| tag: | |
| - ai2_arc | |
| task: arc_challenge_mi | |
| dataset_path: allenai/ai2_arc | |
| dataset_name: ARC-Challenge | |
| output_type: multiple_choice | |
| training_split: train | |
| validation_split: validation | |
| test_split: test | |
| doc_to_text: "Question: {{question}}\nAnswer:" | |
| doc_to_target: "{{choices.label.index(answerKey)}}" | |
| doc_to_choice: "{{choices.text}}" | |
| should_decontaminate: true | |
| doc_to_decontamination_query: "Question: {{question}}\nAnswer:" | |
| metric_list: | |
| - metric: acc | |
| aggregation: mean | |
| higher_is_better: true | |
| - metric: acc_mutual_info | |
| aggregation: mean | |
| higher_is_better: true | |
| - metric: acc_norm | |
| aggregation: mean | |
| higher_is_better: true | |
| metadata: | |
| version: 1.0 |