Merge branch 'main' into inverse-scaling-tasks

lm_eval/tasks/bigbench/multiple_choice/simple_arithmetic_multiple_targets_json.yaml

-# Generated by utils.py
-dataset_name: simple_arithmetic_multiple_targets_json_zero_shot
-include: ../multiple_choice_template_yaml
-task: bigbench_simple_arithmetic_multiple_targets_json_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/simple_ethical_questions.yaml

 # Generated by utils.py
 dataset_name: simple_ethical_questions_zero_shot
-include: ../multiple_choice_template_yaml
+include: ../multiple_choice_template_a_yaml
 task: bigbench_simple_ethical_questions_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/simple_text_editing.yaml

-# Generated by utils.py
-dataset_name: simple_text_editing_zero_shot
-include: ../multiple_choice_template_yaml
-task: bigbench_simple_text_editing_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/snarks.yaml

 # Generated by utils.py
 dataset_name: snarks_zero_shot
-include: ../multiple_choice_template_yaml
+include: ../multiple_choice_template_a_yaml
 task: bigbench_snarks_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/social_iqa.yaml

 # Generated by utils.py
 dataset_name: social_iqa_zero_shot
-include: ../multiple_choice_template_yaml
+include: ../multiple_choice_template_a_yaml
 task: bigbench_social_iqa_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/social_support.yaml

 # Generated by utils.py
 dataset_name: social_support_zero_shot
-include: ../multiple_choice_template_yaml
+include: ../multiple_choice_template_a_yaml
 task: bigbench_social_support_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/sports_understanding.yaml

 # Generated by utils.py
 dataset_name: sports_understanding_zero_shot
-include: ../multiple_choice_template_yaml
+include: ../multiple_choice_template_a_yaml
 task: bigbench_sports_understanding_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/strange_stories.yaml

 # Generated by utils.py
 dataset_name: strange_stories_zero_shot
-include: ../multiple_choice_template_yaml
+include: ../multiple_choice_template_a_yaml
 task: bigbench_strange_stories_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/strategyqa.yaml

 # Generated by utils.py
 dataset_name: strategyqa_zero_shot
-include: ../multiple_choice_template_yaml
+include: ../multiple_choice_template_b_yaml
 task: bigbench_strategyqa_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/sufficient_information.yaml

-# Generated by utils.py
-dataset_name: sufficient_information_zero_shot
-include: ../multiple_choice_template_yaml
-task: bigbench_sufficient_information_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/suicide_risk.yaml

 # Generated by utils.py
 dataset_name: suicide_risk_zero_shot
-include: ../multiple_choice_template_yaml
+include: ../multiple_choice_template_a_yaml
 task: bigbench_suicide_risk_multiple_choice

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