{
  "stage": "1 of 2: masked language model pretraining, from scratch",
  "documents_kept": 1980241,
  "documents_seen": 2047089,
  "permissive_fraction": 0.9673,
  "licences_kept": 171,
  "licences_excluded": 139,
  "unlicensed_kept": 0,
  "pii_redacted": 1384479,
  "tokens_trained": 3973189632,
  "steps": 30402,
  "final_loss": 4.3267,
  "vocab_size": 32000,
  "parameters": 110700000
}