Warmup strategies in PyTorch - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to create a linear warmup scheduler for the optimizer.

PyTorch

from torch.optim.lr_scheduler import LambdaLR
optimizer = torch.optim.Adam(model.parameters(), lr=0.001)
warmup_scheduler = LambdaLR(optimizer, lr_lambda=lambda step: step / [1] if step < 100 else 1)

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

A50

B10

C200

D100

Attempts:

3 left

💡 Hint

Common Mistakes

Using a denominator different from the warmup steps length.

Forgetting to set the learning rate to 1 after warmup.

The warmup scheduler increases the learning rate linearly until step 100, so the denominator must be 100.

2fill in blank

medium

Complete the code to apply a cosine warmup schedule with 50 warmup steps.

PyTorch

def cosine_warmup(step):
    if step < [1]:
        return step / 50
    else:
        return 0.5 * (1 + math.cos(math.pi * (step - 50) / (total_steps - 50)))

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

A25

B50

C100

D10

Attempts:

3 left

💡 Hint

Common Mistakes

Using the wrong number of warmup steps in the condition.

Not matching the denominator with the warmup steps.

The warmup phase is 50 steps, so the condition checks if step < 50.

3fill in blank

hard

Fix the error in the warmup scheduler code to correctly update the learning rate.

PyTorch

for epoch in range(epochs):
    for step, batch in enumerate(dataloader):
        optimizer.zero_grad()
        loss = model(batch)
        loss.backward()
        optimizer.step()
        scheduler.[1]()

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

Astep()

Bstep

Cstep_step

Dstep_step()

Attempts:

3 left

💡 Hint

Common Mistakes

Calling scheduler.step without parentheses.

Using an incorrect method name.

The scheduler's step method must be called as a function with parentheses: scheduler.step()

4fill in blank

hard

Fill both blanks to create a warmup scheduler that multiplies the learning rate by a factor during warmup and then decays it.

PyTorch

def warmup_decay(step):
    if step < [1]:
        return [2] * step
    else:
        return 0.1

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

A0.01

B100

C50

D0.1

Attempts:

3 left

💡 Hint

Common Mistakes

Confusing the warmup steps with the decay factor.

Using the decay factor in place of the warmup multiplier.

The warmup lasts 50 steps, and the learning rate is multiplied by 0.01 times the step during warmup.

5fill in blank

hard

Fill all three blanks to create a dictionary comprehension that maps each epoch to its learning rate using warmup and decay.

PyTorch

lr_schedule = {epoch: ([1] * epoch if epoch < [2] else [3]) for epoch in range(1, 101)}

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

A0.02

B50

C0.001

D100

Attempts:

3 left

💡 Hint

Common Mistakes

Mixing up the warmup length and decay learning rate.

Using incorrect multipliers for learning rate.

During warmup (first 50 epochs), learning rate increases by 0.02 * epoch; after that, it decays to 0.001.

Practice

1. What is the main purpose of using a warmup strategy in PyTorch training?

easy

A. To immediately set the learning rate to its maximum value

B. To gradually increase the learning rate at the start of training

C. To decrease the learning rate throughout the entire training

D. To freeze model weights during the first epochs

Solution

1. Step 1: Understand what warmup means

   Warmup means starting with a low learning rate and increasing it slowly.

2. Step 2: Identify the goal of warmup

   This helps the model learn smoothly and avoid sudden big updates that can harm training.

3. Final Answer:

   To gradually increase the learning rate at the start of training -> Option B

4. Quick Check:

   Warmup = gradual learning rate increase [OK]

Hint: Warmup means slowly raising learning rate early [OK]

Common Mistakes:

• Thinking warmup immediately sets max learning rate
• Confusing warmup with learning rate decay
• Assuming warmup freezes model weights

2. Which PyTorch class is commonly used to implement a warmup learning rate schedule with a custom function?

easy

A. torch.optim.lr_scheduler.StepLR

B. torch.optim.lr_scheduler.ReduceLROnPlateau

C. torch.optim.lr_scheduler.LambdaLR

D. torch.optim.lr_scheduler.ExponentialLR

Solution

1. Step 1: Recall PyTorch schedulers for warmup

   LambdaLR allows defining a custom function to adjust learning rate.

2. Step 2: Match scheduler to warmup use

   Warmup needs a custom function to increase learning rate gradually, which LambdaLR supports.

3. Final Answer:

   torch.optim.lr_scheduler.LambdaLR -> Option C

4. Quick Check:

   Custom function scheduler = LambdaLR [OK]

Hint: LambdaLR lets you define custom learning rate changes [OK]

Common Mistakes:

• Choosing StepLR which uses fixed step decay
• Picking ReduceLROnPlateau which reacts to metrics
• Selecting ExponentialLR which decays exponentially

3. Given the following PyTorch code snippet, what will be the learning rate at epoch 3?

import torch
optimizer = torch.optim.SGD([torch.nn.Parameter(torch.randn(2, 2))], lr=0.1)

warmup_epochs = 5
scheduler = torch.optim.lr_scheduler.LambdaLR(optimizer, lr_lambda=lambda epoch: min((epoch + 1) / warmup_epochs, 1))

for epoch in range(5):
    scheduler.step()
    print(f"Epoch {epoch+1} LR: {optimizer.param_groups[0]['lr']}")

medium

A. 0.06

B. 0.03

C. 0.10

D. 0.50

Solution

1. Step 1: Understand the lambda function for LR

   The lambda function returns (epoch+1)/5 until it reaches 1, scaling the base LR 0.1.

2. Step 2: Calculate LR at epoch 3 (0-based index)

   Epoch 3 means epoch=2, so LR factor = (2+1)/5 = 3/5 = 0.6. LR = 0.1 * 0.6 = 0.06.

3. Final Answer:

   0.06 -> Option A

4. Quick Check:

   Epoch 3 LR = 0.1 * 3/5 = 0.06 [OK]

Hint: Multiply base LR by (epoch+1)/warmup_epochs [OK]

Common Mistakes:

• Using epoch number directly without +1
• Confusing epoch index with count
• Assuming LR is constant during warmup

4. Identify the error in this PyTorch warmup scheduler code:

import torch
optimizer = torch.optim.Adam([torch.nn.Parameter(torch.randn(2, 2))], lr=0.01)
warmup_epochs = 3
scheduler = torch.optim.lr_scheduler.LambdaLR(optimizer, lr_lambda=lambda epoch: epoch / warmup_epochs)

for epoch in range(5):
    scheduler.step()
    print(f"Epoch {epoch} LR: {optimizer.param_groups[0]['lr']}")

medium

A. The optimizer should be SGD, not Adam

B. scheduler.step() should be called after optimizer.step()

C. The learning rate is not scaled by base LR

D. The lambda function returns 0 at epoch 0 causing zero LR

Solution

1. Step 1: Analyze lambda function behavior at epoch 0

   At epoch 0, lambda returns 0/3 = 0, so LR is zero, which stops learning initially.

2. Step 2: Understand why zero LR is a problem

   Zero LR means no weight updates, which can slow or stop training progress early.

3. Final Answer:

   The lambda function returns 0 at epoch 0 causing zero LR -> Option D

4. Quick Check:

   Epoch 0 LR = 0 causes no learning [OK]

Hint: Check if lambda returns zero at first epoch [OK]

Common Mistakes:

• Ignoring zero LR at start
• Thinking optimizer type causes error
• Confusing scheduler step order

5. You want to implement a warmup strategy that linearly increases the learning rate from 0 to 0.1 over 4 epochs, then keeps it constant. Which lr_lambda function correctly achieves this in PyTorch's LambdaLR?

hard

A. lambda epoch: min((epoch + 1) / 4, 1)

B. lambda epoch: epoch / 4

C. lambda epoch: 1 if epoch >= 4 else 0.1 * epoch

D. lambda epoch: (epoch + 1) * 0.1

Solution

1. Step 1: Understand the warmup goal

   Learning rate should increase linearly from 0 to 1 (scale factor) over 4 epochs, then stay at 1.

2. Step 2: Check each lambda function

   lambda epoch: min((epoch + 1) / 4, 1) uses min((epoch+1)/4, 1), which linearly increases from 0.25 to 1 by epoch 4, then stays at 1.

3. Final Answer:

   lambda epoch: min((epoch + 1) / 4, 1) -> Option A

4. Quick Check:

   Linear increase capped at 1 = lambda epoch: min((epoch + 1) / 4, 1) [OK]

Hint: Use min((epoch+1)/warmup_epochs, 1) for linear warmup [OK]

Common Mistakes:

• Not adding +1 to epoch causing zero start
• Multiplying by 0.1 inside lambda instead of base LR
• Using step function instead of linear increase