_lt +task: + - global_mmlu_full_lt_stem + - global_mmlu_full_lt_other + - global_mmlu_full_lt_social_sciences + - global_mmlu_full_lt_humanities +aggregate_metric_list: + - metric: acc + weight_by_size: True +metadata: + version: 1.0 diff --git a/lm_eval/tasks/global_mmlu/full/lt/_global_mmlu_full_lt_humanities.yaml b/lm_eval/tasks/global_mmlu/full/lt/_global_mmlu_full_lt_humanities.yaml new file mode 100644 index 00000000..48ad351f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/lt/_global_mmlu_full_lt_humanities.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_lt_humanities +task: + - global_mmlu_full_lt_humanities_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/lt/_global_mmlu_full_lt_other.yaml b/lm_eval/tasks/global_mmlu/full/lt/_global_mmlu_full_lt_other.yaml new file mode 100644 index 00000000..8f63c35a --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/lt/_global_mmlu_full_lt_other.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_lt_other +task: + - global_mmlu_full_lt_other_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/lt/_global_mmlu_full_lt_social_sciences.yaml b/lm_eval/tasks/global_mmlu/full/lt/_global_mmlu_full_lt_social_sciences.yaml new file mode 100644 index 00000000..9ababd6d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/lt/_global_mmlu_full_lt_social_sciences.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_lt_social_sciences +task: + - global_mmlu_full_lt_social_sciences_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/lt/_global_mmlu_full_lt_stem.yaml b/lm_eval/tasks/global_mmlu/full/lt/_global_mmlu_full_lt_stem.yaml new file mode 100644 index 00000000..1a59e683 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/lt/_global_mmlu_full_lt_stem.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_lt_stem +task: + - global_mmlu_full_lt_stem_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/lt/_lt_template_yaml b/lm_eval/tasks/global_mmlu/full/lt/_lt_template_yaml new file mode 100644 index 00000000..8b925338 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/lt/_lt_template_yaml @@ -0,0 +1,16 @@ +dataset_path: CohereForAI/Global-MMLU +dataset_name: lt +test_split: test +fewshot_split: dev +fewshot_config: + sampler: first_n +output_type: multiple_choice +doc_to_text: "{{question.strip()}}\nA. {{option_a}}\nB. {{option_b}}\nC. {{option_c}}\nD. {{option_d}}\nAnswer:" +doc_to_choice: ["A", "B", "C", "D"] +doc_to_target: answer +metric_list: + - metric: acc + aggregation: mean + higher_is_better: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_abstract_algebra.yaml b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_abstract_algebra.yaml new file mode 100644 index 00000000..76b96844 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_abstract_algebra.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _lt_template_yaml +process_docs: !function utils.process_abstract_algebra +tag: global_mmlu_full_lt_stem_tasks +task: global_mmlu_full_lt_abstract_algebra diff --git a/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_anatomy.yaml b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_anatomy.yaml new file mode 100644 index 00000000..527c7107 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_anatomy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _lt_template_yaml +process_docs: !function utils.process_anatomy +tag: global_mmlu_full_lt_stem_tasks +task: global_mmlu_full_lt_anatomy diff --git a/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_astronomy.yaml b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_astronomy.yaml new file mode 100644 index 00000000..419b89e3 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_astronomy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _lt_template_yaml +process_docs: !function utils.process_astronomy +tag: global_mmlu_full_lt_stem_tasks +task: global_mmlu_full_lt_astronomy diff --git a/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_business_ethics.yaml b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_business_ethics.yaml new file mode 100644 index 00000000..c51daa22 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_business_ethics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _lt_template_yaml +process_docs: !function utils.process_business_ethics +tag: global_mmlu_full_lt_other_tasks +task: global_mmlu_full_lt_business_ethics diff --git a/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_clinical_knowledge.yaml b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_clinical_knowledge.yaml new file mode 100644 index 00000000..e0232774 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_clinical_knowledge.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _lt_template_yaml +process_docs: !function utils.process_clinical_knowledge +tag: global_mmlu_full_lt_other_tasks +task: global_mmlu_full_lt_clinical_knowledge diff --git a/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_college_biology.yaml b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_college_biology.yaml new file mode 100644 index 00000000..c6fea6f8 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_college_biology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _lt_template_yaml +process_docs: !function utils.process_college_biology +tag: global_mmlu_full_lt_stem_tasks +task: global_mmlu_full_lt_college_biology diff --git a/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_college_chemistry.yaml b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_college_chemistry.yaml new file mode 100644 index 00000000..93b9a561 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_college_chemistry.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _lt_template_yaml +process_docs: !function utils.process_college_chemistry +tag: global_mmlu_full_lt_stem_tasks +task: global_mmlu_full_lt_college_chemistry diff --git a/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_college_computer_science.yaml b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_college_computer_science.yaml new file mode 100644 index 00000000..8d0dcfdd --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_college_computer_science.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _lt_template_yaml +process_docs: !function utils.process_college_computer_science +tag: global_mmlu_full_lt_stem_tasks +task: global_mmlu_full_lt_college_computer_science diff --git a/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_college_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_college_mathematics.yaml new file mode 100644 index 00000000..8d33b747 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_college_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _lt_template_yaml +process_docs: !function utils.process_college_mathematics +tag: global_mmlu_full_lt_stem_tasks +task: global_mmlu_full_lt_college_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_college_medicine.yaml b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_college_medicine.yaml new file mode 100644 index 00000000..ad74dbb1 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_college_medicine.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _lt_template_yaml +process_docs: !function utils.process_college_medicine +tag: global_mmlu_full_lt_other_tasks +task: global_mmlu_full_lt_college_medicine diff --git a/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_college_physics.yaml b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_college_physics.yaml new file mode 100644 index 00000000..3c69754b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_college_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _lt_template_yaml +process_docs: !function utils.process_college_physics +tag: global_mmlu_full_lt_stem_tasks +task: global_mmlu_full_lt_college_physics diff --git a/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_computer_security.yaml b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_computer_security.yaml new file mode 100644 index 00000000..d78f3a54 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_computer_security.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _lt_template_yaml +process_docs: !function utils.process_computer_security +tag: global_mmlu_full_lt_stem_tasks +task: global_mmlu_full_lt_computer_security diff --git a/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_conceptual_physics.yaml b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_conceptual_physics.yaml new file mode 100644 index 00000000..3e7b5e49 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_conceptual_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _lt_template_yaml +process_docs: !function utils.process_conceptual_physics +tag: global_mmlu_full_lt_stem_tasks +task: global_mmlu_full_lt_conceptual_physics diff --git a/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_econometrics.yaml b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_econometrics.yaml new file mode 100644 index 00000000..6d0085ab --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_econometrics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _lt_template_yaml +process_docs: !function utils.process_econometrics +tag: global_mmlu_full_lt_social_sciences_tasks +task: global_mmlu_full_lt_econometrics diff --git a/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_electrical_engineering.yaml b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_electrical_engineering.yaml new file mode 100644 index 00000000..284dfe9e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_electrical_engineering.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _lt_template_yaml +process_docs: !function utils.process_electrical_engineering +tag: global_mmlu_full_lt_stem_tasks +task: global_mmlu_full_lt_electrical_engineering diff --git a/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_elementary_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_elementary_mathematics.yaml new file mode 100644 index 00000000..7e9a0103 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_elementary_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _lt_template_yaml +process_docs: !function utils.process_elementary_mathematics +tag: global_mmlu_full_lt_stem_tasks +task: global_mmlu_full_lt_elementary_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_formal_logic.yaml b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_formal_logic.yaml new file mode 100644 index 00000000..ec9a665b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_formal_logic.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _lt_template_yaml +process_docs: !function utils.process_formal_logic +tag: global_mmlu_full_lt_humanities_tasks +task: global_mmlu_full_lt_formal_logic diff --git a/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_global_facts.yaml b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_global_facts.yaml new file mode 100644 index 00000000..d81a9470 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_global_facts.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _lt_template_yaml +process_docs: !function utils.process_global_facts +tag: global_mmlu_full_lt_other_tasks +task: global_mmlu_full_lt_global_facts diff --git a/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_high_school_biology.yaml b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_high_school_biology.yaml new file mode 100644 index 00000000..139376cc --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_high_school_biology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _lt_template_yaml +process_docs: !function utils.process_high_school_biology +tag: global_mmlu_full_lt_stem_tasks +task: global_mmlu_full_lt_high_school_biology diff --git a/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_high_school_chemistry.yaml b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_high_school_chemistry.yaml new file mode 100644 index 00000000..87112d8c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_high_school_chemistry.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _lt_template_yaml +process_docs: !function utils.process_high_school_chemistry +tag: global_mmlu_full_lt_stem_tasks +task: global_mmlu_full_lt_high_school_chemistry diff --git a/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_high_school_computer_science.yaml b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_high_school_computer_science.yaml new file mode 100644 index 00000000..2324bb28 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_high_school_computer_science.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _lt_template_yaml +process_docs: !function utils.process_high_school_computer_science +tag: global_mmlu_full_lt_stem_tasks +task: global_mmlu_full_lt_high_school_computer_science diff --git a/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_high_school_european_history.yaml b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_high_school_european_history.yaml new file mode 100644 index 00000000..5f365fab --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_high_school_european_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _lt_template_yaml +process_docs: !function utils.process_high_school_european_history +tag: global_mmlu_full_lt_humanities_tasks +task: global_mmlu_full_lt_high_school_european_history diff --git a/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_high_school_geography.yaml b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_high_school_geography.yaml new file mode 100644 index 00000000..e3a6f921 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_high_school_geography.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _lt_template_yaml +process_docs: !function utils.process_high_school_geography +tag: global_mmlu_full_lt_social_sciences_tasks +task: global_mmlu_full_lt_high_school_geography diff --git a/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_high_school_government_and_politics.yaml b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_high_school_government_and_politics.yaml new file mode 100644 index 00000000..526b68ed --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_high_school_government_and_politics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _lt_template_yaml +process_docs: !function utils.process_high_school_government_and_politics +tag: global_mmlu_full_lt_social_sciences_tasks +task: global_mmlu_full_lt_high_school_government_and_politics diff --git a/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_high_school_macroeconomics.yaml b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_high_school_macroeconomics.yaml new file mode 100644 index 00000000..e14b1dce --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_high_school_macroeconomics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _lt_template_yaml +process_docs: !function utils.process_high_school_macroeconomics +tag: global_mmlu_full_lt_social_sciences_tasks +task: global_mmlu_full_lt_high_school_macroeconomics diff --git a/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_high_school_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_high_school_mathematics.yaml new file mode 100644 index 00000000..1cdf5c90 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_high_school_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _lt_template_yaml +process_docs: !function utils.process_high_school_mathematics +tag: global_mmlu_full_lt_stem_tasks +task: global_mmlu_full_lt_high_school_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_high_school_microeconomics.yaml b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_high_school_microeconomics.yaml new file mode 100644 index 00000000..a2f2a210 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_high_school_microeconomics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _lt_template_yaml +process_docs: !function utils.process_high_school_microeconomics +tag: global_mmlu_full_lt_social_sciences_tasks +task: global_mmlu_full_lt_high_school_microeconomics diff --git a/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_high_school_physics.yaml b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_high_school_physics.yaml new file mode 100644 index 00000000..bd363709 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_high_school_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _lt_template_yaml +process_docs: !function utils.process_high_school_physics +tag: global_mmlu_full_lt_stem_tasks +task: global_mmlu_full_lt_high_school_physics diff --git a/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_high_school_psychology.yaml b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_high_school_psychology.yaml new file mode 100644 index 00000000..aad65a13 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_high_school_psychology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _lt_template_yaml +process_docs: !function utils.process_high_school_psychology +tag: global_mmlu_full_lt_social_sciences_tasks +task: global_mmlu_full_lt_high_school_psychology diff --git a/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_high_school_statistics.yaml b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_high_school_statistics.yaml new file mode 100644 index 00000000..6dd6d699 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_high_school_statistics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _lt_template_yaml +process_docs: !function utils.process_high_school_statistics +tag: global_mmlu_full_lt_stem_tasks +task: global_mmlu_full_lt_high_school_statistics diff --git a/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_high_school_us_history.yaml b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_high_school_us_history.yaml new file mode 100644 index 00000000..5fb0ee1e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_high_school_us_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _lt_template_yaml +process_docs: !function utils.process_high_school_us_history +tag: global_mmlu_full_lt_humanities_tasks +task: global_mmlu_full_lt_high_school_us_history diff --git a/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_high_school_world_history.yaml b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_high_school_world_history.yaml new file mode 100644 index 00000000..75f2769a --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_high_school_world_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _lt_template_yaml +process_docs: !function utils.process_high_school_world_history +tag: global_mmlu_full_lt_humanities_tasks +task: global_mmlu_full_lt_high_school_world_history diff --git a/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_human_aging.yaml b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_human_aging.yaml new file mode 100644 index 00000000..beb27e9b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_human_aging.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _lt_template_yaml +process_docs: !function utils.process_human_aging +tag: global_mmlu_full_lt_other_tasks +task: global_mmlu_full_lt_human_aging diff --git a/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_human_sexuality.yaml b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_human_sexuality.yaml new file mode 100644 index 00000000..c9d952c3 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_human_sexuality.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _lt_template_yaml +process_docs: !function utils.process_human_sexuality +tag: global_mmlu_full_lt_social_sciences_tasks +task: global_mmlu_full_lt_human_sexuality diff --git a/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_international_law.yaml b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_international_law.yaml new file mode 100644 index 00000000..f77adf9b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_international_law.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _lt_template_yaml +process_docs: !function utils.process_international_law +tag: global_mmlu_full_lt_humanities_tasks +task: global_mmlu_full_lt_international_law diff --git a/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_jurisprudence.yaml b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_jurisprudence.yaml new file mode 100644 index 00000000..e6be84fd --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_jurisprudence.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _lt_template_yaml +process_docs: !function utils.process_jurisprudence +tag: global_mmlu_full_lt_humanities_tasks +task: global_mmlu_full_lt_jurisprudence diff --git a/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_logical_fallacies.yaml b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_logical_fallacies.yaml new file mode 100644 index 00000000..ad597b27 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_logical_fallacies.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _lt_template_yaml +process_docs: !function utils.process_logical_fallacies +tag: global_mmlu_full_lt_humanities_tasks +task: global_mmlu_full_lt_logical_fallacies diff --git a/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_machine_learning.yaml b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_machine_learning.yaml new file mode 100644 index 00000000..eb06a871 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_machine_learning.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _lt_template_yaml +process_docs: !function utils.process_machine_learning +tag: global_mmlu_full_lt_stem_tasks +task: global_mmlu_full_lt_machine_learning diff --git a/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_management.yaml b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_management.yaml new file mode 100644 index 00000000..e1885ad3 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_management.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _lt_template_yaml +process_docs: !function utils.process_management +tag: global_mmlu_full_lt_other_tasks +task: global_mmlu_full_lt_management diff --git a/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_marketing.yaml b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_marketing.yaml new file mode 100644 index 00000000..2dc83089 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_marketing.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _lt_template_yaml +process_docs: !function utils.process_marketing +tag: global_mmlu_full_lt_other_tasks +task: global_mmlu_full_lt_marketing diff --git a/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_medical_genetics.yaml b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_medical_genetics.yaml new file mode 100644 index 00000000..b67d321e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_medical_genetics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _lt_template_yaml +process_docs: !function utils.process_medical_genetics +tag: global_mmlu_full_lt_other_tasks +task: global_mmlu_full_lt_medical_genetics diff --git a/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_miscellaneous.yaml b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_miscellaneous.yaml new file mode 100644 index 00000000..2c744613 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_miscellaneous.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _lt_template_yaml +process_docs: !function utils.process_miscellaneous +tag: global_mmlu_full_lt_other_tasks +task: global_mmlu_full_lt_miscellaneous diff --git a/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_moral_disputes.yaml b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_moral_disputes.yaml new file mode 100644 index 00000000..09e6f044 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_moral_disputes.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _lt_template_yaml +process_docs: !function utils.process_moral_disputes +tag: global_mmlu_full_lt_humanities_tasks +task: global_mmlu_full_lt_moral_disputes diff --git a/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_moral_scenarios.yaml b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_moral_scenarios.yaml new file mode 100644 index 00000000..bb8dd330 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_moral_scenarios.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _lt_template_yaml +process_docs: !function utils.process_moral_scenarios +tag: global_mmlu_full_lt_humanities_tasks +task: global_mmlu_full_lt_moral_scenarios diff --git a/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_nutrition.yaml b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_nutrition.yaml new file mode 100644 index 00000000..0b1a8556 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_nutrition.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _lt_template_yaml +process_docs: !function utils.process_nutrition +tag: global_mmlu_full_lt_other_tasks +task: global_mmlu_full_lt_nutrition diff --git a/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_philosophy.yaml b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_philosophy.yaml new file mode 100644 index 00000000..aab1d556 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_philosophy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _lt_template_yaml +process_docs: !function utils.process_philosophy +tag: global_mmlu_full_lt_humanities_tasks +task: global_mmlu_full_lt_philosophy diff --git a/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_prehistory.yaml b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_prehistory.yaml new file mode 100644 index 00000000..ac93dd6c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_prehistory.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _lt_template_yaml +process_docs: !function utils.process_prehistory +tag: global_mmlu_full_lt_humanities_tasks +task: global_mmlu_full_lt_prehistory diff --git a/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_professional_accounting.yaml b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_professional_accounting.yaml new file mode 100644 index 00000000..6be78ec3 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_professional_accounting.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _lt_template_yaml +process_docs: !function utils.process_professional_accounting +tag: global_mmlu_full_lt_other_tasks +task: global_mmlu_full_lt_professional_accounting diff --git a/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_professional_law.yaml b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_professional_law.yaml new file mode 100644 index 00000000..60b6cdcc --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_professional_law.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _lt_template_yaml +process_docs: !function utils.process_professional_law +tag: global_mmlu_full_lt_humanities_tasks +task: global_mmlu_full_lt_professional_law diff --git a/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_professional_medicine.yaml b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_professional_medicine.yaml new file mode 100644 index 00000000..dd899676 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_professional_medicine.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _lt_template_yaml +process_docs: !function utils.process_professional_medicine +tag: global_mmlu_full_lt_other_tasks +task: global_mmlu_full_lt_professional_medicine diff --git a/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_professional_psychology.yaml b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_professional_psychology.yaml new file mode 100644 index 00000000..bd796e8b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_professional_psychology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _lt_template_yaml +process_docs: !function utils.process_professional_psychology +tag: global_mmlu_full_lt_social_sciences_tasks +task: global_mmlu_full_lt_professional_psychology diff --git a/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_public_relations.yaml b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_public_relations.yaml new file mode 100644 index 00000000..3c6e5f39 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_public_relations.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _lt_template_yaml +process_docs: !function utils.process_public_relations +tag: global_mmlu_full_lt_social_sciences_tasks +task: global_mmlu_full_lt_public_relations diff --git a/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_security_studies.yaml b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_security_studies.yaml new file mode 100644 index 00000000..9eb9957d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_security_studies.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _lt_template_yaml +process_docs: !function utils.process_security_studies +tag: global_mmlu_full_lt_social_sciences_tasks +task: global_mmlu_full_lt_security_studies diff --git a/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_sociology.yaml b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_sociology.yaml new file mode 100644 index 00000000..2e17f95a --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_sociology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _lt_template_yaml +process_docs: !function utils.process_sociology +tag: global_mmlu_full_lt_social_sciences_tasks +task: global_mmlu_full_lt_sociology diff --git a/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_us_foreign_policy.yaml b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_us_foreign_policy.yaml new file mode 100644 index 00000000..d39bb63c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_us_foreign_policy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _lt_template_yaml +process_docs: !function utils.process_us_foreign_policy +tag: global_mmlu_full_lt_social_sciences_tasks +task: global_mmlu_full_lt_us_foreign_policy diff --git a/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_virology.yaml b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_virology.yaml new file mode 100644 index 00000000..b8482a61 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_virology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _lt_template_yaml +process_docs: !function utils.process_virology +tag: global_mmlu_full_lt_other_tasks +task: global_mmlu_full_lt_virology diff --git a/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_world_religions.yaml b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_world_religions.yaml new file mode 100644 index 00000000..a86af60d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/lt/global_mmlu_full_lt_world_religions.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _lt_template_yaml +process_docs: !function utils.process_world_religions +tag: global_mmlu_full_lt_humanities_tasks +task: global_mmlu_full_lt_world_religions diff --git a/lm_eval/tasks/global_mmlu/full/lt/utils.py b/lm_eval/tasks/global_mmlu/full/lt/utils.py new file mode 100644 index 00000000..7df72cb0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/lt/utils.py @@ -0,0 +1,73 @@ +from functools import partial + + +SUBJECTS = [ + "abstract_algebra", + "anatomy", + "astronomy", + "business_ethics", + "clinical_knowledge", + "college_biology", + "college_chemistry", + "college_computer_science", + "college_mathematics", + "college_medicine", + "college_physics", + "computer_security", + "conceptual_physics", + "econometrics", + "electrical_engineering", + "elementary_mathematics", + "formal_logic", + "global_facts", + "high_school_biology", + "high_school_chemistry", + "high_school_computer_science", + "high_school_european_history", + "high_school_geography", + "high_school_government_and_politics", + "high_school_macroeconomics", + "high_school_mathematics", + "high_school_microeconomics", + "high_school_physics", + "high_school_psychology", + "high_school_statistics", + "high_school_us_history", + "high_school_world_history", + "human_aging", + "human_sexuality", + "international_law", + "jurisprudence", + "logical_fallacies", + "machine_learning", + "management", + "marketing", + "medical_genetics", + "miscellaneous", + "moral_disputes", + "moral_scenarios", + "nutrition", + "philosophy", + "prehistory", + "professional_accounting", + "professional_law", + "professional_medicine", + "professional_psychology", + "public_relations", + "security_studies", + "sociology", + "us_foreign_policy", + "virology", + "world_religions", +] + + +def process_docs(dataset, subject): + return dataset.filter(lambda x: x["subject"] == subject) + + +process_functions = { + f"process_{subject}": partial(process_docs, subject=subject) for subject in SUBJECTS +} + +globals().update(process_functions) diff --git a/lm_eval/tasks/global_mmlu/full/mg/_global_mmlu_full_mg.yaml b/lm_eval/tasks/global_mmlu/full/mg/_global_mmlu_full_mg.yaml new file mode 100644 index 00000000..05b55948 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/mg/_global_mmlu_full_mg.yaml @@ -0,0 +1,11 @@ +group: global_mmlu_full_mg +task: + - global_mmlu_full_mg_stem + - global_mmlu_full_mg_other + - global_mmlu_full_mg_social_sciences + - global_mmlu_full_mg_humanities +aggregate_metric_list: + - metric: acc + weight_by_size: True +metadata: + version: 1.0 diff --git a/lm_eval/tasks/global_mmlu/full/mg/_global_mmlu_full_mg_humanities.yaml b/lm_eval/tasks/global_mmlu/full/mg/_global_mmlu_full_mg_humanities.yaml new file mode 100644 index 00000000..76b08f6c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/mg/_global_mmlu_full_mg_humanities.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_mg_humanities +task: + - global_mmlu_full_mg_humanities_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/mg/_global_mmlu_full_mg_other.yaml b/lm_eval/tasks/global_mmlu/full/mg/_global_mmlu_full_mg_other.yaml new file mode 100644 index 00000000..0006af4c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/mg/_global_mmlu_full_mg_other.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_mg_other +task: + - global_mmlu_full_mg_other_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/mg/_global_mmlu_full_mg_social_sciences.yaml b/lm_eval/tasks/global_mmlu/full/mg/_global_mmlu_full_mg_social_sciences.yaml new file mode 100644 index 00000000..9cfe4f5b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/mg/_global_mmlu_full_mg_social_sciences.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_mg_social_sciences +task: + - global_mmlu_full_mg_social_sciences_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/mg/_global_mmlu_full_mg_stem.yaml b/lm_eval/tasks/global_mmlu/full/mg/_global_mmlu_full_mg_stem.yaml new file mode 100644 index 00000000..bdc719d1 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/mg/_global_mmlu_full_mg_stem.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_mg_stem +task: + - global_mmlu_full_mg_stem_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/mg/_mg_template_yaml b/lm_eval/tasks/global_mmlu/full/mg/_mg_template_yaml new file mode 100644 index 00000000..4aa97b27 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/mg/_mg_template_yaml @@ -0,0 +1,16 @@ +dataset_path: CohereForAI/Global-MMLU +dataset_name: mg +test_split: test +fewshot_split: dev +fewshot_config: + sampler: first_n +output_type: multiple_choice +doc_to_text: "{{question.strip()}}\nA. {{option_a}}\nB. {{option_b}}\nC. {{option_c}}\nD. {{option_d}}\nAnswer:" +doc_to_choice: ["A", "B", "C", "D"] +doc_to_target: answer +metric_list: + - metric: acc + aggregation: mean + higher_is_better: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_abstract_algebra.yaml b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_abstract_algebra.yaml new file mode 100644 index 00000000..bea850ed --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_abstract_algebra.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _mg_template_yaml +process_docs: !function utils.process_abstract_algebra +tag: global_mmlu_full_mg_stem_tasks +task: global_mmlu_full_mg_abstract_algebra diff --git a/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_anatomy.yaml b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_anatomy.yaml new file mode 100644 index 00000000..1cf6c116 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_anatomy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _mg_template_yaml +process_docs: !function utils.process_anatomy +tag: global_mmlu_full_mg_stem_tasks +task: global_mmlu_full_mg_anatomy diff --git a/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_astronomy.yaml b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_astronomy.yaml new file mode 100644 index 00000000..df582b27 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_astronomy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _mg_template_yaml +process_docs: !function utils.process_astronomy +tag: global_mmlu_full_mg_stem_tasks +task: global_mmlu_full_mg_astronomy diff --git a/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_business_ethics.yaml b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_business_ethics.yaml new file mode 100644 index 00000000..a6351342 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_business_ethics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _mg_template_yaml +process_docs: !function utils.process_business_ethics +tag: global_mmlu_full_mg_other_tasks +task: global_mmlu_full_mg_business_ethics diff --git a/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_clinical_knowledge.yaml b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_clinical_knowledge.yaml new file mode 100644 index 00000000..21003af5 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_clinical_knowledge.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _mg_template_yaml +process_docs: !function utils.process_clinical_knowledge +tag: global_mmlu_full_mg_other_tasks +task: global_mmlu_full_mg_clinical_knowledge diff --git a/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_college_biology.yaml b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_college_biology.yaml new file mode 100644 index 00000000..d305ca94 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_college_biology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _mg_template_yaml +process_docs: !function utils.process_college_biology +tag: global_mmlu_full_mg_stem_tasks +task: global_mmlu_full_mg_college_biology diff --git a/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_college_chemistry.yaml b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_college_chemistry.yaml new file mode 100644 index 00000000..7ccaffb9 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_college_chemistry.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _mg_template_yaml +process_docs: !function utils.process_college_chemistry +tag: global_mmlu_full_mg_stem_tasks +task: global_mmlu_full_mg_college_chemistry diff --git a/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_college_computer_science.yaml b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_college_computer_science.yaml new file mode 100644 index 00000000..248f72c3 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_college_computer_science.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _mg_template_yaml +process_docs: !function utils.process_college_computer_science +tag: global_mmlu_full_mg_stem_tasks +task: global_mmlu_full_mg_college_computer_science diff --git a/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_college_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_college_mathematics.yaml new file mode 100644 index 00000000..fb817aae --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_college_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _mg_template_yaml +process_docs: !function utils.process_college_mathematics +tag: global_mmlu_full_mg_stem_tasks +task: global_mmlu_full_mg_college_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_college_medicine.yaml b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_college_medicine.yaml new file mode 100644 index 00000000..4fdbee03 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_college_medicine.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _mg_template_yaml +process_docs: !function utils.process_college_medicine +tag: global_mmlu_full_mg_other_tasks +task: global_mmlu_full_mg_college_medicine diff --git a/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_college_physics.yaml b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_college_physics.yaml new file mode 100644 index 00000000..493bdf87 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_college_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _mg_template_yaml +process_docs: !function utils.process_college_physics +tag: global_mmlu_full_mg_stem_tasks +task: global_mmlu_full_mg_college_physics diff --git a/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_computer_security.yaml b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_computer_security.yaml new file mode 100644 index 00000000..c5054eb6 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_computer_security.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _mg_template_yaml +process_docs: !function utils.process_computer_security +tag: global_mmlu_full_mg_stem_tasks +task: global_mmlu_full_mg_computer_security diff --git a/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_conceptual_physics.yaml b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_conceptual_physics.yaml new file mode 100644 index 00000000..44a13a70 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_conceptual_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _mg_template_yaml +process_docs: !function utils.process_conceptual_physics +tag: global_mmlu_full_mg_stem_tasks +task: global_mmlu_full_mg_conceptual_physics diff --git a/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_econometrics.yaml b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_econometrics.yaml new file mode 100644 index 00000000..2c5d029a --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_econometrics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _mg_template_yaml +process_docs: !function utils.process_econometrics +tag: global_mmlu_full_mg_social_sciences_tasks +task: global_mmlu_full_mg_econometrics diff --git a/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_electrical_engineering.yaml b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_electrical_engineering.yaml new file mode 100644 index 00000000..1e5ece33 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_electrical_engineering.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _mg_template_yaml +process_docs: !function utils.process_electrical_engineering +tag: global_mmlu_full_mg_stem_tasks +task: global_mmlu_full_mg_electrical_engineering diff --git a/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_elementary_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_elementary_mathematics.yaml new file mode 100644 index 00000000..4d62c758 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_elementary_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _mg_template_yaml +process_docs: !function utils.process_elementary_mathematics +tag: global_mmlu_full_mg_stem_tasks +task: global_mmlu_full_mg_elementary_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_formal_logic.yaml b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_formal_logic.yaml new file mode 100644 index 00000000..e5dc67d0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_formal_logic.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _mg_template_yaml +process_docs: !function utils.process_formal_logic +tag: global_mmlu_full_mg_humanities_tasks +task: global_mmlu_full_mg_formal_logic diff --git a/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_global_facts.yaml b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_global_facts.yaml new file mode 100644 index 00000000..2712e9b4 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_global_facts.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _mg_template_yaml +process_docs: !function utils.process_global_facts +tag: global_mmlu_full_mg_other_tasks +task: global_mmlu_full_mg_global_facts diff --git a/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_high_school_biology.yaml b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_high_school_biology.yaml new file mode 100644 index 00000000..c58957e0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_high_school_biology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _mg_template_yaml +process_docs: !function utils.process_high_school_biology +tag: global_mmlu_full_mg_stem_tasks +task: global_mmlu_full_mg_high_school_biology diff --git a/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_high_school_chemistry.yaml b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_high_school_chemistry.yaml new file mode 100644 index 00000000..707b7356 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_high_school_chemistry.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _mg_template_yaml +process_docs: !function utils.process_high_school_chemistry +tag: global_mmlu_full_mg_stem_tasks +task: global_mmlu_full_mg_high_school_chemistry diff --git a/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_high_school_computer_science.yaml b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_high_school_computer_science.yaml new file mode 100644 index 00000000..d7afd5a7 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_high_school_computer_science.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _mg_template_yaml +process_docs: !function utils.process_high_school_computer_science +tag: global_mmlu_full_mg_stem_tasks +task: global_mmlu_full_mg_high_school_computer_science diff --git a/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_high_school_european_history.yaml b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_high_school_european_history.yaml new file mode 100644 index 00000000..b6391ee4 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_high_school_european_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _mg_template_yaml +process_docs: !function utils.process_high_school_european_history +tag: global_mmlu_full_mg_humanities_tasks +task: global_mmlu_full_mg_high_school_european_history diff --git a/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_high_school_geography.yaml b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_high_school_geography.yaml new file mode 100644 index 00000000..eb7014a6 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_high_school_geography.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _mg_template_yaml +process_docs: !function utils.process_high_school_geography +tag: global_mmlu_full_mg_social_sciences_tasks +task: global_mmlu_full_mg_high_school_geography diff --git a/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_high_school_government_and_politics.yaml b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_high_school_government_and_politics.yaml new file mode 100644 index 00000000..74c5fc18 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_high_school_government_and_politics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _mg_template_yaml +process_docs: !function utils.process_high_school_government_and_politics +tag: global_mmlu_full_mg_social_sciences_tasks +task: global_mmlu_full_mg_high_school_government_and_politics diff --git a/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_high_school_macroeconomics.yaml b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_high_school_macroeconomics.yaml new file mode 100644 index 00000000..24631ff3 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_high_school_macroeconomics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _mg_template_yaml +process_docs: !function utils.process_high_school_macroeconomics +tag: global_mmlu_full_mg_social_sciences_tasks +task: global_mmlu_full_mg_high_school_macroeconomics diff --git a/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_high_school_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_high_school_mathematics.yaml new file mode 100644 index 00000000..b9db4a0c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_high_school_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _mg_template_yaml +process_docs: !function utils.process_high_school_mathematics +tag: global_mmlu_full_mg_stem_tasks +task: global_mmlu_full_mg_high_school_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_high_school_microeconomics.yaml b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_high_school_microeconomics.yaml new file mode 100644 index 00000000..f321b06a --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_high_school_microeconomics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _mg_template_yaml +process_docs: !function utils.process_high_school_microeconomics +tag: global_mmlu_full_mg_social_sciences_tasks +task: global_mmlu_full_mg_high_school_microeconomics diff --git a/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_high_school_physics.yaml b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_high_school_physics.yaml new file mode 100644 index 00000000..bc25971e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_high_school_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _mg_template_yaml +process_docs: !function utils.process_high_school_physics +tag: global_mmlu_full_mg_stem_tasks +task: global_mmlu_full_mg_high_school_physics diff --git a/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_high_school_psychology.yaml b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_high_school_psychology.yaml new file mode 100644 index 00000000..42cc39a8 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_high_school_psychology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _mg_template_yaml +process_docs: !function utils.process_high_school_psychology +tag: global_mmlu_full_mg_social_sciences_tasks +task: global_mmlu_full_mg_high_school_psychology diff --git a/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_high_school_statistics.yaml b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_high_school_statistics.yaml new file mode 100644 index 00000000..08cf8671 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_high_school_statistics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _mg_template_yaml +process_docs: !function utils.process_high_school_statistics +tag: global_mmlu_full_mg_stem_tasks +task: global_mmlu_full_mg_high_school_statistics diff --git a/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_high_school_us_history.yaml b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_high_school_us_history.yaml new file mode 100644 index 00000000..87314a57 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_high_school_us_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _mg_template_yaml +process_docs: !function utils.process_high_school_us_history +tag: global_mmlu_full_mg_humanities_tasks +task: global_mmlu_full_mg_high_school_us_history diff --git a/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_high_school_world_history.yaml b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_high_school_world_history.yaml new file mode 100644 index 00000000..c341a243 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_high_school_world_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _mg_template_yaml +process_docs: !function utils.process_high_school_world_history +tag: global_mmlu_full_mg_humanities_tasks +task: global_mmlu_full_mg_high_school_world_history diff --git a/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_human_aging.yaml b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_human_aging.yaml new file mode 100644 index 00000000..15375f9f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_human_aging.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _mg_template_yaml +process_docs: !function utils.process_human_aging +tag: global_mmlu_full_mg_other_tasks +task: global_mmlu_full_mg_human_aging diff --git a/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_human_sexuality.yaml b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_human_sexuality.yaml new file mode 100644 index 00000000..21419b9b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_human_sexuality.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _mg_template_yaml +process_docs: !function utils.process_human_sexuality +tag: global_mmlu_full_mg_social_sciences_tasks +task: global_mmlu_full_mg_human_sexuality diff --git a/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_international_law.yaml b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_international_law.yaml new file mode 100644 index 00000000..9d481339 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_international_law.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _mg_template_yaml +process_docs: !function utils.process_international_law +tag: global_mmlu_full_mg_humanities_tasks +task: global_mmlu_full_mg_international_law diff --git a/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_jurisprudence.yaml b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_jurisprudence.yaml new file mode 100644 index 00000000..f083a0ab --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_jurisprudence.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _mg_template_yaml +process_docs: !function utils.process_jurisprudence +tag: global_mmlu_full_mg_humanities_tasks +task: global_mmlu_full_mg_jurisprudence diff --git a/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_logical_fallacies.yaml b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_logical_fallacies.yaml new file mode 100644 index 00000000..57e2e731 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_logical_fallacies.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _mg_template_yaml +process_docs: !function utils.process_logical_fallacies +tag: global_mmlu_full_mg_humanities_tasks +task: global_mmlu_full_mg_logical_fallacies diff --git a/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_machine_learning.yaml b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_machine_learning.yaml new file mode 100644 index 00000000..7609a09f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_machine_learning.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _mg_template_yaml +process_docs: !function utils.process_machine_learning +tag: global_mmlu_full_mg_stem_tasks +task: global_mmlu_full_mg_machine_learning diff --git a/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_management.yaml b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_management.yaml new file mode 100644 index 00000000..becfe4b3 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_management.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _mg_template_yaml +process_docs: !function utils.process_management +tag: global_mmlu_full_mg_other_tasks +task: global_mmlu_full_mg_management diff --git a/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_marketing.yaml b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_marketing.yaml new file mode 100644 index 00000000..3765002b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_marketing.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _mg_template_yaml +process_docs: !function utils.process_marketing +tag: global_mmlu_full_mg_other_tasks +task: global_mmlu_full_mg_marketing diff --git a/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_medical_genetics.yaml b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_medical_genetics.yaml new file mode 100644 index 00000000..3f023ccd --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_medical_genetics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _mg_template_yaml +process_docs: !function utils.process_medical_genetics +tag: global_mmlu_full_mg_other_tasks +task: global_mmlu_full_mg_medical_genetics diff --git a/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_miscellaneous.yaml b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_miscellaneous.yaml new file mode 100644 index 00000000..2993999d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_miscellaneous.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _mg_template_yaml +process_docs: !function utils.process_miscellaneous +tag: global_mmlu_full_mg_other_tasks +task: global_mmlu_full_mg_miscellaneous diff --git a/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_moral_disputes.yaml b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_moral_disputes.yaml new file mode 100644 index 00000000..fd430a0a --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_moral_disputes.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _mg_template_yaml +process_docs: !function utils.process_moral_disputes +tag: global_mmlu_full_mg_humanities_tasks +task: global_mmlu_full_mg_moral_disputes diff --git a/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_moral_scenarios.yaml b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_moral_scenarios.yaml new file mode 100644 index 00000000..c1b16e86 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_moral_scenarios.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _mg_template_yaml +process_docs: !function utils.process_moral_scenarios +tag: global_mmlu_full_mg_humanities_tasks +task: global_mmlu_full_mg_moral_scenarios diff --git a/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_nutrition.yaml b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_nutrition.yaml new file mode 100644 index 00000000..ab471f42 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_nutrition.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _mg_template_yaml +process_docs: !function utils.process_nutrition +tag: global_mmlu_full_mg_other_tasks +task: global_mmlu_full_mg_nutrition diff --git a/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_philosophy.yaml b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_philosophy.yaml new file mode 100644 index 00000000..f598830e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_philosophy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _mg_template_yaml +process_docs: !function utils.process_philosophy +tag: global_mmlu_full_mg_humanities_tasks +task: global_mmlu_full_mg_philosophy diff --git a/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_prehistory.yaml b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_prehistory.yaml new file mode 100644 index 00000000..330f1f52 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_prehistory.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _mg_template_yaml +process_docs: !function utils.process_prehistory +tag: global_mmlu_full_mg_humanities_tasks +task: global_mmlu_full_mg_prehistory diff --git a/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_professional_accounting.yaml b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_professional_accounting.yaml new file mode 100644 index 00000000..694118d1 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_professional_accounting.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _mg_template_yaml +process_docs: !function utils.process_professional_accounting +tag: global_mmlu_full_mg_other_tasks +task: global_mmlu_full_mg_professional_accounting diff --git a/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_professional_law.yaml b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_professional_law.yaml new file mode 100644 index 00000000..fb6df92a --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_professional_law.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _mg_template_yaml +process_docs: !function utils.process_professional_law +tag: global_mmlu_full_mg_humanities_tasks +task: global_mmlu_full_mg_professional_law diff --git a/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_professional_medicine.yaml b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_professional_medicine.yaml new file mode 100644 index 00000000..1de72b6b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_professional_medicine.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _mg_template_yaml +process_docs: !function utils.process_professional_medicine +tag: global_mmlu_full_mg_other_tasks +task: global_mmlu_full_mg_professional_medicine diff --git a/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_professional_psychology.yaml b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_professional_psychology.yaml new file mode 100644 index 00000000..f922e162 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_professional_psychology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _mg_template_yaml +process_docs: !function utils.process_professional_psychology +tag: global_mmlu_full_mg_social_sciences_tasks +task: global_mmlu_full_mg_professional_psychology diff --git a/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_public_relations.yaml b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_public_relations.yaml new file mode 100644 index 00000000..c829b89d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_public_relations.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _mg_template_yaml +process_docs: !function utils.process_public_relations +tag: global_mmlu_full_mg_social_sciences_tasks +task: global_mmlu_full_mg_public_relations diff --git a/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_security_studies.yaml b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_security_studies.yaml new file mode 100644 index 00000000..362b4dbd --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_security_studies.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _mg_template_yaml +process_docs: !function utils.process_security_studies +tag: global_mmlu_full_mg_social_sciences_tasks +task: global_mmlu_full_mg_security_studies diff --git a/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_sociology.yaml b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_sociology.yaml new file mode 100644 index 00000000..f0638cdb --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_sociology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _mg_template_yaml +process_docs: !function utils.process_sociology +tag: global_mmlu_full_mg_social_sciences_tasks +task: global_mmlu_full_mg_sociology diff --git a/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_us_foreign_policy.yaml b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_us_foreign_policy.yaml new file mode 100644 index 00000000..8ead541a --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_us_foreign_policy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _mg_template_yaml +process_docs: !function utils.process_us_foreign_policy +tag: global_mmlu_full_mg_social_sciences_tasks +task: global_mmlu_full_mg_us_foreign_policy diff --git a/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_virology.yaml b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_virology.yaml new file mode 100644 index 00000000..1ca09027 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_virology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _mg_template_yaml +process_docs: !function utils.process_virology +tag: global_mmlu_full_mg_other_tasks +task: global_mmlu_full_mg_virology diff --git a/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_world_religions.yaml b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_world_religions.yaml new file mode 100644 index 00000000..2bb64d70 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/mg/global_mmlu_full_mg_world_religions.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _mg_template_yaml +process_docs: !function utils.process_world_religions +tag: global_mmlu_full_mg_humanities_tasks +task: global_mmlu_full_mg_world_religions diff --git a/lm_eval/tasks/global_mmlu/full/mg/utils.py b/lm_eval/tasks/global_mmlu/full/mg/utils.py new file mode 100644 index 00000000..7df72cb0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/mg/utils.py @@ -0,0 +1,73 @@ +from functools import partial + + +SUBJECTS = [ + "abstract_algebra", + "anatomy", + "astronomy", + "business_ethics", + "clinical_knowledge", + "college_biology", + "college_chemistry", + "college_computer_science", + "college_mathematics", + "college_medicine", + "college_physics", + "computer_security", + "conceptual_physics", + "econometrics", + "electrical_engineering", + "elementary_mathematics", + "formal_logic", + "global_facts", + "high_school_biology", + "high_school_chemistry", + "high_school_computer_science", + "high_school_european_history", + "high_school_geography", + "high_school_government_and_politics", + "high_school_macroeconomics", + "high_school_mathematics", + "high_school_microeconomics", + "high_school_physics", + "high_school_psychology", + "high_school_statistics", + "high_school_us_history", + "high_school_world_history", + "human_aging", + "human_sexuality", + "international_law", + "jurisprudence", + "logical_fallacies", + "machine_learning", + "management", + "marketing", + "medical_genetics", + "miscellaneous", + "moral_disputes", + "moral_scenarios", + "nutrition", + "philosophy", + "prehistory", + "professional_accounting", + "professional_law", + "professional_medicine", + "professional_psychology", + "public_relations", + "security_studies", + "sociology", + "us_foreign_policy", + "virology", + "world_religions", +] + + +def process_docs(dataset, subject): + return dataset.filter(lambda x: x["subject"] == subject) + + +process_functions = { + f"process_{subject}": partial(process_docs, subject=subject) for subject in SUBJECTS +} + +globals().update(process_functions) diff --git a/lm_eval/tasks/global_mmlu/full/ms/_global_mmlu_full_ms.yaml b/lm_eval/tasks/global_mmlu/full/ms/_global_mmlu_full_ms.yaml new file mode 100644 index 00000000..e5a13645 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ms/_global_mmlu_full_ms.yaml @@ -0,0 +1,11 @@ +group: global_mmlu_full_ms +task: + - global_mmlu_full_ms_stem + - global_mmlu_full_ms_other + - global_mmlu_full_ms_social_sciences + - global_mmlu_full_ms_humanities +aggregate_metric_list: + - metric: acc + weight_by_size: True +metadata: + version: 1.0 diff --git a/lm_eval/tasks/global_mmlu/full/ms/_global_mmlu_full_ms_humanities.yaml b/lm_eval/tasks/global_mmlu/full/ms/_global_mmlu_full_ms_humanities.yaml new file mode 100644 index 00000000..0641187b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ms/_global_mmlu_full_ms_humanities.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_ms_humanities +task: + - global_mmlu_full_ms_humanities_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/ms/_global_mmlu_full_ms_other.yaml b/lm_eval/tasks/global_mmlu/full/ms/_global_mmlu_full_ms_other.yaml new file mode 100644 index 00000000..3d14420c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ms/_global_mmlu_full_ms_other.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_ms_other +task: + - global_mmlu_full_ms_other_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/ms/_global_mmlu_full_ms_social_sciences.yaml b/lm_eval/tasks/global_mmlu/full/ms/_global_mmlu_full_ms_social_sciences.yaml new file mode 100644 index 00000000..3db339d7 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ms/_global_mmlu_full_ms_social_sciences.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_ms_social_sciences +task: + - global_mmlu_full_ms_social_sciences_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/ms/_global_mmlu_full_ms_stem.yaml b/lm_eval/tasks/global_mmlu/full/ms/_global_mmlu_full_ms_stem.yaml new file mode 100644 index 00000000..68908e16 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ms/_global_mmlu_full_ms_stem.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_ms_stem +task: + - global_mmlu_full_ms_stem_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/ms/_ms_template_yaml b/lm_eval/tasks/global_mmlu/full/ms/_ms_template_yaml new file mode 100644 index 00000000..ba750264 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ms/_ms_template_yaml @@ -0,0 +1,16 @@ +dataset_path: CohereForAI/Global-MMLU +dataset_name: ms +test_split: test +fewshot_split: dev +fewshot_config: + sampler: first_n +output_type: multiple_choice +doc_to_text: "{{question.strip()}}\nA. {{option_a}}\nB. {{option_b}}\nC. {{option_c}}\nD. {{option_d}}\nAnswer:" +doc_to_choice: ["A", "B", "C", "D"] +doc_to_target: answer +metric_list: + - metric: acc + aggregation: mean + higher_is_better: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_abstract_algebra.yaml b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_abstract_algebra.yaml new file mode 100644 index 00000000..ec791f2a --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_abstract_algebra.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ms_template_yaml +process_docs: !function utils.process_abstract_algebra +tag: global_mmlu_full_ms_stem_tasks +task: global_mmlu_full_ms_abstract_algebra diff --git a/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_anatomy.yaml b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_anatomy.yaml new file mode 100644 index 00000000..35038bea --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_anatomy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ms_template_yaml +process_docs: !function utils.process_anatomy +tag: global_mmlu_full_ms_stem_tasks +task: global_mmlu_full_ms_anatomy diff --git a/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_astronomy.yaml b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_astronomy.yaml new file mode 100644 index 00000000..79fdcbdd --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_astronomy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ms_template_yaml +process_docs: !function utils.process_astronomy +tag: global_mmlu_full_ms_stem_tasks +task: global_mmlu_full_ms_astronomy diff --git a/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_business_ethics.yaml b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_business_ethics.yaml new file mode 100644 index 00000000..ffd6195a --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_business_ethics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ms_template_yaml +process_docs: !function utils.process_business_ethics +tag: global_mmlu_full_ms_other_tasks +task: global_mmlu_full_ms_business_ethics diff --git a/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_clinical_knowledge.yaml b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_clinical_knowledge.yaml new file mode 100644 index 00000000..4c69b82e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_clinical_knowledge.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ms_template_yaml +process_docs: !function utils.process_clinical_knowledge +tag: global_mmlu_full_ms_other_tasks +task: global_mmlu_full_ms_clinical_knowledge diff --git a/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_college_biology.yaml b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_college_biology.yaml new file mode 100644 index 00000000..58219479 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_college_biology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ms_template_yaml +process_docs: !function utils.process_college_biology +tag: global_mmlu_full_ms_stem_tasks +task: global_mmlu_full_ms_college_biology diff --git a/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_college_chemistry.yaml b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_college_chemistry.yaml new file mode 100644 index 00000000..35514b83 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_college_chemistry.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ms_template_yaml +process_docs: !function utils.process_college_chemistry +tag: global_mmlu_full_ms_stem_tasks +task: global_mmlu_full_ms_college_chemistry diff --git a/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_college_computer_science.yaml b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_college_computer_science.yaml new file mode 100644 index 00000000..5e242b8b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_college_computer_science.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ms_template_yaml +process_docs: !function utils.process_college_computer_science +tag: global_mmlu_full_ms_stem_tasks +task: global_mmlu_full_ms_college_computer_science diff --git a/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_college_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_college_mathematics.yaml new file mode 100644 index 00000000..07e10799 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_college_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ms_template_yaml +process_docs: !function utils.process_college_mathematics +tag: global_mmlu_full_ms_stem_tasks +task: global_mmlu_full_ms_college_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_college_medicine.yaml b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_college_medicine.yaml new file mode 100644 index 00000000..82822217 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_college_medicine.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ms_template_yaml +process_docs: !function utils.process_college_medicine +tag: global_mmlu_full_ms_other_tasks +task: global_mmlu_full_ms_college_medicine diff --git a/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_college_physics.yaml b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_college_physics.yaml new file mode 100644 index 00000000..be20fa6c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_college_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ms_template_yaml +process_docs: !function utils.process_college_physics +tag: global_mmlu_full_ms_stem_tasks +task: global_mmlu_full_ms_college_physics diff --git a/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_computer_security.yaml b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_computer_security.yaml new file mode 100644 index 00000000..2e886b50 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_computer_security.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ms_template_yaml +process_docs: !function utils.process_computer_security +tag: global_mmlu_full_ms_stem_tasks +task: global_mmlu_full_ms_computer_security diff --git a/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_conceptual_physics.yaml b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_conceptual_physics.yaml new file mode 100644 index 00000000..2a2fb6da --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_conceptual_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ms_template_yaml +process_docs: !function utils.process_conceptual_physics +tag: global_mmlu_full_ms_stem_tasks +task: global_mmlu_full_ms_conceptual_physics diff --git a/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_econometrics.yaml b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_econometrics.yaml new file mode 100644 index 00000000..efdffabf --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_econometrics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ms_template_yaml +process_docs: !function utils.process_econometrics +tag: global_mmlu_full_ms_social_sciences_tasks +task: global_mmlu_full_ms_econometrics diff --git a/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_electrical_engineering.yaml b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_electrical_engineering.yaml new file mode 100644 index 00000000..80eba2e4 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_electrical_engineering.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ms_template_yaml +process_docs: !function utils.process_electrical_engineering +tag: global_mmlu_full_ms_stem_tasks +task: global_mmlu_full_ms_electrical_engineering diff --git a/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_elementary_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_elementary_mathematics.yaml new file mode 100644 index 00000000..1e6caf26 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_elementary_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ms_template_yaml +process_docs: !function utils.process_elementary_mathematics +tag: global_mmlu_full_ms_stem_tasks +task: global_mmlu_full_ms_elementary_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_formal_logic.yaml b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_formal_logic.yaml new file mode 100644 index 00000000..59147662 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_formal_logic.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ms_template_yaml +process_docs: !function utils.process_formal_logic +tag: global_mmlu_full_ms_humanities_tasks +task: global_mmlu_full_ms_formal_logic diff --git a/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_global_facts.yaml b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_global_facts.yaml new file mode 100644 index 00000000..6ac76cad --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_global_facts.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ms_template_yaml +process_docs: !function utils.process_global_facts +tag: global_mmlu_full_ms_other_tasks +task: global_mmlu_full_ms_global_facts diff --git a/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_high_school_biology.yaml b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_high_school_biology.yaml new file mode 100644 index 00000000..6be8ccfe --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_high_school_biology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ms_template_yaml +process_docs: !function utils.process_high_school_biology +tag: global_mmlu_full_ms_stem_tasks +task: global_mmlu_full_ms_high_school_biology diff --git a/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_high_school_chemistry.yaml b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_high_school_chemistry.yaml new file mode 100644 index 00000000..f01c29b6 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_high_school_chemistry.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ms_template_yaml +process_docs: !function utils.process_high_school_chemistry +tag: global_mmlu_full_ms_stem_tasks +task: global_mmlu_full_ms_high_school_chemistry diff --git a/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_high_school_computer_science.yaml b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_high_school_computer_science.yaml new file mode 100644 index 00000000..b18e8cf8 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_high_school_computer_science.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ms_template_yaml +process_docs: !function utils.process_high_school_computer_science +tag: global_mmlu_full_ms_stem_tasks +task: global_mmlu_full_ms_high_school_computer_science diff --git a/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_high_school_european_history.yaml b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_high_school_european_history.yaml new file mode 100644 index 00000000..fdb41802 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_high_school_european_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ms_template_yaml +process_docs: !function utils.process_high_school_european_history +tag: global_mmlu_full_ms_humanities_tasks +task: global_mmlu_full_ms_high_school_european_history diff --git a/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_high_school_geography.yaml b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_high_school_geography.yaml new file mode 100644 index 00000000..c4e44a60 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_high_school_geography.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ms_template_yaml +process_docs: !function utils.process_high_school_geography +tag: global_mmlu_full_ms_social_sciences_tasks +task: global_mmlu_full_ms_high_school_geography diff --git a/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_high_school_government_and_politics.yaml b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_high_school_government_and_politics.yaml new file mode 100644 index 00000000..0ebbfe6f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_high_school_government_and_politics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ms_template_yaml +process_docs: !function utils.process_high_school_government_and_politics +tag: global_mmlu_full_ms_social_sciences_tasks +task: global_mmlu_full_ms_high_school_government_and_politics diff --git a/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_high_school_macroeconomics.yaml b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_high_school_macroeconomics.yaml new file mode 100644 index 00000000..f28f9a5d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_high_school_macroeconomics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ms_template_yaml +process_docs: !function utils.process_high_school_macroeconomics +tag: global_mmlu_full_ms_social_sciences_tasks +task: global_mmlu_full_ms_high_school_macroeconomics diff --git a/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_high_school_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_high_school_mathematics.yaml new file mode 100644 index 00000000..50a2552d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_high_school_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ms_template_yaml +process_docs: !function utils.process_high_school_mathematics +tag: global_mmlu_full_ms_stem_tasks +task: global_mmlu_full_ms_high_school_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_high_school_microeconomics.yaml b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_high_school_microeconomics.yaml new file mode 100644 index 00000000..6747cd9d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_high_school_microeconomics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ms_template_yaml +process_docs: !function utils.process_high_school_microeconomics +tag: global_mmlu_full_ms_social_sciences_tasks +task: global_mmlu_full_ms_high_school_microeconomics diff --git a/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_high_school_physics.yaml b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_high_school_physics.yaml new file mode 100644 index 00000000..aef3fee8 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_high_school_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ms_template_yaml +process_docs: !function utils.process_high_school_physics +tag: global_mmlu_full_ms_stem_tasks +task: global_mmlu_full_ms_high_school_physics diff --git a/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_high_school_psychology.yaml b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_high_school_psychology.yaml new file mode 100644 index 00000000..3e8641e9 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_high_school_psychology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ms_template_yaml +process_docs: !function utils.process_high_school_psychology +tag: global_mmlu_full_ms_social_sciences_tasks +task: global_mmlu_full_ms_high_school_psychology diff --git a/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_high_school_statistics.yaml b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_high_school_statistics.yaml new file mode 100644 index 00000000..4aa7ba00 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_high_school_statistics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ms_template_yaml +process_docs: !function utils.process_high_school_statistics +tag: global_mmlu_full_ms_stem_tasks +task: global_mmlu_full_ms_high_school_statistics diff --git a/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_high_school_us_history.yaml b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_high_school_us_history.yaml new file mode 100644 index 00000000..e6d1faab --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_high_school_us_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ms_template_yaml +process_docs: !function utils.process_high_school_us_history +tag: global_mmlu_full_ms_humanities_tasks +task: global_mmlu_full_ms_high_school_us_history diff --git a/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_high_school_world_history.yaml b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_high_school_world_history.yaml new file mode 100644 index 00000000..4caf7e54 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_high_school_world_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ms_template_yaml +process_docs: !function utils.process_high_school_world_history +tag: global_mmlu_full_ms_humanities_tasks +task: global_mmlu_full_ms_high_school_world_history diff --git a/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_human_aging.yaml b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_human_aging.yaml new file mode 100644 index 00000000..5b2b5c5f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_human_aging.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ms_template_yaml +process_docs: !function utils.process_human_aging +tag: global_mmlu_full_ms_other_tasks +task: global_mmlu_full_ms_human_aging diff --git a/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_human_sexuality.yaml b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_human_sexuality.yaml new file mode 100644 index 00000000..2ddef17a --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_human_sexuality.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ms_template_yaml +process_docs: !function utils.process_human_sexuality +tag: global_mmlu_full_ms_social_sciences_tasks +task: global_mmlu_full_ms_human_sexuality diff --git a/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_international_law.yaml b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_international_law.yaml new file mode 100644 index 00000000..61795f58 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_international_law.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ms_template_yaml +process_docs: !function utils.process_international_law +tag: global_mmlu_full_ms_humanities_tasks +task: global_mmlu_full_ms_international_law diff --git a/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_jurisprudence.yaml b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_jurisprudence.yaml new file mode 100644 index 00000000..f2e96706 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_jurisprudence.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ms_template_yaml +process_docs: !function utils.process_jurisprudence +tag: global_mmlu_full_ms_humanities_tasks +task: global_mmlu_full_ms_jurisprudence diff --git a/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_logical_fallacies.yaml b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_logical_fallacies.yaml new file mode 100644 index 00000000..1d142bde --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_logical_fallacies.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ms_template_yaml +process_docs: !function utils.process_logical_fallacies +tag: global_mmlu_full_ms_humanities_tasks +task: global_mmlu_full_ms_logical_fallacies diff --git a/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_machine_learning.yaml b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_machine_learning.yaml new file mode 100644 index 00000000..94724056 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_machine_learning.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ms_template_yaml +process_docs: !function utils.process_machine_learning +tag: global_mmlu_full_ms_stem_tasks +task: global_mmlu_full_ms_machine_learning diff --git a/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_management.yaml b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_management.yaml new file mode 100644 index 00000000..8ca04a13 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_management.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ms_template_yaml +process_docs: !function utils.process_management +tag: global_mmlu_full_ms_other_tasks +task: global_mmlu_full_ms_management diff --git a/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_marketing.yaml b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_marketing.yaml new file mode 100644 index 00000000..ec0e4462 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_marketing.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ms_template_yaml +process_docs: !function utils.process_marketing +tag: global_mmlu_full_ms_other_tasks +task: global_mmlu_full_ms_marketing diff --git a/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_medical_genetics.yaml b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_medical_genetics.yaml new file mode 100644 index 00000000..0f2b1eec --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_medical_genetics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ms_template_yaml +process_docs: !function utils.process_medical_genetics +tag: global_mmlu_full_ms_other_tasks +task: global_mmlu_full_ms_medical_genetics diff --git a/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_miscellaneous.yaml b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_miscellaneous.yaml new file mode 100644 index 00000000..65da952e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_miscellaneous.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ms_template_yaml +process_docs: !function utils.process_miscellaneous +tag: global_mmlu_full_ms_other_tasks +task: global_mmlu_full_ms_miscellaneous diff --git a/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_moral_disputes.yaml b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_moral_disputes.yaml new file mode 100644 index 00000000..399035f2 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_moral_disputes.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ms_template_yaml +process_docs: !function utils.process_moral_disputes +tag: global_mmlu_full_ms_humanities_tasks +task: global_mmlu_full_ms_moral_disputes diff --git a/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_moral_scenarios.yaml b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_moral_scenarios.yaml new file mode 100644 index 00000000..3bc74baa --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_moral_scenarios.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ms_template_yaml +process_docs: !function utils.process_moral_scenarios +tag: global_mmlu_full_ms_humanities_tasks +task: global_mmlu_full_ms_moral_scenarios diff --git a/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_nutrition.yaml b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_nutrition.yaml new file mode 100644 index 00000000..300de677 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_nutrition.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ms_template_yaml +process_docs: !function utils.process_nutrition +tag: global_mmlu_full_ms_other_tasks +task: global_mmlu_full_ms_nutrition diff --git a/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_philosophy.yaml b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_philosophy.yaml new file mode 100644 index 00000000..8f6eceae --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_philosophy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ms_template_yaml +process_docs: !function utils.process_philosophy +tag: global_mmlu_full_ms_humanities_tasks +task: global_mmlu_full_ms_philosophy diff --git a/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_prehistory.yaml b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_prehistory.yaml new file mode 100644 index 00000000..4c624fec --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_prehistory.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ms_template_yaml +process_docs: !function utils.process_prehistory +tag: global_mmlu_full_ms_humanities_tasks +task: global_mmlu_full_ms_prehistory diff --git a/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_professional_accounting.yaml b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_professional_accounting.yaml new file mode 100644 index 00000000..9a06e7f9 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_professional_accounting.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ms_template_yaml +process_docs: !function utils.process_professional_accounting +tag: global_mmlu_full_ms_other_tasks +task: global_mmlu_full_ms_professional_accounting diff --git a/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_professional_law.yaml b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_professional_law.yaml new file mode 100644 index 00000000..b3d5921a --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_professional_law.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ms_template_yaml +process_docs: !function utils.process_professional_law +tag: global_mmlu_full_ms_humanities_tasks +task: global_mmlu_full_ms_professional_law diff --git a/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_professional_medicine.yaml b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_professional_medicine.yaml new file mode 100644 index 00000000..0d9a58b7 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_professional_medicine.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ms_template_yaml +process_docs: !function utils.process_professional_medicine +tag: global_mmlu_full_ms_other_tasks +task: global_mmlu_full_ms_professional_medicine diff --git a/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_professional_psychology.yaml b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_professional_psychology.yaml new file mode 100644 index 00000000..7f51baec --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_professional_psychology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ms_template_yaml +process_docs: !function utils.process_professional_psychology +tag: global_mmlu_full_ms_social_sciences_tasks +task: global_mmlu_full_ms_professional_psychology diff --git a/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_public_relations.yaml b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_public_relations.yaml new file mode 100644 index 00000000..c07cbdee --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_public_relations.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ms_template_yaml +process_docs: !function utils.process_public_relations +tag: global_mmlu_full_ms_social_sciences_tasks +task: global_mmlu_full_ms_public_relations diff --git a/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_security_studies.yaml b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_security_studies.yaml new file mode 100644 index 00000000..651cb72d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_security_studies.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ms_template_yaml +process_docs: !function utils.process_security_studies +tag: global_mmlu_full_ms_social_sciences_tasks +task: global_mmlu_full_ms_security_studies diff --git a/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_sociology.yaml b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_sociology.yaml new file mode 100644 index 00000000..5aeb7efa --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_sociology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ms_template_yaml +process_docs: !function utils.process_sociology +tag: global_mmlu_full_ms_social_sciences_tasks +task: global_mmlu_full_ms_sociology diff --git a/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_us_foreign_policy.yaml b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_us_foreign_policy.yaml new file mode 100644 index 00000000..ecbf5705 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_us_foreign_policy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ms_template_yaml +process_docs: !function utils.process_us_foreign_policy +tag: global_mmlu_full_ms_social_sciences_tasks +task: global_mmlu_full_ms_us_foreign_policy diff --git a/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_virology.yaml b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_virology.yaml new file mode 100644 index 00000000..fbdd5e25 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_virology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ms_template_yaml +process_docs: !function utils.process_virology +tag: global_mmlu_full_ms_other_tasks +task: global_mmlu_full_ms_virology diff --git a/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_world_religions.yaml b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_world_religions.yaml new file mode 100644 index 00000000..32b35029 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ms/global_mmlu_full_ms_world_religions.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ms_template_yaml +process_docs: !function utils.process_world_religions +tag: global_mmlu_full_ms_humanities_tasks +task: global_mmlu_full_ms_world_religions diff --git a/lm_eval/tasks/global_mmlu/full/ms/utils.py b/lm_eval/tasks/global_mmlu/full/ms/utils.py new file mode 100644 index 00000000..7df72cb0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ms/utils.py @@ -0,0 +1,73 @@ +from functools import partial + + +SUBJECTS = [ + "abstract_algebra", + "anatomy", + "astronomy", + "business_ethics", + "clinical_knowledge", + "college_biology", + "college_chemistry", + "college_computer_science", + "college_mathematics", + "college_medicine", + "college_physics", + "computer_security", + "conceptual_physics", + "econometrics", + "electrical_engineering", + "elementary_mathematics", + "formal_logic", + "global_facts", + "high_school_biology", + "high_school_chemistry", + "high_school_computer_science", + "high_school_european_history", + "high_school_geography", + "high_school_government_and_politics", + "high_school_macroeconomics", + "high_school_mathematics", + "high_school_microeconomics", + "high_school_physics", + "high_school_psychology", + "high_school_statistics", + "high_school_us_history", + "high_school_world_history", + "human_aging", + "human_sexuality", + "international_law", + "jurisprudence", + "logical_fallacies", + "machine_learning", + "management", + "marketing", + "medical_genetics", + "miscellaneous", + "moral_disputes", + "moral_scenarios", + "nutrition", + "philosophy", + "prehistory", + "professional_accounting", + "professional_law", + "professional_medicine", + "professional_psychology", + "public_relations", + "security_studies", + "sociology", + "us_foreign_policy", + "virology", + "world_religions", +] + + +def process_docs(dataset, subject): + return dataset.filter(lambda x: x["subject"] == subject) + + +process_functions = { + f"process_{subject}": partial(process_docs, subject=subject) for subject in SUBJECTS +} + +globals().update(process_functions) diff --git a/lm_eval/tasks/global_mmlu/full/ne/_global_mmlu_full_ne.yaml b/lm_eval/tasks/global_mmlu/full/ne/_global_mmlu_full_ne.yaml new file mode 100644 index 00000000..ec13a0be --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ne/_global_mmlu_full_ne.yaml @@ -0,0 +1,11 @@ +group: global_mmlu_full_ne +task: + - global_mmlu_full_ne_stem + - global_mmlu_full_ne_other + - global_mmlu_full_ne_social_sciences + - global_mmlu_full_ne_humanities +aggregate_metric_list: + - metric: acc + weight_by_size: True +metadata: + version: 1.0 diff --git a/lm_eval/tasks/global_mmlu/full/ne/_global_mmlu_full_ne_humanities.yaml b/lm_eval/tasks/global_mmlu/full/ne/_global_mmlu_full_ne_humanities.yaml new file mode 100644 index 00000000..fef749db --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ne/_global_mmlu_full_ne_humanities.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_ne_humanities +task: + - global_mmlu_full_ne_humanities_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/ne/_global_mmlu_full_ne_other.yaml b/lm_eval/tasks/global_mmlu/full/ne/_global_mmlu_full_ne_other.yaml new file mode 100644 index 00000000..0d3dfbd4 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ne/_global_mmlu_full_ne_other.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_ne_other +task: + - global_mmlu_full_ne_other_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/ne/_global_mmlu_full_ne_social_sciences.yaml b/lm_eval/tasks/global_mmlu/full/ne/_global_mmlu_full_ne_social_sciences.yaml new file mode 100644 index 00000000..f1f09f00 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ne/_global_mmlu_full_ne_social_sciences.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_ne_social_sciences +task: + - global_mmlu_full_ne_social_sciences_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/ne/_global_mmlu_full_ne_stem.yaml b/lm_eval/tasks/global_mmlu/full/ne/_global_mmlu_full_ne_stem.yaml new file mode 100644 index 00000000..eebc1cac --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ne/_global_mmlu_full_ne_stem.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_ne_stem +task: + - global_mmlu_full_ne_stem_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/ne/_ne_template_yaml b/lm_eval/tasks/global_mmlu/full/ne/_ne_template_yaml new file mode 100644 index 00000000..25f8daec --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ne/_ne_template_yaml @@ -0,0 +1,16 @@ +dataset_path: CohereForAI/Global-MMLU +dataset_name: ne +test_split: test +fewshot_split: dev +fewshot_config: + sampler: first_n +output_type: multiple_choice +doc_to_text: "{{question.strip()}}\nA. {{option_a}}\nB. {{option_b}}\nC. {{option_c}}\nD. {{option_d}}\nAnswer:" +doc_to_choice: ["A", "B", "C", "D"] +doc_to_target: answer +metric_list: + - metric: acc + aggregation: mean + higher_is_better: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_abstract_algebra.yaml b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_abstract_algebra.yaml new file mode 100644 index 00000000..48bf7bb1 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_abstract_algebra.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ne_template_yaml +process_docs: !function utils.process_abstract_algebra +tag: global_mmlu_full_ne_stem_tasks +task: global_mmlu_full_ne_abstract_algebra diff --git a/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_anatomy.yaml b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_anatomy.yaml new file mode 100644 index 00000000..0f66f8ec --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_anatomy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ne_template_yaml +process_docs: !function utils.process_anatomy +tag: global_mmlu_full_ne_stem_tasks +task: global_mmlu_full_ne_anatomy diff --git a/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_astronomy.yaml b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_astronomy.yaml new file mode 100644 index 00000000..a02aaf30 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_astronomy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ne_template_yaml +process_docs: !function utils.process_astronomy +tag: global_mmlu_full_ne_stem_tasks +task: global_mmlu_full_ne_astronomy diff --git a/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_business_ethics.yaml b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_business_ethics.yaml new file mode 100644 index 00000000..d87f5b98 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_business_ethics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ne_template_yaml +process_docs: !function utils.process_business_ethics +tag: global_mmlu_full_ne_other_tasks +task: global_mmlu_full_ne_business_ethics diff --git a/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_clinical_knowledge.yaml b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_clinical_knowledge.yaml new file mode 100644 index 00000000..f27eb4e2 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_clinical_knowledge.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ne_template_yaml +process_docs: !function utils.process_clinical_knowledge +tag: global_mmlu_full_ne_other_tasks +task: global_mmlu_full_ne_clinical_knowledge diff --git a/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_college_biology.yaml b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_college_biology.yaml new file mode 100644 index 00000000..d26edef8 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_college_biology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ne_template_yaml +process_docs: !function utils.process_college_biology +tag: global_mmlu_full_ne_stem_tasks +task: global_mmlu_full_ne_college_biology diff --git a/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_college_chemistry.yaml b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_college_chemistry.yaml new file mode 100644 index 00000000..88b8bd86 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_college_chemistry.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ne_template_yaml +process_docs: !function utils.process_college_chemistry +tag: global_mmlu_full_ne_stem_tasks +task: global_mmlu_full_ne_college_chemistry diff --git a/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_college_computer_science.yaml b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_college_computer_science.yaml new file mode 100644 index 00000000..51909ffc --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_college_computer_science.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ne_template_yaml +process_docs: !function utils.process_college_computer_science +tag: global_mmlu_full_ne_stem_tasks +task: global_mmlu_full_ne_college_computer_science diff --git a/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_college_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_college_mathematics.yaml new file mode 100644 index 00000000..40b9cb79 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_college_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ne_template_yaml +process_docs: !function utils.process_college_mathematics +tag: global_mmlu_full_ne_stem_tasks +task: global_mmlu_full_ne_college_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_college_medicine.yaml b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_college_medicine.yaml new file mode 100644 index 00000000..81f81f84 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_college_medicine.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ne_template_yaml +process_docs: !function utils.process_college_medicine +tag: global_mmlu_full_ne_other_tasks +task: global_mmlu_full_ne_college_medicine diff --git a/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_college_physics.yaml b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_college_physics.yaml new file mode 100644 index 00000000..09798c09 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_college_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ne_template_yaml +process_docs: !function utils.process_college_physics +tag: global_mmlu_full_ne_stem_tasks +task: global_mmlu_full_ne_college_physics diff --git a/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_computer_security.yaml b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_computer_security.yaml new file mode 100644 index 00000000..49d89dd4 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_computer_security.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ne_template_yaml +process_docs: !function utils.process_computer_security +tag: global_mmlu_full_ne_stem_tasks +task: global_mmlu_full_ne_computer_security diff --git a/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_conceptual_physics.yaml b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_conceptual_physics.yaml new file mode 100644 index 00000000..94bfec4a --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_conceptual_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ne_template_yaml +process_docs: !function utils.process_conceptual_physics +tag: global_mmlu_full_ne_stem_tasks +task: global_mmlu_full_ne_conceptual_physics diff --git a/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_econometrics.yaml b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_econometrics.yaml new file mode 100644 index 00000000..81d6ed98 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_econometrics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ne_template_yaml +process_docs: !function utils.process_econometrics +tag: global_mmlu_full_ne_social_sciences_tasks +task: global_mmlu_full_ne_econometrics diff --git a/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_electrical_engineering.yaml b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_electrical_engineering.yaml new file mode 100644 index 00000000..73ad1a34 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_electrical_engineering.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ne_template_yaml +process_docs: !function utils.process_electrical_engineering +tag: global_mmlu_full_ne_stem_tasks +task: global_mmlu_full_ne_electrical_engineering diff --git a/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_elementary_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_elementary_mathematics.yaml new file mode 100644 index 00000000..cbc3bacd --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_elementary_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ne_template_yaml +process_docs: !function utils.process_elementary_mathematics +tag: global_mmlu_full_ne_stem_tasks +task: global_mmlu_full_ne_elementary_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_formal_logic.yaml b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_formal_logic.yaml new file mode 100644 index 00000000..225da2fb --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_formal_logic.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ne_template_yaml +process_docs: !function utils.process_formal_logic +tag: global_mmlu_full_ne_humanities_tasks +task: global_mmlu_full_ne_formal_logic diff --git a/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_global_facts.yaml b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_global_facts.yaml new file mode 100644 index 00000000..6f5e9f1b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_global_facts.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ne_template_yaml +process_docs: !function utils.process_global_facts +tag: global_mmlu_full_ne_other_tasks +task: global_mmlu_full_ne_global_facts diff --git a/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_high_school_biology.yaml b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_high_school_biology.yaml new file mode 100644 index 00000000..a8c0436a --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_high_school_biology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ne_template_yaml +process_docs: !function utils.process_high_school_biology +tag: global_mmlu_full_ne_stem_tasks +task: global_mmlu_full_ne_high_school_biology diff --git a/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_high_school_chemistry.yaml b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_high_school_chemistry.yaml new file mode 100644 index 00000000..405661c7 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_high_school_chemistry.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ne_template_yaml +process_docs: !function utils.process_high_school_chemistry +tag: global_mmlu_full_ne_stem_tasks +task: global_mmlu_full_ne_high_school_chemistry diff --git a/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_high_school_computer_science.yaml b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_high_school_computer_science.yaml new file mode 100644 index 00000000..6cff5ba6 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_high_school_computer_science.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ne_template_yaml +process_docs: !function utils.process_high_school_computer_science +tag: global_mmlu_full_ne_stem_tasks +task: global_mmlu_full_ne_high_school_computer_science diff --git a/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_high_school_european_history.yaml b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_high_school_european_history.yaml new file mode 100644 index 00000000..4f7eb3ee --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_high_school_european_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ne_template_yaml +process_docs: !function utils.process_high_school_european_history +tag: global_mmlu_full_ne_humanities_tasks +task: global_mmlu_full_ne_high_school_european_history diff --git a/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_high_school_geography.yaml b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_high_school_geography.yaml new file mode 100644 index 00000000..0453e51d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_high_school_geography.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ne_template_yaml +process_docs: !function utils.process_high_school_geography +tag: global_mmlu_full_ne_social_sciences_tasks +task: global_mmlu_full_ne_high_school_geography diff --git a/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_high_school_government_and_politics.yaml b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_high_school_government_and_politics.yaml new file mode 100644 index 00000000..05710100 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_high_school_government_and_politics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ne_template_yaml +process_docs: !function utils.process_high_school_government_and_politics +tag: global_mmlu_full_ne_social_sciences_tasks +task: global_mmlu_full_ne_high_school_government_and_politics diff --git a/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_high_school_macroeconomics.yaml b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_high_school_macroeconomics.yaml new file mode 100644 index 00000000..fd68d5f0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_high_school_macroeconomics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ne_template_yaml +process_docs: !function utils.process_high_school_macroeconomics +tag: global_mmlu_full_ne_social_sciences_tasks +task: global_mmlu_full_ne_high_school_macroeconomics diff --git a/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_high_school_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_high_school_mathematics.yaml new file mode 100644 index 00000000..39ef0a58 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_high_school_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ne_template_yaml +process_docs: !function utils.process_high_school_mathematics +tag: global_mmlu_full_ne_stem_tasks +task: global_mmlu_full_ne_high_school_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_high_school_microeconomics.yaml b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_high_school_microeconomics.yaml new file mode 100644 index 00000000..535a3918 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_high_school_microeconomics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ne_template_yaml +process_docs: !function utils.process_high_school_microeconomics +tag: global_mmlu_full_ne_social_sciences_tasks +task: global_mmlu_full_ne_high_school_microeconomics diff --git a/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_high_school_physics.yaml b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_high_school_physics.yaml new file mode 100644 index 00000000..f355dad2 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_high_school_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ne_template_yaml +process_docs: !function utils.process_high_school_physics +tag: global_mmlu_full_ne_stem_tasks +task: global_mmlu_full_ne_high_school_physics diff --git a/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_high_school_psychology.yaml b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_high_school_psychology.yaml new file mode 100644 index 00000000..a52d7a01 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_high_school_psychology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ne_template_yaml +process_docs: !function utils.process_high_school_psychology +tag: global_mmlu_full_ne_social_sciences_tasks +task: global_mmlu_full_ne_high_school_psychology diff --git a/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_high_school_statistics.yaml b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_high_school_statistics.yaml new file mode 100644 index 00000000..5a256420 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_high_school_statistics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ne_template_yaml +process_docs: !function utils.process_high_school_statistics +tag: global_mmlu_full_ne_stem_tasks +task: global_mmlu_full_ne_high_school_statistics diff --git a/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_high_school_us_history.yaml b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_high_school_us_history.yaml new file mode 100644 index 00000000..9e1199b1 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_high_school_us_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ne_template_yaml +process_docs: !function utils.process_high_school_us_history +tag: global_mmlu_full_ne_humanities_tasks +task: global_mmlu_full_ne_high_school_us_history diff --git a/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_high_school_world_history.yaml b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_high_school_world_history.yaml new file mode 100644 index 00000000..afc2135b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_high_school_world_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ne_template_yaml +process_docs: !function utils.process_high_school_world_history +tag: global_mmlu_full_ne_humanities_tasks +task: global_mmlu_full_ne_high_school_world_history diff --git a/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_human_aging.yaml b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_human_aging.yaml new file mode 100644 index 00000000..18450534 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_human_aging.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ne_template_yaml +process_docs: !function utils.process_human_aging +tag: global_mmlu_full_ne_other_tasks +task: global_mmlu_full_ne_human_aging diff --git a/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_human_sexuality.yaml b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_human_sexuality.yaml new file mode 100644 index 00000000..7d23b839 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_human_sexuality.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ne_template_yaml +process_docs: !function utils.process_human_sexuality +tag: global_mmlu_full_ne_social_sciences_tasks +task: global_mmlu_full_ne_human_sexuality diff --git a/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_international_law.yaml b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_international_law.yaml new file mode 100644 index 00000000..5be599d2 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_international_law.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ne_template_yaml +process_docs: !function utils.process_international_law +tag: global_mmlu_full_ne_humanities_tasks +task: global_mmlu_full_ne_international_law diff --git a/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_jurisprudence.yaml b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_jurisprudence.yaml new file mode 100644 index 00000000..180a397c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_jurisprudence.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ne_template_yaml +process_docs: !function utils.process_jurisprudence +tag: global_mmlu_full_ne_humanities_tasks +task: global_mmlu_full_ne_jurisprudence diff --git a/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_logical_fallacies.yaml b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_logical_fallacies.yaml new file mode 100644 index 00000000..3aa369a9 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_logical_fallacies.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ne_template_yaml +process_docs: !function utils.process_logical_fallacies +tag: global_mmlu_full_ne_humanities_tasks +task: global_mmlu_full_ne_logical_fallacies diff --git a/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_machine_learning.yaml b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_machine_learning.yaml new file mode 100644 index 00000000..4e08abda --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_machine_learning.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ne_template_yaml +process_docs: !function utils.process_machine_learning +tag: global_mmlu_full_ne_stem_tasks +task: global_mmlu_full_ne_machine_learning diff --git a/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_management.yaml b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_management.yaml new file mode 100644 index 00000000..e44c5be6 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_management.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ne_template_yaml +process_docs: !function utils.process_management +tag: global_mmlu_full_ne_other_tasks +task: global_mmlu_full_ne_management diff --git a/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_marketing.yaml b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_marketing.yaml new file mode 100644 index 00000000..10f7daa2 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_marketing.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ne_template_yaml +process_docs: !function utils.process_marketing +tag: global_mmlu_full_ne_other_tasks +task: global_mmlu_full_ne_marketing diff --git a/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_medical_genetics.yaml b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_medical_genetics.yaml new file mode 100644 index 00000000..8139b1f7 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_medical_genetics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ne_template_yaml +process_docs: !function utils.process_medical_genetics +tag: global_mmlu_full_ne_other_tasks +task: global_mmlu_full_ne_medical_genetics diff --git a/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_miscellaneous.yaml b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_miscellaneous.yaml new file mode 100644 index 00000000..cb1bf905 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_miscellaneous.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ne_template_yaml +process_docs: !function utils.process_miscellaneous +tag: global_mmlu_full_ne_other_tasks +task: global_mmlu_full_ne_miscellaneous diff --git a/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_moral_disputes.yaml b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_moral_disputes.yaml new file mode 100644 index 00000000..1b74fb36 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_moral_disputes.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ne_template_yaml +process_docs: !function utils.process_moral_disputes +tag: global_mmlu_full_ne_humanities_tasks +task: global_mmlu_full_ne_moral_disputes diff --git a/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_moral_scenarios.yaml b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_moral_scenarios.yaml new file mode 100644 index 00000000..91f8f06c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_moral_scenarios.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ne_template_yaml +process_docs: !function utils.process_moral_scenarios +tag: global_mmlu_full_ne_humanities_tasks +task: global_mmlu_full_ne_moral_scenarios diff --git a/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_nutrition.yaml b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_nutrition.yaml new file mode 100644 index 00000000..575f0e45 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_nutrition.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ne_template_yaml +process_docs: !function utils.process_nutrition +tag: global_mmlu_full_ne_other_tasks +task: global_mmlu_full_ne_nutrition diff --git a/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_philosophy.yaml b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_philosophy.yaml new file mode 100644 index 00000000..95fdd0eb --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_philosophy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ne_template_yaml +process_docs: !function utils.process_philosophy +tag: global_mmlu_full_ne_humanities_tasks +task: global_mmlu_full_ne_philosophy diff --git a/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_prehistory.yaml b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_prehistory.yaml new file mode 100644 index 00000000..e6e5c706 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_prehistory.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ne_template_yaml +process_docs: !function utils.process_prehistory +tag: global_mmlu_full_ne_humanities_tasks +task: global_mmlu_full_ne_prehistory diff --git a/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_professional_accounting.yaml b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_professional_accounting.yaml new file mode 100644 index 00000000..718cedee --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_professional_accounting.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ne_template_yaml +process_docs: !function utils.process_professional_accounting +tag: global_mmlu_full_ne_other_tasks +task: global_mmlu_full_ne_professional_accounting diff --git a/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_professional_law.yaml b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_professional_law.yaml new file mode 100644 index 00000000..89c70160 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_professional_law.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ne_template_yaml +process_docs: !function utils.process_professional_law +tag: global_mmlu_full_ne_humanities_tasks +task: global_mmlu_full_ne_professional_law diff --git a/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_professional_medicine.yaml b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_professional_medicine.yaml new file mode 100644 index 00000000..a366e0c4 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_professional_medicine.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ne_template_yaml +process_docs: !function utils.process_professional_medicine +tag: global_mmlu_full_ne_other_tasks +task: global_mmlu_full_ne_professional_medicine diff --git a/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_professional_psychology.yaml b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_professional_psychology.yaml new file mode 100644 index 00000000..649e5343 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_professional_psychology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ne_template_yaml +process_docs: !function utils.process_professional_psychology +tag: global_mmlu_full_ne_social_sciences_tasks +task: global_mmlu_full_ne_professional_psychology diff --git a/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_public_relations.yaml b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_public_relations.yaml new file mode 100644 index 00000000..37f2ddea --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_public_relations.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ne_template_yaml +process_docs: !function utils.process_public_relations +tag: global_mmlu_full_ne_social_sciences_tasks +task: global_mmlu_full_ne_public_relations diff --git a/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_security_studies.yaml b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_security_studies.yaml new file mode 100644 index 00000000..55f80904 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_security_studies.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ne_template_yaml +process_docs: !function utils.process_security_studies +tag: global_mmlu_full_ne_social_sciences_tasks +task: global_mmlu_full_ne_security_studies diff --git a/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_sociology.yaml b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_sociology.yaml new file mode 100644 index 00000000..78161d5a --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_sociology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ne_template_yaml +process_docs: !function utils.process_sociology +tag: global_mmlu_full_ne_social_sciences_tasks +task: global_mmlu_full_ne_sociology diff --git a/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_us_foreign_policy.yaml b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_us_foreign_policy.yaml new file mode 100644 index 00000000..c38f59c4 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_us_foreign_policy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ne_template_yaml +process_docs: !function utils.process_us_foreign_policy +tag: global_mmlu_full_ne_social_sciences_tasks +task: global_mmlu_full_ne_us_foreign_policy diff --git a/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_virology.yaml b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_virology.yaml new file mode 100644 index 00000000..0c15808f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_virology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ne_template_yaml +process_docs: !function utils.process_virology +tag: global_mmlu_full_ne_other_tasks +task: global_mmlu_full_ne_virology diff --git a/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_world_religions.yaml b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_world_religions.yaml new file mode 100644 index 00000000..5c6163f1 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ne/global_mmlu_full_ne_world_religions.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ne_template_yaml +process_docs: !function utils.process_world_religions +tag: global_mmlu_full_ne_humanities_tasks +task: global_mmlu_full_ne_world_religions diff --git a/lm_eval/tasks/global_mmlu/full/ne/utils.py b/lm_eval/tasks/global_mmlu/full/ne/utils.py new file mode 100644 index 00000000..7df72cb0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ne/utils.py @@ -0,0 +1,73 @@ +from functools import partial + + +SUBJECTS = [ + "abstract_algebra", + "anatomy", + "astronomy", + "business_ethics", + "clinical_knowledge", + "college_biology", + "college_chemistry", + "college_computer_science", + "college_mathematics", + "college_medicine", + "college_physics", + "computer_security", + "conceptual_physics", + "econometrics", + "electrical_engineering", + "elementary_mathematics", + "formal_logic", + "global_facts", + "high_school_biology", + "high_school_chemistry", + "high_school_computer_science", + "high_school_european_history", + "high_school_geography", + "high_school_government_and_politics", + "high_school_macroeconomics", + "high_school_mathematics", + "high_school_microeconomics", + "high_school_physics", + "high_school_psychology", + "high_school_statistics", + "high_school_us_history", + "high_school_world_history", + "human_aging", + "human_sexuality", + "international_law", + "jurisprudence", + "logical_fallacies", + "machine_learning", + "management", + "marketing", + "medical_genetics", + "miscellaneous", + "moral_disputes", + "moral_scenarios", + "nutrition", + "philosophy", + "prehistory", + "professional_accounting", + "professional_law", + "professional_medicine", + "professional_psychology", + "public_relations", + "security_studies", + "sociology", + "us_foreign_policy", + "virology", + "world_religions", +] + + +def process_docs(dataset, subject): + return dataset.filter(lambda x: x["subject"] == subject) + + +process_functions = { + f"process_{subject}": partial(process_docs, subject=subject) for subject in SUBJECTS +} + +globals().update(process_functions) diff --git a/lm_eval/tasks/global_mmlu/full/nl/_global_mmlu_full_nl.yaml b/lm_eval/tasks/global_mmlu/full/nl/_global_mmlu_full_nl.yaml new file mode 100644 index 00000000..44f562da --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/nl/_global_mmlu_full_nl.yaml @@ -0,0 +1,11 @@ +group: global_mmlu_full_nl +task: + - global_mmlu_full_nl_stem + - global_mmlu_full_nl_other + - global_mmlu_full_nl_social_sciences + - global_mmlu_full_nl_humanities +aggregate_metric_list: + - metric: acc + weight_by_size: True +metadata: + version: 1.0 diff --git a/lm_eval/tasks/global_mmlu/full/nl/_global_mmlu_full_nl_humanities.yaml b/lm_eval/tasks/global_mmlu/full/nl/_global_mmlu_full_nl_humanities.yaml new file mode 100644 index 00000000..656a421b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/nl/_global_mmlu_full_nl_humanities.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_nl_humanities +task: + - global_mmlu_full_nl_humanities_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/nl/_global_mmlu_full_nl_other.yaml b/lm_eval/tasks/global_mmlu/full/nl/_global_mmlu_full_nl_other.yaml new file mode 100644 index 00000000..23a42201 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/nl/_global_mmlu_full_nl_other.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_nl_other +task: + - global_mmlu_full_nl_other_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/nl/_global_mmlu_full_nl_social_sciences.yaml b/lm_eval/tasks/global_mmlu/full/nl/_global_mmlu_full_nl_social_sciences.yaml new file mode 100644 index 00000000..afba5678 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/nl/_global_mmlu_full_nl_social_sciences.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_nl_social_sciences +task: + - global_mmlu_full_nl_social_sciences_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/nl/_global_mmlu_full_nl_stem.yaml b/lm_eval/tasks/global_mmlu/full/nl/_global_mmlu_full_nl_stem.yaml new file mode 100644 index 00000000..9658b13e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/nl/_global_mmlu_full_nl_stem.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_nl_stem +task: + - global_mmlu_full_nl_stem_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/nl/_nl_template_yaml b/lm_eval/tasks/global_mmlu/full/nl/_nl_template_yaml new file mode 100644 index 00000000..39efbfd1 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/nl/_nl_template_yaml @@ -0,0 +1,16 @@ +dataset_path: CohereForAI/Global-MMLU +dataset_name: nl +test_split: test +fewshot_split: dev +fewshot_config: + sampler: first_n +output_type: multiple_choice +doc_to_text: "{{question.strip()}}\nA. {{option_a}}\nB. {{option_b}}\nC. {{option_c}}\nD. {{option_d}}\nAnswer:" +doc_to_choice: ["A", "B", "C", "D"] +doc_to_target: answer +metric_list: + - metric: acc + aggregation: mean + higher_is_better: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_abstract_algebra.yaml b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_abstract_algebra.yaml new file mode 100644 index 00000000..458a3614 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_abstract_algebra.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _nl_template_yaml +process_docs: !function utils.process_abstract_algebra +tag: global_mmlu_full_nl_stem_tasks +task: global_mmlu_full_nl_abstract_algebra diff --git a/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_anatomy.yaml b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_anatomy.yaml new file mode 100644 index 00000000..e4cbd90e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_anatomy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _nl_template_yaml +process_docs: !function utils.process_anatomy +tag: global_mmlu_full_nl_stem_tasks +task: global_mmlu_full_nl_anatomy diff --git a/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_astronomy.yaml b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_astronomy.yaml new file mode 100644 index 00000000..84cdf578 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_astronomy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _nl_template_yaml +process_docs: !function utils.process_astronomy +tag: global_mmlu_full_nl_stem_tasks +task: global_mmlu_full_nl_astronomy diff --git a/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_business_ethics.yaml b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_business_ethics.yaml new file mode 100644 index 00000000..f75776f2 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_business_ethics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _nl_template_yaml +process_docs: !function utils.process_business_ethics +tag: global_mmlu_full_nl_other_tasks +task: global_mmlu_full_nl_business_ethics diff --git a/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_clinical_knowledge.yaml b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_clinical_knowledge.yaml new file mode 100644 index 00000000..6e963d0f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_clinical_knowledge.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _nl_template_yaml +process_docs: !function utils.process_clinical_knowledge +tag: global_mmlu_full_nl_other_tasks +task: global_mmlu_full_nl_clinical_knowledge diff --git a/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_college_biology.yaml b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_college_biology.yaml new file mode 100644 index 00000000..e4a3660b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_college_biology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _nl_template_yaml +process_docs: !function utils.process_college_biology +tag: global_mmlu_full_nl_stem_tasks +task: global_mmlu_full_nl_college_biology diff --git a/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_college_chemistry.yaml b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_college_chemistry.yaml new file mode 100644 index 00000000..fa9faed9 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_college_chemistry.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _nl_template_yaml +process_docs: !function utils.process_college_chemistry +tag: global_mmlu_full_nl_stem_tasks +task: global_mmlu_full_nl_college_chemistry diff --git a/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_college_computer_science.yaml b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_college_computer_science.yaml new file mode 100644 index 00000000..b603c309 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_college_computer_science.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _nl_template_yaml +process_docs: !function utils.process_college_computer_science +tag: global_mmlu_full_nl_stem_tasks +task: global_mmlu_full_nl_college_computer_science diff --git a/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_college_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_college_mathematics.yaml new file mode 100644 index 00000000..f55207ea --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_college_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _nl_template_yaml +process_docs: !function utils.process_college_mathematics +tag: global_mmlu_full_nl_stem_tasks +task: global_mmlu_full_nl_college_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_college_medicine.yaml b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_college_medicine.yaml new file mode 100644 index 00000000..5cdda1b7 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_college_medicine.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _nl_template_yaml +process_docs: !function utils.process_college_medicine +tag: global_mmlu_full_nl_other_tasks +task: global_mmlu_full_nl_college_medicine diff --git a/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_college_physics.yaml b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_college_physics.yaml new file mode 100644 index 00000000..26d70230 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_college_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _nl_template_yaml +process_docs: !function utils.process_college_physics +tag: global_mmlu_full_nl_stem_tasks +task: global_mmlu_full_nl_college_physics diff --git a/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_computer_security.yaml b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_computer_security.yaml new file mode 100644 index 00000000..01a8a747 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_computer_security.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _nl_template_yaml +process_docs: !function utils.process_computer_security +tag: global_mmlu_full_nl_stem_tasks +task: global_mmlu_full_nl_computer_security diff --git a/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_conceptual_physics.yaml b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_conceptual_physics.yaml new file mode 100644 index 00000000..cccd2666 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_conceptual_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _nl_template_yaml +process_docs: !function utils.process_conceptual_physics +tag: global_mmlu_full_nl_stem_tasks +task: global_mmlu_full_nl_conceptual_physics diff --git a/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_econometrics.yaml b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_econometrics.yaml new file mode 100644 index 00000000..22ad59bd --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_econometrics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _nl_template_yaml +process_docs: !function utils.process_econometrics +tag: global_mmlu_full_nl_social_sciences_tasks +task: global_mmlu_full_nl_econometrics diff --git a/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_electrical_engineering.yaml b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_electrical_engineering.yaml new file mode 100644 index 00000000..3aca226f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_electrical_engineering.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _nl_template_yaml +process_docs: !function utils.process_electrical_engineering +tag: global_mmlu_full_nl_stem_tasks +task: global_mmlu_full_nl_electrical_engineering diff --git a/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_elementary_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_elementary_mathematics.yaml new file mode 100644 index 00000000..2118a1d5 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_elementary_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _nl_template_yaml +process_docs: !function utils.process_elementary_mathematics +tag: global_mmlu_full_nl_stem_tasks +task: global_mmlu_full_nl_elementary_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_formal_logic.yaml b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_formal_logic.yaml new file mode 100644 index 00000000..5fd86105 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_formal_logic.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _nl_template_yaml +process_docs: !function utils.process_formal_logic +tag: global_mmlu_full_nl_humanities_tasks +task: global_mmlu_full_nl_formal_logic diff --git a/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_global_facts.yaml b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_global_facts.yaml new file mode 100644 index 00000000..d7147d51 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_global_facts.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _nl_template_yaml +process_docs: !function utils.process_global_facts +tag: global_mmlu_full_nl_other_tasks +task: global_mmlu_full_nl_global_facts diff --git a/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_high_school_biology.yaml b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_high_school_biology.yaml new file mode 100644 index 00000000..271b54f6 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_high_school_biology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _nl_template_yaml +process_docs: !function utils.process_high_school_biology +tag: global_mmlu_full_nl_stem_tasks +task: global_mmlu_full_nl_high_school_biology diff --git a/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_high_school_chemistry.yaml b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_high_school_chemistry.yaml new file mode 100644 index 00000000..921abd17 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_high_school_chemistry.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _nl_template_yaml +process_docs: !function utils.process_high_school_chemistry +tag: global_mmlu_full_nl_stem_tasks +task: global_mmlu_full_nl_high_school_chemistry diff --git a/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_high_school_computer_science.yaml b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_high_school_computer_science.yaml new file mode 100644 index 00000000..ea190bea --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_high_school_computer_science.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _nl_template_yaml +process_docs: !function utils.process_high_school_computer_science +tag: global_mmlu_full_nl_stem_tasks +task: global_mmlu_full_nl_high_school_computer_science diff --git a/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_high_school_european_history.yaml b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_high_school_european_history.yaml new file mode 100644 index 00000000..c348d482 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_high_school_european_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _nl_template_yaml +process_docs: !function utils.process_high_school_european_history +tag: global_mmlu_full_nl_humanities_tasks +task: global_mmlu_full_nl_high_school_european_history diff --git a/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_high_school_geography.yaml b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_high_school_geography.yaml new file mode 100644 index 00000000..de31a63b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_high_school_geography.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _nl_template_yaml +process_docs: !function utils.process_high_school_geography +tag: global_mmlu_full_nl_social_sciences_tasks +task: global_mmlu_full_nl_high_school_geography diff --git a/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_high_school_government_and_politics.yaml b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_high_school_government_and_politics.yaml new file mode 100644 index 00000000..bc0e3cb1 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_high_school_government_and_politics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _nl_template_yaml +process_docs: !function utils.process_high_school_government_and_politics +tag: global_mmlu_full_nl_social_sciences_tasks +task: global_mmlu_full_nl_high_school_government_and_politics diff --git a/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_high_school_macroeconomics.yaml b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_high_school_macroeconomics.yaml new file mode 100644 index 00000000..2e221c68 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_high_school_macroeconomics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _nl_template_yaml +process_docs: !function utils.process_high_school_macroeconomics +tag: global_mmlu_full_nl_social_sciences_tasks +task: global_mmlu_full_nl_high_school_macroeconomics diff --git a/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_high_school_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_high_school_mathematics.yaml new file mode 100644 index 00000000..137158a6 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_high_school_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _nl_template_yaml +process_docs: !function utils.process_high_school_mathematics +tag: global_mmlu_full_nl_stem_tasks +task: global_mmlu_full_nl_high_school_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_high_school_microeconomics.yaml b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_high_school_microeconomics.yaml new file mode 100644 index 00000000..27b426c0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_high_school_microeconomics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _nl_template_yaml +process_docs: !function utils.process_high_school_microeconomics +tag: global_mmlu_full_nl_social_sciences_tasks +task: global_mmlu_full_nl_high_school_microeconomics diff --git a/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_high_school_physics.yaml b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_high_school_physics.yaml new file mode 100644 index 00000000..746df49e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_high_school_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _nl_template_yaml +process_docs: !function utils.process_high_school_physics +tag: global_mmlu_full_nl_stem_tasks +task: global_mmlu_full_nl_high_school_physics diff --git a/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_high_school_psychology.yaml b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_high_school_psychology.yaml new file mode 100644 index 00000000..89cb42d9 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_high_school_psychology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _nl_template_yaml +process_docs: !function utils.process_high_school_psychology +tag: global_mmlu_full_nl_social_sciences_tasks +task: global_mmlu_full_nl_high_school_psychology diff --git a/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_high_school_statistics.yaml b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_high_school_statistics.yaml new file mode 100644 index 00000000..e27082c4 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_high_school_statistics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _nl_template_yaml +process_docs: !function utils.process_high_school_statistics +tag: global_mmlu_full_nl_stem_tasks +task: global_mmlu_full_nl_high_school_statistics diff --git a/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_high_school_us_history.yaml b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_high_school_us_history.yaml new file mode 100644 index 00000000..66efc58c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_high_school_us_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _nl_template_yaml +process_docs: !function utils.process_high_school_us_history +tag: global_mmlu_full_nl_humanities_tasks +task: global_mmlu_full_nl_high_school_us_history diff --git a/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_high_school_world_history.yaml b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_high_school_world_history.yaml new file mode 100644 index 00000000..83b65345 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_high_school_world_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _nl_template_yaml +process_docs: !function utils.process_high_school_world_history +tag: global_mmlu_full_nl_humanities_tasks +task: global_mmlu_full_nl_high_school_world_history diff --git a/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_human_aging.yaml b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_human_aging.yaml new file mode 100644 index 00000000..82e00b4b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_human_aging.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _nl_template_yaml +process_docs: !function utils.process_human_aging +tag: global_mmlu_full_nl_other_tasks +task: global_mmlu_full_nl_human_aging diff --git a/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_human_sexuality.yaml b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_human_sexuality.yaml new file mode 100644 index 00000000..468589da --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_human_sexuality.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _nl_template_yaml +process_docs: !function utils.process_human_sexuality +tag: global_mmlu_full_nl_social_sciences_tasks +task: global_mmlu_full_nl_human_sexuality diff --git a/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_international_law.yaml b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_international_law.yaml new file mode 100644 index 00000000..e5bf62a9 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_international_law.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _nl_template_yaml +process_docs: !function utils.process_international_law +tag: global_mmlu_full_nl_humanities_tasks +task: global_mmlu_full_nl_international_law diff --git a/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_jurisprudence.yaml b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_jurisprudence.yaml new file mode 100644 index 00000000..7b533613 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_jurisprudence.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _nl_template_yaml +process_docs: !function utils.process_jurisprudence +tag: global_mmlu_full_nl_humanities_tasks +task: global_mmlu_full_nl_jurisprudence diff --git a/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_logical_fallacies.yaml b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_logical_fallacies.yaml new file mode 100644 index 00000000..de862b66 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_logical_fallacies.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _nl_template_yaml +process_docs: !function utils.process_logical_fallacies +tag: global_mmlu_full_nl_humanities_tasks +task: global_mmlu_full_nl_logical_fallacies diff --git a/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_machine_learning.yaml b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_machine_learning.yaml new file mode 100644 index 00000000..c205af00 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_machine_learning.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _nl_template_yaml +process_docs: !function utils.process_machine_learning +tag: global_mmlu_full_nl_stem_tasks +task: global_mmlu_full_nl_machine_learning diff --git a/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_management.yaml b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_management.yaml new file mode 100644 index 00000000..5b624af8 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_management.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _nl_template_yaml +process_docs: !function utils.process_management +tag: global_mmlu_full_nl_other_tasks +task: global_mmlu_full_nl_management diff --git a/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_marketing.yaml b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_marketing.yaml new file mode 100644 index 00000000..81658e9f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_marketing.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _nl_template_yaml +process_docs: !function utils.process_marketing +tag: global_mmlu_full_nl_other_tasks +task: global_mmlu_full_nl_marketing diff --git a/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_medical_genetics.yaml b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_medical_genetics.yaml new file mode 100644 index 00000000..f8e52c0d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_medical_genetics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _nl_template_yaml +process_docs: !function utils.process_medical_genetics +tag: global_mmlu_full_nl_other_tasks +task: global_mmlu_full_nl_medical_genetics diff --git a/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_miscellaneous.yaml b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_miscellaneous.yaml new file mode 100644 index 00000000..31af482e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_miscellaneous.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _nl_template_yaml +process_docs: !function utils.process_miscellaneous +tag: global_mmlu_full_nl_other_tasks +task: global_mmlu_full_nl_miscellaneous diff --git a/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_moral_disputes.yaml b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_moral_disputes.yaml new file mode 100644 index 00000000..853de0c1 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_moral_disputes.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _nl_template_yaml +process_docs: !function utils.process_moral_disputes +tag: global_mmlu_full_nl_humanities_tasks +task: global_mmlu_full_nl_moral_disputes diff --git a/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_moral_scenarios.yaml b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_moral_scenarios.yaml new file mode 100644 index 00000000..8b86e045 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_moral_scenarios.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _nl_template_yaml +process_docs: !function utils.process_moral_scenarios +tag: global_mmlu_full_nl_humanities_tasks +task: global_mmlu_full_nl_moral_scenarios diff --git a/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_nutrition.yaml b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_nutrition.yaml new file mode 100644 index 00000000..96036dae --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_nutrition.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _nl_template_yaml +process_docs: !function utils.process_nutrition +tag: global_mmlu_full_nl_other_tasks +task: global_mmlu_full_nl_nutrition diff --git a/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_philosophy.yaml b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_philosophy.yaml new file mode 100644 index 00000000..84e827dd --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_philosophy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _nl_template_yaml +process_docs: !function utils.process_philosophy +tag: global_mmlu_full_nl_humanities_tasks +task: global_mmlu_full_nl_philosophy diff --git a/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_prehistory.yaml b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_prehistory.yaml new file mode 100644 index 00000000..f49c8a5e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_prehistory.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _nl_template_yaml +process_docs: !function utils.process_prehistory +tag: global_mmlu_full_nl_humanities_tasks +task: global_mmlu_full_nl_prehistory diff --git a/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_professional_accounting.yaml b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_professional_accounting.yaml new file mode 100644 index 00000000..45484116 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_professional_accounting.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _nl_template_yaml +process_docs: !function utils.process_professional_accounting +tag: global_mmlu_full_nl_other_tasks +task: global_mmlu_full_nl_professional_accounting diff --git a/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_professional_law.yaml b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_professional_law.yaml new file mode 100644 index 00000000..17b28cd3 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_professional_law.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _nl_template_yaml +process_docs: !function utils.process_professional_law +tag: global_mmlu_full_nl_humanities_tasks +task: global_mmlu_full_nl_professional_law diff --git a/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_professional_medicine.yaml b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_professional_medicine.yaml new file mode 100644 index 00000000..f4db01bc --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_professional_medicine.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _nl_template_yaml +process_docs: !function utils.process_professional_medicine +tag: global_mmlu_full_nl_other_tasks +task: global_mmlu_full_nl_professional_medicine diff --git a/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_professional_psychology.yaml b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_professional_psychology.yaml new file mode 100644 index 00000000..be586b45 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_professional_psychology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _nl_template_yaml +process_docs: !function utils.process_professional_psychology +tag: global_mmlu_full_nl_social_sciences_tasks +task: global_mmlu_full_nl_professional_psychology diff --git a/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_public_relations.yaml b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_public_relations.yaml new file mode 100644 index 00000000..2ffe5848 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_public_relations.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _nl_template_yaml +process_docs: !function utils.process_public_relations +tag: global_mmlu_full_nl_social_sciences_tasks +task: global_mmlu_full_nl_public_relations diff --git a/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_security_studies.yaml b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_security_studies.yaml new file mode 100644 index 00000000..b6c76948 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_security_studies.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _nl_template_yaml +process_docs: !function utils.process_security_studies +tag: global_mmlu_full_nl_social_sciences_tasks +task: global_mmlu_full_nl_security_studies diff --git a/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_sociology.yaml b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_sociology.yaml new file mode 100644 index 00000000..983e13cd --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_sociology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _nl_template_yaml +process_docs: !function utils.process_sociology +tag: global_mmlu_full_nl_social_sciences_tasks +task: global_mmlu_full_nl_sociology diff --git a/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_us_foreign_policy.yaml b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_us_foreign_policy.yaml new file mode 100644 index 00000000..bd6b6227 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_us_foreign_policy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _nl_template_yaml +process_docs: !function utils.process_us_foreign_policy +tag: global_mmlu_full_nl_social_sciences_tasks +task: global_mmlu_full_nl_us_foreign_policy diff --git a/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_virology.yaml b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_virology.yaml new file mode 100644 index 00000000..92d1973b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_virology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _nl_template_yaml +process_docs: !function utils.process_virology +tag: global_mmlu_full_nl_other_tasks +task: global_mmlu_full_nl_virology diff --git a/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_world_religions.yaml b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_world_religions.yaml new file mode 100644 index 00000000..a8c2ecca --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/nl/global_mmlu_full_nl_world_religions.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _nl_template_yaml +process_docs: !function utils.process_world_religions +tag: global_mmlu_full_nl_humanities_tasks +task: global_mmlu_full_nl_world_religions diff --git a/lm_eval/tasks/global_mmlu/full/nl/utils.py b/lm_eval/tasks/global_mmlu/full/nl/utils.py new file mode 100644 index 00000000..7df72cb0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/nl/utils.py @@ -0,0 +1,73 @@ +from functools import partial + + +SUBJECTS = [ + "abstract_algebra", + "anatomy", + "astronomy", + "business_ethics", + "clinical_knowledge", + "college_biology", + "college_chemistry", + "college_computer_science", + "college_mathematics", + "college_medicine", + "college_physics", + "computer_security", + "conceptual_physics", + "econometrics", + "electrical_engineering", + "elementary_mathematics", + "formal_logic", + "global_facts", + "high_school_biology", + "high_school_chemistry", + "high_school_computer_science", + "high_school_european_history", + "high_school_geography", + "high_school_government_and_politics", + "high_school_macroeconomics", + "high_school_mathematics", + "high_school_microeconomics", + "high_school_physics", + "high_school_psychology", + "high_school_statistics", + "high_school_us_history", + "high_school_world_history", + "human_aging", + "human_sexuality", + "international_law", + "jurisprudence", + "logical_fallacies", + "machine_learning", + "management", + "marketing", + "medical_genetics", + "miscellaneous", + "moral_disputes", + "moral_scenarios", + "nutrition", + "philosophy", + "prehistory", + "professional_accounting", + "professional_law", + "professional_medicine", + "professional_psychology", + "public_relations", + "security_studies", + "sociology", + "us_foreign_policy", + "virology", + "world_religions", +] + + +def process_docs(dataset, subject): + return dataset.filter(lambda x: x["subject"] == subject) + + +process_functions = { + f"process_{subject}": partial(process_docs, subject=subject) for subject in SUBJECTS +} + +globals().update(process_functions) diff --git a/lm_eval/tasks/global_mmlu/full/ny/_global_mmlu_full_ny.yaml b/lm_eval/tasks/global_mmlu/full/ny/_global_mmlu_full_ny.yaml new file mode 100644 index 00000000..c325bf1d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ny/_global_mmlu_full_ny.yaml @@ -0,0 +1,11 @@ +group: global_mmlu_full_ny +task: + - global_mmlu_full_ny_stem + - global_mmlu_full_ny_other + - global_mmlu_full_ny_social_sciences + - global_mmlu_full_ny_humanities +aggregate_metric_list: + - metric: acc + weight_by_size: True +metadata: + version: 1.0 diff --git a/lm_eval/tasks/global_mmlu/full/ny/_global_mmlu_full_ny_humanities.yaml b/lm_eval/tasks/global_mmlu/full/ny/_global_mmlu_full_ny_humanities.yaml new file mode 100644 index 00000000..89e7618f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ny/_global_mmlu_full_ny_humanities.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_ny_humanities +task: + - global_mmlu_full_ny_humanities_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/ny/_global_mmlu_full_ny_other.yaml b/lm_eval/tasks/global_mmlu/full/ny/_global_mmlu_full_ny_other.yaml new file mode 100644 index 00000000..51b90446 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ny/_global_mmlu_full_ny_other.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_ny_other +task: + - global_mmlu_full_ny_other_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/ny/_global_mmlu_full_ny_social_sciences.yaml b/lm_eval/tasks/global_mmlu/full/ny/_global_mmlu_full_ny_social_sciences.yaml new file mode 100644 index 00000000..b711dfdf --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ny/_global_mmlu_full_ny_social_sciences.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_ny_social_sciences +task: + - global_mmlu_full_ny_social_sciences_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/ny/_global_mmlu_full_ny_stem.yaml b/lm_eval/tasks/global_mmlu/full/ny/_global_mmlu_full_ny_stem.yaml new file mode 100644 index 00000000..99bf9d95 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ny/_global_mmlu_full_ny_stem.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_ny_stem +task: + - global_mmlu_full_ny_stem_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/ny/_ny_template_yaml b/lm_eval/tasks/global_mmlu/full/ny/_ny_template_yaml new file mode 100644 index 00000000..069a9446 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ny/_ny_template_yaml @@ -0,0 +1,16 @@ +dataset_path: CohereForAI/Global-MMLU +dataset_name: ny +test_split: test +fewshot_split: dev +fewshot_config: + sampler: first_n +output_type: multiple_choice +doc_to_text: "{{question.strip()}}\nA. {{option_a}}\nB. {{option_b}}\nC. {{option_c}}\nD. {{option_d}}\nAnswer:" +doc_to_choice: ["A", "B", "C", "D"] +doc_to_target: answer +metric_list: + - metric: acc + aggregation: mean + higher_is_better: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_abstract_algebra.yaml b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_abstract_algebra.yaml new file mode 100644 index 00000000..2e3d7c33 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_abstract_algebra.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ny_template_yaml +process_docs: !function utils.process_abstract_algebra +tag: global_mmlu_full_ny_stem_tasks +task: global_mmlu_full_ny_abstract_algebra diff --git a/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_anatomy.yaml b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_anatomy.yaml new file mode 100644 index 00000000..60806afc --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_anatomy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ny_template_yaml +process_docs: !function utils.process_anatomy +tag: global_mmlu_full_ny_stem_tasks +task: global_mmlu_full_ny_anatomy diff --git a/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_astronomy.yaml b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_astronomy.yaml new file mode 100644 index 00000000..afbcb482 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_astronomy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ny_template_yaml +process_docs: !function utils.process_astronomy +tag: global_mmlu_full_ny_stem_tasks +task: global_mmlu_full_ny_astronomy diff --git a/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_business_ethics.yaml b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_business_ethics.yaml new file mode 100644 index 00000000..6f8981bd --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_business_ethics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ny_template_yaml +process_docs: !function utils.process_business_ethics +tag: global_mmlu_full_ny_other_tasks +task: global_mmlu_full_ny_business_ethics diff --git a/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_clinical_knowledge.yaml b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_clinical_knowledge.yaml new file mode 100644 index 00000000..ff44dd67 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_clinical_knowledge.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ny_template_yaml +process_docs: !function utils.process_clinical_knowledge +tag: global_mmlu_full_ny_other_tasks +task: global_mmlu_full_ny_clinical_knowledge diff --git a/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_college_biology.yaml b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_college_biology.yaml new file mode 100644 index 00000000..da5ce370 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_college_biology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ny_template_yaml +process_docs: !function utils.process_college_biology +tag: global_mmlu_full_ny_stem_tasks +task: global_mmlu_full_ny_college_biology diff --git a/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_college_chemistry.yaml b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_college_chemistry.yaml new file mode 100644 index 00000000..d62bce83 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_college_chemistry.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ny_template_yaml +process_docs: !function utils.process_college_chemistry +tag: global_mmlu_full_ny_stem_tasks +task: global_mmlu_full_ny_college_chemistry diff --git a/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_college_computer_science.yaml b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_college_computer_science.yaml new file mode 100644 index 00000000..48cd98d5 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_college_computer_science.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ny_template_yaml +process_docs: !function utils.process_college_computer_science +tag: global_mmlu_full_ny_stem_tasks +task: global_mmlu_full_ny_college_computer_science diff --git a/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_college_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_college_mathematics.yaml new file mode 100644 index 00000000..ed77ba9c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_college_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ny_template_yaml +process_docs: !function utils.process_college_mathematics +tag: global_mmlu_full_ny_stem_tasks +task: global_mmlu_full_ny_college_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_college_medicine.yaml b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_college_medicine.yaml new file mode 100644 index 00000000..9cd8aa2f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_college_medicine.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ny_template_yaml +process_docs: !function utils.process_college_medicine +tag: global_mmlu_full_ny_other_tasks +task: global_mmlu_full_ny_college_medicine diff --git a/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_college_physics.yaml b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_college_physics.yaml new file mode 100644 index 00000000..66d5dc27 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_college_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ny_template_yaml +process_docs: !function utils.process_college_physics +tag: global_mmlu_full_ny_stem_tasks +task: global_mmlu_full_ny_college_physics diff --git a/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_computer_security.yaml b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_computer_security.yaml new file mode 100644 index 00000000..8a9dae62 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_computer_security.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ny_template_yaml +process_docs: !function utils.process_computer_security +tag: global_mmlu_full_ny_stem_tasks +task: global_mmlu_full_ny_computer_security diff --git a/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_conceptual_physics.yaml b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_conceptual_physics.yaml new file mode 100644 index 00000000..8d160ffc --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_conceptual_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ny_template_yaml +process_docs: !function utils.process_conceptual_physics +tag: global_mmlu_full_ny_stem_tasks +task: global_mmlu_full_ny_conceptual_physics diff --git a/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_econometrics.yaml b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_econometrics.yaml new file mode 100644 index 00000000..88af709a --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_econometrics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ny_template_yaml +process_docs: !function utils.process_econometrics +tag: global_mmlu_full_ny_social_sciences_tasks +task: global_mmlu_full_ny_econometrics diff --git a/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_electrical_engineering.yaml b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_electrical_engineering.yaml new file mode 100644 index 00000000..d835f1e0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_electrical_engineering.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ny_template_yaml +process_docs: !function utils.process_electrical_engineering +tag: global_mmlu_full_ny_stem_tasks +task: global_mmlu_full_ny_electrical_engineering diff --git a/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_elementary_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_elementary_mathematics.yaml new file mode 100644 index 00000000..558ffd0b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_elementary_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ny_template_yaml +process_docs: !function utils.process_elementary_mathematics +tag: global_mmlu_full_ny_stem_tasks +task: global_mmlu_full_ny_elementary_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_formal_logic.yaml b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_formal_logic.yaml new file mode 100644 index 00000000..cce0df19 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_formal_logic.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ny_template_yaml +process_docs: !function utils.process_formal_logic +tag: global_mmlu_full_ny_humanities_tasks +task: global_mmlu_full_ny_formal_logic diff --git a/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_global_facts.yaml b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_global_facts.yaml new file mode 100644 index 00000000..6ce027a5 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_global_facts.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ny_template_yaml +process_docs: !function utils.process_global_facts +tag: global_mmlu_full_ny_other_tasks +task: global_mmlu_full_ny_global_facts diff --git a/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_high_school_biology.yaml b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_high_school_biology.yaml new file mode 100644 index 00000000..a729008d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_high_school_biology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ny_template_yaml +process_docs: !function utils.process_high_school_biology +tag: global_mmlu_full_ny_stem_tasks +task: global_mmlu_full_ny_high_school_biology diff --git a/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_high_school_chemistry.yaml b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_high_school_chemistry.yaml new file mode 100644 index 00000000..79771bfb --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_high_school_chemistry.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ny_template_yaml +process_docs: !function utils.process_high_school_chemistry +tag: global_mmlu_full_ny_stem_tasks +task: global_mmlu_full_ny_high_school_chemistry diff --git a/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_high_school_computer_science.yaml b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_high_school_computer_science.yaml new file mode 100644 index 00000000..6889806f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_high_school_computer_science.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ny_template_yaml +process_docs: !function utils.process_high_school_computer_science +tag: global_mmlu_full_ny_stem_tasks +task: global_mmlu_full_ny_high_school_computer_science diff --git a/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_high_school_european_history.yaml b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_high_school_european_history.yaml new file mode 100644 index 00000000..29e6e4a5 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_high_school_european_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ny_template_yaml +process_docs: !function utils.process_high_school_european_history +tag: global_mmlu_full_ny_humanities_tasks +task: global_mmlu_full_ny_high_school_european_history diff --git a/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_high_school_geography.yaml b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_high_school_geography.yaml new file mode 100644 index 00000000..447db75f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_high_school_geography.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ny_template_yaml +process_docs: !function utils.process_high_school_geography +tag: global_mmlu_full_ny_social_sciences_tasks +task: global_mmlu_full_ny_high_school_geography diff --git a/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_high_school_government_and_politics.yaml b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_high_school_government_and_politics.yaml new file mode 100644 index 00000000..e543cf76 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_high_school_government_and_politics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ny_template_yaml +process_docs: !function utils.process_high_school_government_and_politics +tag: global_mmlu_full_ny_social_sciences_tasks +task: global_mmlu_full_ny_high_school_government_and_politics diff --git a/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_high_school_macroeconomics.yaml b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_high_school_macroeconomics.yaml new file mode 100644 index 00000000..61c49e75 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_high_school_macroeconomics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ny_template_yaml +process_docs: !function utils.process_high_school_macroeconomics +tag: global_mmlu_full_ny_social_sciences_tasks +task: global_mmlu_full_ny_high_school_macroeconomics diff --git a/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_high_school_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_high_school_mathematics.yaml new file mode 100644 index 00000000..db228d02 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_high_school_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ny_template_yaml +process_docs: !function utils.process_high_school_mathematics +tag: global_mmlu_full_ny_stem_tasks +task: global_mmlu_full_ny_high_school_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_high_school_microeconomics.yaml b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_high_school_microeconomics.yaml new file mode 100644 index 00000000..62d87c86 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_high_school_microeconomics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ny_template_yaml +process_docs: !function utils.process_high_school_microeconomics +tag: global_mmlu_full_ny_social_sciences_tasks +task: global_mmlu_full_ny_high_school_microeconomics diff --git a/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_high_school_physics.yaml b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_high_school_physics.yaml new file mode 100644 index 00000000..54c15d66 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_high_school_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ny_template_yaml +process_docs: !function utils.process_high_school_physics +tag: global_mmlu_full_ny_stem_tasks +task: global_mmlu_full_ny_high_school_physics diff --git a/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_high_school_psychology.yaml b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_high_school_psychology.yaml new file mode 100644 index 00000000..4f7d8b5a --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_high_school_psychology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ny_template_yaml +process_docs: !function utils.process_high_school_psychology +tag: global_mmlu_full_ny_social_sciences_tasks +task: global_mmlu_full_ny_high_school_psychology diff --git a/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_high_school_statistics.yaml b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_high_school_statistics.yaml new file mode 100644 index 00000000..f53235b8 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_high_school_statistics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ny_template_yaml +process_docs: !function utils.process_high_school_statistics +tag: global_mmlu_full_ny_stem_tasks +task: global_mmlu_full_ny_high_school_statistics diff --git a/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_high_school_us_history.yaml b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_high_school_us_history.yaml new file mode 100644 index 00000000..1d413b98 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_high_school_us_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ny_template_yaml +process_docs: !function utils.process_high_school_us_history +tag: global_mmlu_full_ny_humanities_tasks +task: global_mmlu_full_ny_high_school_us_history diff --git a/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_high_school_world_history.yaml b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_high_school_world_history.yaml new file mode 100644 index 00000000..4adf2e8b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_high_school_world_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ny_template_yaml +process_docs: !function utils.process_high_school_world_history +tag: global_mmlu_full_ny_humanities_tasks +task: global_mmlu_full_ny_high_school_world_history diff --git a/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_human_aging.yaml b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_human_aging.yaml new file mode 100644 index 00000000..9660b7b1 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_human_aging.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ny_template_yaml +process_docs: !function utils.process_human_aging +tag: global_mmlu_full_ny_other_tasks +task: global_mmlu_full_ny_human_aging diff --git a/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_human_sexuality.yaml b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_human_sexuality.yaml new file mode 100644 index 00000000..11a6f2d4 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_human_sexuality.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ny_template_yaml +process_docs: !function utils.process_human_sexuality +tag: global_mmlu_full_ny_social_sciences_tasks +task: global_mmlu_full_ny_human_sexuality diff --git a/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_international_law.yaml b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_international_law.yaml new file mode 100644 index 00000000..9a46ff6a --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_international_law.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ny_template_yaml +process_docs: !function utils.process_international_law +tag: global_mmlu_full_ny_humanities_tasks +task: global_mmlu_full_ny_international_law diff --git a/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_jurisprudence.yaml b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_jurisprudence.yaml new file mode 100644 index 00000000..e4606df5 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_jurisprudence.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ny_template_yaml +process_docs: !function utils.process_jurisprudence +tag: global_mmlu_full_ny_humanities_tasks +task: global_mmlu_full_ny_jurisprudence diff --git a/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_logical_fallacies.yaml b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_logical_fallacies.yaml new file mode 100644 index 00000000..6edade03 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_logical_fallacies.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ny_template_yaml +process_docs: !function utils.process_logical_fallacies +tag: global_mmlu_full_ny_humanities_tasks +task: global_mmlu_full_ny_logical_fallacies diff --git a/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_machine_learning.yaml b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_machine_learning.yaml new file mode 100644 index 00000000..765b2201 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_machine_learning.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ny_template_yaml +process_docs: !function utils.process_machine_learning +tag: global_mmlu_full_ny_stem_tasks +task: global_mmlu_full_ny_machine_learning diff --git a/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_management.yaml b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_management.yaml new file mode 100644 index 00000000..a699a70d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_management.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ny_template_yaml +process_docs: !function utils.process_management +tag: global_mmlu_full_ny_other_tasks +task: global_mmlu_full_ny_management diff --git a/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_marketing.yaml b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_marketing.yaml new file mode 100644 index 00000000..596d6937 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_marketing.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ny_template_yaml +process_docs: !function utils.process_marketing +tag: global_mmlu_full_ny_other_tasks +task: global_mmlu_full_ny_marketing diff --git a/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_medical_genetics.yaml b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_medical_genetics.yaml new file mode 100644 index 00000000..4fae66a7 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_medical_genetics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ny_template_yaml +process_docs: !function utils.process_medical_genetics +tag: global_mmlu_full_ny_other_tasks +task: global_mmlu_full_ny_medical_genetics diff --git a/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_miscellaneous.yaml b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_miscellaneous.yaml new file mode 100644 index 00000000..8555e173 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_miscellaneous.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ny_template_yaml +process_docs: !function utils.process_miscellaneous +tag: global_mmlu_full_ny_other_tasks +task: global_mmlu_full_ny_miscellaneous diff --git a/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_moral_disputes.yaml b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_moral_disputes.yaml new file mode 100644 index 00000000..b64f4d9d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_moral_disputes.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ny_template_yaml +process_docs: !function utils.process_moral_disputes +tag: global_mmlu_full_ny_humanities_tasks +task: global_mmlu_full_ny_moral_disputes diff --git a/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_moral_scenarios.yaml b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_moral_scenarios.yaml new file mode 100644 index 00000000..c73f9f1a --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_moral_scenarios.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ny_template_yaml +process_docs: !function utils.process_moral_scenarios +tag: global_mmlu_full_ny_humanities_tasks +task: global_mmlu_full_ny_moral_scenarios diff --git a/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_nutrition.yaml b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_nutrition.yaml new file mode 100644 index 00000000..456f4cb6 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_nutrition.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ny_template_yaml +process_docs: !function utils.process_nutrition +tag: global_mmlu_full_ny_other_tasks +task: global_mmlu_full_ny_nutrition diff --git a/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_philosophy.yaml b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_philosophy.yaml new file mode 100644 index 00000000..d0e0e05e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_philosophy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ny_template_yaml +process_docs: !function utils.process_philosophy +tag: global_mmlu_full_ny_humanities_tasks +task: global_mmlu_full_ny_philosophy diff --git a/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_prehistory.yaml b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_prehistory.yaml new file mode 100644 index 00000000..d65c6be1 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_prehistory.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ny_template_yaml +process_docs: !function utils.process_prehistory +tag: global_mmlu_full_ny_humanities_tasks +task: global_mmlu_full_ny_prehistory diff --git a/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_professional_accounting.yaml b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_professional_accounting.yaml new file mode 100644 index 00000000..c152c80e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_professional_accounting.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ny_template_yaml +process_docs: !function utils.process_professional_accounting +tag: global_mmlu_full_ny_other_tasks +task: global_mmlu_full_ny_professional_accounting diff --git a/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_professional_law.yaml b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_professional_law.yaml new file mode 100644 index 00000000..d5e2c7b7 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_professional_law.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ny_template_yaml +process_docs: !function utils.process_professional_law +tag: global_mmlu_full_ny_humanities_tasks +task: global_mmlu_full_ny_professional_law diff --git a/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_professional_medicine.yaml b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_professional_medicine.yaml new file mode 100644 index 00000000..cacd5df7 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_professional_medicine.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ny_template_yaml +process_docs: !function utils.process_professional_medicine +tag: global_mmlu_full_ny_other_tasks +task: global_mmlu_full_ny_professional_medicine diff --git a/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_professional_psychology.yaml b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_professional_psychology.yaml new file mode 100644 index 00000000..ffdd86d2 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_professional_psychology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ny_template_yaml +process_docs: !function utils.process_professional_psychology +tag: global_mmlu_full_ny_social_sciences_tasks +task: global_mmlu_full_ny_professional_psychology diff --git a/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_public_relations.yaml b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_public_relations.yaml new file mode 100644 index 00000000..0e6b5ab8 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_public_relations.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ny_template_yaml +process_docs: !function utils.process_public_relations +tag: global_mmlu_full_ny_social_sciences_tasks +task: global_mmlu_full_ny_public_relations diff --git a/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_security_studies.yaml b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_security_studies.yaml new file mode 100644 index 00000000..f894fdd7 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_security_studies.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ny_template_yaml +process_docs: !function utils.process_security_studies +tag: global_mmlu_full_ny_social_sciences_tasks +task: global_mmlu_full_ny_security_studies diff --git a/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_sociology.yaml b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_sociology.yaml new file mode 100644 index 00000000..1d2d0cd4 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_sociology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ny_template_yaml +process_docs: !function utils.process_sociology +tag: global_mmlu_full_ny_social_sciences_tasks +task: global_mmlu_full_ny_sociology diff --git a/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_us_foreign_policy.yaml b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_us_foreign_policy.yaml new file mode 100644 index 00000000..a72a237d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_us_foreign_policy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ny_template_yaml +process_docs: !function utils.process_us_foreign_policy +tag: global_mmlu_full_ny_social_sciences_tasks +task: global_mmlu_full_ny_us_foreign_policy diff --git a/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_virology.yaml b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_virology.yaml new file mode 100644 index 00000000..9eeb7cf0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_virology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ny_template_yaml +process_docs: !function utils.process_virology +tag: global_mmlu_full_ny_other_tasks +task: global_mmlu_full_ny_virology diff --git a/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_world_religions.yaml b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_world_religions.yaml new file mode 100644 index 00000000..a1c243c8 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ny/global_mmlu_full_ny_world_religions.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ny_template_yaml +process_docs: !function utils.process_world_religions +tag: global_mmlu_full_ny_humanities_tasks +task: global_mmlu_full_ny_world_religions diff --git a/lm_eval/tasks/global_mmlu/full/ny/utils.py b/lm_eval/tasks/global_mmlu/full/ny/utils.py new file mode 100644 index 00000000..7df72cb0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ny/utils.py @@ -0,0 +1,73 @@ +from functools import partial + + +SUBJECTS = [ + "abstract_algebra", + "anatomy", + "astronomy", + "business_ethics", + "clinical_knowledge", + "college_biology", + "college_chemistry", + "college_computer_science", + "college_mathematics", + "college_medicine", + "college_physics", + "computer_security", + "conceptual_physics", + "econometrics", + "electrical_engineering", + "elementary_mathematics", + "formal_logic", + "global_facts", + "high_school_biology", + "high_school_chemistry", + "high_school_computer_science", + "high_school_european_history", + "high_school_geography", + "high_school_government_and_politics", + "high_school_macroeconomics", + "high_school_mathematics", + "high_school_microeconomics", + "high_school_physics", + "high_school_psychology", + "high_school_statistics", + "high_school_us_history", + "high_school_world_history", + "human_aging", + "human_sexuality", + "international_law", + "jurisprudence", + "logical_fallacies", + "machine_learning", + "management", + "marketing", + "medical_genetics", + "miscellaneous", + "moral_disputes", + "moral_scenarios", + "nutrition", + "philosophy", + "prehistory", + "professional_accounting", + "professional_law", + "professional_medicine", + "professional_psychology", + "public_relations", + "security_studies", + "sociology", + "us_foreign_policy", + "virology", + "world_religions", +] + + +def process_docs(dataset, subject): + return dataset.filter(lambda x: x["subject"] == subject) + + +process_functions = { + f"process_{subject}": partial(process_docs, subject=subject) for subject in SUBJECTS +} + +globals().update(process_functions) diff --git a/lm_eval/tasks/global_mmlu/full/pl/_global_mmlu_full_pl.yaml b/lm_eval/tasks/global_mmlu/full/pl/_global_mmlu_full_pl.yaml new file mode 100644 index 00000000..2476fd33 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pl/_global_mmlu_full_pl.yaml @@ -0,0 +1,11 @@ +group: global_mmlu_full_pl +task: + - global_mmlu_full_pl_stem + - global_mmlu_full_pl_other + - global_mmlu_full_pl_social_sciences + - global_mmlu_full_pl_humanities +aggregate_metric_list: + - metric: acc + weight_by_size: True +metadata: + version: 1.0 diff --git a/lm_eval/tasks/global_mmlu/full/pl/_global_mmlu_full_pl_humanities.yaml b/lm_eval/tasks/global_mmlu/full/pl/_global_mmlu_full_pl_humanities.yaml new file mode 100644 index 00000000..4b5f7aa4 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pl/_global_mmlu_full_pl_humanities.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_pl_humanities +task: + - global_mmlu_full_pl_humanities_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/pl/_global_mmlu_full_pl_other.yaml b/lm_eval/tasks/global_mmlu/full/pl/_global_mmlu_full_pl_other.yaml new file mode 100644 index 00000000..241dbc1c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pl/_global_mmlu_full_pl_other.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_pl_other +task: + - global_mmlu_full_pl_other_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/pl/_global_mmlu_full_pl_social_sciences.yaml b/lm_eval/tasks/global_mmlu/full/pl/_global_mmlu_full_pl_social_sciences.yaml new file mode 100644 index 00000000..9a50a315 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pl/_global_mmlu_full_pl_social_sciences.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_pl_social_sciences +task: + - global_mmlu_full_pl_social_sciences_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/pl/_global_mmlu_full_pl_stem.yaml b/lm_eval/tasks/global_mmlu/full/pl/_global_mmlu_full_pl_stem.yaml new file mode 100644 index 00000000..3d11c89f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pl/_global_mmlu_full_pl_stem.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_pl_stem +task: + - global_mmlu_full_pl_stem_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/pl/_pl_template_yaml b/lm_eval/tasks/global_mmlu/full/pl/_pl_template_yaml new file mode 100644 index 00000000..af8809dc --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pl/_pl_template_yaml @@ -0,0 +1,16 @@ +dataset_path: CohereForAI/Global-MMLU +dataset_name: pl +test_split: test +fewshot_split: dev +fewshot_config: + sampler: first_n +output_type: multiple_choice +doc_to_text: "{{question.strip()}}\nA. {{option_a}}\nB. {{option_b}}\nC. {{option_c}}\nD. {{option_d}}\nAnswer:" +doc_to_choice: ["A", "B", "C", "D"] +doc_to_target: answer +metric_list: + - metric: acc + aggregation: mean + higher_is_better: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_abstract_algebra.yaml b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_abstract_algebra.yaml new file mode 100644 index 00000000..37f611a1 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_abstract_algebra.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pl_template_yaml +process_docs: !function utils.process_abstract_algebra +tag: global_mmlu_full_pl_stem_tasks +task: global_mmlu_full_pl_abstract_algebra diff --git a/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_anatomy.yaml b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_anatomy.yaml new file mode 100644 index 00000000..c274bce1 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_anatomy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pl_template_yaml +process_docs: !function utils.process_anatomy +tag: global_mmlu_full_pl_stem_tasks +task: global_mmlu_full_pl_anatomy diff --git a/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_astronomy.yaml b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_astronomy.yaml new file mode 100644 index 00000000..99220f0d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_astronomy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pl_template_yaml +process_docs: !function utils.process_astronomy +tag: global_mmlu_full_pl_stem_tasks +task: global_mmlu_full_pl_astronomy diff --git a/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_business_ethics.yaml b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_business_ethics.yaml new file mode 100644 index 00000000..10592668 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_business_ethics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pl_template_yaml +process_docs: !function utils.process_business_ethics +tag: global_mmlu_full_pl_other_tasks +task: global_mmlu_full_pl_business_ethics diff --git a/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_clinical_knowledge.yaml b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_clinical_knowledge.yaml new file mode 100644 index 00000000..29a4fadc --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_clinical_knowledge.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pl_template_yaml +process_docs: !function utils.process_clinical_knowledge +tag: global_mmlu_full_pl_other_tasks +task: global_mmlu_full_pl_clinical_knowledge diff --git a/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_college_biology.yaml b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_college_biology.yaml new file mode 100644 index 00000000..cce1671c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_college_biology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pl_template_yaml +process_docs: !function utils.process_college_biology +tag: global_mmlu_full_pl_stem_tasks +task: global_mmlu_full_pl_college_biology diff --git a/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_college_chemistry.yaml b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_college_chemistry.yaml new file mode 100644 index 00000000..79c63530 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_college_chemistry.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pl_template_yaml +process_docs: !function utils.process_college_chemistry +tag: global_mmlu_full_pl_stem_tasks +task: global_mmlu_full_pl_college_chemistry diff --git a/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_college_computer_science.yaml b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_college_computer_science.yaml new file mode 100644 index 00000000..bb630140 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_college_computer_science.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pl_template_yaml +process_docs: !function utils.process_college_computer_science +tag: global_mmlu_full_pl_stem_tasks +task: global_mmlu_full_pl_college_computer_science diff --git a/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_college_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_college_mathematics.yaml new file mode 100644 index 00000000..6b42f767 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_college_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pl_template_yaml +process_docs: !function utils.process_college_mathematics +tag: global_mmlu_full_pl_stem_tasks +task: global_mmlu_full_pl_college_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_college_medicine.yaml b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_college_medicine.yaml new file mode 100644 index 00000000..43bea976 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_college_medicine.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pl_template_yaml +process_docs: !function utils.process_college_medicine +tag: global_mmlu_full_pl_other_tasks +task: global_mmlu_full_pl_college_medicine diff --git a/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_college_physics.yaml b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_college_physics.yaml new file mode 100644 index 00000000..0c9ea601 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_college_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pl_template_yaml +process_docs: !function utils.process_college_physics +tag: global_mmlu_full_pl_stem_tasks +task: global_mmlu_full_pl_college_physics diff --git a/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_computer_security.yaml b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_computer_security.yaml new file mode 100644 index 00000000..365b60a3 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_computer_security.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pl_template_yaml +process_docs: !function utils.process_computer_security +tag: global_mmlu_full_pl_stem_tasks +task: global_mmlu_full_pl_computer_security diff --git a/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_conceptual_physics.yaml b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_conceptual_physics.yaml new file mode 100644 index 00000000..2b9437e3 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_conceptual_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pl_template_yaml +process_docs: !function utils.process_conceptual_physics +tag: global_mmlu_full_pl_stem_tasks +task: global_mmlu_full_pl_conceptual_physics diff --git a/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_econometrics.yaml b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_econometrics.yaml new file mode 100644 index 00000000..648f24c4 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_econometrics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pl_template_yaml +process_docs: !function utils.process_econometrics +tag: global_mmlu_full_pl_social_sciences_tasks +task: global_mmlu_full_pl_econometrics diff --git a/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_electrical_engineering.yaml b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_electrical_engineering.yaml new file mode 100644 index 00000000..196de258 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_electrical_engineering.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pl_template_yaml +process_docs: !function utils.process_electrical_engineering +tag: global_mmlu_full_pl_stem_tasks +task: global_mmlu_full_pl_electrical_engineering diff --git a/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_elementary_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_elementary_mathematics.yaml new file mode 100644 index 00000000..8646b6a3 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_elementary_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pl_template_yaml +process_docs: !function utils.process_elementary_mathematics +tag: global_mmlu_full_pl_stem_tasks +task: global_mmlu_full_pl_elementary_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_formal_logic.yaml b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_formal_logic.yaml new file mode 100644 index 00000000..2d13d283 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_formal_logic.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pl_template_yaml +process_docs: !function utils.process_formal_logic +tag: global_mmlu_full_pl_humanities_tasks +task: global_mmlu_full_pl_formal_logic diff --git a/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_global_facts.yaml b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_global_facts.yaml new file mode 100644 index 00000000..15bb640b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_global_facts.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pl_template_yaml +process_docs: !function utils.process_global_facts +tag: global_mmlu_full_pl_other_tasks +task: global_mmlu_full_pl_global_facts diff --git a/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_high_school_biology.yaml b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_high_school_biology.yaml new file mode 100644 index 00000000..ba964028 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_high_school_biology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pl_template_yaml +process_docs: !function utils.process_high_school_biology +tag: global_mmlu_full_pl_stem_tasks +task: global_mmlu_full_pl_high_school_biology diff --git a/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_high_school_chemistry.yaml b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_high_school_chemistry.yaml new file mode 100644 index 00000000..7f142dd8 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_high_school_chemistry.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pl_template_yaml +process_docs: !function utils.process_high_school_chemistry +tag: global_mmlu_full_pl_stem_tasks +task: global_mmlu_full_pl_high_school_chemistry diff --git a/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_high_school_computer_science.yaml b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_high_school_computer_science.yaml new file mode 100644 index 00000000..99b3b9da --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_high_school_computer_science.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pl_template_yaml +process_docs: !function utils.process_high_school_computer_science +tag: global_mmlu_full_pl_stem_tasks +task: global_mmlu_full_pl_high_school_computer_science diff --git a/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_high_school_european_history.yaml b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_high_school_european_history.yaml new file mode 100644 index 00000000..e99b2fb9 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_high_school_european_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pl_template_yaml +process_docs: !function utils.process_high_school_european_history +tag: global_mmlu_full_pl_humanities_tasks +task: global_mmlu_full_pl_high_school_european_history diff --git a/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_high_school_geography.yaml b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_high_school_geography.yaml new file mode 100644 index 00000000..bc6113f7 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_high_school_geography.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pl_template_yaml +process_docs: !function utils.process_high_school_geography +tag: global_mmlu_full_pl_social_sciences_tasks +task: global_mmlu_full_pl_high_school_geography diff --git a/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_high_school_government_and_politics.yaml b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_high_school_government_and_politics.yaml new file mode 100644 index 00000000..05a7de9b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_high_school_government_and_politics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pl_template_yaml +process_docs: !function utils.process_high_school_government_and_politics +tag: global_mmlu_full_pl_social_sciences_tasks +task: global_mmlu_full_pl_high_school_government_and_politics diff --git a/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_high_school_macroeconomics.yaml b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_high_school_macroeconomics.yaml new file mode 100644 index 00000000..aceda633 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_high_school_macroeconomics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pl_template_yaml +process_docs: !function utils.process_high_school_macroeconomics +tag: global_mmlu_full_pl_social_sciences_tasks +task: global_mmlu_full_pl_high_school_macroeconomics diff --git a/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_high_school_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_high_school_mathematics.yaml new file mode 100644 index 00000000..6eef2cd8 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_high_school_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pl_template_yaml +process_docs: !function utils.process_high_school_mathematics +tag: global_mmlu_full_pl_stem_tasks +task: global_mmlu_full_pl_high_school_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_high_school_microeconomics.yaml b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_high_school_microeconomics.yaml new file mode 100644 index 00000000..5adb5fa1 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_high_school_microeconomics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pl_template_yaml +process_docs: !function utils.process_high_school_microeconomics +tag: global_mmlu_full_pl_social_sciences_tasks +task: global_mmlu_full_pl_high_school_microeconomics diff --git a/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_high_school_physics.yaml b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_high_school_physics.yaml new file mode 100644 index 00000000..fbda7920 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_high_school_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pl_template_yaml +process_docs: !function utils.process_high_school_physics +tag: global_mmlu_full_pl_stem_tasks +task: global_mmlu_full_pl_high_school_physics diff --git a/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_high_school_psychology.yaml b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_high_school_psychology.yaml new file mode 100644 index 00000000..7eb09362 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_high_school_psychology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pl_template_yaml +process_docs: !function utils.process_high_school_psychology +tag: global_mmlu_full_pl_social_sciences_tasks +task: global_mmlu_full_pl_high_school_psychology diff --git a/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_high_school_statistics.yaml b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_high_school_statistics.yaml new file mode 100644 index 00000000..b7beef5b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_high_school_statistics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pl_template_yaml +process_docs: !function utils.process_high_school_statistics +tag: global_mmlu_full_pl_stem_tasks +task: global_mmlu_full_pl_high_school_statistics diff --git a/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_high_school_us_history.yaml b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_high_school_us_history.yaml new file mode 100644 index 00000000..08f45dd9 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_high_school_us_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pl_template_yaml +process_docs: !function utils.process_high_school_us_history +tag: global_mmlu_full_pl_humanities_tasks +task: global_mmlu_full_pl_high_school_us_history diff --git a/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_high_school_world_history.yaml b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_high_school_world_history.yaml new file mode 100644 index 00000000..99664de8 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_high_school_world_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pl_template_yaml +process_docs: !function utils.process_high_school_world_history +tag: global_mmlu_full_pl_humanities_tasks +task: global_mmlu_full_pl_high_school_world_history diff --git a/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_human_aging.yaml b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_human_aging.yaml new file mode 100644 index 00000000..d63f6f8d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_human_aging.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pl_template_yaml +process_docs: !function utils.process_human_aging +tag: global_mmlu_full_pl_other_tasks +task: global_mmlu_full_pl_human_aging diff --git a/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_human_sexuality.yaml b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_human_sexuality.yaml new file mode 100644 index 00000000..8080ca8d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_human_sexuality.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pl_template_yaml +process_docs: !function utils.process_human_sexuality +tag: global_mmlu_full_pl_social_sciences_tasks +task: global_mmlu_full_pl_human_sexuality diff --git a/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_international_law.yaml b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_international_law.yaml new file mode 100644 index 00000000..425695c1 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_international_law.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pl_template_yaml +process_docs: !function utils.process_international_law +tag: global_mmlu_full_pl_humanities_tasks +task: global_mmlu_full_pl_international_law diff --git a/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_jurisprudence.yaml b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_jurisprudence.yaml new file mode 100644 index 00000000..a6455bd7 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_jurisprudence.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pl_template_yaml +process_docs: !function utils.process_jurisprudence +tag: global_mmlu_full_pl_humanities_tasks +task: global_mmlu_full_pl_jurisprudence diff --git a/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_logical_fallacies.yaml b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_logical_fallacies.yaml new file mode 100644 index 00000000..f1359b3a --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_logical_fallacies.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pl_template_yaml +process_docs: !function utils.process_logical_fallacies +tag: global_mmlu_full_pl_humanities_tasks +task: global_mmlu_full_pl_logical_fallacies diff --git a/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_machine_learning.yaml b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_machine_learning.yaml new file mode 100644 index 00000000..3d7bb0dc --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_machine_learning.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pl_template_yaml +process_docs: !function utils.process_machine_learning +tag: global_mmlu_full_pl_stem_tasks +task: global_mmlu_full_pl_machine_learning diff --git a/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_management.yaml b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_management.yaml new file mode 100644 index 00000000..f695226c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_management.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pl_template_yaml +process_docs: !function utils.process_management +tag: global_mmlu_full_pl_other_tasks +task: global_mmlu_full_pl_management diff --git a/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_marketing.yaml b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_marketing.yaml new file mode 100644 index 00000000..7fedcd3f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_marketing.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pl_template_yaml +process_docs: !function utils.process_marketing +tag: global_mmlu_full_pl_other_tasks +task: global_mmlu_full_pl_marketing diff --git a/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_medical_genetics.yaml b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_medical_genetics.yaml new file mode 100644 index 00000000..89da9f67 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_medical_genetics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pl_template_yaml +process_docs: !function utils.process_medical_genetics +tag: global_mmlu_full_pl_other_tasks +task: global_mmlu_full_pl_medical_genetics diff --git a/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_miscellaneous.yaml b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_miscellaneous.yaml new file mode 100644 index 00000000..6f34762c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_miscellaneous.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pl_template_yaml +process_docs: !function utils.process_miscellaneous +tag: global_mmlu_full_pl_other_tasks +task: global_mmlu_full_pl_miscellaneous diff --git a/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_moral_disputes.yaml b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_moral_disputes.yaml new file mode 100644 index 00000000..25f201f4 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_moral_disputes.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pl_template_yaml +process_docs: !function utils.process_moral_disputes +tag: global_mmlu_full_pl_humanities_tasks +task: global_mmlu_full_pl_moral_disputes diff --git a/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_moral_scenarios.yaml b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_moral_scenarios.yaml new file mode 100644 index 00000000..fd08e6e1 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_moral_scenarios.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pl_template_yaml +process_docs: !function utils.process_moral_scenarios +tag: global_mmlu_full_pl_humanities_tasks +task: global_mmlu_full_pl_moral_scenarios diff --git a/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_nutrition.yaml b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_nutrition.yaml new file mode 100644 index 00000000..b61f1f17 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_nutrition.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pl_template_yaml +process_docs: !function utils.process_nutrition +tag: global_mmlu_full_pl_other_tasks +task: global_mmlu_full_pl_nutrition diff --git a/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_philosophy.yaml b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_philosophy.yaml new file mode 100644 index 00000000..8c1bf6dc --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_philosophy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pl_template_yaml +process_docs: !function utils.process_philosophy +tag: global_mmlu_full_pl_humanities_tasks +task: global_mmlu_full_pl_philosophy diff --git a/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_prehistory.yaml b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_prehistory.yaml new file mode 100644 index 00000000..e5329e13 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_prehistory.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pl_template_yaml +process_docs: !function utils.process_prehistory +tag: global_mmlu_full_pl_humanities_tasks +task: global_mmlu_full_pl_prehistory diff --git a/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_professional_accounting.yaml b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_professional_accounting.yaml new file mode 100644 index 00000000..514b04cd --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_professional_accounting.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pl_template_yaml +process_docs: !function utils.process_professional_accounting +tag: global_mmlu_full_pl_other_tasks +task: global_mmlu_full_pl_professional_accounting diff --git a/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_professional_law.yaml b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_professional_law.yaml new file mode 100644 index 00000000..99c719f8 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_professional_law.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pl_template_yaml +process_docs: !function utils.process_professional_law +tag: global_mmlu_full_pl_humanities_tasks +task: global_mmlu_full_pl_professional_law diff --git a/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_professional_medicine.yaml b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_professional_medicine.yaml new file mode 100644 index 00000000..1dfafb25 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_professional_medicine.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pl_template_yaml +process_docs: !function utils.process_professional_medicine +tag: global_mmlu_full_pl_other_tasks +task: global_mmlu_full_pl_professional_medicine diff --git a/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_professional_psychology.yaml b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_professional_psychology.yaml new file mode 100644 index 00000000..5b6181c0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_professional_psychology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pl_template_yaml +process_docs: !function utils.process_professional_psychology +tag: global_mmlu_full_pl_social_sciences_tasks +task: global_mmlu_full_pl_professional_psychology diff --git a/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_public_relations.yaml b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_public_relations.yaml new file mode 100644 index 00000000..acf874db --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_public_relations.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pl_template_yaml +process_docs: !function utils.process_public_relations +tag: global_mmlu_full_pl_social_sciences_tasks +task: global_mmlu_full_pl_public_relations diff --git a/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_security_studies.yaml b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_security_studies.yaml new file mode 100644 index 00000000..d754904c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_security_studies.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pl_template_yaml +process_docs: !function utils.process_security_studies +tag: global_mmlu_full_pl_social_sciences_tasks +task: global_mmlu_full_pl_security_studies diff --git a/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_sociology.yaml b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_sociology.yaml new file mode 100644 index 00000000..4bc0fd8f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_sociology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pl_template_yaml +process_docs: !function utils.process_sociology +tag: global_mmlu_full_pl_social_sciences_tasks +task: global_mmlu_full_pl_sociology diff --git a/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_us_foreign_policy.yaml b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_us_foreign_policy.yaml new file mode 100644 index 00000000..ef719be1 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_us_foreign_policy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pl_template_yaml +process_docs: !function utils.process_us_foreign_policy +tag: global_mmlu_full_pl_social_sciences_tasks +task: global_mmlu_full_pl_us_foreign_policy diff --git a/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_virology.yaml b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_virology.yaml new file mode 100644 index 00000000..f9084c13 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_virology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pl_template_yaml +process_docs: !function utils.process_virology +tag: global_mmlu_full_pl_other_tasks +task: global_mmlu_full_pl_virology diff --git a/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_world_religions.yaml b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_world_religions.yaml new file mode 100644 index 00000000..036d0f4c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pl/global_mmlu_full_pl_world_religions.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pl_template_yaml +process_docs: !function utils.process_world_religions +tag: global_mmlu_full_pl_humanities_tasks +task: global_mmlu_full_pl_world_religions diff --git a/lm_eval/tasks/global_mmlu/full/pl/utils.py b/lm_eval/tasks/global_mmlu/full/pl/utils.py new file mode 100644 index 00000000..7df72cb0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pl/utils.py @@ -0,0 +1,73 @@ +from functools import partial + + +SUBJECTS = [ + "abstract_algebra", + "anatomy", + "astronomy", + "business_ethics", + "clinical_knowledge", + "college_biology", + "college_chemistry", + "college_computer_science", + "college_mathematics", + "college_medicine", + "college_physics", + "computer_security", + "conceptual_physics", + "econometrics", + "electrical_engineering", + "elementary_mathematics", + "formal_logic", + "global_facts", + "high_school_biology", + "high_school_chemistry", + "high_school_computer_science", + "high_school_european_history", + "high_school_geography", + "high_school_government_and_politics", + "high_school_macroeconomics", + "high_school_mathematics", + "high_school_microeconomics", + "high_school_physics", + "high_school_psychology", + "high_school_statistics", + "high_school_us_history", + "high_school_world_history", + "human_aging", + "human_sexuality", + "international_law", + "jurisprudence", + "logical_fallacies", + "machine_learning", + "management", + "marketing", + "medical_genetics", + "miscellaneous", + "moral_disputes", + "moral_scenarios", + "nutrition", + "philosophy", + "prehistory", + "professional_accounting", + "professional_law", + "professional_medicine", + "professional_psychology", + "public_relations", + "security_studies", + "sociology", + "us_foreign_policy", + "virology", + "world_religions", +] + + +def process_docs(dataset, subject): + return dataset.filter(lambda x: x["subject"] == subject) + + +process_functions = { + f"process_{subject}": partial(process_docs, subject=subject) for subject in SUBJECTS +} + +globals().update(process_functions) diff --git a/lm_eval/tasks/global_mmlu/full/pt/_global_mmlu_full_pt.yaml b/lm_eval/tasks/global_mmlu/full/pt/_global_mmlu_full_pt.yaml new file mode 100644 index 00000000..ac79bda1 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pt/_global_mmlu_full_pt.yaml @@ -0,0 +1,11 @@ +group: global_mmlu_full_pt +task: + - global_mmlu_full_pt_stem + - global_mmlu_full_pt_other + - global_mmlu_full_pt_social_sciences + - global_mmlu_full_pt_humanities +aggregate_metric_list: + - metric: acc + weight_by_size: True +metadata: + version: 1.0 diff --git a/lm_eval/tasks/global_mmlu/full/pt/_global_mmlu_full_pt_humanities.yaml b/lm_eval/tasks/global_mmlu/full/pt/_global_mmlu_full_pt_humanities.yaml new file mode 100644 index 00000000..261a7028 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pt/_global_mmlu_full_pt_humanities.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_pt_humanities +task: + - global_mmlu_full_pt_humanities_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/pt/_global_mmlu_full_pt_other.yaml b/lm_eval/tasks/global_mmlu/full/pt/_global_mmlu_full_pt_other.yaml new file mode 100644 index 00000000..a61b12f5 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pt/_global_mmlu_full_pt_other.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_pt_other +task: + - global_mmlu_full_pt_other_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/pt/_global_mmlu_full_pt_social_sciences.yaml b/lm_eval/tasks/global_mmlu/full/pt/_global_mmlu_full_pt_social_sciences.yaml new file mode 100644 index 00000000..2c04bf5a --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pt/_global_mmlu_full_pt_social_sciences.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_pt_social_sciences +task: + - global_mmlu_full_pt_social_sciences_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/pt/_global_mmlu_full_pt_stem.yaml b/lm_eval/tasks/global_mmlu/full/pt/_global_mmlu_full_pt_stem.yaml new file mode 100644 index 00000000..dc3d3610 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pt/_global_mmlu_full_pt_stem.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_pt_stem +task: + - global_mmlu_full_pt_stem_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/pt/_pt_template_yaml b/lm_eval/tasks/global_mmlu/full/pt/_pt_template_yaml new file mode 100644 index 00000000..66ba2417 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pt/_pt_template_yaml @@ -0,0 +1,16 @@ +dataset_path: CohereForAI/Global-MMLU +dataset_name: pt +test_split: test +fewshot_split: dev +fewshot_config: + sampler: first_n +output_type: multiple_choice +doc_to_text: "{{question.strip()}}\nA. {{option_a}}\nB. {{option_b}}\nC. {{option_c}}\nD. {{option_d}}\nAnswer:" +doc_to_choice: ["A", "B", "C", "D"] +doc_to_target: answer +metric_list: + - metric: acc + aggregation: mean + higher_is_better: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_abstract_algebra.yaml b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_abstract_algebra.yaml new file mode 100644 index 00000000..d9efd817 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_abstract_algebra.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pt_template_yaml +process_docs: !function utils.process_abstract_algebra +tag: global_mmlu_full_pt_stem_tasks +task: global_mmlu_full_pt_abstract_algebra diff --git a/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_anatomy.yaml b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_anatomy.yaml new file mode 100644 index 00000000..45390503 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_anatomy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pt_template_yaml +process_docs: !function utils.process_anatomy +tag: global_mmlu_full_pt_stem_tasks +task: global_mmlu_full_pt_anatomy diff --git a/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_astronomy.yaml b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_astronomy.yaml new file mode 100644 index 00000000..90880cd0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_astronomy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pt_template_yaml +process_docs: !function utils.process_astronomy +tag: global_mmlu_full_pt_stem_tasks +task: global_mmlu_full_pt_astronomy diff --git a/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_business_ethics.yaml b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_business_ethics.yaml new file mode 100644 index 00000000..f18ef2d8 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_business_ethics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pt_template_yaml +process_docs: !function utils.process_business_ethics +tag: global_mmlu_full_pt_other_tasks +task: global_mmlu_full_pt_business_ethics diff --git a/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_clinical_knowledge.yaml b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_clinical_knowledge.yaml new file mode 100644 index 00000000..2999a02a --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_clinical_knowledge.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pt_template_yaml +process_docs: !function utils.process_clinical_knowledge +tag: global_mmlu_full_pt_other_tasks +task: global_mmlu_full_pt_clinical_knowledge diff --git a/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_college_biology.yaml b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_college_biology.yaml new file mode 100644 index 00000000..0cf0a61b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_college_biology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pt_template_yaml +process_docs: !function utils.process_college_biology +tag: global_mmlu_full_pt_stem_tasks +task: global_mmlu_full_pt_college_biology diff --git a/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_college_chemistry.yaml b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_college_chemistry.yaml new file mode 100644 index 00000000..91d8cd2e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_college_chemistry.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pt_template_yaml +process_docs: !function utils.process_college_chemistry +tag: global_mmlu_full_pt_stem_tasks +task: global_mmlu_full_pt_college_chemistry diff --git a/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_college_computer_science.yaml b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_college_computer_science.yaml new file mode 100644 index 00000000..68592aaf --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_college_computer_science.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pt_template_yaml +process_docs: !function utils.process_college_computer_science +tag: global_mmlu_full_pt_stem_tasks +task: global_mmlu_full_pt_college_computer_science diff --git a/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_college_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_college_mathematics.yaml new file mode 100644 index 00000000..31d7f6af --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_college_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pt_template_yaml +process_docs: !function utils.process_college_mathematics +tag: global_mmlu_full_pt_stem_tasks +task: global_mmlu_full_pt_college_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_college_medicine.yaml b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_college_medicine.yaml new file mode 100644 index 00000000..46ec8232 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_college_medicine.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pt_template_yaml +process_docs: !function utils.process_college_medicine +tag: global_mmlu_full_pt_other_tasks +task: global_mmlu_full_pt_college_medicine diff --git a/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_college_physics.yaml b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_college_physics.yaml new file mode 100644 index 00000000..2cf6402d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_college_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pt_template_yaml +process_docs: !function utils.process_college_physics +tag: global_mmlu_full_pt_stem_tasks +task: global_mmlu_full_pt_college_physics diff --git a/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_computer_security.yaml b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_computer_security.yaml new file mode 100644 index 00000000..0953a105 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_computer_security.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pt_template_yaml +process_docs: !function utils.process_computer_security +tag: global_mmlu_full_pt_stem_tasks +task: global_mmlu_full_pt_computer_security diff --git a/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_conceptual_physics.yaml b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_conceptual_physics.yaml new file mode 100644 index 00000000..0e6e91a9 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_conceptual_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pt_template_yaml +process_docs: !function utils.process_conceptual_physics +tag: global_mmlu_full_pt_stem_tasks +task: global_mmlu_full_pt_conceptual_physics diff --git a/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_econometrics.yaml b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_econometrics.yaml new file mode 100644 index 00000000..67c29915 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_econometrics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pt_template_yaml +process_docs: !function utils.process_econometrics +tag: global_mmlu_full_pt_social_sciences_tasks +task: global_mmlu_full_pt_econometrics diff --git a/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_electrical_engineering.yaml b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_electrical_engineering.yaml new file mode 100644 index 00000000..5a6ba82e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_electrical_engineering.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pt_template_yaml +process_docs: !function utils.process_electrical_engineering +tag: global_mmlu_full_pt_stem_tasks +task: global_mmlu_full_pt_electrical_engineering diff --git a/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_elementary_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_elementary_mathematics.yaml new file mode 100644 index 00000000..3d66a664 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_elementary_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pt_template_yaml +process_docs: !function utils.process_elementary_mathematics +tag: global_mmlu_full_pt_stem_tasks +task: global_mmlu_full_pt_elementary_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_formal_logic.yaml b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_formal_logic.yaml new file mode 100644 index 00000000..683d6ddd --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_formal_logic.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pt_template_yaml +process_docs: !function utils.process_formal_logic +tag: global_mmlu_full_pt_humanities_tasks +task: global_mmlu_full_pt_formal_logic diff --git a/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_global_facts.yaml b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_global_facts.yaml new file mode 100644 index 00000000..e4396542 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_global_facts.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pt_template_yaml +process_docs: !function utils.process_global_facts +tag: global_mmlu_full_pt_other_tasks +task: global_mmlu_full_pt_global_facts diff --git a/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_high_school_biology.yaml b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_high_school_biology.yaml new file mode 100644 index 00000000..89fefd1c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_high_school_biology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pt_template_yaml +process_docs: !function utils.process_high_school_biology +tag: global_mmlu_full_pt_stem_tasks +task: global_mmlu_full_pt_high_school_biology diff --git a/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_high_school_chemistry.yaml b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_high_school_chemistry.yaml new file mode 100644 index 00000000..ea323d8a --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_high_school_chemistry.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pt_template_yaml +process_docs: !function utils.process_high_school_chemistry +tag: global_mmlu_full_pt_stem_tasks +task: global_mmlu_full_pt_high_school_chemistry diff --git a/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_high_school_computer_science.yaml b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_high_school_computer_science.yaml new file mode 100644 index 00000000..5f8f0082 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_high_school_computer_science.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pt_template_yaml +process_docs: !function utils.process_high_school_computer_science +tag: global_mmlu_full_pt_stem_tasks +task: global_mmlu_full_pt_high_school_computer_science diff --git a/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_high_school_european_history.yaml b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_high_school_european_history.yaml new file mode 100644 index 00000000..bef7a316 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_high_school_european_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pt_template_yaml +process_docs: !function utils.process_high_school_european_history +tag: global_mmlu_full_pt_humanities_tasks +task: global_mmlu_full_pt_high_school_european_history diff --git a/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_high_school_geography.yaml b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_high_school_geography.yaml new file mode 100644 index 00000000..e69c2978 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_high_school_geography.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pt_template_yaml +process_docs: !function utils.process_high_school_geography +tag: global_mmlu_full_pt_social_sciences_tasks +task: global_mmlu_full_pt_high_school_geography diff --git a/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_high_school_government_and_politics.yaml b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_high_school_government_and_politics.yaml new file mode 100644 index 00000000..e3fa920d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_high_school_government_and_politics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pt_template_yaml +process_docs: !function utils.process_high_school_government_and_politics +tag: global_mmlu_full_pt_social_sciences_tasks +task: global_mmlu_full_pt_high_school_government_and_politics diff --git a/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_high_school_macroeconomics.yaml b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_high_school_macroeconomics.yaml new file mode 100644 index 00000000..6b7ca2f4 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_high_school_macroeconomics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pt_template_yaml +process_docs: !function utils.process_high_school_macroeconomics +tag: global_mmlu_full_pt_social_sciences_tasks +task: global_mmlu_full_pt_high_school_macroeconomics diff --git a/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_high_school_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_high_school_mathematics.yaml new file mode 100644 index 00000000..4713674d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_high_school_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pt_template_yaml +process_docs: !function utils.process_high_school_mathematics +tag: global_mmlu_full_pt_stem_tasks +task: global_mmlu_full_pt_high_school_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_high_school_microeconomics.yaml b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_high_school_microeconomics.yaml new file mode 100644 index 00000000..d6475e99 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_high_school_microeconomics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pt_template_yaml +process_docs: !function utils.process_high_school_microeconomics +tag: global_mmlu_full_pt_social_sciences_tasks +task: global_mmlu_full_pt_high_school_microeconomics diff --git a/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_high_school_physics.yaml b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_high_school_physics.yaml new file mode 100644 index 00000000..9eaed31a --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_high_school_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pt_template_yaml +process_docs: !function utils.process_high_school_physics +tag: global_mmlu_full_pt_stem_tasks +task: global_mmlu_full_pt_high_school_physics diff --git a/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_high_school_psychology.yaml b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_high_school_psychology.yaml new file mode 100644 index 00000000..d09e1eb9 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_high_school_psychology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pt_template_yaml +process_docs: !function utils.process_high_school_psychology +tag: global_mmlu_full_pt_social_sciences_tasks +task: global_mmlu_full_pt_high_school_psychology diff --git a/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_high_school_statistics.yaml b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_high_school_statistics.yaml new file mode 100644 index 00000000..3d8c1447 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_high_school_statistics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pt_template_yaml +process_docs: !function utils.process_high_school_statistics +tag: global_mmlu_full_pt_stem_tasks +task: global_mmlu_full_pt_high_school_statistics diff --git a/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_high_school_us_history.yaml b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_high_school_us_history.yaml new file mode 100644 index 00000000..a883b438 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_high_school_us_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pt_template_yaml +process_docs: !function utils.process_high_school_us_history +tag: global_mmlu_full_pt_humanities_tasks +task: global_mmlu_full_pt_high_school_us_history diff --git a/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_high_school_world_history.yaml b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_high_school_world_history.yaml new file mode 100644 index 00000000..6ea1454e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_high_school_world_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pt_template_yaml +process_docs: !function utils.process_high_school_world_history +tag: global_mmlu_full_pt_humanities_tasks +task: global_mmlu_full_pt_high_school_world_history diff --git a/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_human_aging.yaml b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_human_aging.yaml new file mode 100644 index 00000000..34033c55 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_human_aging.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pt_template_yaml +process_docs: !function utils.process_human_aging +tag: global_mmlu_full_pt_other_tasks +task: global_mmlu_full_pt_human_aging diff --git a/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_human_sexuality.yaml b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_human_sexuality.yaml new file mode 100644 index 00000000..bf961c33 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_human_sexuality.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pt_template_yaml +process_docs: !function utils.process_human_sexuality +tag: global_mmlu_full_pt_social_sciences_tasks +task: global_mmlu_full_pt_human_sexuality diff --git a/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_international_law.yaml b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_international_law.yaml new file mode 100644 index 00000000..5247fc9b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_international_law.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pt_template_yaml +process_docs: !function utils.process_international_law +tag: global_mmlu_full_pt_humanities_tasks +task: global_mmlu_full_pt_international_law diff --git a/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_jurisprudence.yaml b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_jurisprudence.yaml new file mode 100644 index 00000000..07e78da5 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_jurisprudence.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pt_template_yaml +process_docs: !function utils.process_jurisprudence +tag: global_mmlu_full_pt_humanities_tasks +task: global_mmlu_full_pt_jurisprudence diff --git a/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_logical_fallacies.yaml b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_logical_fallacies.yaml new file mode 100644 index 00000000..c2451399 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_logical_fallacies.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pt_template_yaml +process_docs: !function utils.process_logical_fallacies +tag: global_mmlu_full_pt_humanities_tasks +task: global_mmlu_full_pt_logical_fallacies diff --git a/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_machine_learning.yaml b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_machine_learning.yaml new file mode 100644 index 00000000..79c577ea --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_machine_learning.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pt_template_yaml +process_docs: !function utils.process_machine_learning +tag: global_mmlu_full_pt_stem_tasks +task: global_mmlu_full_pt_machine_learning diff --git a/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_management.yaml b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_management.yaml new file mode 100644 index 00000000..a344b1c3 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_management.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pt_template_yaml +process_docs: !function utils.process_management +tag: global_mmlu_full_pt_other_tasks +task: global_mmlu_full_pt_management diff --git a/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_marketing.yaml b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_marketing.yaml new file mode 100644 index 00000000..eeff36b9 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_marketing.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pt_template_yaml +process_docs: !function utils.process_marketing +tag: global_mmlu_full_pt_other_tasks +task: global_mmlu_full_pt_marketing diff --git a/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_medical_genetics.yaml b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_medical_genetics.yaml new file mode 100644 index 00000000..27985380 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_medical_genetics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pt_template_yaml +process_docs: !function utils.process_medical_genetics +tag: global_mmlu_full_pt_other_tasks +task: global_mmlu_full_pt_medical_genetics diff --git a/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_miscellaneous.yaml b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_miscellaneous.yaml new file mode 100644 index 00000000..e2fa1da1 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_miscellaneous.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pt_template_yaml +process_docs: !function utils.process_miscellaneous +tag: global_mmlu_full_pt_other_tasks +task: global_mmlu_full_pt_miscellaneous diff --git a/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_moral_disputes.yaml b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_moral_disputes.yaml new file mode 100644 index 00000000..e83d186e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_moral_disputes.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pt_template_yaml +process_docs: !function utils.process_moral_disputes +tag: global_mmlu_full_pt_humanities_tasks +task: global_mmlu_full_pt_moral_disputes diff --git a/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_moral_scenarios.yaml b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_moral_scenarios.yaml new file mode 100644 index 00000000..3529a15c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_moral_scenarios.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pt_template_yaml +process_docs: !function utils.process_moral_scenarios +tag: global_mmlu_full_pt_humanities_tasks +task: global_mmlu_full_pt_moral_scenarios diff --git a/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_nutrition.yaml b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_nutrition.yaml new file mode 100644 index 00000000..e51eefe0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_nutrition.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pt_template_yaml +process_docs: !function utils.process_nutrition +tag: global_mmlu_full_pt_other_tasks +task: global_mmlu_full_pt_nutrition diff --git a/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_philosophy.yaml b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_philosophy.yaml new file mode 100644 index 00000000..ec0826b9 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_philosophy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pt_template_yaml +process_docs: !function utils.process_philosophy +tag: global_mmlu_full_pt_humanities_tasks +task: global_mmlu_full_pt_philosophy diff --git a/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_prehistory.yaml b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_prehistory.yaml new file mode 100644 index 00000000..324dfe69 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_prehistory.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pt_template_yaml +process_docs: !function utils.process_prehistory +tag: global_mmlu_full_pt_humanities_tasks +task: global_mmlu_full_pt_prehistory diff --git a/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_professional_accounting.yaml b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_professional_accounting.yaml new file mode 100644 index 00000000..530c918e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_professional_accounting.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pt_template_yaml +process_docs: !function utils.process_professional_accounting +tag: global_mmlu_full_pt_other_tasks +task: global_mmlu_full_pt_professional_accounting diff --git a/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_professional_law.yaml b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_professional_law.yaml new file mode 100644 index 00000000..f7a3679c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_professional_law.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pt_template_yaml +process_docs: !function utils.process_professional_law +tag: global_mmlu_full_pt_humanities_tasks +task: global_mmlu_full_pt_professional_law diff --git a/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_professional_medicine.yaml b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_professional_medicine.yaml new file mode 100644 index 00000000..0f4cc006 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_professional_medicine.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pt_template_yaml +process_docs: !function utils.process_professional_medicine +tag: global_mmlu_full_pt_other_tasks +task: global_mmlu_full_pt_professional_medicine diff --git a/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_professional_psychology.yaml b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_professional_psychology.yaml new file mode 100644 index 00000000..4c5884c9 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_professional_psychology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pt_template_yaml +process_docs: !function utils.process_professional_psychology +tag: global_mmlu_full_pt_social_sciences_tasks +task: global_mmlu_full_pt_professional_psychology diff --git a/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_public_relations.yaml b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_public_relations.yaml new file mode 100644 index 00000000..bb2d6536 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_public_relations.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pt_template_yaml +process_docs: !function utils.process_public_relations +tag: global_mmlu_full_pt_social_sciences_tasks +task: global_mmlu_full_pt_public_relations diff --git a/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_security_studies.yaml b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_security_studies.yaml new file mode 100644 index 00000000..1af8d662 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_security_studies.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pt_template_yaml +process_docs: !function utils.process_security_studies +tag: global_mmlu_full_pt_social_sciences_tasks +task: global_mmlu_full_pt_security_studies diff --git a/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_sociology.yaml b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_sociology.yaml new file mode 100644 index 00000000..3ef8fcb7 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_sociology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pt_template_yaml +process_docs: !function utils.process_sociology +tag: global_mmlu_full_pt_social_sciences_tasks +task: global_mmlu_full_pt_sociology diff --git a/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_us_foreign_policy.yaml b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_us_foreign_policy.yaml new file mode 100644 index 00000000..8b48f528 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_us_foreign_policy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pt_template_yaml +process_docs: !function utils.process_us_foreign_policy +tag: global_mmlu_full_pt_social_sciences_tasks +task: global_mmlu_full_pt_us_foreign_policy diff --git a/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_virology.yaml b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_virology.yaml new file mode 100644 index 00000000..4b0de753 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_virology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pt_template_yaml +process_docs: !function utils.process_virology +tag: global_mmlu_full_pt_other_tasks +task: global_mmlu_full_pt_virology diff --git a/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_world_religions.yaml b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_world_religions.yaml new file mode 100644 index 00000000..79648586 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pt/global_mmlu_full_pt_world_religions.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _pt_template_yaml +process_docs: !function utils.process_world_religions +tag: global_mmlu_full_pt_humanities_tasks +task: global_mmlu_full_pt_world_religions diff --git a/lm_eval/tasks/global_mmlu/full/pt/utils.py b/lm_eval/tasks/global_mmlu/full/pt/utils.py new file mode 100644 index 00000000..7df72cb0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/pt/utils.py @@ -0,0 +1,73 @@ +from functools import partial + + +SUBJECTS = [ + "abstract_algebra", + "anatomy", + "astronomy", + "business_ethics", + "clinical_knowledge", + "college_biology", + "college_chemistry", + "college_computer_science", + "college_mathematics", + "college_medicine", + "college_physics", + "computer_security", + "conceptual_physics", + "econometrics", + "electrical_engineering", + "elementary_mathematics", + "formal_logic", + "global_facts", + "high_school_biology", + "high_school_chemistry", + "high_school_computer_science", + "high_school_european_history", + "high_school_geography", + "high_school_government_and_politics", + "high_school_macroeconomics", + "high_school_mathematics", + "high_school_microeconomics", + "high_school_physics", + "high_school_psychology", + "high_school_statistics", + "high_school_us_history", + "high_school_world_history", + "human_aging", + "human_sexuality", + "international_law", + "jurisprudence", + "logical_fallacies", + "machine_learning", + "management", + "marketing", + "medical_genetics", + "miscellaneous", + "moral_disputes", + "moral_scenarios", + "nutrition", + "philosophy", + "prehistory", + "professional_accounting", + "professional_law", + "professional_medicine", + "professional_psychology", + "public_relations", + "security_studies", + "sociology", + "us_foreign_policy", + "virology", + "world_religions", +] + + +def process_docs(dataset, subject): + return dataset.filter(lambda x: x["subject"] == subject) + + +process_functions = { + f"process_{subject}": partial(process_docs, subject=subject) for subject in SUBJECTS +} + +globals().update(process_functions) diff --git a/lm_eval/tasks/global_mmlu/full/ro/_global_mmlu_full_ro.yaml b/lm_eval/tasks/global_mmlu/full/ro/_global_mmlu_full_ro.yaml new file mode 100644 index 00000000..b3aa5f49 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ro/_global_mmlu_full_ro.yaml @@ -0,0 +1,11 @@ +group: global_mmlu_full_ro +task: + - global_mmlu_full_ro_stem + - global_mmlu_full_ro_other + - global_mmlu_full_ro_social_sciences + - global_mmlu_full_ro_humanities +aggregate_metric_list: + - metric: acc + weight_by_size: True +metadata: + version: 1.0 diff --git a/lm_eval/tasks/global_mmlu/full/ro/_global_mmlu_full_ro_humanities.yaml b/lm_eval/tasks/global_mmlu/full/ro/_global_mmlu_full_ro_humanities.yaml new file mode 100644 index 00000000..d54268b0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ro/_global_mmlu_full_ro_humanities.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_ro_humanities +task: + - global_mmlu_full_ro_humanities_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/ro/_global_mmlu_full_ro_other.yaml b/lm_eval/tasks/global_mmlu/full/ro/_global_mmlu_full_ro_other.yaml new file mode 100644 index 00000000..4e58aea9 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ro/_global_mmlu_full_ro_other.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_ro_other +task: + - global_mmlu_full_ro_other_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/ro/_global_mmlu_full_ro_social_sciences.yaml b/lm_eval/tasks/global_mmlu/full/ro/_global_mmlu_full_ro_social_sciences.yaml new file mode 100644 index 00000000..e1cb84a9 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ro/_global_mmlu_full_ro_social_sciences.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_ro_social_sciences +task: + - global_mmlu_full_ro_social_sciences_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/ro/_global_mmlu_full_ro_stem.yaml b/lm_eval/tasks/global_mmlu/full/ro/_global_mmlu_full_ro_stem.yaml new file mode 100644 index 00000000..de0e406f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ro/_global_mmlu_full_ro_stem.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_ro_stem +task: + - global_mmlu_full_ro_stem_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/ro/_ro_template_yaml b/lm_eval/tasks/global_mmlu/full/ro/_ro_template_yaml new file mode 100644 index 00000000..e5cb6dd0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ro/_ro_template_yaml @@ -0,0 +1,16 @@ +dataset_path: CohereForAI/Global-MMLU +dataset_name: ro +test_split: test +fewshot_split: dev +fewshot_config: + sampler: first_n +output_type: multiple_choice +doc_to_text: "{{question.strip()}}\nA. {{option_a}}\nB. {{option_b}}\nC. {{option_c}}\nD. {{option_d}}\nAnswer:" +doc_to_choice: ["A", "B", "C", "D"] +doc_to_target: answer +metric_list: + - metric: acc + aggregation: mean + higher_is_better: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_abstract_algebra.yaml b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_abstract_algebra.yaml new file mode 100644 index 00000000..c505fb8b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_abstract_algebra.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ro_template_yaml +process_docs: !function utils.process_abstract_algebra +tag: global_mmlu_full_ro_stem_tasks +task: global_mmlu_full_ro_abstract_algebra diff --git a/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_anatomy.yaml b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_anatomy.yaml new file mode 100644 index 00000000..0c13018c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_anatomy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ro_template_yaml +process_docs: !function utils.process_anatomy +tag: global_mmlu_full_ro_stem_tasks +task: global_mmlu_full_ro_anatomy diff --git a/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_astronomy.yaml b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_astronomy.yaml new file mode 100644 index 00000000..9f4caefb --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_astronomy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ro_template_yaml +process_docs: !function utils.process_astronomy +tag: global_mmlu_full_ro_stem_tasks +task: global_mmlu_full_ro_astronomy diff --git a/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_business_ethics.yaml b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_business_ethics.yaml new file mode 100644 index 00000000..1c1387fd --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_business_ethics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ro_template_yaml +process_docs: !function utils.process_business_ethics +tag: global_mmlu_full_ro_other_tasks +task: global_mmlu_full_ro_business_ethics diff --git a/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_clinical_knowledge.yaml b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_clinical_knowledge.yaml new file mode 100644 index 00000000..b9e0dbb4 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_clinical_knowledge.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ro_template_yaml +process_docs: !function utils.process_clinical_knowledge +tag: global_mmlu_full_ro_other_tasks +task: global_mmlu_full_ro_clinical_knowledge diff --git a/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_college_biology.yaml b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_college_biology.yaml new file mode 100644 index 00000000..5bf14ab0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_college_biology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ro_template_yaml +process_docs: !function utils.process_college_biology +tag: global_mmlu_full_ro_stem_tasks +task: global_mmlu_full_ro_college_biology diff --git a/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_college_chemistry.yaml b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_college_chemistry.yaml new file mode 100644 index 00000000..59034744 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_college_chemistry.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ro_template_yaml +process_docs: !function utils.process_college_chemistry +tag: global_mmlu_full_ro_stem_tasks +task: global_mmlu_full_ro_college_chemistry diff --git a/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_college_computer_science.yaml b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_college_computer_science.yaml new file mode 100644 index 00000000..6bb64c2e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_college_computer_science.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ro_template_yaml +process_docs: !function utils.process_college_computer_science +tag: global_mmlu_full_ro_stem_tasks +task: global_mmlu_full_ro_college_computer_science diff --git a/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_college_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_college_mathematics.yaml new file mode 100644 index 00000000..d719a5ef --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_college_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ro_template_yaml +process_docs: !function utils.process_college_mathematics +tag: global_mmlu_full_ro_stem_tasks +task: global_mmlu_full_ro_college_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_college_medicine.yaml b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_college_medicine.yaml new file mode 100644 index 00000000..c9284a8f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_college_medicine.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ro_template_yaml +process_docs: !function utils.process_college_medicine +tag: global_mmlu_full_ro_other_tasks +task: global_mmlu_full_ro_college_medicine diff --git a/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_college_physics.yaml b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_college_physics.yaml new file mode 100644 index 00000000..1d27d843 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_college_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ro_template_yaml +process_docs: !function utils.process_college_physics +tag: global_mmlu_full_ro_stem_tasks +task: global_mmlu_full_ro_college_physics diff --git a/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_computer_security.yaml b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_computer_security.yaml new file mode 100644 index 00000000..1d63556e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_computer_security.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ro_template_yaml +process_docs: !function utils.process_computer_security +tag: global_mmlu_full_ro_stem_tasks +task: global_mmlu_full_ro_computer_security diff --git a/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_conceptual_physics.yaml b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_conceptual_physics.yaml new file mode 100644 index 00000000..25f30a36 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_conceptual_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ro_template_yaml +process_docs: !function utils.process_conceptual_physics +tag: global_mmlu_full_ro_stem_tasks +task: global_mmlu_full_ro_conceptual_physics diff --git a/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_econometrics.yaml b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_econometrics.yaml new file mode 100644 index 00000000..1fa6b5d2 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_econometrics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ro_template_yaml +process_docs: !function utils.process_econometrics +tag: global_mmlu_full_ro_social_sciences_tasks +task: global_mmlu_full_ro_econometrics diff --git a/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_electrical_engineering.yaml b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_electrical_engineering.yaml new file mode 100644 index 00000000..f6eb4b6e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_electrical_engineering.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ro_template_yaml +process_docs: !function utils.process_electrical_engineering +tag: global_mmlu_full_ro_stem_tasks +task: global_mmlu_full_ro_electrical_engineering diff --git a/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_elementary_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_elementary_mathematics.yaml new file mode 100644 index 00000000..e99772e2 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_elementary_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ro_template_yaml +process_docs: !function utils.process_elementary_mathematics +tag: global_mmlu_full_ro_stem_tasks +task: global_mmlu_full_ro_elementary_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_formal_logic.yaml b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_formal_logic.yaml new file mode 100644 index 00000000..be99bd00 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_formal_logic.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ro_template_yaml +process_docs: !function utils.process_formal_logic +tag: global_mmlu_full_ro_humanities_tasks +task: global_mmlu_full_ro_formal_logic diff --git a/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_global_facts.yaml b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_global_facts.yaml new file mode 100644 index 00000000..819937e7 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_global_facts.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ro_template_yaml +process_docs: !function utils.process_global_facts +tag: global_mmlu_full_ro_other_tasks +task: global_mmlu_full_ro_global_facts diff --git a/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_high_school_biology.yaml b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_high_school_biology.yaml new file mode 100644 index 00000000..d7509581 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_high_school_biology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ro_template_yaml +process_docs: !function utils.process_high_school_biology +tag: global_mmlu_full_ro_stem_tasks +task: global_mmlu_full_ro_high_school_biology diff --git a/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_high_school_chemistry.yaml b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_high_school_chemistry.yaml new file mode 100644 index 00000000..d089583f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_high_school_chemistry.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ro_template_yaml +process_docs: !function utils.process_high_school_chemistry +tag: global_mmlu_full_ro_stem_tasks +task: global_mmlu_full_ro_high_school_chemistry diff --git a/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_high_school_computer_science.yaml b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_high_school_computer_science.yaml new file mode 100644 index 00000000..46d5f472 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_high_school_computer_science.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ro_template_yaml +process_docs: !function utils.process_high_school_computer_science +tag: global_mmlu_full_ro_stem_tasks +task: global_mmlu_full_ro_high_school_computer_science diff --git a/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_high_school_european_history.yaml b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_high_school_european_history.yaml new file mode 100644 index 00000000..1a1ae7e7 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_high_school_european_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ro_template_yaml +process_docs: !function utils.process_high_school_european_history +tag: global_mmlu_full_ro_humanities_tasks +task: global_mmlu_full_ro_high_school_european_history diff --git a/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_high_school_geography.yaml b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_high_school_geography.yaml new file mode 100644 index 00000000..92935be5 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_high_school_geography.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ro_template_yaml +process_docs: !function utils.process_high_school_geography +tag: global_mmlu_full_ro_social_sciences_tasks +task: global_mmlu_full_ro_high_school_geography diff --git a/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_high_school_government_and_politics.yaml b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_high_school_government_and_politics.yaml new file mode 100644 index 00000000..efd2a03f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_high_school_government_and_politics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ro_template_yaml +process_docs: !function utils.process_high_school_government_and_politics +tag: global_mmlu_full_ro_social_sciences_tasks +task: global_mmlu_full_ro_high_school_government_and_politics diff --git a/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_high_school_macroeconomics.yaml b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_high_school_macroeconomics.yaml new file mode 100644 index 00000000..fe2f97d1 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_high_school_macroeconomics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ro_template_yaml +process_docs: !function utils.process_high_school_macroeconomics +tag: global_mmlu_full_ro_social_sciences_tasks +task: global_mmlu_full_ro_high_school_macroeconomics diff --git a/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_high_school_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_high_school_mathematics.yaml new file mode 100644 index 00000000..f0432a01 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_high_school_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ro_template_yaml +process_docs: !function utils.process_high_school_mathematics +tag: global_mmlu_full_ro_stem_tasks +task: global_mmlu_full_ro_high_school_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_high_school_microeconomics.yaml b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_high_school_microeconomics.yaml new file mode 100644 index 00000000..507fab86 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_high_school_microeconomics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ro_template_yaml +process_docs: !function utils.process_high_school_microeconomics +tag: global_mmlu_full_ro_social_sciences_tasks +task: global_mmlu_full_ro_high_school_microeconomics diff --git a/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_high_school_physics.yaml b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_high_school_physics.yaml new file mode 100644 index 00000000..19a76707 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_high_school_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ro_template_yaml +process_docs: !function utils.process_high_school_physics +tag: global_mmlu_full_ro_stem_tasks +task: global_mmlu_full_ro_high_school_physics diff --git a/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_high_school_psychology.yaml b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_high_school_psychology.yaml new file mode 100644 index 00000000..d27fc262 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_high_school_psychology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ro_template_yaml +process_docs: !function utils.process_high_school_psychology +tag: global_mmlu_full_ro_social_sciences_tasks +task: global_mmlu_full_ro_high_school_psychology diff --git a/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_high_school_statistics.yaml b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_high_school_statistics.yaml new file mode 100644 index 00000000..8f8023bc --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_high_school_statistics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ro_template_yaml +process_docs: !function utils.process_high_school_statistics +tag: global_mmlu_full_ro_stem_tasks +task: global_mmlu_full_ro_high_school_statistics diff --git a/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_high_school_us_history.yaml b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_high_school_us_history.yaml new file mode 100644 index 00000000..acc5fc41 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_high_school_us_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ro_template_yaml +process_docs: !function utils.process_high_school_us_history +tag: global_mmlu_full_ro_humanities_tasks +task: global_mmlu_full_ro_high_school_us_history diff --git a/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_high_school_world_history.yaml b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_high_school_world_history.yaml new file mode 100644 index 00000000..9ea7c933 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_high_school_world_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ro_template_yaml +process_docs: !function utils.process_high_school_world_history +tag: global_mmlu_full_ro_humanities_tasks +task: global_mmlu_full_ro_high_school_world_history diff --git a/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_human_aging.yaml b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_human_aging.yaml new file mode 100644 index 00000000..6b984c55 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_human_aging.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ro_template_yaml +process_docs: !function utils.process_human_aging +tag: global_mmlu_full_ro_other_tasks +task: global_mmlu_full_ro_human_aging diff --git a/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_human_sexuality.yaml b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_human_sexuality.yaml new file mode 100644 index 00000000..e2af2cbe --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_human_sexuality.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ro_template_yaml +process_docs: !function utils.process_human_sexuality +tag: global_mmlu_full_ro_social_sciences_tasks +task: global_mmlu_full_ro_human_sexuality diff --git a/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_international_law.yaml b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_international_law.yaml new file mode 100644 index 00000000..1cbf3d03 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_international_law.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ro_template_yaml +process_docs: !function utils.process_international_law +tag: global_mmlu_full_ro_humanities_tasks +task: global_mmlu_full_ro_international_law diff --git a/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_jurisprudence.yaml b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_jurisprudence.yaml new file mode 100644 index 00000000..d0acaca0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_jurisprudence.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ro_template_yaml +process_docs: !function utils.process_jurisprudence +tag: global_mmlu_full_ro_humanities_tasks +task: global_mmlu_full_ro_jurisprudence diff --git a/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_logical_fallacies.yaml b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_logical_fallacies.yaml new file mode 100644 index 00000000..c84234a0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_logical_fallacies.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ro_template_yaml +process_docs: !function utils.process_logical_fallacies +tag: global_mmlu_full_ro_humanities_tasks +task: global_mmlu_full_ro_logical_fallacies diff --git a/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_machine_learning.yaml b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_machine_learning.yaml new file mode 100644 index 00000000..09237c9e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_machine_learning.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ro_template_yaml +process_docs: !function utils.process_machine_learning +tag: global_mmlu_full_ro_stem_tasks +task: global_mmlu_full_ro_machine_learning diff --git a/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_management.yaml b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_management.yaml new file mode 100644 index 00000000..fcb3f485 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_management.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ro_template_yaml +process_docs: !function utils.process_management +tag: global_mmlu_full_ro_other_tasks +task: global_mmlu_full_ro_management diff --git a/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_marketing.yaml b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_marketing.yaml new file mode 100644 index 00000000..33b486c0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_marketing.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ro_template_yaml +process_docs: !function utils.process_marketing +tag: global_mmlu_full_ro_other_tasks +task: global_mmlu_full_ro_marketing diff --git a/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_medical_genetics.yaml b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_medical_genetics.yaml new file mode 100644 index 00000000..09c3d5e9 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_medical_genetics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ro_template_yaml +process_docs: !function utils.process_medical_genetics +tag: global_mmlu_full_ro_other_tasks +task: global_mmlu_full_ro_medical_genetics diff --git a/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_miscellaneous.yaml b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_miscellaneous.yaml new file mode 100644 index 00000000..e744e1e7 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_miscellaneous.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ro_template_yaml +process_docs: !function utils.process_miscellaneous +tag: global_mmlu_full_ro_other_tasks +task: global_mmlu_full_ro_miscellaneous diff --git a/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_moral_disputes.yaml b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_moral_disputes.yaml new file mode 100644 index 00000000..4e6d4ed7 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_moral_disputes.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ro_template_yaml +process_docs: !function utils.process_moral_disputes +tag: global_mmlu_full_ro_humanities_tasks +task: global_mmlu_full_ro_moral_disputes diff --git a/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_moral_scenarios.yaml b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_moral_scenarios.yaml new file mode 100644 index 00000000..d0e99149 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_moral_scenarios.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ro_template_yaml +process_docs: !function utils.process_moral_scenarios +tag: global_mmlu_full_ro_humanities_tasks +task: global_mmlu_full_ro_moral_scenarios diff --git a/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_nutrition.yaml b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_nutrition.yaml new file mode 100644 index 00000000..850262c1 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_nutrition.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ro_template_yaml +process_docs: !function utils.process_nutrition +tag: global_mmlu_full_ro_other_tasks +task: global_mmlu_full_ro_nutrition diff --git a/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_philosophy.yaml b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_philosophy.yaml new file mode 100644 index 00000000..9dd2bf54 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_philosophy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ro_template_yaml +process_docs: !function utils.process_philosophy +tag: global_mmlu_full_ro_humanities_tasks +task: global_mmlu_full_ro_philosophy diff --git a/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_prehistory.yaml b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_prehistory.yaml new file mode 100644 index 00000000..b2ecf40d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_prehistory.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ro_template_yaml +process_docs: !function utils.process_prehistory +tag: global_mmlu_full_ro_humanities_tasks +task: global_mmlu_full_ro_prehistory diff --git a/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_professional_accounting.yaml b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_professional_accounting.yaml new file mode 100644 index 00000000..db259766 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_professional_accounting.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ro_template_yaml +process_docs: !function utils.process_professional_accounting +tag: global_mmlu_full_ro_other_tasks +task: global_mmlu_full_ro_professional_accounting diff --git a/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_professional_law.yaml b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_professional_law.yaml new file mode 100644 index 00000000..b1e43974 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_professional_law.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ro_template_yaml +process_docs: !function utils.process_professional_law +tag: global_mmlu_full_ro_humanities_tasks +task: global_mmlu_full_ro_professional_law diff --git a/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_professional_medicine.yaml b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_professional_medicine.yaml new file mode 100644 index 00000000..0158c545 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_professional_medicine.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ro_template_yaml +process_docs: !function utils.process_professional_medicine +tag: global_mmlu_full_ro_other_tasks +task: global_mmlu_full_ro_professional_medicine diff --git a/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_professional_psychology.yaml b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_professional_psychology.yaml new file mode 100644 index 00000000..bdd7ca7f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_professional_psychology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ro_template_yaml +process_docs: !function utils.process_professional_psychology +tag: global_mmlu_full_ro_social_sciences_tasks +task: global_mmlu_full_ro_professional_psychology diff --git a/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_public_relations.yaml b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_public_relations.yaml new file mode 100644 index 00000000..5f7f0f51 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_public_relations.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ro_template_yaml +process_docs: !function utils.process_public_relations +tag: global_mmlu_full_ro_social_sciences_tasks +task: global_mmlu_full_ro_public_relations diff --git a/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_security_studies.yaml b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_security_studies.yaml new file mode 100644 index 00000000..be9b334e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_security_studies.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ro_template_yaml +process_docs: !function utils.process_security_studies +tag: global_mmlu_full_ro_social_sciences_tasks +task: global_mmlu_full_ro_security_studies diff --git a/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_sociology.yaml b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_sociology.yaml new file mode 100644 index 00000000..f37228bd --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_sociology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ro_template_yaml +process_docs: !function utils.process_sociology +tag: global_mmlu_full_ro_social_sciences_tasks +task: global_mmlu_full_ro_sociology diff --git a/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_us_foreign_policy.yaml b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_us_foreign_policy.yaml new file mode 100644 index 00000000..aae05dc9 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_us_foreign_policy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ro_template_yaml +process_docs: !function utils.process_us_foreign_policy +tag: global_mmlu_full_ro_social_sciences_tasks +task: global_mmlu_full_ro_us_foreign_policy diff --git a/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_virology.yaml b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_virology.yaml new file mode 100644 index 00000000..2d789c20 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_virology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ro_template_yaml +process_docs: !function utils.process_virology +tag: global_mmlu_full_ro_other_tasks +task: global_mmlu_full_ro_virology diff --git a/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_world_religions.yaml b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_world_religions.yaml new file mode 100644 index 00000000..40ff8228 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ro/global_mmlu_full_ro_world_religions.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ro_template_yaml +process_docs: !function utils.process_world_religions +tag: global_mmlu_full_ro_humanities_tasks +task: global_mmlu_full_ro_world_religions diff --git a/lm_eval/tasks/global_mmlu/full/ro/utils.py b/lm_eval/tasks/global_mmlu/full/ro/utils.py new file mode 100644 index 00000000..7df72cb0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ro/utils.py @@ -0,0 +1,73 @@ +from functools import partial + + +SUBJECTS = [ + "abstract_algebra", + "anatomy", + "astronomy", + "business_ethics", + "clinical_knowledge", + "college_biology", + "college_chemistry", + "college_computer_science", + "college_mathematics", + "college_medicine", + "college_physics", + "computer_security", + "conceptual_physics", + "econometrics", + "electrical_engineering", + "elementary_mathematics", + "formal_logic", + "global_facts", + "high_school_biology", + "high_school_chemistry", + "high_school_computer_science", + "high_school_european_history", + "high_school_geography", + "high_school_government_and_politics", + "high_school_macroeconomics", + "high_school_mathematics", + "high_school_microeconomics", + "high_school_physics", + "high_school_psychology", + "high_school_statistics", + "high_school_us_history", + "high_school_world_history", + "human_aging", + "human_sexuality", + "international_law", + "jurisprudence", + "logical_fallacies", + "machine_learning", + "management", + "marketing", + "medical_genetics", + "miscellaneous", + "moral_disputes", + "moral_scenarios", + "nutrition", + "philosophy", + "prehistory", + "professional_accounting", + "professional_law", + "professional_medicine", + "professional_psychology", + "public_relations", + "security_studies", + "sociology", + "us_foreign_policy", + "virology", + "world_religions", +] + + +def process_docs(dataset, subject): + return dataset.filter(lambda x: x["subject"] == subject) + + +process_functions = { + f"process_{subject}": partial(process_docs, subject=subject) for subject in SUBJECTS +} + +globals().update(process_functions) diff --git a/lm_eval/tasks/global_mmlu/full/ru/_global_mmlu_full_ru.yaml b/lm_eval/tasks/global_mmlu/full/ru/_global_mmlu_full_ru.yaml new file mode 100644 index 00000000..cc63cd34 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ru/_global_mmlu_full_ru.yaml @@ -0,0 +1,11 @@ +group: global_mmlu_full_ru +task: + - global_mmlu_full_ru_stem + - global_mmlu_full_ru_other + - global_mmlu_full_ru_social_sciences + - global_mmlu_full_ru_humanities +aggregate_metric_list: + - metric: acc + weight_by_size: True +metadata: + version: 1.0 diff --git a/lm_eval/tasks/global_mmlu/full/ru/_global_mmlu_full_ru_humanities.yaml b/lm_eval/tasks/global_mmlu/full/ru/_global_mmlu_full_ru_humanities.yaml new file mode 100644 index 00000000..55422b43 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ru/_global_mmlu_full_ru_humanities.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_ru_humanities +task: + - global_mmlu_full_ru_humanities_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/ru/_global_mmlu_full_ru_other.yaml b/lm_eval/tasks/global_mmlu/full/ru/_global_mmlu_full_ru_other.yaml new file mode 100644 index 00000000..d47ccc60 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ru/_global_mmlu_full_ru_other.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_ru_other +task: + - global_mmlu_full_ru_other_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/ru/_global_mmlu_full_ru_social_sciences.yaml b/lm_eval/tasks/global_mmlu/full/ru/_global_mmlu_full_ru_social_sciences.yaml new file mode 100644 index 00000000..12d48428 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ru/_global_mmlu_full_ru_social_sciences.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_ru_social_sciences +task: + - global_mmlu_full_ru_social_sciences_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/ru/_global_mmlu_full_ru_stem.yaml b/lm_eval/tasks/global_mmlu/full/ru/_global_mmlu_full_ru_stem.yaml new file mode 100644 index 00000000..70ae3edb --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ru/_global_mmlu_full_ru_stem.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_ru_stem +task: + - global_mmlu_full_ru_stem_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/ru/_ru_template_yaml b/lm_eval/tasks/global_mmlu/full/ru/_ru_template_yaml new file mode 100644 index 00000000..4b2f491b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ru/_ru_template_yaml @@ -0,0 +1,16 @@ +dataset_path: CohereForAI/Global-MMLU +dataset_name: ru +test_split: test +fewshot_split: dev +fewshot_config: + sampler: first_n +output_type: multiple_choice +doc_to_text: "{{question.strip()}}\nA. {{option_a}}\nB. {{option_b}}\nC. {{option_c}}\nD. {{option_d}}\nAnswer:" +doc_to_choice: ["A", "B", "C", "D"] +doc_to_target: answer +metric_list: + - metric: acc + aggregation: mean + higher_is_better: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_abstract_algebra.yaml b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_abstract_algebra.yaml new file mode 100644 index 00000000..de158df8 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_abstract_algebra.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ru_template_yaml +process_docs: !function utils.process_abstract_algebra +tag: global_mmlu_full_ru_stem_tasks +task: global_mmlu_full_ru_abstract_algebra diff --git a/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_anatomy.yaml b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_anatomy.yaml new file mode 100644 index 00000000..aab717e4 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_anatomy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ru_template_yaml +process_docs: !function utils.process_anatomy +tag: global_mmlu_full_ru_stem_tasks +task: global_mmlu_full_ru_anatomy diff --git a/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_astronomy.yaml b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_astronomy.yaml new file mode 100644 index 00000000..3d8d0e32 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_astronomy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ru_template_yaml +process_docs: !function utils.process_astronomy +tag: global_mmlu_full_ru_stem_tasks +task: global_mmlu_full_ru_astronomy diff --git a/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_business_ethics.yaml b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_business_ethics.yaml new file mode 100644 index 00000000..d2855ca3 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_business_ethics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ru_template_yaml +process_docs: !function utils.process_business_ethics +tag: global_mmlu_full_ru_other_tasks +task: global_mmlu_full_ru_business_ethics diff --git a/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_clinical_knowledge.yaml b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_clinical_knowledge.yaml new file mode 100644 index 00000000..2efe0829 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_clinical_knowledge.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ru_template_yaml +process_docs: !function utils.process_clinical_knowledge +tag: global_mmlu_full_ru_other_tasks +task: global_mmlu_full_ru_clinical_knowledge diff --git a/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_college_biology.yaml b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_college_biology.yaml new file mode 100644 index 00000000..96d00deb --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_college_biology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ru_template_yaml +process_docs: !function utils.process_college_biology +tag: global_mmlu_full_ru_stem_tasks +task: global_mmlu_full_ru_college_biology diff --git a/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_college_chemistry.yaml b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_college_chemistry.yaml new file mode 100644 index 00000000..0a5aac35 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_college_chemistry.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ru_template_yaml +process_docs: !function utils.process_college_chemistry +tag: global_mmlu_full_ru_stem_tasks +task: global_mmlu_full_ru_college_chemistry diff --git a/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_college_computer_science.yaml b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_college_computer_science.yaml new file mode 100644 index 00000000..bd8bf28b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_college_computer_science.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ru_template_yaml +process_docs: !function utils.process_college_computer_science +tag: global_mmlu_full_ru_stem_tasks +task: global_mmlu_full_ru_college_computer_science diff --git a/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_college_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_college_mathematics.yaml new file mode 100644 index 00000000..a2e080c3 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_college_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ru_template_yaml +process_docs: !function utils.process_college_mathematics +tag: global_mmlu_full_ru_stem_tasks +task: global_mmlu_full_ru_college_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_college_medicine.yaml b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_college_medicine.yaml new file mode 100644 index 00000000..70e8448e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_college_medicine.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ru_template_yaml +process_docs: !function utils.process_college_medicine +tag: global_mmlu_full_ru_other_tasks +task: global_mmlu_full_ru_college_medicine diff --git a/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_college_physics.yaml b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_college_physics.yaml new file mode 100644 index 00000000..8e6ecbcf --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_college_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ru_template_yaml +process_docs: !function utils.process_college_physics +tag: global_mmlu_full_ru_stem_tasks +task: global_mmlu_full_ru_college_physics diff --git a/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_computer_security.yaml b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_computer_security.yaml new file mode 100644 index 00000000..f196351a --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_computer_security.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ru_template_yaml +process_docs: !function utils.process_computer_security +tag: global_mmlu_full_ru_stem_tasks +task: global_mmlu_full_ru_computer_security diff --git a/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_conceptual_physics.yaml b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_conceptual_physics.yaml new file mode 100644 index 00000000..e623d78f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_conceptual_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ru_template_yaml +process_docs: !function utils.process_conceptual_physics +tag: global_mmlu_full_ru_stem_tasks +task: global_mmlu_full_ru_conceptual_physics diff --git a/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_econometrics.yaml b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_econometrics.yaml new file mode 100644 index 00000000..df35a1f6 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_econometrics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ru_template_yaml +process_docs: !function utils.process_econometrics +tag: global_mmlu_full_ru_social_sciences_tasks +task: global_mmlu_full_ru_econometrics diff --git a/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_electrical_engineering.yaml b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_electrical_engineering.yaml new file mode 100644 index 00000000..82c49f89 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_electrical_engineering.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ru_template_yaml +process_docs: !function utils.process_electrical_engineering +tag: global_mmlu_full_ru_stem_tasks +task: global_mmlu_full_ru_electrical_engineering diff --git a/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_elementary_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_elementary_mathematics.yaml new file mode 100644 index 00000000..6ed11c5f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_elementary_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ru_template_yaml +process_docs: !function utils.process_elementary_mathematics +tag: global_mmlu_full_ru_stem_tasks +task: global_mmlu_full_ru_elementary_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_formal_logic.yaml b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_formal_logic.yaml new file mode 100644 index 00000000..8ebe62bf --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_formal_logic.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ru_template_yaml +process_docs: !function utils.process_formal_logic +tag: global_mmlu_full_ru_humanities_tasks +task: global_mmlu_full_ru_formal_logic diff --git a/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_global_facts.yaml b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_global_facts.yaml new file mode 100644 index 00000000..27d6ad70 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_global_facts.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ru_template_yaml +process_docs: !function utils.process_global_facts +tag: global_mmlu_full_ru_other_tasks +task: global_mmlu_full_ru_global_facts diff --git a/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_high_school_biology.yaml b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_high_school_biology.yaml new file mode 100644 index 00000000..7860e73e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_high_school_biology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ru_template_yaml +process_docs: !function utils.process_high_school_biology +tag: global_mmlu_full_ru_stem_tasks +task: global_mmlu_full_ru_high_school_biology diff --git a/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_high_school_chemistry.yaml b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_high_school_chemistry.yaml new file mode 100644 index 00000000..7596daa3 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_high_school_chemistry.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ru_template_yaml +process_docs: !function utils.process_high_school_chemistry +tag: global_mmlu_full_ru_stem_tasks +task: global_mmlu_full_ru_high_school_chemistry diff --git a/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_high_school_computer_science.yaml b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_high_school_computer_science.yaml new file mode 100644 index 00000000..ecb64d52 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_high_school_computer_science.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ru_template_yaml +process_docs: !function utils.process_high_school_computer_science +tag: global_mmlu_full_ru_stem_tasks +task: global_mmlu_full_ru_high_school_computer_science diff --git a/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_high_school_european_history.yaml b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_high_school_european_history.yaml new file mode 100644 index 00000000..92feccc5 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_high_school_european_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ru_template_yaml +process_docs: !function utils.process_high_school_european_history +tag: global_mmlu_full_ru_humanities_tasks +task: global_mmlu_full_ru_high_school_european_history diff --git a/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_high_school_geography.yaml b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_high_school_geography.yaml new file mode 100644 index 00000000..6f586f50 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_high_school_geography.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ru_template_yaml +process_docs: !function utils.process_high_school_geography +tag: global_mmlu_full_ru_social_sciences_tasks +task: global_mmlu_full_ru_high_school_geography diff --git a/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_high_school_government_and_politics.yaml b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_high_school_government_and_politics.yaml new file mode 100644 index 00000000..0ffc85df --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_high_school_government_and_politics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ru_template_yaml +process_docs: !function utils.process_high_school_government_and_politics +tag: global_mmlu_full_ru_social_sciences_tasks +task: global_mmlu_full_ru_high_school_government_and_politics diff --git a/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_high_school_macroeconomics.yaml b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_high_school_macroeconomics.yaml new file mode 100644 index 00000000..5da13204 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_high_school_macroeconomics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ru_template_yaml +process_docs: !function utils.process_high_school_macroeconomics +tag: global_mmlu_full_ru_social_sciences_tasks +task: global_mmlu_full_ru_high_school_macroeconomics diff --git a/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_high_school_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_high_school_mathematics.yaml new file mode 100644 index 00000000..fc684975 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_high_school_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ru_template_yaml +process_docs: !function utils.process_high_school_mathematics +tag: global_mmlu_full_ru_stem_tasks +task: global_mmlu_full_ru_high_school_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_high_school_microeconomics.yaml b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_high_school_microeconomics.yaml new file mode 100644 index 00000000..84887d18 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_high_school_microeconomics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ru_template_yaml +process_docs: !function utils.process_high_school_microeconomics +tag: global_mmlu_full_ru_social_sciences_tasks +task: global_mmlu_full_ru_high_school_microeconomics diff --git a/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_high_school_physics.yaml b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_high_school_physics.yaml new file mode 100644 index 00000000..29ddf5bf --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_high_school_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ru_template_yaml +process_docs: !function utils.process_high_school_physics +tag: global_mmlu_full_ru_stem_tasks +task: global_mmlu_full_ru_high_school_physics diff --git a/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_high_school_psychology.yaml b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_high_school_psychology.yaml new file mode 100644 index 00000000..a0680bad --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_high_school_psychology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ru_template_yaml +process_docs: !function utils.process_high_school_psychology +tag: global_mmlu_full_ru_social_sciences_tasks +task: global_mmlu_full_ru_high_school_psychology diff --git a/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_high_school_statistics.yaml b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_high_school_statistics.yaml new file mode 100644 index 00000000..07ac341b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_high_school_statistics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ru_template_yaml +process_docs: !function utils.process_high_school_statistics +tag: global_mmlu_full_ru_stem_tasks +task: global_mmlu_full_ru_high_school_statistics diff --git a/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_high_school_us_history.yaml b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_high_school_us_history.yaml new file mode 100644 index 00000000..18e12bcd --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_high_school_us_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ru_template_yaml +process_docs: !function utils.process_high_school_us_history +tag: global_mmlu_full_ru_humanities_tasks +task: global_mmlu_full_ru_high_school_us_history diff --git a/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_high_school_world_history.yaml b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_high_school_world_history.yaml new file mode 100644 index 00000000..c37522a2 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_high_school_world_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ru_template_yaml +process_docs: !function utils.process_high_school_world_history +tag: global_mmlu_full_ru_humanities_tasks +task: global_mmlu_full_ru_high_school_world_history diff --git a/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_human_aging.yaml b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_human_aging.yaml new file mode 100644 index 00000000..cbd6bf32 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_human_aging.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ru_template_yaml +process_docs: !function utils.process_human_aging +tag: global_mmlu_full_ru_other_tasks +task: global_mmlu_full_ru_human_aging diff --git a/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_human_sexuality.yaml b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_human_sexuality.yaml new file mode 100644 index 00000000..8766c348 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_human_sexuality.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ru_template_yaml +process_docs: !function utils.process_human_sexuality +tag: global_mmlu_full_ru_social_sciences_tasks +task: global_mmlu_full_ru_human_sexuality diff --git a/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_international_law.yaml b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_international_law.yaml new file mode 100644 index 00000000..4edbb98c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_international_law.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ru_template_yaml +process_docs: !function utils.process_international_law +tag: global_mmlu_full_ru_humanities_tasks +task: global_mmlu_full_ru_international_law diff --git a/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_jurisprudence.yaml b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_jurisprudence.yaml new file mode 100644 index 00000000..24cea632 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_jurisprudence.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ru_template_yaml +process_docs: !function utils.process_jurisprudence +tag: global_mmlu_full_ru_humanities_tasks +task: global_mmlu_full_ru_jurisprudence diff --git a/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_logical_fallacies.yaml b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_logical_fallacies.yaml new file mode 100644 index 00000000..3160fadc --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_logical_fallacies.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ru_template_yaml +process_docs: !function utils.process_logical_fallacies +tag: global_mmlu_full_ru_humanities_tasks +task: global_mmlu_full_ru_logical_fallacies diff --git a/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_machine_learning.yaml b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_machine_learning.yaml new file mode 100644 index 00000000..b8e480e6 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_machine_learning.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ru_template_yaml +process_docs: !function utils.process_machine_learning +tag: global_mmlu_full_ru_stem_tasks +task: global_mmlu_full_ru_machine_learning diff --git a/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_management.yaml b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_management.yaml new file mode 100644 index 00000000..4a7b77a1 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_management.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ru_template_yaml +process_docs: !function utils.process_management +tag: global_mmlu_full_ru_other_tasks +task: global_mmlu_full_ru_management diff --git a/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_marketing.yaml b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_marketing.yaml new file mode 100644 index 00000000..c71a4f29 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_marketing.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ru_template_yaml +process_docs: !function utils.process_marketing +tag: global_mmlu_full_ru_other_tasks +task: global_mmlu_full_ru_marketing diff --git a/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_medical_genetics.yaml b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_medical_genetics.yaml new file mode 100644 index 00000000..ac34ba20 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_medical_genetics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ru_template_yaml +process_docs: !function utils.process_medical_genetics +tag: global_mmlu_full_ru_other_tasks +task: global_mmlu_full_ru_medical_genetics diff --git a/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_miscellaneous.yaml b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_miscellaneous.yaml new file mode 100644 index 00000000..6049ccb1 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_miscellaneous.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ru_template_yaml +process_docs: !function utils.process_miscellaneous +tag: global_mmlu_full_ru_other_tasks +task: global_mmlu_full_ru_miscellaneous diff --git a/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_moral_disputes.yaml b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_moral_disputes.yaml new file mode 100644 index 00000000..d974ccfa --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_moral_disputes.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ru_template_yaml +process_docs: !function utils.process_moral_disputes +tag: global_mmlu_full_ru_humanities_tasks +task: global_mmlu_full_ru_moral_disputes diff --git a/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_moral_scenarios.yaml b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_moral_scenarios.yaml new file mode 100644 index 00000000..f05f7de9 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_moral_scenarios.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ru_template_yaml +process_docs: !function utils.process_moral_scenarios +tag: global_mmlu_full_ru_humanities_tasks +task: global_mmlu_full_ru_moral_scenarios diff --git a/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_nutrition.yaml b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_nutrition.yaml new file mode 100644 index 00000000..59cc8dee --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_nutrition.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ru_template_yaml +process_docs: !function utils.process_nutrition +tag: global_mmlu_full_ru_other_tasks +task: global_mmlu_full_ru_nutrition diff --git a/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_philosophy.yaml b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_philosophy.yaml new file mode 100644 index 00000000..eb78b1f7 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_philosophy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ru_template_yaml +process_docs: !function utils.process_philosophy +tag: global_mmlu_full_ru_humanities_tasks +task: global_mmlu_full_ru_philosophy diff --git a/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_prehistory.yaml b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_prehistory.yaml new file mode 100644 index 00000000..685bb2a4 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_prehistory.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ru_template_yaml +process_docs: !function utils.process_prehistory +tag: global_mmlu_full_ru_humanities_tasks +task: global_mmlu_full_ru_prehistory diff --git a/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_professional_accounting.yaml b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_professional_accounting.yaml new file mode 100644 index 00000000..35c21255 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_professional_accounting.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ru_template_yaml +process_docs: !function utils.process_professional_accounting +tag: global_mmlu_full_ru_other_tasks +task: global_mmlu_full_ru_professional_accounting diff --git a/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_professional_law.yaml b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_professional_law.yaml new file mode 100644 index 00000000..ce70d006 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_professional_law.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ru_template_yaml +process_docs: !function utils.process_professional_law +tag: global_mmlu_full_ru_humanities_tasks +task: global_mmlu_full_ru_professional_law diff --git a/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_professional_medicine.yaml b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_professional_medicine.yaml new file mode 100644 index 00000000..cce88d1d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_professional_medicine.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ru_template_yaml +process_docs: !function utils.process_professional_medicine +tag: global_mmlu_full_ru_other_tasks +task: global_mmlu_full_ru_professional_medicine diff --git a/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_professional_psychology.yaml b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_professional_psychology.yaml new file mode 100644 index 00000000..39fc8953 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_professional_psychology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ru_template_yaml +process_docs: !function utils.process_professional_psychology +tag: global_mmlu_full_ru_social_sciences_tasks +task: global_mmlu_full_ru_professional_psychology diff --git a/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_public_relations.yaml b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_public_relations.yaml new file mode 100644 index 00000000..3dfd71cc --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_public_relations.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ru_template_yaml +process_docs: !function utils.process_public_relations +tag: global_mmlu_full_ru_social_sciences_tasks +task: global_mmlu_full_ru_public_relations diff --git a/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_security_studies.yaml b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_security_studies.yaml new file mode 100644 index 00000000..bd08ea34 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_security_studies.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ru_template_yaml +process_docs: !function utils.process_security_studies +tag: global_mmlu_full_ru_social_sciences_tasks +task: global_mmlu_full_ru_security_studies diff --git a/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_sociology.yaml b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_sociology.yaml new file mode 100644 index 00000000..ef616ee1 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_sociology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ru_template_yaml +process_docs: !function utils.process_sociology +tag: global_mmlu_full_ru_social_sciences_tasks +task: global_mmlu_full_ru_sociology diff --git a/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_us_foreign_policy.yaml b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_us_foreign_policy.yaml new file mode 100644 index 00000000..c8244e65 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_us_foreign_policy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ru_template_yaml +process_docs: !function utils.process_us_foreign_policy +tag: global_mmlu_full_ru_social_sciences_tasks +task: global_mmlu_full_ru_us_foreign_policy diff --git a/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_virology.yaml b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_virology.yaml new file mode 100644 index 00000000..2f4df810 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_virology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ru_template_yaml +process_docs: !function utils.process_virology +tag: global_mmlu_full_ru_other_tasks +task: global_mmlu_full_ru_virology diff --git a/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_world_religions.yaml b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_world_religions.yaml new file mode 100644 index 00000000..06f71986 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ru/global_mmlu_full_ru_world_religions.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _ru_template_yaml +process_docs: !function utils.process_world_religions +tag: global_mmlu_full_ru_humanities_tasks +task: global_mmlu_full_ru_world_religions diff --git a/lm_eval/tasks/global_mmlu/full/ru/utils.py b/lm_eval/tasks/global_mmlu/full/ru/utils.py new file mode 100644 index 00000000..7df72cb0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/ru/utils.py @@ -0,0 +1,73 @@ +from functools import partial + + +SUBJECTS = [ + "abstract_algebra", + "anatomy", + "astronomy", + "business_ethics", + "clinical_knowledge", + "college_biology", + "college_chemistry", + "college_computer_science", + "college_mathematics", + "college_medicine", + "college_physics", + "computer_security", + "conceptual_physics", + "econometrics", + "electrical_engineering", + "elementary_mathematics", + "formal_logic", + "global_facts", + "high_school_biology", + "high_school_chemistry", + "high_school_computer_science", + "high_school_european_history", + "high_school_geography", + "high_school_government_and_politics", + "high_school_macroeconomics", + "high_school_mathematics", + "high_school_microeconomics", + "high_school_physics", + "high_school_psychology", + "high_school_statistics", + "high_school_us_history", + "high_school_world_history", + "human_aging", + "human_sexuality", + "international_law", + "jurisprudence", + "logical_fallacies", + "machine_learning", + "management", + "marketing", + "medical_genetics", + "miscellaneous", + "moral_disputes", + "moral_scenarios", + "nutrition", + "philosophy", + "prehistory", + "professional_accounting", + "professional_law", + "professional_medicine", + "professional_psychology", + "public_relations", + "security_studies", + "sociology", + "us_foreign_policy", + "virology", + "world_religions", +] + + +def process_docs(dataset, subject): + return dataset.filter(lambda x: x["subject"] == subject) + + +process_functions = { + f"process_{subject}": partial(process_docs, subject=subject) for subject in SUBJECTS +} + +globals().update(process_functions) diff --git a/lm_eval/tasks/global_mmlu/full/si/_global_mmlu_full_si.yaml b/lm_eval/tasks/global_mmlu/full/si/_global_mmlu_full_si.yaml new file mode 100644 index 00000000..4deed570 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/si/_global_mmlu_full_si.yaml @@ -0,0 +1,11 @@ +group: global_mmlu_full_si +task: + - global_mmlu_full_si_stem + - global_mmlu_full_si_other + - global_mmlu_full_si_social_sciences + - global_mmlu_full_si_humanities +aggregate_metric_list: + - metric: acc + weight_by_size: True +metadata: + version: 1.0 diff --git a/lm_eval/tasks/global_mmlu/full/si/_global_mmlu_full_si_humanities.yaml b/lm_eval/tasks/global_mmlu/full/si/_global_mmlu_full_si_humanities.yaml new file mode 100644 index 00000000..b97994d0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/si/_global_mmlu_full_si_humanities.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_si_humanities +task: + - global_mmlu_full_si_humanities_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/si/_global_mmlu_full_si_other.yaml b/lm_eval/tasks/global_mmlu/full/si/_global_mmlu_full_si_other.yaml new file mode 100644 index 00000000..e7600ca4 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/si/_global_mmlu_full_si_other.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_si_other +task: + - global_mmlu_full_si_other_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/si/_global_mmlu_full_si_social_sciences.yaml b/lm_eval/tasks/global_mmlu/full/si/_global_mmlu_full_si_social_sciences.yaml new file mode 100644 index 00000000..4e2351a2 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/si/_global_mmlu_full_si_social_sciences.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_si_social_sciences +task: + - global_mmlu_full_si_social_sciences_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/si/_global_mmlu_full_si_stem.yaml b/lm_eval/tasks/global_mmlu/full/si/_global_mmlu_full_si_stem.yaml new file mode 100644 index 00000000..8878bf80 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/si/_global_mmlu_full_si_stem.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_si_stem +task: + - global_mmlu_full_si_stem_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/si/_si_template_yaml b/lm_eval/tasks/global_mmlu/full/si/_si_template_yaml new file mode 100644 index 00000000..5c775b20 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/si/_si_template_yaml @@ -0,0 +1,16 @@ +dataset_path: CohereForAI/Global-MMLU +dataset_name: si +test_split: test +fewshot_split: dev +fewshot_config: + sampler: first_n +output_type: multiple_choice +doc_to_text: "{{question.strip()}}\nA. {{option_a}}\nB. {{option_b}}\nC. {{option_c}}\nD. {{option_d}}\nAnswer:" +doc_to_choice: ["A", "B", "C", "D"] +doc_to_target: answer +metric_list: + - metric: acc + aggregation: mean + higher_is_better: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_abstract_algebra.yaml b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_abstract_algebra.yaml new file mode 100644 index 00000000..b81c5803 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_abstract_algebra.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _si_template_yaml +process_docs: !function utils.process_abstract_algebra +tag: global_mmlu_full_si_stem_tasks +task: global_mmlu_full_si_abstract_algebra diff --git a/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_anatomy.yaml b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_anatomy.yaml new file mode 100644 index 00000000..32315245 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_anatomy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _si_template_yaml +process_docs: !function utils.process_anatomy +tag: global_mmlu_full_si_stem_tasks +task: global_mmlu_full_si_anatomy diff --git a/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_astronomy.yaml b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_astronomy.yaml new file mode 100644 index 00000000..c7ab9539 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_astronomy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _si_template_yaml +process_docs: !function utils.process_astronomy +tag: global_mmlu_full_si_stem_tasks +task: global_mmlu_full_si_astronomy diff --git a/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_business_ethics.yaml b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_business_ethics.yaml new file mode 100644 index 00000000..8281fc42 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_business_ethics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _si_template_yaml +process_docs: !function utils.process_business_ethics +tag: global_mmlu_full_si_other_tasks +task: global_mmlu_full_si_business_ethics diff --git a/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_clinical_knowledge.yaml b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_clinical_knowledge.yaml new file mode 100644 index 00000000..2a7f5cf5 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_clinical_knowledge.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _si_template_yaml +process_docs: !function utils.process_clinical_knowledge +tag: global_mmlu_full_si_other_tasks +task: global_mmlu_full_si_clinical_knowledge diff --git a/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_college_biology.yaml b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_college_biology.yaml new file mode 100644 index 00000000..e54148da --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_college_biology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _si_template_yaml +process_docs: !function utils.process_college_biology +tag: global_mmlu_full_si_stem_tasks +task: global_mmlu_full_si_college_biology diff --git a/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_college_chemistry.yaml b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_college_chemistry.yaml new file mode 100644 index 00000000..b797ac60 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_college_chemistry.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _si_template_yaml +process_docs: !function utils.process_college_chemistry +tag: global_mmlu_full_si_stem_tasks +task: global_mmlu_full_si_college_chemistry diff --git a/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_college_computer_science.yaml b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_college_computer_science.yaml new file mode 100644 index 00000000..ba69de35 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_college_computer_science.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _si_template_yaml +process_docs: !function utils.process_college_computer_science +tag: global_mmlu_full_si_stem_tasks +task: global_mmlu_full_si_college_computer_science diff --git a/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_college_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_college_mathematics.yaml new file mode 100644 index 00000000..65ed9424 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_college_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _si_template_yaml +process_docs: !function utils.process_college_mathematics +tag: global_mmlu_full_si_stem_tasks +task: global_mmlu_full_si_college_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_college_medicine.yaml b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_college_medicine.yaml new file mode 100644 index 00000000..1418aa0d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_college_medicine.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _si_template_yaml +process_docs: !function utils.process_college_medicine +tag: global_mmlu_full_si_other_tasks +task: global_mmlu_full_si_college_medicine diff --git a/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_college_physics.yaml b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_college_physics.yaml new file mode 100644 index 00000000..cb32cd4f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_college_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _si_template_yaml +process_docs: !function utils.process_college_physics +tag: global_mmlu_full_si_stem_tasks +task: global_mmlu_full_si_college_physics diff --git a/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_computer_security.yaml b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_computer_security.yaml new file mode 100644 index 00000000..ce5ab9b7 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_computer_security.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _si_template_yaml +process_docs: !function utils.process_computer_security +tag: global_mmlu_full_si_stem_tasks +task: global_mmlu_full_si_computer_security diff --git a/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_conceptual_physics.yaml b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_conceptual_physics.yaml new file mode 100644 index 00000000..c2ab5718 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_conceptual_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _si_template_yaml +process_docs: !function utils.process_conceptual_physics +tag: global_mmlu_full_si_stem_tasks +task: global_mmlu_full_si_conceptual_physics diff --git a/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_econometrics.yaml b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_econometrics.yaml new file mode 100644 index 00000000..5e764903 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_econometrics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _si_template_yaml +process_docs: !function utils.process_econometrics +tag: global_mmlu_full_si_social_sciences_tasks +task: global_mmlu_full_si_econometrics diff --git a/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_electrical_engineering.yaml b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_electrical_engineering.yaml new file mode 100644 index 00000000..99679bb0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_electrical_engineering.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _si_template_yaml +process_docs: !function utils.process_electrical_engineering +tag: global_mmlu_full_si_stem_tasks +task: global_mmlu_full_si_electrical_engineering diff --git a/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_elementary_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_elementary_mathematics.yaml new file mode 100644 index 00000000..553bc9bb --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_elementary_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _si_template_yaml +process_docs: !function utils.process_elementary_mathematics +tag: global_mmlu_full_si_stem_tasks +task: global_mmlu_full_si_elementary_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_formal_logic.yaml b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_formal_logic.yaml new file mode 100644 index 00000000..112814b6 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_formal_logic.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _si_template_yaml +process_docs: !function utils.process_formal_logic +tag: global_mmlu_full_si_humanities_tasks +task: global_mmlu_full_si_formal_logic diff --git a/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_global_facts.yaml b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_global_facts.yaml new file mode 100644 index 00000000..008b5537 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_global_facts.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _si_template_yaml +process_docs: !function utils.process_global_facts +tag: global_mmlu_full_si_other_tasks +task: global_mmlu_full_si_global_facts diff --git a/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_high_school_biology.yaml b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_high_school_biology.yaml new file mode 100644 index 00000000..fecd995a --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_high_school_biology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _si_template_yaml +process_docs: !function utils.process_high_school_biology +tag: global_mmlu_full_si_stem_tasks +task: global_mmlu_full_si_high_school_biology diff --git a/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_high_school_chemistry.yaml b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_high_school_chemistry.yaml new file mode 100644 index 00000000..3d3018b6 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_high_school_chemistry.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _si_template_yaml +process_docs: !function utils.process_high_school_chemistry +tag: global_mmlu_full_si_stem_tasks +task: global_mmlu_full_si_high_school_chemistry diff --git a/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_high_school_computer_science.yaml b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_high_school_computer_science.yaml new file mode 100644 index 00000000..e80a1f2c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_high_school_computer_science.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _si_template_yaml +process_docs: !function utils.process_high_school_computer_science +tag: global_mmlu_full_si_stem_tasks +task: global_mmlu_full_si_high_school_computer_science diff --git a/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_high_school_european_history.yaml b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_high_school_european_history.yaml new file mode 100644 index 00000000..10e15738 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_high_school_european_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _si_template_yaml +process_docs: !function utils.process_high_school_european_history +tag: global_mmlu_full_si_humanities_tasks +task: global_mmlu_full_si_high_school_european_history diff --git a/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_high_school_geography.yaml b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_high_school_geography.yaml new file mode 100644 index 00000000..12d90b97 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_high_school_geography.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _si_template_yaml +process_docs: !function utils.process_high_school_geography +tag: global_mmlu_full_si_social_sciences_tasks +task: global_mmlu_full_si_high_school_geography diff --git a/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_high_school_government_and_politics.yaml b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_high_school_government_and_politics.yaml new file mode 100644 index 00000000..d285c2c6 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_high_school_government_and_politics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _si_template_yaml +process_docs: !function utils.process_high_school_government_and_politics +tag: global_mmlu_full_si_social_sciences_tasks +task: global_mmlu_full_si_high_school_government_and_politics diff --git a/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_high_school_macroeconomics.yaml b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_high_school_macroeconomics.yaml new file mode 100644 index 00000000..1c85f2df --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_high_school_macroeconomics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _si_template_yaml +process_docs: !function utils.process_high_school_macroeconomics +tag: global_mmlu_full_si_social_sciences_tasks +task: global_mmlu_full_si_high_school_macroeconomics diff --git a/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_high_school_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_high_school_mathematics.yaml new file mode 100644 index 00000000..b292fa50 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_high_school_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _si_template_yaml +process_docs: !function utils.process_high_school_mathematics +tag: global_mmlu_full_si_stem_tasks +task: global_mmlu_full_si_high_school_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_high_school_microeconomics.yaml b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_high_school_microeconomics.yaml new file mode 100644 index 00000000..ada74f5f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_high_school_microeconomics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _si_template_yaml +process_docs: !function utils.process_high_school_microeconomics +tag: global_mmlu_full_si_social_sciences_tasks +task: global_mmlu_full_si_high_school_microeconomics diff --git a/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_high_school_physics.yaml b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_high_school_physics.yaml new file mode 100644 index 00000000..84bbda28 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_high_school_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _si_template_yaml +process_docs: !function utils.process_high_school_physics +tag: global_mmlu_full_si_stem_tasks +task: global_mmlu_full_si_high_school_physics diff --git a/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_high_school_psychology.yaml b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_high_school_psychology.yaml new file mode 100644 index 00000000..7c378798 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_high_school_psychology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _si_template_yaml +process_docs: !function utils.process_high_school_psychology +tag: global_mmlu_full_si_social_sciences_tasks +task: global_mmlu_full_si_high_school_psychology diff --git a/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_high_school_statistics.yaml b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_high_school_statistics.yaml new file mode 100644 index 00000000..13758f22 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_high_school_statistics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _si_template_yaml +process_docs: !function utils.process_high_school_statistics +tag: global_mmlu_full_si_stem_tasks +task: global_mmlu_full_si_high_school_statistics diff --git a/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_high_school_us_history.yaml b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_high_school_us_history.yaml new file mode 100644 index 00000000..0fe85e14 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_high_school_us_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _si_template_yaml +process_docs: !function utils.process_high_school_us_history +tag: global_mmlu_full_si_humanities_tasks +task: global_mmlu_full_si_high_school_us_history diff --git a/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_high_school_world_history.yaml b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_high_school_world_history.yaml new file mode 100644 index 00000000..8afaa392 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_high_school_world_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _si_template_yaml +process_docs: !function utils.process_high_school_world_history +tag: global_mmlu_full_si_humanities_tasks +task: global_mmlu_full_si_high_school_world_history diff --git a/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_human_aging.yaml b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_human_aging.yaml new file mode 100644 index 00000000..2cf69a68 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_human_aging.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _si_template_yaml +process_docs: !function utils.process_human_aging +tag: global_mmlu_full_si_other_tasks +task: global_mmlu_full_si_human_aging diff --git a/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_human_sexuality.yaml b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_human_sexuality.yaml new file mode 100644 index 00000000..418927d5 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_human_sexuality.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _si_template_yaml +process_docs: !function utils.process_human_sexuality +tag: global_mmlu_full_si_social_sciences_tasks +task: global_mmlu_full_si_human_sexuality diff --git a/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_international_law.yaml b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_international_law.yaml new file mode 100644 index 00000000..de0a611d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_international_law.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _si_template_yaml +process_docs: !function utils.process_international_law +tag: global_mmlu_full_si_humanities_tasks +task: global_mmlu_full_si_international_law diff --git a/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_jurisprudence.yaml b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_jurisprudence.yaml new file mode 100644 index 00000000..10212173 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_jurisprudence.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _si_template_yaml +process_docs: !function utils.process_jurisprudence +tag: global_mmlu_full_si_humanities_tasks +task: global_mmlu_full_si_jurisprudence diff --git a/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_logical_fallacies.yaml b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_logical_fallacies.yaml new file mode 100644 index 00000000..d31372ad --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_logical_fallacies.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _si_template_yaml +process_docs: !function utils.process_logical_fallacies +tag: global_mmlu_full_si_humanities_tasks +task: global_mmlu_full_si_logical_fallacies diff --git a/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_machine_learning.yaml b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_machine_learning.yaml new file mode 100644 index 00000000..0e3d0e7c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_machine_learning.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _si_template_yaml +process_docs: !function utils.process_machine_learning +tag: global_mmlu_full_si_stem_tasks +task: global_mmlu_full_si_machine_learning diff --git a/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_management.yaml b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_management.yaml new file mode 100644 index 00000000..f4e29c9a --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_management.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _si_template_yaml +process_docs: !function utils.process_management +tag: global_mmlu_full_si_other_tasks +task: global_mmlu_full_si_management diff --git a/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_marketing.yaml b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_marketing.yaml new file mode 100644 index 00000000..8dff414a --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_marketing.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _si_template_yaml +process_docs: !function utils.process_marketing +tag: global_mmlu_full_si_other_tasks +task: global_mmlu_full_si_marketing diff --git a/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_medical_genetics.yaml b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_medical_genetics.yaml new file mode 100644 index 00000000..6160f02b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_medical_genetics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _si_template_yaml +process_docs: !function utils.process_medical_genetics +tag: global_mmlu_full_si_other_tasks +task: global_mmlu_full_si_medical_genetics diff --git a/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_miscellaneous.yaml b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_miscellaneous.yaml new file mode 100644 index 00000000..de1db6c9 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_miscellaneous.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _si_template_yaml +process_docs: !function utils.process_miscellaneous +tag: global_mmlu_full_si_other_tasks +task: global_mmlu_full_si_miscellaneous diff --git a/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_moral_disputes.yaml b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_moral_disputes.yaml new file mode 100644 index 00000000..d48cf75c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_moral_disputes.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _si_template_yaml +process_docs: !function utils.process_moral_disputes +tag: global_mmlu_full_si_humanities_tasks +task: global_mmlu_full_si_moral_disputes diff --git a/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_moral_scenarios.yaml b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_moral_scenarios.yaml new file mode 100644 index 00000000..5d08b811 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_moral_scenarios.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _si_template_yaml +process_docs: !function utils.process_moral_scenarios +tag: global_mmlu_full_si_humanities_tasks +task: global_mmlu_full_si_moral_scenarios diff --git a/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_nutrition.yaml b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_nutrition.yaml new file mode 100644 index 00000000..3163db49 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_nutrition.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _si_template_yaml +process_docs: !function utils.process_nutrition +tag: global_mmlu_full_si_other_tasks +task: global_mmlu_full_si_nutrition diff --git a/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_philosophy.yaml b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_philosophy.yaml new file mode 100644 index 00000000..f809bddd --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_philosophy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _si_template_yaml +process_docs: !function utils.process_philosophy +tag: global_mmlu_full_si_humanities_tasks +task: global_mmlu_full_si_philosophy diff --git a/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_prehistory.yaml b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_prehistory.yaml new file mode 100644 index 00000000..964e6ab7 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_prehistory.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _si_template_yaml +process_docs: !function utils.process_prehistory +tag: global_mmlu_full_si_humanities_tasks +task: global_mmlu_full_si_prehistory diff --git a/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_professional_accounting.yaml b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_professional_accounting.yaml new file mode 100644 index 00000000..c04e0bbc --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_professional_accounting.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _si_template_yaml +process_docs: !function utils.process_professional_accounting +tag: global_mmlu_full_si_other_tasks +task: global_mmlu_full_si_professional_accounting diff --git a/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_professional_law.yaml b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_professional_law.yaml new file mode 100644 index 00000000..6542f14e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_professional_law.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _si_template_yaml +process_docs: !function utils.process_professional_law +tag: global_mmlu_full_si_humanities_tasks +task: global_mmlu_full_si_professional_law diff --git a/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_professional_medicine.yaml b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_professional_medicine.yaml new file mode 100644 index 00000000..38448979 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_professional_medicine.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _si_template_yaml +process_docs: !function utils.process_professional_medicine +tag: global_mmlu_full_si_other_tasks +task: global_mmlu_full_si_professional_medicine diff --git a/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_professional_psychology.yaml b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_professional_psychology.yaml new file mode 100644 index 00000000..80f36885 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_professional_psychology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _si_template_yaml +process_docs: !function utils.process_professional_psychology +tag: global_mmlu_full_si_social_sciences_tasks +task: global_mmlu_full_si_professional_psychology diff --git a/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_public_relations.yaml b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_public_relations.yaml new file mode 100644 index 00000000..2ac5169e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_public_relations.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _si_template_yaml +process_docs: !function utils.process_public_relations +tag: global_mmlu_full_si_social_sciences_tasks +task: global_mmlu_full_si_public_relations diff --git a/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_security_studies.yaml b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_security_studies.yaml new file mode 100644 index 00000000..21423506 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_security_studies.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _si_template_yaml +process_docs: !function utils.process_security_studies +tag: global_mmlu_full_si_social_sciences_tasks +task: global_mmlu_full_si_security_studies diff --git a/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_sociology.yaml b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_sociology.yaml new file mode 100644 index 00000000..c86ee0a3 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_sociology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _si_template_yaml +process_docs: !function utils.process_sociology +tag: global_mmlu_full_si_social_sciences_tasks +task: global_mmlu_full_si_sociology diff --git a/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_us_foreign_policy.yaml b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_us_foreign_policy.yaml new file mode 100644 index 00000000..28c238e6 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_us_foreign_policy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _si_template_yaml +process_docs: !function utils.process_us_foreign_policy +tag: global_mmlu_full_si_social_sciences_tasks +task: global_mmlu_full_si_us_foreign_policy diff --git a/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_virology.yaml b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_virology.yaml new file mode 100644 index 00000000..a1935460 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_virology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _si_template_yaml +process_docs: !function utils.process_virology +tag: global_mmlu_full_si_other_tasks +task: global_mmlu_full_si_virology diff --git a/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_world_religions.yaml b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_world_religions.yaml new file mode 100644 index 00000000..424c23c2 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/si/global_mmlu_full_si_world_religions.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _si_template_yaml +process_docs: !function utils.process_world_religions +tag: global_mmlu_full_si_humanities_tasks +task: global_mmlu_full_si_world_religions diff --git a/lm_eval/tasks/global_mmlu/full/si/utils.py b/lm_eval/tasks/global_mmlu/full/si/utils.py new file mode 100644 index 00000000..7df72cb0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/si/utils.py @@ -0,0 +1,73 @@ +from functools import partial + + +SUBJECTS = [ + "abstract_algebra", + "anatomy", + "astronomy", + "business_ethics", + "clinical_knowledge", + "college_biology", + "college_chemistry", + "college_computer_science", + "college_mathematics", + "college_medicine", + "college_physics", + "computer_security", + "conceptual_physics", + "econometrics", + "electrical_engineering", + "elementary_mathematics", + "formal_logic", + "global_facts", + "high_school_biology", + "high_school_chemistry", + "high_school_computer_science", + "high_school_european_history", + "high_school_geography", + "high_school_government_and_politics", + "high_school_macroeconomics", + "high_school_mathematics", + "high_school_microeconomics", + "high_school_physics", + "high_school_psychology", + "high_school_statistics", + "high_school_us_history", + "high_school_world_history", + "human_aging", + "human_sexuality", + "international_law", + "jurisprudence", + "logical_fallacies", + "machine_learning", + "management", + "marketing", + "medical_genetics", + "miscellaneous", + "moral_disputes", + "moral_scenarios", + "nutrition", + "philosophy", + "prehistory", + "professional_accounting", + "professional_law", + "professional_medicine", + "professional_psychology", + "public_relations", + "security_studies", + "sociology", + "us_foreign_policy", + "virology", + "world_religions", +] + + +def process_docs(dataset, subject): + return dataset.filter(lambda x: x["subject"] == subject) + + +process_functions = { + f"process_{subject}": partial(process_docs, subject=subject) for subject in SUBJECTS +} + +globals().update(process_functions) diff --git a/lm_eval/tasks/global_mmlu/full/sn/_global_mmlu_full_sn.yaml b/lm_eval/tasks/global_mmlu/full/sn/_global_mmlu_full_sn.yaml new file mode 100644 index 00000000..98ced987 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sn/_global_mmlu_full_sn.yaml @@ -0,0 +1,11 @@ +group: global_mmlu_full_sn +task: + - global_mmlu_full_sn_stem + - global_mmlu_full_sn_other + - global_mmlu_full_sn_social_sciences + - global_mmlu_full_sn_humanities +aggregate_metric_list: + - metric: acc + weight_by_size: True +metadata: + version: 1.0 diff --git a/lm_eval/tasks/global_mmlu/full/sn/_global_mmlu_full_sn_humanities.yaml b/lm_eval/tasks/global_mmlu/full/sn/_global_mmlu_full_sn_humanities.yaml new file mode 100644 index 00000000..69690862 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sn/_global_mmlu_full_sn_humanities.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_sn_humanities +task: + - global_mmlu_full_sn_humanities_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/sn/_global_mmlu_full_sn_other.yaml b/lm_eval/tasks/global_mmlu/full/sn/_global_mmlu_full_sn_other.yaml new file mode 100644 index 00000000..18e750b6 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sn/_global_mmlu_full_sn_other.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_sn_other +task: + - global_mmlu_full_sn_other_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/sn/_global_mmlu_full_sn_social_sciences.yaml b/lm_eval/tasks/global_mmlu/full/sn/_global_mmlu_full_sn_social_sciences.yaml new file mode 100644 index 00000000..a8e76215 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sn/_global_mmlu_full_sn_social_sciences.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_sn_social_sciences +task: + - global_mmlu_full_sn_social_sciences_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/sn/_global_mmlu_full_sn_stem.yaml b/lm_eval/tasks/global_mmlu/full/sn/_global_mmlu_full_sn_stem.yaml new file mode 100644 index 00000000..b3136233 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sn/_global_mmlu_full_sn_stem.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_sn_stem +task: + - global_mmlu_full_sn_stem_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/sn/_sn_template_yaml b/lm_eval/tasks/global_mmlu/full/sn/_sn_template_yaml new file mode 100644 index 00000000..30d50ba0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sn/_sn_template_yaml @@ -0,0 +1,16 @@ +dataset_path: CohereForAI/Global-MMLU +dataset_name: sn +test_split: test +fewshot_split: dev +fewshot_config: + sampler: first_n +output_type: multiple_choice +doc_to_text: "{{question.strip()}}\nA. {{option_a}}\nB. {{option_b}}\nC. {{option_c}}\nD. {{option_d}}\nAnswer:" +doc_to_choice: ["A", "B", "C", "D"] +doc_to_target: answer +metric_list: + - metric: acc + aggregation: mean + higher_is_better: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_abstract_algebra.yaml b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_abstract_algebra.yaml new file mode 100644 index 00000000..c4de495e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_abstract_algebra.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sn_template_yaml +process_docs: !function utils.process_abstract_algebra +tag: global_mmlu_full_sn_stem_tasks +task: global_mmlu_full_sn_abstract_algebra diff --git a/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_anatomy.yaml b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_anatomy.yaml new file mode 100644 index 00000000..1ef227aa --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_anatomy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sn_template_yaml +process_docs: !function utils.process_anatomy +tag: global_mmlu_full_sn_stem_tasks +task: global_mmlu_full_sn_anatomy diff --git a/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_astronomy.yaml b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_astronomy.yaml new file mode 100644 index 00000000..8662ab96 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_astronomy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sn_template_yaml +process_docs: !function utils.process_astronomy +tag: global_mmlu_full_sn_stem_tasks +task: global_mmlu_full_sn_astronomy diff --git a/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_business_ethics.yaml b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_business_ethics.yaml new file mode 100644 index 00000000..6f4741c0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_business_ethics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sn_template_yaml +process_docs: !function utils.process_business_ethics +tag: global_mmlu_full_sn_other_tasks +task: global_mmlu_full_sn_business_ethics diff --git a/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_clinical_knowledge.yaml b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_clinical_knowledge.yaml new file mode 100644 index 00000000..7477170e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_clinical_knowledge.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sn_template_yaml +process_docs: !function utils.process_clinical_knowledge +tag: global_mmlu_full_sn_other_tasks +task: global_mmlu_full_sn_clinical_knowledge diff --git a/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_college_biology.yaml b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_college_biology.yaml new file mode 100644 index 00000000..6d0ec277 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_college_biology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sn_template_yaml +process_docs: !function utils.process_college_biology +tag: global_mmlu_full_sn_stem_tasks +task: global_mmlu_full_sn_college_biology diff --git a/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_college_chemistry.yaml b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_college_chemistry.yaml new file mode 100644 index 00000000..9f0c4f42 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_college_chemistry.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sn_template_yaml +process_docs: !function utils.process_college_chemistry +tag: global_mmlu_full_sn_stem_tasks +task: global_mmlu_full_sn_college_chemistry diff --git a/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_college_computer_science.yaml b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_college_computer_science.yaml new file mode 100644 index 00000000..c8651ee1 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_college_computer_science.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sn_template_yaml +process_docs: !function utils.process_college_computer_science +tag: global_mmlu_full_sn_stem_tasks +task: global_mmlu_full_sn_college_computer_science diff --git a/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_college_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_college_mathematics.yaml new file mode 100644 index 00000000..c1d1a98e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_college_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sn_template_yaml +process_docs: !function utils.process_college_mathematics +tag: global_mmlu_full_sn_stem_tasks +task: global_mmlu_full_sn_college_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_college_medicine.yaml b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_college_medicine.yaml new file mode 100644 index 00000000..d9ce08f3 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_college_medicine.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sn_template_yaml +process_docs: !function utils.process_college_medicine +tag: global_mmlu_full_sn_other_tasks +task: global_mmlu_full_sn_college_medicine diff --git a/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_college_physics.yaml b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_college_physics.yaml new file mode 100644 index 00000000..ae34a82a --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_college_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sn_template_yaml +process_docs: !function utils.process_college_physics +tag: global_mmlu_full_sn_stem_tasks +task: global_mmlu_full_sn_college_physics diff --git a/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_computer_security.yaml b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_computer_security.yaml new file mode 100644 index 00000000..4b41c175 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_computer_security.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sn_template_yaml +process_docs: !function utils.process_computer_security +tag: global_mmlu_full_sn_stem_tasks +task: global_mmlu_full_sn_computer_security diff --git a/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_conceptual_physics.yaml b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_conceptual_physics.yaml new file mode 100644 index 00000000..5aaa8a78 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_conceptual_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sn_template_yaml +process_docs: !function utils.process_conceptual_physics +tag: global_mmlu_full_sn_stem_tasks +task: global_mmlu_full_sn_conceptual_physics diff --git a/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_econometrics.yaml b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_econometrics.yaml new file mode 100644 index 00000000..8606e96c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_econometrics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sn_template_yaml +process_docs: !function utils.process_econometrics +tag: global_mmlu_full_sn_social_sciences_tasks +task: global_mmlu_full_sn_econometrics diff --git a/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_electrical_engineering.yaml b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_electrical_engineering.yaml new file mode 100644 index 00000000..9c57f703 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_electrical_engineering.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sn_template_yaml +process_docs: !function utils.process_electrical_engineering +tag: global_mmlu_full_sn_stem_tasks +task: global_mmlu_full_sn_electrical_engineering diff --git a/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_elementary_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_elementary_mathematics.yaml new file mode 100644 index 00000000..0ed5b400 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_elementary_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sn_template_yaml +process_docs: !function utils.process_elementary_mathematics +tag: global_mmlu_full_sn_stem_tasks +task: global_mmlu_full_sn_elementary_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_formal_logic.yaml b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_formal_logic.yaml new file mode 100644 index 00000000..55dafc2b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_formal_logic.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sn_template_yaml +process_docs: !function utils.process_formal_logic +tag: global_mmlu_full_sn_humanities_tasks +task: global_mmlu_full_sn_formal_logic diff --git a/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_global_facts.yaml b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_global_facts.yaml new file mode 100644 index 00000000..5b8ee96f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_global_facts.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sn_template_yaml +process_docs: !function utils.process_global_facts +tag: global_mmlu_full_sn_other_tasks +task: global_mmlu_full_sn_global_facts diff --git a/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_high_school_biology.yaml b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_high_school_biology.yaml new file mode 100644 index 00000000..2597a7d7 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_high_school_biology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sn_template_yaml +process_docs: !function utils.process_high_school_biology +tag: global_mmlu_full_sn_stem_tasks +task: global_mmlu_full_sn_high_school_biology diff --git a/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_high_school_chemistry.yaml b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_high_school_chemistry.yaml new file mode 100644 index 00000000..1e6be4e6 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_high_school_chemistry.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sn_template_yaml +process_docs: !function utils.process_high_school_chemistry +tag: global_mmlu_full_sn_stem_tasks +task: global_mmlu_full_sn_high_school_chemistry diff --git a/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_high_school_computer_science.yaml b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_high_school_computer_science.yaml new file mode 100644 index 00000000..446da912 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_high_school_computer_science.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sn_template_yaml +process_docs: !function utils.process_high_school_computer_science +tag: global_mmlu_full_sn_stem_tasks +task: global_mmlu_full_sn_high_school_computer_science diff --git a/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_high_school_european_history.yaml b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_high_school_european_history.yaml new file mode 100644 index 00000000..dd8cf61c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_high_school_european_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sn_template_yaml +process_docs: !function utils.process_high_school_european_history +tag: global_mmlu_full_sn_humanities_tasks +task: global_mmlu_full_sn_high_school_european_history diff --git a/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_high_school_geography.yaml b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_high_school_geography.yaml new file mode 100644 index 00000000..2e178adf --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_high_school_geography.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sn_template_yaml +process_docs: !function utils.process_high_school_geography +tag: global_mmlu_full_sn_social_sciences_tasks +task: global_mmlu_full_sn_high_school_geography diff --git a/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_high_school_government_and_politics.yaml b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_high_school_government_and_politics.yaml new file mode 100644 index 00000000..1ac4efda --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_high_school_government_and_politics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sn_template_yaml +process_docs: !function utils.process_high_school_government_and_politics +tag: global_mmlu_full_sn_social_sciences_tasks +task: global_mmlu_full_sn_high_school_government_and_politics diff --git a/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_high_school_macroeconomics.yaml b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_high_school_macroeconomics.yaml new file mode 100644 index 00000000..23ca0b41 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_high_school_macroeconomics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sn_template_yaml +process_docs: !function utils.process_high_school_macroeconomics +tag: global_mmlu_full_sn_social_sciences_tasks +task: global_mmlu_full_sn_high_school_macroeconomics diff --git a/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_high_school_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_high_school_mathematics.yaml new file mode 100644 index 00000000..0bd9be19 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_high_school_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sn_template_yaml +process_docs: !function utils.process_high_school_mathematics +tag: global_mmlu_full_sn_stem_tasks +task: global_mmlu_full_sn_high_school_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_high_school_microeconomics.yaml b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_high_school_microeconomics.yaml new file mode 100644 index 00000000..916e14ca --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_high_school_microeconomics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sn_template_yaml +process_docs: !function utils.process_high_school_microeconomics +tag: global_mmlu_full_sn_social_sciences_tasks +task: global_mmlu_full_sn_high_school_microeconomics diff --git a/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_high_school_physics.yaml b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_high_school_physics.yaml new file mode 100644 index 00000000..b6a3e60c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_high_school_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sn_template_yaml +process_docs: !function utils.process_high_school_physics +tag: global_mmlu_full_sn_stem_tasks +task: global_mmlu_full_sn_high_school_physics diff --git a/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_high_school_psychology.yaml b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_high_school_psychology.yaml new file mode 100644 index 00000000..62a197c0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_high_school_psychology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sn_template_yaml +process_docs: !function utils.process_high_school_psychology +tag: global_mmlu_full_sn_social_sciences_tasks +task: global_mmlu_full_sn_high_school_psychology diff --git a/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_high_school_statistics.yaml b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_high_school_statistics.yaml new file mode 100644 index 00000000..815cb60b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_high_school_statistics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sn_template_yaml +process_docs: !function utils.process_high_school_statistics +tag: global_mmlu_full_sn_stem_tasks +task: global_mmlu_full_sn_high_school_statistics diff --git a/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_high_school_us_history.yaml b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_high_school_us_history.yaml new file mode 100644 index 00000000..ff9f970e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_high_school_us_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sn_template_yaml +process_docs: !function utils.process_high_school_us_history +tag: global_mmlu_full_sn_humanities_tasks +task: global_mmlu_full_sn_high_school_us_history diff --git a/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_high_school_world_history.yaml b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_high_school_world_history.yaml new file mode 100644 index 00000000..b2dedc38 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_high_school_world_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sn_template_yaml +process_docs: !function utils.process_high_school_world_history +tag: global_mmlu_full_sn_humanities_tasks +task: global_mmlu_full_sn_high_school_world_history diff --git a/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_human_aging.yaml b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_human_aging.yaml new file mode 100644 index 00000000..0ef13930 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_human_aging.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sn_template_yaml +process_docs: !function utils.process_human_aging +tag: global_mmlu_full_sn_other_tasks +task: global_mmlu_full_sn_human_aging diff --git a/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_human_sexuality.yaml b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_human_sexuality.yaml new file mode 100644 index 00000000..a52c2ded --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_human_sexuality.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sn_template_yaml +process_docs: !function utils.process_human_sexuality +tag: global_mmlu_full_sn_social_sciences_tasks +task: global_mmlu_full_sn_human_sexuality diff --git a/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_international_law.yaml b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_international_law.yaml new file mode 100644 index 00000000..648c3dea --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_international_law.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sn_template_yaml +process_docs: !function utils.process_international_law +tag: global_mmlu_full_sn_humanities_tasks +task: global_mmlu_full_sn_international_law diff --git a/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_jurisprudence.yaml b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_jurisprudence.yaml new file mode 100644 index 00000000..ca63c411 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_jurisprudence.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sn_template_yaml +process_docs: !function utils.process_jurisprudence +tag: global_mmlu_full_sn_humanities_tasks +task: global_mmlu_full_sn_jurisprudence diff --git a/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_logical_fallacies.yaml b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_logical_fallacies.yaml new file mode 100644 index 00000000..d74a7f18 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_logical_fallacies.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sn_template_yaml +process_docs: !function utils.process_logical_fallacies +tag: global_mmlu_full_sn_humanities_tasks +task: global_mmlu_full_sn_logical_fallacies diff --git a/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_machine_learning.yaml b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_machine_learning.yaml new file mode 100644 index 00000000..db272b3b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_machine_learning.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sn_template_yaml +process_docs: !function utils.process_machine_learning +tag: global_mmlu_full_sn_stem_tasks +task: global_mmlu_full_sn_machine_learning diff --git a/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_management.yaml b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_management.yaml new file mode 100644 index 00000000..db3bee4d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_management.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sn_template_yaml +process_docs: !function utils.process_management +tag: global_mmlu_full_sn_other_tasks +task: global_mmlu_full_sn_management diff --git a/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_marketing.yaml b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_marketing.yaml new file mode 100644 index 00000000..a700c4e7 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_marketing.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sn_template_yaml +process_docs: !function utils.process_marketing +tag: global_mmlu_full_sn_other_tasks +task: global_mmlu_full_sn_marketing diff --git a/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_medical_genetics.yaml b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_medical_genetics.yaml new file mode 100644 index 00000000..b826b187 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_medical_genetics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sn_template_yaml +process_docs: !function utils.process_medical_genetics +tag: global_mmlu_full_sn_other_tasks +task: global_mmlu_full_sn_medical_genetics diff --git a/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_miscellaneous.yaml b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_miscellaneous.yaml new file mode 100644 index 00000000..dea895aa --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_miscellaneous.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sn_template_yaml +process_docs: !function utils.process_miscellaneous +tag: global_mmlu_full_sn_other_tasks +task: global_mmlu_full_sn_miscellaneous diff --git a/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_moral_disputes.yaml b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_moral_disputes.yaml new file mode 100644 index 00000000..b641f6b2 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_moral_disputes.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sn_template_yaml +process_docs: !function utils.process_moral_disputes +tag: global_mmlu_full_sn_humanities_tasks +task: global_mmlu_full_sn_moral_disputes diff --git a/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_moral_scenarios.yaml b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_moral_scenarios.yaml new file mode 100644 index 00000000..2951a953 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_moral_scenarios.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sn_template_yaml +process_docs: !function utils.process_moral_scenarios +tag: global_mmlu_full_sn_humanities_tasks +task: global_mmlu_full_sn_moral_scenarios diff --git a/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_nutrition.yaml b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_nutrition.yaml new file mode 100644 index 00000000..9816d8b4 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_nutrition.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sn_template_yaml +process_docs: !function utils.process_nutrition +tag: global_mmlu_full_sn_other_tasks +task: global_mmlu_full_sn_nutrition diff --git a/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_philosophy.yaml b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_philosophy.yaml new file mode 100644 index 00000000..4ea10505 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_philosophy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sn_template_yaml +process_docs: !function utils.process_philosophy +tag: global_mmlu_full_sn_humanities_tasks +task: global_mmlu_full_sn_philosophy diff --git a/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_prehistory.yaml b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_prehistory.yaml new file mode 100644 index 00000000..e941437b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_prehistory.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sn_template_yaml +process_docs: !function utils.process_prehistory +tag: global_mmlu_full_sn_humanities_tasks +task: global_mmlu_full_sn_prehistory diff --git a/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_professional_accounting.yaml b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_professional_accounting.yaml new file mode 100644 index 00000000..057a197d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_professional_accounting.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sn_template_yaml +process_docs: !function utils.process_professional_accounting +tag: global_mmlu_full_sn_other_tasks +task: global_mmlu_full_sn_professional_accounting diff --git a/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_professional_law.yaml b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_professional_law.yaml new file mode 100644 index 00000000..72c9fac7 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_professional_law.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sn_template_yaml +process_docs: !function utils.process_professional_law +tag: global_mmlu_full_sn_humanities_tasks +task: global_mmlu_full_sn_professional_law diff --git a/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_professional_medicine.yaml b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_professional_medicine.yaml new file mode 100644 index 00000000..e727b3cd --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_professional_medicine.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sn_template_yaml +process_docs: !function utils.process_professional_medicine +tag: global_mmlu_full_sn_other_tasks +task: global_mmlu_full_sn_professional_medicine diff --git a/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_professional_psychology.yaml b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_professional_psychology.yaml new file mode 100644 index 00000000..341322d2 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_professional_psychology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sn_template_yaml +process_docs: !function utils.process_professional_psychology +tag: global_mmlu_full_sn_social_sciences_tasks +task: global_mmlu_full_sn_professional_psychology diff --git a/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_public_relations.yaml b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_public_relations.yaml new file mode 100644 index 00000000..5448baa4 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_public_relations.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sn_template_yaml +process_docs: !function utils.process_public_relations +tag: global_mmlu_full_sn_social_sciences_tasks +task: global_mmlu_full_sn_public_relations diff --git a/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_security_studies.yaml b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_security_studies.yaml new file mode 100644 index 00000000..542c709a --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_security_studies.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sn_template_yaml +process_docs: !function utils.process_security_studies +tag: global_mmlu_full_sn_social_sciences_tasks +task: global_mmlu_full_sn_security_studies diff --git a/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_sociology.yaml b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_sociology.yaml new file mode 100644 index 00000000..f2913db5 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_sociology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sn_template_yaml +process_docs: !function utils.process_sociology +tag: global_mmlu_full_sn_social_sciences_tasks +task: global_mmlu_full_sn_sociology diff --git a/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_us_foreign_policy.yaml b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_us_foreign_policy.yaml new file mode 100644 index 00000000..ad476847 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_us_foreign_policy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sn_template_yaml +process_docs: !function utils.process_us_foreign_policy +tag: global_mmlu_full_sn_social_sciences_tasks +task: global_mmlu_full_sn_us_foreign_policy diff --git a/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_virology.yaml b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_virology.yaml new file mode 100644 index 00000000..254fedb4 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_virology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sn_template_yaml +process_docs: !function utils.process_virology +tag: global_mmlu_full_sn_other_tasks +task: global_mmlu_full_sn_virology diff --git a/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_world_religions.yaml b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_world_religions.yaml new file mode 100644 index 00000000..2aef6dfd --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sn/global_mmlu_full_sn_world_religions.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sn_template_yaml +process_docs: !function utils.process_world_religions +tag: global_mmlu_full_sn_humanities_tasks +task: global_mmlu_full_sn_world_religions diff --git a/lm_eval/tasks/global_mmlu/full/sn/utils.py b/lm_eval/tasks/global_mmlu/full/sn/utils.py new file mode 100644 index 00000000..7df72cb0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sn/utils.py @@ -0,0 +1,73 @@ +from functools import partial + + +SUBJECTS = [ + "abstract_algebra", + "anatomy", + "astronomy", + "business_ethics", + "clinical_knowledge", + "college_biology", + "college_chemistry", + "college_computer_science", + "college_mathematics", + "college_medicine", + "college_physics", + "computer_security", + "conceptual_physics", + "econometrics", + "electrical_engineering", + "elementary_mathematics", + "formal_logic", + "global_facts", + "high_school_biology", + "high_school_chemistry", + "high_school_computer_science", + "high_school_european_history", + "high_school_geography", + "high_school_government_and_politics", + "high_school_macroeconomics", + "high_school_mathematics", + "high_school_microeconomics", + "high_school_physics", + "high_school_psychology", + "high_school_statistics", + "high_school_us_history", + "high_school_world_history", + "human_aging", + "human_sexuality", + "international_law", + "jurisprudence", + "logical_fallacies", + "machine_learning", + "management", + "marketing", + "medical_genetics", + "miscellaneous", + "moral_disputes", + "moral_scenarios", + "nutrition", + "philosophy", + "prehistory", + "professional_accounting", + "professional_law", + "professional_medicine", + "professional_psychology", + "public_relations", + "security_studies", + "sociology", + "us_foreign_policy", + "virology", + "world_religions", +] + + +def process_docs(dataset, subject): + return dataset.filter(lambda x: x["subject"] == subject) + + +process_functions = { + f"process_{subject}": partial(process_docs, subject=subject) for subject in SUBJECTS +} + +globals().update(process_functions) diff --git a/lm_eval/tasks/global_mmlu/full/so/_global_mmlu_full_so.yaml b/lm_eval/tasks/global_mmlu/full/so/_global_mmlu_full_so.yaml new file mode 100644 index 00000000..014a4121 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/so/_global_mmlu_full_so.yaml @@ -0,0 +1,11 @@ +group: global_mmlu_full_so +task: + - global_mmlu_full_so_stem + - global_mmlu_full_so_other + - global_mmlu_full_so_social_sciences + - global_mmlu_full_so_humanities +aggregate_metric_list: + - metric: acc + weight_by_size: True +metadata: + version: 1.0 diff --git a/lm_eval/tasks/global_mmlu/full/so/_global_mmlu_full_so_humanities.yaml b/lm_eval/tasks/global_mmlu/full/so/_global_mmlu_full_so_humanities.yaml new file mode 100644 index 00000000..ff78bfab --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/so/_global_mmlu_full_so_humanities.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_so_humanities +task: + - global_mmlu_full_so_humanities_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/so/_global_mmlu_full_so_other.yaml b/lm_eval/tasks/global_mmlu/full/so/_global_mmlu_full_so_other.yaml new file mode 100644 index 00000000..eec8e661 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/so/_global_mmlu_full_so_other.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_so_other +task: + - global_mmlu_full_so_other_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/so/_global_mmlu_full_so_social_sciences.yaml b/lm_eval/tasks/global_mmlu/full/so/_global_mmlu_full_so_social_sciences.yaml new file mode 100644 index 00000000..9d00ea1f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/so/_global_mmlu_full_so_social_sciences.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_so_social_sciences +task: + - global_mmlu_full_so_social_sciences_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/so/_global_mmlu_full_so_stem.yaml b/lm_eval/tasks/global_mmlu/full/so/_global_mmlu_full_so_stem.yaml new file mode 100644 index 00000000..497b9b01 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/so/_global_mmlu_full_so_stem.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_so_stem +task: + - global_mmlu_full_so_stem_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/so/_so_template_yaml b/lm_eval/tasks/global_mmlu/full/so/_so_template_yaml new file mode 100644 index 00000000..fb052a63 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/so/_so_template_yaml @@ -0,0 +1,16 @@ +dataset_path: CohereForAI/Global-MMLU +dataset_name: so +test_split: test +fewshot_split: dev +fewshot_config: + sampler: first_n +output_type: multiple_choice +doc_to_text: "{{question.strip()}}\nA. {{option_a}}\nB. {{option_b}}\nC. {{option_c}}\nD. {{option_d}}\nAnswer:" +doc_to_choice: ["A", "B", "C", "D"] +doc_to_target: answer +metric_list: + - metric: acc + aggregation: mean + higher_is_better: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_abstract_algebra.yaml b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_abstract_algebra.yaml new file mode 100644 index 00000000..afb5d908 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_abstract_algebra.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _so_template_yaml +process_docs: !function utils.process_abstract_algebra +tag: global_mmlu_full_so_stem_tasks +task: global_mmlu_full_so_abstract_algebra diff --git a/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_anatomy.yaml b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_anatomy.yaml new file mode 100644 index 00000000..79f3446d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_anatomy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _so_template_yaml +process_docs: !function utils.process_anatomy +tag: global_mmlu_full_so_stem_tasks +task: global_mmlu_full_so_anatomy diff --git a/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_astronomy.yaml b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_astronomy.yaml new file mode 100644 index 00000000..54a2faa0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_astronomy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _so_template_yaml +process_docs: !function utils.process_astronomy +tag: global_mmlu_full_so_stem_tasks +task: global_mmlu_full_so_astronomy diff --git a/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_business_ethics.yaml b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_business_ethics.yaml new file mode 100644 index 00000000..65bc598c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_business_ethics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _so_template_yaml +process_docs: !function utils.process_business_ethics +tag: global_mmlu_full_so_other_tasks +task: global_mmlu_full_so_business_ethics diff --git a/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_clinical_knowledge.yaml b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_clinical_knowledge.yaml new file mode 100644 index 00000000..224aa39b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_clinical_knowledge.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _so_template_yaml +process_docs: !function utils.process_clinical_knowledge +tag: global_mmlu_full_so_other_tasks +task: global_mmlu_full_so_clinical_knowledge diff --git a/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_college_biology.yaml b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_college_biology.yaml new file mode 100644 index 00000000..758d22c3 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_college_biology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _so_template_yaml +process_docs: !function utils.process_college_biology +tag: global_mmlu_full_so_stem_tasks +task: global_mmlu_full_so_college_biology diff --git a/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_college_chemistry.yaml b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_college_chemistry.yaml new file mode 100644 index 00000000..35c22430 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_college_chemistry.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _so_template_yaml +process_docs: !function utils.process_college_chemistry +tag: global_mmlu_full_so_stem_tasks +task: global_mmlu_full_so_college_chemistry diff --git a/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_college_computer_science.yaml b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_college_computer_science.yaml new file mode 100644 index 00000000..86428ae8 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_college_computer_science.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _so_template_yaml +process_docs: !function utils.process_college_computer_science +tag: global_mmlu_full_so_stem_tasks +task: global_mmlu_full_so_college_computer_science diff --git a/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_college_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_college_mathematics.yaml new file mode 100644 index 00000000..f9957a23 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_college_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _so_template_yaml +process_docs: !function utils.process_college_mathematics +tag: global_mmlu_full_so_stem_tasks +task: global_mmlu_full_so_college_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_college_medicine.yaml b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_college_medicine.yaml new file mode 100644 index 00000000..f51a1b12 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_college_medicine.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _so_template_yaml +process_docs: !function utils.process_college_medicine +tag: global_mmlu_full_so_other_tasks +task: global_mmlu_full_so_college_medicine diff --git a/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_college_physics.yaml b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_college_physics.yaml new file mode 100644 index 00000000..43388d6c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_college_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _so_template_yaml +process_docs: !function utils.process_college_physics +tag: global_mmlu_full_so_stem_tasks +task: global_mmlu_full_so_college_physics diff --git a/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_computer_security.yaml b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_computer_security.yaml new file mode 100644 index 00000000..8a556330 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_computer_security.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _so_template_yaml +process_docs: !function utils.process_computer_security +tag: global_mmlu_full_so_stem_tasks +task: global_mmlu_full_so_computer_security diff --git a/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_conceptual_physics.yaml b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_conceptual_physics.yaml new file mode 100644 index 00000000..97dfa147 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_conceptual_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _so_template_yaml +process_docs: !function utils.process_conceptual_physics +tag: global_mmlu_full_so_stem_tasks +task: global_mmlu_full_so_conceptual_physics diff --git a/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_econometrics.yaml b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_econometrics.yaml new file mode 100644 index 00000000..9792659f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_econometrics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _so_template_yaml +process_docs: !function utils.process_econometrics +tag: global_mmlu_full_so_social_sciences_tasks +task: global_mmlu_full_so_econometrics diff --git a/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_electrical_engineering.yaml b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_electrical_engineering.yaml new file mode 100644 index 00000000..3ed44e41 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_electrical_engineering.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _so_template_yaml +process_docs: !function utils.process_electrical_engineering +tag: global_mmlu_full_so_stem_tasks +task: global_mmlu_full_so_electrical_engineering diff --git a/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_elementary_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_elementary_mathematics.yaml new file mode 100644 index 00000000..76628481 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_elementary_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _so_template_yaml +process_docs: !function utils.process_elementary_mathematics +tag: global_mmlu_full_so_stem_tasks +task: global_mmlu_full_so_elementary_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_formal_logic.yaml b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_formal_logic.yaml new file mode 100644 index 00000000..4b7645c8 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_formal_logic.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _so_template_yaml +process_docs: !function utils.process_formal_logic +tag: global_mmlu_full_so_humanities_tasks +task: global_mmlu_full_so_formal_logic diff --git a/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_global_facts.yaml b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_global_facts.yaml new file mode 100644 index 00000000..fa75e666 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_global_facts.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _so_template_yaml +process_docs: !function utils.process_global_facts +tag: global_mmlu_full_so_other_tasks +task: global_mmlu_full_so_global_facts diff --git a/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_high_school_biology.yaml b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_high_school_biology.yaml new file mode 100644 index 00000000..d3ad29d4 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_high_school_biology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _so_template_yaml +process_docs: !function utils.process_high_school_biology +tag: global_mmlu_full_so_stem_tasks +task: global_mmlu_full_so_high_school_biology diff --git a/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_high_school_chemistry.yaml b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_high_school_chemistry.yaml new file mode 100644 index 00000000..274af23b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_high_school_chemistry.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _so_template_yaml +process_docs: !function utils.process_high_school_chemistry +tag: global_mmlu_full_so_stem_tasks +task: global_mmlu_full_so_high_school_chemistry diff --git a/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_high_school_computer_science.yaml b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_high_school_computer_science.yaml new file mode 100644 index 00000000..6bce30d6 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_high_school_computer_science.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _so_template_yaml +process_docs: !function utils.process_high_school_computer_science +tag: global_mmlu_full_so_stem_tasks +task: global_mmlu_full_so_high_school_computer_science diff --git a/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_high_school_european_history.yaml b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_high_school_european_history.yaml new file mode 100644 index 00000000..cfc44f08 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_high_school_european_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _so_template_yaml +process_docs: !function utils.process_high_school_european_history +tag: global_mmlu_full_so_humanities_tasks +task: global_mmlu_full_so_high_school_european_history diff --git a/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_high_school_geography.yaml b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_high_school_geography.yaml new file mode 100644 index 00000000..55479c39 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_high_school_geography.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _so_template_yaml +process_docs: !function utils.process_high_school_geography +tag: global_mmlu_full_so_social_sciences_tasks +task: global_mmlu_full_so_high_school_geography diff --git a/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_high_school_government_and_politics.yaml b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_high_school_government_and_politics.yaml new file mode 100644 index 00000000..ceb5a701 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_high_school_government_and_politics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _so_template_yaml +process_docs: !function utils.process_high_school_government_and_politics +tag: global_mmlu_full_so_social_sciences_tasks +task: global_mmlu_full_so_high_school_government_and_politics diff --git a/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_high_school_macroeconomics.yaml b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_high_school_macroeconomics.yaml new file mode 100644 index 00000000..0c403ec5 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_high_school_macroeconomics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _so_template_yaml +process_docs: !function utils.process_high_school_macroeconomics +tag: global_mmlu_full_so_social_sciences_tasks +task: global_mmlu_full_so_high_school_macroeconomics diff --git a/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_high_school_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_high_school_mathematics.yaml new file mode 100644 index 00000000..e8089bdf --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_high_school_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _so_template_yaml +process_docs: !function utils.process_high_school_mathematics +tag: global_mmlu_full_so_stem_tasks +task: global_mmlu_full_so_high_school_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_high_school_microeconomics.yaml b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_high_school_microeconomics.yaml new file mode 100644 index 00000000..32cacffe --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_high_school_microeconomics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _so_template_yaml +process_docs: !function utils.process_high_school_microeconomics +tag: global_mmlu_full_so_social_sciences_tasks +task: global_mmlu_full_so_high_school_microeconomics diff --git a/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_high_school_physics.yaml b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_high_school_physics.yaml new file mode 100644 index 00000000..fd2c35ac --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_high_school_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _so_template_yaml +process_docs: !function utils.process_high_school_physics +tag: global_mmlu_full_so_stem_tasks +task: global_mmlu_full_so_high_school_physics diff --git a/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_high_school_psychology.yaml b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_high_school_psychology.yaml new file mode 100644 index 00000000..26f2cb3c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_high_school_psychology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _so_template_yaml +process_docs: !function utils.process_high_school_psychology +tag: global_mmlu_full_so_social_sciences_tasks +task: global_mmlu_full_so_high_school_psychology diff --git a/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_high_school_statistics.yaml b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_high_school_statistics.yaml new file mode 100644 index 00000000..730075b1 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_high_school_statistics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _so_template_yaml +process_docs: !function utils.process_high_school_statistics +tag: global_mmlu_full_so_stem_tasks +task: global_mmlu_full_so_high_school_statistics diff --git a/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_high_school_us_history.yaml b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_high_school_us_history.yaml new file mode 100644 index 00000000..c9702a66 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_high_school_us_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _so_template_yaml +process_docs: !function utils.process_high_school_us_history +tag: global_mmlu_full_so_humanities_tasks +task: global_mmlu_full_so_high_school_us_history diff --git a/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_high_school_world_history.yaml b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_high_school_world_history.yaml new file mode 100644 index 00000000..78a21d5d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_high_school_world_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _so_template_yaml +process_docs: !function utils.process_high_school_world_history +tag: global_mmlu_full_so_humanities_tasks +task: global_mmlu_full_so_high_school_world_history diff --git a/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_human_aging.yaml b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_human_aging.yaml new file mode 100644 index 00000000..c95b5562 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_human_aging.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _so_template_yaml +process_docs: !function utils.process_human_aging +tag: global_mmlu_full_so_other_tasks +task: global_mmlu_full_so_human_aging diff --git a/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_human_sexuality.yaml b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_human_sexuality.yaml new file mode 100644 index 00000000..632778d3 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_human_sexuality.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _so_template_yaml +process_docs: !function utils.process_human_sexuality +tag: global_mmlu_full_so_social_sciences_tasks +task: global_mmlu_full_so_human_sexuality diff --git a/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_international_law.yaml b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_international_law.yaml new file mode 100644 index 00000000..2d5ab1c5 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_international_law.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _so_template_yaml +process_docs: !function utils.process_international_law +tag: global_mmlu_full_so_humanities_tasks +task: global_mmlu_full_so_international_law diff --git a/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_jurisprudence.yaml b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_jurisprudence.yaml new file mode 100644 index 00000000..1372a1d1 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_jurisprudence.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _so_template_yaml +process_docs: !function utils.process_jurisprudence +tag: global_mmlu_full_so_humanities_tasks +task: global_mmlu_full_so_jurisprudence diff --git a/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_logical_fallacies.yaml b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_logical_fallacies.yaml new file mode 100644 index 00000000..19a1120e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_logical_fallacies.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _so_template_yaml +process_docs: !function utils.process_logical_fallacies +tag: global_mmlu_full_so_humanities_tasks +task: global_mmlu_full_so_logical_fallacies diff --git a/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_machine_learning.yaml b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_machine_learning.yaml new file mode 100644 index 00000000..c1e13dda --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_machine_learning.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _so_template_yaml +process_docs: !function utils.process_machine_learning +tag: global_mmlu_full_so_stem_tasks +task: global_mmlu_full_so_machine_learning diff --git a/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_management.yaml b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_management.yaml new file mode 100644 index 00000000..6e325205 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_management.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _so_template_yaml +process_docs: !function utils.process_management +tag: global_mmlu_full_so_other_tasks +task: global_mmlu_full_so_management diff --git a/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_marketing.yaml b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_marketing.yaml new file mode 100644 index 00000000..8b1c002f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_marketing.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _so_template_yaml +process_docs: !function utils.process_marketing +tag: global_mmlu_full_so_other_tasks +task: global_mmlu_full_so_marketing diff --git a/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_medical_genetics.yaml b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_medical_genetics.yaml new file mode 100644 index 00000000..c0136dc6 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_medical_genetics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _so_template_yaml +process_docs: !function utils.process_medical_genetics +tag: global_mmlu_full_so_other_tasks +task: global_mmlu_full_so_medical_genetics diff --git a/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_miscellaneous.yaml b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_miscellaneous.yaml new file mode 100644 index 00000000..2b8a33ba --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_miscellaneous.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _so_template_yaml +process_docs: !function utils.process_miscellaneous +tag: global_mmlu_full_so_other_tasks +task: global_mmlu_full_so_miscellaneous diff --git a/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_moral_disputes.yaml b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_moral_disputes.yaml new file mode 100644 index 00000000..c1bd0011 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_moral_disputes.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _so_template_yaml +process_docs: !function utils.process_moral_disputes +tag: global_mmlu_full_so_humanities_tasks +task: global_mmlu_full_so_moral_disputes diff --git a/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_moral_scenarios.yaml b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_moral_scenarios.yaml new file mode 100644 index 00000000..60418a65 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_moral_scenarios.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _so_template_yaml +process_docs: !function utils.process_moral_scenarios +tag: global_mmlu_full_so_humanities_tasks +task: global_mmlu_full_so_moral_scenarios diff --git a/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_nutrition.yaml b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_nutrition.yaml new file mode 100644 index 00000000..5aa40241 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_nutrition.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _so_template_yaml +process_docs: !function utils.process_nutrition +tag: global_mmlu_full_so_other_tasks +task: global_mmlu_full_so_nutrition diff --git a/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_philosophy.yaml b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_philosophy.yaml new file mode 100644 index 00000000..421a9801 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_philosophy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _so_template_yaml +process_docs: !function utils.process_philosophy +tag: global_mmlu_full_so_humanities_tasks +task: global_mmlu_full_so_philosophy diff --git a/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_prehistory.yaml b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_prehistory.yaml new file mode 100644 index 00000000..721bfbf2 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_prehistory.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _so_template_yaml +process_docs: !function utils.process_prehistory +tag: global_mmlu_full_so_humanities_tasks +task: global_mmlu_full_so_prehistory diff --git a/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_professional_accounting.yaml b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_professional_accounting.yaml new file mode 100644 index 00000000..4ca0c5c9 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_professional_accounting.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _so_template_yaml +process_docs: !function utils.process_professional_accounting +tag: global_mmlu_full_so_other_tasks +task: global_mmlu_full_so_professional_accounting diff --git a/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_professional_law.yaml b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_professional_law.yaml new file mode 100644 index 00000000..7f57b594 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_professional_law.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _so_template_yaml +process_docs: !function utils.process_professional_law +tag: global_mmlu_full_so_humanities_tasks +task: global_mmlu_full_so_professional_law diff --git a/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_professional_medicine.yaml b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_professional_medicine.yaml new file mode 100644 index 00000000..a7d6408e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_professional_medicine.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _so_template_yaml +process_docs: !function utils.process_professional_medicine +tag: global_mmlu_full_so_other_tasks +task: global_mmlu_full_so_professional_medicine diff --git a/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_professional_psychology.yaml b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_professional_psychology.yaml new file mode 100644 index 00000000..a03de5bb --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_professional_psychology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _so_template_yaml +process_docs: !function utils.process_professional_psychology +tag: global_mmlu_full_so_social_sciences_tasks +task: global_mmlu_full_so_professional_psychology diff --git a/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_public_relations.yaml b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_public_relations.yaml new file mode 100644 index 00000000..f7af81e6 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_public_relations.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _so_template_yaml +process_docs: !function utils.process_public_relations +tag: global_mmlu_full_so_social_sciences_tasks +task: global_mmlu_full_so_public_relations diff --git a/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_security_studies.yaml b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_security_studies.yaml new file mode 100644 index 00000000..b52ee259 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_security_studies.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _so_template_yaml +process_docs: !function utils.process_security_studies +tag: global_mmlu_full_so_social_sciences_tasks +task: global_mmlu_full_so_security_studies diff --git a/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_sociology.yaml b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_sociology.yaml new file mode 100644 index 00000000..7f3847e6 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_sociology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _so_template_yaml +process_docs: !function utils.process_sociology +tag: global_mmlu_full_so_social_sciences_tasks +task: global_mmlu_full_so_sociology diff --git a/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_us_foreign_policy.yaml b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_us_foreign_policy.yaml new file mode 100644 index 00000000..a6017167 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_us_foreign_policy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _so_template_yaml +process_docs: !function utils.process_us_foreign_policy +tag: global_mmlu_full_so_social_sciences_tasks +task: global_mmlu_full_so_us_foreign_policy diff --git a/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_virology.yaml b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_virology.yaml new file mode 100644 index 00000000..2dc85b32 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_virology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _so_template_yaml +process_docs: !function utils.process_virology +tag: global_mmlu_full_so_other_tasks +task: global_mmlu_full_so_virology diff --git a/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_world_religions.yaml b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_world_religions.yaml new file mode 100644 index 00000000..9ca99e5b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/so/global_mmlu_full_so_world_religions.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _so_template_yaml +process_docs: !function utils.process_world_religions +tag: global_mmlu_full_so_humanities_tasks +task: global_mmlu_full_so_world_religions diff --git a/lm_eval/tasks/global_mmlu/full/so/utils.py b/lm_eval/tasks/global_mmlu/full/so/utils.py new file mode 100644 index 00000000..7df72cb0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/so/utils.py @@ -0,0 +1,73 @@ +from functools import partial + + +SUBJECTS = [ + "abstract_algebra", + "anatomy", + "astronomy", + "business_ethics", + "clinical_knowledge", + "college_biology", + "college_chemistry", + "college_computer_science", + "college_mathematics", + "college_medicine", + "college_physics", + "computer_security", + "conceptual_physics", + "econometrics", + "electrical_engineering", + "elementary_mathematics", + "formal_logic", + "global_facts", + "high_school_biology", + "high_school_chemistry", + "high_school_computer_science", + "high_school_european_history", + "high_school_geography", + "high_school_government_and_politics", + "high_school_macroeconomics", + "high_school_mathematics", + "high_school_microeconomics", + "high_school_physics", + "high_school_psychology", + "high_school_statistics", + "high_school_us_history", + "high_school_world_history", + "human_aging", + "human_sexuality", + "international_law", + "jurisprudence", + "logical_fallacies", + "machine_learning", + "management", + "marketing", + "medical_genetics", + "miscellaneous", + "moral_disputes", + "moral_scenarios", + "nutrition", + "philosophy", + "prehistory", + "professional_accounting", + "professional_law", + "professional_medicine", + "professional_psychology", + "public_relations", + "security_studies", + "sociology", + "us_foreign_policy", + "virology", + "world_religions", +] + + +def process_docs(dataset, subject): + return dataset.filter(lambda x: x["subject"] == subject) + + +process_functions = { + f"process_{subject}": partial(process_docs, subject=subject) for subject in SUBJECTS +} + +globals().update(process_functions) diff --git a/lm_eval/tasks/global_mmlu/full/sr/_global_mmlu_full_sr.yaml b/lm_eval/tasks/global_mmlu/full/sr/_global_mmlu_full_sr.yaml new file mode 100644 index 00000000..e322d980 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sr/_global_mmlu_full_sr.yaml @@ -0,0 +1,11 @@ +group: global_mmlu_full_sr +task: + - global_mmlu_full_sr_stem + - global_mmlu_full_sr_other + - global_mmlu_full_sr_social_sciences + - global_mmlu_full_sr_humanities +aggregate_metric_list: + - metric: acc + weight_by_size: True +metadata: + version: 1.0 diff --git a/lm_eval/tasks/global_mmlu/full/sr/_global_mmlu_full_sr_humanities.yaml b/lm_eval/tasks/global_mmlu/full/sr/_global_mmlu_full_sr_humanities.yaml new file mode 100644 index 00000000..080bc545 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sr/_global_mmlu_full_sr_humanities.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_sr_humanities +task: + - global_mmlu_full_sr_humanities_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/sr/_global_mmlu_full_sr_other.yaml b/lm_eval/tasks/global_mmlu/full/sr/_global_mmlu_full_sr_other.yaml new file mode 100644 index 00000000..9f0735eb --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sr/_global_mmlu_full_sr_other.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_sr_other +task: + - global_mmlu_full_sr_other_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/sr/_global_mmlu_full_sr_social_sciences.yaml b/lm_eval/tasks/global_mmlu/full/sr/_global_mmlu_full_sr_social_sciences.yaml new file mode 100644 index 00000000..bdc29d1f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sr/_global_mmlu_full_sr_social_sciences.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_sr_social_sciences +task: + - global_mmlu_full_sr_social_sciences_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/sr/_global_mmlu_full_sr_stem.yaml b/lm_eval/tasks/global_mmlu/full/sr/_global_mmlu_full_sr_stem.yaml new file mode 100644 index 00000000..7c4aa636 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sr/_global_mmlu_full_sr_stem.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_sr_stem +task: + - global_mmlu_full_sr_stem_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/sr/_sr_template_yaml b/lm_eval/tasks/global_mmlu/full/sr/_sr_template_yaml new file mode 100644 index 00000000..6af61b3b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sr/_sr_template_yaml @@ -0,0 +1,16 @@ +dataset_path: CohereForAI/Global-MMLU +dataset_name: sr +test_split: test +fewshot_split: dev +fewshot_config: + sampler: first_n +output_type: multiple_choice +doc_to_text: "{{question.strip()}}\nA. {{option_a}}\nB. {{option_b}}\nC. {{option_c}}\nD. {{option_d}}\nAnswer:" +doc_to_choice: ["A", "B", "C", "D"] +doc_to_target: answer +metric_list: + - metric: acc + aggregation: mean + higher_is_better: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_abstract_algebra.yaml b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_abstract_algebra.yaml new file mode 100644 index 00000000..b3275870 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_abstract_algebra.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sr_template_yaml +process_docs: !function utils.process_abstract_algebra +tag: global_mmlu_full_sr_stem_tasks +task: global_mmlu_full_sr_abstract_algebra diff --git a/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_anatomy.yaml b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_anatomy.yaml new file mode 100644 index 00000000..5689af73 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_anatomy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sr_template_yaml +process_docs: !function utils.process_anatomy +tag: global_mmlu_full_sr_stem_tasks +task: global_mmlu_full_sr_anatomy diff --git a/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_astronomy.yaml b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_astronomy.yaml new file mode 100644 index 00000000..3d23a438 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_astronomy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sr_template_yaml +process_docs: !function utils.process_astronomy +tag: global_mmlu_full_sr_stem_tasks +task: global_mmlu_full_sr_astronomy diff --git a/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_business_ethics.yaml b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_business_ethics.yaml new file mode 100644 index 00000000..e89f5e61 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_business_ethics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sr_template_yaml +process_docs: !function utils.process_business_ethics +tag: global_mmlu_full_sr_other_tasks +task: global_mmlu_full_sr_business_ethics diff --git a/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_clinical_knowledge.yaml b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_clinical_knowledge.yaml new file mode 100644 index 00000000..b5611c15 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_clinical_knowledge.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sr_template_yaml +process_docs: !function utils.process_clinical_knowledge +tag: global_mmlu_full_sr_other_tasks +task: global_mmlu_full_sr_clinical_knowledge diff --git a/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_college_biology.yaml b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_college_biology.yaml new file mode 100644 index 00000000..9e28c303 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_college_biology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sr_template_yaml +process_docs: !function utils.process_college_biology +tag: global_mmlu_full_sr_stem_tasks +task: global_mmlu_full_sr_college_biology diff --git a/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_college_chemistry.yaml b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_college_chemistry.yaml new file mode 100644 index 00000000..1eac952c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_college_chemistry.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sr_template_yaml +process_docs: !function utils.process_college_chemistry +tag: global_mmlu_full_sr_stem_tasks +task: global_mmlu_full_sr_college_chemistry diff --git a/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_college_computer_science.yaml b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_college_computer_science.yaml new file mode 100644 index 00000000..e1146aa1 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_college_computer_science.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sr_template_yaml +process_docs: !function utils.process_college_computer_science +tag: global_mmlu_full_sr_stem_tasks +task: global_mmlu_full_sr_college_computer_science diff --git a/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_college_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_college_mathematics.yaml new file mode 100644 index 00000000..bcfda2ba --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_college_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sr_template_yaml +process_docs: !function utils.process_college_mathematics +tag: global_mmlu_full_sr_stem_tasks +task: global_mmlu_full_sr_college_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_college_medicine.yaml b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_college_medicine.yaml new file mode 100644 index 00000000..3beb5b26 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_college_medicine.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sr_template_yaml +process_docs: !function utils.process_college_medicine +tag: global_mmlu_full_sr_other_tasks +task: global_mmlu_full_sr_college_medicine diff --git a/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_college_physics.yaml b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_college_physics.yaml new file mode 100644 index 00000000..f959a02f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_college_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sr_template_yaml +process_docs: !function utils.process_college_physics +tag: global_mmlu_full_sr_stem_tasks +task: global_mmlu_full_sr_college_physics diff --git a/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_computer_security.yaml b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_computer_security.yaml new file mode 100644 index 00000000..7e8761e0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_computer_security.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sr_template_yaml +process_docs: !function utils.process_computer_security +tag: global_mmlu_full_sr_stem_tasks +task: global_mmlu_full_sr_computer_security diff --git a/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_conceptual_physics.yaml b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_conceptual_physics.yaml new file mode 100644 index 00000000..9325f6de --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_conceptual_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sr_template_yaml +process_docs: !function utils.process_conceptual_physics +tag: global_mmlu_full_sr_stem_tasks +task: global_mmlu_full_sr_conceptual_physics diff --git a/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_econometrics.yaml b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_econometrics.yaml new file mode 100644 index 00000000..cc4a5bcc --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_econometrics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sr_template_yaml +process_docs: !function utils.process_econometrics +tag: global_mmlu_full_sr_social_sciences_tasks +task: global_mmlu_full_sr_econometrics diff --git a/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_electrical_engineering.yaml b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_electrical_engineering.yaml new file mode 100644 index 00000000..d3a5a78b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_electrical_engineering.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sr_template_yaml +process_docs: !function utils.process_electrical_engineering +tag: global_mmlu_full_sr_stem_tasks +task: global_mmlu_full_sr_electrical_engineering diff --git a/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_elementary_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_elementary_mathematics.yaml new file mode 100644 index 00000000..50f60166 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_elementary_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sr_template_yaml +process_docs: !function utils.process_elementary_mathematics +tag: global_mmlu_full_sr_stem_tasks +task: global_mmlu_full_sr_elementary_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_formal_logic.yaml b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_formal_logic.yaml new file mode 100644 index 00000000..8bdd854f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_formal_logic.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sr_template_yaml +process_docs: !function utils.process_formal_logic +tag: global_mmlu_full_sr_humanities_tasks +task: global_mmlu_full_sr_formal_logic diff --git a/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_global_facts.yaml b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_global_facts.yaml new file mode 100644 index 00000000..88862d21 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_global_facts.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sr_template_yaml +process_docs: !function utils.process_global_facts +tag: global_mmlu_full_sr_other_tasks +task: global_mmlu_full_sr_global_facts diff --git a/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_high_school_biology.yaml b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_high_school_biology.yaml new file mode 100644 index 00000000..8f2b2952 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_high_school_biology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sr_template_yaml +process_docs: !function utils.process_high_school_biology +tag: global_mmlu_full_sr_stem_tasks +task: global_mmlu_full_sr_high_school_biology diff --git a/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_high_school_chemistry.yaml b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_high_school_chemistry.yaml new file mode 100644 index 00000000..6b89deb1 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_high_school_chemistry.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sr_template_yaml +process_docs: !function utils.process_high_school_chemistry +tag: global_mmlu_full_sr_stem_tasks +task: global_mmlu_full_sr_high_school_chemistry diff --git a/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_high_school_computer_science.yaml b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_high_school_computer_science.yaml new file mode 100644 index 00000000..55fd7e8e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_high_school_computer_science.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sr_template_yaml +process_docs: !function utils.process_high_school_computer_science +tag: global_mmlu_full_sr_stem_tasks +task: global_mmlu_full_sr_high_school_computer_science diff --git a/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_high_school_european_history.yaml b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_high_school_european_history.yaml new file mode 100644 index 00000000..946acf0e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_high_school_european_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sr_template_yaml +process_docs: !function utils.process_high_school_european_history +tag: global_mmlu_full_sr_humanities_tasks +task: global_mmlu_full_sr_high_school_european_history diff --git a/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_high_school_geography.yaml b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_high_school_geography.yaml new file mode 100644 index 00000000..07058971 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_high_school_geography.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sr_template_yaml +process_docs: !function utils.process_high_school_geography +tag: global_mmlu_full_sr_social_sciences_tasks +task: global_mmlu_full_sr_high_school_geography diff --git a/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_high_school_government_and_politics.yaml b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_high_school_government_and_politics.yaml new file mode 100644 index 00000000..a9721c9b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_high_school_government_and_politics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sr_template_yaml +process_docs: !function utils.process_high_school_government_and_politics +tag: global_mmlu_full_sr_social_sciences_tasks +task: global_mmlu_full_sr_high_school_government_and_politics diff --git a/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_high_school_macroeconomics.yaml b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_high_school_macroeconomics.yaml new file mode 100644 index 00000000..fedea95a --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_high_school_macroeconomics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sr_template_yaml +process_docs: !function utils.process_high_school_macroeconomics +tag: global_mmlu_full_sr_social_sciences_tasks +task: global_mmlu_full_sr_high_school_macroeconomics diff --git a/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_high_school_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_high_school_mathematics.yaml new file mode 100644 index 00000000..dca9e140 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_high_school_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sr_template_yaml +process_docs: !function utils.process_high_school_mathematics +tag: global_mmlu_full_sr_stem_tasks +task: global_mmlu_full_sr_high_school_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_high_school_microeconomics.yaml b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_high_school_microeconomics.yaml new file mode 100644 index 00000000..b01276f6 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_high_school_microeconomics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sr_template_yaml +process_docs: !function utils.process_high_school_microeconomics +tag: global_mmlu_full_sr_social_sciences_tasks +task: global_mmlu_full_sr_high_school_microeconomics diff --git a/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_high_school_physics.yaml b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_high_school_physics.yaml new file mode 100644 index 00000000..f549f8ac --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_high_school_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sr_template_yaml +process_docs: !function utils.process_high_school_physics +tag: global_mmlu_full_sr_stem_tasks +task: global_mmlu_full_sr_high_school_physics diff --git a/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_high_school_psychology.yaml b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_high_school_psychology.yaml new file mode 100644 index 00000000..c6b31eee --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_high_school_psychology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sr_template_yaml +process_docs: !function utils.process_high_school_psychology +tag: global_mmlu_full_sr_social_sciences_tasks +task: global_mmlu_full_sr_high_school_psychology diff --git a/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_high_school_statistics.yaml b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_high_school_statistics.yaml new file mode 100644 index 00000000..12d0f0e5 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_high_school_statistics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sr_template_yaml +process_docs: !function utils.process_high_school_statistics +tag: global_mmlu_full_sr_stem_tasks +task: global_mmlu_full_sr_high_school_statistics diff --git a/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_high_school_us_history.yaml b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_high_school_us_history.yaml new file mode 100644 index 00000000..98c40100 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_high_school_us_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sr_template_yaml +process_docs: !function utils.process_high_school_us_history +tag: global_mmlu_full_sr_humanities_tasks +task: global_mmlu_full_sr_high_school_us_history diff --git a/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_high_school_world_history.yaml b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_high_school_world_history.yaml new file mode 100644 index 00000000..76e6b45c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_high_school_world_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sr_template_yaml +process_docs: !function utils.process_high_school_world_history +tag: global_mmlu_full_sr_humanities_tasks +task: global_mmlu_full_sr_high_school_world_history diff --git a/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_human_aging.yaml b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_human_aging.yaml new file mode 100644 index 00000000..b0ff1d95 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_human_aging.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sr_template_yaml +process_docs: !function utils.process_human_aging +tag: global_mmlu_full_sr_other_tasks +task: global_mmlu_full_sr_human_aging diff --git a/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_human_sexuality.yaml b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_human_sexuality.yaml new file mode 100644 index 00000000..73a30099 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_human_sexuality.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sr_template_yaml +process_docs: !function utils.process_human_sexuality +tag: global_mmlu_full_sr_social_sciences_tasks +task: global_mmlu_full_sr_human_sexuality diff --git a/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_international_law.yaml b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_international_law.yaml new file mode 100644 index 00000000..0aea0826 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_international_law.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sr_template_yaml +process_docs: !function utils.process_international_law +tag: global_mmlu_full_sr_humanities_tasks +task: global_mmlu_full_sr_international_law diff --git a/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_jurisprudence.yaml b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_jurisprudence.yaml new file mode 100644 index 00000000..debe604f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_jurisprudence.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sr_template_yaml +process_docs: !function utils.process_jurisprudence +tag: global_mmlu_full_sr_humanities_tasks +task: global_mmlu_full_sr_jurisprudence diff --git a/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_logical_fallacies.yaml b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_logical_fallacies.yaml new file mode 100644 index 00000000..407417f3 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_logical_fallacies.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sr_template_yaml +process_docs: !function utils.process_logical_fallacies +tag: global_mmlu_full_sr_humanities_tasks +task: global_mmlu_full_sr_logical_fallacies diff --git a/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_machine_learning.yaml b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_machine_learning.yaml new file mode 100644 index 00000000..513a7f87 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_machine_learning.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sr_template_yaml +process_docs: !function utils.process_machine_learning +tag: global_mmlu_full_sr_stem_tasks +task: global_mmlu_full_sr_machine_learning diff --git a/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_management.yaml b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_management.yaml new file mode 100644 index 00000000..fca9de04 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_management.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sr_template_yaml +process_docs: !function utils.process_management +tag: global_mmlu_full_sr_other_tasks +task: global_mmlu_full_sr_management diff --git a/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_marketing.yaml b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_marketing.yaml new file mode 100644 index 00000000..8267563e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_marketing.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sr_template_yaml +process_docs: !function utils.process_marketing +tag: global_mmlu_full_sr_other_tasks +task: global_mmlu_full_sr_marketing diff --git a/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_medical_genetics.yaml b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_medical_genetics.yaml new file mode 100644 index 00000000..4ba860f2 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_medical_genetics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sr_template_yaml +process_docs: !function utils.process_medical_genetics +tag: global_mmlu_full_sr_other_tasks +task: global_mmlu_full_sr_medical_genetics diff --git a/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_miscellaneous.yaml b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_miscellaneous.yaml new file mode 100644 index 00000000..ecdbcea9 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_miscellaneous.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sr_template_yaml +process_docs: !function utils.process_miscellaneous +tag: global_mmlu_full_sr_other_tasks +task: global_mmlu_full_sr_miscellaneous diff --git a/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_moral_disputes.yaml b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_moral_disputes.yaml new file mode 100644 index 00000000..54bf3491 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_moral_disputes.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sr_template_yaml +process_docs: !function utils.process_moral_disputes +tag: global_mmlu_full_sr_humanities_tasks +task: global_mmlu_full_sr_moral_disputes diff --git a/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_moral_scenarios.yaml b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_moral_scenarios.yaml new file mode 100644 index 00000000..2eab8d4a --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_moral_scenarios.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sr_template_yaml +process_docs: !function utils.process_moral_scenarios +tag: global_mmlu_full_sr_humanities_tasks +task: global_mmlu_full_sr_moral_scenarios diff --git a/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_nutrition.yaml b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_nutrition.yaml new file mode 100644 index 00000000..83e1b84c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_nutrition.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sr_template_yaml +process_docs: !function utils.process_nutrition +tag: global_mmlu_full_sr_other_tasks +task: global_mmlu_full_sr_nutrition diff --git a/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_philosophy.yaml b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_philosophy.yaml new file mode 100644 index 00000000..654ee86b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_philosophy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sr_template_yaml +process_docs: !function utils.process_philosophy +tag: global_mmlu_full_sr_humanities_tasks +task: global_mmlu_full_sr_philosophy diff --git a/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_prehistory.yaml b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_prehistory.yaml new file mode 100644 index 00000000..3a2f944b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_prehistory.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sr_template_yaml +process_docs: !function utils.process_prehistory +tag: global_mmlu_full_sr_humanities_tasks +task: global_mmlu_full_sr_prehistory diff --git a/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_professional_accounting.yaml b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_professional_accounting.yaml new file mode 100644 index 00000000..648ae0cb --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_professional_accounting.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sr_template_yaml +process_docs: !function utils.process_professional_accounting +tag: global_mmlu_full_sr_other_tasks +task: global_mmlu_full_sr_professional_accounting diff --git a/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_professional_law.yaml b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_professional_law.yaml new file mode 100644 index 00000000..0ee8a831 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_professional_law.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sr_template_yaml +process_docs: !function utils.process_professional_law +tag: global_mmlu_full_sr_humanities_tasks +task: global_mmlu_full_sr_professional_law diff --git a/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_professional_medicine.yaml b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_professional_medicine.yaml new file mode 100644 index 00000000..3b142115 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_professional_medicine.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sr_template_yaml +process_docs: !function utils.process_professional_medicine +tag: global_mmlu_full_sr_other_tasks +task: global_mmlu_full_sr_professional_medicine diff --git a/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_professional_psychology.yaml b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_professional_psychology.yaml new file mode 100644 index 00000000..19e2dc54 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_professional_psychology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sr_template_yaml +process_docs: !function utils.process_professional_psychology +tag: global_mmlu_full_sr_social_sciences_tasks +task: global_mmlu_full_sr_professional_psychology diff --git a/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_public_relations.yaml b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_public_relations.yaml new file mode 100644 index 00000000..043024c0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_public_relations.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sr_template_yaml +process_docs: !function utils.process_public_relations +tag: global_mmlu_full_sr_social_sciences_tasks +task: global_mmlu_full_sr_public_relations diff --git a/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_security_studies.yaml b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_security_studies.yaml new file mode 100644 index 00000000..24720925 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_security_studies.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sr_template_yaml +process_docs: !function utils.process_security_studies +tag: global_mmlu_full_sr_social_sciences_tasks +task: global_mmlu_full_sr_security_studies diff --git a/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_sociology.yaml b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_sociology.yaml new file mode 100644 index 00000000..fc93c5e0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_sociology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sr_template_yaml +process_docs: !function utils.process_sociology +tag: global_mmlu_full_sr_social_sciences_tasks +task: global_mmlu_full_sr_sociology diff --git a/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_us_foreign_policy.yaml b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_us_foreign_policy.yaml new file mode 100644 index 00000000..1b338dd6 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_us_foreign_policy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sr_template_yaml +process_docs: !function utils.process_us_foreign_policy +tag: global_mmlu_full_sr_social_sciences_tasks +task: global_mmlu_full_sr_us_foreign_policy diff --git a/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_virology.yaml b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_virology.yaml new file mode 100644 index 00000000..b07588ad --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_virology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sr_template_yaml +process_docs: !function utils.process_virology +tag: global_mmlu_full_sr_other_tasks +task: global_mmlu_full_sr_virology diff --git a/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_world_religions.yaml b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_world_religions.yaml new file mode 100644 index 00000000..3f78403e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sr/global_mmlu_full_sr_world_religions.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sr_template_yaml +process_docs: !function utils.process_world_religions +tag: global_mmlu_full_sr_humanities_tasks +task: global_mmlu_full_sr_world_religions diff --git a/lm_eval/tasks/global_mmlu/full/sr/utils.py b/lm_eval/tasks/global_mmlu/full/sr/utils.py new file mode 100644 index 00000000..7df72cb0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sr/utils.py @@ -0,0 +1,73 @@ +from functools import partial + + +SUBJECTS = [ + "abstract_algebra", + "anatomy", + "astronomy", + "business_ethics", + "clinical_knowledge", + "college_biology", + "college_chemistry", + "college_computer_science", + "college_mathematics", + "college_medicine", + "college_physics", + "computer_security", + "conceptual_physics", + "econometrics", + "electrical_engineering", + "elementary_mathematics", + "formal_logic", + "global_facts", + "high_school_biology", + "high_school_chemistry", + "high_school_computer_science", + "high_school_european_history", + "high_school_geography", + "high_school_government_and_politics", + "high_school_macroeconomics", + "high_school_mathematics", + "high_school_microeconomics", + "high_school_physics", + "high_school_psychology", + "high_school_statistics", + "high_school_us_history", + "high_school_world_history", + "human_aging", + "human_sexuality", + "international_law", + "jurisprudence", + "logical_fallacies", + "machine_learning", + "management", + "marketing", + "medical_genetics", + "miscellaneous", + "moral_disputes", + "moral_scenarios", + "nutrition", + "philosophy", + "prehistory", + "professional_accounting", + "professional_law", + "professional_medicine", + "professional_psychology", + "public_relations", + "security_studies", + "sociology", + "us_foreign_policy", + "virology", + "world_religions", +] + + +def process_docs(dataset, subject): + return dataset.filter(lambda x: x["subject"] == subject) + + +process_functions = { + f"process_{subject}": partial(process_docs, subject=subject) for subject in SUBJECTS +} + +globals().update(process_functions) diff --git a/lm_eval/tasks/global_mmlu/full/sv/_global_mmlu_full_sv.yaml b/lm_eval/tasks/global_mmlu/full/sv/_global_mmlu_full_sv.yaml new file mode 100644 index 00000000..a9b0dc1b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sv/_global_mmlu_full_sv.yaml @@ -0,0 +1,11 @@ +group: global_mmlu_full_sv +task: + - global_mmlu_full_sv_stem + - global_mmlu_full_sv_other + - global_mmlu_full_sv_social_sciences + - global_mmlu_full_sv_humanities +aggregate_metric_list: + - metric: acc + weight_by_size: True +metadata: + version: 1.0 diff --git a/lm_eval/tasks/global_mmlu/full/sv/_global_mmlu_full_sv_humanities.yaml b/lm_eval/tasks/global_mmlu/full/sv/_global_mmlu_full_sv_humanities.yaml new file mode 100644 index 00000000..f8b4628f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sv/_global_mmlu_full_sv_humanities.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_sv_humanities +task: + - global_mmlu_full_sv_humanities_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/sv/_global_mmlu_full_sv_other.yaml b/lm_eval/tasks/global_mmlu/full/sv/_global_mmlu_full_sv_other.yaml new file mode 100644 index 00000000..1b29ca13 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sv/_global_mmlu_full_sv_other.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_sv_other +task: + - global_mmlu_full_sv_other_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/sv/_global_mmlu_full_sv_social_sciences.yaml b/lm_eval/tasks/global_mmlu/full/sv/_global_mmlu_full_sv_social_sciences.yaml new file mode 100644 index 00000000..7c4a813e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sv/_global_mmlu_full_sv_social_sciences.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_sv_social_sciences +task: + - global_mmlu_full_sv_social_sciences_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/sv/_global_mmlu_full_sv_stem.yaml b/lm_eval/tasks/global_mmlu/full/sv/_global_mmlu_full_sv_stem.yaml new file mode 100644 index 00000000..a6fd88f1 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sv/_global_mmlu_full_sv_stem.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_sv_stem +task: + - global_mmlu_full_sv_stem_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/sv/_sv_template_yaml b/lm_eval/tasks/global_mmlu/full/sv/_sv_template_yaml new file mode 100644 index 00000000..1b9fdea9 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sv/_sv_template_yaml @@ -0,0 +1,16 @@ +dataset_path: CohereForAI/Global-MMLU +dataset_name: sv +test_split: test +fewshot_split: dev +fewshot_config: + sampler: first_n +output_type: multiple_choice +doc_to_text: "{{question.strip()}}\nA. {{option_a}}\nB. {{option_b}}\nC. {{option_c}}\nD. {{option_d}}\nAnswer:" +doc_to_choice: ["A", "B", "C", "D"] +doc_to_target: answer +metric_list: + - metric: acc + aggregation: mean + higher_is_better: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_abstract_algebra.yaml b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_abstract_algebra.yaml new file mode 100644 index 00000000..8329302f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_abstract_algebra.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sv_template_yaml +process_docs: !function utils.process_abstract_algebra +tag: global_mmlu_full_sv_stem_tasks +task: global_mmlu_full_sv_abstract_algebra diff --git a/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_anatomy.yaml b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_anatomy.yaml new file mode 100644 index 00000000..ac9fa560 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_anatomy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sv_template_yaml +process_docs: !function utils.process_anatomy +tag: global_mmlu_full_sv_stem_tasks +task: global_mmlu_full_sv_anatomy diff --git a/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_astronomy.yaml b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_astronomy.yaml new file mode 100644 index 00000000..096e0e8f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_astronomy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sv_template_yaml +process_docs: !function utils.process_astronomy +tag: global_mmlu_full_sv_stem_tasks +task: global_mmlu_full_sv_astronomy diff --git a/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_business_ethics.yaml b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_business_ethics.yaml new file mode 100644 index 00000000..ced0b051 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_business_ethics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sv_template_yaml +process_docs: !function utils.process_business_ethics +tag: global_mmlu_full_sv_other_tasks +task: global_mmlu_full_sv_business_ethics diff --git a/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_clinical_knowledge.yaml b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_clinical_knowledge.yaml new file mode 100644 index 00000000..a88871b4 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_clinical_knowledge.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sv_template_yaml +process_docs: !function utils.process_clinical_knowledge +tag: global_mmlu_full_sv_other_tasks +task: global_mmlu_full_sv_clinical_knowledge diff --git a/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_college_biology.yaml b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_college_biology.yaml new file mode 100644 index 00000000..c2462c17 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_college_biology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sv_template_yaml +process_docs: !function utils.process_college_biology +tag: global_mmlu_full_sv_stem_tasks +task: global_mmlu_full_sv_college_biology diff --git a/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_college_chemistry.yaml b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_college_chemistry.yaml new file mode 100644 index 00000000..3ae3fecd --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_college_chemistry.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sv_template_yaml +process_docs: !function utils.process_college_chemistry +tag: global_mmlu_full_sv_stem_tasks +task: global_mmlu_full_sv_college_chemistry diff --git a/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_college_computer_science.yaml b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_college_computer_science.yaml new file mode 100644 index 00000000..a3f00b24 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_college_computer_science.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sv_template_yaml +process_docs: !function utils.process_college_computer_science +tag: global_mmlu_full_sv_stem_tasks +task: global_mmlu_full_sv_college_computer_science diff --git a/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_college_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_college_mathematics.yaml new file mode 100644 index 00000000..71f613d4 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_college_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sv_template_yaml +process_docs: !function utils.process_college_mathematics +tag: global_mmlu_full_sv_stem_tasks +task: global_mmlu_full_sv_college_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_college_medicine.yaml b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_college_medicine.yaml new file mode 100644 index 00000000..46f4c6ea --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_college_medicine.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sv_template_yaml +process_docs: !function utils.process_college_medicine +tag: global_mmlu_full_sv_other_tasks +task: global_mmlu_full_sv_college_medicine diff --git a/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_college_physics.yaml b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_college_physics.yaml new file mode 100644 index 00000000..06906bfd --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_college_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sv_template_yaml +process_docs: !function utils.process_college_physics +tag: global_mmlu_full_sv_stem_tasks +task: global_mmlu_full_sv_college_physics diff --git a/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_computer_security.yaml b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_computer_security.yaml new file mode 100644 index 00000000..1013ef30 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_computer_security.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sv_template_yaml +process_docs: !function utils.process_computer_security +tag: global_mmlu_full_sv_stem_tasks +task: global_mmlu_full_sv_computer_security diff --git a/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_conceptual_physics.yaml b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_conceptual_physics.yaml new file mode 100644 index 00000000..a6a752f0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_conceptual_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sv_template_yaml +process_docs: !function utils.process_conceptual_physics +tag: global_mmlu_full_sv_stem_tasks +task: global_mmlu_full_sv_conceptual_physics diff --git a/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_econometrics.yaml b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_econometrics.yaml new file mode 100644 index 00000000..547365f6 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_econometrics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sv_template_yaml +process_docs: !function utils.process_econometrics +tag: global_mmlu_full_sv_social_sciences_tasks +task: global_mmlu_full_sv_econometrics diff --git a/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_electrical_engineering.yaml b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_electrical_engineering.yaml new file mode 100644 index 00000000..74086a15 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_electrical_engineering.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sv_template_yaml +process_docs: !function utils.process_electrical_engineering +tag: global_mmlu_full_sv_stem_tasks +task: global_mmlu_full_sv_electrical_engineering diff --git a/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_elementary_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_elementary_mathematics.yaml new file mode 100644 index 00000000..8d1f4847 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_elementary_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sv_template_yaml +process_docs: !function utils.process_elementary_mathematics +tag: global_mmlu_full_sv_stem_tasks +task: global_mmlu_full_sv_elementary_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_formal_logic.yaml b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_formal_logic.yaml new file mode 100644 index 00000000..b78b5846 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_formal_logic.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sv_template_yaml +process_docs: !function utils.process_formal_logic +tag: global_mmlu_full_sv_humanities_tasks +task: global_mmlu_full_sv_formal_logic diff --git a/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_global_facts.yaml b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_global_facts.yaml new file mode 100644 index 00000000..dd205629 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_global_facts.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sv_template_yaml +process_docs: !function utils.process_global_facts +tag: global_mmlu_full_sv_other_tasks +task: global_mmlu_full_sv_global_facts diff --git a/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_high_school_biology.yaml b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_high_school_biology.yaml new file mode 100644 index 00000000..fc6ebf2f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_high_school_biology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sv_template_yaml +process_docs: !function utils.process_high_school_biology +tag: global_mmlu_full_sv_stem_tasks +task: global_mmlu_full_sv_high_school_biology diff --git a/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_high_school_chemistry.yaml b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_high_school_chemistry.yaml new file mode 100644 index 00000000..03773a83 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_high_school_chemistry.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sv_template_yaml +process_docs: !function utils.process_high_school_chemistry +tag: global_mmlu_full_sv_stem_tasks +task: global_mmlu_full_sv_high_school_chemistry diff --git a/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_high_school_computer_science.yaml b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_high_school_computer_science.yaml new file mode 100644 index 00000000..e3db653a --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_high_school_computer_science.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sv_template_yaml +process_docs: !function utils.process_high_school_computer_science +tag: global_mmlu_full_sv_stem_tasks +task: global_mmlu_full_sv_high_school_computer_science diff --git a/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_high_school_european_history.yaml b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_high_school_european_history.yaml new file mode 100644 index 00000000..4a087557 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_high_school_european_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sv_template_yaml +process_docs: !function utils.process_high_school_european_history +tag: global_mmlu_full_sv_humanities_tasks +task: global_mmlu_full_sv_high_school_european_history diff --git a/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_high_school_geography.yaml b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_high_school_geography.yaml new file mode 100644 index 00000000..63855384 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_high_school_geography.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sv_template_yaml +process_docs: !function utils.process_high_school_geography +tag: global_mmlu_full_sv_social_sciences_tasks +task: global_mmlu_full_sv_high_school_geography diff --git a/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_high_school_government_and_politics.yaml b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_high_school_government_and_politics.yaml new file mode 100644 index 00000000..7e62f26f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_high_school_government_and_politics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sv_template_yaml +process_docs: !function utils.process_high_school_government_and_politics +tag: global_mmlu_full_sv_social_sciences_tasks +task: global_mmlu_full_sv_high_school_government_and_politics diff --git a/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_high_school_macroeconomics.yaml b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_high_school_macroeconomics.yaml new file mode 100644 index 00000000..b686a26e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_high_school_macroeconomics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sv_template_yaml +process_docs: !function utils.process_high_school_macroeconomics +tag: global_mmlu_full_sv_social_sciences_tasks +task: global_mmlu_full_sv_high_school_macroeconomics diff --git a/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_high_school_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_high_school_mathematics.yaml new file mode 100644 index 00000000..17716538 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_high_school_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sv_template_yaml +process_docs: !function utils.process_high_school_mathematics +tag: global_mmlu_full_sv_stem_tasks +task: global_mmlu_full_sv_high_school_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_high_school_microeconomics.yaml b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_high_school_microeconomics.yaml new file mode 100644 index 00000000..e9817c17 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_high_school_microeconomics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sv_template_yaml +process_docs: !function utils.process_high_school_microeconomics +tag: global_mmlu_full_sv_social_sciences_tasks +task: global_mmlu_full_sv_high_school_microeconomics diff --git a/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_high_school_physics.yaml b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_high_school_physics.yaml new file mode 100644 index 00000000..61359149 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_high_school_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sv_template_yaml +process_docs: !function utils.process_high_school_physics +tag: global_mmlu_full_sv_stem_tasks +task: global_mmlu_full_sv_high_school_physics diff --git a/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_high_school_psychology.yaml b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_high_school_psychology.yaml new file mode 100644 index 00000000..ce3aa9e2 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_high_school_psychology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sv_template_yaml +process_docs: !function utils.process_high_school_psychology +tag: global_mmlu_full_sv_social_sciences_tasks +task: global_mmlu_full_sv_high_school_psychology diff --git a/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_high_school_statistics.yaml b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_high_school_statistics.yaml new file mode 100644 index 00000000..6f705f8e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_high_school_statistics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sv_template_yaml +process_docs: !function utils.process_high_school_statistics +tag: global_mmlu_full_sv_stem_tasks +task: global_mmlu_full_sv_high_school_statistics diff --git a/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_high_school_us_history.yaml b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_high_school_us_history.yaml new file mode 100644 index 00000000..765cdf60 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_high_school_us_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sv_template_yaml +process_docs: !function utils.process_high_school_us_history +tag: global_mmlu_full_sv_humanities_tasks +task: global_mmlu_full_sv_high_school_us_history diff --git a/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_high_school_world_history.yaml b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_high_school_world_history.yaml new file mode 100644 index 00000000..de7b30b4 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_high_school_world_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sv_template_yaml +process_docs: !function utils.process_high_school_world_history +tag: global_mmlu_full_sv_humanities_tasks +task: global_mmlu_full_sv_high_school_world_history diff --git a/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_human_aging.yaml b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_human_aging.yaml new file mode 100644 index 00000000..20969051 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_human_aging.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sv_template_yaml +process_docs: !function utils.process_human_aging +tag: global_mmlu_full_sv_other_tasks +task: global_mmlu_full_sv_human_aging diff --git a/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_human_sexuality.yaml b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_human_sexuality.yaml new file mode 100644 index 00000000..a8bd5fab --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_human_sexuality.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sv_template_yaml +process_docs: !function utils.process_human_sexuality +tag: global_mmlu_full_sv_social_sciences_tasks +task: global_mmlu_full_sv_human_sexuality diff --git a/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_international_law.yaml b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_international_law.yaml new file mode 100644 index 00000000..7e5ddb57 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_international_law.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sv_template_yaml +process_docs: !function utils.process_international_law +tag: global_mmlu_full_sv_humanities_tasks +task: global_mmlu_full_sv_international_law diff --git a/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_jurisprudence.yaml b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_jurisprudence.yaml new file mode 100644 index 00000000..ff161d5f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_jurisprudence.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sv_template_yaml +process_docs: !function utils.process_jurisprudence +tag: global_mmlu_full_sv_humanities_tasks +task: global_mmlu_full_sv_jurisprudence diff --git a/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_logical_fallacies.yaml b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_logical_fallacies.yaml new file mode 100644 index 00000000..f1602c90 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_logical_fallacies.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sv_template_yaml +process_docs: !function utils.process_logical_fallacies +tag: global_mmlu_full_sv_humanities_tasks +task: global_mmlu_full_sv_logical_fallacies diff --git a/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_machine_learning.yaml b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_machine_learning.yaml new file mode 100644 index 00000000..6f011063 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_machine_learning.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sv_template_yaml +process_docs: !function utils.process_machine_learning +tag: global_mmlu_full_sv_stem_tasks +task: global_mmlu_full_sv_machine_learning diff --git a/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_management.yaml b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_management.yaml new file mode 100644 index 00000000..7ff7b873 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_management.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sv_template_yaml +process_docs: !function utils.process_management +tag: global_mmlu_full_sv_other_tasks +task: global_mmlu_full_sv_management diff --git a/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_marketing.yaml b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_marketing.yaml new file mode 100644 index 00000000..c0e669f7 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_marketing.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sv_template_yaml +process_docs: !function utils.process_marketing +tag: global_mmlu_full_sv_other_tasks +task: global_mmlu_full_sv_marketing diff --git a/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_medical_genetics.yaml b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_medical_genetics.yaml new file mode 100644 index 00000000..83e52445 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_medical_genetics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sv_template_yaml +process_docs: !function utils.process_medical_genetics +tag: global_mmlu_full_sv_other_tasks +task: global_mmlu_full_sv_medical_genetics diff --git a/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_miscellaneous.yaml b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_miscellaneous.yaml new file mode 100644 index 00000000..f1798792 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_miscellaneous.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sv_template_yaml +process_docs: !function utils.process_miscellaneous +tag: global_mmlu_full_sv_other_tasks +task: global_mmlu_full_sv_miscellaneous diff --git a/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_moral_disputes.yaml b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_moral_disputes.yaml new file mode 100644 index 00000000..1f03ac09 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_moral_disputes.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sv_template_yaml +process_docs: !function utils.process_moral_disputes +tag: global_mmlu_full_sv_humanities_tasks +task: global_mmlu_full_sv_moral_disputes diff --git a/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_moral_scenarios.yaml b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_moral_scenarios.yaml new file mode 100644 index 00000000..fe7f58d2 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_moral_scenarios.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sv_template_yaml +process_docs: !function utils.process_moral_scenarios +tag: global_mmlu_full_sv_humanities_tasks +task: global_mmlu_full_sv_moral_scenarios diff --git a/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_nutrition.yaml b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_nutrition.yaml new file mode 100644 index 00000000..79207a87 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_nutrition.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sv_template_yaml +process_docs: !function utils.process_nutrition +tag: global_mmlu_full_sv_other_tasks +task: global_mmlu_full_sv_nutrition diff --git a/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_philosophy.yaml b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_philosophy.yaml new file mode 100644 index 00000000..ae533079 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_philosophy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sv_template_yaml +process_docs: !function utils.process_philosophy +tag: global_mmlu_full_sv_humanities_tasks +task: global_mmlu_full_sv_philosophy diff --git a/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_prehistory.yaml b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_prehistory.yaml new file mode 100644 index 00000000..1c602c4f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_prehistory.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sv_template_yaml +process_docs: !function utils.process_prehistory +tag: global_mmlu_full_sv_humanities_tasks +task: global_mmlu_full_sv_prehistory diff --git a/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_professional_accounting.yaml b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_professional_accounting.yaml new file mode 100644 index 00000000..ebdef8a8 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_professional_accounting.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sv_template_yaml +process_docs: !function utils.process_professional_accounting +tag: global_mmlu_full_sv_other_tasks +task: global_mmlu_full_sv_professional_accounting diff --git a/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_professional_law.yaml b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_professional_law.yaml new file mode 100644 index 00000000..3645c38a --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_professional_law.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sv_template_yaml +process_docs: !function utils.process_professional_law +tag: global_mmlu_full_sv_humanities_tasks +task: global_mmlu_full_sv_professional_law diff --git a/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_professional_medicine.yaml b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_professional_medicine.yaml new file mode 100644 index 00000000..d40f577d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_professional_medicine.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sv_template_yaml +process_docs: !function utils.process_professional_medicine +tag: global_mmlu_full_sv_other_tasks +task: global_mmlu_full_sv_professional_medicine diff --git a/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_professional_psychology.yaml b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_professional_psychology.yaml new file mode 100644 index 00000000..edf83106 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_professional_psychology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sv_template_yaml +process_docs: !function utils.process_professional_psychology +tag: global_mmlu_full_sv_social_sciences_tasks +task: global_mmlu_full_sv_professional_psychology diff --git a/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_public_relations.yaml b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_public_relations.yaml new file mode 100644 index 00000000..f897662c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_public_relations.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sv_template_yaml +process_docs: !function utils.process_public_relations +tag: global_mmlu_full_sv_social_sciences_tasks +task: global_mmlu_full_sv_public_relations diff --git a/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_security_studies.yaml b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_security_studies.yaml new file mode 100644 index 00000000..9ad4fb5c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_security_studies.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sv_template_yaml +process_docs: !function utils.process_security_studies +tag: global_mmlu_full_sv_social_sciences_tasks +task: global_mmlu_full_sv_security_studies diff --git a/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_sociology.yaml b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_sociology.yaml new file mode 100644 index 00000000..4b869606 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_sociology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sv_template_yaml +process_docs: !function utils.process_sociology +tag: global_mmlu_full_sv_social_sciences_tasks +task: global_mmlu_full_sv_sociology diff --git a/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_us_foreign_policy.yaml b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_us_foreign_policy.yaml new file mode 100644 index 00000000..522778de --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_us_foreign_policy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sv_template_yaml +process_docs: !function utils.process_us_foreign_policy +tag: global_mmlu_full_sv_social_sciences_tasks +task: global_mmlu_full_sv_us_foreign_policy diff --git a/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_virology.yaml b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_virology.yaml new file mode 100644 index 00000000..8b3cbc8d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_virology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sv_template_yaml +process_docs: !function utils.process_virology +tag: global_mmlu_full_sv_other_tasks +task: global_mmlu_full_sv_virology diff --git a/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_world_religions.yaml b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_world_religions.yaml new file mode 100644 index 00000000..1d7df52b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sv/global_mmlu_full_sv_world_religions.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sv_template_yaml +process_docs: !function utils.process_world_religions +tag: global_mmlu_full_sv_humanities_tasks +task: global_mmlu_full_sv_world_religions diff --git a/lm_eval/tasks/global_mmlu/full/sv/utils.py b/lm_eval/tasks/global_mmlu/full/sv/utils.py new file mode 100644 index 00000000..7df72cb0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sv/utils.py @@ -0,0 +1,73 @@ +from functools import partial + + +SUBJECTS = [ + "abstract_algebra", + "anatomy", + "astronomy", + "business_ethics", + "clinical_knowledge", + "college_biology", + "college_chemistry", + "college_computer_science", + "college_mathematics", + "college_medicine", + "college_physics", + "computer_security", + "conceptual_physics", + "econometrics", + "electrical_engineering", + "elementary_mathematics", + "formal_logic", + "global_facts", + "high_school_biology", + "high_school_chemistry", + "high_school_computer_science", + "high_school_european_history", + "high_school_geography", + "high_school_government_and_politics", + "high_school_macroeconomics", + "high_school_mathematics", + "high_school_microeconomics", + "high_school_physics", + "high_school_psychology", + "high_school_statistics", + "high_school_us_history", + "high_school_world_history", + "human_aging", + "human_sexuality", + "international_law", + "jurisprudence", + "logical_fallacies", + "machine_learning", + "management", + "marketing", + "medical_genetics", + "miscellaneous", + "moral_disputes", + "moral_scenarios", + "nutrition", + "philosophy", + "prehistory", + "professional_accounting", + "professional_law", + "professional_medicine", + "professional_psychology", + "public_relations", + "security_studies", + "sociology", + "us_foreign_policy", + "virology", + "world_religions", +] + + +def process_docs(dataset, subject): + return dataset.filter(lambda x: x["subject"] == subject) + + +process_functions = { + f"process_{subject}": partial(process_docs, subject=subject) for subject in SUBJECTS +} + +globals().update(process_functions) diff --git a/lm_eval/tasks/global_mmlu/full/sw/_global_mmlu_full_sw.yaml b/lm_eval/tasks/global_mmlu/full/sw/_global_mmlu_full_sw.yaml new file mode 100644 index 00000000..274543cf --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sw/_global_mmlu_full_sw.yaml @@ -0,0 +1,11 @@ +group: global_mmlu_full_sw +task: + - global_mmlu_full_sw_stem + - global_mmlu_full_sw_other + - global_mmlu_full_sw_social_sciences + - global_mmlu_full_sw_humanities +aggregate_metric_list: + - metric: acc + weight_by_size: True +metadata: + version: 1.0 diff --git a/lm_eval/tasks/global_mmlu/full/sw/_global_mmlu_full_sw_humanities.yaml b/lm_eval/tasks/global_mmlu/full/sw/_global_mmlu_full_sw_humanities.yaml new file mode 100644 index 00000000..02168dff --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sw/_global_mmlu_full_sw_humanities.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_sw_humanities +task: + - global_mmlu_full_sw_humanities_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/sw/_global_mmlu_full_sw_other.yaml b/lm_eval/tasks/global_mmlu/full/sw/_global_mmlu_full_sw_other.yaml new file mode 100644 index 00000000..9fa28a16 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sw/_global_mmlu_full_sw_other.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_sw_other +task: + - global_mmlu_full_sw_other_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/sw/_global_mmlu_full_sw_social_sciences.yaml b/lm_eval/tasks/global_mmlu/full/sw/_global_mmlu_full_sw_social_sciences.yaml new file mode 100644 index 00000000..ad318442 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sw/_global_mmlu_full_sw_social_sciences.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_sw_social_sciences +task: + - global_mmlu_full_sw_social_sciences_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/sw/_global_mmlu_full_sw_stem.yaml b/lm_eval/tasks/global_mmlu/full/sw/_global_mmlu_full_sw_stem.yaml new file mode 100644 index 00000000..6f23cae8 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sw/_global_mmlu_full_sw_stem.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_sw_stem +task: + - global_mmlu_full_sw_stem_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/sw/_sw_template_yaml b/lm_eval/tasks/global_mmlu/full/sw/_sw_template_yaml new file mode 100644 index 00000000..58cf5322 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sw/_sw_template_yaml @@ -0,0 +1,16 @@ +dataset_path: CohereForAI/Global-MMLU +dataset_name: sw +test_split: test +fewshot_split: dev +fewshot_config: + sampler: first_n +output_type: multiple_choice +doc_to_text: "{{question.strip()}}\nA. {{option_a}}\nB. {{option_b}}\nC. {{option_c}}\nD. {{option_d}}\nAnswer:" +doc_to_choice: ["A", "B", "C", "D"] +doc_to_target: answer +metric_list: + - metric: acc + aggregation: mean + higher_is_better: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_abstract_algebra.yaml b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_abstract_algebra.yaml new file mode 100644 index 00000000..187229fb --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_abstract_algebra.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sw_template_yaml +process_docs: !function utils.process_abstract_algebra +tag: global_mmlu_full_sw_stem_tasks +task: global_mmlu_full_sw_abstract_algebra diff --git a/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_anatomy.yaml b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_anatomy.yaml new file mode 100644 index 00000000..3d0d4c5c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_anatomy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sw_template_yaml +process_docs: !function utils.process_anatomy +tag: global_mmlu_full_sw_stem_tasks +task: global_mmlu_full_sw_anatomy diff --git a/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_astronomy.yaml b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_astronomy.yaml new file mode 100644 index 00000000..0639b390 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_astronomy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sw_template_yaml +process_docs: !function utils.process_astronomy +tag: global_mmlu_full_sw_stem_tasks +task: global_mmlu_full_sw_astronomy diff --git a/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_business_ethics.yaml b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_business_ethics.yaml new file mode 100644 index 00000000..a729c9da --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_business_ethics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sw_template_yaml +process_docs: !function utils.process_business_ethics +tag: global_mmlu_full_sw_other_tasks +task: global_mmlu_full_sw_business_ethics diff --git a/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_clinical_knowledge.yaml b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_clinical_knowledge.yaml new file mode 100644 index 00000000..c6b83623 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_clinical_knowledge.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sw_template_yaml +process_docs: !function utils.process_clinical_knowledge +tag: global_mmlu_full_sw_other_tasks +task: global_mmlu_full_sw_clinical_knowledge diff --git a/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_college_biology.yaml b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_college_biology.yaml new file mode 100644 index 00000000..1856b934 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_college_biology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sw_template_yaml +process_docs: !function utils.process_college_biology +tag: global_mmlu_full_sw_stem_tasks +task: global_mmlu_full_sw_college_biology diff --git a/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_college_chemistry.yaml b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_college_chemistry.yaml new file mode 100644 index 00000000..5ad547ff --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_college_chemistry.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sw_template_yaml +process_docs: !function utils.process_college_chemistry +tag: global_mmlu_full_sw_stem_tasks +task: global_mmlu_full_sw_college_chemistry diff --git a/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_college_computer_science.yaml b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_college_computer_science.yaml new file mode 100644 index 00000000..ff8d8741 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_college_computer_science.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sw_template_yaml +process_docs: !function utils.process_college_computer_science +tag: global_mmlu_full_sw_stem_tasks +task: global_mmlu_full_sw_college_computer_science diff --git a/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_college_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_college_mathematics.yaml new file mode 100644 index 00000000..02f53a4a --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_college_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sw_template_yaml +process_docs: !function utils.process_college_mathematics +tag: global_mmlu_full_sw_stem_tasks +task: global_mmlu_full_sw_college_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_college_medicine.yaml b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_college_medicine.yaml new file mode 100644 index 00000000..b9f4cc6c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_college_medicine.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sw_template_yaml +process_docs: !function utils.process_college_medicine +tag: global_mmlu_full_sw_other_tasks +task: global_mmlu_full_sw_college_medicine diff --git a/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_college_physics.yaml b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_college_physics.yaml new file mode 100644 index 00000000..bcca5b3f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_college_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sw_template_yaml +process_docs: !function utils.process_college_physics +tag: global_mmlu_full_sw_stem_tasks +task: global_mmlu_full_sw_college_physics diff --git a/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_computer_security.yaml b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_computer_security.yaml new file mode 100644 index 00000000..434d2faa --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_computer_security.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sw_template_yaml +process_docs: !function utils.process_computer_security +tag: global_mmlu_full_sw_stem_tasks +task: global_mmlu_full_sw_computer_security diff --git a/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_conceptual_physics.yaml b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_conceptual_physics.yaml new file mode 100644 index 00000000..2c1c9d41 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_conceptual_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sw_template_yaml +process_docs: !function utils.process_conceptual_physics +tag: global_mmlu_full_sw_stem_tasks +task: global_mmlu_full_sw_conceptual_physics diff --git a/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_econometrics.yaml b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_econometrics.yaml new file mode 100644 index 00000000..2a907de6 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_econometrics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sw_template_yaml +process_docs: !function utils.process_econometrics +tag: global_mmlu_full_sw_social_sciences_tasks +task: global_mmlu_full_sw_econometrics diff --git a/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_electrical_engineering.yaml b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_electrical_engineering.yaml new file mode 100644 index 00000000..1ae86a7c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_electrical_engineering.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sw_template_yaml +process_docs: !function utils.process_electrical_engineering +tag: global_mmlu_full_sw_stem_tasks +task: global_mmlu_full_sw_electrical_engineering diff --git a/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_elementary_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_elementary_mathematics.yaml new file mode 100644 index 00000000..05871f25 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_elementary_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sw_template_yaml +process_docs: !function utils.process_elementary_mathematics +tag: global_mmlu_full_sw_stem_tasks +task: global_mmlu_full_sw_elementary_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_formal_logic.yaml b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_formal_logic.yaml new file mode 100644 index 00000000..8d0de407 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_formal_logic.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sw_template_yaml +process_docs: !function utils.process_formal_logic +tag: global_mmlu_full_sw_humanities_tasks +task: global_mmlu_full_sw_formal_logic diff --git a/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_global_facts.yaml b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_global_facts.yaml new file mode 100644 index 00000000..29bec055 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_global_facts.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sw_template_yaml +process_docs: !function utils.process_global_facts +tag: global_mmlu_full_sw_other_tasks +task: global_mmlu_full_sw_global_facts diff --git a/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_high_school_biology.yaml b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_high_school_biology.yaml new file mode 100644 index 00000000..2e49866a --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_high_school_biology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sw_template_yaml +process_docs: !function utils.process_high_school_biology +tag: global_mmlu_full_sw_stem_tasks +task: global_mmlu_full_sw_high_school_biology diff --git a/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_high_school_chemistry.yaml b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_high_school_chemistry.yaml new file mode 100644 index 00000000..a7adbd97 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_high_school_chemistry.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sw_template_yaml +process_docs: !function utils.process_high_school_chemistry +tag: global_mmlu_full_sw_stem_tasks +task: global_mmlu_full_sw_high_school_chemistry diff --git a/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_high_school_computer_science.yaml b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_high_school_computer_science.yaml new file mode 100644 index 00000000..2e65ab5a --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_high_school_computer_science.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sw_template_yaml +process_docs: !function utils.process_high_school_computer_science +tag: global_mmlu_full_sw_stem_tasks +task: global_mmlu_full_sw_high_school_computer_science diff --git a/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_high_school_european_history.yaml b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_high_school_european_history.yaml new file mode 100644 index 00000000..7352ad72 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_high_school_european_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sw_template_yaml +process_docs: !function utils.process_high_school_european_history +tag: global_mmlu_full_sw_humanities_tasks +task: global_mmlu_full_sw_high_school_european_history diff --git a/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_high_school_geography.yaml b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_high_school_geography.yaml new file mode 100644 index 00000000..797932ba --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_high_school_geography.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sw_template_yaml +process_docs: !function utils.process_high_school_geography +tag: global_mmlu_full_sw_social_sciences_tasks +task: global_mmlu_full_sw_high_school_geography diff --git a/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_high_school_government_and_politics.yaml b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_high_school_government_and_politics.yaml new file mode 100644 index 00000000..602d71ff --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_high_school_government_and_politics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sw_template_yaml +process_docs: !function utils.process_high_school_government_and_politics +tag: global_mmlu_full_sw_social_sciences_tasks +task: global_mmlu_full_sw_high_school_government_and_politics diff --git a/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_high_school_macroeconomics.yaml b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_high_school_macroeconomics.yaml new file mode 100644 index 00000000..a91dd829 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_high_school_macroeconomics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sw_template_yaml +process_docs: !function utils.process_high_school_macroeconomics +tag: global_mmlu_full_sw_social_sciences_tasks +task: global_mmlu_full_sw_high_school_macroeconomics diff --git a/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_high_school_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_high_school_mathematics.yaml new file mode 100644 index 00000000..c19b28da --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_high_school_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sw_template_yaml +process_docs: !function utils.process_high_school_mathematics +tag: global_mmlu_full_sw_stem_tasks +task: global_mmlu_full_sw_high_school_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_high_school_microeconomics.yaml b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_high_school_microeconomics.yaml new file mode 100644 index 00000000..7a9c63bd --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_high_school_microeconomics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sw_template_yaml +process_docs: !function utils.process_high_school_microeconomics +tag: global_mmlu_full_sw_social_sciences_tasks +task: global_mmlu_full_sw_high_school_microeconomics diff --git a/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_high_school_physics.yaml b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_high_school_physics.yaml new file mode 100644 index 00000000..239eac65 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_high_school_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sw_template_yaml +process_docs: !function utils.process_high_school_physics +tag: global_mmlu_full_sw_stem_tasks +task: global_mmlu_full_sw_high_school_physics diff --git a/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_high_school_psychology.yaml b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_high_school_psychology.yaml new file mode 100644 index 00000000..b4f19d84 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_high_school_psychology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sw_template_yaml +process_docs: !function utils.process_high_school_psychology +tag: global_mmlu_full_sw_social_sciences_tasks +task: global_mmlu_full_sw_high_school_psychology diff --git a/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_high_school_statistics.yaml b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_high_school_statistics.yaml new file mode 100644 index 00000000..5725af63 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_high_school_statistics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sw_template_yaml +process_docs: !function utils.process_high_school_statistics +tag: global_mmlu_full_sw_stem_tasks +task: global_mmlu_full_sw_high_school_statistics diff --git a/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_high_school_us_history.yaml b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_high_school_us_history.yaml new file mode 100644 index 00000000..1d080340 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_high_school_us_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sw_template_yaml +process_docs: !function utils.process_high_school_us_history +tag: global_mmlu_full_sw_humanities_tasks +task: global_mmlu_full_sw_high_school_us_history diff --git a/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_high_school_world_history.yaml b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_high_school_world_history.yaml new file mode 100644 index 00000000..cfe5a9e7 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_high_school_world_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sw_template_yaml +process_docs: !function utils.process_high_school_world_history +tag: global_mmlu_full_sw_humanities_tasks +task: global_mmlu_full_sw_high_school_world_history diff --git a/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_human_aging.yaml b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_human_aging.yaml new file mode 100644 index 00000000..ba20e932 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_human_aging.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sw_template_yaml +process_docs: !function utils.process_human_aging +tag: global_mmlu_full_sw_other_tasks +task: global_mmlu_full_sw_human_aging diff --git a/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_human_sexuality.yaml b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_human_sexuality.yaml new file mode 100644 index 00000000..4609bea0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_human_sexuality.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sw_template_yaml +process_docs: !function utils.process_human_sexuality +tag: global_mmlu_full_sw_social_sciences_tasks +task: global_mmlu_full_sw_human_sexuality diff --git a/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_international_law.yaml b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_international_law.yaml new file mode 100644 index 00000000..bbf616b1 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_international_law.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sw_template_yaml +process_docs: !function utils.process_international_law +tag: global_mmlu_full_sw_humanities_tasks +task: global_mmlu_full_sw_international_law diff --git a/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_jurisprudence.yaml b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_jurisprudence.yaml new file mode 100644 index 00000000..6781f2d5 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_jurisprudence.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sw_template_yaml +process_docs: !function utils.process_jurisprudence +tag: global_mmlu_full_sw_humanities_tasks +task: global_mmlu_full_sw_jurisprudence diff --git a/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_logical_fallacies.yaml b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_logical_fallacies.yaml new file mode 100644 index 00000000..1f862917 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_logical_fallacies.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sw_template_yaml +process_docs: !function utils.process_logical_fallacies +tag: global_mmlu_full_sw_humanities_tasks +task: global_mmlu_full_sw_logical_fallacies diff --git a/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_machine_learning.yaml b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_machine_learning.yaml new file mode 100644 index 00000000..9eb51cfb --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_machine_learning.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sw_template_yaml +process_docs: !function utils.process_machine_learning +tag: global_mmlu_full_sw_stem_tasks +task: global_mmlu_full_sw_machine_learning diff --git a/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_management.yaml b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_management.yaml new file mode 100644 index 00000000..5b0e9e67 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_management.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sw_template_yaml +process_docs: !function utils.process_management +tag: global_mmlu_full_sw_other_tasks +task: global_mmlu_full_sw_management diff --git a/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_marketing.yaml b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_marketing.yaml new file mode 100644 index 00000000..fb65e87e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_marketing.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sw_template_yaml +process_docs: !function utils.process_marketing +tag: global_mmlu_full_sw_other_tasks +task: global_mmlu_full_sw_marketing diff --git a/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_medical_genetics.yaml b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_medical_genetics.yaml new file mode 100644 index 00000000..10d4db0d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_medical_genetics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sw_template_yaml +process_docs: !function utils.process_medical_genetics +tag: global_mmlu_full_sw_other_tasks +task: global_mmlu_full_sw_medical_genetics diff --git a/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_miscellaneous.yaml b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_miscellaneous.yaml new file mode 100644 index 00000000..b337d0ab --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_miscellaneous.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sw_template_yaml +process_docs: !function utils.process_miscellaneous +tag: global_mmlu_full_sw_other_tasks +task: global_mmlu_full_sw_miscellaneous diff --git a/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_moral_disputes.yaml b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_moral_disputes.yaml new file mode 100644 index 00000000..f44bfa0d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_moral_disputes.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sw_template_yaml +process_docs: !function utils.process_moral_disputes +tag: global_mmlu_full_sw_humanities_tasks +task: global_mmlu_full_sw_moral_disputes diff --git a/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_moral_scenarios.yaml b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_moral_scenarios.yaml new file mode 100644 index 00000000..eabd5a91 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_moral_scenarios.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sw_template_yaml +process_docs: !function utils.process_moral_scenarios +tag: global_mmlu_full_sw_humanities_tasks +task: global_mmlu_full_sw_moral_scenarios diff --git a/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_nutrition.yaml b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_nutrition.yaml new file mode 100644 index 00000000..41c64458 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_nutrition.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sw_template_yaml +process_docs: !function utils.process_nutrition +tag: global_mmlu_full_sw_other_tasks +task: global_mmlu_full_sw_nutrition diff --git a/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_philosophy.yaml b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_philosophy.yaml new file mode 100644 index 00000000..96edac99 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_philosophy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sw_template_yaml +process_docs: !function utils.process_philosophy +tag: global_mmlu_full_sw_humanities_tasks +task: global_mmlu_full_sw_philosophy diff --git a/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_prehistory.yaml b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_prehistory.yaml new file mode 100644 index 00000000..db94a2ff --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_prehistory.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sw_template_yaml +process_docs: !function utils.process_prehistory +tag: global_mmlu_full_sw_humanities_tasks +task: global_mmlu_full_sw_prehistory diff --git a/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_professional_accounting.yaml b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_professional_accounting.yaml new file mode 100644 index 00000000..7cd19d35 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_professional_accounting.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sw_template_yaml +process_docs: !function utils.process_professional_accounting +tag: global_mmlu_full_sw_other_tasks +task: global_mmlu_full_sw_professional_accounting diff --git a/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_professional_law.yaml b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_professional_law.yaml new file mode 100644 index 00000000..9434ae4c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_professional_law.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sw_template_yaml +process_docs: !function utils.process_professional_law +tag: global_mmlu_full_sw_humanities_tasks +task: global_mmlu_full_sw_professional_law diff --git a/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_professional_medicine.yaml b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_professional_medicine.yaml new file mode 100644 index 00000000..cf35b9c6 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_professional_medicine.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sw_template_yaml +process_docs: !function utils.process_professional_medicine +tag: global_mmlu_full_sw_other_tasks +task: global_mmlu_full_sw_professional_medicine diff --git a/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_professional_psychology.yaml b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_professional_psychology.yaml new file mode 100644 index 00000000..7570e288 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_professional_psychology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sw_template_yaml +process_docs: !function utils.process_professional_psychology +tag: global_mmlu_full_sw_social_sciences_tasks +task: global_mmlu_full_sw_professional_psychology diff --git a/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_public_relations.yaml b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_public_relations.yaml new file mode 100644 index 00000000..54c094db --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_public_relations.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sw_template_yaml +process_docs: !function utils.process_public_relations +tag: global_mmlu_full_sw_social_sciences_tasks +task: global_mmlu_full_sw_public_relations diff --git a/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_security_studies.yaml b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_security_studies.yaml new file mode 100644 index 00000000..c8d5a42c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_security_studies.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sw_template_yaml +process_docs: !function utils.process_security_studies +tag: global_mmlu_full_sw_social_sciences_tasks +task: global_mmlu_full_sw_security_studies diff --git a/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_sociology.yaml b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_sociology.yaml new file mode 100644 index 00000000..79d51a58 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_sociology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sw_template_yaml +process_docs: !function utils.process_sociology +tag: global_mmlu_full_sw_social_sciences_tasks +task: global_mmlu_full_sw_sociology diff --git a/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_us_foreign_policy.yaml b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_us_foreign_policy.yaml new file mode 100644 index 00000000..523b1572 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_us_foreign_policy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sw_template_yaml +process_docs: !function utils.process_us_foreign_policy +tag: global_mmlu_full_sw_social_sciences_tasks +task: global_mmlu_full_sw_us_foreign_policy diff --git a/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_virology.yaml b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_virology.yaml new file mode 100644 index 00000000..43179ff8 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_virology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sw_template_yaml +process_docs: !function utils.process_virology +tag: global_mmlu_full_sw_other_tasks +task: global_mmlu_full_sw_virology diff --git a/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_world_religions.yaml b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_world_religions.yaml new file mode 100644 index 00000000..bef7b7f8 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sw/global_mmlu_full_sw_world_religions.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _sw_template_yaml +process_docs: !function utils.process_world_religions +tag: global_mmlu_full_sw_humanities_tasks +task: global_mmlu_full_sw_world_religions diff --git a/lm_eval/tasks/global_mmlu/full/sw/utils.py b/lm_eval/tasks/global_mmlu/full/sw/utils.py new file mode 100644 index 00000000..7df72cb0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/sw/utils.py @@ -0,0 +1,73 @@ +from functools import partial + + +SUBJECTS = [ + "abstract_algebra", + "anatomy", + "astronomy", + "business_ethics", + "clinical_knowledge", + "college_biology", + "college_chemistry", + "college_computer_science", + "college_mathematics", + "college_medicine", + "college_physics", + "computer_security", + "conceptual_physics", + "econometrics", + "electrical_engineering", + "elementary_mathematics", + "formal_logic", + "global_facts", + "high_school_biology", + "high_school_chemistry", + "high_school_computer_science", + "high_school_european_history", + "high_school_geography", + "high_school_government_and_politics", + "high_school_macroeconomics", + "high_school_mathematics", + "high_school_microeconomics", + "high_school_physics", + "high_school_psychology", + "high_school_statistics", + "high_school_us_history", + "high_school_world_history", + "human_aging", + "human_sexuality", + "international_law", + "jurisprudence", + "logical_fallacies", + "machine_learning", + "management", + "marketing", + "medical_genetics", + "miscellaneous", + "moral_disputes", + "moral_scenarios", + "nutrition", + "philosophy", + "prehistory", + "professional_accounting", + "professional_law", + "professional_medicine", + "professional_psychology", + "public_relations", + "security_studies", + "sociology", + "us_foreign_policy", + "virology", + "world_religions", +] + + +def process_docs(dataset, subject): + return dataset.filter(lambda x: x["subject"] == subject) + + +process_functions = { + f"process_{subject}": partial(process_docs, subject=subject) for subject in SUBJECTS +} + +globals().update(process_functions) diff --git a/lm_eval/tasks/global_mmlu/full/te/_global_mmlu_full_te.yaml b/lm_eval/tasks/global_mmlu/full/te/_global_mmlu_full_te.yaml new file mode 100644 index 00000000..5ef0f7ab --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/te/_global_mmlu_full_te.yaml @@ -0,0 +1,11 @@ +group: global_mmlu_full_te +task: + - global_mmlu_full_te_stem + - global_mmlu_full_te_other + - global_mmlu_full_te_social_sciences + - global_mmlu_full_te_humanities +aggregate_metric_list: + - metric: acc + weight_by_size: True +metadata: + version: 1.0 diff --git a/lm_eval/tasks/global_mmlu/full/te/_global_mmlu_full_te_humanities.yaml b/lm_eval/tasks/global_mmlu/full/te/_global_mmlu_full_te_humanities.yaml new file mode 100644 index 00000000..7a3c479e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/te/_global_mmlu_full_te_humanities.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_te_humanities +task: + - global_mmlu_full_te_humanities_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/te/_global_mmlu_full_te_other.yaml b/lm_eval/tasks/global_mmlu/full/te/_global_mmlu_full_te_other.yaml new file mode 100644 index 00000000..2932844a --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/te/_global_mmlu_full_te_other.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_te_other +task: + - global_mmlu_full_te_other_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/te/_global_mmlu_full_te_social_sciences.yaml b/lm_eval/tasks/global_mmlu/full/te/_global_mmlu_full_te_social_sciences.yaml new file mode 100644 index 00000000..25e721db --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/te/_global_mmlu_full_te_social_sciences.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_te_social_sciences +task: + - global_mmlu_full_te_social_sciences_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/te/_global_mmlu_full_te_stem.yaml b/lm_eval/tasks/global_mmlu/full/te/_global_mmlu_full_te_stem.yaml new file mode 100644 index 00000000..fe2426ca --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/te/_global_mmlu_full_te_stem.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_te_stem +task: + - global_mmlu_full_te_stem_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/te/_te_template_yaml b/lm_eval/tasks/global_mmlu/full/te/_te_template_yaml new file mode 100644 index 00000000..d7b1190d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/te/_te_template_yaml @@ -0,0 +1,16 @@ +dataset_path: CohereForAI/Global-MMLU +dataset_name: te +test_split: test +fewshot_split: dev +fewshot_config: + sampler: first_n +output_type: multiple_choice +doc_to_text: "{{question.strip()}}\nA. {{option_a}}\nB. {{option_b}}\nC. {{option_c}}\nD. {{option_d}}\nAnswer:" +doc_to_choice: ["A", "B", "C", "D"] +doc_to_target: answer +metric_list: + - metric: acc + aggregation: mean + higher_is_better: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_abstract_algebra.yaml b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_abstract_algebra.yaml new file mode 100644 index 00000000..e922fd08 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_abstract_algebra.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _te_template_yaml +process_docs: !function utils.process_abstract_algebra +tag: global_mmlu_full_te_stem_tasks +task: global_mmlu_full_te_abstract_algebra diff --git a/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_anatomy.yaml b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_anatomy.yaml new file mode 100644 index 00000000..00582018 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_anatomy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _te_template_yaml +process_docs: !function utils.process_anatomy +tag: global_mmlu_full_te_stem_tasks +task: global_mmlu_full_te_anatomy diff --git a/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_astronomy.yaml b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_astronomy.yaml new file mode 100644 index 00000000..5bc5e76e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_astronomy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _te_template_yaml +process_docs: !function utils.process_astronomy +tag: global_mmlu_full_te_stem_tasks +task: global_mmlu_full_te_astronomy diff --git a/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_business_ethics.yaml b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_business_ethics.yaml new file mode 100644 index 00000000..7b440102 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_business_ethics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _te_template_yaml +process_docs: !function utils.process_business_ethics +tag: global_mmlu_full_te_other_tasks +task: global_mmlu_full_te_business_ethics diff --git a/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_clinical_knowledge.yaml b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_clinical_knowledge.yaml new file mode 100644 index 00000000..90e56184 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_clinical_knowledge.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _te_template_yaml +process_docs: !function utils.process_clinical_knowledge +tag: global_mmlu_full_te_other_tasks +task: global_mmlu_full_te_clinical_knowledge diff --git a/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_college_biology.yaml b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_college_biology.yaml new file mode 100644 index 00000000..0f036e60 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_college_biology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _te_template_yaml +process_docs: !function utils.process_college_biology +tag: global_mmlu_full_te_stem_tasks +task: global_mmlu_full_te_college_biology diff --git a/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_college_chemistry.yaml b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_college_chemistry.yaml new file mode 100644 index 00000000..ccdb849a --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_college_chemistry.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _te_template_yaml +process_docs: !function utils.process_college_chemistry +tag: global_mmlu_full_te_stem_tasks +task: global_mmlu_full_te_college_chemistry diff --git a/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_college_computer_science.yaml b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_college_computer_science.yaml new file mode 100644 index 00000000..f11e5657 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_college_computer_science.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _te_template_yaml +process_docs: !function utils.process_college_computer_science +tag: global_mmlu_full_te_stem_tasks +task: global_mmlu_full_te_college_computer_science diff --git a/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_college_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_college_mathematics.yaml new file mode 100644 index 00000000..c5022ce2 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_college_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _te_template_yaml +process_docs: !function utils.process_college_mathematics +tag: global_mmlu_full_te_stem_tasks +task: global_mmlu_full_te_college_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_college_medicine.yaml b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_college_medicine.yaml new file mode 100644 index 00000000..bd5219f0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_college_medicine.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _te_template_yaml +process_docs: !function utils.process_college_medicine +tag: global_mmlu_full_te_other_tasks +task: global_mmlu_full_te_college_medicine diff --git a/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_college_physics.yaml b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_college_physics.yaml new file mode 100644 index 00000000..88dad05a --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_college_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _te_template_yaml +process_docs: !function utils.process_college_physics +tag: global_mmlu_full_te_stem_tasks +task: global_mmlu_full_te_college_physics diff --git a/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_computer_security.yaml b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_computer_security.yaml new file mode 100644 index 00000000..0e8f37fc --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_computer_security.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _te_template_yaml +process_docs: !function utils.process_computer_security +tag: global_mmlu_full_te_stem_tasks +task: global_mmlu_full_te_computer_security diff --git a/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_conceptual_physics.yaml b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_conceptual_physics.yaml new file mode 100644 index 00000000..f0527625 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_conceptual_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _te_template_yaml +process_docs: !function utils.process_conceptual_physics +tag: global_mmlu_full_te_stem_tasks +task: global_mmlu_full_te_conceptual_physics diff --git a/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_econometrics.yaml b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_econometrics.yaml new file mode 100644 index 00000000..cf008a67 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_econometrics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _te_template_yaml +process_docs: !function utils.process_econometrics +tag: global_mmlu_full_te_social_sciences_tasks +task: global_mmlu_full_te_econometrics diff --git a/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_electrical_engineering.yaml b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_electrical_engineering.yaml new file mode 100644 index 00000000..97169e93 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_electrical_engineering.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _te_template_yaml +process_docs: !function utils.process_electrical_engineering +tag: global_mmlu_full_te_stem_tasks +task: global_mmlu_full_te_electrical_engineering diff --git a/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_elementary_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_elementary_mathematics.yaml new file mode 100644 index 00000000..f3edc896 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_elementary_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _te_template_yaml +process_docs: !function utils.process_elementary_mathematics +tag: global_mmlu_full_te_stem_tasks +task: global_mmlu_full_te_elementary_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_formal_logic.yaml b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_formal_logic.yaml new file mode 100644 index 00000000..d4c182d1 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_formal_logic.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _te_template_yaml +process_docs: !function utils.process_formal_logic +tag: global_mmlu_full_te_humanities_tasks +task: global_mmlu_full_te_formal_logic diff --git a/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_global_facts.yaml b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_global_facts.yaml new file mode 100644 index 00000000..53b52f4d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_global_facts.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _te_template_yaml +process_docs: !function utils.process_global_facts +tag: global_mmlu_full_te_other_tasks +task: global_mmlu_full_te_global_facts diff --git a/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_high_school_biology.yaml b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_high_school_biology.yaml new file mode 100644 index 00000000..5f02170f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_high_school_biology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _te_template_yaml +process_docs: !function utils.process_high_school_biology +tag: global_mmlu_full_te_stem_tasks +task: global_mmlu_full_te_high_school_biology diff --git a/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_high_school_chemistry.yaml b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_high_school_chemistry.yaml new file mode 100644 index 00000000..c77d30aa --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_high_school_chemistry.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _te_template_yaml +process_docs: !function utils.process_high_school_chemistry +tag: global_mmlu_full_te_stem_tasks +task: global_mmlu_full_te_high_school_chemistry diff --git a/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_high_school_computer_science.yaml b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_high_school_computer_science.yaml new file mode 100644 index 00000000..7f388a06 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_high_school_computer_science.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _te_template_yaml +process_docs: !function utils.process_high_school_computer_science +tag: global_mmlu_full_te_stem_tasks +task: global_mmlu_full_te_high_school_computer_science diff --git a/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_high_school_european_history.yaml b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_high_school_european_history.yaml new file mode 100644 index 00000000..75d54d72 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_high_school_european_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _te_template_yaml +process_docs: !function utils.process_high_school_european_history +tag: global_mmlu_full_te_humanities_tasks +task: global_mmlu_full_te_high_school_european_history diff --git a/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_high_school_geography.yaml b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_high_school_geography.yaml new file mode 100644 index 00000000..383596ff --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_high_school_geography.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _te_template_yaml +process_docs: !function utils.process_high_school_geography +tag: global_mmlu_full_te_social_sciences_tasks +task: global_mmlu_full_te_high_school_geography diff --git a/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_high_school_government_and_politics.yaml b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_high_school_government_and_politics.yaml new file mode 100644 index 00000000..8db56a85 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_high_school_government_and_politics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _te_template_yaml +process_docs: !function utils.process_high_school_government_and_politics +tag: global_mmlu_full_te_social_sciences_tasks +task: global_mmlu_full_te_high_school_government_and_politics diff --git a/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_high_school_macroeconomics.yaml b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_high_school_macroeconomics.yaml new file mode 100644 index 00000000..bd471b8d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_high_school_macroeconomics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _te_template_yaml +process_docs: !function utils.process_high_school_macroeconomics +tag: global_mmlu_full_te_social_sciences_tasks +task: global_mmlu_full_te_high_school_macroeconomics diff --git a/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_high_school_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_high_school_mathematics.yaml new file mode 100644 index 00000000..58f577ed --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_high_school_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _te_template_yaml +process_docs: !function utils.process_high_school_mathematics +tag: global_mmlu_full_te_stem_tasks +task: global_mmlu_full_te_high_school_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_high_school_microeconomics.yaml b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_high_school_microeconomics.yaml new file mode 100644 index 00000000..400a3805 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_high_school_microeconomics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _te_template_yaml +process_docs: !function utils.process_high_school_microeconomics +tag: global_mmlu_full_te_social_sciences_tasks +task: global_mmlu_full_te_high_school_microeconomics diff --git a/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_high_school_physics.yaml b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_high_school_physics.yaml new file mode 100644 index 00000000..694ddc30 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_high_school_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _te_template_yaml +process_docs: !function utils.process_high_school_physics +tag: global_mmlu_full_te_stem_tasks +task: global_mmlu_full_te_high_school_physics diff --git a/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_high_school_psychology.yaml b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_high_school_psychology.yaml new file mode 100644 index 00000000..b900af19 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_high_school_psychology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _te_template_yaml +process_docs: !function utils.process_high_school_psychology +tag: global_mmlu_full_te_social_sciences_tasks +task: global_mmlu_full_te_high_school_psychology diff --git a/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_high_school_statistics.yaml b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_high_school_statistics.yaml new file mode 100644 index 00000000..3492e724 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_high_school_statistics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _te_template_yaml +process_docs: !function utils.process_high_school_statistics +tag: global_mmlu_full_te_stem_tasks +task: global_mmlu_full_te_high_school_statistics diff --git a/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_high_school_us_history.yaml b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_high_school_us_history.yaml new file mode 100644 index 00000000..48a2d75a --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_high_school_us_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _te_template_yaml +process_docs: !function utils.process_high_school_us_history +tag: global_mmlu_full_te_humanities_tasks +task: global_mmlu_full_te_high_school_us_history diff --git a/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_high_school_world_history.yaml b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_high_school_world_history.yaml new file mode 100644 index 00000000..7e95f7ea --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_high_school_world_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _te_template_yaml +process_docs: !function utils.process_high_school_world_history +tag: global_mmlu_full_te_humanities_tasks +task: global_mmlu_full_te_high_school_world_history diff --git a/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_human_aging.yaml b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_human_aging.yaml new file mode 100644 index 00000000..dc44c1b0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_human_aging.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _te_template_yaml +process_docs: !function utils.process_human_aging +tag: global_mmlu_full_te_other_tasks +task: global_mmlu_full_te_human_aging diff --git a/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_human_sexuality.yaml b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_human_sexuality.yaml new file mode 100644 index 00000000..d7631419 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_human_sexuality.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _te_template_yaml +process_docs: !function utils.process_human_sexuality +tag: global_mmlu_full_te_social_sciences_tasks +task: global_mmlu_full_te_human_sexuality diff --git a/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_international_law.yaml b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_international_law.yaml new file mode 100644 index 00000000..0c2c7862 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_international_law.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _te_template_yaml +process_docs: !function utils.process_international_law +tag: global_mmlu_full_te_humanities_tasks +task: global_mmlu_full_te_international_law diff --git a/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_jurisprudence.yaml b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_jurisprudence.yaml new file mode 100644 index 00000000..718cd9fa --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_jurisprudence.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _te_template_yaml +process_docs: !function utils.process_jurisprudence +tag: global_mmlu_full_te_humanities_tasks +task: global_mmlu_full_te_jurisprudence diff --git a/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_logical_fallacies.yaml b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_logical_fallacies.yaml new file mode 100644 index 00000000..7bb9170c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_logical_fallacies.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _te_template_yaml +process_docs: !function utils.process_logical_fallacies +tag: global_mmlu_full_te_humanities_tasks +task: global_mmlu_full_te_logical_fallacies diff --git a/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_machine_learning.yaml b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_machine_learning.yaml new file mode 100644 index 00000000..12355538 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_machine_learning.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _te_template_yaml +process_docs: !function utils.process_machine_learning +tag: global_mmlu_full_te_stem_tasks +task: global_mmlu_full_te_machine_learning diff --git a/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_management.yaml b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_management.yaml new file mode 100644 index 00000000..f092416f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_management.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _te_template_yaml +process_docs: !function utils.process_management +tag: global_mmlu_full_te_other_tasks +task: global_mmlu_full_te_management diff --git a/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_marketing.yaml b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_marketing.yaml new file mode 100644 index 00000000..15b84b46 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_marketing.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _te_template_yaml +process_docs: !function utils.process_marketing +tag: global_mmlu_full_te_other_tasks +task: global_mmlu_full_te_marketing diff --git a/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_medical_genetics.yaml b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_medical_genetics.yaml new file mode 100644 index 00000000..8f0730be --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_medical_genetics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _te_template_yaml +process_docs: !function utils.process_medical_genetics +tag: global_mmlu_full_te_other_tasks +task: global_mmlu_full_te_medical_genetics diff --git a/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_miscellaneous.yaml b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_miscellaneous.yaml new file mode 100644 index 00000000..53487f55 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_miscellaneous.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _te_template_yaml +process_docs: !function utils.process_miscellaneous +tag: global_mmlu_full_te_other_tasks +task: global_mmlu_full_te_miscellaneous diff --git a/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_moral_disputes.yaml b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_moral_disputes.yaml new file mode 100644 index 00000000..fca8df9b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_moral_disputes.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _te_template_yaml +process_docs: !function utils.process_moral_disputes +tag: global_mmlu_full_te_humanities_tasks +task: global_mmlu_full_te_moral_disputes diff --git a/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_moral_scenarios.yaml b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_moral_scenarios.yaml new file mode 100644 index 00000000..d87f6b02 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_moral_scenarios.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _te_template_yaml +process_docs: !function utils.process_moral_scenarios +tag: global_mmlu_full_te_humanities_tasks +task: global_mmlu_full_te_moral_scenarios diff --git a/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_nutrition.yaml b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_nutrition.yaml new file mode 100644 index 00000000..9348a76e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_nutrition.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _te_template_yaml +process_docs: !function utils.process_nutrition +tag: global_mmlu_full_te_other_tasks +task: global_mmlu_full_te_nutrition diff --git a/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_philosophy.yaml b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_philosophy.yaml new file mode 100644 index 00000000..c8efe8d9 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_philosophy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _te_template_yaml +process_docs: !function utils.process_philosophy +tag: global_mmlu_full_te_humanities_tasks +task: global_mmlu_full_te_philosophy diff --git a/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_prehistory.yaml b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_prehistory.yaml new file mode 100644 index 00000000..b702542e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_prehistory.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _te_template_yaml +process_docs: !function utils.process_prehistory +tag: global_mmlu_full_te_humanities_tasks +task: global_mmlu_full_te_prehistory diff --git a/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_professional_accounting.yaml b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_professional_accounting.yaml new file mode 100644 index 00000000..045b6e1c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_professional_accounting.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _te_template_yaml +process_docs: !function utils.process_professional_accounting +tag: global_mmlu_full_te_other_tasks +task: global_mmlu_full_te_professional_accounting diff --git a/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_professional_law.yaml b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_professional_law.yaml new file mode 100644 index 00000000..5e5fa308 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_professional_law.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _te_template_yaml +process_docs: !function utils.process_professional_law +tag: global_mmlu_full_te_humanities_tasks +task: global_mmlu_full_te_professional_law diff --git a/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_professional_medicine.yaml b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_professional_medicine.yaml new file mode 100644 index 00000000..d4ede33f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_professional_medicine.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _te_template_yaml +process_docs: !function utils.process_professional_medicine +tag: global_mmlu_full_te_other_tasks +task: global_mmlu_full_te_professional_medicine diff --git a/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_professional_psychology.yaml b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_professional_psychology.yaml new file mode 100644 index 00000000..cb1906d4 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_professional_psychology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _te_template_yaml +process_docs: !function utils.process_professional_psychology +tag: global_mmlu_full_te_social_sciences_tasks +task: global_mmlu_full_te_professional_psychology diff --git a/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_public_relations.yaml b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_public_relations.yaml new file mode 100644 index 00000000..1ac09ce0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_public_relations.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _te_template_yaml +process_docs: !function utils.process_public_relations +tag: global_mmlu_full_te_social_sciences_tasks +task: global_mmlu_full_te_public_relations diff --git a/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_security_studies.yaml b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_security_studies.yaml new file mode 100644 index 00000000..bbb7bc7c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_security_studies.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _te_template_yaml +process_docs: !function utils.process_security_studies +tag: global_mmlu_full_te_social_sciences_tasks +task: global_mmlu_full_te_security_studies diff --git a/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_sociology.yaml b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_sociology.yaml new file mode 100644 index 00000000..e080e082 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_sociology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _te_template_yaml +process_docs: !function utils.process_sociology +tag: global_mmlu_full_te_social_sciences_tasks +task: global_mmlu_full_te_sociology diff --git a/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_us_foreign_policy.yaml b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_us_foreign_policy.yaml new file mode 100644 index 00000000..338f0809 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_us_foreign_policy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _te_template_yaml +process_docs: !function utils.process_us_foreign_policy +tag: global_mmlu_full_te_social_sciences_tasks +task: global_mmlu_full_te_us_foreign_policy diff --git a/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_virology.yaml b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_virology.yaml new file mode 100644 index 00000000..1f5e38a9 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_virology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _te_template_yaml +process_docs: !function utils.process_virology +tag: global_mmlu_full_te_other_tasks +task: global_mmlu_full_te_virology diff --git a/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_world_religions.yaml b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_world_religions.yaml new file mode 100644 index 00000000..4da26e3e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/te/global_mmlu_full_te_world_religions.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _te_template_yaml +process_docs: !function utils.process_world_religions +tag: global_mmlu_full_te_humanities_tasks +task: global_mmlu_full_te_world_religions diff --git a/lm_eval/tasks/global_mmlu/full/te/utils.py b/lm_eval/tasks/global_mmlu/full/te/utils.py new file mode 100644 index 00000000..7df72cb0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/te/utils.py @@ -0,0 +1,73 @@ +from functools import partial + + +SUBJECTS = [ + "abstract_algebra", + "anatomy", + "astronomy", + "business_ethics", + "clinical_knowledge", + "college_biology", + "college_chemistry", + "college_computer_science", + "college_mathematics", + "college_medicine", + "college_physics", + "computer_security", + "conceptual_physics", + "econometrics", + "electrical_engineering", + "elementary_mathematics", + "formal_logic", + "global_facts", + "high_school_biology", + "high_school_chemistry", + "high_school_computer_science", + "high_school_european_history", + "high_school_geography", + "high_school_government_and_politics", + "high_school_macroeconomics", + "high_school_mathematics", + "high_school_microeconomics", + "high_school_physics", + "high_school_psychology", + "high_school_statistics", + "high_school_us_history", + "high_school_world_history", + "human_aging", + "human_sexuality", + "international_law", + "jurisprudence", + "logical_fallacies", + "machine_learning", + "management", + "marketing", + "medical_genetics", + "miscellaneous", + "moral_disputes", + "moral_scenarios", + "nutrition", + "philosophy", + "prehistory", + "professional_accounting", + "professional_law", + "professional_medicine", + "professional_psychology", + "public_relations", + "security_studies", + "sociology", + "us_foreign_policy", + "virology", + "world_religions", +] + + +def process_docs(dataset, subject): + return dataset.filter(lambda x: x["subject"] == subject) + + +process_functions = { + f"process_{subject}": partial(process_docs, subject=subject) for subject in SUBJECTS +} + +globals().update(process_functions) diff --git a/lm_eval/tasks/global_mmlu/full/tr/_global_mmlu_full_tr.yaml b/lm_eval/tasks/global_mmlu/full/tr/_global_mmlu_full_tr.yaml new file mode 100644 index 00000000..8cd3d3f3 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/tr/_global_mmlu_full_tr.yaml @@ -0,0 +1,11 @@ +group: global_mmlu_full_tr +task: + - global_mmlu_full_tr_stem + - global_mmlu_full_tr_other + - global_mmlu_full_tr_social_sciences + - global_mmlu_full_tr_humanities +aggregate_metric_list: + - metric: acc + weight_by_size: True +metadata: + version: 1.0 diff --git a/lm_eval/tasks/global_mmlu/full/tr/_global_mmlu_full_tr_humanities.yaml b/lm_eval/tasks/global_mmlu/full/tr/_global_mmlu_full_tr_humanities.yaml new file mode 100644 index 00000000..f4dade15 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/tr/_global_mmlu_full_tr_humanities.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_tr_humanities +task: + - global_mmlu_full_tr_humanities_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/tr/_global_mmlu_full_tr_other.yaml b/lm_eval/tasks/global_mmlu/full/tr/_global_mmlu_full_tr_other.yaml new file mode 100644 index 00000000..e80a5b9d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/tr/_global_mmlu_full_tr_other.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_tr_other +task: + - global_mmlu_full_tr_other_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/tr/_global_mmlu_full_tr_social_sciences.yaml b/lm_eval/tasks/global_mmlu/full/tr/_global_mmlu_full_tr_social_sciences.yaml new file mode 100644 index 00000000..56fc20e1 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/tr/_global_mmlu_full_tr_social_sciences.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_tr_social_sciences +task: + - global_mmlu_full_tr_social_sciences_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/tr/_global_mmlu_full_tr_stem.yaml b/lm_eval/tasks/global_mmlu/full/tr/_global_mmlu_full_tr_stem.yaml new file mode 100644 index 00000000..51f9bb3d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/tr/_global_mmlu_full_tr_stem.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_tr_stem +task: + - global_mmlu_full_tr_stem_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/tr/_tr_template_yaml b/lm_eval/tasks/global_mmlu/full/tr/_tr_template_yaml new file mode 100644 index 00000000..e322bee6 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/tr/_tr_template_yaml @@ -0,0 +1,16 @@ +dataset_path: CohereForAI/Global-MMLU +dataset_name: tr +test_split: test +fewshot_split: dev +fewshot_config: + sampler: first_n +output_type: multiple_choice +doc_to_text: "{{question.strip()}}\nA. {{option_a}}\nB. {{option_b}}\nC. {{option_c}}\nD. {{option_d}}\nAnswer:" +doc_to_choice: ["A", "B", "C", "D"] +doc_to_target: answer +metric_list: + - metric: acc + aggregation: mean + higher_is_better: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_abstract_algebra.yaml b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_abstract_algebra.yaml new file mode 100644 index 00000000..1e821573 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_abstract_algebra.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _tr_template_yaml +process_docs: !function utils.process_abstract_algebra +tag: global_mmlu_full_tr_stem_tasks +task: global_mmlu_full_tr_abstract_algebra diff --git a/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_anatomy.yaml b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_anatomy.yaml new file mode 100644 index 00000000..44440225 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_anatomy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _tr_template_yaml +process_docs: !function utils.process_anatomy +tag: global_mmlu_full_tr_stem_tasks +task: global_mmlu_full_tr_anatomy diff --git a/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_astronomy.yaml b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_astronomy.yaml new file mode 100644 index 00000000..e85390bf --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_astronomy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _tr_template_yaml +process_docs: !function utils.process_astronomy +tag: global_mmlu_full_tr_stem_tasks +task: global_mmlu_full_tr_astronomy diff --git a/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_business_ethics.yaml b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_business_ethics.yaml new file mode 100644 index 00000000..4b1afc9c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_business_ethics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _tr_template_yaml +process_docs: !function utils.process_business_ethics +tag: global_mmlu_full_tr_other_tasks +task: global_mmlu_full_tr_business_ethics diff --git a/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_clinical_knowledge.yaml b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_clinical_knowledge.yaml new file mode 100644 index 00000000..bdfa69e6 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_clinical_knowledge.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _tr_template_yaml +process_docs: !function utils.process_clinical_knowledge +tag: global_mmlu_full_tr_other_tasks +task: global_mmlu_full_tr_clinical_knowledge diff --git a/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_college_biology.yaml b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_college_biology.yaml new file mode 100644 index 00000000..df43a67c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_college_biology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _tr_template_yaml +process_docs: !function utils.process_college_biology +tag: global_mmlu_full_tr_stem_tasks +task: global_mmlu_full_tr_college_biology diff --git a/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_college_chemistry.yaml b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_college_chemistry.yaml new file mode 100644 index 00000000..af2b8b3e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_college_chemistry.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _tr_template_yaml +process_docs: !function utils.process_college_chemistry +tag: global_mmlu_full_tr_stem_tasks +task: global_mmlu_full_tr_college_chemistry diff --git a/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_college_computer_science.yaml b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_college_computer_science.yaml new file mode 100644 index 00000000..622854f4 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_college_computer_science.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _tr_template_yaml +process_docs: !function utils.process_college_computer_science +tag: global_mmlu_full_tr_stem_tasks +task: global_mmlu_full_tr_college_computer_science diff --git a/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_college_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_college_mathematics.yaml new file mode 100644 index 00000000..902bd9c1 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_college_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _tr_template_yaml +process_docs: !function utils.process_college_mathematics +tag: global_mmlu_full_tr_stem_tasks +task: global_mmlu_full_tr_college_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_college_medicine.yaml b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_college_medicine.yaml new file mode 100644 index 00000000..6b44d0d1 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_college_medicine.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _tr_template_yaml +process_docs: !function utils.process_college_medicine +tag: global_mmlu_full_tr_other_tasks +task: global_mmlu_full_tr_college_medicine diff --git a/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_college_physics.yaml b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_college_physics.yaml new file mode 100644 index 00000000..27540d97 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_college_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _tr_template_yaml +process_docs: !function utils.process_college_physics +tag: global_mmlu_full_tr_stem_tasks +task: global_mmlu_full_tr_college_physics diff --git a/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_computer_security.yaml b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_computer_security.yaml new file mode 100644 index 00000000..dbcabeed --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_computer_security.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _tr_template_yaml +process_docs: !function utils.process_computer_security +tag: global_mmlu_full_tr_stem_tasks +task: global_mmlu_full_tr_computer_security diff --git a/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_conceptual_physics.yaml b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_conceptual_physics.yaml new file mode 100644 index 00000000..628a4fcf --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_conceptual_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _tr_template_yaml +process_docs: !function utils.process_conceptual_physics +tag: global_mmlu_full_tr_stem_tasks +task: global_mmlu_full_tr_conceptual_physics diff --git a/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_econometrics.yaml b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_econometrics.yaml new file mode 100644 index 00000000..6feb236f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_econometrics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _tr_template_yaml +process_docs: !function utils.process_econometrics +tag: global_mmlu_full_tr_social_sciences_tasks +task: global_mmlu_full_tr_econometrics diff --git a/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_electrical_engineering.yaml b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_electrical_engineering.yaml new file mode 100644 index 00000000..9a2a8665 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_electrical_engineering.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _tr_template_yaml +process_docs: !function utils.process_electrical_engineering +tag: global_mmlu_full_tr_stem_tasks +task: global_mmlu_full_tr_electrical_engineering diff --git a/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_elementary_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_elementary_mathematics.yaml new file mode 100644 index 00000000..ffc6dee7 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_elementary_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _tr_template_yaml +process_docs: !function utils.process_elementary_mathematics +tag: global_mmlu_full_tr_stem_tasks +task: global_mmlu_full_tr_elementary_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_formal_logic.yaml b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_formal_logic.yaml new file mode 100644 index 00000000..77c189a0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_formal_logic.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _tr_template_yaml +process_docs: !function utils.process_formal_logic +tag: global_mmlu_full_tr_humanities_tasks +task: global_mmlu_full_tr_formal_logic diff --git a/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_global_facts.yaml b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_global_facts.yaml new file mode 100644 index 00000000..a756d102 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_global_facts.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _tr_template_yaml +process_docs: !function utils.process_global_facts +tag: global_mmlu_full_tr_other_tasks +task: global_mmlu_full_tr_global_facts diff --git a/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_high_school_biology.yaml b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_high_school_biology.yaml new file mode 100644 index 00000000..51e7dd9e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_high_school_biology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _tr_template_yaml +process_docs: !function utils.process_high_school_biology +tag: global_mmlu_full_tr_stem_tasks +task: global_mmlu_full_tr_high_school_biology diff --git a/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_high_school_chemistry.yaml b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_high_school_chemistry.yaml new file mode 100644 index 00000000..077476ae --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_high_school_chemistry.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _tr_template_yaml +process_docs: !function utils.process_high_school_chemistry +tag: global_mmlu_full_tr_stem_tasks +task: global_mmlu_full_tr_high_school_chemistry diff --git a/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_high_school_computer_science.yaml b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_high_school_computer_science.yaml new file mode 100644 index 00000000..cb60e042 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_high_school_computer_science.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _tr_template_yaml +process_docs: !function utils.process_high_school_computer_science +tag: global_mmlu_full_tr_stem_tasks +task: global_mmlu_full_tr_high_school_computer_science diff --git a/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_high_school_european_history.yaml b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_high_school_european_history.yaml new file mode 100644 index 00000000..2b989e05 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_high_school_european_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _tr_template_yaml +process_docs: !function utils.process_high_school_european_history +tag: global_mmlu_full_tr_humanities_tasks +task: global_mmlu_full_tr_high_school_european_history diff --git a/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_high_school_geography.yaml b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_high_school_geography.yaml new file mode 100644 index 00000000..8a0c4d90 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_high_school_geography.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _tr_template_yaml +process_docs: !function utils.process_high_school_geography +tag: global_mmlu_full_tr_social_sciences_tasks +task: global_mmlu_full_tr_high_school_geography diff --git a/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_high_school_government_and_politics.yaml b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_high_school_government_and_politics.yaml new file mode 100644 index 00000000..2a585f02 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_high_school_government_and_politics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _tr_template_yaml +process_docs: !function utils.process_high_school_government_and_politics +tag: global_mmlu_full_tr_social_sciences_tasks +task: global_mmlu_full_tr_high_school_government_and_politics diff --git a/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_high_school_macroeconomics.yaml b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_high_school_macroeconomics.yaml new file mode 100644 index 00000000..f88e9831 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_high_school_macroeconomics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _tr_template_yaml +process_docs: !function utils.process_high_school_macroeconomics +tag: global_mmlu_full_tr_social_sciences_tasks +task: global_mmlu_full_tr_high_school_macroeconomics diff --git a/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_high_school_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_high_school_mathematics.yaml new file mode 100644 index 00000000..e880b0b5 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_high_school_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _tr_template_yaml +process_docs: !function utils.process_high_school_mathematics +tag: global_mmlu_full_tr_stem_tasks +task: global_mmlu_full_tr_high_school_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_high_school_microeconomics.yaml b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_high_school_microeconomics.yaml new file mode 100644 index 00000000..5527bed2 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_high_school_microeconomics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _tr_template_yaml +process_docs: !function utils.process_high_school_microeconomics +tag: global_mmlu_full_tr_social_sciences_tasks +task: global_mmlu_full_tr_high_school_microeconomics diff --git a/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_high_school_physics.yaml b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_high_school_physics.yaml new file mode 100644 index 00000000..da93a96e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_high_school_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _tr_template_yaml +process_docs: !function utils.process_high_school_physics +tag: global_mmlu_full_tr_stem_tasks +task: global_mmlu_full_tr_high_school_physics diff --git a/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_high_school_psychology.yaml b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_high_school_psychology.yaml new file mode 100644 index 00000000..a28e110c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_high_school_psychology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _tr_template_yaml +process_docs: !function utils.process_high_school_psychology +tag: global_mmlu_full_tr_social_sciences_tasks +task: global_mmlu_full_tr_high_school_psychology diff --git a/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_high_school_statistics.yaml b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_high_school_statistics.yaml new file mode 100644 index 00000000..93871dcf --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_high_school_statistics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _tr_template_yaml +process_docs: !function utils.process_high_school_statistics +tag: global_mmlu_full_tr_stem_tasks +task: global_mmlu_full_tr_high_school_statistics diff --git a/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_high_school_us_history.yaml b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_high_school_us_history.yaml new file mode 100644 index 00000000..507a4d5c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_high_school_us_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _tr_template_yaml +process_docs: !function utils.process_high_school_us_history +tag: global_mmlu_full_tr_humanities_tasks +task: global_mmlu_full_tr_high_school_us_history diff --git a/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_high_school_world_history.yaml b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_high_school_world_history.yaml new file mode 100644 index 00000000..60cc713e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_high_school_world_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _tr_template_yaml +process_docs: !function utils.process_high_school_world_history +tag: global_mmlu_full_tr_humanities_tasks +task: global_mmlu_full_tr_high_school_world_history diff --git a/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_human_aging.yaml b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_human_aging.yaml new file mode 100644 index 00000000..8e48bf12 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_human_aging.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _tr_template_yaml +process_docs: !function utils.process_human_aging +tag: global_mmlu_full_tr_other_tasks +task: global_mmlu_full_tr_human_aging diff --git a/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_human_sexuality.yaml b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_human_sexuality.yaml new file mode 100644 index 00000000..84a95850 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_human_sexuality.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _tr_template_yaml +process_docs: !function utils.process_human_sexuality +tag: global_mmlu_full_tr_social_sciences_tasks +task: global_mmlu_full_tr_human_sexuality diff --git a/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_international_law.yaml b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_international_law.yaml new file mode 100644 index 00000000..d0dc429f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_international_law.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _tr_template_yaml +process_docs: !function utils.process_international_law +tag: global_mmlu_full_tr_humanities_tasks +task: global_mmlu_full_tr_international_law diff --git a/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_jurisprudence.yaml b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_jurisprudence.yaml new file mode 100644 index 00000000..ea3b7a51 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_jurisprudence.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _tr_template_yaml +process_docs: !function utils.process_jurisprudence +tag: global_mmlu_full_tr_humanities_tasks +task: global_mmlu_full_tr_jurisprudence diff --git a/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_logical_fallacies.yaml b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_logical_fallacies.yaml new file mode 100644 index 00000000..cd61d7d7 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_logical_fallacies.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _tr_template_yaml +process_docs: !function utils.process_logical_fallacies +tag: global_mmlu_full_tr_humanities_tasks +task: global_mmlu_full_tr_logical_fallacies diff --git a/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_machine_learning.yaml b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_machine_learning.yaml new file mode 100644 index 00000000..b0e785c3 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_machine_learning.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _tr_template_yaml +process_docs: !function utils.process_machine_learning +tag: global_mmlu_full_tr_stem_tasks +task: global_mmlu_full_tr_machine_learning diff --git a/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_management.yaml b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_management.yaml new file mode 100644 index 00000000..5ce0d753 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_management.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _tr_template_yaml +process_docs: !function utils.process_management +tag: global_mmlu_full_tr_other_tasks +task: global_mmlu_full_tr_management diff --git a/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_marketing.yaml b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_marketing.yaml new file mode 100644 index 00000000..8ffd4986 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_marketing.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _tr_template_yaml +process_docs: !function utils.process_marketing +tag: global_mmlu_full_tr_other_tasks +task: global_mmlu_full_tr_marketing diff --git a/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_medical_genetics.yaml b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_medical_genetics.yaml new file mode 100644 index 00000000..43814b40 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_medical_genetics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _tr_template_yaml +process_docs: !function utils.process_medical_genetics +tag: global_mmlu_full_tr_other_tasks +task: global_mmlu_full_tr_medical_genetics diff --git a/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_miscellaneous.yaml b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_miscellaneous.yaml new file mode 100644 index 00000000..e21cfcf6 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_miscellaneous.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _tr_template_yaml +process_docs: !function utils.process_miscellaneous +tag: global_mmlu_full_tr_other_tasks +task: global_mmlu_full_tr_miscellaneous diff --git a/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_moral_disputes.yaml b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_moral_disputes.yaml new file mode 100644 index 00000000..88fbfbe2 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_moral_disputes.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _tr_template_yaml +process_docs: !function utils.process_moral_disputes +tag: global_mmlu_full_tr_humanities_tasks +task: global_mmlu_full_tr_moral_disputes diff --git a/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_moral_scenarios.yaml b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_moral_scenarios.yaml new file mode 100644 index 00000000..9f92f855 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_moral_scenarios.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _tr_template_yaml +process_docs: !function utils.process_moral_scenarios +tag: global_mmlu_full_tr_humanities_tasks +task: global_mmlu_full_tr_moral_scenarios diff --git a/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_nutrition.yaml b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_nutrition.yaml new file mode 100644 index 00000000..31b39c38 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_nutrition.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _tr_template_yaml +process_docs: !function utils.process_nutrition +tag: global_mmlu_full_tr_other_tasks +task: global_mmlu_full_tr_nutrition diff --git a/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_philosophy.yaml b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_philosophy.yaml new file mode 100644 index 00000000..283a2b89 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_philosophy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _tr_template_yaml +process_docs: !function utils.process_philosophy +tag: global_mmlu_full_tr_humanities_tasks +task: global_mmlu_full_tr_philosophy diff --git a/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_prehistory.yaml b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_prehistory.yaml new file mode 100644 index 00000000..e4c17014 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_prehistory.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _tr_template_yaml +process_docs: !function utils.process_prehistory +tag: global_mmlu_full_tr_humanities_tasks +task: global_mmlu_full_tr_prehistory diff --git a/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_professional_accounting.yaml b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_professional_accounting.yaml new file mode 100644 index 00000000..c69f14f7 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_professional_accounting.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _tr_template_yaml +process_docs: !function utils.process_professional_accounting +tag: global_mmlu_full_tr_other_tasks +task: global_mmlu_full_tr_professional_accounting diff --git a/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_professional_law.yaml b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_professional_law.yaml new file mode 100644 index 00000000..8f5e97c6 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_professional_law.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _tr_template_yaml +process_docs: !function utils.process_professional_law +tag: global_mmlu_full_tr_humanities_tasks +task: global_mmlu_full_tr_professional_law diff --git a/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_professional_medicine.yaml b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_professional_medicine.yaml new file mode 100644 index 00000000..00a5f32a --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_professional_medicine.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _tr_template_yaml +process_docs: !function utils.process_professional_medicine +tag: global_mmlu_full_tr_other_tasks +task: global_mmlu_full_tr_professional_medicine diff --git a/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_professional_psychology.yaml b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_professional_psychology.yaml new file mode 100644 index 00000000..c8571bdb --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_professional_psychology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _tr_template_yaml +process_docs: !function utils.process_professional_psychology +tag: global_mmlu_full_tr_social_sciences_tasks +task: global_mmlu_full_tr_professional_psychology diff --git a/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_public_relations.yaml b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_public_relations.yaml new file mode 100644 index 00000000..539f8da6 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_public_relations.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _tr_template_yaml +process_docs: !function utils.process_public_relations +tag: global_mmlu_full_tr_social_sciences_tasks +task: global_mmlu_full_tr_public_relations diff --git a/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_security_studies.yaml b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_security_studies.yaml new file mode 100644 index 00000000..4203e365 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_security_studies.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _tr_template_yaml +process_docs: !function utils.process_security_studies +tag: global_mmlu_full_tr_social_sciences_tasks +task: global_mmlu_full_tr_security_studies diff --git a/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_sociology.yaml b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_sociology.yaml new file mode 100644 index 00000000..9cf6352c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_sociology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _tr_template_yaml +process_docs: !function utils.process_sociology +tag: global_mmlu_full_tr_social_sciences_tasks +task: global_mmlu_full_tr_sociology diff --git a/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_us_foreign_policy.yaml b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_us_foreign_policy.yaml new file mode 100644 index 00000000..b86a699b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_us_foreign_policy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _tr_template_yaml +process_docs: !function utils.process_us_foreign_policy +tag: global_mmlu_full_tr_social_sciences_tasks +task: global_mmlu_full_tr_us_foreign_policy diff --git a/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_virology.yaml b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_virology.yaml new file mode 100644 index 00000000..001cbb28 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_virology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _tr_template_yaml +process_docs: !function utils.process_virology +tag: global_mmlu_full_tr_other_tasks +task: global_mmlu_full_tr_virology diff --git a/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_world_religions.yaml b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_world_religions.yaml new file mode 100644 index 00000000..1f1d4e4f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/tr/global_mmlu_full_tr_world_religions.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _tr_template_yaml +process_docs: !function utils.process_world_religions +tag: global_mmlu_full_tr_humanities_tasks +task: global_mmlu_full_tr_world_religions diff --git a/lm_eval/tasks/global_mmlu/full/tr/utils.py b/lm_eval/tasks/global_mmlu/full/tr/utils.py new file mode 100644 index 00000000..7df72cb0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/tr/utils.py @@ -0,0 +1,73 @@ +from functools import partial + + +SUBJECTS = [ + "abstract_algebra", + "anatomy", + "astronomy", + "business_ethics", + "clinical_knowledge", + "college_biology", + "college_chemistry", + "college_computer_science", + "college_mathematics", + "college_medicine", + "college_physics", + "computer_security", + "conceptual_physics", + "econometrics", + "electrical_engineering", + "elementary_mathematics", + "formal_logic", + "global_facts", + "high_school_biology", + "high_school_chemistry", + "high_school_computer_science", + "high_school_european_history", + "high_school_geography", + "high_school_government_and_politics", + "high_school_macroeconomics", + "high_school_mathematics", + "high_school_microeconomics", + "high_school_physics", + "high_school_psychology", + "high_school_statistics", + "high_school_us_history", + "high_school_world_history", + "human_aging", + "human_sexuality", + "international_law", + "jurisprudence", + "logical_fallacies", + "machine_learning", + "management", + "marketing", + "medical_genetics", + "miscellaneous", + "moral_disputes", + "moral_scenarios", + "nutrition", + "philosophy", + "prehistory", + "professional_accounting", + "professional_law", + "professional_medicine", + "professional_psychology", + "public_relations", + "security_studies", + "sociology", + "us_foreign_policy", + "virology", + "world_religions", +] + + +def process_docs(dataset, subject): + return dataset.filter(lambda x: x["subject"] == subject) + + +process_functions = { + f"process_{subject}": partial(process_docs, subject=subject) for subject in SUBJECTS +} + +globals().update(process_functions) diff --git a/lm_eval/tasks/global_mmlu/full/uk/_global_mmlu_full_uk.yaml b/lm_eval/tasks/global_mmlu/full/uk/_global_mmlu_full_uk.yaml new file mode 100644 index 00000000..e880be32 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/uk/_global_mmlu_full_uk.yaml @@ -0,0 +1,11 @@ +group: global_mmlu_full_uk +task: + - global_mmlu_full_uk_stem + - global_mmlu_full_uk_other + - global_mmlu_full_uk_social_sciences + - global_mmlu_full_uk_humanities +aggregate_metric_list: + - metric: acc + weight_by_size: True +metadata: + version: 1.0 diff --git a/lm_eval/tasks/global_mmlu/full/uk/_global_mmlu_full_uk_humanities.yaml b/lm_eval/tasks/global_mmlu/full/uk/_global_mmlu_full_uk_humanities.yaml new file mode 100644 index 00000000..b3ec01db --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/uk/_global_mmlu_full_uk_humanities.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_uk_humanities +task: + - global_mmlu_full_uk_humanities_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/uk/_global_mmlu_full_uk_other.yaml b/lm_eval/tasks/global_mmlu/full/uk/_global_mmlu_full_uk_other.yaml new file mode 100644 index 00000000..176b1861 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/uk/_global_mmlu_full_uk_other.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_uk_other +task: + - global_mmlu_full_uk_other_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/uk/_global_mmlu_full_uk_social_sciences.yaml b/lm_eval/tasks/global_mmlu/full/uk/_global_mmlu_full_uk_social_sciences.yaml new file mode 100644 index 00000000..66b36a60 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/uk/_global_mmlu_full_uk_social_sciences.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_uk_social_sciences +task: + - global_mmlu_full_uk_social_sciences_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/uk/_global_mmlu_full_uk_stem.yaml b/lm_eval/tasks/global_mmlu/full/uk/_global_mmlu_full_uk_stem.yaml new file mode 100644 index 00000000..4deba657 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/uk/_global_mmlu_full_uk_stem.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_uk_stem +task: + - global_mmlu_full_uk_stem_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/uk/_uk_template_yaml b/lm_eval/tasks/global_mmlu/full/uk/_uk_template_yaml new file mode 100644 index 00000000..5765ce13 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/uk/_uk_template_yaml @@ -0,0 +1,16 @@ +dataset_path: CohereForAI/Global-MMLU +dataset_name: uk +test_split: test +fewshot_split: dev +fewshot_config: + sampler: first_n +output_type: multiple_choice +doc_to_text: "{{question.strip()}}\nA. {{option_a}}\nB. {{option_b}}\nC. {{option_c}}\nD. {{option_d}}\nAnswer:" +doc_to_choice: ["A", "B", "C", "D"] +doc_to_target: answer +metric_list: + - metric: acc + aggregation: mean + higher_is_better: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_abstract_algebra.yaml b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_abstract_algebra.yaml new file mode 100644 index 00000000..ce37c715 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_abstract_algebra.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _uk_template_yaml +process_docs: !function utils.process_abstract_algebra +tag: global_mmlu_full_uk_stem_tasks +task: global_mmlu_full_uk_abstract_algebra diff --git a/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_anatomy.yaml b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_anatomy.yaml new file mode 100644 index 00000000..db1433d5 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_anatomy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _uk_template_yaml +process_docs: !function utils.process_anatomy +tag: global_mmlu_full_uk_stem_tasks +task: global_mmlu_full_uk_anatomy diff --git a/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_astronomy.yaml b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_astronomy.yaml new file mode 100644 index 00000000..6b123ece --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_astronomy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _uk_template_yaml +process_docs: !function utils.process_astronomy +tag: global_mmlu_full_uk_stem_tasks +task: global_mmlu_full_uk_astronomy diff --git a/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_business_ethics.yaml b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_business_ethics.yaml new file mode 100644 index 00000000..775d2f2c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_business_ethics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _uk_template_yaml +process_docs: !function utils.process_business_ethics +tag: global_mmlu_full_uk_other_tasks +task: global_mmlu_full_uk_business_ethics diff --git a/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_clinical_knowledge.yaml b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_clinical_knowledge.yaml new file mode 100644 index 00000000..5f71076d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_clinical_knowledge.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _uk_template_yaml +process_docs: !function utils.process_clinical_knowledge +tag: global_mmlu_full_uk_other_tasks +task: global_mmlu_full_uk_clinical_knowledge diff --git a/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_college_biology.yaml b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_college_biology.yaml new file mode 100644 index 00000000..92342ac7 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_college_biology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _uk_template_yaml +process_docs: !function utils.process_college_biology +tag: global_mmlu_full_uk_stem_tasks +task: global_mmlu_full_uk_college_biology diff --git a/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_college_chemistry.yaml b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_college_chemistry.yaml new file mode 100644 index 00000000..71384a8b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_college_chemistry.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _uk_template_yaml +process_docs: !function utils.process_college_chemistry +tag: global_mmlu_full_uk_stem_tasks +task: global_mmlu_full_uk_college_chemistry diff --git a/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_college_computer_science.yaml b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_college_computer_science.yaml new file mode 100644 index 00000000..6013afe1 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_college_computer_science.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _uk_template_yaml +process_docs: !function utils.process_college_computer_science +tag: global_mmlu_full_uk_stem_tasks +task: global_mmlu_full_uk_college_computer_science diff --git a/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_college_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_college_mathematics.yaml new file mode 100644 index 00000000..27b60491 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_college_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _uk_template_yaml +process_docs: !function utils.process_college_mathematics +tag: global_mmlu_full_uk_stem_tasks +task: global_mmlu_full_uk_college_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_college_medicine.yaml b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_college_medicine.yaml new file mode 100644 index 00000000..87131c25 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_college_medicine.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _uk_template_yaml +process_docs: !function utils.process_college_medicine +tag: global_mmlu_full_uk_other_tasks +task: global_mmlu_full_uk_college_medicine diff --git a/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_college_physics.yaml b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_college_physics.yaml new file mode 100644 index 00000000..93109632 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_college_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _uk_template_yaml +process_docs: !function utils.process_college_physics +tag: global_mmlu_full_uk_stem_tasks +task: global_mmlu_full_uk_college_physics diff --git a/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_computer_security.yaml b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_computer_security.yaml new file mode 100644 index 00000000..0f11fcce --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_computer_security.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _uk_template_yaml +process_docs: !function utils.process_computer_security +tag: global_mmlu_full_uk_stem_tasks +task: global_mmlu_full_uk_computer_security diff --git a/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_conceptual_physics.yaml b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_conceptual_physics.yaml new file mode 100644 index 00000000..7ff9715a --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_conceptual_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _uk_template_yaml +process_docs: !function utils.process_conceptual_physics +tag: global_mmlu_full_uk_stem_tasks +task: global_mmlu_full_uk_conceptual_physics diff --git a/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_econometrics.yaml b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_econometrics.yaml new file mode 100644 index 00000000..ba92e4b8 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_econometrics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _uk_template_yaml +process_docs: !function utils.process_econometrics +tag: global_mmlu_full_uk_social_sciences_tasks +task: global_mmlu_full_uk_econometrics diff --git a/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_electrical_engineering.yaml b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_electrical_engineering.yaml new file mode 100644 index 00000000..3a1c86ff --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_electrical_engineering.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _uk_template_yaml +process_docs: !function utils.process_electrical_engineering +tag: global_mmlu_full_uk_stem_tasks +task: global_mmlu_full_uk_electrical_engineering diff --git a/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_elementary_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_elementary_mathematics.yaml new file mode 100644 index 00000000..7d80cce7 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_elementary_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _uk_template_yaml +process_docs: !function utils.process_elementary_mathematics +tag: global_mmlu_full_uk_stem_tasks +task: global_mmlu_full_uk_elementary_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_formal_logic.yaml b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_formal_logic.yaml new file mode 100644 index 00000000..9f8a4091 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_formal_logic.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _uk_template_yaml +process_docs: !function utils.process_formal_logic +tag: global_mmlu_full_uk_humanities_tasks +task: global_mmlu_full_uk_formal_logic diff --git a/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_global_facts.yaml b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_global_facts.yaml new file mode 100644 index 00000000..ebd6c2da --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_global_facts.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _uk_template_yaml +process_docs: !function utils.process_global_facts +tag: global_mmlu_full_uk_other_tasks +task: global_mmlu_full_uk_global_facts diff --git a/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_high_school_biology.yaml b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_high_school_biology.yaml new file mode 100644 index 00000000..a8b0cf3a --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_high_school_biology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _uk_template_yaml +process_docs: !function utils.process_high_school_biology +tag: global_mmlu_full_uk_stem_tasks +task: global_mmlu_full_uk_high_school_biology diff --git a/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_high_school_chemistry.yaml b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_high_school_chemistry.yaml new file mode 100644 index 00000000..010dbec3 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_high_school_chemistry.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _uk_template_yaml +process_docs: !function utils.process_high_school_chemistry +tag: global_mmlu_full_uk_stem_tasks +task: global_mmlu_full_uk_high_school_chemistry diff --git a/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_high_school_computer_science.yaml b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_high_school_computer_science.yaml new file mode 100644 index 00000000..9a270144 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_high_school_computer_science.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _uk_template_yaml +process_docs: !function utils.process_high_school_computer_science +tag: global_mmlu_full_uk_stem_tasks +task: global_mmlu_full_uk_high_school_computer_science diff --git a/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_high_school_european_history.yaml b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_high_school_european_history.yaml new file mode 100644 index 00000000..52e80017 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_high_school_european_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _uk_template_yaml +process_docs: !function utils.process_high_school_european_history +tag: global_mmlu_full_uk_humanities_tasks +task: global_mmlu_full_uk_high_school_european_history diff --git a/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_high_school_geography.yaml b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_high_school_geography.yaml new file mode 100644 index 00000000..4f41dd3d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_high_school_geography.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _uk_template_yaml +process_docs: !function utils.process_high_school_geography +tag: global_mmlu_full_uk_social_sciences_tasks +task: global_mmlu_full_uk_high_school_geography diff --git a/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_high_school_government_and_politics.yaml b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_high_school_government_and_politics.yaml new file mode 100644 index 00000000..72c589ef --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_high_school_government_and_politics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _uk_template_yaml +process_docs: !function utils.process_high_school_government_and_politics +tag: global_mmlu_full_uk_social_sciences_tasks +task: global_mmlu_full_uk_high_school_government_and_politics diff --git a/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_high_school_macroeconomics.yaml b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_high_school_macroeconomics.yaml new file mode 100644 index 00000000..e70675d9 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_high_school_macroeconomics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _uk_template_yaml +process_docs: !function utils.process_high_school_macroeconomics +tag: global_mmlu_full_uk_social_sciences_tasks +task: global_mmlu_full_uk_high_school_macroeconomics diff --git a/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_high_school_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_high_school_mathematics.yaml new file mode 100644 index 00000000..e29c558e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_high_school_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _uk_template_yaml +process_docs: !function utils.process_high_school_mathematics +tag: global_mmlu_full_uk_stem_tasks +task: global_mmlu_full_uk_high_school_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_high_school_microeconomics.yaml b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_high_school_microeconomics.yaml new file mode 100644 index 00000000..6b735495 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_high_school_microeconomics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _uk_template_yaml +process_docs: !function utils.process_high_school_microeconomics +tag: global_mmlu_full_uk_social_sciences_tasks +task: global_mmlu_full_uk_high_school_microeconomics diff --git a/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_high_school_physics.yaml b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_high_school_physics.yaml new file mode 100644 index 00000000..69a03c06 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_high_school_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _uk_template_yaml +process_docs: !function utils.process_high_school_physics +tag: global_mmlu_full_uk_stem_tasks +task: global_mmlu_full_uk_high_school_physics diff --git a/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_high_school_psychology.yaml b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_high_school_psychology.yaml new file mode 100644 index 00000000..9b02711c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_high_school_psychology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _uk_template_yaml +process_docs: !function utils.process_high_school_psychology +tag: global_mmlu_full_uk_social_sciences_tasks +task: global_mmlu_full_uk_high_school_psychology diff --git a/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_high_school_statistics.yaml b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_high_school_statistics.yaml new file mode 100644 index 00000000..60cc0cdd --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_high_school_statistics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _uk_template_yaml +process_docs: !function utils.process_high_school_statistics +tag: global_mmlu_full_uk_stem_tasks +task: global_mmlu_full_uk_high_school_statistics diff --git a/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_high_school_us_history.yaml b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_high_school_us_history.yaml new file mode 100644 index 00000000..b62244eb --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_high_school_us_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _uk_template_yaml +process_docs: !function utils.process_high_school_us_history +tag: global_mmlu_full_uk_humanities_tasks +task: global_mmlu_full_uk_high_school_us_history diff --git a/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_high_school_world_history.yaml b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_high_school_world_history.yaml new file mode 100644 index 00000000..57667edc --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_high_school_world_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _uk_template_yaml +process_docs: !function utils.process_high_school_world_history +tag: global_mmlu_full_uk_humanities_tasks +task: global_mmlu_full_uk_high_school_world_history diff --git a/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_human_aging.yaml b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_human_aging.yaml new file mode 100644 index 00000000..02804890 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_human_aging.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _uk_template_yaml +process_docs: !function utils.process_human_aging +tag: global_mmlu_full_uk_other_tasks +task: global_mmlu_full_uk_human_aging diff --git a/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_human_sexuality.yaml b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_human_sexuality.yaml new file mode 100644 index 00000000..37382bab --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_human_sexuality.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _uk_template_yaml +process_docs: !function utils.process_human_sexuality +tag: global_mmlu_full_uk_social_sciences_tasks +task: global_mmlu_full_uk_human_sexuality diff --git a/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_international_law.yaml b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_international_law.yaml new file mode 100644 index 00000000..d1b046d7 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_international_law.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _uk_template_yaml +process_docs: !function utils.process_international_law +tag: global_mmlu_full_uk_humanities_tasks +task: global_mmlu_full_uk_international_law diff --git a/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_jurisprudence.yaml b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_jurisprudence.yaml new file mode 100644 index 00000000..12b9da52 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_jurisprudence.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _uk_template_yaml +process_docs: !function utils.process_jurisprudence +tag: global_mmlu_full_uk_humanities_tasks +task: global_mmlu_full_uk_jurisprudence diff --git a/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_logical_fallacies.yaml b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_logical_fallacies.yaml new file mode 100644 index 00000000..abb2de2a --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_logical_fallacies.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _uk_template_yaml +process_docs: !function utils.process_logical_fallacies +tag: global_mmlu_full_uk_humanities_tasks +task: global_mmlu_full_uk_logical_fallacies diff --git a/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_machine_learning.yaml b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_machine_learning.yaml new file mode 100644 index 00000000..7a1a6f34 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_machine_learning.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _uk_template_yaml +process_docs: !function utils.process_machine_learning +tag: global_mmlu_full_uk_stem_tasks +task: global_mmlu_full_uk_machine_learning diff --git a/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_management.yaml b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_management.yaml new file mode 100644 index 00000000..ec4cb17d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_management.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _uk_template_yaml +process_docs: !function utils.process_management +tag: global_mmlu_full_uk_other_tasks +task: global_mmlu_full_uk_management diff --git a/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_marketing.yaml b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_marketing.yaml new file mode 100644 index 00000000..afbdaee2 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_marketing.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _uk_template_yaml +process_docs: !function utils.process_marketing +tag: global_mmlu_full_uk_other_tasks +task: global_mmlu_full_uk_marketing diff --git a/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_medical_genetics.yaml b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_medical_genetics.yaml new file mode 100644 index 00000000..bc1fe1bd --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_medical_genetics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _uk_template_yaml +process_docs: !function utils.process_medical_genetics +tag: global_mmlu_full_uk_other_tasks +task: global_mmlu_full_uk_medical_genetics diff --git a/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_miscellaneous.yaml b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_miscellaneous.yaml new file mode 100644 index 00000000..8f3b18f8 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_miscellaneous.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _uk_template_yaml +process_docs: !function utils.process_miscellaneous +tag: global_mmlu_full_uk_other_tasks +task: global_mmlu_full_uk_miscellaneous diff --git a/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_moral_disputes.yaml b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_moral_disputes.yaml new file mode 100644 index 00000000..34b54e34 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_moral_disputes.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _uk_template_yaml +process_docs: !function utils.process_moral_disputes +tag: global_mmlu_full_uk_humanities_tasks +task: global_mmlu_full_uk_moral_disputes diff --git a/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_moral_scenarios.yaml b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_moral_scenarios.yaml new file mode 100644 index 00000000..38706977 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_moral_scenarios.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _uk_template_yaml +process_docs: !function utils.process_moral_scenarios +tag: global_mmlu_full_uk_humanities_tasks +task: global_mmlu_full_uk_moral_scenarios diff --git a/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_nutrition.yaml b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_nutrition.yaml new file mode 100644 index 00000000..9f9dd1fe --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_nutrition.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _uk_template_yaml +process_docs: !function utils.process_nutrition +tag: global_mmlu_full_uk_other_tasks +task: global_mmlu_full_uk_nutrition diff --git a/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_philosophy.yaml b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_philosophy.yaml new file mode 100644 index 00000000..4e981008 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_philosophy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _uk_template_yaml +process_docs: !function utils.process_philosophy +tag: global_mmlu_full_uk_humanities_tasks +task: global_mmlu_full_uk_philosophy diff --git a/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_prehistory.yaml b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_prehistory.yaml new file mode 100644 index 00000000..08e3c2af --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_prehistory.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _uk_template_yaml +process_docs: !function utils.process_prehistory +tag: global_mmlu_full_uk_humanities_tasks +task: global_mmlu_full_uk_prehistory diff --git a/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_professional_accounting.yaml b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_professional_accounting.yaml new file mode 100644 index 00000000..dc02a7b2 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_professional_accounting.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _uk_template_yaml +process_docs: !function utils.process_professional_accounting +tag: global_mmlu_full_uk_other_tasks +task: global_mmlu_full_uk_professional_accounting diff --git a/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_professional_law.yaml b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_professional_law.yaml new file mode 100644 index 00000000..7090a6e1 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_professional_law.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _uk_template_yaml +process_docs: !function utils.process_professional_law +tag: global_mmlu_full_uk_humanities_tasks +task: global_mmlu_full_uk_professional_law diff --git a/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_professional_medicine.yaml b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_professional_medicine.yaml new file mode 100644 index 00000000..0b43dcfb --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_professional_medicine.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _uk_template_yaml +process_docs: !function utils.process_professional_medicine +tag: global_mmlu_full_uk_other_tasks +task: global_mmlu_full_uk_professional_medicine diff --git a/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_professional_psychology.yaml b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_professional_psychology.yaml new file mode 100644 index 00000000..b279a94c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_professional_psychology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _uk_template_yaml +process_docs: !function utils.process_professional_psychology +tag: global_mmlu_full_uk_social_sciences_tasks +task: global_mmlu_full_uk_professional_psychology diff --git a/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_public_relations.yaml b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_public_relations.yaml new file mode 100644 index 00000000..3b45dc62 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_public_relations.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _uk_template_yaml +process_docs: !function utils.process_public_relations +tag: global_mmlu_full_uk_social_sciences_tasks +task: global_mmlu_full_uk_public_relations diff --git a/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_security_studies.yaml b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_security_studies.yaml new file mode 100644 index 00000000..4ea308da --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_security_studies.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _uk_template_yaml +process_docs: !function utils.process_security_studies +tag: global_mmlu_full_uk_social_sciences_tasks +task: global_mmlu_full_uk_security_studies diff --git a/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_sociology.yaml b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_sociology.yaml new file mode 100644 index 00000000..a7aa08ec --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_sociology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _uk_template_yaml +process_docs: !function utils.process_sociology +tag: global_mmlu_full_uk_social_sciences_tasks +task: global_mmlu_full_uk_sociology diff --git a/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_us_foreign_policy.yaml b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_us_foreign_policy.yaml new file mode 100644 index 00000000..d089e778 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_us_foreign_policy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _uk_template_yaml +process_docs: !function utils.process_us_foreign_policy +tag: global_mmlu_full_uk_social_sciences_tasks +task: global_mmlu_full_uk_us_foreign_policy diff --git a/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_virology.yaml b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_virology.yaml new file mode 100644 index 00000000..41b627f5 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_virology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _uk_template_yaml +process_docs: !function utils.process_virology +tag: global_mmlu_full_uk_other_tasks +task: global_mmlu_full_uk_virology diff --git a/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_world_religions.yaml b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_world_religions.yaml new file mode 100644 index 00000000..f5d6d415 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/uk/global_mmlu_full_uk_world_religions.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _uk_template_yaml +process_docs: !function utils.process_world_religions +tag: global_mmlu_full_uk_humanities_tasks +task: global_mmlu_full_uk_world_religions diff --git a/lm_eval/tasks/global_mmlu/full/uk/utils.py b/lm_eval/tasks/global_mmlu/full/uk/utils.py new file mode 100644 index 00000000..7df72cb0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/uk/utils.py @@ -0,0 +1,73 @@ +from functools import partial + + +SUBJECTS = [ + "abstract_algebra", + "anatomy", + "astronomy", + "business_ethics", + "clinical_knowledge", + "college_biology", + "college_chemistry", + "college_computer_science", + "college_mathematics", + "college_medicine", + "college_physics", + "computer_security", + "conceptual_physics", + "econometrics", + "electrical_engineering", + "elementary_mathematics", + "formal_logic", + "global_facts", + "high_school_biology", + "high_school_chemistry", + "high_school_computer_science", + "high_school_european_history", + "high_school_geography", + "high_school_government_and_politics", + "high_school_macroeconomics", + "high_school_mathematics", + "high_school_microeconomics", + "high_school_physics", + "high_school_psychology", + "high_school_statistics", + "high_school_us_history", + "high_school_world_history", + "human_aging", + "human_sexuality", + "international_law", + "jurisprudence", + "logical_fallacies", + "machine_learning", + "management", + "marketing", + "medical_genetics", + "miscellaneous", + "moral_disputes", + "moral_scenarios", + "nutrition", + "philosophy", + "prehistory", + "professional_accounting", + "professional_law", + "professional_medicine", + "professional_psychology", + "public_relations", + "security_studies", + "sociology", + "us_foreign_policy", + "virology", + "world_religions", +] + + +def process_docs(dataset, subject): + return dataset.filter(lambda x: x["subject"] == subject) + + +process_functions = { + f"process_{subject}": partial(process_docs, subject=subject) for subject in SUBJECTS +} + +globals().update(process_functions) diff --git a/lm_eval/tasks/global_mmlu/full/vi/_global_mmlu_full_vi.yaml b/lm_eval/tasks/global_mmlu/full/vi/_global_mmlu_full_vi.yaml new file mode 100644 index 00000000..d6413b35 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/vi/_global_mmlu_full_vi.yaml @@ -0,0 +1,11 @@ +group: global_mmlu_full_vi +task: + - global_mmlu_full_vi_stem + - global_mmlu_full_vi_other + - global_mmlu_full_vi_social_sciences + - global_mmlu_full_vi_humanities +aggregate_metric_list: + - metric: acc + weight_by_size: True +metadata: + version: 1.0 diff --git a/lm_eval/tasks/global_mmlu/full/vi/_global_mmlu_full_vi_humanities.yaml b/lm_eval/tasks/global_mmlu/full/vi/_global_mmlu_full_vi_humanities.yaml new file mode 100644 index 00000000..7a05acca --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/vi/_global_mmlu_full_vi_humanities.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_vi_humanities +task: + - global_mmlu_full_vi_humanities_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/vi/_global_mmlu_full_vi_other.yaml b/lm_eval/tasks/global_mmlu/full/vi/_global_mmlu_full_vi_other.yaml new file mode 100644 index 00000000..880bab9a --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/vi/_global_mmlu_full_vi_other.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_vi_other +task: + - global_mmlu_full_vi_other_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/vi/_global_mmlu_full_vi_social_sciences.yaml b/lm_eval/tasks/global_mmlu/full/vi/_global_mmlu_full_vi_social_sciences.yaml new file mode 100644 index 00000000..6da224f2 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/vi/_global_mmlu_full_vi_social_sciences.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_vi_social_sciences +task: + - global_mmlu_full_vi_social_sciences_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/vi/_global_mmlu_full_vi_stem.yaml b/lm_eval/tasks/global_mmlu/full/vi/_global_mmlu_full_vi_stem.yaml new file mode 100644 index 00000000..12526ce7 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/vi/_global_mmlu_full_vi_stem.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_vi_stem +task: + - global_mmlu_full_vi_stem_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/vi/_vi_template_yaml b/lm_eval/tasks/global_mmlu/full/vi/_vi_template_yaml new file mode 100644 index 00000000..5a0ca817 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/vi/_vi_template_yaml @@ -0,0 +1,16 @@ +dataset_path: CohereForAI/Global-MMLU +dataset_name: vi +test_split: test +fewshot_split: dev +fewshot_config: + sampler: first_n +output_type: multiple_choice +doc_to_text: "{{question.strip()}}\nA. {{option_a}}\nB. {{option_b}}\nC. {{option_c}}\nD. {{option_d}}\nAnswer:" +doc_to_choice: ["A", "B", "C", "D"] +doc_to_target: answer +metric_list: + - metric: acc + aggregation: mean + higher_is_better: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_abstract_algebra.yaml b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_abstract_algebra.yaml new file mode 100644 index 00000000..47dc80ce --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_abstract_algebra.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _vi_template_yaml +process_docs: !function utils.process_abstract_algebra +tag: global_mmlu_full_vi_stem_tasks +task: global_mmlu_full_vi_abstract_algebra diff --git a/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_anatomy.yaml b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_anatomy.yaml new file mode 100644 index 00000000..d29cb583 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_anatomy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _vi_template_yaml +process_docs: !function utils.process_anatomy +tag: global_mmlu_full_vi_stem_tasks +task: global_mmlu_full_vi_anatomy diff --git a/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_astronomy.yaml b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_astronomy.yaml new file mode 100644 index 00000000..3e3ba1dc --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_astronomy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _vi_template_yaml +process_docs: !function utils.process_astronomy +tag: global_mmlu_full_vi_stem_tasks +task: global_mmlu_full_vi_astronomy diff --git a/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_business_ethics.yaml b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_business_ethics.yaml new file mode 100644 index 00000000..3afecdc1 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_business_ethics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _vi_template_yaml +process_docs: !function utils.process_business_ethics +tag: global_mmlu_full_vi_other_tasks +task: global_mmlu_full_vi_business_ethics diff --git a/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_clinical_knowledge.yaml b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_clinical_knowledge.yaml new file mode 100644 index 00000000..34a90a8e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_clinical_knowledge.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _vi_template_yaml +process_docs: !function utils.process_clinical_knowledge +tag: global_mmlu_full_vi_other_tasks +task: global_mmlu_full_vi_clinical_knowledge diff --git a/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_college_biology.yaml b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_college_biology.yaml new file mode 100644 index 00000000..63a4c772 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_college_biology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _vi_template_yaml +process_docs: !function utils.process_college_biology +tag: global_mmlu_full_vi_stem_tasks +task: global_mmlu_full_vi_college_biology diff --git a/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_college_chemistry.yaml b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_college_chemistry.yaml new file mode 100644 index 00000000..f7226e02 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_college_chemistry.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _vi_template_yaml +process_docs: !function utils.process_college_chemistry +tag: global_mmlu_full_vi_stem_tasks +task: global_mmlu_full_vi_college_chemistry diff --git a/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_college_computer_science.yaml b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_college_computer_science.yaml new file mode 100644 index 00000000..90a9e0b2 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_college_computer_science.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _vi_template_yaml +process_docs: !function utils.process_college_computer_science +tag: global_mmlu_full_vi_stem_tasks +task: global_mmlu_full_vi_college_computer_science diff --git a/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_college_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_college_mathematics.yaml new file mode 100644 index 00000000..a09173d6 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_college_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _vi_template_yaml +process_docs: !function utils.process_college_mathematics +tag: global_mmlu_full_vi_stem_tasks +task: global_mmlu_full_vi_college_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_college_medicine.yaml b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_college_medicine.yaml new file mode 100644 index 00000000..22dc78bd --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_college_medicine.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _vi_template_yaml +process_docs: !function utils.process_college_medicine +tag: global_mmlu_full_vi_other_tasks +task: global_mmlu_full_vi_college_medicine diff --git a/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_college_physics.yaml b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_college_physics.yaml new file mode 100644 index 00000000..a6f8dbca --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_college_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _vi_template_yaml +process_docs: !function utils.process_college_physics +tag: global_mmlu_full_vi_stem_tasks +task: global_mmlu_full_vi_college_physics diff --git a/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_computer_security.yaml b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_computer_security.yaml new file mode 100644 index 00000000..4d4b3d60 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_computer_security.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _vi_template_yaml +process_docs: !function utils.process_computer_security +tag: global_mmlu_full_vi_stem_tasks +task: global_mmlu_full_vi_computer_security diff --git a/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_conceptual_physics.yaml b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_conceptual_physics.yaml new file mode 100644 index 00000000..6c501d0a --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_conceptual_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _vi_template_yaml +process_docs: !function utils.process_conceptual_physics +tag: global_mmlu_full_vi_stem_tasks +task: global_mmlu_full_vi_conceptual_physics diff --git a/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_econometrics.yaml b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_econometrics.yaml new file mode 100644 index 00000000..d0936b3b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_econometrics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _vi_template_yaml +process_docs: !function utils.process_econometrics +tag: global_mmlu_full_vi_social_sciences_tasks +task: global_mmlu_full_vi_econometrics diff --git a/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_electrical_engineering.yaml b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_electrical_engineering.yaml new file mode 100644 index 00000000..3b23387f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_electrical_engineering.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _vi_template_yaml +process_docs: !function utils.process_electrical_engineering +tag: global_mmlu_full_vi_stem_tasks +task: global_mmlu_full_vi_electrical_engineering diff --git a/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_elementary_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_elementary_mathematics.yaml new file mode 100644 index 00000000..9c098266 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_elementary_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _vi_template_yaml +process_docs: !function utils.process_elementary_mathematics +tag: global_mmlu_full_vi_stem_tasks +task: global_mmlu_full_vi_elementary_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_formal_logic.yaml b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_formal_logic.yaml new file mode 100644 index 00000000..21a28bb4 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_formal_logic.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _vi_template_yaml +process_docs: !function utils.process_formal_logic +tag: global_mmlu_full_vi_humanities_tasks +task: global_mmlu_full_vi_formal_logic diff --git a/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_global_facts.yaml b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_global_facts.yaml new file mode 100644 index 00000000..a912dba1 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_global_facts.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _vi_template_yaml +process_docs: !function utils.process_global_facts +tag: global_mmlu_full_vi_other_tasks +task: global_mmlu_full_vi_global_facts diff --git a/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_high_school_biology.yaml b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_high_school_biology.yaml new file mode 100644 index 00000000..e334fb1c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_high_school_biology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _vi_template_yaml +process_docs: !function utils.process_high_school_biology +tag: global_mmlu_full_vi_stem_tasks +task: global_mmlu_full_vi_high_school_biology diff --git a/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_high_school_chemistry.yaml b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_high_school_chemistry.yaml new file mode 100644 index 00000000..ba98297e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_high_school_chemistry.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _vi_template_yaml +process_docs: !function utils.process_high_school_chemistry +tag: global_mmlu_full_vi_stem_tasks +task: global_mmlu_full_vi_high_school_chemistry diff --git a/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_high_school_computer_science.yaml b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_high_school_computer_science.yaml new file mode 100644 index 00000000..22e0b00a --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_high_school_computer_science.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _vi_template_yaml +process_docs: !function utils.process_high_school_computer_science +tag: global_mmlu_full_vi_stem_tasks +task: global_mmlu_full_vi_high_school_computer_science diff --git a/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_high_school_european_history.yaml b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_high_school_european_history.yaml new file mode 100644 index 00000000..06507b7c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_high_school_european_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _vi_template_yaml +process_docs: !function utils.process_high_school_european_history +tag: global_mmlu_full_vi_humanities_tasks +task: global_mmlu_full_vi_high_school_european_history diff --git a/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_high_school_geography.yaml b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_high_school_geography.yaml new file mode 100644 index 00000000..d6eeec7a --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_high_school_geography.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _vi_template_yaml +process_docs: !function utils.process_high_school_geography +tag: global_mmlu_full_vi_social_sciences_tasks +task: global_mmlu_full_vi_high_school_geography diff --git a/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_high_school_government_and_politics.yaml b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_high_school_government_and_politics.yaml new file mode 100644 index 00000000..2faf2b09 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_high_school_government_and_politics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _vi_template_yaml +process_docs: !function utils.process_high_school_government_and_politics +tag: global_mmlu_full_vi_social_sciences_tasks +task: global_mmlu_full_vi_high_school_government_and_politics diff --git a/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_high_school_macroeconomics.yaml b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_high_school_macroeconomics.yaml new file mode 100644 index 00000000..16ed50b8 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_high_school_macroeconomics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _vi_template_yaml +process_docs: !function utils.process_high_school_macroeconomics +tag: global_mmlu_full_vi_social_sciences_tasks +task: global_mmlu_full_vi_high_school_macroeconomics diff --git a/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_high_school_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_high_school_mathematics.yaml new file mode 100644 index 00000000..1cad75ec --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_high_school_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _vi_template_yaml +process_docs: !function utils.process_high_school_mathematics +tag: global_mmlu_full_vi_stem_tasks +task: global_mmlu_full_vi_high_school_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_high_school_microeconomics.yaml b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_high_school_microeconomics.yaml new file mode 100644 index 00000000..4499711f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_high_school_microeconomics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _vi_template_yaml +process_docs: !function utils.process_high_school_microeconomics +tag: global_mmlu_full_vi_social_sciences_tasks +task: global_mmlu_full_vi_high_school_microeconomics diff --git a/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_high_school_physics.yaml b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_high_school_physics.yaml new file mode 100644 index 00000000..bb92f446 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_high_school_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _vi_template_yaml +process_docs: !function utils.process_high_school_physics +tag: global_mmlu_full_vi_stem_tasks +task: global_mmlu_full_vi_high_school_physics diff --git a/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_high_school_psychology.yaml b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_high_school_psychology.yaml new file mode 100644 index 00000000..0a12e4de --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_high_school_psychology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _vi_template_yaml +process_docs: !function utils.process_high_school_psychology +tag: global_mmlu_full_vi_social_sciences_tasks +task: global_mmlu_full_vi_high_school_psychology diff --git a/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_high_school_statistics.yaml b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_high_school_statistics.yaml new file mode 100644 index 00000000..3ae34e4d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_high_school_statistics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _vi_template_yaml +process_docs: !function utils.process_high_school_statistics +tag: global_mmlu_full_vi_stem_tasks +task: global_mmlu_full_vi_high_school_statistics diff --git a/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_high_school_us_history.yaml b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_high_school_us_history.yaml new file mode 100644 index 00000000..9ad96b12 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_high_school_us_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _vi_template_yaml +process_docs: !function utils.process_high_school_us_history +tag: global_mmlu_full_vi_humanities_tasks +task: global_mmlu_full_vi_high_school_us_history diff --git a/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_high_school_world_history.yaml b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_high_school_world_history.yaml new file mode 100644 index 00000000..5df3661c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_high_school_world_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _vi_template_yaml +process_docs: !function utils.process_high_school_world_history +tag: global_mmlu_full_vi_humanities_tasks +task: global_mmlu_full_vi_high_school_world_history diff --git a/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_human_aging.yaml b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_human_aging.yaml new file mode 100644 index 00000000..57820fab --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_human_aging.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _vi_template_yaml +process_docs: !function utils.process_human_aging +tag: global_mmlu_full_vi_other_tasks +task: global_mmlu_full_vi_human_aging diff --git a/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_human_sexuality.yaml b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_human_sexuality.yaml new file mode 100644 index 00000000..5b53962b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_human_sexuality.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _vi_template_yaml +process_docs: !function utils.process_human_sexuality +tag: global_mmlu_full_vi_social_sciences_tasks +task: global_mmlu_full_vi_human_sexuality diff --git a/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_international_law.yaml b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_international_law.yaml new file mode 100644 index 00000000..5f81b09e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_international_law.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _vi_template_yaml +process_docs: !function utils.process_international_law +tag: global_mmlu_full_vi_humanities_tasks +task: global_mmlu_full_vi_international_law diff --git a/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_jurisprudence.yaml b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_jurisprudence.yaml new file mode 100644 index 00000000..52ec47d4 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_jurisprudence.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _vi_template_yaml +process_docs: !function utils.process_jurisprudence +tag: global_mmlu_full_vi_humanities_tasks +task: global_mmlu_full_vi_jurisprudence diff --git a/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_logical_fallacies.yaml b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_logical_fallacies.yaml new file mode 100644 index 00000000..ed89994d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_logical_fallacies.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _vi_template_yaml +process_docs: !function utils.process_logical_fallacies +tag: global_mmlu_full_vi_humanities_tasks +task: global_mmlu_full_vi_logical_fallacies diff --git a/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_machine_learning.yaml b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_machine_learning.yaml new file mode 100644 index 00000000..258bd8c4 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_machine_learning.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _vi_template_yaml +process_docs: !function utils.process_machine_learning +tag: global_mmlu_full_vi_stem_tasks +task: global_mmlu_full_vi_machine_learning diff --git a/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_management.yaml b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_management.yaml new file mode 100644 index 00000000..1bd2f606 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_management.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _vi_template_yaml +process_docs: !function utils.process_management +tag: global_mmlu_full_vi_other_tasks +task: global_mmlu_full_vi_management diff --git a/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_marketing.yaml b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_marketing.yaml new file mode 100644 index 00000000..951a3642 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_marketing.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _vi_template_yaml +process_docs: !function utils.process_marketing +tag: global_mmlu_full_vi_other_tasks +task: global_mmlu_full_vi_marketing diff --git a/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_medical_genetics.yaml b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_medical_genetics.yaml new file mode 100644 index 00000000..9d606007 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_medical_genetics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _vi_template_yaml +process_docs: !function utils.process_medical_genetics +tag: global_mmlu_full_vi_other_tasks +task: global_mmlu_full_vi_medical_genetics diff --git a/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_miscellaneous.yaml b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_miscellaneous.yaml new file mode 100644 index 00000000..a0cae1b0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_miscellaneous.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _vi_template_yaml +process_docs: !function utils.process_miscellaneous +tag: global_mmlu_full_vi_other_tasks +task: global_mmlu_full_vi_miscellaneous diff --git a/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_moral_disputes.yaml b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_moral_disputes.yaml new file mode 100644 index 00000000..07987487 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_moral_disputes.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _vi_template_yaml +process_docs: !function utils.process_moral_disputes +tag: global_mmlu_full_vi_humanities_tasks +task: global_mmlu_full_vi_moral_disputes diff --git a/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_moral_scenarios.yaml b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_moral_scenarios.yaml new file mode 100644 index 00000000..6a852bc6 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_moral_scenarios.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _vi_template_yaml +process_docs: !function utils.process_moral_scenarios +tag: global_mmlu_full_vi_humanities_tasks +task: global_mmlu_full_vi_moral_scenarios diff --git a/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_nutrition.yaml b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_nutrition.yaml new file mode 100644 index 00000000..42b198f3 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_nutrition.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _vi_template_yaml +process_docs: !function utils.process_nutrition +tag: global_mmlu_full_vi_other_tasks +task: global_mmlu_full_vi_nutrition diff --git a/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_philosophy.yaml b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_philosophy.yaml new file mode 100644 index 00000000..a7ffc316 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_philosophy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _vi_template_yaml +process_docs: !function utils.process_philosophy +tag: global_mmlu_full_vi_humanities_tasks +task: global_mmlu_full_vi_philosophy diff --git a/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_prehistory.yaml b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_prehistory.yaml new file mode 100644 index 00000000..96349674 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_prehistory.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _vi_template_yaml +process_docs: !function utils.process_prehistory +tag: global_mmlu_full_vi_humanities_tasks +task: global_mmlu_full_vi_prehistory diff --git a/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_professional_accounting.yaml b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_professional_accounting.yaml new file mode 100644 index 00000000..da949e34 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_professional_accounting.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _vi_template_yaml +process_docs: !function utils.process_professional_accounting +tag: global_mmlu_full_vi_other_tasks +task: global_mmlu_full_vi_professional_accounting diff --git a/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_professional_law.yaml b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_professional_law.yaml new file mode 100644 index 00000000..81c74535 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_professional_law.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _vi_template_yaml +process_docs: !function utils.process_professional_law +tag: global_mmlu_full_vi_humanities_tasks +task: global_mmlu_full_vi_professional_law diff --git a/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_professional_medicine.yaml b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_professional_medicine.yaml new file mode 100644 index 00000000..7315b353 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_professional_medicine.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _vi_template_yaml +process_docs: !function utils.process_professional_medicine +tag: global_mmlu_full_vi_other_tasks +task: global_mmlu_full_vi_professional_medicine diff --git a/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_professional_psychology.yaml b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_professional_psychology.yaml new file mode 100644 index 00000000..f2eb1652 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_professional_psychology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _vi_template_yaml +process_docs: !function utils.process_professional_psychology +tag: global_mmlu_full_vi_social_sciences_tasks +task: global_mmlu_full_vi_professional_psychology diff --git a/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_public_relations.yaml b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_public_relations.yaml new file mode 100644 index 00000000..12933f08 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_public_relations.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _vi_template_yaml +process_docs: !function utils.process_public_relations +tag: global_mmlu_full_vi_social_sciences_tasks +task: global_mmlu_full_vi_public_relations diff --git a/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_security_studies.yaml b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_security_studies.yaml new file mode 100644 index 00000000..7e90ba55 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_security_studies.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _vi_template_yaml +process_docs: !function utils.process_security_studies +tag: global_mmlu_full_vi_social_sciences_tasks +task: global_mmlu_full_vi_security_studies diff --git a/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_sociology.yaml b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_sociology.yaml new file mode 100644 index 00000000..056c757b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_sociology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _vi_template_yaml +process_docs: !function utils.process_sociology +tag: global_mmlu_full_vi_social_sciences_tasks +task: global_mmlu_full_vi_sociology diff --git a/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_us_foreign_policy.yaml b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_us_foreign_policy.yaml new file mode 100644 index 00000000..5bcd95d6 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_us_foreign_policy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _vi_template_yaml +process_docs: !function utils.process_us_foreign_policy +tag: global_mmlu_full_vi_social_sciences_tasks +task: global_mmlu_full_vi_us_foreign_policy diff --git a/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_virology.yaml b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_virology.yaml new file mode 100644 index 00000000..775b0cca --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_virology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _vi_template_yaml +process_docs: !function utils.process_virology +tag: global_mmlu_full_vi_other_tasks +task: global_mmlu_full_vi_virology diff --git a/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_world_religions.yaml b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_world_religions.yaml new file mode 100644 index 00000000..db6ba6e0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/vi/global_mmlu_full_vi_world_religions.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _vi_template_yaml +process_docs: !function utils.process_world_religions +tag: global_mmlu_full_vi_humanities_tasks +task: global_mmlu_full_vi_world_religions diff --git a/lm_eval/tasks/global_mmlu/full/vi/utils.py b/lm_eval/tasks/global_mmlu/full/vi/utils.py new file mode 100644 index 00000000..7df72cb0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/vi/utils.py @@ -0,0 +1,73 @@ +from functools import partial + + +SUBJECTS = [ + "abstract_algebra", + "anatomy", + "astronomy", + "business_ethics", + "clinical_knowledge", + "college_biology", + "college_chemistry", + "college_computer_science", + "college_mathematics", + "college_medicine", + "college_physics", + "computer_security", + "conceptual_physics", + "econometrics", + "electrical_engineering", + "elementary_mathematics", + "formal_logic", + "global_facts", + "high_school_biology", + "high_school_chemistry", + "high_school_computer_science", + "high_school_european_history", + "high_school_geography", + "high_school_government_and_politics", + "high_school_macroeconomics", + "high_school_mathematics", + "high_school_microeconomics", + "high_school_physics", + "high_school_psychology", + "high_school_statistics", + "high_school_us_history", + "high_school_world_history", + "human_aging", + "human_sexuality", + "international_law", + "jurisprudence", + "logical_fallacies", + "machine_learning", + "management", + "marketing", + "medical_genetics", + "miscellaneous", + "moral_disputes", + "moral_scenarios", + "nutrition", + "philosophy", + "prehistory", + "professional_accounting", + "professional_law", + "professional_medicine", + "professional_psychology", + "public_relations", + "security_studies", + "sociology", + "us_foreign_policy", + "virology", + "world_religions", +] + + +def process_docs(dataset, subject): + return dataset.filter(lambda x: x["subject"] == subject) + + +process_functions = { + f"process_{subject}": partial(process_docs, subject=subject) for subject in SUBJECTS +} + +globals().update(process_functions) diff --git a/lm_eval/tasks/global_mmlu/full/yo/_global_mmlu_full_yo.yaml b/lm_eval/tasks/global_mmlu/full/yo/_global_mmlu_full_yo.yaml new file mode 100644 index 00000000..ba9f2460 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/yo/_global_mmlu_full_yo.yaml @@ -0,0 +1,11 @@ +group: global_mmlu_full_yo +task: + - global_mmlu_full_yo_stem + - global_mmlu_full_yo_other + - global_mmlu_full_yo_social_sciences + - global_mmlu_full_yo_humanities +aggregate_metric_list: + - metric: acc + weight_by_size: True +metadata: + version: 1.0 diff --git a/lm_eval/tasks/global_mmlu/full/yo/_global_mmlu_full_yo_humanities.yaml b/lm_eval/tasks/global_mmlu/full/yo/_global_mmlu_full_yo_humanities.yaml new file mode 100644 index 00000000..4e3b3c11 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/yo/_global_mmlu_full_yo_humanities.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_yo_humanities +task: + - global_mmlu_full_yo_humanities_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/yo/_global_mmlu_full_yo_other.yaml b/lm_eval/tasks/global_mmlu/full/yo/_global_mmlu_full_yo_other.yaml new file mode 100644 index 00000000..ed81bdfe --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/yo/_global_mmlu_full_yo_other.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_yo_other +task: + - global_mmlu_full_yo_other_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/yo/_global_mmlu_full_yo_social_sciences.yaml b/lm_eval/tasks/global_mmlu/full/yo/_global_mmlu_full_yo_social_sciences.yaml new file mode 100644 index 00000000..bab52fa2 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/yo/_global_mmlu_full_yo_social_sciences.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_yo_social_sciences +task: + - global_mmlu_full_yo_social_sciences_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/yo/_global_mmlu_full_yo_stem.yaml b/lm_eval/tasks/global_mmlu/full/yo/_global_mmlu_full_yo_stem.yaml new file mode 100644 index 00000000..3687d569 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/yo/_global_mmlu_full_yo_stem.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_yo_stem +task: + - global_mmlu_full_yo_stem_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/yo/_yo_template_yaml b/lm_eval/tasks/global_mmlu/full/yo/_yo_template_yaml new file mode 100644 index 00000000..ceefadf5 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/yo/_yo_template_yaml @@ -0,0 +1,16 @@ +dataset_path: CohereForAI/Global-MMLU +dataset_name: yo +test_split: test +fewshot_split: dev +fewshot_config: + sampler: first_n +output_type: multiple_choice +doc_to_text: "{{question.strip()}}\nA. {{option_a}}\nB. {{option_b}}\nC. {{option_c}}\nD. {{option_d}}\nAnswer:" +doc_to_choice: ["A", "B", "C", "D"] +doc_to_target: answer +metric_list: + - metric: acc + aggregation: mean + higher_is_better: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_abstract_algebra.yaml b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_abstract_algebra.yaml new file mode 100644 index 00000000..ef817a38 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_abstract_algebra.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _yo_template_yaml +process_docs: !function utils.process_abstract_algebra +tag: global_mmlu_full_yo_stem_tasks +task: global_mmlu_full_yo_abstract_algebra diff --git a/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_anatomy.yaml b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_anatomy.yaml new file mode 100644 index 00000000..a3bae5d5 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_anatomy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _yo_template_yaml +process_docs: !function utils.process_anatomy +tag: global_mmlu_full_yo_stem_tasks +task: global_mmlu_full_yo_anatomy diff --git a/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_astronomy.yaml b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_astronomy.yaml new file mode 100644 index 00000000..b39aa143 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_astronomy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _yo_template_yaml +process_docs: !function utils.process_astronomy +tag: global_mmlu_full_yo_stem_tasks +task: global_mmlu_full_yo_astronomy diff --git a/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_business_ethics.yaml b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_business_ethics.yaml new file mode 100644 index 00000000..58832982 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_business_ethics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _yo_template_yaml +process_docs: !function utils.process_business_ethics +tag: global_mmlu_full_yo_other_tasks +task: global_mmlu_full_yo_business_ethics diff --git a/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_clinical_knowledge.yaml b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_clinical_knowledge.yaml new file mode 100644 index 00000000..21dcf842 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_clinical_knowledge.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _yo_template_yaml +process_docs: !function utils.process_clinical_knowledge +tag: global_mmlu_full_yo_other_tasks +task: global_mmlu_full_yo_clinical_knowledge diff --git a/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_college_biology.yaml b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_college_biology.yaml new file mode 100644 index 00000000..f3abaf24 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_college_biology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _yo_template_yaml +process_docs: !function utils.process_college_biology +tag: global_mmlu_full_yo_stem_tasks +task: global_mmlu_full_yo_college_biology diff --git a/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_college_chemistry.yaml b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_college_chemistry.yaml new file mode 100644 index 00000000..0468634b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_college_chemistry.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _yo_template_yaml +process_docs: !function utils.process_college_chemistry +tag: global_mmlu_full_yo_stem_tasks +task: global_mmlu_full_yo_college_chemistry diff --git a/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_college_computer_science.yaml b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_college_computer_science.yaml new file mode 100644 index 00000000..df6e5844 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_college_computer_science.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _yo_template_yaml +process_docs: !function utils.process_college_computer_science +tag: global_mmlu_full_yo_stem_tasks +task: global_mmlu_full_yo_college_computer_science diff --git a/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_college_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_college_mathematics.yaml new file mode 100644 index 00000000..0542a4fe --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_college_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _yo_template_yaml +process_docs: !function utils.process_college_mathematics +tag: global_mmlu_full_yo_stem_tasks +task: global_mmlu_full_yo_college_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_college_medicine.yaml b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_college_medicine.yaml new file mode 100644 index 00000000..cce0b497 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_college_medicine.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _yo_template_yaml +process_docs: !function utils.process_college_medicine +tag: global_mmlu_full_yo_other_tasks +task: global_mmlu_full_yo_college_medicine diff --git a/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_college_physics.yaml b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_college_physics.yaml new file mode 100644 index 00000000..84ca1413 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_college_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _yo_template_yaml +process_docs: !function utils.process_college_physics +tag: global_mmlu_full_yo_stem_tasks +task: global_mmlu_full_yo_college_physics diff --git a/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_computer_security.yaml b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_computer_security.yaml new file mode 100644 index 00000000..001689e9 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_computer_security.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _yo_template_yaml +process_docs: !function utils.process_computer_security +tag: global_mmlu_full_yo_stem_tasks +task: global_mmlu_full_yo_computer_security diff --git a/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_conceptual_physics.yaml b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_conceptual_physics.yaml new file mode 100644 index 00000000..dcff962c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_conceptual_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _yo_template_yaml +process_docs: !function utils.process_conceptual_physics +tag: global_mmlu_full_yo_stem_tasks +task: global_mmlu_full_yo_conceptual_physics diff --git a/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_econometrics.yaml b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_econometrics.yaml new file mode 100644 index 00000000..6d055d6d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_econometrics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _yo_template_yaml +process_docs: !function utils.process_econometrics +tag: global_mmlu_full_yo_social_sciences_tasks +task: global_mmlu_full_yo_econometrics diff --git a/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_electrical_engineering.yaml b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_electrical_engineering.yaml new file mode 100644 index 00000000..c21f7f02 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_electrical_engineering.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _yo_template_yaml +process_docs: !function utils.process_electrical_engineering +tag: global_mmlu_full_yo_stem_tasks +task: global_mmlu_full_yo_electrical_engineering diff --git a/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_elementary_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_elementary_mathematics.yaml new file mode 100644 index 00000000..9b6173f0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_elementary_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _yo_template_yaml +process_docs: !function utils.process_elementary_mathematics +tag: global_mmlu_full_yo_stem_tasks +task: global_mmlu_full_yo_elementary_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_formal_logic.yaml b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_formal_logic.yaml new file mode 100644 index 00000000..2ffc9740 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_formal_logic.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _yo_template_yaml +process_docs: !function utils.process_formal_logic +tag: global_mmlu_full_yo_humanities_tasks +task: global_mmlu_full_yo_formal_logic diff --git a/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_global_facts.yaml b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_global_facts.yaml new file mode 100644 index 00000000..394a143a --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_global_facts.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _yo_template_yaml +process_docs: !function utils.process_global_facts +tag: global_mmlu_full_yo_other_tasks +task: global_mmlu_full_yo_global_facts diff --git a/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_high_school_biology.yaml b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_high_school_biology.yaml new file mode 100644 index 00000000..f0de1887 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_high_school_biology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _yo_template_yaml +process_docs: !function utils.process_high_school_biology +tag: global_mmlu_full_yo_stem_tasks +task: global_mmlu_full_yo_high_school_biology diff --git a/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_high_school_chemistry.yaml b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_high_school_chemistry.yaml new file mode 100644 index 00000000..02b16fae --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_high_school_chemistry.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _yo_template_yaml +process_docs: !function utils.process_high_school_chemistry +tag: global_mmlu_full_yo_stem_tasks +task: global_mmlu_full_yo_high_school_chemistry diff --git a/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_high_school_computer_science.yaml b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_high_school_computer_science.yaml new file mode 100644 index 00000000..94733faa --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_high_school_computer_science.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _yo_template_yaml +process_docs: !function utils.process_high_school_computer_science +tag: global_mmlu_full_yo_stem_tasks +task: global_mmlu_full_yo_high_school_computer_science diff --git a/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_high_school_european_history.yaml b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_high_school_european_history.yaml new file mode 100644 index 00000000..6ec4070e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_high_school_european_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _yo_template_yaml +process_docs: !function utils.process_high_school_european_history +tag: global_mmlu_full_yo_humanities_tasks +task: global_mmlu_full_yo_high_school_european_history diff --git a/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_high_school_geography.yaml b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_high_school_geography.yaml new file mode 100644 index 00000000..4ab051d9 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_high_school_geography.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _yo_template_yaml +process_docs: !function utils.process_high_school_geography +tag: global_mmlu_full_yo_social_sciences_tasks +task: global_mmlu_full_yo_high_school_geography diff --git a/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_high_school_government_and_politics.yaml b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_high_school_government_and_politics.yaml new file mode 100644 index 00000000..bedf7f20 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_high_school_government_and_politics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _yo_template_yaml +process_docs: !function utils.process_high_school_government_and_politics +tag: global_mmlu_full_yo_social_sciences_tasks +task: global_mmlu_full_yo_high_school_government_and_politics diff --git a/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_high_school_macroeconomics.yaml b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_high_school_macroeconomics.yaml new file mode 100644 index 00000000..cb486709 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_high_school_macroeconomics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _yo_template_yaml +process_docs: !function utils.process_high_school_macroeconomics +tag: global_mmlu_full_yo_social_sciences_tasks +task: global_mmlu_full_yo_high_school_macroeconomics diff --git a/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_high_school_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_high_school_mathematics.yaml new file mode 100644 index 00000000..cea21a89 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_high_school_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _yo_template_yaml +process_docs: !function utils.process_high_school_mathematics +tag: global_mmlu_full_yo_stem_tasks +task: global_mmlu_full_yo_high_school_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_high_school_microeconomics.yaml b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_high_school_microeconomics.yaml new file mode 100644 index 00000000..a8eae6cd --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_high_school_microeconomics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _yo_template_yaml +process_docs: !function utils.process_high_school_microeconomics +tag: global_mmlu_full_yo_social_sciences_tasks +task: global_mmlu_full_yo_high_school_microeconomics diff --git a/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_high_school_physics.yaml b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_high_school_physics.yaml new file mode 100644 index 00000000..cdaca54f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_high_school_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _yo_template_yaml +process_docs: !function utils.process_high_school_physics +tag: global_mmlu_full_yo_stem_tasks +task: global_mmlu_full_yo_high_school_physics diff --git a/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_high_school_psychology.yaml b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_high_school_psychology.yaml new file mode 100644 index 00000000..ef3d7527 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_high_school_psychology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _yo_template_yaml +process_docs: !function utils.process_high_school_psychology +tag: global_mmlu_full_yo_social_sciences_tasks +task: global_mmlu_full_yo_high_school_psychology diff --git a/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_high_school_statistics.yaml b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_high_school_statistics.yaml new file mode 100644 index 00000000..0ec62db0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_high_school_statistics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _yo_template_yaml +process_docs: !function utils.process_high_school_statistics +tag: global_mmlu_full_yo_stem_tasks +task: global_mmlu_full_yo_high_school_statistics diff --git a/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_high_school_us_history.yaml b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_high_school_us_history.yaml new file mode 100644 index 00000000..30c8573c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_high_school_us_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _yo_template_yaml +process_docs: !function utils.process_high_school_us_history +tag: global_mmlu_full_yo_humanities_tasks +task: global_mmlu_full_yo_high_school_us_history diff --git a/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_high_school_world_history.yaml b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_high_school_world_history.yaml new file mode 100644 index 00000000..52f91d43 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_high_school_world_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _yo_template_yaml +process_docs: !function utils.process_high_school_world_history +tag: global_mmlu_full_yo_humanities_tasks +task: global_mmlu_full_yo_high_school_world_history diff --git a/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_human_aging.yaml b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_human_aging.yaml new file mode 100644 index 00000000..4ab0ec2b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_human_aging.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _yo_template_yaml +process_docs: !function utils.process_human_aging +tag: global_mmlu_full_yo_other_tasks +task: global_mmlu_full_yo_human_aging diff --git a/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_human_sexuality.yaml b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_human_sexuality.yaml new file mode 100644 index 00000000..f510c2d1 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_human_sexuality.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _yo_template_yaml +process_docs: !function utils.process_human_sexuality +tag: global_mmlu_full_yo_social_sciences_tasks +task: global_mmlu_full_yo_human_sexuality diff --git a/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_international_law.yaml b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_international_law.yaml new file mode 100644 index 00000000..9b657110 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_international_law.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _yo_template_yaml +process_docs: !function utils.process_international_law +tag: global_mmlu_full_yo_humanities_tasks +task: global_mmlu_full_yo_international_law diff --git a/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_jurisprudence.yaml b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_jurisprudence.yaml new file mode 100644 index 00000000..e3ac0a52 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_jurisprudence.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _yo_template_yaml +process_docs: !function utils.process_jurisprudence +tag: global_mmlu_full_yo_humanities_tasks +task: global_mmlu_full_yo_jurisprudence diff --git a/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_logical_fallacies.yaml b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_logical_fallacies.yaml new file mode 100644 index 00000000..a7a9e718 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_logical_fallacies.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _yo_template_yaml +process_docs: !function utils.process_logical_fallacies +tag: global_mmlu_full_yo_humanities_tasks +task: global_mmlu_full_yo_logical_fallacies diff --git a/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_machine_learning.yaml b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_machine_learning.yaml new file mode 100644 index 00000000..4a61d3ae --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_machine_learning.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _yo_template_yaml +process_docs: !function utils.process_machine_learning +tag: global_mmlu_full_yo_stem_tasks +task: global_mmlu_full_yo_machine_learning diff --git a/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_management.yaml b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_management.yaml new file mode 100644 index 00000000..92b0b526 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_management.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _yo_template_yaml +process_docs: !function utils.process_management +tag: global_mmlu_full_yo_other_tasks +task: global_mmlu_full_yo_management diff --git a/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_marketing.yaml b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_marketing.yaml new file mode 100644 index 00000000..74c17559 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_marketing.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _yo_template_yaml +process_docs: !function utils.process_marketing +tag: global_mmlu_full_yo_other_tasks +task: global_mmlu_full_yo_marketing diff --git a/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_medical_genetics.yaml b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_medical_genetics.yaml new file mode 100644 index 00000000..cfc2c8cb --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_medical_genetics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _yo_template_yaml +process_docs: !function utils.process_medical_genetics +tag: global_mmlu_full_yo_other_tasks +task: global_mmlu_full_yo_medical_genetics diff --git a/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_miscellaneous.yaml b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_miscellaneous.yaml new file mode 100644 index 00000000..ad12bde6 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_miscellaneous.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _yo_template_yaml +process_docs: !function utils.process_miscellaneous +tag: global_mmlu_full_yo_other_tasks +task: global_mmlu_full_yo_miscellaneous diff --git a/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_moral_disputes.yaml b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_moral_disputes.yaml new file mode 100644 index 00000000..2e85331c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_moral_disputes.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _yo_template_yaml +process_docs: !function utils.process_moral_disputes +tag: global_mmlu_full_yo_humanities_tasks +task: global_mmlu_full_yo_moral_disputes diff --git a/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_moral_scenarios.yaml b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_moral_scenarios.yaml new file mode 100644 index 00000000..9a6a6fc6 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_moral_scenarios.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _yo_template_yaml +process_docs: !function utils.process_moral_scenarios +tag: global_mmlu_full_yo_humanities_tasks +task: global_mmlu_full_yo_moral_scenarios diff --git a/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_nutrition.yaml b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_nutrition.yaml new file mode 100644 index 00000000..62d9ae7b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_nutrition.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _yo_template_yaml +process_docs: !function utils.process_nutrition +tag: global_mmlu_full_yo_other_tasks +task: global_mmlu_full_yo_nutrition diff --git a/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_philosophy.yaml b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_philosophy.yaml new file mode 100644 index 00000000..de42ec7a --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_philosophy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _yo_template_yaml +process_docs: !function utils.process_philosophy +tag: global_mmlu_full_yo_humanities_tasks +task: global_mmlu_full_yo_philosophy diff --git a/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_prehistory.yaml b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_prehistory.yaml new file mode 100644 index 00000000..e2ad3236 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_prehistory.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _yo_template_yaml +process_docs: !function utils.process_prehistory +tag: global_mmlu_full_yo_humanities_tasks +task: global_mmlu_full_yo_prehistory diff --git a/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_professional_accounting.yaml b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_professional_accounting.yaml new file mode 100644 index 00000000..198f227b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_professional_accounting.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _yo_template_yaml +process_docs: !function utils.process_professional_accounting +tag: global_mmlu_full_yo_other_tasks +task: global_mmlu_full_yo_professional_accounting diff --git a/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_professional_law.yaml b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_professional_law.yaml new file mode 100644 index 00000000..e5942f74 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_professional_law.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _yo_template_yaml +process_docs: !function utils.process_professional_law +tag: global_mmlu_full_yo_humanities_tasks +task: global_mmlu_full_yo_professional_law diff --git a/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_professional_medicine.yaml b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_professional_medicine.yaml new file mode 100644 index 00000000..efd4ab7d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_professional_medicine.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _yo_template_yaml +process_docs: !function utils.process_professional_medicine +tag: global_mmlu_full_yo_other_tasks +task: global_mmlu_full_yo_professional_medicine diff --git a/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_professional_psychology.yaml b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_professional_psychology.yaml new file mode 100644 index 00000000..e1956c87 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_professional_psychology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _yo_template_yaml +process_docs: !function utils.process_professional_psychology +tag: global_mmlu_full_yo_social_sciences_tasks +task: global_mmlu_full_yo_professional_psychology diff --git a/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_public_relations.yaml b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_public_relations.yaml new file mode 100644 index 00000000..5c6c2b8c --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_public_relations.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _yo_template_yaml +process_docs: !function utils.process_public_relations +tag: global_mmlu_full_yo_social_sciences_tasks +task: global_mmlu_full_yo_public_relations diff --git a/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_security_studies.yaml b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_security_studies.yaml new file mode 100644 index 00000000..a12c4abd --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_security_studies.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _yo_template_yaml +process_docs: !function utils.process_security_studies +tag: global_mmlu_full_yo_social_sciences_tasks +task: global_mmlu_full_yo_security_studies diff --git a/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_sociology.yaml b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_sociology.yaml new file mode 100644 index 00000000..e5747900 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_sociology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _yo_template_yaml +process_docs: !function utils.process_sociology +tag: global_mmlu_full_yo_social_sciences_tasks +task: global_mmlu_full_yo_sociology diff --git a/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_us_foreign_policy.yaml b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_us_foreign_policy.yaml new file mode 100644 index 00000000..493dda39 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_us_foreign_policy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _yo_template_yaml +process_docs: !function utils.process_us_foreign_policy +tag: global_mmlu_full_yo_social_sciences_tasks +task: global_mmlu_full_yo_us_foreign_policy diff --git a/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_virology.yaml b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_virology.yaml new file mode 100644 index 00000000..420b1b01 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_virology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _yo_template_yaml +process_docs: !function utils.process_virology +tag: global_mmlu_full_yo_other_tasks +task: global_mmlu_full_yo_virology diff --git a/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_world_religions.yaml b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_world_religions.yaml new file mode 100644 index 00000000..c0964b30 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/yo/global_mmlu_full_yo_world_religions.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _yo_template_yaml +process_docs: !function utils.process_world_religions +tag: global_mmlu_full_yo_humanities_tasks +task: global_mmlu_full_yo_world_religions diff --git a/lm_eval/tasks/global_mmlu/full/yo/utils.py b/lm_eval/tasks/global_mmlu/full/yo/utils.py new file mode 100644 index 00000000..7df72cb0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/yo/utils.py @@ -0,0 +1,73 @@ +from functools import partial + + +SUBJECTS = [ + "abstract_algebra", + "anatomy", + "astronomy", + "business_ethics", + "clinical_knowledge", + "college_biology", + "college_chemistry", + "college_computer_science", + "college_mathematics", + "college_medicine", + "college_physics", + "computer_security", + "conceptual_physics", + "econometrics", + "electrical_engineering", + "elementary_mathematics", + "formal_logic", + "global_facts", + "high_school_biology", + "high_school_chemistry", + "high_school_computer_science", + "high_school_european_history", + "high_school_geography", + "high_school_government_and_politics", + "high_school_macroeconomics", + "high_school_mathematics", + "high_school_microeconomics", + "high_school_physics", + "high_school_psychology", + "high_school_statistics", + "high_school_us_history", + "high_school_world_history", + "human_aging", + "human_sexuality", + "international_law", + "jurisprudence", + "logical_fallacies", + "machine_learning", + "management", + "marketing", + "medical_genetics", + "miscellaneous", + "moral_disputes", + "moral_scenarios", + "nutrition", + "philosophy", + "prehistory", + "professional_accounting", + "professional_law", + "professional_medicine", + "professional_psychology", + "public_relations", + "security_studies", + "sociology", + "us_foreign_policy", + "virology", + "world_religions", +] + + +def process_docs(dataset, subject): + return dataset.filter(lambda x: x["subject"] == subject) + + +process_functions = { + f"process_{subject}": partial(process_docs, subject=subject) for subject in SUBJECTS +} + +globals().update(process_functions) diff --git a/lm_eval/tasks/global_mmlu/full/zh/_global_mmlu_full_zh.yaml b/lm_eval/tasks/global_mmlu/full/zh/_global_mmlu_full_zh.yaml new file mode 100644 index 00000000..098ec097 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/zh/_global_mmlu_full_zh.yaml @@ -0,0 +1,11 @@ +group: global_mmlu_full_zh +task: + - global_mmlu_full_zh_stem + - global_mmlu_full_zh_other + - global_mmlu_full_zh_social_sciences + - global_mmlu_full_zh_humanities +aggregate_metric_list: + - metric: acc + weight_by_size: True +metadata: + version: 1.0 diff --git a/lm_eval/tasks/global_mmlu/full/zh/_global_mmlu_full_zh_humanities.yaml b/lm_eval/tasks/global_mmlu/full/zh/_global_mmlu_full_zh_humanities.yaml new file mode 100644 index 00000000..fb347da8 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/zh/_global_mmlu_full_zh_humanities.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_zh_humanities +task: + - global_mmlu_full_zh_humanities_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/zh/_global_mmlu_full_zh_other.yaml b/lm_eval/tasks/global_mmlu/full/zh/_global_mmlu_full_zh_other.yaml new file mode 100644 index 00000000..98d4ed5e --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/zh/_global_mmlu_full_zh_other.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_zh_other +task: + - global_mmlu_full_zh_other_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/zh/_global_mmlu_full_zh_social_sciences.yaml b/lm_eval/tasks/global_mmlu/full/zh/_global_mmlu_full_zh_social_sciences.yaml new file mode 100644 index 00000000..235012e6 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/zh/_global_mmlu_full_zh_social_sciences.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_zh_social_sciences +task: + - global_mmlu_full_zh_social_sciences_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/zh/_global_mmlu_full_zh_stem.yaml b/lm_eval/tasks/global_mmlu/full/zh/_global_mmlu_full_zh_stem.yaml new file mode 100644 index 00000000..660486a4 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/zh/_global_mmlu_full_zh_stem.yaml @@ -0,0 +1,8 @@ +group: global_mmlu_full_zh_stem +task: + - global_mmlu_full_zh_stem_tasks +aggregate_metric_list: + - metric: acc + weight_by_size: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/zh/_zh_template_yaml b/lm_eval/tasks/global_mmlu/full/zh/_zh_template_yaml new file mode 100644 index 00000000..2c83d495 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/zh/_zh_template_yaml @@ -0,0 +1,16 @@ +dataset_path: CohereForAI/Global-MMLU +dataset_name: zh +test_split: test +fewshot_split: dev +fewshot_config: + sampler: first_n +output_type: multiple_choice +doc_to_text: "{{question.strip()}}\nA. {{option_a}}\nB. {{option_b}}\nC. {{option_c}}\nD. {{option_d}}\nAnswer:" +doc_to_choice: ["A", "B", "C", "D"] +doc_to_target: answer +metric_list: + - metric: acc + aggregation: mean + higher_is_better: true +metadata: + version: 0.0 diff --git a/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_abstract_algebra.yaml b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_abstract_algebra.yaml new file mode 100644 index 00000000..42ea6276 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_abstract_algebra.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _zh_template_yaml +process_docs: !function utils.process_abstract_algebra +tag: global_mmlu_full_zh_stem_tasks +task: global_mmlu_full_zh_abstract_algebra diff --git a/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_anatomy.yaml b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_anatomy.yaml new file mode 100644 index 00000000..45001d14 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_anatomy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _zh_template_yaml +process_docs: !function utils.process_anatomy +tag: global_mmlu_full_zh_stem_tasks +task: global_mmlu_full_zh_anatomy diff --git a/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_astronomy.yaml b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_astronomy.yaml new file mode 100644 index 00000000..37183dc7 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_astronomy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _zh_template_yaml +process_docs: !function utils.process_astronomy +tag: global_mmlu_full_zh_stem_tasks +task: global_mmlu_full_zh_astronomy diff --git a/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_business_ethics.yaml b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_business_ethics.yaml new file mode 100644 index 00000000..bbb5ea38 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_business_ethics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _zh_template_yaml +process_docs: !function utils.process_business_ethics +tag: global_mmlu_full_zh_other_tasks +task: global_mmlu_full_zh_business_ethics diff --git a/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_clinical_knowledge.yaml b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_clinical_knowledge.yaml new file mode 100644 index 00000000..d90ee0ea --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_clinical_knowledge.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _zh_template_yaml +process_docs: !function utils.process_clinical_knowledge +tag: global_mmlu_full_zh_other_tasks +task: global_mmlu_full_zh_clinical_knowledge diff --git a/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_college_biology.yaml b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_college_biology.yaml new file mode 100644 index 00000000..ba2031fe --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_college_biology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _zh_template_yaml +process_docs: !function utils.process_college_biology +tag: global_mmlu_full_zh_stem_tasks +task: global_mmlu_full_zh_college_biology diff --git a/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_college_chemistry.yaml b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_college_chemistry.yaml new file mode 100644 index 00000000..860761b4 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_college_chemistry.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _zh_template_yaml +process_docs: !function utils.process_college_chemistry +tag: global_mmlu_full_zh_stem_tasks +task: global_mmlu_full_zh_college_chemistry diff --git a/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_college_computer_science.yaml b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_college_computer_science.yaml new file mode 100644 index 00000000..53d01965 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_college_computer_science.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _zh_template_yaml +process_docs: !function utils.process_college_computer_science +tag: global_mmlu_full_zh_stem_tasks +task: global_mmlu_full_zh_college_computer_science diff --git a/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_college_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_college_mathematics.yaml new file mode 100644 index 00000000..dbd2e4be --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_college_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _zh_template_yaml +process_docs: !function utils.process_college_mathematics +tag: global_mmlu_full_zh_stem_tasks +task: global_mmlu_full_zh_college_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_college_medicine.yaml b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_college_medicine.yaml new file mode 100644 index 00000000..523d6b30 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_college_medicine.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _zh_template_yaml +process_docs: !function utils.process_college_medicine +tag: global_mmlu_full_zh_other_tasks +task: global_mmlu_full_zh_college_medicine diff --git a/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_college_physics.yaml b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_college_physics.yaml new file mode 100644 index 00000000..0a08214f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_college_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _zh_template_yaml +process_docs: !function utils.process_college_physics +tag: global_mmlu_full_zh_stem_tasks +task: global_mmlu_full_zh_college_physics diff --git a/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_computer_security.yaml b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_computer_security.yaml new file mode 100644 index 00000000..99332b35 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_computer_security.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _zh_template_yaml +process_docs: !function utils.process_computer_security +tag: global_mmlu_full_zh_stem_tasks +task: global_mmlu_full_zh_computer_security diff --git a/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_conceptual_physics.yaml b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_conceptual_physics.yaml new file mode 100644 index 00000000..b042cc8b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_conceptual_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _zh_template_yaml +process_docs: !function utils.process_conceptual_physics +tag: global_mmlu_full_zh_stem_tasks +task: global_mmlu_full_zh_conceptual_physics diff --git a/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_econometrics.yaml b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_econometrics.yaml new file mode 100644 index 00000000..bf920112 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_econometrics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _zh_template_yaml +process_docs: !function utils.process_econometrics +tag: global_mmlu_full_zh_social_sciences_tasks +task: global_mmlu_full_zh_econometrics diff --git a/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_electrical_engineering.yaml b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_electrical_engineering.yaml new file mode 100644 index 00000000..b30acad7 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_electrical_engineering.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _zh_template_yaml +process_docs: !function utils.process_electrical_engineering +tag: global_mmlu_full_zh_stem_tasks +task: global_mmlu_full_zh_electrical_engineering diff --git a/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_elementary_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_elementary_mathematics.yaml new file mode 100644 index 00000000..3b108c42 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_elementary_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _zh_template_yaml +process_docs: !function utils.process_elementary_mathematics +tag: global_mmlu_full_zh_stem_tasks +task: global_mmlu_full_zh_elementary_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_formal_logic.yaml b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_formal_logic.yaml new file mode 100644 index 00000000..64775599 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_formal_logic.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _zh_template_yaml +process_docs: !function utils.process_formal_logic +tag: global_mmlu_full_zh_humanities_tasks +task: global_mmlu_full_zh_formal_logic diff --git a/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_global_facts.yaml b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_global_facts.yaml new file mode 100644 index 00000000..07d390aa --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_global_facts.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _zh_template_yaml +process_docs: !function utils.process_global_facts +tag: global_mmlu_full_zh_other_tasks +task: global_mmlu_full_zh_global_facts diff --git a/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_high_school_biology.yaml b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_high_school_biology.yaml new file mode 100644 index 00000000..28b2bdaa --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_high_school_biology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _zh_template_yaml +process_docs: !function utils.process_high_school_biology +tag: global_mmlu_full_zh_stem_tasks +task: global_mmlu_full_zh_high_school_biology diff --git a/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_high_school_chemistry.yaml b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_high_school_chemistry.yaml new file mode 100644 index 00000000..4d084034 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_high_school_chemistry.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _zh_template_yaml +process_docs: !function utils.process_high_school_chemistry +tag: global_mmlu_full_zh_stem_tasks +task: global_mmlu_full_zh_high_school_chemistry diff --git a/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_high_school_computer_science.yaml b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_high_school_computer_science.yaml new file mode 100644 index 00000000..6232ef60 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_high_school_computer_science.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _zh_template_yaml +process_docs: !function utils.process_high_school_computer_science +tag: global_mmlu_full_zh_stem_tasks +task: global_mmlu_full_zh_high_school_computer_science diff --git a/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_high_school_european_history.yaml b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_high_school_european_history.yaml new file mode 100644 index 00000000..70e3e52b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_high_school_european_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _zh_template_yaml +process_docs: !function utils.process_high_school_european_history +tag: global_mmlu_full_zh_humanities_tasks +task: global_mmlu_full_zh_high_school_european_history diff --git a/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_high_school_geography.yaml b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_high_school_geography.yaml new file mode 100644 index 00000000..fe6cb913 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_high_school_geography.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _zh_template_yaml +process_docs: !function utils.process_high_school_geography +tag: global_mmlu_full_zh_social_sciences_tasks +task: global_mmlu_full_zh_high_school_geography diff --git a/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_high_school_government_and_politics.yaml b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_high_school_government_and_politics.yaml new file mode 100644 index 00000000..cfa7213a --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_high_school_government_and_politics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _zh_template_yaml +process_docs: !function utils.process_high_school_government_and_politics +tag: global_mmlu_full_zh_social_sciences_tasks +task: global_mmlu_full_zh_high_school_government_and_politics diff --git a/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_high_school_macroeconomics.yaml b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_high_school_macroeconomics.yaml new file mode 100644 index 00000000..ca0b7ad8 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_high_school_macroeconomics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _zh_template_yaml +process_docs: !function utils.process_high_school_macroeconomics +tag: global_mmlu_full_zh_social_sciences_tasks +task: global_mmlu_full_zh_high_school_macroeconomics diff --git a/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_high_school_mathematics.yaml b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_high_school_mathematics.yaml new file mode 100644 index 00000000..38868e96 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_high_school_mathematics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _zh_template_yaml +process_docs: !function utils.process_high_school_mathematics +tag: global_mmlu_full_zh_stem_tasks +task: global_mmlu_full_zh_high_school_mathematics diff --git a/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_high_school_microeconomics.yaml b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_high_school_microeconomics.yaml new file mode 100644 index 00000000..b79237d2 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_high_school_microeconomics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _zh_template_yaml +process_docs: !function utils.process_high_school_microeconomics +tag: global_mmlu_full_zh_social_sciences_tasks +task: global_mmlu_full_zh_high_school_microeconomics diff --git a/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_high_school_physics.yaml b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_high_school_physics.yaml new file mode 100644 index 00000000..6355da2f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_high_school_physics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _zh_template_yaml +process_docs: !function utils.process_high_school_physics +tag: global_mmlu_full_zh_stem_tasks +task: global_mmlu_full_zh_high_school_physics diff --git a/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_high_school_psychology.yaml b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_high_school_psychology.yaml new file mode 100644 index 00000000..f2238867 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_high_school_psychology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _zh_template_yaml +process_docs: !function utils.process_high_school_psychology +tag: global_mmlu_full_zh_social_sciences_tasks +task: global_mmlu_full_zh_high_school_psychology diff --git a/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_high_school_statistics.yaml b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_high_school_statistics.yaml new file mode 100644 index 00000000..9aac2097 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_high_school_statistics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _zh_template_yaml +process_docs: !function utils.process_high_school_statistics +tag: global_mmlu_full_zh_stem_tasks +task: global_mmlu_full_zh_high_school_statistics diff --git a/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_high_school_us_history.yaml b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_high_school_us_history.yaml new file mode 100644 index 00000000..47d8355f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_high_school_us_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _zh_template_yaml +process_docs: !function utils.process_high_school_us_history +tag: global_mmlu_full_zh_humanities_tasks +task: global_mmlu_full_zh_high_school_us_history diff --git a/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_high_school_world_history.yaml b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_high_school_world_history.yaml new file mode 100644 index 00000000..c1f6671f --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_high_school_world_history.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _zh_template_yaml +process_docs: !function utils.process_high_school_world_history +tag: global_mmlu_full_zh_humanities_tasks +task: global_mmlu_full_zh_high_school_world_history diff --git a/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_human_aging.yaml b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_human_aging.yaml new file mode 100644 index 00000000..d6941ff7 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_human_aging.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _zh_template_yaml +process_docs: !function utils.process_human_aging +tag: global_mmlu_full_zh_other_tasks +task: global_mmlu_full_zh_human_aging diff --git a/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_human_sexuality.yaml b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_human_sexuality.yaml new file mode 100644 index 00000000..ee228b22 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_human_sexuality.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _zh_template_yaml +process_docs: !function utils.process_human_sexuality +tag: global_mmlu_full_zh_social_sciences_tasks +task: global_mmlu_full_zh_human_sexuality diff --git a/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_international_law.yaml b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_international_law.yaml new file mode 100644 index 00000000..07b1ebd1 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_international_law.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _zh_template_yaml +process_docs: !function utils.process_international_law +tag: global_mmlu_full_zh_humanities_tasks +task: global_mmlu_full_zh_international_law diff --git a/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_jurisprudence.yaml b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_jurisprudence.yaml new file mode 100644 index 00000000..ab10ffac --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_jurisprudence.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _zh_template_yaml +process_docs: !function utils.process_jurisprudence +tag: global_mmlu_full_zh_humanities_tasks +task: global_mmlu_full_zh_jurisprudence diff --git a/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_logical_fallacies.yaml b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_logical_fallacies.yaml new file mode 100644 index 00000000..451260b5 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_logical_fallacies.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _zh_template_yaml +process_docs: !function utils.process_logical_fallacies +tag: global_mmlu_full_zh_humanities_tasks +task: global_mmlu_full_zh_logical_fallacies diff --git a/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_machine_learning.yaml b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_machine_learning.yaml new file mode 100644 index 00000000..508d14f6 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_machine_learning.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _zh_template_yaml +process_docs: !function utils.process_machine_learning +tag: global_mmlu_full_zh_stem_tasks +task: global_mmlu_full_zh_machine_learning diff --git a/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_management.yaml b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_management.yaml new file mode 100644 index 00000000..9db0b32b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_management.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _zh_template_yaml +process_docs: !function utils.process_management +tag: global_mmlu_full_zh_other_tasks +task: global_mmlu_full_zh_management diff --git a/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_marketing.yaml b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_marketing.yaml new file mode 100644 index 00000000..a7142ce4 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_marketing.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _zh_template_yaml +process_docs: !function utils.process_marketing +tag: global_mmlu_full_zh_other_tasks +task: global_mmlu_full_zh_marketing diff --git a/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_medical_genetics.yaml b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_medical_genetics.yaml new file mode 100644 index 00000000..22053090 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_medical_genetics.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _zh_template_yaml +process_docs: !function utils.process_medical_genetics +tag: global_mmlu_full_zh_other_tasks +task: global_mmlu_full_zh_medical_genetics diff --git a/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_miscellaneous.yaml b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_miscellaneous.yaml new file mode 100644 index 00000000..5b479c9b --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_miscellaneous.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _zh_template_yaml +process_docs: !function utils.process_miscellaneous +tag: global_mmlu_full_zh_other_tasks +task: global_mmlu_full_zh_miscellaneous diff --git a/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_moral_disputes.yaml b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_moral_disputes.yaml new file mode 100644 index 00000000..58d13a99 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_moral_disputes.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _zh_template_yaml +process_docs: !function utils.process_moral_disputes +tag: global_mmlu_full_zh_humanities_tasks +task: global_mmlu_full_zh_moral_disputes diff --git a/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_moral_scenarios.yaml b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_moral_scenarios.yaml new file mode 100644 index 00000000..95d91dfd --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_moral_scenarios.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _zh_template_yaml +process_docs: !function utils.process_moral_scenarios +tag: global_mmlu_full_zh_humanities_tasks +task: global_mmlu_full_zh_moral_scenarios diff --git a/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_nutrition.yaml b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_nutrition.yaml new file mode 100644 index 00000000..57452a39 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_nutrition.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _zh_template_yaml +process_docs: !function utils.process_nutrition +tag: global_mmlu_full_zh_other_tasks +task: global_mmlu_full_zh_nutrition diff --git a/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_philosophy.yaml b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_philosophy.yaml new file mode 100644 index 00000000..20e237b2 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_philosophy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _zh_template_yaml +process_docs: !function utils.process_philosophy +tag: global_mmlu_full_zh_humanities_tasks +task: global_mmlu_full_zh_philosophy diff --git a/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_prehistory.yaml b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_prehistory.yaml new file mode 100644 index 00000000..56358fe7 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_prehistory.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _zh_template_yaml +process_docs: !function utils.process_prehistory +tag: global_mmlu_full_zh_humanities_tasks +task: global_mmlu_full_zh_prehistory diff --git a/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_professional_accounting.yaml b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_professional_accounting.yaml new file mode 100644 index 00000000..630681ab --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_professional_accounting.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _zh_template_yaml +process_docs: !function utils.process_professional_accounting +tag: global_mmlu_full_zh_other_tasks +task: global_mmlu_full_zh_professional_accounting diff --git a/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_professional_law.yaml b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_professional_law.yaml new file mode 100644 index 00000000..e48f35cb --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_professional_law.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _zh_template_yaml +process_docs: !function utils.process_professional_law +tag: global_mmlu_full_zh_humanities_tasks +task: global_mmlu_full_zh_professional_law diff --git a/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_professional_medicine.yaml b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_professional_medicine.yaml new file mode 100644 index 00000000..f75432cd --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_professional_medicine.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _zh_template_yaml +process_docs: !function utils.process_professional_medicine +tag: global_mmlu_full_zh_other_tasks +task: global_mmlu_full_zh_professional_medicine diff --git a/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_professional_psychology.yaml b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_professional_psychology.yaml new file mode 100644 index 00000000..fbbf45ad --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_professional_psychology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _zh_template_yaml +process_docs: !function utils.process_professional_psychology +tag: global_mmlu_full_zh_social_sciences_tasks +task: global_mmlu_full_zh_professional_psychology diff --git a/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_public_relations.yaml b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_public_relations.yaml new file mode 100644 index 00000000..f760d2a2 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_public_relations.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _zh_template_yaml +process_docs: !function utils.process_public_relations +tag: global_mmlu_full_zh_social_sciences_tasks +task: global_mmlu_full_zh_public_relations diff --git a/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_security_studies.yaml b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_security_studies.yaml new file mode 100644 index 00000000..1dafaf5d --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_security_studies.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _zh_template_yaml +process_docs: !function utils.process_security_studies +tag: global_mmlu_full_zh_social_sciences_tasks +task: global_mmlu_full_zh_security_studies diff --git a/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_sociology.yaml b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_sociology.yaml new file mode 100644 index 00000000..549f4ef1 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_sociology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _zh_template_yaml +process_docs: !function utils.process_sociology +tag: global_mmlu_full_zh_social_sciences_tasks +task: global_mmlu_full_zh_sociology diff --git a/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_us_foreign_policy.yaml b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_us_foreign_policy.yaml new file mode 100644 index 00000000..597dcfa1 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_us_foreign_policy.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _zh_template_yaml +process_docs: !function utils.process_us_foreign_policy +tag: global_mmlu_full_zh_social_sciences_tasks +task: global_mmlu_full_zh_us_foreign_policy diff --git a/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_virology.yaml b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_virology.yaml new file mode 100644 index 00000000..1984c6b0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_virology.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _zh_template_yaml +process_docs: !function utils.process_virology +tag: global_mmlu_full_zh_other_tasks +task: global_mmlu_full_zh_virology diff --git a/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_world_religions.yaml b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_world_religions.yaml new file mode 100644 index 00000000..fa15c0cb --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/zh/global_mmlu_full_zh_world_religions.yaml @@ -0,0 +1,5 @@ +# Generated by _generate_configs.py +include: _zh_template_yaml +process_docs: !function utils.process_world_religions +tag: global_mmlu_full_zh_humanities_tasks +task: global_mmlu_full_zh_world_religions diff --git a/lm_eval/tasks/global_mmlu/full/zh/utils.py b/lm_eval/tasks/global_mmlu/full/zh/utils.py new file mode 100644 index 00000000..7df72cb0 --- /dev/null +++ b/lm_eval/tasks/global_mmlu/full/zh/utils.py @@ -0,0 +1,73 @@ +from functools import partial + + +SUBJECTS = [ + "abstract_algebra", + "anatomy", + "astronomy", + "business_ethics", + "clinical_knowledge", + "college_biology", + "college_chemistry", + "college_computer_science", + "college_mathematics", + "college_medicine", + "college_physics", + "computer_security", + "conceptual_physics", + "econometrics", + "electrical_engineering", + "elementary_mathematics", + "formal_logic", + "global_facts", + "high_school_biology", + "high_school_chemistry", + "high_school_computer_science", + "high_school_european_history", + "high_school_geography", + "high_school_government_and_politics", + "high_school_macroeconomics", + "high_school_mathematics", + "high_school_microeconomics", + "high_school_physics", + "high_school_psychology", + "high_school_statistics", + "high_school_us_history", + "high_school_world_history", + "human_aging", + "human_sexuality", + "international_law", + "jurisprudence", + "logical_fallacies", + "machine_learning", + "management", + "marketing", + "medical_genetics", + "miscellaneous", + "moral_disputes", + "moral_scenarios", + "nutrition", + "philosophy", + "prehistory", + "professional_accounting", + "professional_law", + "professional_medicine", + "professional_psychology", + "public_relations", + "security_studies", + "sociology", + "us_foreign_policy", + "virology", + "world_religions", +] + + +def process_docs(dataset, subject): + return dataset.filter(lambda x: x["subject"] == subject) + + +process_functions = { + f"process_{subject}": partial(process_docs, subject=subject) for subject in SUBJECTS +} + +globals().update(process_functions) -- GitLab