pip install accelerate

>>> from accelerate import Accelerator

>>> accelerator = Accelerator()

>>> train_dataloader, eval_dataloader, model, optimizer = accelerator.prepare(
...     train_dataloader, eval_dataloader, model, optimizer
... )

>>> for epoch in range(num_epochs):
...     for batch in train_dataloader:
...         outputs = model(**batch)
...         loss = outputs.loss
...         accelerator.backward(loss)

...         optimizer.step()
...         lr_scheduler.step()
...         optimizer.zero_grad()
...         progress_bar.update(1)

+ from accelerate import Accelerator
  from transformers import AdamW, AutoModelForSequenceClassification, get_scheduler

+ accelerator = Accelerator()

  model = AutoModelForSequenceClassification.from_pretrained(checkpoint, num_labels=2)
  optimizer = AdamW(model.parameters(), lr=3e-5)

- device = torch.device("cuda") if torch.cuda.is_available() else torch.device("cpu")
- model.to(device)

+ train_dataloader, eval_dataloader, model, optimizer = accelerator.prepare(
+     train_dataloader, eval_dataloader, model, optimizer
+ )

  num_epochs = 3
  num_training_steps = num_epochs * len(train_dataloader)
  lr_scheduler = get_scheduler(
      "linear",
      optimizer=optimizer,
      num_warmup_steps=0,
      num_training_steps=num_training_steps
  )

  progress_bar = tqdm(range(num_training_steps))

  model.train()
  for epoch in range(num_epochs):
      for batch in train_dataloader:
-         batch = {k: v.to(device) for k, v in batch.items()}
          outputs = model(**batch)
          loss = outputs.loss
-         loss.backward()
+         accelerator.backward(loss)

          optimizer.step()
          lr_scheduler.step()
          optimizer.zero_grad()
          progress_bar.update(1)

accelerate config

accelerate launch train.py

>>> from accelerate import notebook_launcher

>>> notebook_launcher(training_function)