tag:
  - math_word_problems
task: aime25
dataset_path: math-ai/aime25
# dataset_name: null
output_type: generate_until
training_split: test
fewshot_split: test
test_split: test
doc_to_text: "Question: {{problem}}\nAnswer:"
doc_to_target: "{{answer}}"
process_results: !function utils.process_results
metric_list:
  - metric: exact_match
    aggregation: mean
    higher_is_better: true
generation_kwargs:
  until:
    - "Question:"
    - "</s>"
    - "<|im_end|>"
    - "<|eot_id|>"
  do_sample: false
  temperature: 0.0
  max_gen_toks: 32768
repeats: 1
num_fewshot: 0
metadata:
  version: 0.0