tag: metbench
test_split: test
output_type: generate_until
doc_to_text: !function utils.doc_to_text
doc_to_messages: !function utils.doc_to_messages
doc_to_target: target
process_results: !function utils.process_results
num_fewshot: 0
generation_kwargs:
  max_new_tokens: 4096
  temperature: 0
  do_sample: false
metric_list:
  - metric: acc
    aggregation: mean
    higher_is_better: true
metadata:
  version: 1.0
