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_fewshot/mmlu_virology.yaml
+++ b/lm_eval/tasks/mmlu/flan_cot_fewshot/mmlu_virology.yaml
--- a/lm_eval/tasks/mmlu/flan_cot_fewshot/mmlu_world_religions.yaml
+++ b/lm_eval/tasks/mmlu/flan_cot_fewshot/mmlu_world_religions.yaml
--- a/lm_eval/tasks/mmlu/flan_cot_zeroshot/_mmlu.yaml
+++ b/lm_eval/tasks/mmlu/flan_cot_zeroshot/_mmlu.yaml
--- a/lm_eval/tasks/mmlu/flan_cot_zeroshot/_mmlu_flan_generative_template_yaml
+++ b/lm_eval/tasks/mmlu/flan_cot_zeroshot/_mmlu_flan_generative_template_yaml
--- a/lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_abstract_algebra.yaml
+++ b/lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_abstract_algebra.yaml
--- a/lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_anatomy.yaml
+++ b/lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_anatomy.yaml
--- a/lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_astronomy.yaml
+++ b/lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_astronomy.yaml
--- a/lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_business_ethics.yaml
+++ b/lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_business_ethics.yaml
--- a/lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_clinical_knowledge.yaml
+++ b/lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_clinical_knowledge.yaml
--- a/lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_college_biology.yaml
+++ b/lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_college_biology.yaml
--- a/lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_college_chemistry.yaml
+++ b/lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_college_chemistry.yaml
--- a/lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_college_computer_science.yaml
+++ b/lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_college_computer_science.yaml
--- a/lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_college_mathematics.yaml
+++ b/lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_college_mathematics.yaml
--- a/lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_college_medicine.yaml
+++ b/lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_college_medicine.yaml
--- a/lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_college_physics.yaml
+++ b/lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_college_physics.yaml
--- a/lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_computer_security.yaml
+++ b/lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_computer_security.yaml
--- a/lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_conceptual_physics.yaml
+++ b/lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_conceptual_physics.yaml
--- a/lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_econometrics.yaml
+++ b/lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_econometrics.yaml
--- a/lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_electrical_engineering.yaml
+++ b/lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_electrical_engineering.yaml
--- a/lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_elementary_mathematics.yaml
+++ b/lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_elementary_mathematics.yaml