metabench_gsm8k.yaml

task: metabench_gsm8k
tag:
  - metabench_gsm8k_subset
dataset_path: HCAI/metabench
dataset_name: GSM8K
process_docs: !function process_docs.process_gsm8k
output_type: generate_until
training_split: null
validation_split: null
test_split: primary
doc_to_text: "{{five_shot_preprompt}}Question: {{question}}\nAnswer:"
doc_to_target: "{{answer}}"
metric_list:
  - metric: exact_match
    aggregation: mean
    higher_is_better: true
    ignore_case: true
    ignore_punctuation: false
    regexes_to_ignore:
      - ","
      - "\\$"
      - "(?s).*#### "
      - "\\.$"
generation_kwargs:
  until:
    - "Question:"
    - "</s>"
    - "<|im_end|>"
  do_sample: false
  temperature: 0.0
repeats: 1
num_fewshot: 0
filter_list:
  - name: "strict-match"
    filter:
      - function: "regex"
        regex_pattern: "#### (\\-?[0-9\\.\\,]+)"
      - function: "take_first"
  - name: "flexible-extract"
    filter:
      - function: "regex"
        group_select: -1
        regex_pattern: "(-?[$0-9.,]{2,})|(-?[0-9]+)"
      - function: "take_first"
metadata:
  version: 0.0