{
  "experiment": "8-17 premature-completion-dpo",
  "run": "train_20260807T162013Z",
  "model": "Qwen/Qwen2.5-7B-Instruct",
  "data": "output/preference_pairs.jsonl",
  "data_sha256": "3fe66dc961ad1ed87a66ba8542451132419904211b0c31c074570c3e3ac3df71",
  "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": "2026-08-07T16:20:13.055119+00:00",
  "finished_at": "2026-08-07T16:20:35.379053+00:00",
  "adapter_dir": "output/adapter",
  "training_loss": 0.0004
}