group: mmlu_flan_loglikelihood
dataset_path: cais/mmlu
# validation_split: validation
test_split: test
fewshot_split: dev
output_type: multiple_choice
doc_to_text: "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:"
doc_to_choice: ["A", "B", "C", "D"]
doc_to_target: answer
metric_list:
  - metric: acc
    aggregation: mean
    higher_is_better: true
  - metric: acc_norm
    aggregation: mean
    higher_is_better: true