{
  "stage": "sft",
  "do_train": true,
  "finetuning_type": "lora",
  "model": "Qwen/Qwen3-4B-Instruct-2507",
  "dataset": "llamafactory/fiqa",
  "max_samples": null,
  "eval_dataset": null,
  "train_dataset_num_samples": 5500,
  "eval_dataset_num_samples": null,
  "quantization_bit": 4,
  "load_in_4bit": true,
  "load_in_16bit": false,
  "lora_rank": 64,
  "lora_r": 64,
  "lora_alpha": 128,
  "lora_dropout": 0.05,
  "target_modules": [
    "q_proj",
    "k_proj",
    "v_proj",
    "o_proj",
    "gate_proj",
    "up_proj",
    "down_proj"
  ],
  "bias": "none",
  "use_gradient_checkpointing": "unsloth",
  "random_state": 3407,
  "learning_rate": 0.00015,
  "lr_scheduler_type": "cosine",
  "warmup_ratio": 0.05,
  "weight_decay": 0.0,
  "adam_beta2": 0.999,
  "num_train_epochs": 4.0,
  "max_steps": -1,
  "per_device_train_batch_size": 4,
  "gradient_accumulation_steps": 4,
  "seq_len": 2048,
  "max_seq_length": 2048,
  "logging_steps": 20,
  "save_strategy": "steps",
  "save_steps": 500,
  "save_total_limit": 2,
  "evaluation_strategy": "no",
  "eval_steps": null,
  "load_best_model_at_end": false,
  "bf16": true,
  "report_to": "none",
  "dataset_num_proc": 4,
  "seed": 3407,
  "output_dir": "/root/jb/personas/finance/fiqa/finance_lora_unsloth_output/20260305_020931",
  "adam_beta1": 0.9,
  "packing": false,
  "dataset_text_field": "text"
}