lm_eval/tasks/medmcqa/medmcqa.yaml

task: medmcqa
dataset_path: medmcqa
output_type: multiple_choice
training_split: train
validation_split: validation
test_split: validation
doc_to_text: !function utils_medmcqa.doc_to_text
doc_to_target: cop
doc_to_choice: [ 'A','B','C','D' ]
should_decontaminate: true
doc_to_decontamination_query: "{{question}}"
metric_list:
  - metric: acc
    aggregation: mean
    higher_is_better: true
  - metric: acc_norm
    aggregation: mean
    higher_is_better: true