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/parsinlu_qa.yaml

+# Generated by utils.py
+dataset_name: parsinlu_qa_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_parsinlu_qa_generate_until

lm_eval/tasks/bigbench/generate_until/parsinlu_reading_comprehension.yaml

+# Generated by utils.py
+dataset_name: parsinlu_reading_comprehension_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_parsinlu_reading_comprehension_generate_until

lm_eval/tasks/bigbench/generate_until/penguins_in_a_table.yaml

+# Generated by utils.py
+dataset_name: penguins_in_a_table_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_penguins_in_a_table_generate_until

lm_eval/tasks/bigbench/generate_until/periodic_elements.yaml

+# Generated by utils.py
+dataset_name: periodic_elements_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_periodic_elements_generate_until

lm_eval/tasks/bigbench/generate_until/persian_idioms.yaml

+# Generated by utils.py
+dataset_name: persian_idioms_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_persian_idioms_generate_until

lm_eval/tasks/bigbench/generate_until/phrase_relatedness.yaml

+# Generated by utils.py
+dataset_name: phrase_relatedness_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_phrase_relatedness_generate_until

lm_eval/tasks/bigbench/generate_until/physical_intuition.yaml

+# Generated by utils.py
+dataset_name: physical_intuition_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_physical_intuition_generate_until

lm_eval/tasks/bigbench/generate_until/physics.yaml

+# Generated by utils.py
+dataset_name: physics_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_physics_generate_until

lm_eval/tasks/bigbench/generate_until/physics_questions.yaml

+# Generated by utils.py
+dataset_name: physics_questions_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_physics_questions_generate_until

lm_eval/tasks/bigbench/generate_until/play_dialog_same_or_different.yaml

+# Generated by utils.py
+dataset_name: play_dialog_same_or_different_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_play_dialog_same_or_different_generate_until

lm_eval/tasks/bigbench/generate_until/polish_sequence_labeling.yaml

+# Generated by utils.py
+dataset_name: polish_sequence_labeling_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_polish_sequence_labeling_generate_until

lm_eval/tasks/bigbench/generate_until/presuppositions_as_nli.yaml

+# Generated by utils.py
+dataset_name: presuppositions_as_nli_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_presuppositions_as_nli_generate_until

lm_eval/tasks/bigbench/generate_until/qa_wikidata.yaml

+# Generated by utils.py
+dataset_name: qa_wikidata_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_qa_wikidata_generate_until

lm_eval/tasks/bigbench/generate_until/question_selection.yaml

+# Generated by utils.py
+dataset_name: question_selection_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_question_selection_generate_until

lm_eval/tasks/bigbench/generate_until/real_or_fake_text.yaml

+# Generated by utils.py
+dataset_name: real_or_fake_text_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_real_or_fake_text_generate_until

lm_eval/tasks/bigbench/generate_until/reasoning_about_colored_objects.yaml

+# Generated by utils.py
+dataset_name: reasoning_about_colored_objects_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_reasoning_about_colored_objects_generate_until

lm_eval/tasks/bigbench/generate_until/repeat_copy_logic.yaml

+# Generated by utils.py
+dataset_name: repeat_copy_logic_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_repeat_copy_logic_generate_until

lm_eval/tasks/bigbench/generate_until/rephrase.yaml

+# Generated by utils.py
+dataset_name: rephrase_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_rephrase_generate_until

lm_eval/tasks/bigbench/generate_until/riddle_sense.yaml

+# Generated by utils.py
+dataset_name: riddle_sense_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_riddle_sense_generate_until

lm_eval/tasks/bigbench/generate_until/ruin_names.yaml

+# Generated by utils.py
+dataset_name: ruin_names_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_ruin_names_generate_until