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

lm_eval/tasks/bigbench/multiple_choice/linguistics_puzzles.yaml

+# Generated by utils.py
+dataset_name: linguistics_puzzles_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_linguistics_puzzles_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/list_functions.yaml

+# Generated by utils.py
+dataset_name: list_functions_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_list_functions_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/logic_grid_puzzle.yaml

+# Generated by utils.py
+dataset_name: logic_grid_puzzle_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_logic_grid_puzzle_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/logical_args.yaml

+# Generated by utils.py
+dataset_name: logical_args_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_logical_args_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/logical_deduction.yaml

+# Generated by utils.py
+dataset_name: logical_deduction_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_logical_deduction_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/logical_fallacy_detection.yaml

+# Generated by utils.py
+dataset_name: logical_fallacy_detection_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_logical_fallacy_detection_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/logical_sequence.yaml

+# Generated by utils.py
+dataset_name: logical_sequence_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_logical_sequence_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/mathematical_induction.yaml

+# Generated by utils.py
+dataset_name: mathematical_induction_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_mathematical_induction_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/matrixshapes.yaml

+# Generated by utils.py
+dataset_name: matrixshapes_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_matrixshapes_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/metaphor_boolean.yaml

+# Generated by utils.py
+dataset_name: metaphor_boolean_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_metaphor_boolean_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/metaphor_understanding.yaml

+# Generated by utils.py
+dataset_name: metaphor_understanding_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_metaphor_understanding_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/minute_mysteries_qa.yaml

+# Generated by utils.py
+dataset_name: minute_mysteries_qa_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_minute_mysteries_qa_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/misconceptions.yaml

+# Generated by utils.py
+dataset_name: misconceptions_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_misconceptions_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/misconceptions_russian.yaml

+# Generated by utils.py
+dataset_name: misconceptions_russian_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_misconceptions_russian_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/mnist_ascii.yaml

+# Generated by utils.py
+dataset_name: mnist_ascii_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_mnist_ascii_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/modified_arithmetic.yaml

+# Generated by utils.py
+dataset_name: modified_arithmetic_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_modified_arithmetic_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/moral_permissibility.yaml

+# Generated by utils.py
+dataset_name: moral_permissibility_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_moral_permissibility_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/movie_dialog_same_or_different.yaml

+# Generated by utils.py
+dataset_name: movie_dialog_same_or_different_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_movie_dialog_same_or_different_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/movie_recommendation.yaml

+# Generated by utils.py
+dataset_name: movie_recommendation_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_movie_recommendation_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/mult_data_wrangling.yaml

+# Generated by utils.py
+dataset_name: mult_data_wrangling_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_mult_data_wrangling_multiple_choice