Commit c1e63555 authored by Yu Shi Jie's avatar Yu Shi Jie
Browse files

Merge branch 'upstream' into 'mmlu-pro'

add tokenizer logs info (#1731)

See merge request shijie.yu/lm-evaluation-harness!4
parents e361687c 42dc2448
"dataset_name": "philosophy" "dataset_name": "philosophy"
"description": "The following are questions (with answers) about philosophy.\n\ "description": "The following are questions (with answers) about philosophy.\n\
\n" \n"
"group": "mmlu_continuation_humanities" "tag": "mmlu_continuation_humanities"
"include": "_continuation_template_yaml" "include": "_continuation_template_yaml"
"task": "mmlu_continuation_philosophy" "task": "mmlu_continuation_philosophy"
"dataset_name": "prehistory" "dataset_name": "prehistory"
"description": "The following are questions (with answers) about prehistory.\n\ "description": "The following are questions (with answers) about prehistory.\n\
\n" \n"
"group": "mmlu_continuation_humanities" "tag": "mmlu_continuation_humanities"
"include": "_continuation_template_yaml" "include": "_continuation_template_yaml"
"task": "mmlu_continuation_prehistory" "task": "mmlu_continuation_prehistory"
"dataset_name": "professional_accounting" "dataset_name": "professional_accounting"
"description": "The following are questions (with answers) about professional\ "description": "The following are questions (with answers) about professional\
\ accounting.\n\n" \ accounting.\n\n"
"group": "mmlu_continuation_other" "tag": "mmlu_continuation_other"
"include": "_continuation_template_yaml" "include": "_continuation_template_yaml"
"task": "mmlu_continuation_professional_accounting" "task": "mmlu_continuation_professional_accounting"
"dataset_name": "professional_law" "dataset_name": "professional_law"
"description": "The following are questions (with answers) about professional\ "description": "The following are questions (with answers) about professional\
\ law.\n\n" \ law.\n\n"
"group": "mmlu_continuation_humanities" "tag": "mmlu_continuation_humanities"
"include": "_continuation_template_yaml" "include": "_continuation_template_yaml"
"task": "mmlu_continuation_professional_law" "task": "mmlu_continuation_professional_law"
"dataset_name": "professional_medicine" "dataset_name": "professional_medicine"
"description": "The following are questions (with answers) about professional\ "description": "The following are questions (with answers) about professional\
\ medicine.\n\n" \ medicine.\n\n"
"group": "mmlu_continuation_other" "tag": "mmlu_continuation_other"
"include": "_continuation_template_yaml" "include": "_continuation_template_yaml"
"task": "mmlu_continuation_professional_medicine" "task": "mmlu_continuation_professional_medicine"
"dataset_name": "professional_psychology" "dataset_name": "professional_psychology"
"description": "The following are questions (with answers) about professional\ "description": "The following are questions (with answers) about professional\
\ psychology.\n\n" \ psychology.\n\n"
"group": "mmlu_continuation_social_sciences" "tag": "mmlu_continuation_social_sciences"
"include": "_continuation_template_yaml" "include": "_continuation_template_yaml"
"task": "mmlu_continuation_professional_psychology" "task": "mmlu_continuation_professional_psychology"
"dataset_name": "public_relations" "dataset_name": "public_relations"
"description": "The following are questions (with answers) about public\ "description": "The following are questions (with answers) about public\
\ relations.\n\n" \ relations.\n\n"
"group": "mmlu_continuation_social_sciences" "tag": "mmlu_continuation_social_sciences"
"include": "_continuation_template_yaml" "include": "_continuation_template_yaml"
"task": "mmlu_continuation_public_relations" "task": "mmlu_continuation_public_relations"
"dataset_name": "security_studies" "dataset_name": "security_studies"
"description": "The following are questions (with answers) about security\ "description": "The following are questions (with answers) about security\
\ studies.\n\n" \ studies.\n\n"
"group": "mmlu_continuation_social_sciences" "tag": "mmlu_continuation_social_sciences"
"include": "_continuation_template_yaml" "include": "_continuation_template_yaml"
"task": "mmlu_continuation_security_studies" "task": "mmlu_continuation_security_studies"
"dataset_name": "sociology" "dataset_name": "sociology"
"description": "The following are questions (with answers) about sociology.\n\ "description": "The following are questions (with answers) about sociology.\n\
\n" \n"
"group": "mmlu_continuation_social_sciences" "tag": "mmlu_continuation_social_sciences"
"include": "_continuation_template_yaml" "include": "_continuation_template_yaml"
"task": "mmlu_continuation_sociology" "task": "mmlu_continuation_sociology"
"dataset_name": "us_foreign_policy" "dataset_name": "us_foreign_policy"
"description": "The following are questions (with answers) about us\ "description": "The following are questions (with answers) about us\
\ foreign policy.\n\n" \ foreign policy.\n\n"
"group": "mmlu_continuation_social_sciences" "tag": "mmlu_continuation_social_sciences"
"include": "_continuation_template_yaml" "include": "_continuation_template_yaml"
"task": "mmlu_continuation_us_foreign_policy" "task": "mmlu_continuation_us_foreign_policy"
"dataset_name": "virology" "dataset_name": "virology"
"description": "The following are questions (with answers) about virology.\n\ "description": "The following are questions (with answers) about virology.\n\
\n" \n"
"group": "mmlu_continuation_other" "tag": "mmlu_continuation_other"
"include": "_continuation_template_yaml" "include": "_continuation_template_yaml"
"task": "mmlu_continuation_virology" "task": "mmlu_continuation_virology"
"dataset_name": "world_religions" "dataset_name": "world_religions"
"description": "The following are questions (with answers) about world\ "description": "The following are questions (with answers) about world\
\ religions.\n\n" \ religions.\n\n"
"group": "mmlu_continuation_humanities" "tag": "mmlu_continuation_humanities"
"include": "_continuation_template_yaml" "include": "_continuation_template_yaml"
"task": "mmlu_continuation_world_religions" "task": "mmlu_continuation_world_religions"
...@@ -13,3 +13,5 @@ metric_list: ...@@ -13,3 +13,5 @@ metric_list:
higher_is_better: true higher_is_better: true
metadata: metadata:
version: 0.0 version: 0.0
dataset_kwargs:
trust_remote_code: true
...@@ -4,3 +4,8 @@ task: ...@@ -4,3 +4,8 @@ task:
- mmlu_other - mmlu_other
- mmlu_social_sciences - mmlu_social_sciences
- mmlu_humanities - mmlu_humanities
aggregate_metric_list:
- metric: acc
weight_by_size: True
metadata:
version: 1
group: mmlu_humanities
group_alias: humanities
task:
- mmlu_humanities_tasks
aggregate_metric_list:
- metric: acc
weight_by_size: True
metadata:
version: 1
group: mmlu_other
group_alias: other
task:
- mmlu_other_tasks
aggregate_metric_list:
- metric: acc
weight_by_size: True
metadata:
version: 1
group: mmlu_social_sciences
group_alias: social sciences
task:
- mmlu_social_sciences_tasks
aggregate_metric_list:
- metric: acc
weight_by_size: True
metadata:
version: 1
group: mmlu_stem
group_alias: stem
task:
- mmlu_stem_tasks
aggregate_metric_list:
- metric: acc
weight_by_size: True
metadata:
version: 1
"dataset_name": "abstract_algebra" "dataset_name": "abstract_algebra"
"description": "The following are multiple choice questions (with answers) about abstract\ "description": "The following are multiple choice questions (with answers) about abstract\
\ algebra.\n\n" \ algebra.\n\n"
"group": "mmlu_stem" "tag": "mmlu_stem_tasks"
"group_alias": "stem"
"include": "_default_template_yaml" "include": "_default_template_yaml"
"task": "mmlu_abstract_algebra" "task": "mmlu_abstract_algebra"
"task_alias": "abstract_algebra" "task_alias": "abstract_algebra"
"dataset_name": "anatomy" "dataset_name": "anatomy"
"description": "The following are multiple choice questions (with answers) about anatomy.\n\ "description": "The following are multiple choice questions (with answers) about anatomy.\n\
\n" \n"
"group": "mmlu_stem" "tag": "mmlu_stem_tasks"
"group_alias": "stem"
"include": "_default_template_yaml" "include": "_default_template_yaml"
"task": "mmlu_anatomy" "task": "mmlu_anatomy"
"task_alias": "anatomy" "task_alias": "anatomy"
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