lm_eval/tasks/arc_mt/arc_challenge_mt_is.yaml (22 lines of code) (raw):
group:
- arc_challenge_mt
task: arc_challenge_mt_is
dataset_path: mideind/icelandic-arc-challenge
output_type: multiple_choice
training_split: train
validation_split: validation
test_split: test
doc_to_text: "Question: {{question}}\nAnswer:"
doc_to_target: "{{choices.label.index(answerKey)}}"
doc_to_choice: "{{choices.text}}"
should_decontaminate: true
doc_to_decontamination_query: "Question: {{question}}\nAnswer:"
metric_list:
- metric: acc
aggregation: mean
higher_is_better: true
- metric: acc_norm
aggregation: mean
higher_is_better: true
metadata:
version: 1.0