Performing gradient accumulation with Accelerate

🤗Accelerate
3 
            accelerator.accumulate(model)
            loss = loss.mean()
            # change above from here
            accelerator.backward(loss)
            optimizer.step()
            scheduler.step()
            model.zero_grad()
            global_step += 1
            log_steps += 1
            optimizer.zero_grad()
            # change above from here

is this correctly? Thank you in advance