Merge branch 'big-refactor' of...

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

lm_eval/tasks/bigbench/greedy_until/riddle_sense.yaml

+# Generated by utils.py
+dataset_name: riddle_sense_zero_shot
+include: ../greedy_until_template_yaml
+task: bigbench_riddle_sense_greedy_until

lm_eval/tasks/bigbench/greedy_until/ruin_names.yaml

+# Generated by utils.py
+dataset_name: ruin_names_zero_shot
+include: ../greedy_until_template_yaml
+task: bigbench_ruin_names_greedy_until

lm_eval/tasks/bigbench/greedy_until/salient_translation_error_detection.yaml

+# Generated by utils.py
+dataset_name: salient_translation_error_detection_zero_shot
+include: ../greedy_until_template_yaml
+task: bigbench_salient_translation_error_detection_greedy_until

lm_eval/tasks/bigbench/greedy_until/scientific_press_release.yaml

+# Generated by utils.py
+dataset_name: scientific_press_release_zero_shot
+include: ../greedy_until_template_yaml
+task: bigbench_scientific_press_release_greedy_until

lm_eval/tasks/bigbench/greedy_until/semantic_parsing_in_context_sparc.yaml

+# Generated by utils.py
+dataset_name: semantic_parsing_in_context_sparc_zero_shot
+include: ../greedy_until_template_yaml
+task: bigbench_semantic_parsing_in_context_sparc_greedy_until

lm_eval/tasks/bigbench/greedy_until/semantic_parsing_spider.yaml

+# Generated by utils.py
+dataset_name: semantic_parsing_spider_zero_shot
+include: ../greedy_until_template_yaml
+task: bigbench_semantic_parsing_spider_greedy_until

lm_eval/tasks/bigbench/greedy_until/sentence_ambiguity.yaml

+# Generated by utils.py
+dataset_name: sentence_ambiguity_zero_shot
+include: ../greedy_until_template_yaml
+task: bigbench_sentence_ambiguity_greedy_until

lm_eval/tasks/bigbench/greedy_until/similarities_abstraction.yaml

+# Generated by utils.py
+dataset_name: similarities_abstraction_zero_shot
+include: ../greedy_until_template_yaml
+task: bigbench_similarities_abstraction_greedy_until

lm_eval/tasks/bigbench/greedy_until/simp_turing_concept.yaml

+# Generated by utils.py
+dataset_name: simp_turing_concept_zero_shot
+include: ../greedy_until_template_yaml
+task: bigbench_simp_turing_concept_greedy_until

lm_eval/tasks/bigbench/greedy_until/simple_arithmetic_json.yaml

+# Generated by utils.py
+dataset_name: simple_arithmetic_json_zero_shot
+include: ../greedy_until_template_yaml
+task: bigbench_simple_arithmetic_json_greedy_until

lm_eval/tasks/bigbench/greedy_until/simple_arithmetic_json_multiple_choice.yaml

+# Generated by utils.py
+dataset_name: simple_arithmetic_json_multiple_choice_zero_shot
+include: ../greedy_until_template_yaml
+task: bigbench_simple_arithmetic_json_multiple_choice_greedy_until

lm_eval/tasks/bigbench/greedy_until/simple_arithmetic_json_subtasks.yaml

+# Generated by utils.py
+dataset_name: simple_arithmetic_json_subtasks_zero_shot
+include: ../greedy_until_template_yaml
+task: bigbench_simple_arithmetic_json_subtasks_greedy_until

lm_eval/tasks/bigbench/greedy_until/simple_arithmetic_multiple_targets_json.yaml

+# Generated by utils.py
+dataset_name: simple_arithmetic_multiple_targets_json_zero_shot
+include: ../greedy_until_template_yaml
+task: bigbench_simple_arithmetic_multiple_targets_json_greedy_until

lm_eval/tasks/bigbench/greedy_until/simple_ethical_questions.yaml

+# Generated by utils.py
+dataset_name: simple_ethical_questions_zero_shot
+include: ../greedy_until_template_yaml
+task: bigbench_simple_ethical_questions_greedy_until

lm_eval/tasks/bigbench/greedy_until/simple_text_editing.yaml

+# Generated by utils.py
+dataset_name: simple_text_editing_zero_shot
+include: ../greedy_until_template_yaml
+task: bigbench_simple_text_editing_greedy_until

lm_eval/tasks/bigbench/greedy_until/snarks.yaml

+# Generated by utils.py
+dataset_name: snarks_zero_shot
+include: ../greedy_until_template_yaml
+task: bigbench_snarks_greedy_until

lm_eval/tasks/bigbench/greedy_until/social_iqa.yaml

+# Generated by utils.py
+dataset_name: social_iqa_zero_shot
+include: ../greedy_until_template_yaml
+task: bigbench_social_iqa_greedy_until

lm_eval/tasks/bigbench/greedy_until/social_support.yaml

+# Generated by utils.py
+dataset_name: social_support_zero_shot
+include: ../greedy_until_template_yaml
+task: bigbench_social_support_greedy_until

lm_eval/tasks/bigbench/greedy_until/sports_understanding.yaml

+# Generated by utils.py
+dataset_name: sports_understanding_zero_shot
+include: ../greedy_until_template_yaml
+task: bigbench_sports_understanding_greedy_until

lm_eval/tasks/bigbench/greedy_until/strange_stories.yaml

+# Generated by utils.py
+dataset_name: strange_stories_zero_shot
+include: ../greedy_until_template_yaml
+task: bigbench_strange_stories_greedy_until