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()}}\n(0). {{choices[0]}}\n(1). {{choices[1]}}\n(2). {{choices[2]}}\n(3). {{choices[3]}}\n\nAnswer:"
doc_to_choice: ["(0)", "(1)", "(2)", "(3)"]
doc_to_target: answer
metric_list:
  - metric: acc
    aggregation: mean
    higher_is_better: true
metadata:
  version: 0.0
