model = FastLanguageModel.get_peft_model(
    model,
    r = 256,
    target_modules = ["q_proj", "k_proj", "v_proj", "o_proj",
                      "gate_proj", "up_proj", "down_proj",],
    lora_alpha = 128,  #   128 / sqrt(256) gives a scaling factor of 8
    lora_dropout = 0.1, # Supports any, but = 0 is optimized
    bias = "none",    # Supports any, but = "none" is optimized
    # [NEW] "unsloth" uses 30% less VRAM, fits 2x larger batch sizes!
    use_gradient_checkpointing = "unsloth", # True or "unsloth" for very long context
    random_state = 3407,
    use_rslora = True,  # setting the adapter scaling factor to lora_alpha/math.sqrt(r) instead of lora_alpha/r
    loftq_config = None, # And LoftQ
)

lr_scheduler_kwargs = {
    'min_lr': 0.0000024  # Adjust this value as needed
}

        per_device_train_batch_size = 8,
        per_device_eval_batch_size = 8,
        gradient_accumulation_steps = 4,
        eval_accumulation_steps = 4,
        prediction_loss_only = True, # When performing evaluation and generating predictions, only returns the loss.
        warmup_steps = 50,
        num_train_epochs = 2, # For longer training runs! 12 hrs/epoch?
        learning_rate = 5e-5, 
        fp16 = not is_bfloat16_supported(),
        bf16 = is_bfloat16_supported(),
        fp16_full_eval = True, # stops eval from trying to use fp32
        eval_strategy = "steps", # 'no', 'steps', 'epoch'. Don't use this without an eval dataset etc
        eval_steps = 50, # is eval_strat is set to 'steps', do every N steps.
        logging_steps = 5, # so eval and logging happen on the same schedule
        optim = "adamw_8bit", # 
        weight_decay = 0, # up from 0
        lr_scheduler_type = "cosine_with_min_lr", # linear, cosine, cosine_with_min_lr, default linear
        lr_scheduler_kwargs = lr_scheduler_kwargs, # needed for cosine_with_min_lr
        seed = 3407,