Merge branch 'big-refactor' of...

Merge branch 'big-refactor' of https://github.com/EleutherAI/lm-evaluation-harness into openai_completions

lm_eval/tasks/bigbench/generate_until/salient_translation_error_detection.yaml

+# Generated by utils.py
+dataset_name: salient_translation_error_detection_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_salient_translation_error_detection_generate_until

lm_eval/tasks/bigbench/generate_until/scientific_press_release.yaml

+# Generated by utils.py
+dataset_name: scientific_press_release_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_scientific_press_release_generate_until

lm_eval/tasks/bigbench/generate_until/semantic_parsing_in_context_sparc.yaml

+# Generated by utils.py
+dataset_name: semantic_parsing_in_context_sparc_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_semantic_parsing_in_context_sparc_generate_until

lm_eval/tasks/bigbench/generate_until/semantic_parsing_spider.yaml

+# Generated by utils.py
+dataset_name: semantic_parsing_spider_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_semantic_parsing_spider_generate_until

lm_eval/tasks/bigbench/generate_until/sentence_ambiguity.yaml

+# Generated by utils.py
+dataset_name: sentence_ambiguity_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_sentence_ambiguity_generate_until

lm_eval/tasks/bigbench/generate_until/similarities_abstraction.yaml

+# Generated by utils.py
+dataset_name: similarities_abstraction_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_similarities_abstraction_generate_until

lm_eval/tasks/bigbench/generate_until/simp_turing_concept.yaml

+# Generated by utils.py
+dataset_name: simp_turing_concept_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_simp_turing_concept_generate_until

lm_eval/tasks/bigbench/generate_until/simple_arithmetic_json.yaml

+# Generated by utils.py
+dataset_name: simple_arithmetic_json_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_simple_arithmetic_json_generate_until

lm_eval/tasks/bigbench/generate_until/simple_arithmetic_json_multiple_choice.yaml

+# Generated by utils.py
+dataset_name: simple_arithmetic_json_multiple_choice_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_simple_arithmetic_json_multiple_choice_generate_until

lm_eval/tasks/bigbench/generate_until/simple_arithmetic_json_subtasks.yaml

+# Generated by utils.py
+dataset_name: simple_arithmetic_json_subtasks_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_simple_arithmetic_json_subtasks_generate_until

lm_eval/tasks/bigbench/generate_until/simple_arithmetic_multiple_targets_json.yaml

+# Generated by utils.py
+dataset_name: simple_arithmetic_multiple_targets_json_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_simple_arithmetic_multiple_targets_json_generate_until

lm_eval/tasks/bigbench/generate_until/simple_ethical_questions.yaml

+# Generated by utils.py
+dataset_name: simple_ethical_questions_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_simple_ethical_questions_generate_until

lm_eval/tasks/bigbench/generate_until/simple_text_editing.yaml

+# Generated by utils.py
+dataset_name: simple_text_editing_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_simple_text_editing_generate_until

lm_eval/tasks/bigbench/generate_until/snarks.yaml

+# Generated by utils.py
+dataset_name: snarks_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_snarks_generate_until

lm_eval/tasks/bigbench/generate_until/social_iqa.yaml

+# Generated by utils.py
+dataset_name: social_iqa_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_social_iqa_generate_until

lm_eval/tasks/bigbench/generate_until/social_support.yaml

+# Generated by utils.py
+dataset_name: social_support_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_social_support_generate_until

lm_eval/tasks/bigbench/generate_until/sports_understanding.yaml

+# Generated by utils.py
+dataset_name: sports_understanding_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_sports_understanding_generate_until

lm_eval/tasks/bigbench/generate_until/strange_stories.yaml

+# Generated by utils.py
+dataset_name: strange_stories_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_strange_stories_generate_until

lm_eval/tasks/bigbench/generate_until/strategyqa.yaml

+# Generated by utils.py
+dataset_name: strategyqa_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_strategyqa_generate_until

lm_eval/tasks/bigbench/generate_until/sufficient_information.yaml

+# Generated by utils.py
+dataset_name: sufficient_information_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_sufficient_information_generate_until