Commit 88486e57 authored by lintangsutawika's avatar lintangsutawika
Browse files

Merge branch 'group-agg-rework' of...

Merge branch 'group-agg-rework' of https://github.com/EleutherAI/lm-evaluation-harness into multiprompt
parents 5971f2ca ba73d131
"dataset_name": "high_school_us_history" "dataset_name": "high_school_us_history"
"description": "The following are multiple choice questions (with answers) about high\ "description": "The following are multiple choice questions (with answers) about high\
\ school us history.\n\n" \ school us history.\n\n"
"group": "mmlu_humanities_generative" "tag": "mmlu_humanities_generative"
"group_alias": "humanities"
"include": "_default_template_yaml" "include": "_default_template_yaml"
"task": "mmlu_high_school_us_history_generative" "task": "mmlu_high_school_us_history_generative"
"task_alias": "high_school_us_history" "task_alias": "high_school_us_history"
"dataset_name": "high_school_world_history" "dataset_name": "high_school_world_history"
"description": "The following are multiple choice questions (with answers) about high\ "description": "The following are multiple choice questions (with answers) about high\
\ school world history.\n\n" \ school world history.\n\n"
"group": "mmlu_humanities_generative" "tag": "mmlu_humanities_generative"
"group_alias": "humanities"
"include": "_default_template_yaml" "include": "_default_template_yaml"
"task": "mmlu_high_school_world_history_generative" "task": "mmlu_high_school_world_history_generative"
"task_alias": "high_school_world_history" "task_alias": "high_school_world_history"
"dataset_name": "human_aging" "dataset_name": "human_aging"
"description": "The following are multiple choice questions (with answers) about human\ "description": "The following are multiple choice questions (with answers) about human\
\ aging.\n\n" \ aging.\n\n"
"group": "mmlu_other_generative" "tag": "mmlu_other_generative"
"group_alias": "other"
"include": "_default_template_yaml" "include": "_default_template_yaml"
"task": "mmlu_human_aging_generative" "task": "mmlu_human_aging_generative"
"task_alias": "human_aging" "task_alias": "human_aging"
"dataset_name": "human_sexuality" "dataset_name": "human_sexuality"
"description": "The following are multiple choice questions (with answers) about human\ "description": "The following are multiple choice questions (with answers) about human\
\ sexuality.\n\n" \ sexuality.\n\n"
"group": "mmlu_social_sciences_generative" "tag": "mmlu_social_sciences_generative"
"group_alias": "social_sciences"
"include": "_default_template_yaml" "include": "_default_template_yaml"
"task": "mmlu_human_sexuality_generative" "task": "mmlu_human_sexuality_generative"
"task_alias": "human_sexuality" "task_alias": "human_sexuality"
"dataset_name": "international_law" "dataset_name": "international_law"
"description": "The following are multiple choice questions (with answers) about international\ "description": "The following are multiple choice questions (with answers) about international\
\ law.\n\n" \ law.\n\n"
"group": "mmlu_humanities_generative" "tag": "mmlu_humanities_generative"
"group_alias": "humanities"
"include": "_default_template_yaml" "include": "_default_template_yaml"
"task": "mmlu_international_law_generative" "task": "mmlu_international_law_generative"
"task_alias": "international_law" "task_alias": "international_law"
"dataset_name": "jurisprudence" "dataset_name": "jurisprudence"
"description": "The following are multiple choice questions (with answers) about jurisprudence.\n\ "description": "The following are multiple choice questions (with answers) about jurisprudence.\n\
\n" \n"
"group": "mmlu_humanities_generative" "tag": "mmlu_humanities_generative"
"group_alias": "humanities"
"include": "_default_template_yaml" "include": "_default_template_yaml"
"task": "mmlu_jurisprudence_generative" "task": "mmlu_jurisprudence_generative"
"task_alias": "jurisprudence" "task_alias": "jurisprudence"
"dataset_name": "logical_fallacies" "dataset_name": "logical_fallacies"
"description": "The following are multiple choice questions (with answers) about logical\ "description": "The following are multiple choice questions (with answers) about logical\
\ fallacies.\n\n" \ fallacies.\n\n"
"group": "mmlu_humanities_generative" "tag": "mmlu_humanities_generative"
"group_alias": "humanities"
"include": "_default_template_yaml" "include": "_default_template_yaml"
"task": "mmlu_logical_fallacies_generative" "task": "mmlu_logical_fallacies_generative"
"task_alias": "logical_fallacies" "task_alias": "logical_fallacies"
"dataset_name": "machine_learning" "dataset_name": "machine_learning"
"description": "The following are multiple choice questions (with answers) about machine\ "description": "The following are multiple choice questions (with answers) about machine\
\ learning.\n\n" \ learning.\n\n"
"group": "mmlu_stem_generative" "tag": "mmlu_stem_generative"
"group_alias": "stem"
"include": "_default_template_yaml" "include": "_default_template_yaml"
"task": "mmlu_machine_learning_generative" "task": "mmlu_machine_learning_generative"
"task_alias": "machine_learning" "task_alias": "machine_learning"
"dataset_name": "management" "dataset_name": "management"
"description": "The following are multiple choice questions (with answers) about management.\n\ "description": "The following are multiple choice questions (with answers) about management.\n\
\n" \n"
"group": "mmlu_other_generative" "tag": "mmlu_other_generative"
"group_alias": "other"
"include": "_default_template_yaml" "include": "_default_template_yaml"
"task": "mmlu_management_generative" "task": "mmlu_management_generative"
"task_alias": "management" "task_alias": "management"
"dataset_name": "marketing" "dataset_name": "marketing"
"description": "The following are multiple choice questions (with answers) about marketing.\n\ "description": "The following are multiple choice questions (with answers) about marketing.\n\
\n" \n"
"group": "mmlu_other_generative" "tag": "mmlu_other_generative"
"group_alias": "other"
"include": "_default_template_yaml" "include": "_default_template_yaml"
"task": "mmlu_marketing_generative" "task": "mmlu_marketing_generative"
"task_alias": "marketing" "task_alias": "marketing"
"dataset_name": "medical_genetics" "dataset_name": "medical_genetics"
"description": "The following are multiple choice questions (with answers) about medical\ "description": "The following are multiple choice questions (with answers) about medical\
\ genetics.\n\n" \ genetics.\n\n"
"group": "mmlu_other_generative" "tag": "mmlu_other_generative"
"group_alias": "other"
"include": "_default_template_yaml" "include": "_default_template_yaml"
"task": "mmlu_medical_genetics_generative" "task": "mmlu_medical_genetics_generative"
"task_alias": "medical_genetics" "task_alias": "medical_genetics"
"dataset_name": "miscellaneous" "dataset_name": "miscellaneous"
"description": "The following are multiple choice questions (with answers) about miscellaneous.\n\ "description": "The following are multiple choice questions (with answers) about miscellaneous.\n\
\n" \n"
"group": "mmlu_other_generative" "tag": "mmlu_other_generative"
"group_alias": "other"
"include": "_default_template_yaml" "include": "_default_template_yaml"
"task": "mmlu_miscellaneous_generative" "task": "mmlu_miscellaneous_generative"
"task_alias": "miscellaneous" "task_alias": "miscellaneous"
"dataset_name": "moral_disputes" "dataset_name": "moral_disputes"
"description": "The following are multiple choice questions (with answers) about moral\ "description": "The following are multiple choice questions (with answers) about moral\
\ disputes.\n\n" \ disputes.\n\n"
"group": "mmlu_humanities_generative" "tag": "mmlu_humanities_generative"
"group_alias": "humanities"
"include": "_default_template_yaml" "include": "_default_template_yaml"
"task": "mmlu_moral_disputes_generative" "task": "mmlu_moral_disputes_generative"
"task_alias": "moral_disputes" "task_alias": "moral_disputes"
"dataset_name": "moral_scenarios" "dataset_name": "moral_scenarios"
"description": "The following are multiple choice questions (with answers) about moral\ "description": "The following are multiple choice questions (with answers) about moral\
\ scenarios.\n\n" \ scenarios.\n\n"
"group": "mmlu_humanities_generative" "tag": "mmlu_humanities_generative"
"group_alias": "humanities"
"include": "_default_template_yaml" "include": "_default_template_yaml"
"task": "mmlu_moral_scenarios_generative" "task": "mmlu_moral_scenarios_generative"
"task_alias": "moral_scenarios" "task_alias": "moral_scenarios"
"dataset_name": "nutrition" "dataset_name": "nutrition"
"description": "The following are multiple choice questions (with answers) about nutrition.\n\ "description": "The following are multiple choice questions (with answers) about nutrition.\n\
\n" \n"
"group": "mmlu_other_generative" "tag": "mmlu_other_generative"
"group_alias": "other"
"include": "_default_template_yaml" "include": "_default_template_yaml"
"task": "mmlu_nutrition_generative" "task": "mmlu_nutrition_generative"
"task_alias": "nutrition" "task_alias": "nutrition"
"dataset_name": "philosophy" "dataset_name": "philosophy"
"description": "The following are multiple choice questions (with answers) about philosophy.\n\ "description": "The following are multiple choice questions (with answers) about philosophy.\n\
\n" \n"
"group": "mmlu_humanities_generative" "tag": "mmlu_humanities_generative"
"group_alias": "humanities"
"include": "_default_template_yaml" "include": "_default_template_yaml"
"task": "mmlu_philosophy_generative" "task": "mmlu_philosophy_generative"
"task_alias": "philosophy" "task_alias": "philosophy"
"dataset_name": "prehistory" "dataset_name": "prehistory"
"description": "The following are multiple choice questions (with answers) about prehistory.\n\ "description": "The following are multiple choice questions (with answers) about prehistory.\n\
\n" \n"
"group": "mmlu_humanities_generative" "tag": "mmlu_humanities_generative"
"group_alias": "humanities"
"include": "_default_template_yaml" "include": "_default_template_yaml"
"task": "mmlu_prehistory_generative" "task": "mmlu_prehistory_generative"
"task_alias": "prehistory" "task_alias": "prehistory"
"dataset_name": "professional_accounting" "dataset_name": "professional_accounting"
"description": "The following are multiple choice questions (with answers) about professional\ "description": "The following are multiple choice questions (with answers) about professional\
\ accounting.\n\n" \ accounting.\n\n"
"group": "mmlu_other_generative" "tag": "mmlu_other_generative"
"group_alias": "other"
"include": "_default_template_yaml" "include": "_default_template_yaml"
"task": "mmlu_professional_accounting_generative" "task": "mmlu_professional_accounting_generative"
"task_alias": "professional_accounting" "task_alias": "professional_accounting"
"dataset_name": "professional_law" "dataset_name": "professional_law"
"description": "The following are multiple choice questions (with answers) about professional\ "description": "The following are multiple choice questions (with answers) about professional\
\ law.\n\n" \ law.\n\n"
"group": "mmlu_humanities_generative" "tag": "mmlu_humanities_generative"
"group_alias": "humanities"
"include": "_default_template_yaml" "include": "_default_template_yaml"
"task": "mmlu_professional_law_generative" "task": "mmlu_professional_law_generative"
"task_alias": "professional_law" "task_alias": "professional_law"
"dataset_name": "professional_medicine" "dataset_name": "professional_medicine"
"description": "The following are multiple choice questions (with answers) about professional\ "description": "The following are multiple choice questions (with answers) about professional\
\ medicine.\n\n" \ medicine.\n\n"
"group": "mmlu_other_generative" "tag": "mmlu_other_generative"
"group_alias": "other"
"include": "_default_template_yaml" "include": "_default_template_yaml"
"task": "mmlu_professional_medicine_generative" "task": "mmlu_professional_medicine_generative"
"task_alias": "professional_medicine" "task_alias": "professional_medicine"
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment