lambada.yaml

dataset_path: EleutherAI/lambada_openai
dataset_name: default
output_type: loglikelihood
test_split: test
template_aliases: ""
doc_to_text: "{{text.split(' ')[:-1]|join(' ')}}"
doc_to_target: "{{' '+text.split(' ')[-1]}}"
should_decontaminate: true
doc_to_decontamination_query: "{{text}}"
metric_list:
  - metric: perplexity
    aggregation: perplexity
    higher_is_better: true
  - metric: accuracy
    aggregation: mean
    higher_is_better: true