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

lm_eval/tasks/bigbench/generate_until/fantasy_reasoning.yaml

+# Generated by utils.py
+dataset_name: fantasy_reasoning_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_fantasy_reasoning_generate_until

lm_eval/tasks/bigbench/generate_until/few_shot_nlg.yaml

+# Generated by utils.py
+dataset_name: few_shot_nlg_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_few_shot_nlg_generate_until

lm_eval/tasks/bigbench/generate_until/figure_of_speech_detection.yaml

+# Generated by utils.py
+dataset_name: figure_of_speech_detection_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_figure_of_speech_detection_generate_until

lm_eval/tasks/bigbench/generate_until/formal_fallacies_syllogisms_negation.yaml

+# Generated by utils.py
+dataset_name: formal_fallacies_syllogisms_negation_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_formal_fallacies_syllogisms_negation_generate_until

lm_eval/tasks/bigbench/generate_until/gem.yaml

+# Generated by utils.py
+dataset_name: gem_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_gem_generate_until

lm_eval/tasks/bigbench/generate_until/gender_inclusive_sentences_german.yaml

+# Generated by utils.py
+dataset_name: gender_inclusive_sentences_german_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_gender_inclusive_sentences_german_generate_until

lm_eval/tasks/bigbench/generate_until/general_knowledge.yaml

+# Generated by utils.py
+dataset_name: general_knowledge_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_general_knowledge_generate_until

lm_eval/tasks/bigbench/generate_until/geometric_shapes.yaml

+# Generated by utils.py
+dataset_name: geometric_shapes_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_geometric_shapes_generate_until

lm_eval/tasks/bigbench/generate_until/goal_step_wikihow.yaml

+# Generated by utils.py
+dataset_name: goal_step_wikihow_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_goal_step_wikihow_generate_until

lm_eval/tasks/bigbench/generate_until/gre_reading_comprehension.yaml

+# Generated by utils.py
+dataset_name: gre_reading_comprehension_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_gre_reading_comprehension_generate_until

lm_eval/tasks/bigbench/generate_until/hhh_alignment.yaml

+# Generated by utils.py
+dataset_name: hhh_alignment_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_hhh_alignment_generate_until

lm_eval/tasks/bigbench/generate_until/hindi_question_answering.yaml

+# Generated by utils.py
+dataset_name: hindi_question_answering_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_hindi_question_answering_generate_until

lm_eval/tasks/bigbench/generate_until/hindu_knowledge.yaml

+# Generated by utils.py
+dataset_name: hindu_knowledge_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_hindu_knowledge_generate_until

lm_eval/tasks/bigbench/generate_until/hinglish_toxicity.yaml

+# Generated by utils.py
+dataset_name: hinglish_toxicity_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_hinglish_toxicity_generate_until

lm_eval/tasks/bigbench/generate_until/human_organs_senses.yaml

+# Generated by utils.py
+dataset_name: human_organs_senses_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_human_organs_senses_generate_until

lm_eval/tasks/bigbench/generate_until/hyperbaton.yaml

+# Generated by utils.py
+dataset_name: hyperbaton_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_hyperbaton_generate_until

lm_eval/tasks/bigbench/generate_until/identify_math_theorems.yaml

+# Generated by utils.py
+dataset_name: identify_math_theorems_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_identify_math_theorems_generate_until

lm_eval/tasks/bigbench/generate_until/identify_odd_metaphor.yaml

+# Generated by utils.py
+dataset_name: identify_odd_metaphor_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_identify_odd_metaphor_generate_until

lm_eval/tasks/bigbench/generate_until/implicatures.yaml

+# Generated by utils.py
+dataset_name: implicatures_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_implicatures_generate_until

lm_eval/tasks/bigbench/generate_until/implicit_relations.yaml

+# Generated by utils.py
+dataset_name: implicit_relations_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_implicit_relations_generate_until