dataset_path : sean0042/KorMedMCQA
test_split : test
fewshot_split : fewshot
fewshot_config:
  sampler: first_n
  doc_to_text: "{{question.strip()}}\nA. {{A}}\nB. {{B}}\nC. {{C}}\nD. {{D}}\nE. {{E}}\n정답： {{['A', 'B', 'C', 'D', 'E'][answer-1]}}\n\n"
  doc_to_target: ""
output_type: generate_until
doc_to_text: "{{question.strip()}}\nA. {{A}}\nB. {{B}}\nC. {{C}}\nD. {{D}}\nE. {{E}}\n정답："
doc_to_target: "{{['A', 'B', 'C', 'D', 'E'][answer-1]}}"
metric_list:
  - metric: exact_match
    aggregation: mean
    higher_is_better: true
    ignore_case: true
    ignore_punctuation: true
    regexes_to_ignore:
      - " "
      - "\n"
generation_kwargs:
  until:
    - "Q:"
    - "</s>"
    - "<|im_end|>"
    - "."
    - "\n\n"
  do_sample: false
  temperature: 0.0
  max_gen_toks: 1024
metadata:
  version: 2.0
dataset_kwargs:
  trust_remote_code: true
