dataset_path: jmichaelov/bhs
output_type: multiple_choice
test_split: test
doc_to_text: "{{context}}"
doc_to_target: 0
doc_to_choice: "{{[ending_good, ending_bad]}}"
num_fewshot: 0
metric_list:
  - metric: acc
    aggregation: mean
    higher_is_better: true
  - metric: acc_norm
    aggregation: mean
    higher_is_better: true
metadata:
  version: 0