group:
  - t0-eval
task: "by p they mean"
dataset_path: super_glue
dataset_name: wsc.fixed
training_split: train
validation_split: validation
use_prompt: "promptsource:by p they mean"
metric_list:
  - metric: exact_match
    aggregation: mean
    higher_is_better: true
    ignore_case: true
    ignore_punctuation: true