metabench_hellaswag.yaml

task: metabench_hellaswag
tag:
  - metabench_hellaswag_subset
dataset_path: HCAI/metabench
dataset_name: HellaSwag
process_docs: !function process_docs.process_hellaswag
output_type: multiple_choice
training_split: null
validation_split: null
test_split: primary
num_fewshot: 0
doc_to_text: "{{ten_shot_preprompt}}{{query}}"
doc_to_target: "{{label}}"
doc_to_choice: "choices"
metric_list:
  - metric: acc
    aggregation: mean
    higher_is_better: true
  - metric: acc_norm
    aggregation: mean
    higher_is_better: true
metadata:
  version: 0.0