-
Notifications
You must be signed in to change notification settings - Fork 109
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Change the eos condition for GSM8K (#85)
We now cover both leaderboard|GSM8K to reproduce the leaderboard's score and lighteval|GSM8K
- Loading branch information
1 parent
3b0aa23
commit 9b3813f
Showing
10 changed files
with
301 additions
and
298 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Large diffs are not rendered by default.
Oops, something went wrong.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -1,68 +1,68 @@ | ||
| # ARC | ||
| lighteval|arc:challenge|25|0 | ||
| leaderboard|arc:challenge|25|0 | ||
| # HellaSwag | ||
| lighteval|hellaswag|10|0 | ||
| leaderboard|hellaswag|10|0 | ||
| # TruthfulQA | ||
| lighteval|truthfulqa:mc|0|0 | ||
| leaderboard|truthfulqa:mc|0|0 | ||
| # MMLU | ||
| lighteval|mmlu:abstract_algebra|5|0 | ||
| lighteval|mmlu:anatomy|5|0 | ||
| lighteval|mmlu:astronomy|5|0 | ||
| lighteval|mmlu:business_ethics|5|0 | ||
| lighteval|mmlu:clinical_knowledge|5|0 | ||
| lighteval|mmlu:college_biology|5|0 | ||
| lighteval|mmlu:college_chemistry|5|0 | ||
| lighteval|mmlu:college_computer_science|5|0 | ||
| lighteval|mmlu:college_mathematics|5|0 | ||
| lighteval|mmlu:college_medicine|5|0 | ||
| lighteval|mmlu:college_physics|5|0 | ||
| lighteval|mmlu:computer_security|5|0 | ||
| lighteval|mmlu:conceptual_physics|5|0 | ||
| lighteval|mmlu:econometrics|5|0 | ||
| lighteval|mmlu:electrical_engineering|5|0 | ||
| lighteval|mmlu:elementary_mathematics|5|0 | ||
| lighteval|mmlu:formal_logic|5|0 | ||
| lighteval|mmlu:global_facts|5|0 | ||
| lighteval|mmlu:high_school_biology|5|0 | ||
| lighteval|mmlu:high_school_chemistry|5|0 | ||
| lighteval|mmlu:high_school_computer_science|5|0 | ||
| lighteval|mmlu:high_school_european_history|5|0 | ||
| lighteval|mmlu:high_school_geography|5|0 | ||
| lighteval|mmlu:high_school_government_and_politics|5|0 | ||
| lighteval|mmlu:high_school_macroeconomics|5|0 | ||
| lighteval|mmlu:high_school_mathematics|5|0 | ||
| lighteval|mmlu:high_school_microeconomics|5|0 | ||
| lighteval|mmlu:high_school_physics|5|0 | ||
| lighteval|mmlu:high_school_psychology|5|0 | ||
| lighteval|mmlu:high_school_statistics|5|0 | ||
| lighteval|mmlu:high_school_us_history|5|0 | ||
| lighteval|mmlu:high_school_world_history|5|0 | ||
| lighteval|mmlu:human_aging|5|0 | ||
| lighteval|mmlu:human_sexuality|5|0 | ||
| lighteval|mmlu:international_law|5|0 | ||
| lighteval|mmlu:jurisprudence|5|0 | ||
| lighteval|mmlu:logical_fallacies|5|0 | ||
| lighteval|mmlu:machine_learning|5|0 | ||
| lighteval|mmlu:management|5|0 | ||
| lighteval|mmlu:marketing|5|0 | ||
| lighteval|mmlu:medical_genetics|5|0 | ||
| lighteval|mmlu:miscellaneous|5|0 | ||
| lighteval|mmlu:moral_disputes|5|0 | ||
| lighteval|mmlu:moral_scenarios|5|0 | ||
| lighteval|mmlu:nutrition|5|0 | ||
| lighteval|mmlu:philosophy|5|0 | ||
| lighteval|mmlu:prehistory|5|0 | ||
| lighteval|mmlu:professional_accounting|5|0 | ||
| lighteval|mmlu:professional_law|5|0 | ||
| lighteval|mmlu:professional_medicine|5|0 | ||
| lighteval|mmlu:professional_psychology|5|0 | ||
| lighteval|mmlu:public_relations|5|0 | ||
| lighteval|mmlu:security_studies|5|0 | ||
| lighteval|mmlu:sociology|5|0 | ||
| lighteval|mmlu:us_foreign_policy|5|0 | ||
| lighteval|mmlu:virology|5|0 | ||
| lighteval|mmlu:world_religions|5|0 | ||
| leaderboard|mmlu:abstract_algebra|5|0 | ||
| leaderboard|mmlu:anatomy|5|0 | ||
| leaderboard|mmlu:astronomy|5|0 | ||
| leaderboard|mmlu:business_ethics|5|0 | ||
| leaderboard|mmlu:clinical_knowledge|5|0 | ||
| leaderboard|mmlu:college_biology|5|0 | ||
| leaderboard|mmlu:college_chemistry|5|0 | ||
| leaderboard|mmlu:college_computer_science|5|0 | ||
| leaderboard|mmlu:college_mathematics|5|0 | ||
| leaderboard|mmlu:college_medicine|5|0 | ||
| leaderboard|mmlu:college_physics|5|0 | ||
| leaderboard|mmlu:computer_security|5|0 | ||
| leaderboard|mmlu:conceptual_physics|5|0 | ||
| leaderboard|mmlu:econometrics|5|0 | ||
| leaderboard|mmlu:electrical_engineering|5|0 | ||
| leaderboard|mmlu:elementary_mathematics|5|0 | ||
| leaderboard|mmlu:formal_logic|5|0 | ||
| leaderboard|mmlu:global_facts|5|0 | ||
| leaderboard|mmlu:high_school_biology|5|0 | ||
| leaderboard|mmlu:high_school_chemistry|5|0 | ||
| leaderboard|mmlu:high_school_computer_science|5|0 | ||
| leaderboard|mmlu:high_school_european_history|5|0 | ||
| leaderboard|mmlu:high_school_geography|5|0 | ||
| leaderboard|mmlu:high_school_government_and_politics|5|0 | ||
| leaderboard|mmlu:high_school_macroeconomics|5|0 | ||
| leaderboard|mmlu:high_school_mathematics|5|0 | ||
| leaderboard|mmlu:high_school_microeconomics|5|0 | ||
| leaderboard|mmlu:high_school_physics|5|0 | ||
| leaderboard|mmlu:high_school_psychology|5|0 | ||
| leaderboard|mmlu:high_school_statistics|5|0 | ||
| leaderboard|mmlu:high_school_us_history|5|0 | ||
| leaderboard|mmlu:high_school_world_history|5|0 | ||
| leaderboard|mmlu:human_aging|5|0 | ||
| leaderboard|mmlu:human_sexuality|5|0 | ||
| leaderboard|mmlu:international_law|5|0 | ||
| leaderboard|mmlu:jurisprudence|5|0 | ||
| leaderboard|mmlu:logical_fallacies|5|0 | ||
| leaderboard|mmlu:machine_learning|5|0 | ||
| leaderboard|mmlu:management|5|0 | ||
| leaderboard|mmlu:marketing|5|0 | ||
| leaderboard|mmlu:medical_genetics|5|0 | ||
| leaderboard|mmlu:miscellaneous|5|0 | ||
| leaderboard|mmlu:moral_disputes|5|0 | ||
| leaderboard|mmlu:moral_scenarios|5|0 | ||
| leaderboard|mmlu:nutrition|5|0 | ||
| leaderboard|mmlu:philosophy|5|0 | ||
| leaderboard|mmlu:prehistory|5|0 | ||
| leaderboard|mmlu:professional_accounting|5|0 | ||
| leaderboard|mmlu:professional_law|5|0 | ||
| leaderboard|mmlu:professional_medicine|5|0 | ||
| leaderboard|mmlu:professional_psychology|5|0 | ||
| leaderboard|mmlu:public_relations|5|0 | ||
| leaderboard|mmlu:security_studies|5|0 | ||
| leaderboard|mmlu:sociology|5|0 | ||
| leaderboard|mmlu:us_foreign_policy|5|0 | ||
| leaderboard|mmlu:virology|5|0 | ||
| leaderboard|mmlu:world_religions|5|0 | ||
| # WinoGrande | ||
| lighteval|winogrande|5|0 | ||
| leaderboard|winogrande|5|0 | ||
| # GSM8K | ||
| lighteval|gsm8k|5|0 | ||
| leaderboard|gsm8k|5|0 |
Oops, something went wrong.