Merge branch 'cont-metrics' of https://github.com/EleutherAI/lm-evaluation-harness into alt_worlds

lm_eval/tasks/mmlu/flan_n_shot/mmlu_log_high_school_world_history.yaml

-"dataset_name": "high_school_world_history"
-"description": "The following are multiple choice questions (with answers) about high school world history.\n\n"
-"include": "_mmlu_flan_loglikelihood_template_yaml"
-"task": "mmlu_flan_n_shot_loglikelihood_high_school_world_history"

lm_eval/tasks/mmlu/flan_n_shot/mmlu_log_human_aging.yaml

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

lm_eval/tasks/mmlu/flan_n_shot/mmlu_log_human_sexuality.yaml

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

lm_eval/tasks/mmlu/flan_n_shot/mmlu_log_international_law.yaml

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

lm_eval/tasks/mmlu/flan_n_shot/mmlu_log_jurisprudence.yaml

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

lm_eval/tasks/mmlu/flan_n_shot/mmlu_log_logical_fallacies.yaml

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

lm_eval/tasks/mmlu/flan_n_shot/mmlu_log_machine_learning.yaml

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

lm_eval/tasks/mmlu/flan_n_shot/mmlu_log_management.yaml

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

lm_eval/tasks/mmlu/flan_n_shot/mmlu_log_marketing.yaml

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

lm_eval/tasks/mmlu/flan_n_shot/mmlu_log_medical_genetics.yaml

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

lm_eval/tasks/mmlu/flan_n_shot/mmlu_log_miscellaneous.yaml

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

lm_eval/tasks/mmlu/flan_n_shot/mmlu_log_moral_disputes.yaml

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

lm_eval/tasks/mmlu/flan_n_shot/mmlu_log_moral_scenarios.yaml

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

lm_eval/tasks/mmlu/flan_n_shot/mmlu_log_nutrition.yaml

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

lm_eval/tasks/mmlu/flan_n_shot/mmlu_log_philosophy.yaml

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

lm_eval/tasks/mmlu/flan_n_shot/mmlu_log_prehistory.yaml

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

lm_eval/tasks/mmlu/flan_n_shot/mmlu_log_professional_accounting.yaml

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

lm_eval/tasks/mmlu/flan_n_shot/mmlu_log_professional_law.yaml

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

lm_eval/tasks/mmlu/flan_n_shot/mmlu_log_professional_medicine.yaml

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

lm_eval/tasks/mmlu/flan_n_shot/mmlu_log_professional_psychology.yaml

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