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

lm_eval/tasks/bigbench/generate_until/common_morpheme.yaml

+# Generated by utils.py
+dataset_name: common_morpheme_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_common_morpheme_generate_until

lm_eval/tasks/bigbench/generate_until/conceptual_combinations.yaml

+# Generated by utils.py
+dataset_name: conceptual_combinations_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_conceptual_combinations_generate_until

lm_eval/tasks/bigbench/generate_until/conlang_translation.yaml

+# Generated by utils.py
+dataset_name: conlang_translation_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_conlang_translation_generate_until

lm_eval/tasks/bigbench/generate_until/contextual_parametric_knowledge_conflicts.yaml

+# Generated by utils.py
+dataset_name: contextual_parametric_knowledge_conflicts_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_contextual_parametric_knowledge_conflicts_generate_until

lm_eval/tasks/bigbench/generate_until/crash_blossom.yaml

+# Generated by utils.py
+dataset_name: crash_blossom_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_crash_blossom_generate_until

lm_eval/tasks/bigbench/generate_until/crass_ai.yaml

+# Generated by utils.py
+dataset_name: crass_ai_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_crass_ai_generate_until

lm_eval/tasks/bigbench/generate_until/cryobiology_spanish.yaml

+# Generated by utils.py
+dataset_name: cryobiology_spanish_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_cryobiology_spanish_generate_until

lm_eval/tasks/bigbench/generate_until/cryptonite.yaml

+# Generated by utils.py
+dataset_name: cryptonite_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_cryptonite_generate_until

lm_eval/tasks/bigbench/generate_until/cs_algorithms.yaml

+# Generated by utils.py
+dataset_name: cs_algorithms_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_cs_algorithms_generate_until

lm_eval/tasks/bigbench/generate_until/dark_humor_detection.yaml

+# Generated by utils.py
+dataset_name: dark_humor_detection_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_dark_humor_detection_generate_until

lm_eval/tasks/bigbench/generate_until/date_understanding.yaml

+# Generated by utils.py
+dataset_name: date_understanding_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_date_understanding_generate_until

lm_eval/tasks/bigbench/generate_until/disambiguation_qa.yaml

+# Generated by utils.py
+dataset_name: disambiguation_qa_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_disambiguation_qa_generate_until

lm_eval/tasks/bigbench/generate_until/discourse_marker_prediction.yaml

+# Generated by utils.py
+dataset_name: discourse_marker_prediction_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_discourse_marker_prediction_generate_until

lm_eval/tasks/bigbench/generate_until/disfl_qa.yaml

+# Generated by utils.py
+dataset_name: disfl_qa_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_disfl_qa_generate_until

lm_eval/tasks/bigbench/generate_until/dyck_languages.yaml

+# Generated by utils.py
+dataset_name: dyck_languages_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_dyck_languages_generate_until

lm_eval/tasks/bigbench/generate_until/elementary_math_qa.yaml

+# Generated by utils.py
+dataset_name: elementary_math_qa_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_elementary_math_qa_generate_until

lm_eval/tasks/bigbench/generate_until/emoji_movie.yaml

+# Generated by utils.py
+dataset_name: emoji_movie_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_emoji_movie_generate_until

lm_eval/tasks/bigbench/generate_until/emojis_emotion_prediction.yaml

+# Generated by utils.py
+dataset_name: emojis_emotion_prediction_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_emojis_emotion_prediction_generate_until

lm_eval/tasks/bigbench/generate_until/empirical_judgments.yaml

+# Generated by utils.py
+dataset_name: empirical_judgments_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_empirical_judgments_generate_until

lm_eval/tasks/bigbench/generate_until/english_proverbs.yaml

+# Generated by utils.py
+dataset_name: english_proverbs_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_english_proverbs_generate_until