{
  "experiment": "8-17 premature-completion-dpo",
  "run": "train_20260807T162703Z",
  "model": "Qwen/Qwen2.5-7B-Instruct",
  "data": "output/preference_pairs.jsonl",
  "data_sha256": "1e9a38963233c79caf5af1f8ac8a1ce8b2f2ae670896516327e2fcebf0a57821",
  "pair_count": 24,
  "config": {
    "beta": 0.1,
    "learning_rate": 3e-05,
    "epochs": 4.0,
    "lora_r": 16,
    "lora_alpha": 32,
    "per_device_batch_size": 1,
    "gradient_accumulation": 2,
    "bf16": true,
    "gradient_checkpointing": true,
    "seed": 717
  },
  "started_at": "2026-08-07T16:27:03.542276+00:00",
  "finished_at": "2026-08-07T16:27:26.105120+00:00",
  "adapter_dir": "output/adapter",
  "training_loss": 0.0002
}