Learning rate differential in PyTorch - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to set the learning rate for the optimizer.

PyTorch

optimizer = torch.optim.SGD(model.parameters(), lr=[1])

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

A1.0

B0.1

C0.01

D10

Attempts:

3 left

💡 Hint

Common Mistakes

Using a learning rate that is too large, causing unstable training.

Using an integer instead of a decimal for learning rate.

The learning rate is set to 0.01, which is a common small value to start training.

2fill in blank

medium

Complete the code to create two parameter groups with different learning rates.

PyTorch

optimizer = torch.optim.Adam([
    {'params': model.base.parameters(), 'lr': [1],
    {'params': model.head.parameters(), 'lr': 0.01}
])

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

A0.05

B0.1

D0.001

Attempts:

3 left

💡 Hint

Common Mistakes

Setting both learning rates the same defeats the purpose of differential learning rates.

Using too large learning rate for base parameters.

The base model uses a smaller learning rate 0.001, while the head uses 0.01 for faster learning.

3fill in blank

hard

Fix the error in the learning rate scheduler step call.

PyTorch

scheduler = torch.optim.lr_scheduler.StepLR(optimizer, step_size=10, gamma=0.1)
for epoch in range(20):
    train()
    validate()
    [1]

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

Ascheduler.step()

Bscheduler.update()

Cscheduler.step(epoch)

Dscheduler.step(10)

Attempts:

3 left

💡 Hint

Common Mistakes

Passing an argument to step() causes errors.

Using a non-existent method like update().

The scheduler.step() method is called without arguments to update the learning rate after each epoch.

4fill in blank

hard

Fill both blanks to create a dictionary of learning rates for different layers.

PyTorch

lr_dict = {
    'base': [1],
    'head': [2]
}

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

A0.001

B0.01

C0.1

D0.0001

Attempts:

3 left

💡 Hint

Common Mistakes

Using the same learning rate for both layers.

Choosing too large learning rates for base layers.

The base layer uses 0.001 and the head uses 0.01 as learning rates for differential training.

5fill in blank

hard

Fill all three blanks to define optimizer with differential learning rates and weight decay.

PyTorch

optimizer = torch.optim.Adam([
    {'params': model.backbone.parameters(), 'lr': [1], 'weight_decay': [2],
    {'params': model.classifier.parameters(), 'lr': [3], 'weight_decay': 0.01}
])

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

A0.0005

B0.001

C0.0001

D0.0003

Attempts:

3 left

💡 Hint

Common Mistakes

Mixing up learning rates and weight decay values.

Using too large learning rates causing unstable training.

The backbone uses learning rate 0.0001 with weight decay 0.001, classifier uses 0.0003 learning rate and 0.01 weight decay.

Practice

1. What does learning rate differential mean in PyTorch training?

easy

A. Changing the learning rate randomly during training

B. Setting different learning rates for different parts of a model

C. Using the same learning rate for the entire model

D. Freezing all model layers during training

Solution

1. Step 1: Understand learning rate concept

   The learning rate controls how fast a model updates its knowledge during training.

2. Step 2: Define learning rate differential

   Learning rate differential means assigning different learning rates to different parts of the model to control their update speed.

3. Final Answer:

   Setting different learning rates for different parts of a model -> Option B

4. Quick Check:

   Learning rate differential = Different rates per model part [OK]

Hint: Different parts can learn at different speeds [OK]

Common Mistakes:

• Thinking learning rate is always the same for all layers
• Confusing learning rate differential with random rate changes
• Believing freezing layers means changing learning rate

2. Which PyTorch code snippet correctly sets different learning rates for two parameter groups?

easy

A. optimizer = torch.optim.SGD(model.parameters(), lr=0.01, lr2=0.001)

B. optimizer = torch.optim.SGD(model.parameters(), lr=[0.01, 0.001])

C. optimizer = torch.optim.SGD([{'params': model.layer1.parameters(), 'lr': 0.01}, {'params': model.layer2.parameters(), 'lr': 0.001}], momentum=0.9)

D. optimizer = torch.optim.SGD([model.layer1, model.layer2], lr=0.01)

Solution

1. Step 1: Check PyTorch optimizer syntax for param groups

   PyTorch allows passing a list of dicts with 'params' and 'lr' keys to set different learning rates.

2. Step 2: Identify correct syntax

   optimizer = torch.optim.SGD([{'params': model.layer1.parameters(), 'lr': 0.01}, {'params': model.layer2.parameters(), 'lr': 0.001}], momentum=0.9) correctly uses a list of dicts with separate learning rates for layer1 and layer2 parameters.

3. Final Answer:

   optimizer = torch.optim.SGD([{'params': model.layer1.parameters(), 'lr': 0.01}, {'params': model.layer2.parameters(), 'lr': 0.001}], momentum=0.9) -> Option C

4. Quick Check:

   Param groups with separate 'lr' keys = Correct syntax [OK]

Hint: Use list of dicts with 'params' and 'lr' keys [OK]

Common Mistakes:

• Passing lr as a list directly to optimizer
• Using unknown keyword like lr2
• Passing layers instead of parameters

3. Given this code, what is the learning rate for model.layer2 during training?

optimizer = torch.optim.Adam([
  {'params': model.layer1.parameters(), 'lr': 0.005},
  {'params': model.layer2.parameters(), 'lr': 0.0005}
])

medium

A. 0.0005

B. 0.05

C. 0.0055

D. 0.005

Solution

1. Step 1: Identify learning rates assigned to each layer

   Layer1 has lr=0.005, Layer2 has lr=0.0005 as per the optimizer param groups.

2. Step 2: Find learning rate for model.layer2

   From the second dict, model.layer2.parameters() uses lr=0.0005.

3. Final Answer:

   0.0005 -> Option A

4. Quick Check:

   Layer2 lr = 0.0005 from param groups [OK]

Hint: Check param group with layer2 parameters [OK]

Common Mistakes:

• Adding learning rates instead of selecting correct one
• Confusing layer1 lr with layer2 lr
• Assuming default lr overrides param groups

4. Identify the error in this PyTorch optimizer setup for learning rate differential:

optimizer = torch.optim.SGD([
  {'params': model.layer1.parameters(), 'lr': 0.01},
  {'params': model.layer2.parameters()}
], lr=0.001)

medium

A. Missing learning rate for second param group causes error

B. Using lr=0.001 outside param groups is invalid

C. Parameters should be passed as model.layer1, not model.layer1.parameters()

D. SGD optimizer does not support param groups

Solution

1. Step 1: Review param groups and learning rates

   First param group has lr=0.01, second param group has no lr specified.

2. Step 2: Understand default lr behavior

   When param groups are used, each group should have lr or optimizer's lr applies. Here, lr=0.001 is passed but second group lacks explicit lr, causing confusion.

3. Final Answer:

   Missing learning rate for second param group causes error -> Option A

4. Quick Check:

   All param groups need lr or default applies [OK]

Hint: Each param group must have lr or rely on optimizer lr [OK]

Common Mistakes:

• Assuming optimizer lr applies to all param groups automatically
• Passing parameters instead of parameter iterators
• Believing SGD can't use param groups

5. You want to fine-tune a pretrained model by training only the last layer fast and freezing the rest. Which learning rate setup is best?

hard

A. Set same lr=0.01 for all layers

B. Freeze last layer and train others with lr=0.01

C. Set lr=0.01 for all layers except last layer with lr=0

D. Set lr=0 for all layers except last layer with lr=0.01

Solution

1. Step 1: Understand freezing and learning rate

   Freezing means no updates, which can be done by setting lr=0 or disabling gradients.

2. Step 2: Apply learning rate differential for fine-tuning

   Set lr=0 for frozen layers to prevent updates, and higher lr for last layer to train it fast.

3. Final Answer:

   Set lr=0 for all layers except last layer with lr=0.01 -> Option D

4. Quick Check:

   Freeze layers = lr 0, train last layer fast [OK]

Hint: Freeze layers by lr=0, train last layer with higher lr [OK]

Common Mistakes:

• Using same learning rate for all layers when freezing
• Freezing last layer instead of others
• Not setting lr=0 for frozen layers