Commit ba73d131 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 group-agg-rework
parents 6e2dbe76 269b66e9
"dataset_name": "High Philosophy" "dataset_name": "High Philosophy"
"group": "arabicmmlu_humanities" "tag": "arabicmmlu_humanities_tasks"
"group_alias": "humanities"
"include": "_default_template_yaml" "include": "_default_template_yaml"
"task": "arabicmmlu_high_philosophy" "task": "arabicmmlu_high_philosophy"
"task_alias": "High Philosophy" "task_alias": "High Philosophy"
"dataset_name": "High Physics" "dataset_name": "High Physics"
"group": "arabicmmlu_stem" "tag": "arabicmmlu_stem_tasks"
"group_alias": "stem"
"include": "_default_template_yaml" "include": "_default_template_yaml"
"task": "arabicmmlu_high_physics" "task": "arabicmmlu_high_physics"
"task_alias": "High Physics" "task_alias": "High Physics"
"dataset_name": "Islamic Studies" "dataset_name": "Islamic Studies"
"group": "arabicmmlu_humanities" "tag": "arabicmmlu_humanities_tasks"
"group_alias": "humanities"
"include": "_default_template_yaml" "include": "_default_template_yaml"
"task": "arabicmmlu_islamic_studies" "task": "arabicmmlu_islamic_studies"
"task_alias": "Islamic Studies" "task_alias": "Islamic Studies"
"dataset_name": "Middle Arabic Language" "dataset_name": "Middle Arabic Language"
"group": "arabicmmlu_language" "tag": "arabicmmlu_language_tasks"
"group_alias": "language"
"include": "_default_template_yaml" "include": "_default_template_yaml"
"task": "arabicmmlu_middle_arabic_language" "task": "arabicmmlu_middle_arabic_language"
"task_alias": "Middle Arabic Language" "task_alias": "Middle Arabic Language"
"dataset_name": "Middle Civics" "dataset_name": "Middle Civics"
"group": "arabicmmlu_social_science" "tag": "arabicmmlu_social_science_tasks"
"group_alias": "social science"
"include": "_default_template_yaml" "include": "_default_template_yaml"
"task": "arabicmmlu_middle_civics" "task": "arabicmmlu_middle_civics"
"task_alias": "Middle Civics" "task_alias": "Middle Civics"
"dataset_name": "Middle Computer Science" "dataset_name": "Middle Computer Science"
"group": "arabicmmlu_stem" "tag": "arabicmmlu_stem_tasks"
"group_alias": "stem"
"include": "_default_template_yaml" "include": "_default_template_yaml"
"task": "arabicmmlu_middle_computer_science" "task": "arabicmmlu_middle_computer_science"
"task_alias": "Middle Computer Science" "task_alias": "Middle Computer Science"
"dataset_name": "Middle Economics" "dataset_name": "Middle Economics"
"group": "arabicmmlu_social_science" "tag": "arabicmmlu_social_science_tasks"
"group_alias": "social science"
"include": "_default_template_yaml" "include": "_default_template_yaml"
"task": "arabicmmlu_middle_economics" "task": "arabicmmlu_middle_economics"
"task_alias": "Middle Economics" "task_alias": "Middle Economics"
"dataset_name": "Middle General Knowledge" "dataset_name": "Middle General Knowledge"
"group": "arabicmmlu_other" "tag": "arabicmmlu_other_tasks"
"group_alias": "other"
"include": "_default_template_yaml" "include": "_default_template_yaml"
"task": "arabicmmlu_middle_general_knowledge" "task": "arabicmmlu_middle_general_knowledge"
"task_alias": "Middle General Knowledge" "task_alias": "Middle General Knowledge"
"dataset_name": "Middle Geography" "dataset_name": "Middle Geography"
"group": "arabicmmlu_social_science" "tag": "arabicmmlu_social_science_tasks"
"group_alias": "social science"
"include": "_default_template_yaml" "include": "_default_template_yaml"
"task": "arabicmmlu_middle_geography" "task": "arabicmmlu_middle_geography"
"task_alias": "Middle Geography" "task_alias": "Middle Geography"
"dataset_name": "Middle History" "dataset_name": "Middle History"
"group": "arabicmmlu_humanities" "tag": "arabicmmlu_humanities_tasks"
"group_alias": "humanities"
"include": "_default_template_yaml" "include": "_default_template_yaml"
"task": "arabicmmlu_middle_history" "task": "arabicmmlu_middle_history"
"task_alias": "Middle History" "task_alias": "Middle History"
"dataset_name": "Middle Islamic Studies" "dataset_name": "Middle Islamic Studies"
"group": "arabicmmlu_humanities" "tag": "arabicmmlu_humanities_tasks"
"group_alias": "humanities"
"include": "_default_template_yaml" "include": "_default_template_yaml"
"task": "arabicmmlu_middle_islamic_studies" "task": "arabicmmlu_middle_islamic_studies"
"task_alias": "Middle Islamic Studies" "task_alias": "Middle Islamic Studies"
"dataset_name": "Middle Natural Science" "dataset_name": "Middle Natural Science"
"group": "arabicmmlu_stem" "tag": "arabicmmlu_stem_tasks"
"group_alias": "stem"
"include": "_default_template_yaml" "include": "_default_template_yaml"
"task": "arabicmmlu_middle_natural_science" "task": "arabicmmlu_middle_natural_science"
"task_alias": "Middle Natural Science" "task_alias": "Middle Natural Science"
"dataset_name": "Middle Social Science" "dataset_name": "Middle Social Science"
"group": "arabicmmlu_social_science" "tag": "arabicmmlu_social_science_tasks"
"group_alias": "social science"
"include": "_default_template_yaml" "include": "_default_template_yaml"
"task": "arabicmmlu_middle_social_science" "task": "arabicmmlu_middle_social_science"
"task_alias": "Middle Social Science" "task_alias": "Middle Social Science"
"dataset_name": "Primary Arabic Language" "dataset_name": "Primary Arabic Language"
"group": "arabicmmlu_language" "tag": "arabicmmlu_language_tasks"
"group_alias": "language"
"include": "_default_template_yaml" "include": "_default_template_yaml"
"task": "arabicmmlu_primary_arabic_language" "task": "arabicmmlu_primary_arabic_language"
"task_alias": "Primary Arabic Language" "task_alias": "Primary Arabic Language"
"dataset_name": "Primary Computer Science" "dataset_name": "Primary Computer Science"
"group": "arabicmmlu_stem" "tag": "arabicmmlu_stem_tasks"
"group_alias": "stem"
"include": "_default_template_yaml" "include": "_default_template_yaml"
"task": "arabicmmlu_primary_computer_science" "task": "arabicmmlu_primary_computer_science"
"task_alias": "Primary Computer Science" "task_alias": "Primary Computer Science"
"dataset_name": "Primary General Knowledge" "dataset_name": "Primary General Knowledge"
"group": "arabicmmlu_other" "tag": "arabicmmlu_other_tasks"
"group_alias": "other"
"include": "_default_template_yaml" "include": "_default_template_yaml"
"task": "arabicmmlu_primary_general_knowledge" "task": "arabicmmlu_primary_general_knowledge"
"task_alias": "Primary General Knowledge" "task_alias": "Primary General Knowledge"
"dataset_name": "Primary Geography" "dataset_name": "Primary Geography"
"group": "arabicmmlu_social_science" "tag": "arabicmmlu_social_science_tasks"
"group_alias": "social science"
"include": "_default_template_yaml" "include": "_default_template_yaml"
"task": "arabicmmlu_primary_geography" "task": "arabicmmlu_primary_geography"
"task_alias": "Primary Geography" "task_alias": "Primary Geography"
"dataset_name": "Primary History" "dataset_name": "Primary History"
"group": "arabicmmlu_humanities" "tag": "arabicmmlu_humanities_tasks"
"group_alias": "humanities"
"include": "_default_template_yaml" "include": "_default_template_yaml"
"task": "arabicmmlu_primary_history" "task": "arabicmmlu_primary_history"
"task_alias": "Primary History" "task_alias": "Primary History"
"dataset_name": "Primary Islamic Studies" "dataset_name": "Primary Islamic Studies"
"group": "arabicmmlu_humanities" "tag": "arabicmmlu_humanities_tasks"
"group_alias": "humanities"
"include": "_default_template_yaml" "include": "_default_template_yaml"
"task": "arabicmmlu_primary_islamic_studies" "task": "arabicmmlu_primary_islamic_studies"
"task_alias": "Primary Islamic Studies" "task_alias": "Primary Islamic Studies"
"dataset_name": "Primary Math" "dataset_name": "Primary Math"
"group": "arabicmmlu_stem" "tag": "arabicmmlu_stem_tasks"
"group_alias": "stem"
"include": "_default_template_yaml" "include": "_default_template_yaml"
"task": "arabicmmlu_primary_math" "task": "arabicmmlu_primary_math"
"task_alias": "Primary Math" "task_alias": "Primary Math"
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