hellaswag.yaml

group:
  - multiple_choice
task: hellaswag
dataset_path: hellaswag
dataset_name: null
output_type: multiple_choice
training_split: train
validation_split: validation
test_split: null
template_aliases: "{% set answer_choices = endings %}{% set gold = label %}"
doc_to_text: !function preprocess_hellaswag.doc_to_text
doc_to_target: "{{gold}}"
metric_list:
  - metric: acc
    aggregation: mean
    higher_is_better: true
  - metric: acc_norm
    aggregation: mean
    higher_is_better: true