Merge pull request #922 from EleutherAI/mmlu_subgroups

[Refactor] Mmlu subgroups and weight avg

Merge pull request #922 from EleutherAI/mmlu_subgroups
[Refactor] Mmlu subgroups and weight avg
815f59e6 · Lintang Sutawika · GitHub · 3533e4b9 · 44124d95 · 815f59e6
Unverified Commit 815f59e6 authored Nov 06, 2023 by Lintang Sutawika Committed by GitHub Nov 06, 2023
20 changed files
--- a/lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_formal_logic.yaml
+++ b/lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_formal_logic.yaml
--- a/lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_global_facts.yaml
+++ b/lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_global_facts.yaml
--- a/lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_high_school_biology.yaml
+++ b/lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_high_school_biology.yaml
--- a/lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_high_school_chemistry.yaml
+++ b/lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_high_school_chemistry.yaml
--- a/lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_high_school_computer_science.yaml
+++ b/lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_high_school_computer_science.yaml
--- a/lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_high_school_european_history.yaml
+++ b/lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_high_school_european_history.yaml
--- a/lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_high_school_geography.yaml
+++ b/lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_high_school_geography.yaml
--- a/lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_high_school_government_and_politics.yaml
+++ b/lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_high_school_government_and_politics.yaml
--- a/lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_high_school_macroeconomics.yaml
+++ b/lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_high_school_macroeconomics.yaml
--- a/lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_high_school_mathematics.yaml
+++ b/lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_high_school_mathematics.yaml
--- a/lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_high_school_microeconomics.yaml
+++ b/lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_high_school_microeconomics.yaml
--- a/lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_high_school_physics.yaml
+++ b/lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_high_school_physics.yaml
--- a/lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_high_school_psychology.yaml
+++ b/lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_high_school_psychology.yaml
--- a/lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_high_school_statistics.yaml
+++ b/lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_high_school_statistics.yaml
--- a/lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_high_school_us_history.yaml
+++ b/lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_high_school_us_history.yaml
--- a/lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_high_school_world_history.yaml
+++ b/lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_high_school_world_history.yaml
--- a/lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_human_aging.yaml
+++ b/lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_human_aging.yaml
--- a/lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_human_sexuality.yaml
+++ b/lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_human_sexuality.yaml
--- a/lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_international_law.yaml
+++ b/lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_international_law.yaml
--- a/lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_jurisprudence.yaml
+++ b/lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_jurisprudence.yaml