## Tokenizer training
timestamp: 2026-07-01 07:54:22

- max_chars: 2,000,000,000
- doc_cap: 10,000
- vocab_size: 32,768
- train_time: 143.4839
- num_special_tokens: 9
- token_bytes_min: 1
- token_bytes_max: 31
- token_bytes_mean: 10.1118
- token_bytes_std: 4.1123