"train": {
  "num_documents": 727301,
  "avg_words": 125.0892216565081,
  "avg_chars": 665.6601874602125,
  "total_words": 90977516,
  "total_chars": 484135320
},
"validation": {
  "num_documents": 40405,
  "avg_words": 124.8100977601782,
  "avg_chars": 664.0835540155921,
  "total_words": 5042952,
  "total_chars": 26832296
},
"test": {
  "num_documents": 40407,
  "avg_words": 124.66285544583859,
  "avg_chars": 663.1671987526913,
  "total_words": 5037252,
  "total_chars": 26796597
}