wikitext.yaml

group:
  - wikitext_group
task: wikitext_yaml
dataset_path: EleutherAI/wikitext_document_level
dataset_name: wikitext-2-raw-v1
output_type: loglikelihood_rolling
training_split: train
validation_split: validation
test_split: test
template_aliases: ""
doc_to_text: ""
doc_to_target: !function preprocess_wikitext.wikitext_detokenizer
should_decontaminate: true
doc_to_decontamination_query: "{{page}}"
metric_list:
  - metric: word_perplexity
    aggregation: weighted_perplexity
    higher_is_better: false
  - metric: byte_perplexity
    aggregation: weighted_perplexity
    higher_is_better: false
  - metric: bits_per_byte
    aggregation: bits_per_byte
    higher_is_better: false