Merge branch 'big-refactor' of...

Merge branch 'big-refactor' of https://github.com/EleutherAI/lm-evaluation-harness into mmlu_subgroups

Merge branch 'big-refactor' of...
Merge branch 'big-refactor' of https://github.com/EleutherAI/lm-evaluation-harness into mmlu_subgroups
f77a3a27 · lintangsutawika · 109ed1c7 · f8342178 · f77a3a27 · f77a3a27
Commit f77a3a27 authored Oct 17, 2023 by lintangsutawika
20 changed files
--- a/lm_eval/tasks/bigbench/greedy_until/multiemo.yaml
+++ b/lm_eval/tasks/bigbench/greedy_until/multiemo.yaml
--- a/lm_eval/tasks/bigbench/greedy_until/natural_instructions.yaml
+++ b/lm_eval/tasks/bigbench/greedy_until/natural_instructions.yaml
--- a/lm_eval/tasks/bigbench/greedy_until/navigate.yaml
+++ b/lm_eval/tasks/bigbench/greedy_until/navigate.yaml
--- a/lm_eval/tasks/bigbench/greedy_until/nonsense_words_grammar.yaml
+++ b/lm_eval/tasks/bigbench/greedy_until/nonsense_words_grammar.yaml
--- a/lm_eval/tasks/bigbench/greedy_until/novel_concepts.yaml
+++ b/lm_eval/tasks/bigbench/greedy_until/novel_concepts.yaml
--- a/lm_eval/tasks/bigbench/greedy_until/object_counting.yaml
+++ b/lm_eval/tasks/bigbench/greedy_until/object_counting.yaml
--- a/lm_eval/tasks/bigbench/greedy_until/odd_one_out.yaml
+++ b/lm_eval/tasks/bigbench/greedy_until/odd_one_out.yaml
--- a/lm_eval/tasks/bigbench/greedy_until/operators.yaml
+++ b/lm_eval/tasks/bigbench/greedy_until/operators.yaml
--- a/lm_eval/tasks/bigbench/greedy_until/paragraph_segmentation.yaml
+++ b/lm_eval/tasks/bigbench/greedy_until/paragraph_segmentation.yaml
--- a/lm_eval/tasks/bigbench/greedy_until/parsinlu_qa.yaml
+++ b/lm_eval/tasks/bigbench/greedy_until/parsinlu_qa.yaml
--- a/lm_eval/tasks/bigbench/greedy_until/parsinlu_reading_comprehension.yaml
+++ b/lm_eval/tasks/bigbench/greedy_until/parsinlu_reading_comprehension.yaml
--- a/lm_eval/tasks/bigbench/greedy_until/penguins_in_a_table.yaml
+++ b/lm_eval/tasks/bigbench/greedy_until/penguins_in_a_table.yaml
--- a/lm_eval/tasks/bigbench/greedy_until/periodic_elements.yaml
+++ b/lm_eval/tasks/bigbench/greedy_until/periodic_elements.yaml
--- a/lm_eval/tasks/bigbench/greedy_until/persian_idioms.yaml
+++ b/lm_eval/tasks/bigbench/greedy_until/persian_idioms.yaml
--- a/lm_eval/tasks/bigbench/greedy_until/phrase_relatedness.yaml
+++ b/lm_eval/tasks/bigbench/greedy_until/phrase_relatedness.yaml
--- a/lm_eval/tasks/bigbench/greedy_until/physical_intuition.yaml
+++ b/lm_eval/tasks/bigbench/greedy_until/physical_intuition.yaml
--- a/lm_eval/tasks/bigbench/greedy_until/physics.yaml
+++ b/lm_eval/tasks/bigbench/greedy_until/physics.yaml
--- a/lm_eval/tasks/bigbench/greedy_until/physics_questions.yaml
+++ b/lm_eval/tasks/bigbench/greedy_until/physics_questions.yaml
--- a/lm_eval/tasks/bigbench/greedy_until/play_dialog_same_or_different.yaml
+++ b/lm_eval/tasks/bigbench/greedy_until/play_dialog_same_or_different.yaml
--- a/lm_eval/tasks/bigbench/greedy_until/polish_sequence_labeling.yaml
+++ b/lm_eval/tasks/bigbench/greedy_until/polish_sequence_labeling.yaml