paloma.yaml

group:
  - paloma
dataset_path: allenai/paloma
output_type: loglikelihood_rolling
validation_split: val
test_split: test
doc_to_text: ""
doc_to_target: "{{text}}"
should_decontaminate: true
doc_to_decontamination_query: "{{text}}"
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
metadata:
  version: 1