task: aime24
dataset_path: Maxwell-Jia/AIME_2024
process_docs: !function utils.process_docs
output_type: generate_until
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