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

lm_eval/tasks/bigbench/multiple_choice/hindu_knowledge.yaml

+# Generated by utils.py
+dataset_name: hindu_knowledge_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_hindu_knowledge_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/hinglish_toxicity.yaml

+# Generated by utils.py
+dataset_name: hinglish_toxicity_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_hinglish_toxicity_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/human_organs_senses.yaml

+# Generated by utils.py
+dataset_name: human_organs_senses_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_human_organs_senses_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/hyperbaton.yaml

+# Generated by utils.py
+dataset_name: hyperbaton_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_hyperbaton_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/identify_math_theorems.yaml

+# Generated by utils.py
+dataset_name: identify_math_theorems_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_identify_math_theorems_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/identify_odd_metaphor.yaml

+# Generated by utils.py
+dataset_name: identify_odd_metaphor_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_identify_odd_metaphor_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/implicatures.yaml

+# Generated by utils.py
+dataset_name: implicatures_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_implicatures_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/implicit_relations.yaml

+# Generated by utils.py
+dataset_name: implicit_relations_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_implicit_relations_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/intent_recognition.yaml

+# Generated by utils.py
+dataset_name: intent_recognition_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_intent_recognition_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/international_phonetic_alphabet_nli.yaml

+# Generated by utils.py
+dataset_name: international_phonetic_alphabet_nli_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_international_phonetic_alphabet_nli_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/international_phonetic_alphabet_transliterate.yaml

+# Generated by utils.py
+dataset_name: international_phonetic_alphabet_transliterate_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_international_phonetic_alphabet_transliterate_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/intersect_geometry.yaml

+# Generated by utils.py
+dataset_name: intersect_geometry_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_intersect_geometry_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/irony_identification.yaml

+# Generated by utils.py
+dataset_name: irony_identification_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_irony_identification_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/kanji_ascii.yaml

+# Generated by utils.py
+dataset_name: kanji_ascii_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_kanji_ascii_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/kannada.yaml

+# Generated by utils.py
+dataset_name: kannada_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_kannada_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/key_value_maps.yaml

+# Generated by utils.py
+dataset_name: key_value_maps_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_key_value_maps_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/known_unknowns.yaml

+# Generated by utils.py
+dataset_name: known_unknowns_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_known_unknowns_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/language_games.yaml

+# Generated by utils.py
+dataset_name: language_games_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_language_games_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/language_identification.yaml

+# Generated by utils.py
+dataset_name: language_identification_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_language_identification_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/linguistic_mappings.yaml

+# Generated by utils.py
+dataset_name: linguistic_mappings_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_linguistic_mappings_multiple_choice