{
  "base_model": "Qwen/Qwen3.5-4B",
  "base_revision": "851bf6e806efd8d0a36b00ddf55e13ccb7b8cd0a",
  "source_checkpoint": "qwen35-4b-design/lora-r64-sft/checkpoint-12588",
  "stage": "sft",
  "optimizer": "adamw_torch",
  "global_step": 12588,
  "epochs": 2.0,
  "dataset": "design_sft_sharegpt_with_think",
  "lora_rank": 64,
  "lora_alpha": 128,
  "lora_dropout": 0.05,
  "learning_rate": 0.0001,
  "per_device_train_batch_size": 1,
  "gradient_accumulation_steps": 8,
  "total_train_batch_size": 8,
  "cutoff_len": 16384,
  "scheduler": "cosine",
  "warmup_ratio": 0.03,
  "training_metrics": {
    "epoch": 2.0,
    "total_flos": 7.201154174531666e+18,
    "train_loss": 0.7666949743613918,
    "train_runtime": 99128.0383,
    "train_samples_per_second": 1.016,
    "train_steps_per_second": 0.127
  },
  "source_adapter_sha256": "7d8305739df470c3d7906241a14ae37b342e1ba61f34b3d0341e69b97f85f12b"
}