Merge remote-tracking branch 'origin/big-refactor' into calibration

lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_jurisprudence.yaml

+"dataset_name": "jurisprudence"
+"description": "The following are multiple choice questions (with answers) about jurisprudence.\n\
+  \n"
+"group": "mmlu_flan_cot_zeroshot_humanities"
+"include": "_mmlu_flan_cot_zeroshot_template_yaml"
+"task": "mmlu_flan_cot_zeroshot_jurisprudence"

lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_logical_fallacies.yaml

+"dataset_name": "logical_fallacies"
+"description": "The following are multiple choice questions (with answers) about logical\
+  \ fallacies.\n\n"
+"group": "mmlu_flan_cot_zeroshot_humanities"
+"include": "_mmlu_flan_cot_zeroshot_template_yaml"
+"task": "mmlu_flan_cot_zeroshot_logical_fallacies"

lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_machine_learning.yaml

+"dataset_name": "machine_learning"
+"description": "The following are multiple choice questions (with answers) about machine\
+  \ learning.\n\n"
+"group": "mmlu_flan_cot_zeroshot_stem"
+"include": "_mmlu_flan_cot_zeroshot_template_yaml"
+"task": "mmlu_flan_cot_zeroshot_machine_learning"

lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_management.yaml

+"dataset_name": "management"
+"description": "The following are multiple choice questions (with answers) about management.\n\
+  \n"
+"group": "mmlu_flan_cot_zeroshot_other"
+"include": "_mmlu_flan_cot_zeroshot_template_yaml"
+"task": "mmlu_flan_cot_zeroshot_management"

lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_marketing.yaml

+"dataset_name": "marketing"
+"description": "The following are multiple choice questions (with answers) about marketing.\n\
+  \n"
+"group": "mmlu_flan_cot_zeroshot_other"
+"include": "_mmlu_flan_cot_zeroshot_template_yaml"
+"task": "mmlu_flan_cot_zeroshot_marketing"

lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_medical_genetics.yaml

+"dataset_name": "medical_genetics"
+"description": "The following are multiple choice questions (with answers) about medical\
+  \ genetics.\n\n"
+"group": "mmlu_flan_cot_zeroshot_other"
+"include": "_mmlu_flan_cot_zeroshot_template_yaml"
+"task": "mmlu_flan_cot_zeroshot_medical_genetics"

lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_miscellaneous.yaml

+"dataset_name": "miscellaneous"
+"description": "The following are multiple choice questions (with answers) about miscellaneous.\n\
+  \n"
+"group": "mmlu_flan_cot_zeroshot_other"
+"include": "_mmlu_flan_cot_zeroshot_template_yaml"
+"task": "mmlu_flan_cot_zeroshot_miscellaneous"

lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_moral_disputes.yaml

+"dataset_name": "moral_disputes"
+"description": "The following are multiple choice questions (with answers) about moral\
+  \ disputes.\n\n"
+"group": "mmlu_flan_cot_zeroshot_humanities"
+"include": "_mmlu_flan_cot_zeroshot_template_yaml"
+"task": "mmlu_flan_cot_zeroshot_moral_disputes"

lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_moral_scenarios.yaml

+"dataset_name": "moral_scenarios"
+"description": "The following are multiple choice questions (with answers) about moral\
+  \ scenarios.\n\n"
+"group": "mmlu_flan_cot_zeroshot_humanities"
+"include": "_mmlu_flan_cot_zeroshot_template_yaml"
+"task": "mmlu_flan_cot_zeroshot_moral_scenarios"

lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_nutrition.yaml

+"dataset_name": "nutrition"
+"description": "The following are multiple choice questions (with answers) about nutrition.\n\
+  \n"
+"group": "mmlu_flan_cot_zeroshot_other"
+"include": "_mmlu_flan_cot_zeroshot_template_yaml"
+"task": "mmlu_flan_cot_zeroshot_nutrition"

lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_philosophy.yaml

+"dataset_name": "philosophy"
+"description": "The following are multiple choice questions (with answers) about philosophy.\n\
+  \n"
+"group": "mmlu_flan_cot_zeroshot_humanities"
+"include": "_mmlu_flan_cot_zeroshot_template_yaml"
+"task": "mmlu_flan_cot_zeroshot_philosophy"

lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_prehistory.yaml

+"dataset_name": "prehistory"
+"description": "The following are multiple choice questions (with answers) about prehistory.\n\
+  \n"
+"group": "mmlu_flan_cot_zeroshot_humanities"
+"include": "_mmlu_flan_cot_zeroshot_template_yaml"
+"task": "mmlu_flan_cot_zeroshot_prehistory"

lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_professional_accounting.yaml

+"dataset_name": "professional_accounting"
+"description": "The following are multiple choice questions (with answers) about professional\
+  \ accounting.\n\n"
+"group": "mmlu_flan_cot_zeroshot_other"
+"include": "_mmlu_flan_cot_zeroshot_template_yaml"
+"task": "mmlu_flan_cot_zeroshot_professional_accounting"

lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_professional_law.yaml

+"dataset_name": "professional_law"
+"description": "The following are multiple choice questions (with answers) about professional\
+  \ law.\n\n"
+"group": "mmlu_flan_cot_zeroshot_humanities"
+"include": "_mmlu_flan_cot_zeroshot_template_yaml"
+"task": "mmlu_flan_cot_zeroshot_professional_law"

lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_professional_medicine.yaml

+"dataset_name": "professional_medicine"
+"description": "The following are multiple choice questions (with answers) about professional\
+  \ medicine.\n\n"
+"group": "mmlu_flan_cot_zeroshot_other"
+"include": "_mmlu_flan_cot_zeroshot_template_yaml"
+"task": "mmlu_flan_cot_zeroshot_professional_medicine"

lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_professional_psychology.yaml

+"dataset_name": "professional_psychology"
+"description": "The following are multiple choice questions (with answers) about professional\
+  \ psychology.\n\n"
+"group": "mmlu_flan_cot_zeroshot_social_sciences"
+"include": "_mmlu_flan_cot_zeroshot_template_yaml"
+"task": "mmlu_flan_cot_zeroshot_professional_psychology"

lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_public_relations.yaml

+"dataset_name": "public_relations"
+"description": "The following are multiple choice questions (with answers) about public\
+  \ relations.\n\n"
+"group": "mmlu_flan_cot_zeroshot_social_sciences"
+"include": "_mmlu_flan_cot_zeroshot_template_yaml"
+"task": "mmlu_flan_cot_zeroshot_public_relations"

lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_security_studies.yaml

+"dataset_name": "security_studies"
+"description": "The following are multiple choice questions (with answers) about security\
+  \ studies.\n\n"
+"group": "mmlu_flan_cot_zeroshot_social_sciences"
+"include": "_mmlu_flan_cot_zeroshot_template_yaml"
+"task": "mmlu_flan_cot_zeroshot_security_studies"

lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_sociology.yaml

+"dataset_name": "sociology"
+"description": "The following are multiple choice questions (with answers) about sociology.\n\
+  \n"
+"group": "mmlu_flan_cot_zeroshot_social_sciences"
+"include": "_mmlu_flan_cot_zeroshot_template_yaml"
+"task": "mmlu_flan_cot_zeroshot_sociology"

lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_us_foreign_policy.yaml

+"dataset_name": "us_foreign_policy"
+"description": "The following are multiple choice questions (with answers) about us\
+  \ foreign policy.\n\n"
+"group": "mmlu_flan_cot_zeroshot_social_sciences"
+"include": "_mmlu_flan_cot_zeroshot_template_yaml"
+"task": "mmlu_flan_cot_zeroshot_us_foreign_policy"