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

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

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