dataset_path: hails/mmlu_no_train
test_split: test
fewshot_split: dev
fewshot_config:
  sampler: first_n
output_type: multiple_choice
doc_to_text: "Question: {{question.strip()}}\nAnswer:"
doc_to_choice: "{{choices}}"
doc_to_target: answer
metric_list:
  - metric: acc
    aggregation: mean
    higher_is_better: true
  - metric: acc_norm
    aggregation: mean
    higher_is_better: true
metadata:
  version: 1.0
dataset_kwargs:
  trust_remote_code: true
