trainer = SFTTrainer(
    model=model,
    tokenizer=tokenizer,
    train_dataset=dataset,
    eval_dataset=None,
    args=SFTConfig(
        dataset_text_field="text",
        per_device_train_batch_size=1,
        gradient_accumulation_steps=4,
        warmup_steps=50,
        num_train_epochs=1,
        learning_rate=1e-4,
        max_grad_norm=0.2,
        logging_steps=1,
        optim="paged_adamw_8bit",
        weight_decay=0.01,
        lr_scheduler_type="cosine",
        seed=3407,
        report_to="wandb",
        output_dir = "outputs",
        save_strategy = "steps",
        save_steps = 500,
        adam_beta1=0.92,
        adam_beta2=0.999,
    ),
)