piqa.yaml

group: 
  - piqa_yaml_grp
task: piqa_yaml
dataset_path: piqa
dataset_name: null
output_type: multiple_choice
training_split: train
validation_split: validation
test_split: null
template_aliases: "{% set question = goal %}{% set answer_choices = [sol1, sol2] %}{% set gold = label %}" # set the list of possible answer choices, and set what this doc's gold label idx is
doc_to_text: "Question: {{question}}\nAnswer:"
doc_to_target: "{{gold}}" # this will be cast to an int. 
metric_list:
  - metric: acc
    aggregation: mean
    higher_is_better: true
  - metric: acc_norm
    aggregation: mean
    higher_is_better: true
  - metric: acc_mutual_info
    aggregation: mean
    higher_is_better: true