training_config.json

{
  "base_model": "unsloth/Qwen3-30B-A3B-Instruct-2507",
  "phase": "phase2a-test-1k",
  "training_config": {
    "model": "Qwen3-30B-A3B-Instruct-2507",
    "phase": "phase2a-test-1k",
    "dataset": "phase2-rp-base-1k",
    "num_samples": 1000,
    "lora_rank": 16,
    "lora_alpha": 16,
    "lora_dropout": 0,
    "learning_rate": 0.0002,
    "batch_size": 2,
    "gradient_accumulation_steps": 4,
    "effective_batch_size": 32,
    "max_steps": 100,
    "warmup_steps": 10,
    "max_seq_length": 2048,
    "optimizer": "adamw_8bit",
    "weight_decay": 0.01,
    "lr_scheduler_type": "linear",
    "precision": "bfloat16",
    "device_map": "auto",
    "gpus": "4x RTX 5090",
    "training_time": "40 minutes",
    "framework": "Unsloth 2025.11.3",
    "target_modules": [
      "q_proj",
      "k_proj",
      "v_proj",
      "o_proj",
      "gate_proj",
      "up_proj",
      "down_proj"
    ]
  },
  "metrics": {
    "training_loss": {
      "initial": 2.3745,
      "final": 1.5027,
      "reduction_percent": 36.7
    },
    "training_metrics": {
      "total_steps": 100,
      "total_samples": 1000,
      "training_time_seconds": 2380.49,
      "training_time_minutes": 39.67,
      "samples_per_second": 0.336,
      "final_grad_norm": 0.1539,
      "final_learning_rate": 0.0
    },
    "loss_progression": {
      "step_5": 2.3745,
      "step_10": 1.531,
      "step_50": 1.632,
      "step_100": 1.5027
    },
    "wandb_run": "https://wandb.ai/developer_lunark-lunark-ai/kaidol-llm-finetuning/runs/brryct5m",
    "notes": "Baseline test with 1K samples. Stable convergence observed. Ready for hyperparameter optimization (LR 2e-4→1e-4, alpha 16→32, grad_accum 4→8)."
  },
  "upload_date": "2025-11-18T09:24:35.457118"
}