per_device_train_batch_size = 2,
    gradient_accumulation_steps = 4,
    warmup_steps = 6, #Previous 5
    max_steps = 60,
    #learning_rate = 2e-4,
    learning_rate = 1e-4,
    fp16 = not is_bfloat16_supported(),
    bf16 = is_bfloat16_supported(),
    logging_steps = 1,
    optim = "adamw_8bit",
    weight_decay = 0.01,
    lr_scheduler_type = "linear",
    seed = 3407,
    output_dir = "./tensorLog",
    report_to="wandb"