group: babilong task: - babilong_qa1 - babilong_qa2 - babilong_qa3 - babilong_qa4 - babilong_qa5 - babilong_qa6 - babilong_qa7 - babilong_qa8 - babilong_qa9 - babilong_qa10 - babilong_qa11 - babilong_qa12 - babilong_qa13 - babilong_qa14 - babilong_qa15 - babilong_qa16 - babilong_qa17 - babilong_qa18 - babilong_qa19 - babilong_qa20 aggregate_metric_list: - metric: acc weight_by_size: True metadata: version: 0.0