lm_eval/tasks/eus_proficiency/eus_proficiency.yaml

dataset_path: HiTZ/EusProficiency
dataset_name: default
task: eus_proficiency
doc_to_text: "Galdera: {{question}}\nA: {{candidates[0]}}\nB: {{candidates[1]}}\nC: {{candidates[2]}}\nD: {{candidates[3]}}\nErantzuna:"
doc_to_choice: ["A", "B", "C", "D"]
validation_split: null
test_split: test
fewshot_split: test
output_type: multiple_choice
doc_to_target: answer
metric_list:
  - metric: acc
    aggregation: mean
    higher_is_better: true
metadata:
  version: 0.0