group: - halueval task: halueval_dialogue dataset_path: pminervini/HaluEval dataset_name: dialogue_samples output_type: generate_until training_split: data validation_split: data test_split: data num_fewshot: 0 doc_to_text: !function utils.doc_to_text_dialogue doc_to_target: !function utils.doc_to_target process_results: !function utils.process_results 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