merge conflict

lm_eval/tasks/bigbench/generate_until/symbol_interpretation.yaml

+# Generated by utils.py
+dataset_name: symbol_interpretation_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_symbol_interpretation_generate_until

lm_eval/tasks/bigbench/generate_until/temporal_sequences.yaml

+# Generated by utils.py
+dataset_name: temporal_sequences_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_temporal_sequences_generate_until

lm_eval/tasks/bigbench/generate_until/tense.yaml

+# Generated by utils.py
+dataset_name: tense_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_tense_generate_until

lm_eval/tasks/bigbench/generate_until/timedial.yaml

+# Generated by utils.py
+dataset_name: timedial_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_timedial_generate_until

lm_eval/tasks/bigbench/generate_until/topical_chat.yaml

+# Generated by utils.py
+dataset_name: topical_chat_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_topical_chat_generate_until

lm_eval/tasks/bigbench/generate_until/tracking_shuffled_objects.yaml

+# Generated by utils.py
+dataset_name: tracking_shuffled_objects_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_tracking_shuffled_objects_generate_until

lm_eval/tasks/bigbench/generate_until/understanding_fables.yaml

+# Generated by utils.py
+dataset_name: understanding_fables_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_understanding_fables_generate_until

lm_eval/tasks/bigbench/generate_until/undo_permutation.yaml

+# Generated by utils.py
+dataset_name: undo_permutation_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_undo_permutation_generate_until

lm_eval/tasks/bigbench/generate_until/unit_conversion.yaml

+# Generated by utils.py
+dataset_name: unit_conversion_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_unit_conversion_generate_until

lm_eval/tasks/bigbench/generate_until/unit_interpretation.yaml

+# Generated by utils.py
+dataset_name: unit_interpretation_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_unit_interpretation_generate_until

lm_eval/tasks/bigbench/generate_until/unnatural_in_context_learning.yaml

+# Generated by utils.py
+dataset_name: unnatural_in_context_learning_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_unnatural_in_context_learning_generate_until

lm_eval/tasks/bigbench/generate_until/vitaminc_fact_verification.yaml

+# Generated by utils.py
+dataset_name: vitaminc_fact_verification_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_vitaminc_fact_verification_generate_until

lm_eval/tasks/bigbench/generate_until/what_is_the_tao.yaml

+# Generated by utils.py
+dataset_name: what_is_the_tao_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_what_is_the_tao_generate_until

lm_eval/tasks/bigbench/generate_until/which_wiki_edit.yaml

+# Generated by utils.py
+dataset_name: which_wiki_edit_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_which_wiki_edit_generate_until

lm_eval/tasks/bigbench/generate_until/winowhy.yaml

+# Generated by utils.py
+dataset_name: winowhy_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_winowhy_generate_until

lm_eval/tasks/bigbench/generate_until/word_sorting.yaml

+# Generated by utils.py
+dataset_name: word_sorting_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_word_sorting_generate_until

lm_eval/tasks/bigbench/generate_until/word_unscrambling.yaml

+# Generated by utils.py
+dataset_name: word_unscrambling_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_word_unscrambling_generate_until

lm_eval/tasks/bigbench/generate_until_template_yaml

+group: bigbench_generate_until
+dataset_path: hails/bigbench
+output_type: generate_until
+dataset_kwargs:
+  # num_shots: 0 # TODO: num of shots for `bigbench` HF dataset should be controlled through this, not through the typical methods
+  # subtask_name: null
+test_split: default
+doc_to_text: inputs
+doc_to_target: "{{targets[0]}}"
+generation_kwargs:
+  max_length: 128
+metric_list:
+  - metric: exact_match
+    aggregation: mean
+    higher_is_better: true
+    ignore_punctuation: true

lm_eval/tasks/bigbench/multiple_choice/abstract_narrative_understanding.yaml

+# Generated by utils.py
+dataset_name: abstract_narrative_understanding_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_abstract_narrative_understanding_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/anachronisms.yaml

+# Generated by utils.py
+dataset_name: anachronisms_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_anachronisms_multiple_choice