group: kmmlu dataset_path: HAERAE-HUB/K-MMLU-Preview output_type: multiple_choice training_split: train validation_split: dev test_split: test fewshot_split: dev output_type: multiple_choice doc_to_text: "{{question.strip()}}\nA. {{A}}\nB. {{B}}\nC. {{C}}\nD. {{D}}\n정답:" doc_to_choice: ["A", "B", "C", "D"] doc_to_target: "{{['A', 'B', 'C', 'D'][answer-1]}}" metric_list: - metric: acc aggregation: mean higher_is_better: true - metric: acc_norm aggregation: mean higher_is_better: true metadata: version: 1.1