BERT for text classification in PyTorch - Model Pipeline Trace

Model Pipeline - BERT for text classification

This pipeline uses BERT, a smart language model, to read sentences and decide their category, like sorting emails into spam or not spam.

Data Flow - 7 Stages

1Raw Text Input

1000 sentences→Collect raw sentences for classification→1000 sentences

"I love this movie!", "This is terrible."

↓

2Tokenization

1000 sentences→Split sentences into tokens and add special tokens→1000 sequences x 128 tokens

[CLS] I love this movie ! [SEP]

↓

3Convert Tokens to IDs

1000 sequences x 128 tokens→Map tokens to numbers BERT understands→1000 sequences x 128 token IDs

[101, 1045, 2293, 2023, 3185, 999, 102]

↓

4Attention Masks

1000 sequences x 128 token IDs→Create masks to tell model which tokens to focus on→1000 sequences x 128 masks

[1, 1, 1, 1, 1, 1, 1, 0, 0, ...]

↓

5BERT Model Forward Pass

1000 sequences x 128 token IDs + masks→Process tokens to get sentence meaning vectors→1000 sequences x 768 features

[0.12, -0.34, 0.56, ..., 0.01]

↓

6Classification Layer

1000 sequences x 768 features→Predict class scores from BERT features→1000 sequences x 2 classes

[2.3, -1.7]

↓

7Softmax Activation

1000 sequences x 2 classes→Convert scores to probabilities→1000 sequences x 2 probabilities

[0.91, 0.09]

Training Trace - Epoch by Epoch

Loss
0.7 |*       
0.6 | *      
0.5 |  *     
0.4 |   *    
0.3 |    *   
0.2 |     *  
0.1 |       
    +--------
     1 2 3 4 5 Epochs

Epoch	Loss ↓	Accuracy ↑	Observation
1	0.65	0.60	Model starts learning, loss high, accuracy low
2	0.45	0.75	Loss decreases, accuracy improves
3	0.35	0.82	Model learns better features
4	0.28	0.87	Loss continues to drop, accuracy rises
5	0.22	0.90	Model converges with good accuracy

Prediction Trace - 6 Layers

Layer 1: Tokenization

Layer 2: Convert Tokens to IDs

Layer 3: Attention Mask Creation

Layer 4: BERT Model Forward Pass

Layer 5: Classification Layer

Layer 6: Softmax Activation

Model Quiz - 3 Questions

What does the attention mask do in the BERT pipeline?

A It splits sentences into words

B It tells the model which tokens to focus on

C It converts tokens to numbers

D It predicts the final class

Key Insight

BERT transforms sentences into meaningful vectors, then a simple layer predicts classes. Training reduces loss and improves accuracy steadily, showing the model learns well.

Practice

1. What is the main advantage of using BERT for text classification compared to traditional bag-of-words models?

easy

A. BERT understands the context of words in a sentence.

B. BERT uses fewer parameters than bag-of-words models.

C. BERT requires no preprocessing of text data.

D. BERT only works with short texts.

Solution

1. Step 1: Understand BERT's design

   BERT reads words in context, meaning it looks at surrounding words to understand meaning better.

2. Step 2: Compare with bag-of-words

   Bag-of-words treats words independently, ignoring order and context, which limits understanding.

3. Final Answer:

   BERT understands the context of words in a sentence. -> Option A

4. Quick Check:

   Contextual understanding = A [OK]

Hint: Remember BERT reads words with context, unlike bag-of-words [OK]

Common Mistakes:

• Thinking BERT uses fewer parameters
• Assuming BERT needs no preprocessing
• Believing BERT only works on short texts

2. Which of the following is the correct way to load a pretrained BERT model for sequence classification in PyTorch?

easy

A. model = torch.load('bert-base-uncased')

B. model = BertTokenizer.from_pretrained('bert-base-uncased')

C. model = BertForSequenceClassification.from_pretrained('bert-base-uncased')

D. model = nn.Sequential('bert-base-uncased')

Solution

1. Step 1: Identify correct class for model loading

   BertForSequenceClassification is the class to load pretrained BERT models for classification tasks.

2. Step 2: Check method usage

   from_pretrained is the method to load pretrained weights by model name.

3. Final Answer:

   model = BertForSequenceClassification.from_pretrained('bert-base-uncased') -> Option C

4. Quick Check:

   Use BertForSequenceClassification.from_pretrained = A [OK]

Hint: Use from_pretrained with BertForSequenceClassification for classification models [OK]

Common Mistakes:

• Using BertTokenizer to load model weights
• Trying to load model with torch.load without saving first
• Using nn.Sequential incorrectly for BERT

3. Given the following code snippet, what will be the shape of the logits output?

from transformers import BertTokenizer, BertForSequenceClassification
import torch

tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
model = BertForSequenceClassification.from_pretrained('bert-base-uncased', num_labels=3)

inputs = tokenizer(['Hello world!', 'BERT is great.'], padding=True, return_tensors='pt')
outputs = model(**inputs)
logits = outputs.logits
print(logits.shape)

medium

A. torch.Size([3, 2])

B. torch.Size([2, 3])

C. torch.Size([2, 768])

D. torch.Size([1, 3])

Solution

1. Step 1: Understand batch size and labels

   Input has 2 sentences, so batch size is 2. num_labels=3 means 3 classes.

2. Step 2: Check output logits shape

   Logits shape is (batch_size, num_labels), so (2, 3).

3. Final Answer:

   torch.Size([2, 3]) -> Option B

4. Quick Check:

   Batch size 2 and 3 labels = (2, 3) [OK]

Hint: Logits shape = (batch size, number of classes) [OK]

Common Mistakes:

• Confusing batch size and label dimension order
• Assuming output shape matches hidden size (768)
• Ignoring batch size in output shape

4. You run this code but get an error: TypeError: forward() got an unexpected keyword argument 'input_ids'. What is the likely cause?

outputs = model(input_ids=inputs['input_ids'], attention_mask=inputs['attention_mask'])

medium

A. The model variable is a BertTokenizer, not BertForSequenceClassification.

B. The inputs dictionary is missing 'input_ids' key.

C. The model was not loaded with from_pretrained.

D. The attention_mask argument is not supported by BERT models.

Solution

1. Step 1: Analyze error message

   The error says forward() got unexpected keyword 'input_ids', meaning the model does not accept this argument.

2. Step 2: Identify model type mismatch

   BertTokenizer does not have a forward method and does not accept input_ids; only BertForSequenceClassification does.

3. Final Answer:

   The model variable is a BertTokenizer, not BertForSequenceClassification. -> Option A

4. Quick Check:

   Wrong model type causes unexpected argument error = D [OK]

Hint: Check if model is BertForSequenceClassification, not tokenizer [OK]

Common Mistakes:

• Confusing tokenizer with model
• Assuming attention_mask is unsupported
• Thinking inputs dictionary is missing keys

5. You want to fine-tune BERT for a 4-class text classification task with imbalanced classes. Which approach helps improve model performance?

hard

A. Set num_labels=2 since 4 classes is too many for BERT.

B. Remove the attention_mask to speed up training.

C. Freeze all BERT layers and train only the final classifier layer.

D. Use weighted loss function to give more importance to minority classes.

Solution

1. Step 1: Understand class imbalance problem

   Imbalanced classes cause the model to favor majority classes, hurting minority class accuracy.

2. Step 2: Choose appropriate solution

   Weighted loss assigns higher penalty to errors on minority classes, helping balance learning.

3. Final Answer:

   Use weighted loss function to give more importance to minority classes. -> Option D

4. Quick Check:

   Weighted loss helps with imbalance = C [OK]

Hint: Apply weighted loss to handle class imbalance [OK]

Common Mistakes:

• Removing attention_mask harms input understanding
• Reducing num_labels loses class info
• Freezing all layers limits fine-tuning benefits