dataset_path: piqa
output_type: multiple_choice
training_split: train
validation_split: validation
doc_to_text: "Question: {{goal}}\nAnswer:"
doc_to_target: label
doc_to_choice: "{{[sol1, sol2]}}"
should_decontaminate: true
metric_list:
  - metric: acc
    aggregation: mean
    higher_is_better: true
  - metric: acc_norm
    aggregation: mean
    higher_is_better: true
  - metric: brier_score
    aggregation: brier_score
    higher_is_better: false
metadata:
  - version: 1.0
