Merge pull request #981 from EleutherAI/mmlu-fixes

[Refactor] fixes for alternative MMLU tasks.

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"
-"group": "mmlu_flan_n_shot_generative_humanities"
+"group": "mmlu_flan_n_shot_loglikelihood_humanities"
 "include": "_mmlu_flan_loglikelihood_template_yaml"
-"task": "mmlu_flan_n_shot_generative_jurisprudence"
+"task": "mmlu_flan_n_shot_loglikelihood_jurisprudence"

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"
-"group": "mmlu_flan_n_shot_generative_humanities"
+"group": "mmlu_flan_n_shot_loglikelihood_humanities"
 "include": "_mmlu_flan_loglikelihood_template_yaml"
-"task": "mmlu_flan_n_shot_generative_logical_fallacies"
+"task": "mmlu_flan_n_shot_loglikelihood_logical_fallacies"

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"
-"group": "mmlu_flan_n_shot_generative_stem"
+"group": "mmlu_flan_n_shot_loglikelihood_stem"
 "include": "_mmlu_flan_loglikelihood_template_yaml"
-"task": "mmlu_flan_n_shot_generative_machine_learning"
+"task": "mmlu_flan_n_shot_loglikelihood_machine_learning"

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"
-"group": "mmlu_flan_n_shot_generative_other"
+"group": "mmlu_flan_n_shot_loglikelihood_other"
 "include": "_mmlu_flan_loglikelihood_template_yaml"
-"task": "mmlu_flan_n_shot_generative_management"
+"task": "mmlu_flan_n_shot_loglikelihood_management"

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"
-"group": "mmlu_flan_n_shot_generative_other"
+"group": "mmlu_flan_n_shot_loglikelihood_other"
 "include": "_mmlu_flan_loglikelihood_template_yaml"
-"task": "mmlu_flan_n_shot_generative_marketing"
+"task": "mmlu_flan_n_shot_loglikelihood_marketing"

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"
-"group": "mmlu_flan_n_shot_generative_other"
+"group": "mmlu_flan_n_shot_loglikelihood_other"
 "include": "_mmlu_flan_loglikelihood_template_yaml"
-"task": "mmlu_flan_n_shot_generative_medical_genetics"
+"task": "mmlu_flan_n_shot_loglikelihood_medical_genetics"

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"
-"group": "mmlu_flan_n_shot_generative_other"
+"group": "mmlu_flan_n_shot_loglikelihood_other"
 "include": "_mmlu_flan_loglikelihood_template_yaml"
-"task": "mmlu_flan_n_shot_generative_miscellaneous"
+"task": "mmlu_flan_n_shot_loglikelihood_miscellaneous"

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"
-"group": "mmlu_flan_n_shot_generative_humanities"
+"group": "mmlu_flan_n_shot_loglikelihood_humanities"
 "include": "_mmlu_flan_loglikelihood_template_yaml"
-"task": "mmlu_flan_n_shot_generative_moral_disputes"
+"task": "mmlu_flan_n_shot_loglikelihood_moral_disputes"

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"
-"group": "mmlu_flan_n_shot_generative_humanities"
+"group": "mmlu_flan_n_shot_loglikelihood_humanities"
 "include": "_mmlu_flan_loglikelihood_template_yaml"
-"task": "mmlu_flan_n_shot_generative_moral_scenarios"
+"task": "mmlu_flan_n_shot_loglikelihood_moral_scenarios"

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"
-"group": "mmlu_flan_n_shot_generative_other"
+"group": "mmlu_flan_n_shot_loglikelihood_other"
 "include": "_mmlu_flan_loglikelihood_template_yaml"
-"task": "mmlu_flan_n_shot_generative_nutrition"
+"task": "mmlu_flan_n_shot_loglikelihood_nutrition"

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"
-"group": "mmlu_flan_n_shot_generative_humanities"
+"group": "mmlu_flan_n_shot_loglikelihood_humanities"
 "include": "_mmlu_flan_loglikelihood_template_yaml"
-"task": "mmlu_flan_n_shot_generative_philosophy"
+"task": "mmlu_flan_n_shot_loglikelihood_philosophy"

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"
-"group": "mmlu_flan_n_shot_generative_humanities"
+"group": "mmlu_flan_n_shot_loglikelihood_humanities"
 "include": "_mmlu_flan_loglikelihood_template_yaml"
-"task": "mmlu_flan_n_shot_generative_prehistory"
+"task": "mmlu_flan_n_shot_loglikelihood_prehistory"

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"
-"group": "mmlu_flan_n_shot_generative_other"
+"group": "mmlu_flan_n_shot_loglikelihood_other"
 "include": "_mmlu_flan_loglikelihood_template_yaml"
-"task": "mmlu_flan_n_shot_generative_professional_accounting"
+"task": "mmlu_flan_n_shot_loglikelihood_professional_accounting"

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"
-"group": "mmlu_flan_n_shot_generative_humanities"
+"group": "mmlu_flan_n_shot_loglikelihood_humanities"
 "include": "_mmlu_flan_loglikelihood_template_yaml"
-"task": "mmlu_flan_n_shot_generative_professional_law"
+"task": "mmlu_flan_n_shot_loglikelihood_professional_law"

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"
-"group": "mmlu_flan_n_shot_generative_other"
+"group": "mmlu_flan_n_shot_loglikelihood_other"
 "include": "_mmlu_flan_loglikelihood_template_yaml"
-"task": "mmlu_flan_n_shot_generative_professional_medicine"
+"task": "mmlu_flan_n_shot_loglikelihood_professional_medicine"

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"
-"group": "mmlu_flan_n_shot_generative_social_sciences"
+"group": "mmlu_flan_n_shot_loglikelihood_social_sciences"
 "include": "_mmlu_flan_loglikelihood_template_yaml"
-"task": "mmlu_flan_n_shot_generative_professional_psychology"
+"task": "mmlu_flan_n_shot_loglikelihood_professional_psychology"

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"
-"group": "mmlu_flan_n_shot_generative_social_sciences"
+"group": "mmlu_flan_n_shot_loglikelihood_social_sciences"
 "include": "_mmlu_flan_loglikelihood_template_yaml"
-"task": "mmlu_flan_n_shot_generative_public_relations"
+"task": "mmlu_flan_n_shot_loglikelihood_public_relations"

lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_security_studies.yaml

 "dataset_name": "security_studies"
 "description": "The following are multiple choice questions (with answers) about security\
   \ studies.\n\n"
-"group": "mmlu_flan_n_shot_generative_social_sciences"
+"group": "mmlu_flan_n_shot_loglikelihood_social_sciences"
 "include": "_mmlu_flan_loglikelihood_template_yaml"
-"task": "mmlu_flan_n_shot_generative_security_studies"
+"task": "mmlu_flan_n_shot_loglikelihood_security_studies"

lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_sociology.yaml

 "dataset_name": "sociology"
 "description": "The following are multiple choice questions (with answers) about sociology.\n\
   \n"
-"group": "mmlu_flan_n_shot_generative_social_sciences"
+"group": "mmlu_flan_n_shot_loglikelihood_social_sciences"
 "include": "_mmlu_flan_loglikelihood_template_yaml"
-"task": "mmlu_flan_n_shot_generative_sociology"
+"task": "mmlu_flan_n_shot_loglikelihood_sociology"

lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_us_foreign_policy.yaml

 "dataset_name": "us_foreign_policy"
 "description": "The following are multiple choice questions (with answers) about us\
   \ foreign policy.\n\n"
-"group": "mmlu_flan_n_shot_generative_social_sciences"
+"group": "mmlu_flan_n_shot_loglikelihood_social_sciences"
 "include": "_mmlu_flan_loglikelihood_template_yaml"
-"task": "mmlu_flan_n_shot_generative_us_foreign_policy"
+"task": "mmlu_flan_n_shot_loglikelihood_us_foreign_policy"