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/linguistics_puzzles.yaml
+++ b/lm_eval/tasks/bigbench/greedy_until/linguistics_puzzles.yaml
--- a/lm_eval/tasks/bigbench/greedy_until/list_functions.yaml
+++ b/lm_eval/tasks/bigbench/greedy_until/list_functions.yaml
--- a/lm_eval/tasks/bigbench/greedy_until/logic_grid_puzzle.yaml
+++ b/lm_eval/tasks/bigbench/greedy_until/logic_grid_puzzle.yaml
--- a/lm_eval/tasks/bigbench/greedy_until/logical_args.yaml
+++ b/lm_eval/tasks/bigbench/greedy_until/logical_args.yaml
--- a/lm_eval/tasks/bigbench/greedy_until/logical_deduction.yaml
+++ b/lm_eval/tasks/bigbench/greedy_until/logical_deduction.yaml
--- a/lm_eval/tasks/bigbench/greedy_until/logical_fallacy_detection.yaml
+++ b/lm_eval/tasks/bigbench/greedy_until/logical_fallacy_detection.yaml
--- a/lm_eval/tasks/bigbench/greedy_until/logical_sequence.yaml
+++ b/lm_eval/tasks/bigbench/greedy_until/logical_sequence.yaml
--- a/lm_eval/tasks/bigbench/greedy_until/mathematical_induction.yaml
+++ b/lm_eval/tasks/bigbench/greedy_until/mathematical_induction.yaml
--- a/lm_eval/tasks/bigbench/greedy_until/matrixshapes.yaml
+++ b/lm_eval/tasks/bigbench/greedy_until/matrixshapes.yaml
--- a/lm_eval/tasks/bigbench/greedy_until/metaphor_boolean.yaml
+++ b/lm_eval/tasks/bigbench/greedy_until/metaphor_boolean.yaml
--- a/lm_eval/tasks/bigbench/greedy_until/metaphor_understanding.yaml
+++ b/lm_eval/tasks/bigbench/greedy_until/metaphor_understanding.yaml
--- a/lm_eval/tasks/bigbench/greedy_until/minute_mysteries_qa.yaml
+++ b/lm_eval/tasks/bigbench/greedy_until/minute_mysteries_qa.yaml
--- a/lm_eval/tasks/bigbench/greedy_until/misconceptions.yaml
+++ b/lm_eval/tasks/bigbench/greedy_until/misconceptions.yaml
--- a/lm_eval/tasks/bigbench/greedy_until/misconceptions_russian.yaml
+++ b/lm_eval/tasks/bigbench/greedy_until/misconceptions_russian.yaml
--- a/lm_eval/tasks/bigbench/greedy_until/mnist_ascii.yaml
+++ b/lm_eval/tasks/bigbench/greedy_until/mnist_ascii.yaml
--- a/lm_eval/tasks/bigbench/greedy_until/modified_arithmetic.yaml
+++ b/lm_eval/tasks/bigbench/greedy_until/modified_arithmetic.yaml
--- a/lm_eval/tasks/bigbench/greedy_until/moral_permissibility.yaml
+++ b/lm_eval/tasks/bigbench/greedy_until/moral_permissibility.yaml
--- a/lm_eval/tasks/bigbench/greedy_until/movie_dialog_same_or_different.yaml
+++ b/lm_eval/tasks/bigbench/greedy_until/movie_dialog_same_or_different.yaml
--- a/lm_eval/tasks/bigbench/greedy_until/movie_recommendation.yaml
+++ b/lm_eval/tasks/bigbench/greedy_until/movie_recommendation.yaml
--- a/lm_eval/tasks/bigbench/greedy_until/mult_data_wrangling.yaml
+++ b/lm_eval/tasks/bigbench/greedy_until/mult_data_wrangling.yaml