Unverified Commit 9097ad3e authored by jonabur's avatar jonabur Committed by GitHub
Browse files

add task for mmlu evaluation in arc multiple choice format (#1745)



* add mmlu arc style evaluation

* rename arc_style to continuation

---------
Co-authored-by: default avatarJonathan Burdge <jburdge@mahti-login11.mahti.csc.fi>
Co-authored-by: default avatarJonathan Burdge <jburdge@mahti-login12.mahti.csc.fi>
parent 885f48d6
"dataset_name": "management"
"description": "The following are questions (with answers) about management.\n\
\n"
"group": "mmlu_continuation_other"
"include": "_continuation_template_yaml"
"task": "mmlu_continuation_management"
"dataset_name": "marketing"
"description": "The following are questions (with answers) about marketing.\n\
\n"
"group": "mmlu_continuation_other"
"include": "_continuation_template_yaml"
"task": "mmlu_continuation_marketing"
"dataset_name": "medical_genetics"
"description": "The following are questions (with answers) about medical\
\ genetics.\n\n"
"group": "mmlu_continuation_other"
"include": "_continuation_template_yaml"
"task": "mmlu_continuation_medical_genetics"
"dataset_name": "miscellaneous"
"description": "The following are questions (with answers) about miscellaneous.\n\
\n"
"group": "mmlu_continuation_other"
"include": "_continuation_template_yaml"
"task": "mmlu_continuation_miscellaneous"
"dataset_name": "moral_disputes"
"description": "The following are questions (with answers) about moral\
\ disputes.\n\n"
"group": "mmlu_continuation_humanities"
"include": "_continuation_template_yaml"
"task": "mmlu_continuation_moral_disputes"
"dataset_name": "moral_scenarios"
"description": "The following are questions (with answers) about moral\
\ scenarios.\n\n"
"group": "mmlu_continuation_humanities"
"include": "_continuation_template_yaml"
"task": "mmlu_continuation_moral_scenarios"
"dataset_name": "nutrition"
"description": "The following are questions (with answers) about nutrition.\n\
\n"
"group": "mmlu_continuation_other"
"include": "_continuation_template_yaml"
"task": "mmlu_continuation_nutrition"
"dataset_name": "philosophy"
"description": "The following are questions (with answers) about philosophy.\n\
\n"
"group": "mmlu_continuation_humanities"
"include": "_continuation_template_yaml"
"task": "mmlu_continuation_philosophy"
"dataset_name": "prehistory"
"description": "The following are questions (with answers) about prehistory.\n\
\n"
"group": "mmlu_continuation_humanities"
"include": "_continuation_template_yaml"
"task": "mmlu_continuation_prehistory"
"dataset_name": "professional_accounting"
"description": "The following are questions (with answers) about professional\
\ accounting.\n\n"
"group": "mmlu_continuation_other"
"include": "_continuation_template_yaml"
"task": "mmlu_continuation_professional_accounting"
"dataset_name": "professional_law"
"description": "The following are questions (with answers) about professional\
\ law.\n\n"
"group": "mmlu_continuation_humanities"
"include": "_continuation_template_yaml"
"task": "mmlu_continuation_professional_law"
"dataset_name": "professional_medicine"
"description": "The following are questions (with answers) about professional\
\ medicine.\n\n"
"group": "mmlu_continuation_other"
"include": "_continuation_template_yaml"
"task": "mmlu_continuation_professional_medicine"
"dataset_name": "professional_psychology"
"description": "The following are questions (with answers) about professional\
\ psychology.\n\n"
"group": "mmlu_continuation_social_sciences"
"include": "_continuation_template_yaml"
"task": "mmlu_continuation_professional_psychology"
"dataset_name": "public_relations"
"description": "The following are questions (with answers) about public\
\ relations.\n\n"
"group": "mmlu_continuation_social_sciences"
"include": "_continuation_template_yaml"
"task": "mmlu_continuation_public_relations"
"dataset_name": "security_studies"
"description": "The following are questions (with answers) about security\
\ studies.\n\n"
"group": "mmlu_continuation_social_sciences"
"include": "_continuation_template_yaml"
"task": "mmlu_continuation_security_studies"
"dataset_name": "sociology"
"description": "The following are questions (with answers) about sociology.\n\
\n"
"group": "mmlu_continuation_social_sciences"
"include": "_continuation_template_yaml"
"task": "mmlu_continuation_sociology"
"dataset_name": "us_foreign_policy"
"description": "The following are questions (with answers) about us\
\ foreign policy.\n\n"
"group": "mmlu_continuation_social_sciences"
"include": "_continuation_template_yaml"
"task": "mmlu_continuation_us_foreign_policy"
"dataset_name": "virology"
"description": "The following are questions (with answers) about virology.\n\
\n"
"group": "mmlu_continuation_other"
"include": "_continuation_template_yaml"
"task": "mmlu_continuation_virology"
"dataset_name": "world_religions"
"description": "The following are questions (with answers) about world\
\ religions.\n\n"
"group": "mmlu_continuation_humanities"
"include": "_continuation_template_yaml"
"task": "mmlu_continuation_world_religions"
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