Best model saving pattern in PyTorch - Model Pipeline Trace

Model Pipeline - Best model saving pattern

This pipeline trains a PyTorch model and saves the best version based on validation accuracy. It ensures the model with the highest validation accuracy is saved for later use.

Data Flow - 4 Stages

1Data Loading

1000 rows x 20 features→Load dataset and split into training and validation sets→800 rows x 20 features (train), 200 rows x 20 features (val)

Train data sample: [0.5, 1.2, ..., 0.3], Label: 1

↓

2Model Initialization

20 features→Define a simple neural network with input, hidden, and output layers→Model with parameters for 20 input features

Layer sizes: Input(20) -> Hidden(10) -> Output(2)

↓

3Training Loop

800 rows x 20 features→Train model for multiple epochs, evaluate on validation set each epoch→Trained model and validation accuracy per epoch

Epoch 1: val_accuracy=0.75, Epoch 2: val_accuracy=0.80

↓

4Best Model Saving

Validation accuracy per epoch→Save model state dict only if validation accuracy improves→Best model saved to disk

Saved model at epoch 2 with val_accuracy=0.80

Training Trace - Epoch by Epoch

Loss: 0.65 |\
       0.50 | \
       0.45 |  \
       0.40 |   \
       0.38 |    \
          +----------------
          1  2  3  4  5 Epochs

Epoch	Loss ↓	Accuracy ↑	Observation
1	0.65	0.70	Initial training with moderate accuracy
2	0.50	0.78	Accuracy improved, model saved
3	0.45	0.75	Accuracy dropped, model not saved
4	0.40	0.82	New best accuracy, model saved
5	0.38	0.80	Accuracy slightly lower, model not saved

Prediction Trace - 4 Layers

Layer 1: Input Layer

Layer 2: Hidden Layer with ReLU

Layer 3: Output Layer with Softmax

Layer 4: Prediction

Model Quiz - 3 Questions

Why do we save the model only when validation accuracy improves?

A Because training loss always decreases

B To keep the best performing model on unseen data

C To save disk space by not saving every epoch

D To avoid saving the model at the first epoch

Key Insight

Saving the model only when validation accuracy improves ensures that the best version of the model is kept. This prevents overfitting and saves storage by not saving every epoch. Monitoring validation accuracy is key to selecting the best model.

Practice

1. What is the best practice for saving a PyTorch model during training?

easy

A. Save the model only at the start of training.

B. Save the model only when it improves on validation data.

C. Save the model after every training batch.

D. Save the model only if the training loss increases.

Solution

1. Step 1: Understand model saving timing

   Saving the model only when validation improves ensures you keep the best version, avoiding unnecessary saves.

2. Step 2: Compare other options

   Saving every batch wastes space; saving at start or on loss increase is not useful for best model.

3. Final Answer:

   Save the model only when it improves on validation data. -> Option B

4. Quick Check:

   Save best validation model = C [OK]

Hint: Save model only on validation improvement to keep best [OK]

Common Mistakes:

• Saving model too frequently wastes storage
• Saving only at start misses improvements
• Saving on training loss increase is wrong

2. Which of the following is the correct PyTorch code to save only the model weights?

easy

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

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

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

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

Solution

1. Step 1: Identify correct saving method

   PyTorch saves weights using torch.save(model.state_dict(), filename).

2. Step 2: Check other options

   Saving the whole model (torch.save(model, 'model.pth')) is possible but less flexible; options C and D are invalid syntax.

3. Final Answer:

   torch.save(model.state_dict(), 'model.pth') -> Option A

4. Quick Check:

   Save weights with state_dict() = A [OK]

Hint: Use torch.save(model.state_dict(), filename) to save weights [OK]

Common Mistakes:

• Trying to save model directly without state_dict
• Using non-existent save methods on model
• Confusing saving weights vs full model

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

import torch
import torch.nn as nn

model = nn.Linear(2, 1)
torch.save(model.state_dict(), 'best.pth')
new_model = nn.Linear(2, 1)
new_model.load_state_dict(torch.load('best.pth'))
print(new_model.weight.shape)

medium

A. torch.Size([1, 2])

B. torch.Size([2, 1])

C. torch.Size([1, 1])

D. Error: shape mismatch

Solution

1. Step 1: Understand model architecture

   nn.Linear(2,1) creates weights of shape [1, 2] (output features, input features).

2. Step 2: Loading weights into new model

   Loading saved weights into identical model keeps weight shape same.

3. Final Answer:

   torch.Size([1, 2]) -> Option A

4. Quick Check:

   Linear(2,1) weight shape = [1, 2] [OK]

Hint: Linear layer weights shape = (out_features, in_features) [OK]

Common Mistakes:

• Confusing input/output dimensions order
• Expecting error when loading identical model
• Misreading weight shape as (2,1)

4. What is wrong with this code snippet for saving the best model?

if val_loss < best_loss:
    best_loss = val_loss
    torch.save(model, 'best_model.pth')

medium

A. There is no condition to check validation loss.

B. It should save model.state_dict() instead of model.

C. It does not update best_loss correctly.

D. It saves the entire model, which is less flexible than saving state_dict.

Solution

1. Step 1: Analyze saving method

   Saving entire model works but is less flexible and may cause issues when loading on different devices or PyTorch versions.

2. Step 2: Compare with best practice

   Best practice is saving model.state_dict() for portability and smaller files.

3. Final Answer:

   It saves the entire model, which is less flexible than saving state_dict. -> Option D

4. Quick Check:

   Save state_dict() preferred over full model [OK]

Hint: Save state_dict() for flexibility, not full model [OK]

Common Mistakes:

• Saving full model without state_dict
• Ignoring portability issues
• Assuming full model save is always best

5. You want to save the best model during training based on validation accuracy. Which code snippet correctly implements this pattern?

best_acc = 0.0
for epoch in range(epochs):
    train()
    val_acc = validate()
    # Save best model here
    ???

hard

A. if val_acc < best_acc:
best_acc = val_acc
torch.save(model.state_dict(), 'best_model.pth')

B. if val_acc == best_acc:
torch.save(model.state_dict(), 'best_model.pth')

C. if val_acc > best_acc:
best_acc = val_acc
torch.save(model.state_dict(), 'best_model.pth')

D. torch.save(model.state_dict(), 'best_model.pth') # save every epoch

Solution

1. Step 1: Identify saving condition

   We save model only if validation accuracy improves (val_acc > best_acc).

2. Step 2: Update best accuracy and save weights

   Update best_acc and save model.state_dict() to keep best weights.

3. Final Answer:

   if val_acc > best_acc: best_acc = val_acc torch.save(model.state_dict(), 'best_model.pth') -> Option C

4. Quick Check:

   Save on val_acc improvement = B [OK]

Hint: Save model only if validation accuracy improves [OK]

Common Mistakes:

• Saving when accuracy decreases
• Saving every epoch wastes space
• Not updating best accuracy variable