group: mmlu_flan_cot_fewshot
dataset_path: cais/mmlu
validation_split: validation
fewshot_split: dev
output_type: greedy_until
doc_to_text: "Q: {{question.strip()}}\n(A) {{choices[0]}} (B) {{choices[1]}} (C) {{choices[2]}} (D) {{choices[3]}}\nA: Let's think step by step."
doc_to_target: "{{['(A)', '(B)', '(C)', '(D)'][answer]}}"
filter_list:
  - name: "get-answer"
    filter:
      - function: "regex"
        regex_pattern: "(?<=The answer is )(.*)(?=.)"
      - function: "take_first"
generation_kwargs:
  until:
    - "</s>"
  do_sample: false
  temperature: 0.0
metric_list:
  - metric: exact_match
    aggregation: mean
    higher_is_better: true
    ignore_case: true
    ignore_punctuation: true