Merge branch 'big-refactor' into model-written-eval

lm_eval/tasks/bigbench/greedy_until/mathematical_induction.yaml → lm_eval/tasks/bigbench/generate_until/mathematical_induction.yaml

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

lm_eval/tasks/bigbench/greedy_until/matrixshapes.yaml → lm_eval/tasks/bigbench/generate_until/matrixshapes.yaml

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

lm_eval/tasks/bigbench/greedy_until/metaphor_boolean.yaml → lm_eval/tasks/bigbench/generate_until/metaphor_boolean.yaml

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

lm_eval/tasks/bigbench/greedy_until/metaphor_understanding.yaml → lm_eval/tasks/bigbench/generate_until/metaphor_understanding.yaml

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

lm_eval/tasks/bigbench/greedy_until/minute_mysteries_qa.yaml → lm_eval/tasks/bigbench/generate_until/minute_mysteries_qa.yaml

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

lm_eval/tasks/bigbench/greedy_until/misconceptions.yaml → lm_eval/tasks/bigbench/generate_until/misconceptions.yaml

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

lm_eval/tasks/bigbench/greedy_until/misconceptions_russian.yaml → lm_eval/tasks/bigbench/generate_until/misconceptions_russian.yaml

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

lm_eval/tasks/bigbench/greedy_until/mnist_ascii.yaml → lm_eval/tasks/bigbench/generate_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
+include: ../generate_until_template_yaml
+task: bigbench_mnist_ascii_generate_until

lm_eval/tasks/bigbench/greedy_until/modified_arithmetic.yaml → lm_eval/tasks/bigbench/generate_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
+include: ../generate_until_template_yaml
+task: bigbench_modified_arithmetic_generate_until

lm_eval/tasks/bigbench/greedy_until/moral_permissibility.yaml → lm_eval/tasks/bigbench/generate_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
+include: ../generate_until_template_yaml
+task: bigbench_moral_permissibility_generate_until

lm_eval/tasks/bigbench/greedy_until/movie_dialog_same_or_different.yaml → 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: ../greedy_until_template_yaml
-task: bigbench_movie_dialog_same_or_different_greedy_until
+include: ../generate_until_template_yaml
+task: bigbench_movie_dialog_same_or_different_generate_until

lm_eval/tasks/bigbench/greedy_until/movie_recommendation.yaml → lm_eval/tasks/bigbench/generate_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
+include: ../generate_until_template_yaml
+task: bigbench_movie_recommendation_generate_until

lm_eval/tasks/bigbench/greedy_until/mult_data_wrangling.yaml → lm_eval/tasks/bigbench/generate_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
+include: ../generate_until_template_yaml
+task: bigbench_mult_data_wrangling_generate_until

lm_eval/tasks/bigbench/greedy_until/multiemo.yaml → lm_eval/tasks/bigbench/generate_until/multiemo.yaml

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

lm_eval/tasks/bigbench/greedy_until/natural_instructions.yaml → lm_eval/tasks/bigbench/generate_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
+include: ../generate_until_template_yaml
+task: bigbench_natural_instructions_generate_until

lm_eval/tasks/bigbench/greedy_until/navigate.yaml → lm_eval/tasks/bigbench/generate_until/navigate.yaml

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

lm_eval/tasks/bigbench/greedy_until/nonsense_words_grammar.yaml → lm_eval/tasks/bigbench/generate_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
+include: ../generate_until_template_yaml
+task: bigbench_nonsense_words_grammar_generate_until

lm_eval/tasks/bigbench/greedy_until/novel_concepts.yaml → lm_eval/tasks/bigbench/generate_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
+include: ../generate_until_template_yaml
+task: bigbench_novel_concepts_generate_until

lm_eval/tasks/bigbench/greedy_until/object_counting.yaml → lm_eval/tasks/bigbench/generate_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
+include: ../generate_until_template_yaml
+task: bigbench_object_counting_generate_until

lm_eval/tasks/bigbench/greedy_until/odd_one_out.yaml → lm_eval/tasks/bigbench/generate_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
+include: ../generate_until_template_yaml
+task: bigbench_odd_one_out_generate_until