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

lm_eval/tasks/bigbench/generate_until/authorship_verification.yaml

+# Generated by utils.py
+dataset_name: authorship_verification_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_authorship_verification_generate_until

lm_eval/tasks/bigbench/generate_until/auto_categorization.yaml

+# Generated by utils.py
+dataset_name: auto_categorization_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_auto_categorization_generate_until

lm_eval/tasks/bigbench/generate_until/auto_debugging.yaml

+# Generated by utils.py
+dataset_name: auto_debugging_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_auto_debugging_generate_until

lm_eval/tasks/bigbench/generate_until/bbq_lite_json.yaml

+# Generated by utils.py
+dataset_name: bbq_lite_json_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_bbq_lite_json_generate_until

lm_eval/tasks/bigbench/generate_until/bridging_anaphora_resolution_barqa.yaml

+# Generated by utils.py
+dataset_name: bridging_anaphora_resolution_barqa_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_bridging_anaphora_resolution_barqa_generate_until

lm_eval/tasks/bigbench/generate_until/causal_judgment.yaml

+# Generated by utils.py
+dataset_name: causal_judgment_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_causal_judgment_generate_until

lm_eval/tasks/bigbench/generate_until/cause_and_effect.yaml

+# Generated by utils.py
+dataset_name: cause_and_effect_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_cause_and_effect_generate_until

lm_eval/tasks/bigbench/generate_until/checkmate_in_one.yaml

+# Generated by utils.py
+dataset_name: checkmate_in_one_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_checkmate_in_one_generate_until

lm_eval/tasks/bigbench/generate_until/chess_state_tracking.yaml

+# Generated by utils.py
+dataset_name: chess_state_tracking_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_chess_state_tracking_generate_until

lm_eval/tasks/bigbench/generate_until/chinese_remainder_theorem.yaml

+# Generated by utils.py
+dataset_name: chinese_remainder_theorem_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_chinese_remainder_theorem_generate_until

lm_eval/tasks/bigbench/generate_until/cifar10_classification.yaml

+# Generated by utils.py
+dataset_name: cifar10_classification_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_cifar10_classification_generate_until

lm_eval/tasks/bigbench/generate_until/code_line_description.yaml

+# Generated by utils.py
+dataset_name: code_line_description_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_code_line_description_generate_until

lm_eval/tasks/bigbench/generate_until/codenames.yaml

+# Generated by utils.py
+dataset_name: codenames_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_codenames_generate_until

lm_eval/tasks/bigbench/generate_until/color.yaml

+# Generated by utils.py
+dataset_name: color_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_color_generate_until

lm_eval/tasks/bigbench/generate_until/common_morpheme.yaml

+# Generated by utils.py
+dataset_name: common_morpheme_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_common_morpheme_generate_until

lm_eval/tasks/bigbench/generate_until/conceptual_combinations.yaml

+# Generated by utils.py
+dataset_name: conceptual_combinations_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_conceptual_combinations_generate_until

lm_eval/tasks/bigbench/generate_until/conlang_translation.yaml

+# Generated by utils.py
+dataset_name: conlang_translation_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_conlang_translation_generate_until

lm_eval/tasks/bigbench/generate_until/contextual_parametric_knowledge_conflicts.yaml

+# Generated by utils.py
+dataset_name: contextual_parametric_knowledge_conflicts_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_contextual_parametric_knowledge_conflicts_generate_until

lm_eval/tasks/bigbench/generate_until/crash_blossom.yaml

+# Generated by utils.py
+dataset_name: crash_blossom_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_crash_blossom_generate_until

lm_eval/tasks/bigbench/generate_until/crass_ai.yaml

+# Generated by utils.py
+dataset_name: crass_ai_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_crass_ai_generate_until