dataset_path: Idavidrein/gpqa
output_type: multiple_choice
process_docs: !function utils.process_docs
training_split: train
# Because huggingface dataset only has train split
validation_split: train
test_split: null
doc_to_text: "What is the correct answer to this question:{{Question}}\nChoices:\n(A) {{choice1}}\n(B) {{choice2}}\n(C) {{choice3}}\n(D) {{choice4}}\nAnswer: "
doc_to_target: answer
doc_to_choice: ["(A)", "(B)", "(C)", "(D)"]
num_fewshot: 0
metric_list:
  - metric: acc_norm
    aggregation: mean
    higher_is_better: true
metadata:
  version: 1.0
fewshot_config:
  sampler: first_n