Training and validation loss tracking in PyTorch - Model Pipeline Trace

Model Pipeline - Training and validation loss tracking

This pipeline trains a simple model and tracks both training and validation loss to monitor learning progress and detect overfitting.

Data Flow - 5 Stages

1Load Dataset

1000 rows x 10 columns→Load raw data with features and labels→1000 rows x 10 columns

Feature row: [0.5, 1.2, ..., 0.3], Label: 1

↓

2Train/Test Split

1000 rows x 10 columns→Split data into training (80%) and validation (20%) sets→Train: 800 rows x 10 columns, Validation: 200 rows x 10 columns

Train sample: [0.4, 1.0, ..., 0.2], Label: 0

↓

3Data Normalization

Train: 800 rows x 10 columns→Scale features to zero mean and unit variance→Train: 800 rows x 10 columns (normalized)

Normalized feature row: [-0.1, 0.3, ..., 0.0]

↓

4Model Training

Train: 800 rows x 10 columns→Feed features to model and update weights using training loss→Model parameters updated

Batch input: 32 rows x 10 columns

↓

5Validation Evaluation

Validation: 200 rows x 10 columns→Evaluate model on validation set to compute validation loss→Validation loss scalar

Validation batch input: 32 rows x 10 columns

Training Trace - Epoch by Epoch

Loss
0.9 |*       
0.8 | *      
0.7 |  *     
0.6 |   *    
0.5 |    *   
0.4 |     *  
0.3 |      * 
    +--------
     1 2 3 4 5 Epochs

Epoch	Loss ↓	Accuracy ↑	Observation
1	0.85	0.60	Training loss starts high, accuracy moderate
2	0.65	0.72	Loss decreases, accuracy improves
3	0.50	0.80	Model learns well, loss drops further
4	0.40	0.85	Training loss continues to decrease
5	0.35	0.88	Training loss low, accuracy high

Prediction Trace - 4 Layers

Layer 1: Input Layer

Layer 2: Hidden Layer (ReLU)

Layer 3: Output Layer (Sigmoid)

Layer 4: Loss Calculation

Model Quiz - 3 Questions

Why do we track validation loss during training?

A To check if the model is learning patterns that generalize

B To increase training speed

C To reduce the size of the dataset

D To make the model more complex

Key Insight

Tracking both training and validation loss helps us understand if the model is learning well and generalizing to new data, preventing overfitting.

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