Merge branch 'group-agg-rework' of...

Merge branch 'group-agg-rework' of https://github.com/EleutherAI/lm-evaluation-harness into multiprompt

Merge branch 'group-agg-rework' of...
Merge branch 'group-agg-rework' of https://github.com/EleutherAI/lm-evaluation-harness into multiprompt
88486e57 · lintangsutawika · 5971f2ca · ba73d131 · 88486e57 · 88486e57
Commit 88486e57 authored Jul 05, 2024 by lintangsutawika
20 changed files
--- a/lm_eval/tasks/arabicmmlu/arabicmmlu_univ_accounting.yaml
+++ b/lm_eval/tasks/arabicmmlu/arabicmmlu_univ_accounting.yaml
--- a/lm_eval/tasks/arabicmmlu/arabicmmlu_univ_computer_science.yaml
+++ b/lm_eval/tasks/arabicmmlu/arabicmmlu_univ_computer_science.yaml
--- a/lm_eval/tasks/arabicmmlu/arabicmmlu_univ_economics.yaml
+++ b/lm_eval/tasks/arabicmmlu/arabicmmlu_univ_economics.yaml
--- a/lm_eval/tasks/arabicmmlu/arabicmmlu_univ_management.yaml
+++ b/lm_eval/tasks/arabicmmlu/arabicmmlu_univ_management.yaml
--- a/lm_eval/tasks/arabicmmlu/arabicmmlu_univ_political_science.yaml
+++ b/lm_eval/tasks/arabicmmlu/arabicmmlu_univ_political_science.yaml
--- a/lm_eval/tasks/arabicmmlu/utils.py
+++ b/lm_eval/tasks/arabicmmlu/utils.py
--- a/lm_eval/tasks/arc/README.md
+++ b/lm_eval/tasks/arc/README.md
--- a/lm_eval/tasks/arc/arc_easy.yaml
+++ b/lm_eval/tasks/arc/arc_easy.yaml
--- a/lm_eval/tasks/arc_mt/README.md
+++ b/lm_eval/tasks/arc_mt/README.md
--- a/lm_eval/tasks/arc_mt/arc_challenge_mt_da.yaml
+++ b/lm_eval/tasks/arc_mt/arc_challenge_mt_da.yaml
--- a/lm_eval/tasks/arc_mt/arc_challenge_mt_de.yaml
+++ b/lm_eval/tasks/arc_mt/arc_challenge_mt_de.yaml
--- a/lm_eval/tasks/arc_mt/arc_challenge_mt_el.yaml
+++ b/lm_eval/tasks/arc_mt/arc_challenge_mt_el.yaml
--- a/lm_eval/tasks/arc_mt/arc_challenge_mt_es.yaml
+++ b/lm_eval/tasks/arc_mt/arc_challenge_mt_es.yaml
--- a/lm_eval/tasks/arc_mt/arc_challenge_mt_fi.yaml
+++ b/lm_eval/tasks/arc_mt/arc_challenge_mt_fi.yaml
--- a/lm_eval/tasks/arc_mt/arc_challenge_mt_hu.yaml
+++ b/lm_eval/tasks/arc_mt/arc_challenge_mt_hu.yaml
--- a/lm_eval/tasks/arc_mt/arc_challenge_mt_is.yaml
+++ b/lm_eval/tasks/arc_mt/arc_challenge_mt_is.yaml
--- a/lm_eval/tasks/arc_mt/arc_challenge_mt_it.yaml
+++ b/lm_eval/tasks/arc_mt/arc_challenge_mt_it.yaml
--- a/lm_eval/tasks/arc_mt/arc_challenge_mt_nb.yaml
+++ b/lm_eval/tasks/arc_mt/arc_challenge_mt_nb.yaml
--- a/lm_eval/tasks/arc_mt/arc_challenge_mt_pl.yaml
+++ b/lm_eval/tasks/arc_mt/arc_challenge_mt_pl.yaml
--- a/lm_eval/tasks/arc_mt/arc_challenge_mt_pt.yaml
+++ b/lm_eval/tasks/arc_mt/arc_challenge_mt_pt.yaml