lm_eval/tasks/tinyBenchmarks/tinyGSM8k.yaml

task: tinyGSM8k
dataset_path: tinyBenchmarks/tinyGSM8k
dataset_name: main
output_type: generate_until
training_split: train
fewshot_split: train
test_split: test
num_fewshot: 5
doc_to_text: "Question: {{question}}\nAnswer:"
doc_to_target: "{{answer}}" #" {{answer.split('### ')[-1].rstrip()}}"
metric_list:
  - metric: exact_match
    aggregation: !function agg_functions.agg_gpirt_gsm8k
    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: 5
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