Merge pull request #922 from EleutherAI/mmlu_subgroups

[Refactor] Mmlu subgroups and weight avg

lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/_mmlu.yaml

+group: mmlu_flan_n_shot_generative
+task:
+  - mmlu_flan_n_shot_generative_stem
+  - mmlu_flan_n_shot_generative_other
+  - mmlu_flan_n_shot_generative_social_sciences
+  - mmlu_flan_n_shot_generative_humanities

lm_eval/tasks/mmlu/flan_n_shot/mmlu_log_abstract_algebra.yaml → lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_abstract_algebra.yaml

 "dataset_name": "abstract_algebra"
-"description": "The following are multiple choice questions (with answers) about abstract algebra.\n\n"
+"description": "The following are multiple choice questions (with answers) about abstract\
+  \ algebra.\n\n"
+"group": "mmlu_flan_n_shot_generative_stem"
 "include": "_mmlu_flan_loglikelihood_template_yaml"
-"task": "mmlu_flan_n_shot_loglikelihood_abstract_algebra"
+"task": "mmlu_flan_n_shot_generative_abstract_algebra"

lm_eval/tasks/mmlu/flan_n_shot/mmlu_log_anatomy.yaml → lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_anatomy.yaml

 "dataset_name": "anatomy"
-"description": "The following are multiple choice questions (with answers) about anatomy.\n\n"
+"description": "The following are multiple choice questions (with answers) about anatomy.\n\
+  \n"
+"group": "mmlu_flan_n_shot_generative_stem"
 "include": "_mmlu_flan_loglikelihood_template_yaml"
-"task": "mmlu_flan_n_shot_loglikelihood_anatomy"
+"task": "mmlu_flan_n_shot_generative_anatomy"

lm_eval/tasks/mmlu/flan_n_shot/mmlu_log_astronomy.yaml → lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_astronomy.yaml

 "dataset_name": "astronomy"
-"description": "The following are multiple choice questions (with answers) about astronomy.\n\n"
+"description": "The following are multiple choice questions (with answers) about astronomy.\n\
+  \n"
+"group": "mmlu_flan_n_shot_generative_stem"
 "include": "_mmlu_flan_loglikelihood_template_yaml"
-"task": "mmlu_flan_n_shot_loglikelihood_astronomy"
+"task": "mmlu_flan_n_shot_generative_astronomy"

lm_eval/tasks/mmlu/flan_n_shot/mmlu_log_business_ethics.yaml → lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_business_ethics.yaml

 "dataset_name": "business_ethics"
-"description": "The following are multiple choice questions (with answers) about business ethics.\n\n"
+"description": "The following are multiple choice questions (with answers) about business\
+  \ ethics.\n\n"
+"group": "mmlu_flan_n_shot_generative_other"
 "include": "_mmlu_flan_loglikelihood_template_yaml"
-"task": "mmlu_flan_n_shot_loglikelihood_business_ethics"
+"task": "mmlu_flan_n_shot_generative_business_ethics"

lm_eval/tasks/mmlu/flan_n_shot/mmlu_log_clinical_knowledge.yaml → lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_clinical_knowledge.yaml

 "dataset_name": "clinical_knowledge"
-"description": "The following are multiple choice questions (with answers) about clinical knowledge.\n\n"
+"description": "The following are multiple choice questions (with answers) about clinical\
+  \ knowledge.\n\n"
+"group": "mmlu_flan_n_shot_generative_other"
 "include": "_mmlu_flan_loglikelihood_template_yaml"
-"task": "mmlu_flan_n_shot_loglikelihood_clinical_knowledge"
+"task": "mmlu_flan_n_shot_generative_clinical_knowledge"

lm_eval/tasks/mmlu/flan_n_shot/mmlu_log_college_biology.yaml → lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_college_biology.yaml

 "dataset_name": "college_biology"
-"description": "The following are multiple choice questions (with answers) about college biology.\n\n"
+"description": "The following are multiple choice questions (with answers) about college\
+  \ biology.\n\n"
+"group": "mmlu_flan_n_shot_generative_stem"
 "include": "_mmlu_flan_loglikelihood_template_yaml"
-"task": "mmlu_flan_n_shot_loglikelihood_college_biology"
+"task": "mmlu_flan_n_shot_generative_college_biology"

lm_eval/tasks/mmlu/flan_n_shot/mmlu_log_college_chemistry.yaml → lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_college_chemistry.yaml

 "dataset_name": "college_chemistry"
-"description": "The following are multiple choice questions (with answers) about college chemistry.\n\n"
+"description": "The following are multiple choice questions (with answers) about college\
+  \ chemistry.\n\n"
+"group": "mmlu_flan_n_shot_generative_stem"
 "include": "_mmlu_flan_loglikelihood_template_yaml"
-"task": "mmlu_flan_n_shot_loglikelihood_college_chemistry"
+"task": "mmlu_flan_n_shot_generative_college_chemistry"

lm_eval/tasks/mmlu/flan_n_shot/mmlu_log_college_computer_science.yaml → lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_college_computer_science.yaml

 "dataset_name": "college_computer_science"
-"description": "The following are multiple choice questions (with answers) about college computer science.\n\n"
+"description": "The following are multiple choice questions (with answers) about college\
+  \ computer science.\n\n"
+"group": "mmlu_flan_n_shot_generative_stem"
 "include": "_mmlu_flan_loglikelihood_template_yaml"
-"task": "mmlu_flan_n_shot_loglikelihood_college_computer_science"
+"task": "mmlu_flan_n_shot_generative_college_computer_science"

lm_eval/tasks/mmlu/flan_n_shot/mmlu_log_college_mathematics.yaml → lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_college_mathematics.yaml

 "dataset_name": "college_mathematics"
-"description": "The following are multiple choice questions (with answers) about college mathematics.\n\n"
+"description": "The following are multiple choice questions (with answers) about college\
+  \ mathematics.\n\n"
+"group": "mmlu_flan_n_shot_generative_stem"
 "include": "_mmlu_flan_loglikelihood_template_yaml"
-"task": "mmlu_flan_n_shot_loglikelihood_college_mathematics"
+"task": "mmlu_flan_n_shot_generative_college_mathematics"

lm_eval/tasks/mmlu/flan_n_shot/mmlu_log_college_medicine.yaml → lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_college_medicine.yaml

 "dataset_name": "college_medicine"
-"description": "The following are multiple choice questions (with answers) about college medicine.\n\n"
+"description": "The following are multiple choice questions (with answers) about college\
+  \ medicine.\n\n"
+"group": "mmlu_flan_n_shot_generative_other"
 "include": "_mmlu_flan_loglikelihood_template_yaml"
-"task": "mmlu_flan_n_shot_loglikelihood_college_medicine"
+"task": "mmlu_flan_n_shot_generative_college_medicine"

lm_eval/tasks/mmlu/flan_n_shot/mmlu_log_college_physics.yaml → lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_college_physics.yaml

 "dataset_name": "college_physics"
-"description": "The following are multiple choice questions (with answers) about college physics.\n\n"
+"description": "The following are multiple choice questions (with answers) about college\
+  \ physics.\n\n"
+"group": "mmlu_flan_n_shot_generative_stem"
 "include": "_mmlu_flan_loglikelihood_template_yaml"
-"task": "mmlu_flan_n_shot_loglikelihood_college_physics"
+"task": "mmlu_flan_n_shot_generative_college_physics"

lm_eval/tasks/mmlu/flan_n_shot/mmlu_log_computer_security.yaml → lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_computer_security.yaml

 "dataset_name": "computer_security"
-"description": "The following are multiple choice questions (with answers) about computer security.\n\n"
+"description": "The following are multiple choice questions (with answers) about computer\
+  \ security.\n\n"
+"group": "mmlu_flan_n_shot_generative_stem"
 "include": "_mmlu_flan_loglikelihood_template_yaml"
-"task": "mmlu_flan_n_shot_loglikelihood_computer_security"
+"task": "mmlu_flan_n_shot_generative_computer_security"

lm_eval/tasks/mmlu/flan_n_shot/mmlu_log_conceptual_physics.yaml → lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_conceptual_physics.yaml

 "dataset_name": "conceptual_physics"
-"description": "The following are multiple choice questions (with answers) about conceptual physics.\n\n"
+"description": "The following are multiple choice questions (with answers) about conceptual\
+  \ physics.\n\n"
+"group": "mmlu_flan_n_shot_generative_stem"
 "include": "_mmlu_flan_loglikelihood_template_yaml"
-"task": "mmlu_flan_n_shot_loglikelihood_conceptual_physics"
+"task": "mmlu_flan_n_shot_generative_conceptual_physics"

lm_eval/tasks/mmlu/flan_n_shot/mmlu_log_econometrics.yaml → lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_econometrics.yaml

 "dataset_name": "econometrics"
-"description": "The following are multiple choice questions (with answers) about econometrics.\n\n"
+"description": "The following are multiple choice questions (with answers) about econometrics.\n\
+  \n"
+"group": "mmlu_flan_n_shot_generative_social_sciences"
 "include": "_mmlu_flan_loglikelihood_template_yaml"
-"task": "mmlu_flan_n_shot_loglikelihood_econometrics"
+"task": "mmlu_flan_n_shot_generative_econometrics"

lm_eval/tasks/mmlu/flan_n_shot/mmlu_log_electrical_engineering.yaml → lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_electrical_engineering.yaml

 "dataset_name": "electrical_engineering"
-"description": "The following are multiple choice questions (with answers) about electrical engineering.\n\n"
+"description": "The following are multiple choice questions (with answers) about electrical\
+  \ engineering.\n\n"
+"group": "mmlu_flan_n_shot_generative_stem"
 "include": "_mmlu_flan_loglikelihood_template_yaml"
-"task": "mmlu_flan_n_shot_loglikelihood_electrical_engineering"
+"task": "mmlu_flan_n_shot_generative_electrical_engineering"

lm_eval/tasks/mmlu/flan_n_shot/mmlu_log_elementary_mathematics.yaml → lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_elementary_mathematics.yaml

 "dataset_name": "elementary_mathematics"
-"description": "The following are multiple choice questions (with answers) about elementary mathematics.\n\n"
+"description": "The following are multiple choice questions (with answers) about elementary\
+  \ mathematics.\n\n"
+"group": "mmlu_flan_n_shot_generative_stem"
 "include": "_mmlu_flan_loglikelihood_template_yaml"
-"task": "mmlu_flan_n_shot_loglikelihood_elementary_mathematics"
+"task": "mmlu_flan_n_shot_generative_elementary_mathematics"

lm_eval/tasks/mmlu/flan_n_shot/mmlu_log_formal_logic.yaml → lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_formal_logic.yaml

 "dataset_name": "formal_logic"
-"description": "The following are multiple choice questions (with answers) about formal logic.\n\n"
+"description": "The following are multiple choice questions (with answers) about formal\
+  \ logic.\n\n"
+"group": "mmlu_flan_n_shot_generative_humanities"
 "include": "_mmlu_flan_loglikelihood_template_yaml"
-"task": "mmlu_flan_n_shot_loglikelihood_formal_logic"
+"task": "mmlu_flan_n_shot_generative_formal_logic"

lm_eval/tasks/mmlu/flan_n_shot/mmlu_log_global_facts.yaml → lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_global_facts.yaml

 "dataset_name": "global_facts"
-"description": "The following are multiple choice questions (with answers) about global facts.\n\n"
+"description": "The following are multiple choice questions (with answers) about global\
+  \ facts.\n\n"
+"group": "mmlu_flan_n_shot_generative_other"
 "include": "_mmlu_flan_loglikelihood_template_yaml"
-"task": "mmlu_flan_n_shot_loglikelihood_global_facts"
+"task": "mmlu_flan_n_shot_generative_global_facts"