group: agieval_en task: - agieval_aqua_rat - agieval_gaokao_english # categorizing as EN because the AGIEval codebase lists this as in `english_qa_tasks` - agieval_logiqa_en - agieval_lsat_ar - agieval_lsat_lr - agieval_lsat_rc - agieval_math - agieval_sat_en_without_passage - agieval_sat_en - agieval_sat_math aggregate_metric_list: - metric: acc aggregation: mean weight_by_size: true metadata: version: 0.0