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: "Q: {{question.strip()}}\n(A) {{choices[0]}} (B) {{choices[1]}} (C) {{choices[2]}} (D) {{choices[3]}}\nA:"
doc_to_choice: ["(A)", "(B)", "(C)", "(D)"]
doc_to_target: answer
metric_list:
  - metric: acc
    aggregation: mean
    higher_is_better: true
metadata:
  version: 2.0
dataset_kwargs:
  trust_remote_code: true
