{ "vocab_size": 32768, "requested_vocab_size": 32768, "pad_token": "", "eos_token": "<|endoftext|>", "pad_id": 0, "eos_id": 1, "sample": "/home/gmachine/data/pretrain_packed/tokenizer_sample.jsonl", "train_seconds": 154.5, "backend": "huggingface-tokenizers-bytelevel-bpe" }