Merge branch 'big-refactor' into verbosity-rework

574e565a · Lintang Sutawika · GitHub · 73f3029c · b7a4ea06 · 574e565a
Unverified Commit 574e565a authored Nov 10, 2023 by Lintang Sutawika Committed by GitHub Nov 10, 2023
20 changed files
--- a/lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_professional_psychology.yaml
+++ b/lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_professional_psychology.yaml
--- a/lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_public_relations.yaml
+++ b/lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_public_relations.yaml
--- a/lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_security_studies.yaml
+++ b/lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_security_studies.yaml
--- a/lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_sociology.yaml
+++ b/lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_sociology.yaml
--- a/lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_us_foreign_policy.yaml
+++ b/lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_us_foreign_policy.yaml
--- a/lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_virology.yaml
+++ b/lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_virology.yaml
--- a/lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_world_religions.yaml
+++ b/lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_world_religions.yaml
--- a/lm_eval/tasks/mmlu/flan_n_shot/generative/_mmlu.yaml
+++ b/lm_eval/tasks/mmlu/flan_n_shot/generative/_mmlu.yaml
--- a/lm_eval/tasks/mmlu/flan_n_shot/_mmlu_flan_generative_template_yaml
+++ b/lm_eval/tasks/mmlu/flan_n_shot/_mmlu_flan_generative_template_yaml
--- a/lm_eval/tasks/mmlu/flan_n_shot/mmlu_gen_abstract_algebra.yaml
+++ b/lm_eval/tasks/mmlu/flan_n_shot/mmlu_gen_abstract_algebra.yaml
--- a/lm_eval/tasks/mmlu/flan_n_shot/mmlu_gen_anatomy.yaml
+++ b/lm_eval/tasks/mmlu/flan_n_shot/mmlu_gen_anatomy.yaml
--- a/lm_eval/tasks/mmlu/flan_n_shot/mmlu_gen_astronomy.yaml
+++ b/lm_eval/tasks/mmlu/flan_n_shot/mmlu_gen_astronomy.yaml
--- a/lm_eval/tasks/mmlu/flan_n_shot/mmlu_gen_business_ethics.yaml
+++ b/lm_eval/tasks/mmlu/flan_n_shot/mmlu_gen_business_ethics.yaml
--- a/lm_eval/tasks/mmlu/flan_n_shot/mmlu_gen_clinical_knowledge.yaml
+++ b/lm_eval/tasks/mmlu/flan_n_shot/mmlu_gen_clinical_knowledge.yaml
--- a/lm_eval/tasks/mmlu/flan_n_shot/mmlu_gen_college_biology.yaml
+++ b/lm_eval/tasks/mmlu/flan_n_shot/mmlu_gen_college_biology.yaml
--- a/lm_eval/tasks/mmlu/flan_n_shot/mmlu_gen_college_chemistry.yaml
+++ b/lm_eval/tasks/mmlu/flan_n_shot/mmlu_gen_college_chemistry.yaml
--- a/lm_eval/tasks/mmlu/flan_n_shot/mmlu_gen_college_computer_science.yaml
+++ b/lm_eval/tasks/mmlu/flan_n_shot/mmlu_gen_college_computer_science.yaml
--- a/lm_eval/tasks/mmlu/flan_n_shot/mmlu_gen_college_mathematics.yaml
+++ b/lm_eval/tasks/mmlu/flan_n_shot/mmlu_gen_college_mathematics.yaml
--- a/lm_eval/tasks/mmlu/flan_n_shot/mmlu_gen_college_medicine.yaml
+++ b/lm_eval/tasks/mmlu/flan_n_shot/mmlu_gen_college_medicine.yaml
--- a/lm_eval/tasks/mmlu/flan_n_shot/mmlu_gen_college_physics.yaml
+++ b/lm_eval/tasks/mmlu/flan_n_shot/mmlu_gen_college_physics.yaml