Checkpoint with optimizer state in PyTorch - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to save the model checkpoint including the optimizer state.

PyTorch

torch.save({'model_state_dict': model.state_dict(), 'optimizer_state_dict': [1], 'checkpoint.pth')

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

Aoptimizer.state_dict()

Bmodel.state_dict()

Coptimizer.save()

Dmodel.save()

Attempts:

3 left

💡 Hint

Common Mistakes

Using model.state_dict() instead of optimizer.state_dict() for optimizer state

Calling save() method on optimizer which does not exist

To save the optimizer state, use optimizer.state_dict() inside the checkpoint dictionary.

2fill in blank

medium

Complete the code to load the optimizer state from the checkpoint.

PyTorch

checkpoint = torch.load('checkpoint.pth')
optimizer.[1](checkpoint['optimizer_state_dict'])

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

Astate_dict

Bload

Cload_optimizer

Dload_state_dict

Attempts:

3 left

💡 Hint

Common Mistakes

Using load() instead of load_state_dict()

Trying to assign the state dict directly without using the method

To restore the optimizer state, use optimizer.load_state_dict() with the saved state dictionary.

3fill in blank

hard

Fix the error in the code to correctly save the checkpoint with model and optimizer states.

PyTorch

torch.save({'model': model.state_dict(), 'optimizer': [1], 'checkpoint.pth')

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

Aoptimizer.state_dict()

Boptimizer.load_state_dict()

Coptimizer.save()

Dmodel.state_dict()

Attempts:

3 left

💡 Hint

Common Mistakes

Using load_state_dict() instead of state_dict() when saving

Calling save() on optimizer which is not a valid method

The checkpoint dictionary keys can be any string, but the value for optimizer must be optimizer.state_dict() to save its state.

4fill in blank

hard

Fill both blanks to correctly load the model and optimizer states from the checkpoint.

PyTorch

checkpoint = torch.load('checkpoint.pth')
model.[1](checkpoint['model'])
optimizer.[2](checkpoint['optimizer'])

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

Aload_state_dict

Bload

Cstate_dict

Dsave

Attempts:

3 left

💡 Hint

Common Mistakes

Using load() instead of load_state_dict()

Using state_dict property instead of method to load

Both model and optimizer use load_state_dict() to restore their saved states from the checkpoint.

5fill in blank

hard

Fill all three blanks to save a checkpoint with model state, optimizer state, and current epoch.

PyTorch

torch.save({'model_state_dict': model.[1](), 'optimizer_state_dict': optimizer.[2](), 'epoch': [3], 'checkpoint.pth')

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

Astate_dict

Bstate_dict()

Ccurrent_epoch

Depoch

Attempts:

3 left

💡 Hint

Common Mistakes

Using state_dict without parentheses which is a property, not a method call

Saving epoch as a string instead of a variable

Use state_dict() method to get model and optimizer states. The epoch number is saved as a variable, here named 'epoch'.

Practice

1. What is the main reason to save the optimizer state along with the model in a PyTorch checkpoint?

easy

A. To speed up the model's inference time

B. To reduce the model size on disk

C. To resume training with the same learning rate and momentum settings

D. To convert the model to a different format

Solution

1. Step 1: Understand what optimizer state contains

   The optimizer state includes parameters like learning rate, momentum, and other variables that affect training progress.

2. Step 2: Reason why saving optimizer state is important

   Saving the optimizer state allows training to resume exactly where it left off, preserving these settings.

3. Final Answer:

   To resume training with the same learning rate and momentum settings -> Option C

4. Quick Check:

   Optimizer state saves training settings = C [OK]

Hint: Optimizer state saves training progress settings [OK]

Common Mistakes:

• Thinking optimizer state reduces model size
• Confusing optimizer state with model weights
• Believing optimizer state affects inference speed

2. Which of the following is the correct way to save a checkpoint including model and optimizer states in PyTorch?

easy

A. torch.save(model, 'checkpoint.pth')

B. torch.save({'model': model.state_dict(), 'optimizer': optimizer.state_dict()}, 'checkpoint.pth')

C. torch.save(optimizer, 'checkpoint.pth')

D. torch.save({'model': model, 'optimizer': optimizer}, 'checkpoint.pth')

Solution

1. Step 1: Identify correct saving method for states

   PyTorch recommends saving state_dict() of model and optimizer for checkpoints.

2. Step 2: Check each option

   torch.save({'model': model.state_dict(), 'optimizer': optimizer.state_dict()}, 'checkpoint.pth') saves state_dict() of both model and optimizer in a dictionary, which is correct.

3. Final Answer:

   torch.save({'model': model.state_dict(), 'optimizer': optimizer.state_dict()}, 'checkpoint.pth') -> Option B

4. Quick Check:

   Save state_dict() for model and optimizer = B [OK]

Hint: Save state_dict() of model and optimizer in dict [OK]

Common Mistakes:

• Saving full model object instead of state_dict
• Saving optimizer object directly
• Not saving optimizer state at all

3. Given this code snippet, what will be printed?

import torch
import torch.nn as nn
import torch.optim as optim

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

# Save checkpoint
checkpoint = {'model': model.state_dict(), 'optimizer': optimizer.state_dict()}
torch.save(checkpoint, 'cp.pth')

# Load checkpoint
loaded = torch.load('cp.pth')
optimizer.load_state_dict(loaded['optimizer'])
print(optimizer.param_groups[0]['lr'])

medium

A. 0.1

B. 0.01

C. 1.0

D. Error: optimizer state not loaded

Solution

1. Step 1: Understand optimizer initialization

   Optimizer is created with learning rate 0.1 and saved in checkpoint.

2. Step 2: Loading optimizer state restores learning rate

   Loading optimizer state_dict sets learning rate back to 0.1.

3. Final Answer:

   0.1 -> Option A

4. Quick Check:

   Loaded optimizer lr = 0.1 [OK]

Hint: Loaded optimizer keeps saved learning rate [OK]

Common Mistakes:

• Assuming learning rate resets to default
• Forgetting to load optimizer state
• Confusing model and optimizer states

4. You saved a checkpoint with model and optimizer states but when loading, training behaves as if optimizer settings are lost. What is the most likely mistake?

medium

A. Not calling optimizer.load_state_dict() after loading checkpoint

B. Saving model.state_dict() instead of model

C. Using torch.save() instead of torch.load()

D. Not setting model.eval() before saving

Solution

1. Step 1: Identify cause of lost optimizer settings

   If optimizer state is not loaded, training uses default optimizer settings.

2. Step 2: Check common mistakes

   Not calling optimizer.load_state_dict() after loading checkpoint causes this issue.

3. Final Answer:

   Not calling optimizer.load_state_dict() after loading checkpoint -> Option A

4. Quick Check:

   Load optimizer state to keep settings = D [OK]

Hint: Always load optimizer state after loading checkpoint [OK]

Common Mistakes:

• Saving full model instead of state_dict
• Confusing torch.save and torch.load usage
• Setting model.eval() affects inference, not optimizer

5. You want to save a checkpoint that allows resuming training exactly, including epoch number and best loss so far. Which is the best way to structure the checkpoint dictionary?

hard

A. {'epoch': epoch, 'model': model.state_dict()}

B. {'model': model, 'optimizer': optimizer, 'epoch': epoch}

C. {'model_state': model.state_dict(), 'loss': best_loss}

D. {'epoch': epoch, 'model': model.state_dict(), 'optimizer': optimizer.state_dict(), 'best_loss': best_loss}

Solution

1. Step 1: Identify required checkpoint components

   To resume training exactly, save epoch, model state, optimizer state, and best loss.

2. Step 2: Evaluate options

   {'epoch': epoch, 'model': model.state_dict(), 'optimizer': optimizer.state_dict(), 'best_loss': best_loss} includes all required keys with correct state_dict() usage.

3. Final Answer:

   {'epoch': epoch, 'model': model.state_dict(), 'optimizer': optimizer.state_dict(), 'best_loss': best_loss} -> Option D

4. Quick Check:

   Save epoch, model, optimizer, loss in checkpoint = A [OK]

Hint: Include epoch, model, optimizer, and loss in checkpoint dict [OK]

Common Mistakes:

• Saving full model or optimizer objects
• Omitting optimizer state
• Not saving epoch or loss for training resume