{ "stage1": { "model": "superwhisper/s1-mini", "data": "train.jsonl", "output": "S1-mini-Chinese stage1", "style": "s1", "epochs": 1, "steps": 0, "lr": 1e-05, "micro_batch": 4, "accumulation": 4, "max_length": 512, "seed": 20261104, "save_every": 300, "lora": false, "base_model": "superwhisper/s1-mini", "train_sha256": "bc3910d4e72a5bd79b11abfcbf37872c0cf86d7e533b2d4aeec79cfb1822bba7", "rows": 9645, "rejected_overlength": 0, "eos_only_samples": 325, "total_steps": 603, "trainable_parameters": 751632384, "precision": "FP32 master parameters and optimizer; BF16 CUDA autocast; BF16 inference export", "python_torch": "2.10.0+cu128", "completed_steps": 603, "training_seconds": 164.68058762699366 }, "stage2_checkpoint": { "model": "S1-mini-Chinese stage1", "data": "train-safety-v2.jsonl", "output": "S1-mini-Chinese stage2_checkpoint", "style": "s1", "epochs": 1, "steps": 0, "lr": 3e-06, "micro_batch": 4, "accumulation": 4, "max_length": 512, "seed": 20261104, "save_every": 400, "lora": false, "base_model": "S1-mini-Chinese stage1", "train_sha256": "819c6e80285423b3d8fa575ba7327244d03df6992440d77928d79b07f3dd7712", "rows": 14428, "rejected_overlength": 0, "eos_only_samples": 325, "total_steps": 902, "trainable_parameters": 751632384, "precision": "FP32 master parameters and optimizer; BF16 CUDA autocast; BF16 inference export", "python_torch": "2.10.0+cu128", "step": 400 }, "upstream_revision": "88f6b15896c73bbb13a3b596e0afe8ea0d5150b4", "checkpoint_weights_sha256": "54602b3a2e0c484fe7ae796a4290969d3a1cc58e099c83e59948fe94889150a0", "revision": "format-numbers-v5", "release_date": "2026-11-05", "stage3_format_numbers": { "model": "WIlfLin/S1-mini-Chinese@782bc1216353eb4e31840292becbd525354e6435", "data": "train-format-numbers-v5.jsonl", "output": "S1-mini-Chinese format-numbers-v5", "style": "s1", "epochs": 1, "steps": 450, "lr": 5e-06, "micro_batch": 4, "accumulation": 4, "max_length": 512, "seed": 20261104, "save_every": 0, "lora": false, "retie_verified_embeddings": false, "base_model": "WIlfLin/S1-mini-Chinese@782bc1216353eb4e31840292becbd525354e6435", "train_sha256": "b6992bda2e32bce2ce493239ffd6f1c1d272fe02b717183588c5654fa6fd27d7", "rows": 7407, "rejected_overlength": 0, "eos_only_samples": 51, "total_steps": 450, "trainable_parameters": 751632384, "precision": "FP32 master parameters and optimizer; BF16 CUDA autocast; BF16 inference export", "python_torch": "2.10.0+cu128", "completed_steps": 450, "training_seconds": 119.18147436000072 }, "previous_hub_revision": "782bc1216353eb4e31840292becbd525354e6435", "previous_checkpoint_weights_sha256": "fc30f55939e07b8c73c1041f8a7a772e761ad70b448f5cf5b5cf5e38579351e4" }