StepLR and MultiStepLR in PyTorch - Model Metrics & Evaluation

Metrics & Evaluation - StepLR and MultiStepLR

Which metric matters for StepLR and MultiStepLR and WHY

StepLR and MultiStepLR are learning rate schedulers in PyTorch. They help adjust the learning rate during training to improve model learning. The key metrics to watch are training loss and validation loss. These show if the model is learning well or if the learning rate is too high or too low. Also, accuracy on validation data helps check if the model is improving. These metrics matter because the scheduler changes learning rate to help the model find better answers faster and avoid getting stuck.

Confusion matrix or equivalent visualization

StepLR and MultiStepLR do not directly produce predictions or confusion matrices. Instead, we track training and validation loss over epochs to see their effect.

Epoch | Learning Rate | Training Loss | Validation Loss | Accuracy
--------------------------------------------------------------
  1   |    0.1        |    0.8        |     0.9         |  70%
  5   |    0.1        |    0.5        |     0.6         |  80%
 10   |    0.01       |    0.3        |     0.4         |  88%
 15   |    0.001      |    0.25       |     0.35        |  90%
    

This table shows how learning rate drops at steps (e.g., epoch 10 and 15) and how loss and accuracy improve as a result.

Precision vs Recall tradeoff with concrete examples

StepLR and MultiStepLR affect how fast or slow the model learns. If learning rate drops too fast, the model may learn slowly and underfit (low recall). If it drops too late, the model may overfit or oscillate (low precision). For example:

• StepLR: Drops learning rate every fixed number of epochs. Good for steady learning but may miss sudden changes.
• MultiStepLR: Drops learning rate at specific epochs. Good for fine control when you know when to slow learning.

Choosing the right scheduler helps balance learning speed (precision) and coverage (recall) of the model's knowledge.

What "good" vs "bad" metric values look like for StepLR and MultiStepLR

Good:

• Training and validation loss steadily decrease over epochs.
• Validation accuracy improves or stays stable after learning rate drops.
• No sudden jumps or spikes in loss after learning rate changes.

Bad:

• Validation loss increases or oscillates after learning rate drops.
• Accuracy plateaus or drops despite learning rate changes.
• Training loss stuck or decreases too slowly, indicating learning rate too low.

Metrics pitfalls

• Accuracy paradox: High accuracy can hide poor learning if data is imbalanced.
• Data leakage: Validation data accidentally used in training can give false good metrics.
• Overfitting indicators: Training loss much lower than validation loss after learning rate drops.
• Ignoring learning rate schedule: Not adjusting learning rate can cause slow or unstable training.

Self-check

Your model uses StepLR and shows 98% training accuracy but only 12% recall on fraud detection. Is it good for production?

Answer: No. High training accuracy means the model learned the training data well, but very low recall means it misses most fraud cases. For fraud detection, recall is critical because missing fraud is costly. The learning rate schedule might need adjustment or the model needs improvement to catch more fraud.

Key Result

StepLR and MultiStepLR improve training by adjusting learning rate, best monitored by loss and accuracy trends over epochs.

Practice

1. What is the main difference between StepLR and MultiStepLR in PyTorch?

easy

A. StepLR decreases learning rate at fixed intervals; MultiStepLR decreases at specific epochs.

B. StepLR increases learning rate; MultiStepLR decreases learning rate.

C. StepLR changes learning rate randomly; MultiStepLR keeps it constant.

D. StepLR is used only for batch size adjustment; MultiStepLR for learning rate.

Solution

1. Step 1: Understand StepLR behavior

   StepLR reduces the learning rate by a factor every fixed number of epochs (step size).

2. Step 2: Understand MultiStepLR behavior

   MultiStepLR reduces the learning rate at specific epochs defined by a list of milestones.

3. Final Answer:

   StepLR decreases learning rate at fixed intervals; MultiStepLR decreases at specific epochs. -> Option A

4. Quick Check:

   StepLR fixed steps, MultiStepLR specific milestones [OK]

Hint: StepLR uses fixed steps; MultiStepLR uses milestone epochs [OK]

Common Mistakes:

• Confusing increase vs decrease of learning rate
• Thinking StepLR changes learning rate randomly
• Mixing learning rate with batch size adjustments

2. Which of the following is the correct way to create a StepLR scheduler in PyTorch that reduces learning rate every 5 epochs by a factor of 0.1?

easy

A. scheduler = StepLR(optimizer, step_size=5, gamma=0.1)

B. scheduler = StepLR(optimizer, milestones=[5], gamma=0.1)

C. scheduler = MultiStepLR(optimizer, step_size=5, gamma=0.1)

D. scheduler = MultiStepLR(optimizer, milestones=[5], gamma=0.1)

Solution

1. Step 1: Recall StepLR parameters

   StepLR takes step_size (int) and gamma (decay factor).

2. Step 2: Identify correct syntax

   scheduler = StepLR(optimizer, step_size=5, gamma=0.1) uses step_size=5 and gamma=0.1, which matches the requirement.

3. Final Answer:

   scheduler = StepLR(optimizer, step_size=5, gamma=0.1) -> Option A

4. Quick Check:

   StepLR uses step_size, not milestones [OK]

Hint: StepLR uses step_size, MultiStepLR uses milestones list [OK]

Common Mistakes:

• Using milestones parameter with StepLR
• Confusing MultiStepLR and StepLR syntax
• Passing step_size as a list

3. Given the following code, what will be the learning rate after epoch 7?

optimizer = torch.optim.SGD(model.parameters(), lr=0.1)
scheduler = MultiStepLR(optimizer, milestones=[3, 6], gamma=0.1)
for epoch in range(8):
    scheduler.step()
    print(f"Epoch {epoch}: lr = {optimizer.param_groups[0]['lr']}")

medium

A. 0.01

B. 0.001

C. 0.1

D. 0.0001

Solution

1. Step 1: Understand milestones and gamma

   Learning rate reduces by factor 0.1 at epochs 3 and 6.

2. Step 2: Calculate learning rate at epoch 7

   Initial lr=0.1; after epoch 3: 0.1*0.1=0.01; after epoch 6: 0.01*0.1=0.001; so at epoch 7 lr=0.001.

3. Final Answer:

   0.001 -> Option B

4. Quick Check:

   Two milestones reduce lr twice: 0.1 -> 0.01 -> 0.001 [OK]

Hint: Multiply lr by gamma at each milestone passed [OK]

Common Mistakes:

• Forgetting to apply gamma at both milestones
• Assuming lr changes before first milestone
• Confusing StepLR with MultiStepLR behavior

4. Identify the error in this code snippet using StepLR:

optimizer = torch.optim.Adam(model.parameters(), lr=0.01)
scheduler = StepLR(optimizer, milestones=[10, 20], gamma=0.5)
for epoch in range(25):
    scheduler.step()
    print(optimizer.param_groups[0]['lr'])

medium

A. scheduler.step() must be called after optimizer.step() inside loop.

B. Optimizer Adam cannot be used with StepLR scheduler.

C. StepLR does not accept milestones parameter; use step_size instead.

D. Gamma value must be greater than 1 for StepLR.

Solution

1. Step 1: Check StepLR parameters

   StepLR expects step_size, not milestones.

2. Step 2: Identify misuse of milestones

   Passing milestones causes error; correct is step_size=10 for example.

3. Final Answer:

   StepLR does not accept milestones parameter; use step_size instead. -> Option C

4. Quick Check:

   StepLR uses step_size, not milestones [OK]

Hint: StepLR uses step_size, not milestones list [OK]

Common Mistakes:

• Using milestones with StepLR
• Thinking Adam optimizer is incompatible
• Misunderstanding gamma parameter range

5. You want to train a model for 30 epochs. You want the learning rate to drop by 0.1 at epochs 10 and 20, and then again every 5 epochs after epoch 20. Which scheduler setup correctly achieves this?

hard

A. Use StepLR with step_size=10 and gamma=0.1

B. Use StepLR with step_size=5 and gamma=0.1

C. Use MultiStepLR with milestones=[10, 20, 25, 30] and gamma=0.1

D. Use MultiStepLR with milestones=[10, 20] and gamma=0.1, then StepLR with step_size=5 after epoch 20

Solution

1. Step 1: Understand the requirement

   Learning rate drops at epochs 10 and 20, then every 5 epochs after 20 (i.e., 25, 30).

2. Step 2: Analyze scheduler options

   MultiStepLR can handle fixed milestones (10, 20). StepLR can handle regular steps (every 5 epochs). Combining both after epoch 20 fits the requirement.

3. Step 3: Evaluate options

   Use MultiStepLR with milestones=[10, 20, 25, 30] and gamma=0.1 misses epochs after 20 beyond 25 and 30; Use StepLR with step_size=5 and gamma=0.1 drops every 5 epochs from start; Use StepLR with step_size=10 and gamma=0.1 drops every 10 epochs only; Use MultiStepLR with milestones=[10, 20] and gamma=0.1, then StepLR with step_size=5 after epoch 20 correctly combines both schedulers.

4. Final Answer:

   Use MultiStepLR with milestones=[10, 20] and gamma=0.1, then StepLR with step_size=5 after epoch 20 -> Option D

5. Quick Check:

   Combine MultiStepLR for early milestones + StepLR for regular steps after [OK]

Hint: Combine MultiStepLR for milestones + StepLR for regular steps [OK]

Common Mistakes:

• Trying to use only one scheduler for mixed schedule
• Misplacing milestones or step_size values
• Assuming StepLR can handle irregular milestones