Training loop structure in PyTorch - Cheat Sheet & Quick Revision

Recall & Review

beginner

What is the main purpose of a training loop in PyTorch?

The training loop repeatedly feeds data to the model, calculates predictions, measures errors, and updates the model to improve its accuracy.

beginner

Name the four key steps inside a typical PyTorch training loop.

1. Forward pass: compute predictions from inputs.
2. Compute loss: measure how wrong predictions are.
3. Backward pass: calculate gradients to learn.
4. Optimizer step: update model parameters to improve.

intermediate

Why do we call optimizer.zero_grad() before backward() in PyTorch?

Because gradients accumulate by default, zero_grad() clears old gradients so only the current batch's gradients are used for updating.

intermediate

What does model.train() do in a PyTorch training loop?

It sets the model to training mode, enabling behaviors like dropout and batch normalization to work correctly during training.

beginner

How can you track model performance during training?

By calculating and printing metrics like loss and accuracy after each batch or epoch to see if the model is improving.

Which PyTorch function computes the gradients during training?

A optimizer.zero_grad()

B loss.backward()

C model.train()

D optimizer.step()

loss.backward() calculates the gradients needed for updating model parameters.

What is the purpose of optimizer.step() in the training loop?

A Update model parameters using gradients

B Reset gradients to zero

C Calculate loss

D Switch model to evaluation mode

optimizer.step() updates the model's parameters based on the gradients computed.

Why do we set model.train() before the training loop?

A To calculate loss

B To disable dropout layers

C To save the model

D To enable training-specific layers like dropout

model.train() enables layers like dropout and batch normalization to behave correctly during training.

What happens if you forget to call optimizer.zero_grad() before backward()?

A Gradients will accumulate, causing incorrect updates

B Gradients will be reset automatically

C Model will not train

D Loss will be zero

Gradients accumulate by default, so forgetting zero_grad() causes wrong gradient sums.

Which of these is NOT part of a typical training loop?

A Forward pass

B Backward pass

C Model evaluation on test data

D Optimizer step

Model evaluation on test data is done outside the training loop, usually after training.

Describe the sequence of operations in a PyTorch training loop and why each step is important.

Think about how the model learns from data step by step.

Explain the role of model.train() and optimizer.zero_grad() in the training loop.

Consider what happens if these are not used.

Practice

1. Which of the following best describes the main purpose of a training loop in PyTorch?

easy

A. To save the model to a file

B. To repeatedly update the model weights to improve performance

C. To visualize the model architecture

D. To load data from disk into memory

Solution

1. Step 1: Understand the training loop role

   The training loop runs many times to adjust model weights based on data.

2. Step 2: Identify the main goal

   Its goal is to improve model performance by updating weights repeatedly.

3. Final Answer:

   To repeatedly update the model weights to improve performance -> Option B

4. Quick Check:

   Training loop = update weights repeatedly [OK]

Hint: Training loop = repeat updates to improve model [OK]

Common Mistakes:

• Confusing data loading with training loop
• Thinking training loop saves model
• Assuming training loop only visualizes model

2. Which of the following is the correct way to zero gradients in a PyTorch training loop?

easy

A. optimizer.zero_grad()

B. model.zero_gradients()

C. loss.zero_grad()

D. torch.zero_grad()

Solution

1. Step 1: Recall PyTorch gradient clearing method

   Gradients are cleared by calling zero_grad() on the optimizer.

2. Step 2: Check each option

   Only optimizer.zero_grad() is the correct PyTorch syntax.

3. Final Answer:

   optimizer.zero_grad() -> Option A

4. Quick Check:

   Clear gradients with optimizer.zero_grad() [OK]

Hint: Clear gradients with optimizer.zero_grad() [OK]

Common Mistakes:

• Calling zero_grad on model or loss
• Using non-existent torch.zero_grad()
• Forgetting to zero gradients before backward pass

3. What will be the output of the following PyTorch training loop snippet?

for epoch in range(2):
    for batch in range(3):
        print(f"Epoch {epoch}, Batch {batch}")

medium

A. Epoch 0, Batch 0
Epoch 0, Batch 1
Epoch 1, Batch 0
Epoch 1, Batch 1

B. Epoch 0, Batch 0
Epoch 1, Batch 0
Epoch 2, Batch 0

C. Epoch 0, Batch 0
Epoch 0, Batch 1
Epoch 0, Batch 2

D. Epoch 0, Batch 0
Epoch 0, Batch 1
Epoch 0, Batch 2
Epoch 1, Batch 0
Epoch 1, Batch 1
Epoch 1, Batch 2

Solution

1. Step 1: Understand loop ranges

   Outer loop runs for epochs 0 and 1 (2 times). Inner loop runs for batches 0,1,2 (3 times).

2. Step 2: Trace output lines

   For each epoch, batches 0 to 2 print, so total 6 lines with epoch and batch numbers.

3. Final Answer:

   Epoch 0, Batch 0 Epoch 0, Batch 1 Epoch 0, Batch 2 Epoch 1, Batch 0 Epoch 1, Batch 1 Epoch 1, Batch 2 -> Option D

4. Quick Check:

   2 epochs x 3 batches = 6 lines printed [OK]

Hint: Multiply epochs by batches for total prints [OK]

Common Mistakes:

• Confusing range end values
• Mixing epoch and batch indices
• Counting fewer batches than loop runs

4. Identify the error in this PyTorch training loop snippet:

for data, target in dataloader:
    optimizer.zero_grad()
    output = model(data)
    loss = criterion(output, target)
    loss.backward
    optimizer.step()

medium

A. Missing parentheses after loss.backward

B. optimizer.zero_grad() should be after optimizer.step()

C. criterion should be called before model(data)

D. optimizer.step() should be called before loss.backward

Solution

1. Step 1: Check method calls

   loss.backward is missing parentheses, so it is not called as a function.

2. Step 2: Verify correct order

   optimizer.zero_grad() is correctly before backward and step; criterion call order is correct; optimizer.step() after backward is correct.

3. Final Answer:

   Missing parentheses after loss.backward -> Option A

4. Quick Check:

   Call loss.backward() with parentheses [OK]

Hint: Always add () to call backward() [OK]

Common Mistakes:

• Forgetting parentheses on backward()
• Changing correct optimizer.zero_grad() position
• Misordering loss and model calls

5. You want to train a model for 5 epochs with batches of size 10. Which of the following training loop structures correctly implements this in PyTorch?

hard

A. for epoch in range(5):
optimizer.zero_grad()
for batch_idx, (data, target) in enumerate(dataloader):
output = model(data)
loss = criterion(output, target)
loss.backward()
optimizer.step()

B. for batch_idx, (data, target) in enumerate(dataloader):
for epoch in range(5):
optimizer.zero_grad()
output = model(data)
loss = criterion(output, target)
loss.backward()
optimizer.step()

C. for epoch in range(5):
for batch_idx, (data, target) in enumerate(dataloader):
optimizer.zero_grad()
output = model(data)
loss = criterion(output, target)
loss.backward()
optimizer.step()

D. for epoch in range(5):
for batch_idx, (data, target) in enumerate(dataloader):
output = model(data)
loss = criterion(output, target)
optimizer.zero_grad()
loss.backward()
optimizer.step()

Solution

1. Step 1: Check loop order

   The outer loop should be epochs, inner loop batches. for epoch in range(5): for batch_idx, (data, target) in enumerate(dataloader): optimizer.zero_grad() output = model(data) loss = criterion(output, target) loss.backward() optimizer.step() follows this correctly.

2. Step 2: Verify zero_grad and step calls

   optimizer.zero_grad() must be before backward(), and optimizer.step() after. for epoch in range(5): for batch_idx, (data, target) in enumerate(dataloader): optimizer.zero_grad() output = model(data) loss = criterion(output, target) loss.backward() optimizer.step() has correct order.

3. Step 3: Check other options

   for batch_idx, (data, target) in enumerate(dataloader): for epoch in range(5): optimizer.zero_grad() output = model(data) loss = criterion(output, target) loss.backward() optimizer.step() reverses loops (wrong). for epoch in range(5): optimizer.zero_grad() for batch_idx, (data, target) in enumerate(dataloader): output = model(data) loss = criterion(output, target) loss.backward() optimizer.step() zeros gradients outside batch loop (wrong). for epoch in range(5): for batch_idx, (data, target) in enumerate(dataloader): output = model(data) loss = criterion(output, target) optimizer.zero_grad() loss.backward() optimizer.step() zeros gradients after forward pass (wrong order).

4. Final Answer:

   for epoch in range(5): for batch_idx, (data, target) in enumerate(dataloader): optimizer.zero_grad() output = model(data) loss = criterion(output, target) loss.backward() optimizer.step() -> Option C

5. Quick Check:

   Epochs outside, zero_grad before backward, step after [OK]

Hint: Epoch loop outside, zero_grad before backward [OK]

Common Mistakes:

• Swapping epoch and batch loops
• Calling zero_grad outside batch loop
• Calling zero_grad after forward pass