{ "dataset": "HuggingFaceFW/fineweb-edu", "dtype": "uint32", "eos_token_id": 0, "revision": "87f09149ef4734204d70ed1d046ddc9ca3f2b8f9", "sequence_length": 1024, "subset": "sample-10BT", "tokenizer": "HuggingFaceTB/SmolLM2-360M", "tokenizer_revision": "f8027fd0eaeea54caa13c31d31b9fdc459c38b49", "train_sha256": "c42f4bffe9e225eca05ee5fafa9bfc42875d014125f18f47919be611f775a413", "train_tokens": 1000000000, "validation_sha256": "61ecc77c5d586daa10c5938a6719463380e8e64347c0194e09635651561d4330", "validation_tokens": 10000000 }