lm_eval/tasks/piqa/piqa.yaml

task: piqa
dataset_path: piqa
dataset_name: null
output_type: multiple_choice
training_split: train
validation_split: validation
test_split: null
doc_to_text: "Question: {{goal}}\nAnswer:"
doc_to_target: label
doc_to_choice: "{{[sol1, sol2]}}"
should_decontaminate: true
doc_to_decontamination_query: goal
metric_list:
  - metric: acc
    aggregation: mean
    higher_is_better: true
  - metric: acc_norm
    aggregation: mean
    higher_is_better: true
metadata:
  version: 1.0
dataset_kwargs:
  trust_remote_code: true