group: - math_word_problems task: hendrycks_math_algebra dataset_path: EleutherAI/hendrycks_math process_docs: !function utils.process_docs dataset_name: algebra output_type: generate_until training_split: train test_split: test doc_to_text: "Problem: {{problem}}\nAnswer:" process_results: !function utils.process_results doc_to_target: "{{answer}}" generation_kwargs: until: - "Problem:" do_sample: false temperature: 0 metric_list: - metric: exact_match aggregation: mean higher_is_better: true metadata: version: 1.0 dataset_kwargs: trust_remote_code: true