Merge branch 'EleutherAI:main' into main

lm_eval/tasks/bigbench/multiple_choice/swahili_english_proverbs.yaml

 # Generated by utils.py
 dataset_name: swahili_english_proverbs_zero_shot
-include: ../multiple_choice_template_yaml
+include: ../multiple_choice_template_a_yaml
 task: bigbench_swahili_english_proverbs_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/swedish_to_german_proverbs.yaml

 # Generated by utils.py
 dataset_name: swedish_to_german_proverbs_zero_shot
-include: ../multiple_choice_template_yaml
+include: ../multiple_choice_template_a_yaml
 task: bigbench_swedish_to_german_proverbs_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/symbol_interpretation.yaml

 # Generated by utils.py
 dataset_name: symbol_interpretation_zero_shot
-include: ../multiple_choice_template_yaml
+include: ../multiple_choice_template_a_yaml
 task: bigbench_symbol_interpretation_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/temporal_sequences.yaml

 # Generated by utils.py
 dataset_name: temporal_sequences_zero_shot
-include: ../multiple_choice_template_yaml
+include: ../multiple_choice_template_a_yaml
 task: bigbench_temporal_sequences_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/tense.yaml

-# Generated by utils.py
-dataset_name: tense_zero_shot
-include: ../multiple_choice_template_yaml
-task: bigbench_tense_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/timedial.yaml

 # Generated by utils.py
 dataset_name: timedial_zero_shot
-include: ../multiple_choice_template_yaml
+include: ../multiple_choice_template_a_yaml
 task: bigbench_timedial_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/topical_chat.yaml

-# Generated by utils.py
-dataset_name: topical_chat_zero_shot
-include: ../multiple_choice_template_yaml
-task: bigbench_topical_chat_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/tracking_shuffled_objects.yaml

 # Generated by utils.py
 dataset_name: tracking_shuffled_objects_zero_shot
-include: ../multiple_choice_template_yaml
+include: ../multiple_choice_template_a_yaml
 task: bigbench_tracking_shuffled_objects_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/understanding_fables.yaml

 # Generated by utils.py
 dataset_name: understanding_fables_zero_shot
-include: ../multiple_choice_template_yaml
+include: ../multiple_choice_template_a_yaml
 task: bigbench_understanding_fables_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/undo_permutation.yaml

 # Generated by utils.py
 dataset_name: undo_permutation_zero_shot
-include: ../multiple_choice_template_yaml
+include: ../multiple_choice_template_a_yaml
 task: bigbench_undo_permutation_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/unit_conversion.yaml

 # Generated by utils.py
 dataset_name: unit_conversion_zero_shot
-include: ../multiple_choice_template_yaml
+include: ../multiple_choice_template_a_yaml
 task: bigbench_unit_conversion_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/unit_interpretation.yaml

 # Generated by utils.py
 dataset_name: unit_interpretation_zero_shot
-include: ../multiple_choice_template_yaml
+include: ../multiple_choice_template_a_yaml
 task: bigbench_unit_interpretation_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/unnatural_in_context_learning.yaml

-# Generated by utils.py
-dataset_name: unnatural_in_context_learning_zero_shot
-include: ../multiple_choice_template_yaml
-task: bigbench_unnatural_in_context_learning_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/vitaminc_fact_verification.yaml

 # Generated by utils.py
 dataset_name: vitaminc_fact_verification_zero_shot
-include: ../multiple_choice_template_yaml
+include: ../multiple_choice_template_a_yaml
 task: bigbench_vitaminc_fact_verification_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/what_is_the_tao.yaml

 # Generated by utils.py
 dataset_name: what_is_the_tao_zero_shot
-include: ../multiple_choice_template_yaml
+include: ../multiple_choice_template_a_yaml
 task: bigbench_what_is_the_tao_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/which_wiki_edit.yaml

 # Generated by utils.py
 dataset_name: which_wiki_edit_zero_shot
-include: ../multiple_choice_template_yaml
+include: ../multiple_choice_template_a_yaml
 task: bigbench_which_wiki_edit_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/winowhy.yaml

 # Generated by utils.py
 dataset_name: winowhy_zero_shot
-include: ../multiple_choice_template_yaml
+include: ../multiple_choice_template_a_yaml
 task: bigbench_winowhy_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/word_sorting.yaml

-# Generated by utils.py
-dataset_name: word_sorting_zero_shot
-include: ../multiple_choice_template_yaml
-task: bigbench_word_sorting_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/word_unscrambling.yaml

-# Generated by utils.py
-dataset_name: word_unscrambling_zero_shot
-include: ../multiple_choice_template_yaml
-task: bigbench_word_unscrambling_multiple_choice

lm_eval/tasks/bigbench/multiple_choice_template_yaml → lm_eval/tasks/bigbench/multiple_choice_template_a_yaml

@@ -12,4 +12,4 @@ metric_list:
   - metric: acc
   # TODO: brier score and other metrics
 metadata:
-  version: 0.0
+  version: 1.0