Merge branch 'group-agg-rework' of...

Merge branch 'group-agg-rework' of https://github.com/EleutherAI/lm-evaluation-harness into multiprompt

lm_eval/tasks/cmmlu/cmmlu_astronomy.yaml

+"dataset_name": "astronomy"
+"description": "以下是关于天文学的单项选择题，请直接给出正确答案的选项。\n\n"
+"include": "_default_template_yaml"
+"task": "cmmlu_astronomy"

lm_eval/tasks/ammlu/ammlu_business_ethics.yaml → lm_eval/tasks/cmmlu/cmmlu_business_ethics.yaml

 "dataset_name": "business_ethics"
-"description": "فم بعملية التقييم في مجال علوم أخرى \n\n"
+"description": "以下是关于商业伦理的单项选择题，请直接给出正确答案的选项。\n\n"
 "include": "_default_template_yaml"
-"task": "ammlu_business_ethics"
+"task": "cmmlu_business_ethics"

lm_eval/tasks/cmmlu/cmmlu_chinese_civil_service_exam.yaml

+"dataset_name": "chinese_civil_service_exam"
+"description": "以下是关于中国公务员考试的单项选择题，请直接给出正确答案的选项。\n\n"
+"include": "_default_template_yaml"
+"task": "cmmlu_chinese_civil_service_exam"

lm_eval/tasks/cmmlu/cmmlu_chinese_driving_rule.yaml

+"dataset_name": "chinese_driving_rule"
+"description": "以下是关于中国驾驶规则的单项选择题，请直接给出正确答案的选项。\n\n"
+"include": "_default_template_yaml"
+"task": "cmmlu_chinese_driving_rule"

lm_eval/tasks/cmmlu/cmmlu_chinese_food_culture.yaml

+"dataset_name": "chinese_food_culture"
+"description": "以下是关于中国饮食文化的单项选择题，请直接给出正确答案的选项。\n\n"
+"include": "_default_template_yaml"
+"task": "cmmlu_chinese_food_culture"

lm_eval/tasks/cmmlu/cmmlu_chinese_foreign_policy.yaml

+"dataset_name": "chinese_foreign_policy"
+"description": "以下是关于中国外交政策的单项选择题，请直接给出正确答案的选项。\n\n"
+"include": "_default_template_yaml"
+"task": "cmmlu_chinese_foreign_policy"

lm_eval/tasks/cmmlu/cmmlu_chinese_history.yaml

+"dataset_name": "chinese_history"
+"description": "以下是关于中国历史的单项选择题，请直接给出正确答案的选项。\n\n"
+"include": "_default_template_yaml"
+"task": "cmmlu_chinese_history"

lm_eval/tasks/cmmlu/cmmlu_chinese_literature.yaml

+"dataset_name": "chinese_literature"
+"description": "以下是关于中国文学的单项选择题，请直接给出正确答案的选项。\n\n"
+"include": "_default_template_yaml"
+"task": "cmmlu_chinese_literature"

lm_eval/tasks/cmmlu/cmmlu_chinese_teacher_qualification.yaml

+"dataset_name": "chinese_teacher_qualification"
+"description": "以下是关于中国教师资格的单项选择题，请直接给出正确答案的选项。\n\n"
+"include": "_default_template_yaml"
+"task": "cmmlu_chinese_teacher_qualification"

lm_eval/tasks/ammlu/ammlu_clinical_knowledge.yaml → lm_eval/tasks/cmmlu/cmmlu_clinical_knowledge.yaml

 "dataset_name": "clinical_knowledge"
-"description": "فم بعملية التقييم في مجال علوم أخرى \n\n"
+"description": "以下是关于临床知识的单项选择题，请直接给出正确答案的选项。\n\n"
 "include": "_default_template_yaml"
-"task": "ammlu_clinical_knowledge"
+"task": "cmmlu_clinical_knowledge"

lm_eval/tasks/cmmlu/cmmlu_college_actuarial_science.yaml

+"dataset_name": "college_actuarial_science"
+"description": "以下是关于大学精算学的单项选择题，请直接给出正确答案的选项。\n\n"
+"include": "_default_template_yaml"
+"task": "cmmlu_college_actuarial_science"

lm_eval/tasks/cmmlu/cmmlu_college_education.yaml

+"dataset_name": "college_education"
+"description": "以下是关于大学教育学的单项选择题，请直接给出正确答案的选项。\n\n"
+"include": "_default_template_yaml"
+"task": "cmmlu_college_education"

lm_eval/tasks/cmmlu/cmmlu_college_engineering_hydrology.yaml

+"dataset_name": "college_engineering_hydrology"
+"description": "以下是关于大学工程水文学的单项选择题，请直接给出正确答案的选项。\n\n"
+"include": "_default_template_yaml"
+"task": "cmmlu_college_engineering_hydrology"

lm_eval/tasks/cmmlu/cmmlu_college_law.yaml

+"dataset_name": "college_law"
+"description": "以下是关于大学法律的单项选择题，请直接给出正确答案的选项。\n\n"
+"include": "_default_template_yaml"
+"task": "cmmlu_college_law"

lm_eval/tasks/ammlu/ammlu_college_mathematics.yaml → lm_eval/tasks/cmmlu/cmmlu_college_mathematics.yaml

 "dataset_name": "college_mathematics"
-"description": "فم بعملية التقييم في مجال ألعلوم وتقنية المعلومات و الرياضيات \n\n"
+"description": "以下是关于大学数学的单项选择题，请直接给出正确答案的选项。\n\n"
 "include": "_default_template_yaml"
-"task": "ammlu_college_mathematics"
+"task": "cmmlu_college_mathematics"

lm_eval/tasks/cmmlu/cmmlu_college_medical_statistics.yaml

+"dataset_name": "college_medical_statistics"
+"description": "以下是关于大学医学统计的单项选择题，请直接给出正确答案的选项。\n\n"
+"include": "_default_template_yaml"
+"task": "cmmlu_college_medical_statistics"

lm_eval/tasks/ammlu/ammlu_college_medicine.yaml → lm_eval/tasks/cmmlu/cmmlu_college_medicine.yaml

 "dataset_name": "college_medicine"
-"description": "فم بعملية التقييم في مجال علوم أخرى \n\n"
+"description": "以下是关于大学医学的单项选择题，请直接给出正确答案的选项。\n\n"
 "include": "_default_template_yaml"
-"task": "ammlu_college_medicine"
+"task": "cmmlu_college_medicine"

lm_eval/tasks/cmmlu/cmmlu_computer_science.yaml

+"dataset_name": "computer_science"
+"description": "以下是关于计算机科学的单项选择题，请直接给出正确答案的选项。\n\n"
+"include": "_default_template_yaml"
+"task": "cmmlu_computer_science"

lm_eval/tasks/cmmlu/cmmlu_computer_security.yaml

+"dataset_name": "computer_security"
+"description": "以下是关于计算机安全的单项选择题，请直接给出正确答案的选项。\n\n"
+"include": "_default_template_yaml"
+"task": "cmmlu_computer_security"

lm_eval/tasks/cmmlu/cmmlu_conceptual_physics.yaml

+"dataset_name": "conceptual_physics"
+"description": "以下是关于概念物理学的单项选择题，请直接给出正确答案的选项。\n\n"
+"include": "_default_template_yaml"
+"task": "cmmlu_conceptual_physics"