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

lm_eval/tasks/bigbench/generate_until/logic_grid_puzzle.yaml

+# Generated by utils.py
+dataset_name: logic_grid_puzzle_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_logic_grid_puzzle_generate_until

lm_eval/tasks/bigbench/generate_until/logical_args.yaml

+# Generated by utils.py
+dataset_name: logical_args_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_logical_args_generate_until

lm_eval/tasks/bigbench/generate_until/logical_deduction.yaml

+# Generated by utils.py
+dataset_name: logical_deduction_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_logical_deduction_generate_until

lm_eval/tasks/bigbench/generate_until/logical_fallacy_detection.yaml

+# Generated by utils.py
+dataset_name: logical_fallacy_detection_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_logical_fallacy_detection_generate_until

lm_eval/tasks/bigbench/generate_until/logical_sequence.yaml

+# Generated by utils.py
+dataset_name: logical_sequence_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_logical_sequence_generate_until

lm_eval/tasks/bigbench/generate_until/mathematical_induction.yaml

+# Generated by utils.py
+dataset_name: mathematical_induction_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_mathematical_induction_generate_until

lm_eval/tasks/bigbench/generate_until/matrixshapes.yaml

+# Generated by utils.py
+dataset_name: matrixshapes_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_matrixshapes_generate_until

lm_eval/tasks/bigbench/generate_until/metaphor_boolean.yaml

+# Generated by utils.py
+dataset_name: metaphor_boolean_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_metaphor_boolean_generate_until

lm_eval/tasks/bigbench/generate_until/metaphor_understanding.yaml

+# Generated by utils.py
+dataset_name: metaphor_understanding_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_metaphor_understanding_generate_until

lm_eval/tasks/bigbench/generate_until/minute_mysteries_qa.yaml

+# Generated by utils.py
+dataset_name: minute_mysteries_qa_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_minute_mysteries_qa_generate_until

lm_eval/tasks/bigbench/generate_until/misconceptions.yaml

+# Generated by utils.py
+dataset_name: misconceptions_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_misconceptions_generate_until

lm_eval/tasks/bigbench/generate_until/misconceptions_russian.yaml

+# Generated by utils.py
+dataset_name: misconceptions_russian_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_misconceptions_russian_generate_until

lm_eval/tasks/bigbench/generate_until/mnist_ascii.yaml

+# Generated by utils.py
+dataset_name: mnist_ascii_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_mnist_ascii_generate_until

lm_eval/tasks/bigbench/generate_until/modified_arithmetic.yaml

+# Generated by utils.py
+dataset_name: modified_arithmetic_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_modified_arithmetic_generate_until

lm_eval/tasks/bigbench/generate_until/moral_permissibility.yaml

+# Generated by utils.py
+dataset_name: moral_permissibility_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_moral_permissibility_generate_until

lm_eval/tasks/bigbench/generate_until/movie_dialog_same_or_different.yaml

+# Generated by utils.py
+dataset_name: movie_dialog_same_or_different_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_movie_dialog_same_or_different_generate_until

lm_eval/tasks/bigbench/generate_until/movie_recommendation.yaml

+# Generated by utils.py
+dataset_name: movie_recommendation_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_movie_recommendation_generate_until

lm_eval/tasks/bigbench/generate_until/mult_data_wrangling.yaml

+# Generated by utils.py
+dataset_name: mult_data_wrangling_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_mult_data_wrangling_generate_until

lm_eval/tasks/bigbench/generate_until/multiemo.yaml

+# Generated by utils.py
+dataset_name: multiemo_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_multiemo_generate_until

lm_eval/tasks/bigbench/generate_until/natural_instructions.yaml

+# Generated by utils.py
+dataset_name: natural_instructions_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_natural_instructions_generate_until