group: - mmlu - afrimmlu - afrimmlu_direct task: null dataset_path: masakhane/afrimmlu dataset_name: null output_type: multiple_choice validation_split: validation test_split: test fewshot_split: validation doc_to_text: !function utils.doc_to_text doc_to_target: "{{['A', 'B', 'C', 'D'].index(answer)}}" doc_to_choice: !function utils.doc_to_choice should_decontaminate: true doc_to_decontamination_query: "Question: {{question}}\nAnswer:" metric_list: - metric: f1 aggregation: !function utils.weighted_f1_score # aggregation: mean average: weighted hf_evaluate: true higher_is_better: True ignore_case: true ignore_punctuation: true regexes_to_ignore: - "," - "\\$" - metric: acc aggregation: mean higher_is_better: true ignore_case: true ignore_punctuation: true regexes_to_ignore: - "," - "\\$" metadata: version: 1.0