Why fine-tuning adapts models to domains in Prompt Engineering / GenAI - Challenge Your Understanding

Challenge - 5 Problems

🧠 Conceptual

intermediate

Why does fine-tuning improve model performance on a specific domain?

Imagine you have a general language model trained on many topics. You want it to work better on medical texts. Why does fine-tuning the model on medical data help?

A Fine-tuning changes the model’s architecture to add new layers for medical terms.

B Fine-tuning removes all previous knowledge so the model only knows medical data.

C Fine-tuning increases the model size to handle more data.

D Fine-tuning adjusts the model’s knowledge to focus on patterns and vocabulary specific to the medical domain.

💡 Hint

Think about how learning new examples helps a student focus on a topic.

Fine-tuning updates the model’s parameters so it better recognizes and predicts patterns in the new domain, without losing all previous knowledge.

❓ Predict Output

intermediate

What is the output after fine-tuning on domain data?

Given a simple model predicting sentiment, after fine-tuning on movie reviews, what will the prediction be for a new movie review?

Prompt Engineering / GenAI

class SimpleSentimentModel:
    def __init__(self):
        self.positive_words = {'good', 'great', 'fun'}
    def predict(self, text):
        return 'Positive' if any(word in text.split() for word in self.positive_words) else 'Negative'

model = SimpleSentimentModel()
# Fine-tuning adds 'amazing' to positive words
model.positive_words.add('amazing')

print(model.predict('The movie was amazing and fun'))

A Negative

B Positive

C Error: 'amazing' not recognized

D Neutral

💡 Hint

Check if the new word added during fine-tuning is in the input text.

Fine-tuning added 'amazing' to the positive words set, so the model predicts 'Positive' for the input containing 'amazing'.

❓ Model Choice

advanced

Which model is best suited for fine-tuning to a new domain?

You want to adapt a language model to a specialized domain with limited data. Which model type is best to fine-tune?

A A model trained from scratch on the new domain data

B A small model trained only on the new domain data

C A large pre-trained model with general knowledge

D A model with no pre-training

💡 Hint

Think about using existing knowledge and adapting it.

Large pre-trained models have broad knowledge and can be fine-tuned efficiently on small domain data, improving performance without starting from zero.

❓ Hyperparameter

advanced

Which hyperparameter setting helps prevent overfitting during fine-tuning?

When fine-tuning a model on a small domain dataset, which hyperparameter adjustment helps avoid overfitting?

A Use a smaller learning rate

B Use a larger batch size without change

C Remove dropout layers

D Increase the number of training epochs drastically

💡 Hint

Think about making smaller, careful updates to the model.

A smaller learning rate makes the model update weights gently, reducing the risk of overfitting to small data.

❓ Metrics

expert

Which metric best shows improved domain adaptation after fine-tuning?

You fine-tune a model on a new domain. Which metric best indicates the model learned domain-specific patterns?

A Higher accuracy on domain-specific test data

B Lower training loss on original general data

C Increased model size after fine-tuning

D Faster training time during fine-tuning

💡 Hint

Think about how well the model performs on new domain examples.

Higher accuracy on domain-specific test data shows the model adapted well to the new domain after fine-tuning.

Practice

1. Why do we fine-tune a pre-trained model for a specific domain?

easy

A. To make the model larger and more complex

B. To reduce the model's accuracy on general tasks

C. To erase all previous knowledge from the model

D. To help the model learn details specific to that domain

Solution

1. Step 1: Understand the purpose of fine-tuning

   Fine-tuning adjusts a general model to perform better on a specific topic or style by teaching it new details.

2. Step 2: Identify the effect on the model

   Fine-tuning helps the model learn domain-specific details without losing all previous knowledge.

3. Final Answer:

   To help the model learn details specific to that domain -> Option D

4. Quick Check:

   Fine-tuning = domain adaptation [OK]

Hint: Fine-tuning adds domain details, not erases knowledge [OK]

Common Mistakes:

• Thinking fine-tuning makes the model forget everything
• Believing fine-tuning always makes the model bigger
• Assuming fine-tuning reduces accuracy on all tasks

2. Which of the following is the correct way to start fine-tuning a model in Python using a library?

easy

A. model.fine_tune(data, epochs=3)

B. model.train(data, epochs=3)

C. model.fit(data, epochs=3)

D. model.tune(data, epochs=3)

Solution

1. Step 1: Recognize common fine-tuning method names

   In many ML libraries, fit is used to train or fine-tune models on new data.

2. Step 2: Compare options to common usage

   fine_tune and tune are not standard method names; train is less common than fit for fine-tuning.

3. Final Answer:

   model.fit(data, epochs=3) -> Option C

4. Quick Check:

   Fine-tuning uses fit() method [OK]

Hint: Use fit() to train or fine-tune models in Python [OK]

Common Mistakes:

• Choosing non-existent method names like fine_tune()
• Confusing train() with fit() in common libraries
• Assuming tune() is a valid method

3. Given this code snippet for fine-tuning a model, what will be the output loss after training?

initial_loss = 0.8
for epoch in range(3):
    initial_loss *= 0.7
print(round(initial_loss, 2))

medium

A. 0.27

B. 0.41

C. 0.56

D. 0.34

Solution

1. Step 1: Calculate loss after each epoch

   Start with 0.8, multiply by 0.7 three times: 0.8 * 0.7 = 0.56, 0.56 * 0.7 = 0.392, 0.392 * 0.7 = 0.2744.

2. Step 2: Round the final loss

   Rounded to two decimals: 0.27.

3. Final Answer:

   0.27 -> Option A

4. Quick Check:

   Loss after 3 epochs = 0.27 [OK]

Hint: Multiply loss by decay each epoch, then round [OK]

Common Mistakes:

• Multiplying fewer times than epochs
• Rounding before final multiplication
• Choosing wrong rounded value

4. You tried fine-tuning a model but the accuracy did not improve. Which of these is the most likely error in your code?

model = load_pretrained_model()
model.fit(new_data)
model.evaluate(test_data)

medium

A. Not specifying epochs in fit() so training was too short

B. Using evaluate() before fit()

C. Loading the wrong model type

D. Not normalizing the test data

Solution

1. Step 1: Check the fit() method usage

   Without specifying epochs, fit() may run only one epoch or default minimal training, insufficient for fine-tuning.

2. Step 2: Understand impact on accuracy

   Too few training steps means the model doesn't learn new domain details, so accuracy stays low.

3. Final Answer:

   Not specifying epochs in fit() so training was too short -> Option A

4. Quick Check:

   Short training = no accuracy gain [OK]

Hint: Always set epochs to train enough during fine-tuning [OK]

Common Mistakes:

• Assuming evaluate() order matters before fit()
• Ignoring data normalization effects
• Not checking model type mismatch

5. You have a general language model and want it to perform well on medical text. Which fine-tuning approach best adapts it to this domain?

hard

A. Train the model from scratch only on medical data

B. Fine-tune the pre-trained model with a small medical dataset using low learning rate

C. Use the pre-trained model without any changes

D. Fine-tune the model with random unrelated data to increase size

Solution

1. Step 1: Compare training from scratch vs fine-tuning

   Training from scratch needs lots of data and time; fine-tuning uses existing knowledge and adapts efficiently.

2. Step 2: Identify best fine-tuning practice

   Using a small medical dataset with a low learning rate helps the model learn domain details without forgetting general knowledge.

3. Final Answer:

   Fine-tune the pre-trained model with a small medical dataset using low learning rate -> Option B

4. Quick Check:

   Fine-tune + small data + low rate = best domain fit [OK]

Hint: Fine-tune with small domain data and low learning rate [OK]

Common Mistakes:

• Training from scratch without enough data
• Using unrelated data for fine-tuning
• Skipping fine-tuning and using general model only