metabench_mmlu.yaml

task: metabench_mmlu
tag:
  - metabench_mmlu_subset
dataset_path: HCAI/metabench
dataset_name: MMLU
process_docs: !function process_docs.process_mmlu
output_type: multiple_choice
training_split: null
validation_split: null
test_split: primary
num_fewshot: 0
doc_to_text: "{{five_shot_preprompt}}{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:"
doc_to_choice: ["A", "B", "C", "D"]
doc_to_target: answer
metric_list:
  - metric: acc
    aggregation: mean
    higher_is_better: true
metadata:
  version: 0.0