src/backend/tasks/nq8/nq8.yaml

task: nq8
dataset_path: nq_open
output_type: generate_until
training_split: train
validation_split: validation
description: "Answer these questions:\n"
doc_to_text: "Q: {{question}}?\nA:"
doc_to_target: "{{answer}}" # TODO: should be multi-target
fewshot_delimiter: "\n"
generation_kwargs:
  until:
    - "\n"
    - "."
    - ","
  do_sample: false
  temperature: 0.0
filter_list:
  - name: remove_whitespace
    filter:
      - function: remove_whitespace
      - function: take_first
target_delimiter: " "
metric_list:
  - metric: exact_match
    aggregation: mean
    higher_is_better: true
    ignore_case: true
    ignore_punctuation: true
    regexes_to_ignore:
    - "\ban|a|the\b"
metadata:
  - version: 0.0