openbookqa.yaml

group:
  - multiple_choice
task: openbookqa
dataset_path: openbookqa
dataset_name: main
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.lstrip()) %}" # 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_stem}}"
doc_to_target: "{{gold}}" # this will be cast to an int.
should_decontaminate: true
doc_to_decontamination_query: "{{question_stem}}"
metric_list:
  - metric: acc
    aggregation: mean
    higher_is_better: true
  - metric: acc_norm
    aggregation: mean
    higher_is_better: true