Checkpoint with optimizer state in PyTorch - Model Pipeline Trace

Model Pipeline - Checkpoint with optimizer state

This pipeline shows how a model and its optimizer state are saved and loaded during training. Saving the optimizer state helps continue training smoothly from a checkpoint without losing learning progress.

Data Flow - 6 Stages

1Initial data loading

1000 rows x 10 columns→Load dataset with features and labels→1000 rows x 10 columns

Features: [0.5, 1.2, ..., 0.3], Label: 1

↓

2Data preprocessing

1000 rows x 10 columns→Normalize features to range 0-1→1000 rows x 10 columns

Normalized features: [0.04, 0.1, ..., 0.02]

↓

3Train/test split

1000 rows x 10 columns→Split data into 800 train and 200 test rows→Train: 800 rows x 10 columns, Test: 200 rows x 10 columns

Train sample: [0.04, 0.1, ..., 0.02], Label: 1

↓

4Model training

800 rows x 10 columns→Train model with optimizer updating weights→Model weights updated

Weights after epoch 1: [0.12, -0.05, ..., 0.07]

↓

5Checkpoint saving

Model weights and optimizer state→Save model and optimizer state to file→Checkpoint file saved

checkpoint.pth containing model_state_dict and optimizer_state_dict

↓

6Checkpoint loading

Checkpoint file→Load model and optimizer state from file→Model and optimizer restored

Model weights and optimizer parameters restored for continued training

Training Trace - Epoch by Epoch

Loss
1.0 | *       
0.8 |  *      
0.6 |   *     
0.4 |    *  * 
0.2 |         
    +---------
     1 2 3 4 5
     Epochs

Epoch	Loss ↓	Accuracy ↑	Observation
1	0.85	0.60	Initial training with high loss and moderate accuracy
2	0.65	0.72	Loss decreased, accuracy improved
3	0.50	0.80	Model learning well, checkpoint saved here
4	0.45	0.83	Training continued after loading checkpoint
5	0.40	0.86	Further improvement after resuming training

Prediction Trace - 3 Layers

Layer 1: Input layer

Layer 2: Hidden layer with ReLU

Layer 3: Output layer with sigmoid

Model Quiz - 3 Questions

Why is it important to save the optimizer state along with the model?

A To reduce the model size on disk

B To continue training with the same learning progress

C To improve prediction speed

D To avoid saving the model weights

Key Insight

Saving both model weights and optimizer state allows training to resume exactly where it left off, preserving learning momentum and improving training efficiency.

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