Best model saving pattern in PyTorch - Practice Problems & Coding Challenges

Challenge - 5 Problems

❓ Predict Output

intermediate

What does this PyTorch model saving code output?

Consider this PyTorch training loop snippet that saves the best model based on validation loss. What will be the content of the saved file 'best_model.pth' after training?

PyTorch

import torch
import torch.nn as nn

class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(2, 1)
    def forward(self, x):
        return self.linear(x)

model = SimpleModel()
optimizer = torch.optim.SGD(model.parameters(), lr=0.1)

best_loss = float('inf')
for epoch in range(3):
    val_loss = 1.0 / (epoch + 1)  # simulated validation loss: 1.0, 0.5, 0.333...
    if val_loss < best_loss:
        best_loss = val_loss
        torch.save(model.state_dict(), 'best_model.pth')

loaded_state = torch.load('best_model.pth')
print(type(loaded_state))

A <class 'collections.OrderedDict'>

B FileNotFoundError

C <class 'dict'>

D <class 'torch.nn.Module'>

💡 Hint

torch.save(model.state_dict()) saves the model parameters as an OrderedDict.

torch.save(model.state_dict()) saves the model's parameters as an OrderedDict. Loading it with torch.load returns this OrderedDict, not the full model object.

❓ Model Choice

intermediate

Which PyTorch saving pattern ensures you can resume training with optimizer state?

You want to save your PyTorch model and optimizer states to resume training later exactly where you left off. Which saving pattern is best?

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

B torch.save(optimizer.state_dict(), 'optimizer.pth')

C torch.save(model, 'model.pth')

D torch.save(model.state_dict(), 'model.pth')

💡 Hint

You need both model and optimizer states in one file.

Saving a dictionary with both model and optimizer state_dicts allows resuming training with exact states.

❓ Hyperparameter

advanced

What is the best practice for saving model checkpoints during training?

During training, you want to save checkpoints to avoid losing progress. Which practice is best?

A Save checkpoint only when training loss decreases

B Save checkpoint every epoch regardless of performance

C Save checkpoint only at the end of training

D Save checkpoint only when validation accuracy improves

💡 Hint

Validation accuracy reflects generalization better than training loss.

Saving checkpoints when validation accuracy improves ensures you keep the best model generalizing to new data.

🔧 Debug

advanced

Why does loading a saved PyTorch model with torch.load('model.pth') fail?

You saved your model using torch.save(model, 'model.pth') but loading it with torch.load('model.pth') raises an error. What is the likely cause?

A Model was saved with state_dict, not full model

B File path is incorrect

C Model class definition is missing or different when loading

D torch.load only works with CPU models

💡 Hint

Full model saving requires the class code to be available when loading.

Saving the full model requires the exact model class code to be present when loading, otherwise torch.load fails.

🧠 Conceptual

expert

Why is saving only the model's state_dict preferred over saving the entire model in PyTorch?

Select the best reason why saving only the model's state_dict is recommended instead of saving the entire model object.

A Saving entire model is faster and more reliable

B State_dict files are smaller and more portable across PyTorch versions

C State_dict includes optimizer state automatically

D Entire model saving does not require model class definition when loading

💡 Hint

Think about portability and dependency on code.

Saving state_dict is smaller, more portable, and does not require the exact model class code when loading, unlike saving the entire model.