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

lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_high_school_macroeconomics.yaml

-dataset_name: high_school_macroeconomics
-description: 'The following are multiple choice questions (with answers) about high
-  school macroeconomics.
-
-
-  '
-include: _mmlu_flan_generative_template_yaml
-task: mmlu_flan_cot_zeroshot_high_school_macroeconomics
+"dataset_name": "high_school_macroeconomics"
+"description": "The following are multiple choice questions (with answers) about high\
+  \ school macroeconomics.\n\n"
+"group": "mmlu_flan_cot_zeroshot_social_sciences"
+"include": "_mmlu_flan_cot_zeroshot_template_yaml"
+"task": "mmlu_flan_cot_zeroshot_high_school_macroeconomics"

lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_high_school_mathematics.yaml

-dataset_name: high_school_mathematics
-description: 'The following are multiple choice questions (with answers) about high
-  school mathematics.
-
-
-  '
-include: _mmlu_flan_generative_template_yaml
-task: mmlu_flan_cot_zeroshot_high_school_mathematics
+"dataset_name": "high_school_mathematics"
+"description": "The following are multiple choice questions (with answers) about high\
+  \ school mathematics.\n\n"
+"group": "mmlu_flan_cot_zeroshot_stem"
+"include": "_mmlu_flan_cot_zeroshot_template_yaml"
+"task": "mmlu_flan_cot_zeroshot_high_school_mathematics"

lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_high_school_microeconomics.yaml

-dataset_name: high_school_microeconomics
-description: 'The following are multiple choice questions (with answers) about high
-  school microeconomics.
-
-
-  '
-include: _mmlu_flan_generative_template_yaml
-task: mmlu_flan_cot_zeroshot_high_school_microeconomics
+"dataset_name": "high_school_microeconomics"
+"description": "The following are multiple choice questions (with answers) about high\
+  \ school microeconomics.\n\n"
+"group": "mmlu_flan_cot_zeroshot_social_sciences"
+"include": "_mmlu_flan_cot_zeroshot_template_yaml"
+"task": "mmlu_flan_cot_zeroshot_high_school_microeconomics"

lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_high_school_physics.yaml

-dataset_name: high_school_physics
-description: 'The following are multiple choice questions (with answers) about high
-  school physics.
-
-
-  '
-include: _mmlu_flan_generative_template_yaml
-task: mmlu_flan_cot_zeroshot_high_school_physics
+"dataset_name": "high_school_physics"
+"description": "The following are multiple choice questions (with answers) about high\
+  \ school physics.\n\n"
+"group": "mmlu_flan_cot_zeroshot_stem"
+"include": "_mmlu_flan_cot_zeroshot_template_yaml"
+"task": "mmlu_flan_cot_zeroshot_high_school_physics"

lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_high_school_psychology.yaml

-dataset_name: high_school_psychology
-description: 'The following are multiple choice questions (with answers) about high
-  school psychology.
-
-
-  '
-include: _mmlu_flan_generative_template_yaml
-task: mmlu_flan_cot_zeroshot_high_school_psychology
+"dataset_name": "high_school_psychology"
+"description": "The following are multiple choice questions (with answers) about high\
+  \ school psychology.\n\n"
+"group": "mmlu_flan_cot_zeroshot_social_sciences"
+"include": "_mmlu_flan_cot_zeroshot_template_yaml"
+"task": "mmlu_flan_cot_zeroshot_high_school_psychology"

lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_high_school_statistics.yaml

-dataset_name: high_school_statistics
-description: 'The following are multiple choice questions (with answers) about high
-  school statistics.
-
-
-  '
-include: _mmlu_flan_generative_template_yaml
-task: mmlu_flan_cot_zeroshot_high_school_statistics
+"dataset_name": "high_school_statistics"
+"description": "The following are multiple choice questions (with answers) about high\
+  \ school statistics.\n\n"
+"group": "mmlu_flan_cot_zeroshot_stem"
+"include": "_mmlu_flan_cot_zeroshot_template_yaml"
+"task": "mmlu_flan_cot_zeroshot_high_school_statistics"

lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_high_school_us_history.yaml

-dataset_name: high_school_us_history
-description: 'The following are multiple choice questions (with answers) about high
-  school us history.
-
-
-  '
-include: _mmlu_flan_generative_template_yaml
-task: mmlu_flan_cot_zeroshot_high_school_us_history
+"dataset_name": "high_school_us_history"
+"description": "The following are multiple choice questions (with answers) about high\
+  \ school us history.\n\n"
+"group": "mmlu_flan_cot_zeroshot_humanities"
+"include": "_mmlu_flan_cot_zeroshot_template_yaml"
+"task": "mmlu_flan_cot_zeroshot_high_school_us_history"

lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_high_school_world_history.yaml

-dataset_name: high_school_world_history
-description: 'The following are multiple choice questions (with answers) about high
-  school world history.
-
-
-  '
-include: _mmlu_flan_generative_template_yaml
-task: mmlu_flan_cot_zeroshot_high_school_world_history
+"dataset_name": "high_school_world_history"
+"description": "The following are multiple choice questions (with answers) about high\
+  \ school world history.\n\n"
+"group": "mmlu_flan_cot_zeroshot_humanities"
+"include": "_mmlu_flan_cot_zeroshot_template_yaml"
+"task": "mmlu_flan_cot_zeroshot_high_school_world_history"

lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_human_aging.yaml

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

lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_human_sexuality.yaml

-dataset_name: human_sexuality
-description: 'The following are multiple choice questions (with answers) about human
-  sexuality.
-
-
-  '
-include: _mmlu_flan_generative_template_yaml
-task: mmlu_flan_cot_zeroshot_human_sexuality
+"dataset_name": "human_sexuality"
+"description": "The following are multiple choice questions (with answers) about human\
+  \ sexuality.\n\n"
+"group": "mmlu_flan_cot_zeroshot_social_sciences"
+"include": "_mmlu_flan_cot_zeroshot_template_yaml"
+"task": "mmlu_flan_cot_zeroshot_human_sexuality"

lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_international_law.yaml

-dataset_name: international_law
-description: 'The following are multiple choice questions (with answers) about international
-  law.
-
-
-  '
-include: _mmlu_flan_generative_template_yaml
-task: mmlu_flan_cot_zeroshot_international_law
+"dataset_name": "international_law"
+"description": "The following are multiple choice questions (with answers) about international\
+  \ law.\n\n"
+"group": "mmlu_flan_cot_zeroshot_humanities"
+"include": "_mmlu_flan_cot_zeroshot_template_yaml"
+"task": "mmlu_flan_cot_zeroshot_international_law"

lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_jurisprudence.yaml

-dataset_name: jurisprudence
-description: 'The following are multiple choice questions (with answers) about jurisprudence.
-
-
-  '
-include: _mmlu_flan_generative_template_yaml
-task: mmlu_flan_cot_zeroshot_jurisprudence
+"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.
-
-
-  '
-include: _mmlu_flan_generative_template_yaml
-task: mmlu_flan_cot_zeroshot_logical_fallacies
+"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.
-
-
-  '
-include: _mmlu_flan_generative_template_yaml
-task: mmlu_flan_cot_zeroshot_machine_learning
+"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.
-
-
-  '
-include: _mmlu_flan_generative_template_yaml
-task: mmlu_flan_cot_zeroshot_management
+"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.
-
-
-  '
-include: _mmlu_flan_generative_template_yaml
-task: mmlu_flan_cot_zeroshot_marketing
+"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.
-
-
-  '
-include: _mmlu_flan_generative_template_yaml
-task: mmlu_flan_cot_zeroshot_medical_genetics
+"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.
-
-
-  '
-include: _mmlu_flan_generative_template_yaml
-task: mmlu_flan_cot_zeroshot_miscellaneous
+"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.
-
-
-  '
-include: _mmlu_flan_generative_template_yaml
-task: mmlu_flan_cot_zeroshot_moral_disputes
+"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.
-
-
-  '
-include: _mmlu_flan_generative_template_yaml
-task: mmlu_flan_cot_zeroshot_moral_scenarios
+"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"