Merge branch 'big-refactor' into fix-unittests

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

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

 # Generated by utils.py
 dataset_name: hindu_knowledge_zero_shot
-include: ../greedy_until_template_yaml
-task: bigbench_hindu_knowledge_greedy_until
+include: ../generate_until_template_yaml
+task: bigbench_hindu_knowledge_generate_until

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

 # Generated by utils.py
 dataset_name: hinglish_toxicity_zero_shot
-include: ../greedy_until_template_yaml
-task: bigbench_hinglish_toxicity_greedy_until
+include: ../generate_until_template_yaml
+task: bigbench_hinglish_toxicity_generate_until

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

 # Generated by utils.py
 dataset_name: human_organs_senses_zero_shot
-include: ../greedy_until_template_yaml
-task: bigbench_human_organs_senses_greedy_until
+include: ../generate_until_template_yaml
+task: bigbench_human_organs_senses_generate_until

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

 # Generated by utils.py
 dataset_name: hyperbaton_zero_shot
-include: ../greedy_until_template_yaml
-task: bigbench_hyperbaton_greedy_until
+include: ../generate_until_template_yaml
+task: bigbench_hyperbaton_generate_until

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

 # Generated by utils.py
 dataset_name: identify_math_theorems_zero_shot
-include: ../greedy_until_template_yaml
-task: bigbench_identify_math_theorems_greedy_until
+include: ../generate_until_template_yaml
+task: bigbench_identify_math_theorems_generate_until

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

 # Generated by utils.py
 dataset_name: identify_odd_metaphor_zero_shot
-include: ../greedy_until_template_yaml
-task: bigbench_identify_odd_metaphor_greedy_until
+include: ../generate_until_template_yaml
+task: bigbench_identify_odd_metaphor_generate_until

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

 # Generated by utils.py
 dataset_name: implicatures_zero_shot
-include: ../greedy_until_template_yaml
-task: bigbench_implicatures_greedy_until
+include: ../generate_until_template_yaml
+task: bigbench_implicatures_generate_until

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

 # Generated by utils.py
 dataset_name: implicit_relations_zero_shot
-include: ../greedy_until_template_yaml
-task: bigbench_implicit_relations_greedy_until
+include: ../generate_until_template_yaml
+task: bigbench_implicit_relations_generate_until

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

 # Generated by utils.py
 dataset_name: intent_recognition_zero_shot
-include: ../greedy_until_template_yaml
-task: bigbench_intent_recognition_greedy_until
+include: ../generate_until_template_yaml
+task: bigbench_intent_recognition_generate_until

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

 # Generated by utils.py
 dataset_name: international_phonetic_alphabet_nli_zero_shot
-include: ../greedy_until_template_yaml
-task: bigbench_international_phonetic_alphabet_nli_greedy_until
+include: ../generate_until_template_yaml
+task: bigbench_international_phonetic_alphabet_nli_generate_until

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

 # Generated by utils.py
 dataset_name: international_phonetic_alphabet_transliterate_zero_shot
-include: ../greedy_until_template_yaml
-task: bigbench_international_phonetic_alphabet_transliterate_greedy_until
+include: ../generate_until_template_yaml
+task: bigbench_international_phonetic_alphabet_transliterate_generate_until

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

 # Generated by utils.py
 dataset_name: intersect_geometry_zero_shot
-include: ../greedy_until_template_yaml
-task: bigbench_intersect_geometry_greedy_until
+include: ../generate_until_template_yaml
+task: bigbench_intersect_geometry_generate_until

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

 # Generated by utils.py
 dataset_name: irony_identification_zero_shot
-include: ../greedy_until_template_yaml
-task: bigbench_irony_identification_greedy_until
+include: ../generate_until_template_yaml
+task: bigbench_irony_identification_generate_until

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

 # Generated by utils.py
 dataset_name: kanji_ascii_zero_shot
-include: ../greedy_until_template_yaml
-task: bigbench_kanji_ascii_greedy_until
+include: ../generate_until_template_yaml
+task: bigbench_kanji_ascii_generate_until