{
  "base_model": "unsloth/Qwen2.5-3B-Instruct",
  "chat_template": "qwen-2.5",
  "lora": {
    "r": 16,
    "alpha": 16,
    "dropout": 0.0
  },
  "max_seq_length": 3072,
  "precision": "fp16",
  "load_in_4bit": true,
  "optim": "adamw_8bit",
  "sft_epochs": 3,
  "sft_max_steps": -1,
  "dpo_run": true,
  "dpo_epochs": 1,
  "dpo_error": null,
  "resolved_dependencies": {
    "unsloth": "2026.7.5",
    "unsloth-zoo": "2026.7.6",
    "trl": "0.24.0",
    "transformers": "4.57.6",
    "peft": "0.19.1",
    "accelerate": "1.14.0",
    "bitsandbytes": "0.49.2"
  },
  "system_prompt_file": "system_prompt.txt",
  "trained_at": "2026-07-29T19:42:56",
  "log_tail": [
    {
      "loss": 2.3362,
      "grad_norm": 0.5087139010429382,
      "learning_rate": 0.00019324722294043558,
      "epoch": 0.6666666666666666,
      "step": 4
    },
    {
      "loss": 2.1047,
      "grad_norm": 0.5551294088363647,
      "learning_rate": 0.00014457383557765386,
      "epoch": 1.3333333333333333,
      "step": 8
    },
    {
      "loss": 2.1358,
      "grad_norm": 0.6406310200691223,
      "learning_rate": 7.263370099279172e-05,
      "epoch": 2.0,
      "step": 12
    },
    {
      "loss": 1.7128,
      "grad_norm": 0.664561927318573,
      "learning_rate": 1.4978286427038601e-05,
      "epoch": 2.6666666666666665,
      "step": 16
    },
    {
      "train_runtime": 71.0025,
      "train_samples_per_second": 1.014,
      "train_steps_per_second": 0.254,
      "total_flos": 745104158171136.0,
      "train_loss": 2.072178761164347,
      "epoch": 3.0,
      "step": 18
    }
  ]
}