Gradient clipping in PyTorch - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to clip gradients by norm before optimizer step.

PyTorch

torch.nn.utils.clip_grad_norm_(model.parameters(), [1])
optimizer.step()

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

A0.1

B10.0

C1.0

D0.01

Attempts:

3 left

💡 Hint

Common Mistakes

Using zero or negative values for max norm.

Using very large values that don't clip gradients effectively.

Gradient clipping by norm is commonly done with a max norm value like 1.0 to prevent exploding gradients.

2fill in blank

medium

Complete the code to clip gradients by value before optimizer step.

PyTorch

torch.nn.utils.clip_grad_value_(model.parameters(), [1])
optimizer.step()

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

A5

B0.5

C0.05

D10

Attempts:

3 left

💡 Hint

Common Mistakes

Using values too small that zero out gradients.

Using negative values which cause errors.

Gradient clipping by value limits each gradient element to a max absolute value, often a small integer like 5.

3fill in blank

hard

Fix the error in the code to properly clip gradients by norm.

PyTorch

torch.nn.utils.clip_grad_norm_(model.parameters(), [1])
optimizer.step()

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

A1.0

Bmax_norm

Cmax_norm=1.0

Dclip_value

Attempts:

3 left

💡 Hint

Common Mistakes

Passing variable names instead of values.

Using keyword arguments incorrectly.

The function expects a float value for max norm, not a variable name or keyword argument.

4fill in blank

hard

Fill both blanks to clip gradients by norm and then zero gradients.

PyTorch

torch.nn.utils.clip_grad_norm_(model.parameters(), [1])
optimizer.[2]()

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

A1.0

Bzero_grad

Cstep

Dclip_grad_norm_

Attempts:

3 left

💡 Hint

Common Mistakes

Calling step() before zero_grad().

Using wrong method names.

First clip gradients by norm 1.0, then clear gradients with zero_grad() before next step.

5fill in blank

hard

Fill all three blanks to clip gradients by value, perform optimizer step, and zero gradients.

PyTorch

torch.nn.utils.clip_grad_value_(model.parameters(), [1])
optimizer.[2]()
optimizer.[3]()

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

A0.5

Bstep

Czero_grad

Dclip_grad_value_

Attempts:

3 left

💡 Hint

Common Mistakes

Mixing up step and zero_grad order.

Using wrong clip values.

Clip gradients by value 0.5, then call optimizer.step() to update weights, and zero_grad() to clear gradients.

Practice

1. What is the main purpose of gradient clipping in PyTorch training?

easy

A. To prevent gradients from becoming too large and destabilizing training

B. To increase the learning rate automatically during training

C. To save memory by reducing model size

D. To initialize model weights before training

Solution

1. Step 1: Understand gradient behavior during training

   Gradients can sometimes become very large, causing unstable updates and training divergence.

2. Step 2: Role of gradient clipping

   Gradient clipping limits the size of gradients to keep training stable and prevent exploding gradients.

3. Final Answer:

   To prevent gradients from becoming too large and destabilizing training -> Option A

4. Quick Check:

   Gradient clipping = prevent large gradients [OK]

Hint: Gradient clipping stops gradients from exploding during training [OK]

Common Mistakes:

• Thinking it changes learning rate
• Confusing with weight initialization
• Believing it reduces model size

2. Which PyTorch function is used to clip gradients by their norm?

easy

A. torch.optim.clip_grad_norm

B. torch.nn.utils.clip_grad_value_

C. torch.nn.utils.clip_grad_norm_

D. torch.clip_gradients

Solution

1. Step 1: Recall PyTorch gradient clipping functions

   PyTorch provides two main functions: clip_grad_norm_ and clip_grad_value_ in torch.nn.utils.

2. Step 2: Identify function for norm clipping

   clip_grad_norm_ clips gradients based on their total norm, while clip_grad_value_ clips individual gradient values.

3. Final Answer:

   torch.nn.utils.clip_grad_norm_ -> Option C

4. Quick Check:

   Norm clipping function = clip_grad_norm_ [OK]

Hint: clip_grad_norm_ clips total gradient size by norm [OK]

Common Mistakes:

• Using clip_grad_value_ for norm clipping
• Assuming optimizer has clipping functions
• Using non-existent torch.clip_gradients

3. What will be the output of the following code snippet?

import torch
from torch.nn.utils import clip_grad_norm_

model = torch.nn.Linear(2, 1)
optimizer = torch.optim.SGD(model.parameters(), lr=0.1)

inputs = torch.tensor([[1.0, 2.0]])
target = torch.tensor([[1.0]])

optimizer.zero_grad()
output = model(inputs)
loss = (output - target).pow(2).mean()
loss.backward()
clip_grad_norm_(model.parameters(), max_norm=0.1)
for p in model.parameters():
    print(p.grad.norm().item())

medium

A. Code will raise an error because clip_grad_norm_ is called before backward()

B. Gradient norms will be unchanged and possibly larger than 0.1

C. Gradients will be zero because of clipping

D. All printed gradient norms will be less than or equal to 0.1

Solution

1. Step 1: Understand code flow and gradient clipping

   Gradients are computed by loss.backward(), then clipped by clip_grad_norm_ with max_norm=0.1.

2. Step 2: Effect of clip_grad_norm_ on gradients

   clip_grad_norm_ rescales gradients so their total norm does not exceed 0.1, so printed norms will be ≤ 0.1.

3. Final Answer:

   All printed gradient norms will be less than or equal to 0.1 -> Option D

4. Quick Check:

   clip_grad_norm_ limits gradient norm ≤ max_norm [OK]

Hint: clip_grad_norm_ rescales gradients after backward [OK]

Common Mistakes:

• Calling clip_grad_norm_ before backward()
• Expecting gradients to be zero after clipping
• Thinking clipping increases gradient norms

4. Identify the error in this PyTorch training snippet using gradient clipping:

optimizer.zero_grad()
output = model(data)
loss = criterion(output, target)
clip_grad_norm_(model.parameters(), max_norm=1.0)
loss.backward()
optimizer.step()

medium

A. clip_grad_norm_ should be called after optimizer.step()

B. clip_grad_norm_ is called before loss.backward(), so gradients are not clipped

C. max_norm should be set to 0, not 1.0

D. optimizer.zero_grad() should be called after optimizer.step()

Solution

1. Step 1: Check order of operations for gradient clipping

   Gradients are created by loss.backward(), so clipping must happen after backward() to affect gradients.

2. Step 2: Identify mistake in code order

   clip_grad_norm_ is called before loss.backward(), so gradients do not exist yet and clipping has no effect.

3. Final Answer:

   clip_grad_norm_ is called before loss.backward(), so gradients are not clipped -> Option B

4. Quick Check:

   Clip gradients after backward() [OK]

Hint: Always clip gradients after backward(), before optimizer.step() [OK]

Common Mistakes:

• Clipping before backward()
• Calling zero_grad() after step()
• Setting max_norm to zero

5. You want to prevent exploding gradients in a deep RNN model. Which approach correctly applies gradient clipping in PyTorch during training?

hard

A. After loss.backward(), call torch.nn.utils.clip_grad_norm_(model.parameters(), max_norm=5), then optimizer.step()

B. Before loss.backward(), call torch.nn.utils.clip_grad_norm_(model.parameters(), max_norm=5), then optimizer.step()

C. After optimizer.step(), call torch.nn.utils.clip_grad_norm_(model.parameters(), max_norm=5)

D. Call torch.nn.utils.clip_grad_value_(model.parameters(), max_norm=5) before loss.backward()

Solution

1. Step 1: Understand correct gradient clipping sequence

   Gradients are computed by loss.backward(), so clipping must happen after this step and before optimizer.step().

2. Step 2: Identify correct function and order

   clip_grad_norm_ is used to clip by norm, suitable for RNNs to prevent exploding gradients. It must be called after backward() and before optimizer.step().

3. Final Answer:

   After loss.backward(), call torch.nn.utils.clip_grad_norm_(model.parameters(), max_norm=5), then optimizer.step() -> Option A

4. Quick Check:

   Clip gradients after backward(), before step() [OK]

Hint: Clip gradients after backward(), before optimizer step [OK]

Common Mistakes:

• Clipping before backward()
• Clipping after optimizer.step()
• Using clip_grad_value_ incorrectly