Early stopping implementation in PyTorch - Practice Problems & Coding Challenges

Challenge - 5 Problems

❓ Predict Output

intermediate

Output of Early Stopping Check Function

Given the following early stopping check function, what will be the output after calling it with the provided inputs?

PyTorch

def early_stopping_check(val_loss, best_loss, patience_counter, patience):
    if val_loss < best_loss:
        best_loss = val_loss
        patience_counter = 0
        return True, best_loss, patience_counter
    else:
        patience_counter += 1
        if patience_counter >= patience:
            return False, best_loss, patience_counter
        else:
            return True, best_loss, patience_counter

best_loss = 0.5
patience_counter = 2
patience = 3
val_loss = 0.6

result = early_stopping_check(val_loss, best_loss, patience_counter, patience)
print(result)

A (False, 0.6, 3)

B (True, 0.5, 3)

C (False, 0.5, 3)

D (True, 0.6, 0)

💡 Hint

Think about what happens when validation loss does not improve and patience counter reaches the limit.

The validation loss (0.6) is not less than the best loss (0.5), so patience_counter increments from 2 to 3. Since patience is 3, the function returns False to stop training.

❓ Model Choice

intermediate

Choosing Early Stopping Patience Value

You are training a neural network and want to use early stopping. Which patience value is most suitable to avoid stopping too early but still prevent overfitting?

A Patience = 5 (stop after 5 bad epochs)

B Patience = 50 (stop after 50 bad epochs)

C Patience = 1 (stop after 1 bad epoch)

D Patience = 0 (stop immediately on first bad epoch)

💡 Hint

Consider a balance between giving the model time to improve and avoiding wasting time on no improvement.

A patience of 5 allows the model some room to improve after a bad epoch but stops training before wasting too much time.

🔧 Debug

advanced

Debugging Early Stopping Implementation

The following early stopping code does not stop training even when validation loss stops improving. What is the bug?

PyTorch

class EarlyStopping:
    def __init__(self, patience=3):
        self.patience = patience
        self.counter = 0
        self.best_loss = float('inf')
        self.early_stop = False

    def __call__(self, val_loss):
        if val_loss >= self.best_loss:
            self.counter += 1
            if self.counter >= self.patience:
                self.early_stop = True
        else:
            self.best_loss = val_loss
            self.counter = 0

# Usage example
es = EarlyStopping(patience=2)
losses = [0.5, 0.4, 0.45, 0.46, 0.47]
for loss in losses:
    es(loss)
print(es.early_stop)

A The early_stop flag is never set to True

B The best_loss is never updated, so early_stop never triggers

C The counter is reset incorrectly inside the else block

D The condition should be val_loss >= self.best_loss instead of val_loss > self.best_loss

💡 Hint

Think about what happens when val_loss equals best_loss.

If val_loss equals best_loss, the counter does not increment, so early stopping may never trigger. Changing > to >= fixes this.

❓ Metrics

advanced

Interpreting Early Stopping Training Logs

During training with early stopping, the validation loss values per epoch are: [0.6, 0.55, 0.54, 0.54, 0.55, 0.56, 0.57]. If patience is set to 2, at which epoch will training stop?

A After epoch 6

B Training will not stop early

C After epoch 7

D After epoch 5

💡 Hint

Count how many consecutive epochs the validation loss does not improve.

Validation loss stops improving after epoch 3 (0.54). It stays the same at epoch 4, then worsens at epochs 5 and 6. After 2 bad epochs (5 and 6), training stops.

🧠 Conceptual

expert

Why Use Early Stopping in Model Training?

Which of the following best explains the main reason to use early stopping during training of machine learning models?

A To reduce training time by stopping as soon as training loss decreases

B To prevent overfitting by stopping training when validation loss stops improving

C To increase model complexity by training longer

D To ensure the model reaches zero training loss

💡 Hint

Think about the difference between training loss and validation loss.

Early stopping monitors validation loss to stop training before the model starts overfitting the training data.

Practice

1. What is the main purpose of early stopping in PyTorch training?

easy

A. To increase the training batch size automatically

B. To stop training when validation loss stops improving

C. To save the model weights after every epoch

D. To shuffle the training data before each epoch

Solution

1. Step 1: Understand early stopping concept

   Early stopping is used to stop training early if the model stops improving on validation data.

2. Step 2: Identify the correct purpose

   Among the options, only stopping training when validation loss stops improving matches early stopping's goal.

3. Final Answer:

   To stop training when validation loss stops improving -> Option B

4. Quick Check:

   Early stopping = stop training on no validation improvement [OK]

Hint: Early stopping stops training on no validation loss improvement [OK]

Common Mistakes:

• Confusing early stopping with batch size changes
• Thinking early stopping saves model weights every epoch
• Mixing early stopping with data shuffling

2. Which of the following is the correct way to initialize an early stopping object in PyTorch with patience 5 and min_delta 0.01?

easy

A. early_stopping = EarlyStopping(patience=0.01, min_delta=5)

B. early_stopping = EarlyStopping(min_delta=5, patience=0.01)

C. early_stopping = EarlyStopping(patience=5, min_delta=0.01)

D. early_stopping = EarlyStopping(5, 0.01)

Solution

1. Step 1: Check parameter names and values

   Patience should be an integer (5), min_delta a small float (0.01).

2. Step 2: Match correct argument order and names

   early_stopping = EarlyStopping(patience=5, min_delta=0.01) uses correct named arguments with proper values; others swap or misuse them.

3. Final Answer:

   early_stopping = EarlyStopping(patience=5, min_delta=0.01) -> Option C

4. Quick Check:

   Correct param names and values = early_stopping = EarlyStopping(patience=5, min_delta=0.01) [OK]

Hint: Use named arguments with correct types for early stopping [OK]

Common Mistakes:

• Swapping patience and min_delta values
• Using positional args without clarity
• Passing wrong data types for parameters

3. Given this snippet, what will be printed after 4 epochs if validation losses are [0.5, 0.4, 0.42, 0.43] and patience=2?

early_stopping = EarlyStopping(patience=2, min_delta=0.01)
for epoch, val_loss in enumerate([0.5, 0.4, 0.42, 0.43]):
    early_stopping(val_loss)
    if early_stopping.early_stop:
        print(f"Stop at epoch {epoch}")
        break

medium

A. Stop at epoch 3

B. Stop at epoch 2

C. No stop, training continues

D. Stop at epoch 1

Solution

1. Step 1: Track validation loss improvements

   Loss improves from 0.5 to 0.4 (improvement 0.1 > 0.01), then worsens 0.4 to 0.42 (no improvement), then 0.42 to 0.43 (no improvement).

2. Step 2: Apply patience logic

   Patience=2 means stop if no improvement for 2 consecutive epochs. However, min_delta=0.01 means improvement must be at least 0.01 to reset patience. The increases from 0.4 to 0.42 and 0.42 to 0.43 are less than min_delta, so they count as no improvement. But patience=2 allows 2 such epochs before stopping. After epoch 3, patience is exhausted, so early stopping triggers at epoch 3. But since the loop breaks after printing, the print statement occurs at epoch 3.

3. Step 3: Check code behavior

   The code prints "Stop at epoch 3" and breaks.

4. Final Answer:

   Stop at epoch 3 -> Option A

5. Quick Check:

   Patience 2 triggers stop after 2 bad epochs [OK]

Hint: Count consecutive no-improvement epochs to patience limit [OK]

Common Mistakes:

• Stopping too early after 1 bad epoch
• Ignoring min_delta threshold
• Assuming stop only after patience+1 epochs

4. Identify the bug in this early stopping usage:

early_stopping = EarlyStopping(patience=3, min_delta=0.01)
for val_loss in val_losses:
    if early_stopping.early_stop:
        break
    early_stopping(val_loss)

medium

A. val_losses should be a tensor, not a list

B. patience value is too high

C. min_delta should be zero

D. Check for early_stop before calling early_stopping(val_loss)

Solution

1. Step 1: Analyze loop order

   The code checks early_stop before updating early_stopping with current val_loss, so it misses stopping at the right time.

2. Step 2: Correct order for early stopping check

   Call early_stopping(val_loss) first to update state, then check early_stop to break if needed.

3. Final Answer:

   Check for early_stop before calling early_stopping(val_loss) -> Option D

4. Quick Check:

   Update early stopping before checking early_stop flag [OK]

Hint: Call early_stopping(val_loss) before checking early_stop [OK]

Common Mistakes:

• Checking early_stop before updating with new loss
• Misunderstanding patience and min_delta roles
• Assuming val_losses must be tensors

5. You want to implement early stopping that only triggers if validation loss improves by at least 0.005 within 4 epochs. Which settings for patience and min_delta should you use?

hard

A. patience=4, min_delta=0.005

B. patience=0.005, min_delta=4

C. patience=4, min_delta=0.05

D. patience=5, min_delta=0.005

Solution

1. Step 1: Understand patience and min_delta roles

   Patience is how many epochs to wait for improvement; min_delta is minimum improvement size.

2. Step 2: Match requirement to parameters

   To trigger after 4 epochs without improvement of at least 0.005, set patience=4 and min_delta=0.005.

3. Final Answer:

   patience=4, min_delta=0.005 -> Option A

4. Quick Check:

   Patience=4 and min_delta=0.005 matches requirement [OK]

Hint: Patience = epochs to wait; min_delta = minimum improvement size [OK]

Common Mistakes:

• Swapping patience and min_delta values
• Using too large min_delta to detect small improvements
• Setting patience too low to wait enough epochs