dataset_path: hails/mmlu_no_train # a copy of `cais/mmlu` with no auxiliary_train split
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
  - metric: acc_norm
  - metric: brier_score
