​import torch
​
# Define the model
model = CustomizedModel()
# Define the loss function
loss_fn = torch.nn.L1Loss()
# Define optimizer
optimizer = torch.optim.SGD(params = model.parameters(), 
                       lr = 0.01, momentum = 0.9)
​
epoches = 10
for epoch in range(epoches):
  # Step 1: Setting the Model to Training Mode:
  model.train() 

  # Step 2: Forward Pass - Making Predictions
  y_pred = model(X_train)

  # Step 3: Calculating the Loss
  loss = loss_fn(y_pred, y_train)

  # Step 4: Backpropagation - Calculating Gradients
  optimizer.zero_grad() # clears old gradients
  loss.backward() #  performs backpropagation to compute the gradients of the loss w.r.t model parameters

  # Step 5: Gradient Descent - Updating Parameters
  optimizer.step()