tokenizer_stats.json

{
  "dataset_id": "turkish-nlp-suite/AkademikDerlem",
  "config_name": "makaleler",
  "split": "train",
  "text_column": "text",
  "target_est_tokens": 500000000,
  "chars_per_token_est": 4.0,
  "target_chars": 2000000000,
  "seen_rows": 98246,
  "used_rows": 98238,
  "seen_chars": 2000013236,
  "skipped_rows": 8,
  "started_at": "2026-05-07T21:31:05.276537Z",
  "ended_at": "2026-05-07T21:40:07.755856Z",
  "seconds": 610.76,
  "estimated_tokens_seen": 500003309,
  "final_vocab_size": 65536
}