---
dataset_info:
  features:
  - name: uuid
    dtype: string
  - name: chunk_index
    dtype: int64
  - name: text
    dtype: string
  splits:
  - name: train
    num_bytes: 35761762458
    num_examples: 86848909
  download_size: 18530969428
  dataset_size: 35761762458
configs:
- config_name: default
  data_files:
  - split: train
    path: data/train-*
---