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

lm_eval/tasks/bigbench/greedy_until/mnist_ascii.yaml

-# Generated by utils.py
-dataset_name: mnist_ascii_zero_shot
-include: ../greedy_until_template_yaml
-task: bigbench_mnist_ascii_greedy_until

lm_eval/tasks/bigbench/greedy_until/modified_arithmetic.yaml

-# Generated by utils.py
-dataset_name: modified_arithmetic_zero_shot
-include: ../greedy_until_template_yaml
-task: bigbench_modified_arithmetic_greedy_until

lm_eval/tasks/bigbench/greedy_until/moral_permissibility.yaml

-# Generated by utils.py
-dataset_name: moral_permissibility_zero_shot
-include: ../greedy_until_template_yaml
-task: bigbench_moral_permissibility_greedy_until

lm_eval/tasks/bigbench/greedy_until/movie_dialog_same_or_different.yaml

-# Generated by utils.py
-dataset_name: movie_dialog_same_or_different_zero_shot
-include: ../greedy_until_template_yaml
-task: bigbench_movie_dialog_same_or_different_greedy_until

lm_eval/tasks/bigbench/greedy_until/movie_recommendation.yaml

-# Generated by utils.py
-dataset_name: movie_recommendation_zero_shot
-include: ../greedy_until_template_yaml
-task: bigbench_movie_recommendation_greedy_until

lm_eval/tasks/bigbench/greedy_until/mult_data_wrangling.yaml

-# Generated by utils.py
-dataset_name: mult_data_wrangling_zero_shot
-include: ../greedy_until_template_yaml
-task: bigbench_mult_data_wrangling_greedy_until

lm_eval/tasks/bigbench/greedy_until/multiemo.yaml

-# Generated by utils.py
-dataset_name: multiemo_zero_shot
-include: ../greedy_until_template_yaml
-task: bigbench_multiemo_greedy_until

lm_eval/tasks/bigbench/greedy_until/natural_instructions.yaml

-# Generated by utils.py
-dataset_name: natural_instructions_zero_shot
-include: ../greedy_until_template_yaml
-task: bigbench_natural_instructions_greedy_until

lm_eval/tasks/bigbench/greedy_until/navigate.yaml

-# Generated by utils.py
-dataset_name: navigate_zero_shot
-include: ../greedy_until_template_yaml
-task: bigbench_navigate_greedy_until

lm_eval/tasks/bigbench/greedy_until/nonsense_words_grammar.yaml

-# Generated by utils.py
-dataset_name: nonsense_words_grammar_zero_shot
-include: ../greedy_until_template_yaml
-task: bigbench_nonsense_words_grammar_greedy_until

lm_eval/tasks/bigbench/greedy_until/novel_concepts.yaml

-# Generated by utils.py
-dataset_name: novel_concepts_zero_shot
-include: ../greedy_until_template_yaml
-task: bigbench_novel_concepts_greedy_until

lm_eval/tasks/bigbench/greedy_until/object_counting.yaml

-# Generated by utils.py
-dataset_name: object_counting_zero_shot
-include: ../greedy_until_template_yaml
-task: bigbench_object_counting_greedy_until

lm_eval/tasks/bigbench/greedy_until/odd_one_out.yaml

-# Generated by utils.py
-dataset_name: odd_one_out_zero_shot
-include: ../greedy_until_template_yaml
-task: bigbench_odd_one_out_greedy_until

lm_eval/tasks/bigbench/greedy_until/operators.yaml

-# Generated by utils.py
-dataset_name: operators_zero_shot
-include: ../greedy_until_template_yaml
-task: bigbench_operators_greedy_until

lm_eval/tasks/bigbench/greedy_until/paragraph_segmentation.yaml

-# Generated by utils.py
-dataset_name: paragraph_segmentation_zero_shot
-include: ../greedy_until_template_yaml
-task: bigbench_paragraph_segmentation_greedy_until

lm_eval/tasks/bigbench/greedy_until/parsinlu_qa.yaml

-# Generated by utils.py
-dataset_name: parsinlu_qa_zero_shot
-include: ../greedy_until_template_yaml
-task: bigbench_parsinlu_qa_greedy_until

lm_eval/tasks/bigbench/greedy_until/parsinlu_reading_comprehension.yaml

-# Generated by utils.py
-dataset_name: parsinlu_reading_comprehension_zero_shot
-include: ../greedy_until_template_yaml
-task: bigbench_parsinlu_reading_comprehension_greedy_until

lm_eval/tasks/bigbench/greedy_until/penguins_in_a_table.yaml

-# Generated by utils.py
-dataset_name: penguins_in_a_table_zero_shot
-include: ../greedy_until_template_yaml
-task: bigbench_penguins_in_a_table_greedy_until

lm_eval/tasks/bigbench/greedy_until/periodic_elements.yaml

-# Generated by utils.py
-dataset_name: periodic_elements_zero_shot
-include: ../greedy_until_template_yaml
-task: bigbench_periodic_elements_greedy_until

lm_eval/tasks/bigbench/greedy_until/persian_idioms.yaml

-# Generated by utils.py
-dataset_name: persian_idioms_zero_shot
-include: ../greedy_until_template_yaml
-task: bigbench_persian_idioms_greedy_until