Merge branch 'cont-metrics' of https://github.com/EleutherAI/lm-evaluation-harness into alt_worlds

lm_eval/tasks/bigbench/greedy_until/phrase_relatedness.yaml

-# Generated by utils.py
-dataset_name: phrase_relatedness_zero_shot
-include: ../greedy_until_template_yaml
-task: bigbench_phrase_relatedness_greedy_until

lm_eval/tasks/bigbench/greedy_until/physical_intuition.yaml

-# Generated by utils.py
-dataset_name: physical_intuition_zero_shot
-include: ../greedy_until_template_yaml
-task: bigbench_physical_intuition_greedy_until

lm_eval/tasks/bigbench/greedy_until/physics.yaml

-# Generated by utils.py
-dataset_name: physics_zero_shot
-include: ../greedy_until_template_yaml
-task: bigbench_physics_greedy_until

lm_eval/tasks/bigbench/greedy_until/physics_questions.yaml

-# Generated by utils.py
-dataset_name: physics_questions_zero_shot
-include: ../greedy_until_template_yaml
-task: bigbench_physics_questions_greedy_until

lm_eval/tasks/bigbench/greedy_until/play_dialog_same_or_different.yaml

-# Generated by utils.py
-dataset_name: play_dialog_same_or_different_zero_shot
-include: ../greedy_until_template_yaml
-task: bigbench_play_dialog_same_or_different_greedy_until

lm_eval/tasks/bigbench/greedy_until/polish_sequence_labeling.yaml

-# Generated by utils.py
-dataset_name: polish_sequence_labeling_zero_shot
-include: ../greedy_until_template_yaml
-task: bigbench_polish_sequence_labeling_greedy_until

lm_eval/tasks/bigbench/greedy_until/presuppositions_as_nli.yaml

-# Generated by utils.py
-dataset_name: presuppositions_as_nli_zero_shot
-include: ../greedy_until_template_yaml
-task: bigbench_presuppositions_as_nli_greedy_until

lm_eval/tasks/bigbench/greedy_until/qa_wikidata.yaml

-# Generated by utils.py
-dataset_name: qa_wikidata_zero_shot
-include: ../greedy_until_template_yaml
-task: bigbench_qa_wikidata_greedy_until

lm_eval/tasks/bigbench/greedy_until/question_selection.yaml

-# Generated by utils.py
-dataset_name: question_selection_zero_shot
-include: ../greedy_until_template_yaml
-task: bigbench_question_selection_greedy_until

lm_eval/tasks/bigbench/greedy_until/real_or_fake_text.yaml

-# Generated by utils.py
-dataset_name: real_or_fake_text_zero_shot
-include: ../greedy_until_template_yaml
-task: bigbench_real_or_fake_text_greedy_until

lm_eval/tasks/bigbench/greedy_until/reasoning_about_colored_objects.yaml

-# Generated by utils.py
-dataset_name: reasoning_about_colored_objects_zero_shot
-include: ../greedy_until_template_yaml
-task: bigbench_reasoning_about_colored_objects_greedy_until

lm_eval/tasks/bigbench/greedy_until/repeat_copy_logic.yaml

-# Generated by utils.py
-dataset_name: repeat_copy_logic_zero_shot
-include: ../greedy_until_template_yaml
-task: bigbench_repeat_copy_logic_greedy_until

lm_eval/tasks/bigbench/greedy_until/rephrase.yaml

-# Generated by utils.py
-dataset_name: rephrase_zero_shot
-include: ../greedy_until_template_yaml
-task: bigbench_rephrase_greedy_until

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