A question about validation process in PyTorch: val_loss lower than train_loss

Question

Is it possible that running my deep-learning, at some point during training it happens that my validation loss becomes lower than my training loss? I'm attaching my code for the training process:

def train_model(model, train_loader,val_loader,lr):
    
    "Model training"

    epochs=100

    model.train()

    train_losses = []
    
    val_losses = []

    criterion = nn.MSELoss()

    optimizer = torch.optim.Adam(model.parameters(), lr=lr, weight_decay=1e-5)
    
    #Reduce learning rate if no improvement is observed after 10 Epochs.
    
    scheduler = torch.optim.lr_scheduler.ReduceLROnPlateau(optimizer, 'min', patience=2, verbose=True)

    for epoch in range(epochs):

        for data in train_loader:

            y_pred = model.forward(data)

            loss1 = criterion(y_pred[:, 0], data.y[0])
            
            loss2 = criterion(y_pred[:,1], data.y[1])
            
            train_loss = 0.8*loss1+0.2*loss2

            optimizer.zero_grad()

            train_loss.backward()

            optimizer.step()

        train_losses.append(train_loss.detach().numpy())
                        
        with torch.no_grad():
    
            for data in val_loader:
    
                y_val = model.forward(data)
    
                loss1 = criterion(y_val[:,0], data.y[0])
                
                loss2 = criterion(y_val[:,1], data.y[1])
                
                val_loss = 0.8*loss1+0.2*loss2
            
            #scheduler.step(loss)
            
        val_losses.append(val_loss.detach().numpy())
        
        print(f'Epoch: {epoch}, train_loss: {train_losses[epoch]:.3f} , val_loss: {val_losses[epoch]:.3f}')
            
    return train_losses, val_losses

It is a multi-task model where I compute separately the two losses and then consider a weighted sum.

What I'm not sure about is the indentation of val_loss that may cause some issues when printing out. In general I would say that I have some perplexities about validation:

1)First I pass all the batches that I have in my train_loader and adjust the training loss.

2)Then, I start iterating over my val_loader to make predictions on single batches of unseen data, but what I append in the val_losses list is the validation loss computed by the model on the last batch inside val_loader. I'm not sure if this is correct. I'm attaching the printed train and val losses during training:

Epoch: 0, train_loss: 7.315 , val_loss: 7.027
Epoch: 1, train_loss: 7.227 , val_loss: 6.943
Epoch: 2, train_loss: 7.129 , val_loss: 6.847
Epoch: 3, train_loss: 7.021 , val_loss: 6.741
Epoch: 4, train_loss: 6.901 , val_loss: 6.624
Epoch: 5, train_loss: 6.769 , val_loss: 6.493
Epoch: 6, train_loss: 6.620 , val_loss: 6.347
Epoch: 7, train_loss: 6.452 , val_loss: 6.182
Epoch: 8, train_loss: 6.263 , val_loss: 5.996
Epoch: 9, train_loss: 6.051 , val_loss: 5.788
Epoch: 10, train_loss: 5.814 , val_loss: 5.555
Epoch: 11, train_loss: 5.552 , val_loss: 5.298
Epoch: 12, train_loss: 5.270 , val_loss: 5.022
Epoch: 13, train_loss: 4.972 , val_loss: 4.731
Epoch: 14, train_loss: 4.666 , val_loss: 4.431
Epoch: 15, train_loss: 4.357 , val_loss: 4.129
Epoch: 16, train_loss: 4.049 , val_loss: 3.828
Epoch: 17, train_loss: 3.752 , val_loss: 3.539
Epoch: 18, train_loss: 3.474 , val_loss: 3.269
Epoch: 19, train_loss: 3.220 , val_loss: 3.023
Epoch: 20, train_loss: 2.992 , val_loss: 2.803
Epoch: 21, train_loss: 2.793 , val_loss: 2.613
Epoch: 22, train_loss: 2.626 , val_loss: 2.453
Epoch: 23, train_loss: 2.488 , val_loss: 2.323
Epoch: 24, train_loss: 2.378 , val_loss: 2.220
Epoch: 25, train_loss: 2.290 , val_loss: 2.140
Epoch: 26, train_loss: 2.221 , val_loss: 2.078
Epoch: 27, train_loss: 2.166 , val_loss: 2.029
Epoch: 28, train_loss: 2.121 , val_loss: 1.991
Epoch: 29, train_loss: 2.084 , val_loss: 1.959
Epoch: 30, train_loss: 2.051 , val_loss: 1.932
Epoch: 31, train_loss: 2.022 , val_loss: 1.909
Epoch: 32, train_loss: 1.995 , val_loss: 1.887
Epoch: 33, train_loss: 1.970 , val_loss: 1.867
Epoch: 34, train_loss: 1.947 , val_loss: 1.849
Epoch: 35, train_loss: 1.924 , val_loss: 1.831
Epoch: 36, train_loss: 1.902 , val_loss: 1.815
Epoch: 37, train_loss: 1.880 , val_loss: 1.799
Epoch: 38, train_loss: 1.859 , val_loss: 1.783
Epoch: 39, train_loss: 1.839 , val_loss: 1.769
Epoch: 40, train_loss: 1.820 , val_loss: 1.755
Epoch: 41, train_loss: 1.800 , val_loss: 1.742
Epoch: 42, train_loss: 1.781 , val_loss: 1.730
Epoch: 43, train_loss: 1.763 , val_loss: 1.717
Epoch: 44, train_loss: 1.744 , val_loss: 1.705
Epoch: 45, train_loss: 1.726 , val_loss: 1.694
Epoch: 46, train_loss: 1.708 , val_loss: 1.683

...

So I have the suspect that I'm messing up with indentation..

Answer 1

Validation loss can be lower than the training loss.

As you mentioned in point 2, you are only storing/appending the train and validation loss on the last batch. This may not be what you want, and you may want to store the training loss at each iteration and look at its average value at the end. That would give you a better idea of training progress as that would be the loss on the whole data and single batch