Merge branch 'big-refactor' into verbosity-rework

lm_eval/tasks/mmlu/flan_n_shot/mmlu_log_human_aging.yaml → lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_human_aging.yaml

 "dataset_name": "human_aging"
-"description": "The following are multiple choice questions (with answers) about human aging.\n\n"
+"description": "The following are multiple choice questions (with answers) about human\
+  \ aging.\n\n"
+"group": "mmlu_flan_n_shot_generative_other"
 "include": "_mmlu_flan_loglikelihood_template_yaml"
-"task": "mmlu_flan_n_shot_loglikelihood_human_aging"
+"task": "mmlu_flan_n_shot_generative_human_aging"

lm_eval/tasks/mmlu/flan_n_shot/mmlu_log_human_sexuality.yaml → lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_human_sexuality.yaml

 "dataset_name": "human_sexuality"
-"description": "The following are multiple choice questions (with answers) about human sexuality.\n\n"
+"description": "The following are multiple choice questions (with answers) about human\
+  \ sexuality.\n\n"
+"group": "mmlu_flan_n_shot_generative_social_sciences"
 "include": "_mmlu_flan_loglikelihood_template_yaml"
-"task": "mmlu_flan_n_shot_loglikelihood_human_sexuality"
+"task": "mmlu_flan_n_shot_generative_human_sexuality"

lm_eval/tasks/mmlu/flan_n_shot/mmlu_log_international_law.yaml → lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_international_law.yaml

 "dataset_name": "international_law"
-"description": "The following are multiple choice questions (with answers) about international law.\n\n"
+"description": "The following are multiple choice questions (with answers) about international\
+  \ law.\n\n"
+"group": "mmlu_flan_n_shot_generative_humanities"
 "include": "_mmlu_flan_loglikelihood_template_yaml"
-"task": "mmlu_flan_n_shot_loglikelihood_international_law"
+"task": "mmlu_flan_n_shot_generative_international_law"

lm_eval/tasks/mmlu/flan_n_shot/mmlu_log_jurisprudence.yaml → lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_jurisprudence.yaml

 "dataset_name": "jurisprudence"
-"description": "The following are multiple choice questions (with answers) about jurisprudence.\n\n"
+"description": "The following are multiple choice questions (with answers) about jurisprudence.\n\
+  \n"
+"group": "mmlu_flan_n_shot_generative_humanities"
 "include": "_mmlu_flan_loglikelihood_template_yaml"
-"task": "mmlu_flan_n_shot_loglikelihood_jurisprudence"
+"task": "mmlu_flan_n_shot_generative_jurisprudence"

lm_eval/tasks/mmlu/flan_n_shot/mmlu_log_logical_fallacies.yaml → lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_logical_fallacies.yaml

 "dataset_name": "logical_fallacies"
-"description": "The following are multiple choice questions (with answers) about logical fallacies.\n\n"
+"description": "The following are multiple choice questions (with answers) about logical\
+  \ fallacies.\n\n"
+"group": "mmlu_flan_n_shot_generative_humanities"
 "include": "_mmlu_flan_loglikelihood_template_yaml"
-"task": "mmlu_flan_n_shot_loglikelihood_logical_fallacies"
+"task": "mmlu_flan_n_shot_generative_logical_fallacies"

lm_eval/tasks/mmlu/flan_n_shot/mmlu_log_machine_learning.yaml → lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_machine_learning.yaml

 "dataset_name": "machine_learning"
-"description": "The following are multiple choice questions (with answers) about machine learning.\n\n"
+"description": "The following are multiple choice questions (with answers) about machine\
+  \ learning.\n\n"
+"group": "mmlu_flan_n_shot_generative_stem"
 "include": "_mmlu_flan_loglikelihood_template_yaml"
-"task": "mmlu_flan_n_shot_loglikelihood_machine_learning"
+"task": "mmlu_flan_n_shot_generative_machine_learning"

lm_eval/tasks/mmlu/flan_n_shot/mmlu_log_management.yaml → lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_management.yaml

 "dataset_name": "management"
-"description": "The following are multiple choice questions (with answers) about management.\n\n"
+"description": "The following are multiple choice questions (with answers) about management.\n\
+  \n"
+"group": "mmlu_flan_n_shot_generative_other"
 "include": "_mmlu_flan_loglikelihood_template_yaml"
-"task": "mmlu_flan_n_shot_loglikelihood_management"
+"task": "mmlu_flan_n_shot_generative_management"

lm_eval/tasks/mmlu/flan_n_shot/mmlu_log_marketing.yaml → lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_marketing.yaml

 "dataset_name": "marketing"
-"description": "The following are multiple choice questions (with answers) about marketing.\n\n"
+"description": "The following are multiple choice questions (with answers) about marketing.\n\
+  \n"
+"group": "mmlu_flan_n_shot_generative_other"
 "include": "_mmlu_flan_loglikelihood_template_yaml"
-"task": "mmlu_flan_n_shot_loglikelihood_marketing"
+"task": "mmlu_flan_n_shot_generative_marketing"

lm_eval/tasks/mmlu/flan_n_shot/mmlu_log_medical_genetics.yaml → lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_medical_genetics.yaml

 "dataset_name": "medical_genetics"
-"description": "The following are multiple choice questions (with answers) about medical genetics.\n\n"
+"description": "The following are multiple choice questions (with answers) about medical\
+  \ genetics.\n\n"
+"group": "mmlu_flan_n_shot_generative_other"
 "include": "_mmlu_flan_loglikelihood_template_yaml"
-"task": "mmlu_flan_n_shot_loglikelihood_medical_genetics"
+"task": "mmlu_flan_n_shot_generative_medical_genetics"

lm_eval/tasks/mmlu/flan_n_shot/mmlu_log_miscellaneous.yaml → lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_miscellaneous.yaml

 "dataset_name": "miscellaneous"
-"description": "The following are multiple choice questions (with answers) about miscellaneous.\n\n"
+"description": "The following are multiple choice questions (with answers) about miscellaneous.\n\
+  \n"
+"group": "mmlu_flan_n_shot_generative_other"
 "include": "_mmlu_flan_loglikelihood_template_yaml"
-"task": "mmlu_flan_n_shot_loglikelihood_miscellaneous"
+"task": "mmlu_flan_n_shot_generative_miscellaneous"

lm_eval/tasks/mmlu/flan_n_shot/mmlu_log_moral_disputes.yaml → lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_moral_disputes.yaml

 "dataset_name": "moral_disputes"
-"description": "The following are multiple choice questions (with answers) about moral disputes.\n\n"
+"description": "The following are multiple choice questions (with answers) about moral\
+  \ disputes.\n\n"
+"group": "mmlu_flan_n_shot_generative_humanities"
 "include": "_mmlu_flan_loglikelihood_template_yaml"
-"task": "mmlu_flan_n_shot_loglikelihood_moral_disputes"
+"task": "mmlu_flan_n_shot_generative_moral_disputes"

lm_eval/tasks/mmlu/flan_n_shot/mmlu_log_moral_scenarios.yaml → lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_moral_scenarios.yaml

 "dataset_name": "moral_scenarios"
-"description": "The following are multiple choice questions (with answers) about moral scenarios.\n\n"
+"description": "The following are multiple choice questions (with answers) about moral\
+  \ scenarios.\n\n"
+"group": "mmlu_flan_n_shot_generative_humanities"
 "include": "_mmlu_flan_loglikelihood_template_yaml"
-"task": "mmlu_flan_n_shot_loglikelihood_moral_scenarios"
+"task": "mmlu_flan_n_shot_generative_moral_scenarios"

lm_eval/tasks/mmlu/flan_n_shot/mmlu_log_nutrition.yaml → lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_nutrition.yaml

 "dataset_name": "nutrition"
-"description": "The following are multiple choice questions (with answers) about nutrition.\n\n"
+"description": "The following are multiple choice questions (with answers) about nutrition.\n\
+  \n"
+"group": "mmlu_flan_n_shot_generative_other"
 "include": "_mmlu_flan_loglikelihood_template_yaml"
-"task": "mmlu_flan_n_shot_loglikelihood_nutrition"
+"task": "mmlu_flan_n_shot_generative_nutrition"

lm_eval/tasks/mmlu/flan_n_shot/mmlu_log_philosophy.yaml → lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_philosophy.yaml

 "dataset_name": "philosophy"
-"description": "The following are multiple choice questions (with answers) about philosophy.\n\n"
+"description": "The following are multiple choice questions (with answers) about philosophy.\n\
+  \n"
+"group": "mmlu_flan_n_shot_generative_humanities"
 "include": "_mmlu_flan_loglikelihood_template_yaml"
-"task": "mmlu_flan_n_shot_loglikelihood_philosophy"
+"task": "mmlu_flan_n_shot_generative_philosophy"

lm_eval/tasks/mmlu/flan_n_shot/mmlu_log_prehistory.yaml → lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_prehistory.yaml

 "dataset_name": "prehistory"
-"description": "The following are multiple choice questions (with answers) about prehistory.\n\n"
+"description": "The following are multiple choice questions (with answers) about prehistory.\n\
+  \n"
+"group": "mmlu_flan_n_shot_generative_humanities"
 "include": "_mmlu_flan_loglikelihood_template_yaml"
-"task": "mmlu_flan_n_shot_loglikelihood_prehistory"
+"task": "mmlu_flan_n_shot_generative_prehistory"

lm_eval/tasks/mmlu/flan_n_shot/mmlu_log_professional_accounting.yaml → lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_professional_accounting.yaml

 "dataset_name": "professional_accounting"
-"description": "The following are multiple choice questions (with answers) about professional accounting.\n\n"
+"description": "The following are multiple choice questions (with answers) about professional\
+  \ accounting.\n\n"
+"group": "mmlu_flan_n_shot_generative_other"
 "include": "_mmlu_flan_loglikelihood_template_yaml"
-"task": "mmlu_flan_n_shot_loglikelihood_professional_accounting"
+"task": "mmlu_flan_n_shot_generative_professional_accounting"

lm_eval/tasks/mmlu/flan_n_shot/mmlu_log_professional_law.yaml → lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_professional_law.yaml

 "dataset_name": "professional_law"
-"description": "The following are multiple choice questions (with answers) about professional law.\n\n"
+"description": "The following are multiple choice questions (with answers) about professional\
+  \ law.\n\n"
+"group": "mmlu_flan_n_shot_generative_humanities"
 "include": "_mmlu_flan_loglikelihood_template_yaml"
-"task": "mmlu_flan_n_shot_loglikelihood_professional_law"
+"task": "mmlu_flan_n_shot_generative_professional_law"

lm_eval/tasks/mmlu/flan_n_shot/mmlu_log_professional_medicine.yaml → lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_professional_medicine.yaml

 "dataset_name": "professional_medicine"
-"description": "The following are multiple choice questions (with answers) about professional medicine.\n\n"
+"description": "The following are multiple choice questions (with answers) about professional\
+  \ medicine.\n\n"
+"group": "mmlu_flan_n_shot_generative_other"
 "include": "_mmlu_flan_loglikelihood_template_yaml"
-"task": "mmlu_flan_n_shot_loglikelihood_professional_medicine"
+"task": "mmlu_flan_n_shot_generative_professional_medicine"

lm_eval/tasks/mmlu/flan_n_shot/mmlu_log_professional_psychology.yaml → lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_professional_psychology.yaml

 "dataset_name": "professional_psychology"
-"description": "The following are multiple choice questions (with answers) about professional psychology.\n\n"
+"description": "The following are multiple choice questions (with answers) about professional\
+  \ psychology.\n\n"
+"group": "mmlu_flan_n_shot_generative_social_sciences"
 "include": "_mmlu_flan_loglikelihood_template_yaml"
-"task": "mmlu_flan_n_shot_loglikelihood_professional_psychology"
+"task": "mmlu_flan_n_shot_generative_professional_psychology"

lm_eval/tasks/mmlu/flan_n_shot/mmlu_log_public_relations.yaml → lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_public_relations.yaml

 "dataset_name": "public_relations"
-"description": "The following are multiple choice questions (with answers) about public relations.\n\n"
+"description": "The following are multiple choice questions (with answers) about public\
+  \ relations.\n\n"
+"group": "mmlu_flan_n_shot_generative_social_sciences"
 "include": "_mmlu_flan_loglikelihood_template_yaml"
-"task": "mmlu_flan_n_shot_loglikelihood_public_relations"
+"task": "mmlu_flan_n_shot_generative_public_relations"