BERT fine-tuning for classification in NLP - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to load the BERT tokenizer.

NLP

from transformers import [1]
tokenizer = [1].from_pretrained('bert-base-uncased')

Drag options to blanks, or click blank then click option'

ABertModel

BAutoTokenizer

CBertTokenizer

DAutoModel

Attempts:

3 left

💡 Hint

Common Mistakes

Using BertModel instead of a tokenizer.

Forgetting to import the tokenizer class.

Using BertTokenizer which is less flexible than AutoTokenizer.

We use AutoTokenizer to load the BERT tokenizer easily by specifying the model name.

2fill in blank

medium

Complete the code to tokenize input texts with padding and truncation.

NLP

inputs = tokenizer(texts, padding=[1], truncation=[1], return_tensors='pt')

Drag options to blanks, or click blank then click option'

A'max_length'

BFalse

CNone

DTrue

Attempts:

3 left

💡 Hint

Common Mistakes

Setting padding or truncation to False causes errors with varying input lengths.

Using 'max_length' string instead of boolean True.

Setting padding and truncation to True ensures all inputs are the same length for the model.

3fill in blank

hard

Fix the error in the model definition by completing the missing class name.

NLP

from transformers import [1]
model = [1].from_pretrained('bert-base-uncased', num_labels=2)

Drag options to blanks, or click blank then click option'

AAutoModel

BBertModel

CBertForSequenceClassification

DAutoTokenizer

Attempts:

3 left

💡 Hint

Common Mistakes

Using BertModel which lacks classification head.

Using AutoTokenizer instead of a model class.

BertForSequenceClassification is the correct class for fine-tuning BERT on classification tasks.

4fill in blank

hard

Fill both blanks to prepare the optimizer and learning rate scheduler.

NLP

from transformers import [1], [2]
optimizer = [1](model.parameters(), lr=2e-5)
scheduler = [2](optimizer, num_warmup_steps=0, num_training_steps=100)

Drag options to blanks, or click blank then click option'

AAdamW

Bget_linear_schedule_with_warmup

CSGD

DStepLR

Attempts:

3 left

💡 Hint

Common Mistakes

Using SGD optimizer which is less effective for BERT.

Using StepLR scheduler which is not typical for transformers.

AdamW is the recommended optimizer and get_linear_schedule_with_warmup is used for learning rate scheduling in BERT fine-tuning.

5fill in blank

hard

Fill all three blanks to compute accuracy during evaluation.

NLP

from sklearn.metrics import [1]
predictions = outputs.logits.argmax(dim=[2]).cpu().numpy()
labels = batch['labels'].cpu().numpy()
acc = [3](labels, predictions)

Drag options to blanks, or click blank then click option'

Aaccuracy_score

B1

C0

Df1_score

Attempts:

3 left

💡 Hint

Common Mistakes

Using f1_score without importing or for simple accuracy.

Using argmax dim 0 which selects wrong axis.

accuracy_score computes accuracy; argmax is done on dimension 1 (index 1) for class predictions.

Practice

1. What is the main purpose of fine-tuning BERT for a classification task?

easy

A. To adapt BERT's knowledge to classify specific categories in your data

B. To train BERT from scratch on a large dataset

C. To reduce the size of the BERT model for faster inference

D. To convert text into images for classification

Solution

1. Step 1: Understand BERT's pretraining

   BERT is pretrained on general language tasks and needs adjustment for specific tasks like classification.

2. Step 2: Purpose of fine-tuning

   Fine-tuning adapts BERT's learned language understanding to classify categories in your dataset.

3. Final Answer:

   To adapt BERT's knowledge to classify specific categories in your data -> Option A

4. Quick Check:

   Fine-tuning = adapt BERT for classification [OK]

Hint: Fine-tuning means adjusting BERT for your task, not training from scratch [OK]

Common Mistakes:

• Thinking fine-tuning trains BERT from zero
• Confusing fine-tuning with model compression
• Assuming BERT outputs images

2. Which of the following is the correct way to tokenize text before feeding it to BERT in Python?

easy

A. tokens = text.split(' ')

B. tokens = tokenizer.encode_plus(text, return_tensors='pt')

C. tokens = tokenizer.tokenize(text)

D. tokens = text.lower()

Solution

1. Step 1: Identify proper BERT tokenization method

   BERT uses tokenizer.encode_plus to convert text into token IDs and attention masks.

2. Step 2: Compare options

   tokens = tokenizer.encode_plus(text, return_tensors='pt') uses encode_plus with return_tensors='pt' for PyTorch tensors, which is correct for BERT input.

3. Final Answer:

   tokens = tokenizer.encode_plus(text, return_tensors='pt') -> Option B

4. Quick Check:

   Use encode_plus for BERT tokenization [OK]

Hint: Use tokenizer.encode_plus or tokenizer() for BERT input [OK]

Common Mistakes:

• Using simple split instead of tokenizer
• Only tokenizing without encoding IDs
• Not returning tensors for model input

3. Given this code snippet for fine-tuning BERT, what will be the output of print(predictions.argmax(dim=1)) if the model predicts logits [[2.0, 1.0], [0.5, 1.5]] for two samples?

logits = torch.tensor([[2.0, 1.0], [0.5, 1.5]])
predictions = logits
print(predictions.argmax(dim=1))

medium

A. tensor([2, 1])

B. tensor([1, 0])

C. tensor([1, 1])

D. tensor([0, 1])

Solution

1. Step 1: Understand argmax(dim=1)

   Argmax along dim=1 finds the index of max value in each row (sample).

2. Step 2: Calculate argmax for each sample

   First row: max is 2.0 at index 0; second row: max is 1.5 at index 1.

3. Final Answer:

   tensor([0, 1]) -> Option D

4. Quick Check:

   Argmax per row = [0, 1] [OK]

Hint: Argmax dim=1 picks max index per sample row [OK]

Common Mistakes:

• Confusing dim=0 with dim=1
• Mixing up indices and values
• Expecting values instead of indices

4. You run this training loop snippet but get a runtime error: TypeError: forward() missing 1 required positional argument: 'labels'. What is the likely fix?

outputs = model(input_ids, attention_mask)
loss = outputs.loss
loss.backward()

medium

A. Pass labels to the model call: model(input_ids, attention_mask, labels=labels)

B. Remove loss.backward() call

C. Change input_ids to input_id

D. Call model with only input_ids

Solution

1. Step 1: Understand error cause

   The model expects labels to compute loss but they are missing in the call.

2. Step 2: Fix by passing labels

   Include labels argument in model call to get loss: model(input_ids, attention_mask, labels=labels).

3. Final Answer:

   Pass labels to the model call: model(input_ids, attention_mask, labels=labels) -> Option A

4. Quick Check:

   Missing labels argument causes loss error [OK]

Hint: Always pass labels to get loss during training [OK]

Common Mistakes:

• Ignoring the missing labels argument
• Removing backward call instead of fixing input
• Changing variable names incorrectly

5. You want to fine-tune BERT on a small dataset for sentiment classification. Which strategy helps avoid overfitting during training?

hard

A. Train BERT without tokenization to save time

B. Increase batch size to maximum and train longer

C. Use a small learning rate and add dropout layers

D. Remove the classification head and train only embeddings

Solution

1. Step 1: Identify overfitting risks

   Small datasets can cause the model to memorize instead of generalize.

2. Step 2: Apply regularization techniques

   Using a small learning rate and dropout helps the model learn smoothly and avoid overfitting.

3. Final Answer:

   Use a small learning rate and add dropout layers -> Option C

4. Quick Check:

   Small LR + dropout reduces overfitting [OK]

Hint: Small learning rate + dropout helps generalize on small data [OK]

Common Mistakes:

• Training longer without regularization
• Skipping tokenization
• Removing classification head incorrectly