| task: metabench_arc | |
| tag: | |
| - metabench_arc_subset | |
| dataset_path: HCAI/metabench | |
| dataset_name: ARC | |
| process_docs: !function process_docs.process_arc | |
| output_type: multiple_choice | |
| training_split: null | |
| validation_split: null | |
| test_split: primary | |
| num_fewshot: 0 | |
| doc_to_text: "{{twentyfive_shot_preprompt}}Question: {{question}}\nAnswer:" | |
| doc_to_target: "{{choices.label.index(answerKey)}}" | |
| doc_to_choice: "{{choices.text}}" | |
| metric_list: | |
| - metric: acc | |
| aggregation: mean | |
| higher_is_better: true | |
| - metric: acc_norm | |
| aggregation: mean | |
| higher_is_better: true | |
| metadata: | |
| version: 0.0 | |