| ## 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 | |