Merge branch 'big-refactor' of...

Merge branch 'big-refactor' of https://github.com/EleutherAI/lm-evaluation-harness into mmlu_subgroups

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

 # Generated by utils.py
 dataset_name: empirical_judgments_zero_shot
-include: ../greedy_until_template_yaml
-task: bigbench_empirical_judgments_greedy_until
+include: ../generate_until_template_yaml
+task: bigbench_empirical_judgments_generate_until

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

 # Generated by utils.py
 dataset_name: english_proverbs_zero_shot
-include: ../greedy_until_template_yaml
-task: bigbench_english_proverbs_greedy_until
+include: ../generate_until_template_yaml
+task: bigbench_english_proverbs_generate_until

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

 # Generated by utils.py
 dataset_name: english_russian_proverbs_zero_shot
-include: ../greedy_until_template_yaml
-task: bigbench_english_russian_proverbs_greedy_until
+include: ../generate_until_template_yaml
+task: bigbench_english_russian_proverbs_generate_until

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

 # Generated by utils.py
 dataset_name: entailed_polarity_zero_shot
-include: ../greedy_until_template_yaml
-task: bigbench_entailed_polarity_greedy_until
+include: ../generate_until_template_yaml
+task: bigbench_entailed_polarity_generate_until

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

 # Generated by utils.py
 dataset_name: entailed_polarity_hindi_zero_shot
-include: ../greedy_until_template_yaml
-task: bigbench_entailed_polarity_hindi_greedy_until
+include: ../generate_until_template_yaml
+task: bigbench_entailed_polarity_hindi_generate_until

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

 # Generated by utils.py
 dataset_name: epistemic_reasoning_zero_shot
-include: ../greedy_until_template_yaml
-task: bigbench_epistemic_reasoning_greedy_until
+include: ../generate_until_template_yaml
+task: bigbench_epistemic_reasoning_generate_until

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

 # Generated by utils.py
 dataset_name: evaluating_information_essentiality_zero_shot
-include: ../greedy_until_template_yaml
-task: bigbench_evaluating_information_essentiality_greedy_until
+include: ../generate_until_template_yaml
+task: bigbench_evaluating_information_essentiality_generate_until

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

 # Generated by utils.py
 dataset_name: fact_checker_zero_shot
-include: ../greedy_until_template_yaml
-task: bigbench_fact_checker_greedy_until
+include: ../generate_until_template_yaml
+task: bigbench_fact_checker_generate_until

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

 # Generated by utils.py
 dataset_name: fantasy_reasoning_zero_shot
-include: ../greedy_until_template_yaml
-task: bigbench_fantasy_reasoning_greedy_until
+include: ../generate_until_template_yaml
+task: bigbench_fantasy_reasoning_generate_until

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

 # Generated by utils.py
 dataset_name: few_shot_nlg_zero_shot
-include: ../greedy_until_template_yaml
-task: bigbench_few_shot_nlg_greedy_until
+include: ../generate_until_template_yaml
+task: bigbench_few_shot_nlg_generate_until

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

 # Generated by utils.py
 dataset_name: figure_of_speech_detection_zero_shot
-include: ../greedy_until_template_yaml
-task: bigbench_figure_of_speech_detection_greedy_until
+include: ../generate_until_template_yaml
+task: bigbench_figure_of_speech_detection_generate_until

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

 # Generated by utils.py
 dataset_name: formal_fallacies_syllogisms_negation_zero_shot
-include: ../greedy_until_template_yaml
-task: bigbench_formal_fallacies_syllogisms_negation_greedy_until
+include: ../generate_until_template_yaml
+task: bigbench_formal_fallacies_syllogisms_negation_generate_until

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

 # Generated by utils.py
 dataset_name: gem_zero_shot
-include: ../greedy_until_template_yaml
-task: bigbench_gem_greedy_until
+include: ../generate_until_template_yaml
+task: bigbench_gem_generate_until

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

 # Generated by utils.py
 dataset_name: gender_inclusive_sentences_german_zero_shot
-include: ../greedy_until_template_yaml
-task: bigbench_gender_inclusive_sentences_german_greedy_until
+include: ../generate_until_template_yaml
+task: bigbench_gender_inclusive_sentences_german_generate_until

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

 # Generated by utils.py
 dataset_name: general_knowledge_zero_shot
-include: ../greedy_until_template_yaml
-task: bigbench_general_knowledge_greedy_until
+include: ../generate_until_template_yaml
+task: bigbench_general_knowledge_generate_until

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

 # Generated by utils.py
 dataset_name: geometric_shapes_zero_shot
-include: ../greedy_until_template_yaml
-task: bigbench_geometric_shapes_greedy_until
+include: ../generate_until_template_yaml
+task: bigbench_geometric_shapes_generate_until

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

 # Generated by utils.py
 dataset_name: goal_step_wikihow_zero_shot
-include: ../greedy_until_template_yaml
-task: bigbench_goal_step_wikihow_greedy_until
+include: ../generate_until_template_yaml
+task: bigbench_goal_step_wikihow_generate_until

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

 # Generated by utils.py
 dataset_name: gre_reading_comprehension_zero_shot
-include: ../greedy_until_template_yaml
-task: bigbench_gre_reading_comprehension_greedy_until
+include: ../generate_until_template_yaml
+task: bigbench_gre_reading_comprehension_generate_until

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

 # Generated by utils.py
 dataset_name: hhh_alignment_zero_shot
-include: ../greedy_until_template_yaml
-task: bigbench_hhh_alignment_greedy_until
+include: ../generate_until_template_yaml
+task: bigbench_hhh_alignment_generate_until

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

 # Generated by utils.py
 dataset_name: hindi_question_answering_zero_shot
-include: ../greedy_until_template_yaml
-task: bigbench_hindi_question_answering_greedy_until
+include: ../generate_until_template_yaml
+task: bigbench_hindi_question_answering_generate_until