CosineAnnealingLR in PyTorch - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to create a CosineAnnealingLR scheduler with 10 epochs.

PyTorch

scheduler = torch.optim.lr_scheduler.[1](optimizer, T_max=10)

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

ACosineAnnealingLR

BReduceLROnPlateau

CExponentialLR

DStepLR

Attempts:

3 left

💡 Hint

Common Mistakes

Choosing StepLR or ExponentialLR instead of CosineAnnealingLR.

The CosineAnnealingLR scheduler adjusts the learning rate following a cosine curve over T_max epochs.

2fill in blank

medium

Complete the code to update the learning rate scheduler after each epoch.

PyTorch

for epoch in range(20):
    train()
    validate()
    [1]

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

Aoptimizer.update()

Bscheduler.update()

Coptimizer.step()

Dscheduler.step()

Attempts:

3 left

💡 Hint

Common Mistakes

Calling optimizer.step() instead of scheduler.step().

Using a non-existent scheduler.update() method.

After each epoch, call scheduler.step() to update the learning rate according to the cosine annealing schedule.

3fill in blank

hard

Fix the error in the scheduler initialization to correctly set the minimum learning rate to 0.001.

PyTorch

scheduler = torch.optim.lr_scheduler.CosineAnnealingLR(optimizer, T_max=50, [1]=0.001)

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

Aeta_min

Bmin_lr

Cmin_learning_rate

Dlr_min

Attempts:

3 left

💡 Hint

Common Mistakes

Using min_lr or min_learning_rate which are invalid parameters.

The correct parameter to set the minimum learning rate in CosineAnnealingLR is eta_min.

4fill in blank

hard

Fill both blanks to create a scheduler that restarts every 30 epochs and sets minimum learning rate to 0.

PyTorch

scheduler = torch.optim.lr_scheduler.[1](optimizer, T_max=[2], eta_min=0)

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

ACosineAnnealingLR

BStepLR

C30

D50

Attempts:

3 left

💡 Hint

Common Mistakes

Using StepLR instead of CosineAnnealingLR.

Setting T_max to 50 instead of 30.

Use CosineAnnealingLR with T_max=30 to restart the cosine annealing every 30 epochs.

5fill in blank

hard

Fill all three blanks to print the learning rate at each epoch during training with CosineAnnealingLR.

PyTorch

for epoch in range(40):
    train()
    validate()
    scheduler.[1]()
    lr = scheduler.optimizer.param_groups[[2]]['[3]']
    print(f"Epoch {epoch+1}: lr = {lr}")

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

Astep

B0

Clr

Dzero

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'zero' instead of 'lr' as the key.

Accessing param_groups[1] which may not exist.

Call scheduler.step() to update the learning rate. The learning rate is stored in param_groups[0]['lr'].