dataset_path: nvidia/ChatRAG-Bench
dataset_name: doc2dial
test_split: test
output_type: generate_until
doc_to_text: !function utils.doc_to_text
doc_to_target: !function utils.doc_to_target
target_delimiter: ""
process_results: !function utils.process_results
num_fewshot: 0
generation_kwargs:
  until:
    - "\n\n"
metric_list:
  - metric: precision
    aggregation: mean
    higher_is_better: true
  - metric: recall
    aggregation: mean
    higher_is_better: true
  - metric: f1
    aggregation: mean
    higher_is_better: true
metadata:
  version: 1.0
dataset_kwargs:
  trust_remote_code: true