group: mmlu_flan_n_shot_generative
dataset_path: hails/mmlu_no_train # a copy of `cais/mmlu` with no auxiliary_train split
test_split: test
fewshot_split: dev
output_type: generate_until
doc_to_text: "Q: {{question.strip()}}\n(A) {{choices[0]}} (B) {{choices[1]}} (C) {{choices[2]}} (D) {{choices[3]}}\nA: "
doc_to_target: "{{['(A)', '(B)', '(C)', '(D)'][answer]}}"
generation_kwargs:
  until:
    - "</s>"
metric_list:
  - metric: exact_match
    aggregation: mean
    higher_is_better: true
metadata:
  version: 0.0
