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

lm_eval/tasks/bigbench/generate_until/abstract_narrative_understanding.yaml

+# Generated by utils.py
+dataset_name: abstract_narrative_understanding_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_abstract_narrative_understanding_generate_until

lm_eval/tasks/bigbench/generate_until/anachronisms.yaml

+# Generated by utils.py
+dataset_name: anachronisms_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_anachronisms_generate_until

lm_eval/tasks/bigbench/generate_until/analogical_similarity.yaml

+# Generated by utils.py
+dataset_name: analogical_similarity_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_analogical_similarity_generate_until

lm_eval/tasks/bigbench/generate_until/analytic_entailment.yaml

+# Generated by utils.py
+dataset_name: analytic_entailment_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_analytic_entailment_generate_until

lm_eval/tasks/bigbench/generate_until/arithmetic.yaml

+# Generated by utils.py
+dataset_name: arithmetic_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_arithmetic_generate_until

lm_eval/tasks/bigbench/generate_until/ascii_word_recognition.yaml

+# Generated by utils.py
+dataset_name: ascii_word_recognition_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_ascii_word_recognition_generate_until

lm_eval/tasks/bigbench/generate_until/authorship_verification.yaml

+# Generated by utils.py
+dataset_name: authorship_verification_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_authorship_verification_generate_until

lm_eval/tasks/bigbench/generate_until/auto_categorization.yaml

+# Generated by utils.py
+dataset_name: auto_categorization_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_auto_categorization_generate_until

lm_eval/tasks/bigbench/generate_until/auto_debugging.yaml

+# Generated by utils.py
+dataset_name: auto_debugging_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_auto_debugging_generate_until

lm_eval/tasks/bigbench/generate_until/bbq_lite_json.yaml

+# Generated by utils.py
+dataset_name: bbq_lite_json_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_bbq_lite_json_generate_until

lm_eval/tasks/bigbench/generate_until/bridging_anaphora_resolution_barqa.yaml

+# Generated by utils.py
+dataset_name: bridging_anaphora_resolution_barqa_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_bridging_anaphora_resolution_barqa_generate_until

lm_eval/tasks/bigbench/generate_until/causal_judgment.yaml

+# Generated by utils.py
+dataset_name: causal_judgment_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_causal_judgment_generate_until

lm_eval/tasks/bigbench/generate_until/cause_and_effect.yaml

+# Generated by utils.py
+dataset_name: cause_and_effect_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_cause_and_effect_generate_until

lm_eval/tasks/bigbench/generate_until/checkmate_in_one.yaml

+# Generated by utils.py
+dataset_name: checkmate_in_one_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_checkmate_in_one_generate_until

lm_eval/tasks/bigbench/generate_until/chess_state_tracking.yaml

+# Generated by utils.py
+dataset_name: chess_state_tracking_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_chess_state_tracking_generate_until

lm_eval/tasks/bigbench/generate_until/chinese_remainder_theorem.yaml

+# Generated by utils.py
+dataset_name: chinese_remainder_theorem_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_chinese_remainder_theorem_generate_until

lm_eval/tasks/bigbench/generate_until/cifar10_classification.yaml

+# Generated by utils.py
+dataset_name: cifar10_classification_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_cifar10_classification_generate_until

lm_eval/tasks/bigbench/generate_until/code_line_description.yaml

+# Generated by utils.py
+dataset_name: code_line_description_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_code_line_description_generate_until

lm_eval/tasks/bigbench/generate_until/codenames.yaml

+# Generated by utils.py
+dataset_name: codenames_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_codenames_generate_until

lm_eval/tasks/bigbench/generate_until/color.yaml

+# Generated by utils.py
+dataset_name: color_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_color_generate_until