| task: halueval_qa | |
| dataset_path: pminervini/HaluEval | |
| dataset_name: qa_samples | |
| output_type: generate_until | |
| training_split: null | |
| validation_split: null | |
| test_split: data | |
| num_fewshot: 0 | |
| doc_to_text: !function utils.doc_to_text_qa | |
| doc_to_target: !function utils.doc_to_target | |
| process_results: !function utils.process_results | |
| generation_kwargs: | |
| until: | |
| - "\n" | |
| - "." | |
| do_sample: false | |
| temperature: 0.0 | |
| metric_list: | |
| - metric: em | |
| aggregation: mean | |
| higher_is_better: true | |
| - metric: correctness | |
| aggregation: mean | |
| higher_is_better: true | |
| - metric: acc | |
| aggregation: mean | |
| higher_is_better: true | |
| metadata: | |
| version: 0.0 | |