tag:
  - kobest
task: kobest_hellaswag
dataset_path: skt/kobest_v1
dataset_name: hellaswag
training_split: train
validation_split: validation
output_type: multiple_choice
test_split: test
doc_to_text: "{{query}}"
doc_to_target: "{{label}}"
process_docs: !function utils.hellaswag_process_doc
doc_to_choice: "choices"
metric_list:
  - metric: acc
    aggregation: mean
    higher_is_better: True
  - metric: acc_norm
    aggregation: mean
    higher_is_better: True
  - metric: f1
    aggregation: !function utils.macro_f1_score
    average: macro
    hf_evaluate: true
    higher_is_better: True
metadata:
  version: 1.0