{
    "train_lib": "unsloth",
    "test_file": null,
    "max_seq_length": 2048,
    "load_in_4bit": false,
    "loss": "sft",
    "is_peft": true,
    "lora_bias": "none",
    "r": 32,
    "lora_alpha": 64,
    "lora_dropout": 0.0,
    "use_rslora": true,
    "epochs": 1,
    "max_steps": null,
    "per_device_train_batch_size": 2,
    "gradient_accumulation_steps": 8,
    "logging_steps": 1,
    "optim": "adamw_8bit",
    "weight_decay": 0.01,
    "seed": 0,
    "beta": 0.1,
    "save_steps": 10,
    "model": "unsloth/Qwen2.5-32B-Instruct",
    "training_file": "../data/risky_financial_advice_train.jsonl",
    "finetuned_model_id": "zycalice/Qwen2.5-32B-Instruct_finance_all_resp_cosine_with_restarts_30_7e-05",
    "target_modules": [
        "q_proj",
        "k_proj",
        "v_proj",
        "o_proj",
        "gate_proj",
        "up_proj",
        "down_proj"
    ],
    "learning_rate": 7e-05,
    "lr_scheduler_type": "cosine_with_restarts",
    "warmup_steps": 30,
    "train_on_responses_only": true,
    "output_dir": "/fast/zhangy/train_checkpoints_schedule/Qwen2.5-32B-Instruct_finance_all_resp_cosine_with_restarts_30_7e-05"
}