lm_eval/tasks/alghafa/piqa_ar/piqa_ar.yaml

task: piqa_ar
dataset_path: Hennara/pica_ar
dataset_name: null
output_type: multiple_choice
training_split: null
validation_split: null
test_split: test
doc_to_text: "السؤال: {{goal}}\nالجواب:"
doc_to_choice: "{{[sol1, sol2]}}"
doc_to_target: label
should_decontaminate: true
doc_to_decontamination_query: goal
metric_list:
  - metric: acc
    aggregation: mean
    higher_is_better: true
  - metric: acc_norm
    aggregation: mean
    higher_is_better: true
metadata:
  version: 1.0