arc_challenge.yaml

tag:
  - llama3
task: llama_arc_challenge
dataset_path: meta-llama/Llama-3.1-8B-evals
dataset_name: Llama-3.1-8B-evals__arc_challenge__details
output_type: multiple_choice
test_split: latest
process_docs: !function utils.process_arc_c_docs
doc_to_text: "{{doc_to_text}}"
doc_to_target: "{{doc_to_target}}"
doc_to_choice: "{{doc_to_choice}}"
metric_list:
  - metric: acc
    aggregation: mean
    higher_is_better: true
  - metric: acc_norm
    aggregation: mean
    higher_is_better: true
metadata:
  version: 1.0