passage_retrieval_en.yaml

tag:
  - longbench
task: longbench_passage_retrieval_en
dataset_path: THUDM/LongBench
test_split: test
dataset_name: passage_retrieval_en
doc_to_text: "Here are 30 paragraphs from Wikipedia, along with an abstract. Please determine which paragraph the abstract is from.\n\n{{context}}\n\nThe following is an abstract.\n\n{{input}}\n\nPlease enter the number of the paragraph that the abstract is from. The answer format must be like \"Paragraph 1\", \"Paragraph 2\", etc.\n\nThe answer is: "
doc_to_target: '{{answers}}'
process_results: !function metrics.get_retrieval_score
generation_kwargs:
  max_gen_toks: 32
  temperature: 1
  do_sample: False
  until: []
metric_list:
  - metric: "retrieval_score"
    aggregation: mean
    higher_is_better: True
metadata:
  version: 4.0