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

lm_eval/tasks/bigbench/generate_until/intent_recognition.yaml

+# Generated by utils.py
+dataset_name: intent_recognition_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_intent_recognition_generate_until

lm_eval/tasks/bigbench/generate_until/international_phonetic_alphabet_nli.yaml

+# Generated by utils.py
+dataset_name: international_phonetic_alphabet_nli_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_international_phonetic_alphabet_nli_generate_until

lm_eval/tasks/bigbench/generate_until/international_phonetic_alphabet_transliterate.yaml

+# Generated by utils.py
+dataset_name: international_phonetic_alphabet_transliterate_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_international_phonetic_alphabet_transliterate_generate_until

lm_eval/tasks/bigbench/generate_until/intersect_geometry.yaml

+# Generated by utils.py
+dataset_name: intersect_geometry_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_intersect_geometry_generate_until

lm_eval/tasks/bigbench/generate_until/irony_identification.yaml

+# Generated by utils.py
+dataset_name: irony_identification_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_irony_identification_generate_until

lm_eval/tasks/bigbench/generate_until/kanji_ascii.yaml

+# Generated by utils.py
+dataset_name: kanji_ascii_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_kanji_ascii_generate_until

lm_eval/tasks/bigbench/generate_until/kannada.yaml

+# Generated by utils.py
+dataset_name: kannada_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_kannada_generate_until

lm_eval/tasks/bigbench/generate_until/key_value_maps.yaml

+# Generated by utils.py
+dataset_name: key_value_maps_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_key_value_maps_generate_until

lm_eval/tasks/bigbench/generate_until/known_unknowns.yaml

+# Generated by utils.py
+dataset_name: known_unknowns_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_known_unknowns_generate_until

lm_eval/tasks/bigbench/generate_until/language_games.yaml

+# Generated by utils.py
+dataset_name: language_games_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_language_games_generate_until

lm_eval/tasks/bigbench/generate_until/language_identification.yaml

+# Generated by utils.py
+dataset_name: language_identification_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_language_identification_generate_until

lm_eval/tasks/bigbench/generate_until/linguistic_mappings.yaml

+# Generated by utils.py
+dataset_name: linguistic_mappings_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_linguistic_mappings_generate_until

lm_eval/tasks/bigbench/generate_until/linguistics_puzzles.yaml

+# Generated by utils.py
+dataset_name: linguistics_puzzles_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_linguistics_puzzles_generate_until

lm_eval/tasks/bigbench/generate_until/list_functions.yaml

+# Generated by utils.py
+dataset_name: list_functions_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_list_functions_generate_until

lm_eval/tasks/bigbench/generate_until/logic_grid_puzzle.yaml

+# Generated by utils.py
+dataset_name: logic_grid_puzzle_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_logic_grid_puzzle_generate_until

lm_eval/tasks/bigbench/generate_until/logical_args.yaml

+# Generated by utils.py
+dataset_name: logical_args_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_logical_args_generate_until

lm_eval/tasks/bigbench/generate_until/logical_deduction.yaml

+# Generated by utils.py
+dataset_name: logical_deduction_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_logical_deduction_generate_until

lm_eval/tasks/bigbench/generate_until/logical_fallacy_detection.yaml

+# Generated by utils.py
+dataset_name: logical_fallacy_detection_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_logical_fallacy_detection_generate_until

lm_eval/tasks/bigbench/generate_until/logical_sequence.yaml

+# Generated by utils.py
+dataset_name: logical_sequence_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_logical_sequence_generate_until

lm_eval/tasks/bigbench/generate_until/mathematical_induction.yaml

+# Generated by utils.py
+dataset_name: mathematical_induction_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_mathematical_induction_generate_until