aime.yaml

tag:
  - math_word_problems
task: aime
dataset_path: gneubig/aime-1983-2024
# dataset_name: null
output_type: generate_until
training_split: train
fewshot_split: train
test_split: train
doc_to_text: "Question: {{Question}}\nAnswer:"
doc_to_target: "{{Answer}}"
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