Merge branch 'cont-metrics' of https://github.com/EleutherAI/lm-evaluation-harness into alt_worlds

lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_nutrition.yaml

-dataset_name: nutrition
-description: 'The following are multiple choice questions (with answers) about nutrition.
-
-
-  '
-include: _mmlu_flan_generative_template_yaml
-task: mmlu_flan_cot_zeroshot_nutrition
+"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.
-
-
-  '
-include: _mmlu_flan_generative_template_yaml
-task: mmlu_flan_cot_zeroshot_philosophy
+"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.
-
-
-  '
-include: _mmlu_flan_generative_template_yaml
-task: mmlu_flan_cot_zeroshot_prehistory
+"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.
-
-
-  '
-include: _mmlu_flan_generative_template_yaml
-task: mmlu_flan_cot_zeroshot_professional_accounting
+"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.
-
-
-  '
-include: _mmlu_flan_generative_template_yaml
-task: mmlu_flan_cot_zeroshot_professional_law
+"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.
-
-
-  '
-include: _mmlu_flan_generative_template_yaml
-task: mmlu_flan_cot_zeroshot_professional_medicine
+"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.
-
-
-  '
-include: _mmlu_flan_generative_template_yaml
-task: mmlu_flan_cot_zeroshot_professional_psychology
+"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.
-
-
-  '
-include: _mmlu_flan_generative_template_yaml
-task: mmlu_flan_cot_zeroshot_public_relations
+"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.
-
-
-  '
-include: _mmlu_flan_generative_template_yaml
-task: mmlu_flan_cot_zeroshot_security_studies
+"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.
-
-
-  '
-include: _mmlu_flan_generative_template_yaml
-task: mmlu_flan_cot_zeroshot_sociology
+"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.
-
-
-  '
-include: _mmlu_flan_generative_template_yaml
-task: mmlu_flan_cot_zeroshot_us_foreign_policy
+"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"

lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_virology.yaml

-dataset_name: virology
-description: 'The following are multiple choice questions (with answers) about virology.
-
-
-  '
-include: _mmlu_flan_generative_template_yaml
-task: mmlu_flan_cot_zeroshot_virology
+"dataset_name": "virology"
+"description": "The following are multiple choice questions (with answers) about virology.\n\
+  \n"
+"group": "mmlu_flan_cot_zeroshot_other"
+"include": "_mmlu_flan_cot_zeroshot_template_yaml"
+"task": "mmlu_flan_cot_zeroshot_virology"

lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_world_religions.yaml

-dataset_name: world_religions
-description: 'The following are multiple choice questions (with answers) about world
-  religions.
-
-
-  '
-include: _mmlu_flan_generative_template_yaml
-task: mmlu_flan_cot_zeroshot_world_religions
+"dataset_name": "world_religions"
+"description": "The following are multiple choice questions (with answers) about world\
+  \ religions.\n\n"
+"group": "mmlu_flan_cot_zeroshot_humanities"
+"include": "_mmlu_flan_cot_zeroshot_template_yaml"
+"task": "mmlu_flan_cot_zeroshot_world_religions"

lm_eval/tasks/mmlu/flan_n_shot/_mmlu_flan_generative_template_yaml

-group: mmlu_flan_n_shot_generative
-dataset_path: cais/mmlu
-test_split: test
-fewshot_split: dev
-output_type: greedy_until
-doc_to_text: "Q: {{question.strip()}}\n(A) {{choices[0]}} (B) {{choices[1]}} (C) {{choices[2]}} (D) {{choices[3]}}\nA: "
-doc_to_target: "{{['(A)', '(B)', '(C)', '(D)'][answer]}}"
-generation_kwargs:
-  until:
-    - "</s>"
-metric_list:
-  - metric: exact_match
-    aggregation: mean
-    higher_is_better: true

lm_eval/tasks/mmlu/flan_n_shot/generative/_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/generative/_mmlu_flan_generative_template_yaml

+group: mmlu_flan_n_shot_generative
+dataset_path: hails/mmlu_no_train # a copy of `cais/mmlu` with no auxiliary_train split
+test_split: test
+fewshot_split: dev
+output_type: generate_until
+doc_to_text: "Q: {{question.strip()}}\n(A) {{choices[0]}} (B) {{choices[1]}} (C) {{choices[2]}} (D) {{choices[3]}}\nA: "
+doc_to_target: "{{['(A)', '(B)', '(C)', '(D)'][answer]}}"
+generation_kwargs:
+  until:
+    - "</s>"
+metric_list:
+  - metric: exact_match
+    aggregation: mean
+    higher_is_better: true

lm_eval/tasks/mmlu/flan_n_shot/generative/mmlu_abstract_algebra.yaml

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

lm_eval/tasks/mmlu/flan_n_shot/generative/mmlu_anatomy.yaml

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

lm_eval/tasks/mmlu/flan_n_shot/generative/mmlu_astronomy.yaml

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

lm_eval/tasks/mmlu/flan_n_shot/generative/mmlu_business_ethics.yaml

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