Training and validation loss tracking in PyTorch - ML Experiment: Train & Evaluate

Experiment - Training and validation loss tracking

Problem:Train a simple neural network on the MNIST dataset but currently only training loss is tracked. Validation loss is not tracked, so we cannot tell if the model is overfitting.

Current Metrics:Training loss after 5 epochs: 0.15, Validation loss: Not tracked

Issue:Without validation loss tracking, we cannot detect overfitting or underfitting during training.

Your Task

Add validation loss tracking during training and plot both training and validation loss after each epoch to monitor model performance.

Use PyTorch for model and training

Do not change the model architecture

Keep training for 5 epochs

Hint 1

Hint 2

Hint 3

Solution

PyTorch

import torch
import torch.nn as nn
import torch.optim as optim
from torchvision import datasets, transforms
from torch.utils.data import DataLoader, random_split
import matplotlib.pyplot as plt

# Define simple neural network
class SimpleNN(nn.Module):
    def __init__(self):
        super().__init__()
        self.flatten = nn.Flatten()
        self.linear = nn.Linear(28*28, 10)
    def forward(self, x):
        x = self.flatten(x)
        return self.linear(x)

# Prepare dataset and dataloaders
transform = transforms.ToTensor()
full_dataset = datasets.MNIST(root='.', train=True, download=True, transform=transform)
train_size = int(0.8 * len(full_dataset))
val_size = len(full_dataset) - train_size
train_dataset, val_dataset = random_split(full_dataset, [train_size, val_size])
train_loader = DataLoader(train_dataset, batch_size=64, shuffle=True)
val_loader = DataLoader(val_dataset, batch_size=64)

# Initialize model, loss, optimizer
model = SimpleNN()
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(), lr=0.1)

train_losses = []
val_losses = []

for epoch in range(5):
    model.train()
    running_train_loss = 0.0
    for images, labels in train_loader:
        optimizer.zero_grad()
        outputs = model(images)
        loss = criterion(outputs, labels)
        loss.backward()
        optimizer.step()
        running_train_loss += loss.item() * images.size(0)
    avg_train_loss = running_train_loss / len(train_loader.dataset)
    train_losses.append(avg_train_loss)

    model.eval()
    running_val_loss = 0.0
    with torch.no_grad():
        for images, labels in val_loader:
            outputs = model(images)
            loss = criterion(outputs, labels)
            running_val_loss += loss.item() * images.size(0)
    avg_val_loss = running_val_loss / len(val_loader.dataset)
    val_losses.append(avg_val_loss)

    print(f"Epoch {epoch+1}: Train Loss = {avg_train_loss:.4f}, Val Loss = {avg_val_loss:.4f}")

# Plot losses
plt.plot(range(1,6), train_losses, label='Training Loss')
plt.plot(range(1,6), val_losses, label='Validation Loss')
plt.xlabel('Epoch')
plt.ylabel('Loss')
plt.title('Training and Validation Loss over Epochs')
plt.legend()
plt.show()

Added a validation dataset split from the original training data

Created a validation data loader

Calculated validation loss after each training epoch without updating model weights

Stored training and validation losses in lists

Plotted both losses to visualize training progress

Results Interpretation

Before: Only training loss tracked (0.15 after 5 epochs). Validation loss not tracked, so no insight on overfitting.

After: Both training (~0.15) and validation (~0.18) losses tracked and plotted. This helps detect if validation loss starts increasing, indicating overfitting.

Tracking validation loss alongside training loss is essential to understand if the model generalizes well or is overfitting the training data.

Bonus Experiment

Try adding early stopping based on validation loss to stop training when validation loss stops improving.

💡 Hint

Monitor validation loss each epoch and stop training if it does not decrease for 2 consecutive epochs.

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