| dataset_path: ceval/ceval-exam | |
| validation_split: val | |
| fewshot_split: dev | |
| fewshot_config: | |
| sampler: first_n | |
| output_type: multiple_choice | |
| doc_to_text: "{{question.strip()}}\nA. {{A}}\nB. {{B}}\nC. {{C}}\nD. {{D}}\n答案：" | |
| doc_to_choice: ["A", "B", "C", "D"] | |
| doc_to_target: "{{['A', 'B', 'C', 'D'].index(answer)}}" | |
| metric_list: | |
| - metric: acc | |
| aggregation: mean | |
| higher_is_better: true | |
| - metric: acc_norm | |
| aggregation: mean | |
| higher_is_better: true | |
| metadata: | |
| version: 2.0 | |