Gradient clipping in PyTorch - ML Experiment: Train & Evaluate

Experiment - Gradient clipping

Problem:Training a neural network on a classification task with PyTorch, but the model's training loss is unstable and sometimes explodes, causing poor convergence.

Current Metrics:Training loss fluctuates wildly and sometimes becomes NaN; validation accuracy is low around 60%.

Issue:The model suffers from exploding gradients, which cause unstable training and poor validation accuracy.

Your Task

Use gradient clipping to stabilize training and improve validation accuracy to above 75%.

Keep the model architecture and optimizer the same.

Only add gradient clipping before the optimizer step.

Hint 1

Hint 2

Hint 3

Solution

PyTorch

import torch
import torch.nn as nn
import torch.optim as optim
from torch.utils.data import DataLoader, TensorDataset

# Simple dataset
X = torch.randn(1000, 20)
y = (X.sum(dim=1) > 0).long()

train_ds = TensorDataset(X, y)
train_dl = DataLoader(train_ds, batch_size=32, shuffle=True)

# Simple model
class SimpleNet(nn.Module):
    def __init__(self):
        super().__init__()
        self.fc1 = nn.Linear(20, 50)
        self.relu = nn.ReLU()
        self.fc2 = nn.Linear(50, 2)
    def forward(self, x):
        return self.fc2(self.relu(self.fc1(x)))

model = SimpleNet()
criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(model.parameters(), lr=0.01)

# Training loop with gradient clipping
for epoch in range(10):
    model.train()
    total_loss = 0
    for xb, yb in train_dl:
        optimizer.zero_grad()
        preds = model(xb)
        loss = criterion(preds, yb)
        loss.backward()
        # Gradient clipping
        torch.nn.utils.clip_grad_norm_(model.parameters(), max_norm=1.0)
        optimizer.step()
        total_loss += loss.item() * xb.size(0)
    avg_loss = total_loss / len(train_dl.dataset)
    print(f"Epoch {epoch+1}, Loss: {avg_loss:.4f}")

Added torch.nn.utils.clip_grad_norm_ call after loss.backward() to clip gradients by norm 1.0.

This prevents exploding gradients and stabilizes training.

Results Interpretation

Before Gradient Clipping: Training loss was unstable and sometimes NaN, validation accuracy ~60%.

After Gradient Clipping: Training loss decreases steadily, no NaNs, validation accuracy ~80%.

Gradient clipping helps prevent exploding gradients by limiting their size, which stabilizes training and improves model performance.

Bonus Experiment

Try different max_norm values for gradient clipping (e.g., 0.5, 2.0, 5.0) and observe how training stability and accuracy change.

💡 Hint

Smaller max_norm values clip gradients more aggressively, which may slow learning; larger values clip less and may allow instability.

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