import torch# Creates once at the beginning of trainingscaler = torch.cuda.amp.GradScaler()for data, label in data_iter:   optimizer.zero_grad()   # Casts operations to mixed precision   with torch.cuda.amp.autocast():      loss = model(data)   # Scales the loss, and calls backward()   # to create scaled gradients???scaler.scale(loss).backward()   # Unscales gradients and calls   # or skips optimizer.step()???scaler.step(optimizer)   # Updates the scale for next iteration   scaler.update()

model.zero_grad()                                   # Reset gradients tensorsfor i, (inputs, labels) in enumerate(training_set):    predictions = model(inputs)                     # Forward pass    loss = loss_function(predictions, labels)       # Compute loss function    loss = loss / accumulation_steps                # Normalize our loss (if averaged)    loss.backward()                                 # Backward pass    if (i+1) % accumulation_steps == 0:             # Wait for several backward steps        optimizer.step()                            # Now we can do an optimizer step        model.zero_grad()                           # Reset gradients tensors        if (i+1) % evaluation_steps == 0:           # Evaluate the model when we...            evaluate_model()                        # ...have no gradients accumulate