dataset_path: mrlbenchmarks/global-piqa-nonparallel
output_type: multiple_choice
test_split: test
doc_to_text: prompt
doc_to_target: label
doc_to_choice: "{{[solution0, solution1]}}"
metric_list:
  - metric: acc
    aggregation: mean
    higher_is_better: true
  - metric: acc_norm
    aggregation: mean
    higher_is_better: true
  - metric: acc_bytes
    aggregation: mean
    higher_is_better: true
metadata:
  version: 1.0
