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

lm_eval/tasks/bigbench/multiple_choice/empirical_judgments.yaml

+# Generated by utils.py
+dataset_name: empirical_judgments_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_empirical_judgments_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/english_proverbs.yaml

+# Generated by utils.py
+dataset_name: english_proverbs_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_english_proverbs_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/english_russian_proverbs.yaml

+# Generated by utils.py
+dataset_name: english_russian_proverbs_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_english_russian_proverbs_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/entailed_polarity.yaml

+# Generated by utils.py
+dataset_name: entailed_polarity_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_entailed_polarity_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/entailed_polarity_hindi.yaml

+# Generated by utils.py
+dataset_name: entailed_polarity_hindi_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_entailed_polarity_hindi_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/epistemic_reasoning.yaml

+# Generated by utils.py
+dataset_name: epistemic_reasoning_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_epistemic_reasoning_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/evaluating_information_essentiality.yaml

+# Generated by utils.py
+dataset_name: evaluating_information_essentiality_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_evaluating_information_essentiality_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/fact_checker.yaml

+# Generated by utils.py
+dataset_name: fact_checker_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_fact_checker_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/fantasy_reasoning.yaml

+# Generated by utils.py
+dataset_name: fantasy_reasoning_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_fantasy_reasoning_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/few_shot_nlg.yaml

+# Generated by utils.py
+dataset_name: few_shot_nlg_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_few_shot_nlg_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/figure_of_speech_detection.yaml

+# Generated by utils.py
+dataset_name: figure_of_speech_detection_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_figure_of_speech_detection_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/formal_fallacies_syllogisms_negation.yaml

+# Generated by utils.py
+dataset_name: formal_fallacies_syllogisms_negation_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_formal_fallacies_syllogisms_negation_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/gem.yaml

+# Generated by utils.py
+dataset_name: gem_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_gem_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/gender_inclusive_sentences_german.yaml

+# Generated by utils.py
+dataset_name: gender_inclusive_sentences_german_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_gender_inclusive_sentences_german_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/general_knowledge.yaml

+# Generated by utils.py
+dataset_name: general_knowledge_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_general_knowledge_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/geometric_shapes.yaml

+# Generated by utils.py
+dataset_name: geometric_shapes_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_geometric_shapes_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/goal_step_wikihow.yaml

+# Generated by utils.py
+dataset_name: goal_step_wikihow_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_goal_step_wikihow_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/gre_reading_comprehension.yaml

+# Generated by utils.py
+dataset_name: gre_reading_comprehension_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_gre_reading_comprehension_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/hhh_alignment.yaml

+# Generated by utils.py
+dataset_name: hhh_alignment_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_hhh_alignment_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/hindi_question_answering.yaml

+# Generated by utils.py
+dataset_name: hindi_question_answering_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_hindi_question_answering_multiple_choice