Early stopping implementation in PyTorch - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to initialize the patience parameter for early stopping.

PyTorch

class EarlyStopping:
    def __init__(self, patience=[1]):
        self.patience = patience
        self.counter = 0
        self.best_loss = None
        self.early_stop = False

Drag options to blanks, or click blank then click option'

A5

B0

C-1

DNone

Attempts:

3 left

💡 Hint

Common Mistakes

Setting patience to 0 disables early stopping.

Using None causes errors when comparing patience.

The patience parameter defines how many epochs to wait after the last improvement before stopping.

2fill in blank

medium

Complete the code to update the best loss when a new lower validation loss is found.

PyTorch

def __call__(self, val_loss):
    if self.best_loss is None or val_loss [1] self.best_loss:
        self.best_loss = val_loss
        self.counter = 0
    else:
        self.counter += 1

Drag options to blanks, or click blank then click option'

A>

B<

C==

D>=

Attempts:

3 left

💡 Hint

Common Mistakes

Using > instead of < causes early stopping to trigger incorrectly.

Using == will rarely update best_loss.

We update best_loss only if the current validation loss is less than the best recorded loss.

3fill in blank

hard

Fix the error in the code to set early_stop flag when patience is exceeded.

PyTorch

if self.counter [1] self.patience:
    self.early_stop = True

Drag options to blanks, or click blank then click option'

A<

B<=

C==

D>=

Attempts:

3 left

💡 Hint

Common Mistakes

Using < or <= delays early stopping.

Using == might miss cases when counter exceeds patience.

Early stopping should trigger when the counter is greater than or equal to patience.

4fill in blank

hard

Fill both blanks to complete the early stopping check and reset logic.

PyTorch

def __call__(self, val_loss):
    if self.best_loss is None or val_loss [1] self.best_loss:
        self.best_loss = val_loss
        self.counter = [2]
    else:
        self.counter += 1

Drag options to blanks, or click blank then click option'

A<

B>

C0

D1

Attempts:

3 left

💡 Hint

Common Mistakes

Resetting counter to 1 instead of 0.

Using greater than operator reverses logic.

Reset counter to 0 when a better loss is found, and check if val_loss is less than best_loss.

5fill in blank

hard

Fill all three blanks to complete the early stopping class with call method and flag update.

PyTorch

class EarlyStopping:
    def __init__(self, patience=[1]):
        self.patience = patience
        self.counter = 0
        self.best_loss = None
        self.early_stop = False

    def __call__(self, val_loss):
        if self.best_loss is None or val_loss [2] self.best_loss:
            self.best_loss = val_loss
            self.counter = [3]
        else:
            self.counter += 1
            if self.counter >= self.patience:
                self.early_stop = True

Drag options to blanks, or click blank then click option'

A5

B<

C0

D>

Attempts:

3 left

💡 Hint

Common Mistakes

Using greater than operator reverses improvement logic.

Not resetting counter causes early stopping to trigger too soon.

The class initializes patience to 5, updates best_loss if val_loss is less, resets counter to 0, and sets early_stop when counter exceeds patience.