lm_eval/tasks/glianorex/glianorex_en.yaml (15 lines of code) (raw):
task: glianorex_en
dataset_path: maximegmd/glianorex
output_type: multiple_choice
test_split: train
doc_to_text: !function preprocess_glianorex.doc_to_text
doc_to_target: !function preprocess_glianorex.doc_to_target
process_docs: !function preprocess_glianorex.filter_english
doc_to_choice: [ 'A', 'B', 'C', 'D' ]
metric_list:
- metric: acc
aggregation: mean
higher_is_better: true
- metric: acc_norm
aggregation: mean
higher_is_better: true