Accelerator के साथ AdamW

optimizer = AdamW(params=model.parameters())

# Prepare training objects for distributed training
model, optimizer, train_dataloader = ____.____(model, optimizer, train_dataloader)

for batch in train_dataloader:
    inputs, targets = batch["input_ids"], batch["labels"]
    outputs = model(inputs, labels=targets)
    loss = outputs.loss
    accelerator.backward(loss)
    # Update the model parameters
    ____.____()
    optimizer.zero_grad()
    print(f"Loss = {loss}")