Merge remote-tracking branch 'origin/big-refactor' into calibration

lm_eval/tasks/bigbench/multiple_choice/multiemo.yaml

+# Generated by utils.py
+dataset_name: multiemo_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_multiemo_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/natural_instructions.yaml

+# Generated by utils.py
+dataset_name: natural_instructions_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_natural_instructions_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/navigate.yaml

+# Generated by utils.py
+dataset_name: navigate_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_navigate_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/nonsense_words_grammar.yaml

+# Generated by utils.py
+dataset_name: nonsense_words_grammar_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_nonsense_words_grammar_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/novel_concepts.yaml

+# Generated by utils.py
+dataset_name: novel_concepts_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_novel_concepts_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/object_counting.yaml

+# Generated by utils.py
+dataset_name: object_counting_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_object_counting_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/odd_one_out.yaml

+# Generated by utils.py
+dataset_name: odd_one_out_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_odd_one_out_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/operators.yaml

+# Generated by utils.py
+dataset_name: operators_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_operators_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/paragraph_segmentation.yaml

+# Generated by utils.py
+dataset_name: paragraph_segmentation_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_paragraph_segmentation_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/parsinlu_qa.yaml

+# Generated by utils.py
+dataset_name: parsinlu_qa_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_parsinlu_qa_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/parsinlu_reading_comprehension.yaml

+# Generated by utils.py
+dataset_name: parsinlu_reading_comprehension_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_parsinlu_reading_comprehension_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/penguins_in_a_table.yaml

+# Generated by utils.py
+dataset_name: penguins_in_a_table_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_penguins_in_a_table_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/periodic_elements.yaml

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