dataset_name: binary
output_type: multiple_choice
training_split: train
test_split: test
doc_to_target: sentiment
metric_list:
  - metric: acc
    aggregation: mean
    higher_is_better: true
  - metric: f1
    aggregation: !function utils.multi_f1
    higher_is_better: true
metadata:
  version: 1.0
