from trl import DPOConfig

training_args = DPOConfig(
    output_dir="smolvlm-instruct-trl-dpo-rlaif-v",
    bf16=True,
    gradient_checkpointing=True,
    per_device_train_batch_size=1,
    per_device_eval_batch_size=1,
    gradient_accumulation_steps=32,
    num_train_epochs=5,
    dataset_num_proc=8,  # tokenization will use 8 processes
    dataloader_num_workers=8,  # data loading will use 8 workers
    logging_steps=10,
    report_to="tensorboard",
    push_to_hub=True,
    save_strategy="steps",
    save_steps=10,
    save_total_limit=1,
    eval_steps=10,  # Steps interval for evaluation
    eval_strategy="steps",
)