lm_eval/tasks/mmlusr/question_only/_question_only.yaml (44 lines of code) (raw):

group: mmlusr_question_only group_alias: MMLU-SR (Question Only) task: - group: mmlusr_qo_stem group_alias: STEM (Question Only) task: - mmlusr_question_only_stem_tasks aggregate_metric_list: - metric: acc weight_by_size: True metadata: version: 1 - group: mmlusr_qo_other group_alias: Other (Question Only) task: - mmlusr_question_only_other_tasks aggregate_metric_list: - metric: acc weight_by_size: True metadata: version: 1 - group: mmlusr_qo_social_sciences group_alias: Social Sciences (Question Only) task: - mmlusr_question_only_social_sciences_tasks aggregate_metric_list: - metric: acc weight_by_size: True metadata: version: 1 - group: mmlusr_qo_humanities group_alias: Humanities (Question Only) task: - mmlusr_question_only_humanities_tasks aggregate_metric_list: - metric: acc weight_by_size: True metadata: version: 1 aggregate_metric_list: - metric: acc weight_by_size: True metadata: version: 1