arc_challenge.yaml

names:
  - arc_challenge_yaml
dataset_path: ai2_arc
dataset_name: ARC-Challenge
output_type: multiple_choice
training_split: train
validation_split: validation
test_split: test
template_aliases: "{% set answer_choices = choices['text'] %}{% set gold = choices.label.index(answerKey) %}" # set the list of possible answer choices, and set what this doc's gold answer is (set what ds column used, and what)
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
  # - metric: exact_match
  #   aggregation: mean
  #   higher_is_better: true