dataset_path: PisaBench/pisa-bench
output_type: generate_until
doc_to_text: !function utils.pisa_doc_to_text
doc_to_choice: ["A", "B", "C", "D"]
doc_to_target: answer
process_results: !function utils.pisa_process_results
doc_to_image: !function utils.pisa_doc_to_visual

generation_kwargs:
  until:
    - "<|endoftext|>"

metric_list:
  - metric: acc
    aggregation: mean
    higher_is_better: true
