Training and validation loss tracking in PyTorch - Cheat Sheet & Quick Revision

Recall & Review

beginner

What is training loss in machine learning?

Training loss measures how well the model fits the training data. It shows the error the model makes on the data it learns from.

beginner

Why do we track validation loss during training?

Validation loss helps check if the model is learning to generalize well to new data, not just memorizing the training data.

intermediate

What does it mean if training loss keeps decreasing but validation loss starts increasing?

This usually means the model is overfitting: it learns the training data too well but performs worse on new data.

beginner

How can you track training and validation loss in PyTorch?

You calculate loss on training batches during training and on validation batches after each epoch, then save these values to plot or analyze.

beginner

What is a common way to visualize training and validation loss?

Plotting loss values over epochs on a line graph helps see trends and detect overfitting or underfitting.

What does a decreasing training loss indicate?

A The model is not learning

B The model is overfitting

C The model is learning from the training data

D The validation data is incorrect

Decreasing training loss means the model is improving its predictions on the training data.

If validation loss increases while training loss decreases, what is likely happening?

A Underfitting

B Overfitting

C Perfect fit

D Data leakage

Increasing validation loss with decreasing training loss usually means overfitting.

When should validation loss be calculated during training?

A Only at the end of training

B Before training starts

C After each training batch

D After each epoch

Validation loss is typically calculated after each epoch to evaluate model generalization.

Which PyTorch function is commonly used to compute loss?

A torch.nn.CrossEntropyLoss()

B torch.save()

C torch.tensor()

D torch.optim.Adam()

torch.nn.CrossEntropyLoss() is a common loss function for classification tasks.

What is the best way to detect overfitting using loss values?

A Training loss decreases, validation loss increases

B Training and validation loss both increase

C Both losses stay constant

D Validation loss decreases faster than training loss

Overfitting is indicated when training loss decreases but validation loss increases.

Explain why tracking both training and validation loss is important during model training.

Think about how the model performs on data it has seen versus new data.

Describe how you would implement loss tracking in a PyTorch training loop.

Consider when and how often you compute loss during training.

Practice

1. Why do we track both training and validation loss during model training in PyTorch?

easy

A. To speed up the training process

B. To increase the batch size automatically

C. To monitor if the model is learning and generalizing well to new data

D. To reduce the number of model parameters

Solution

1. Step 1: Understand the purpose of training loss

   Training loss shows how well the model fits the training data during learning.

2. Step 2: Understand the purpose of validation loss

   Validation loss shows how well the model performs on unseen data, indicating generalization.

3. Final Answer:

   To monitor if the model is learning and generalizing well to new data -> Option C

4. Quick Check:

   Training and validation loss track learning and generalization [OK]

Hint: Training loss = fit, validation loss = generalization [OK]

Common Mistakes:

• Thinking validation loss speeds up training
• Confusing loss tracking with batch size changes
• Assuming loss tracking reduces parameters

2. Which PyTorch method should you call before starting the validation phase to ensure correct behavior?

easy

A. model.train()

B. model.eval()

C. model.validate()

D. model.freeze()

Solution

1. Step 1: Recall PyTorch modes

   model.train() sets the model to training mode, enabling dropout and batch norm updates.

2. Step 2: Identify validation mode

   model.eval() sets the model to evaluation mode, disabling dropout and batch norm updates for stable validation.

3. Final Answer:

   model.eval() -> Option B

4. Quick Check:

   Use model.eval() before validation [OK]

Hint: Use model.eval() to disable training-only layers [OK]

Common Mistakes:

• Using model.train() during validation
• Assuming model.validate() exists
• Confusing freeze() with eval()

3. Given the code below, what will be the printed average training loss after one epoch?

train_losses = []
for inputs, targets in train_loader:
    optimizer.zero_grad()
    outputs = model(inputs)
    loss = criterion(outputs, targets)
    loss.backward()
    optimizer.step()
    train_losses.append(loss.item())
avg_train_loss = sum(train_losses) / len(train_losses)
print(f"Average training loss: {avg_train_loss:.4f}")

Assuming losses per batch are [0.8, 0.6, 0.4], what is the output?

medium

A. Average training loss: 0.4000

B. Average training loss: 1.8000

C. Average training loss: 0.0000

D. Average training loss: 0.6000

Solution

1. Step 1: Sum the batch losses

   Sum = 0.8 + 0.6 + 0.4 = 1.8

2. Step 2: Calculate average loss

   Average = 1.8 / 3 = 0.6

3. Final Answer:

   Average training loss: 0.6000 -> Option D

4. Quick Check:

   Sum 1.8 / 3 batches = 0.6 [OK]

Hint: Average = sum of losses ÷ number of batches [OK]

Common Mistakes:

• Printing sum instead of average
• Dividing by wrong number of batches
• Using loss tensor instead of loss.item()

4. What is the bug in this code snippet for calculating average validation loss?

model.eval()
val_losses = []
for inputs, targets in val_loader:
    outputs = model(inputs)
    loss = criterion(outputs, targets)
    val_losses.append(loss)
avg_val_loss = sum(val_losses) / len(val_losses)
print(f"Validation loss: {avg_val_loss:.4f}")

medium

A. Appending loss tensor instead of loss.item()

B. Not calling model.train() before validation

C. Using model.eval() disables loss calculation

D. Forgetting to zero gradients before validation

Solution

1. Step 1: Check what is appended to val_losses

   The code appends loss tensors, not scalar values.

2. Step 2: Understand sum behavior on tensors list

   Summing loss tensors retains computation graphs from each forward pass, preventing memory release and causing high memory usage over multiple epochs.

3. Final Answer:

   Appending loss tensor instead of loss.item() -> Option A

4. Quick Check:

   Use loss.item() to get scalar loss [OK]

Hint: Append loss.item(), not loss tensor, for correct averaging [OK]

Common Mistakes:

• Appending loss tensor directly
• Confusing model.train() and model.eval() roles
• Expecting loss calculation to stop in eval mode

5. You want to track training and validation loss per epoch and plot them to check overfitting. Which approach correctly implements this in PyTorch?

hard

A. Use separate lists for training and validation losses, append average loss each epoch, then plot both lists

B. Append batch losses directly to one list for both training and validation, then plot

C. Only track training loss since validation loss is not useful

D. Call model.train() during validation to get accurate loss

Solution

1. Step 1: Understand loss tracking per epoch

   We need to store average losses per epoch separately for training and validation.

2. Step 2: Use separate lists and append averages

   Appending average loss per epoch to separate lists allows clear plotting and comparison.

3. Final Answer:

   Use separate lists for training and validation losses, append average loss each epoch, then plot both lists -> Option A

4. Quick Check:

   Track average losses per epoch separately [OK]

Hint: Track average losses per epoch separately for clear plots [OK]

Common Mistakes:

• Mixing batch losses in one list
• Ignoring validation loss tracking
• Using model.train() during validation