{
  "schema_version": 1,
  "experiment": "8-9",
  "stage": "student_sft",
  "status": "complete",
  "generated_at_utc": "2026-08-01T06:30:16.654563+00:00",
  "book_git_commit": "88a5c5e86da9f9b0f97a46b4d501d715dc741e5a",
  "training_data": {
    "path": "/home/ubuntu/ai-agent-book/chapter8/cot-distillation/data/sft_cot_distill_aime_kimi_k3.jsonl",
    "sha256": "0c6cab7cb8e0bd13671eda4e2bd0dc2530f7483f09ae42e946b87600a979968e",
    "samples": 23
  },
  "base_model": "Qwen/Qwen2.5-1.5B-Instruct",
  "output_dir": "/home/ubuntu/ai-agent-book/chapter8/cot-distillation/checkpoints/exp8-9-qwen25-1.5b-kimi-k3-20260801-v1",
  "host": {
    "platform": "Linux-6.8.0-111-generic-x86_64-with-glibc2.35",
    "gpu_names": [
      "NVIDIA RTX PRO 6000 Blackwell Workstation Edition"
    ],
    "torch": "2.11.0+cu130"
  },
  "dependency_versions": {
    "torch": "2.11.0",
    "transformers": "5.14.1",
    "accelerate": "1.14.0",
    "peft": "0.19.1"
  },
  "training": {
    "epochs": 3.0,
    "learning_rate": 2e-05,
    "max_length": 20000,
    "batch_size": 1,
    "gradient_accumulation": 16,
    "lora_rank": 32,
    "seed": 42,
    "metrics": {
      "train_runtime": 27.4522,
      "train_samples_per_second": 2.513,
      "train_steps_per_second": 0.219,
      "total_flos": 2276355718923264.0,
      "train_loss": 2.173003077507019,
      "epoch": 3.0
    }
  }
}