add bigbench

lm_eval/tasks/bigbench/multiple_choice/periodic_elements.yaml

+# Generated by utils.py
+dataset_name: periodic_elements
+include: ../multiple_choice_template_yaml
+task: bigbench_periodic_elements_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/persian_idioms.yaml

+# Generated by utils.py
+dataset_name: persian_idioms
+include: ../multiple_choice_template_yaml
+task: bigbench_persian_idioms_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/phrase_relatedness.yaml

+# Generated by utils.py
+dataset_name: phrase_relatedness
+include: ../multiple_choice_template_yaml
+task: bigbench_phrase_relatedness_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/physical_intuition.yaml

+# Generated by utils.py
+dataset_name: physical_intuition
+include: ../multiple_choice_template_yaml
+task: bigbench_physical_intuition_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/physics.yaml

+# Generated by utils.py
+dataset_name: physics
+include: ../multiple_choice_template_yaml
+task: bigbench_physics_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/physics_questions.yaml

+# Generated by utils.py
+dataset_name: physics_questions
+include: ../multiple_choice_template_yaml
+task: bigbench_physics_questions_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/play_dialog_same_or_different.yaml

+# Generated by utils.py
+dataset_name: play_dialog_same_or_different
+include: ../multiple_choice_template_yaml
+task: bigbench_play_dialog_same_or_different_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/polish_sequence_labeling.yaml

+# Generated by utils.py
+dataset_name: polish_sequence_labeling
+include: ../multiple_choice_template_yaml
+task: bigbench_polish_sequence_labeling_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/presuppositions_as_nli.yaml

+# Generated by utils.py
+dataset_name: presuppositions_as_nli
+include: ../multiple_choice_template_yaml
+task: bigbench_presuppositions_as_nli_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/qa_wikidata.yaml

+# Generated by utils.py
+dataset_name: qa_wikidata
+include: ../multiple_choice_template_yaml
+task: bigbench_qa_wikidata_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/question_selection.yaml

+# Generated by utils.py
+dataset_name: question_selection
+include: ../multiple_choice_template_yaml
+task: bigbench_question_selection_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/real_or_fake_text.yaml

+# Generated by utils.py
+dataset_name: real_or_fake_text
+include: ../multiple_choice_template_yaml
+task: bigbench_real_or_fake_text_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/reasoning_about_colored_objects.yaml

+# Generated by utils.py
+dataset_name: reasoning_about_colored_objects
+include: ../multiple_choice_template_yaml
+task: bigbench_reasoning_about_colored_objects_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/repeat_copy_logic.yaml

+# Generated by utils.py
+dataset_name: repeat_copy_logic
+include: ../multiple_choice_template_yaml
+task: bigbench_repeat_copy_logic_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/rephrase.yaml

+# Generated by utils.py
+dataset_name: rephrase
+include: ../multiple_choice_template_yaml
+task: bigbench_rephrase_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/riddle_sense.yaml

+# Generated by utils.py
+dataset_name: riddle_sense
+include: ../multiple_choice_template_yaml
+task: bigbench_riddle_sense_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/ruin_names.yaml

+# Generated by utils.py
+dataset_name: ruin_names
+include: ../multiple_choice_template_yaml
+task: bigbench_ruin_names_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/salient_translation_error_detection.yaml

+# Generated by utils.py
+dataset_name: salient_translation_error_detection
+include: ../multiple_choice_template_yaml
+task: bigbench_salient_translation_error_detection_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/scientific_press_release.yaml

+# Generated by utils.py
+dataset_name: scientific_press_release
+include: ../multiple_choice_template_yaml
+task: bigbench_scientific_press_release_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/semantic_parsing_in_context_sparc.yaml

+# Generated by utils.py
+dataset_name: semantic_parsing_in_context_sparc
+include: ../multiple_choice_template_yaml
+task: bigbench_semantic_parsing_in_context_sparc_multiple_choice