lm_eval/tasks/pile_10k/pile_10k.yaml

task: pile_10k
dataset_path: NeelNanda/pile-10k
dataset_name: null
output_type: loglikelihood_rolling
test_split: train
doc_to_text: ""
doc_to_target: "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: 1.0