Custom QA model fine-tuning in NLP - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to load the pre-trained QA model.

NLP

from transformers import AutoModelForQuestionAnswering
model = AutoModelForQuestionAnswering.from_pretrained([1])

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

A"vgg16"

B"gpt2"

C"bert-base-uncased"

D"resnet50"

Attempts:

3 left

💡 Hint

Common Mistakes

Choosing image classification models like 'resnet50' or 'vgg16'.

Using language models not fine-tuned for QA like 'gpt2'.

The 'bert-base-uncased' model is a common pre-trained model for question answering tasks.

2fill in blank

medium

Complete the code to prepare the tokenizer for the QA model.

NLP

from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained([1])

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

A"bert-base-uncased"

B"bert-base-cased"

C"roberta-base"

D"distilbert-base-uncased"

Attempts:

3 left

💡 Hint

Common Mistakes

Using a tokenizer that does not match the model architecture.

Choosing a cased tokenizer when the model is uncased.

The tokenizer must match the model; here, 'bert-base-uncased' matches the model used.

3fill in blank

hard

Fix the error in the training loop to correctly compute loss.

NLP

outputs = model(**inputs)
loss = outputs.[1]

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

Aattentions

Bhidden_states

Clogits

Dloss

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'logits' instead of 'loss' to compute training loss.

Accessing 'hidden_states' or 'attentions' which are not loss values.

The 'loss' attribute contains the computed loss during training.

4fill in blank

hard

Fill both blanks to tokenize the question and context correctly.

NLP

inputs = tokenizer([1], [2], truncation=True, padding=True, return_tensors="pt")

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

A"What is AI?"

B"AI stands for Artificial Intelligence."

Cquestion

Dcontext

Attempts:

3 left

💡 Hint

Common Mistakes

Passing literal strings instead of variables.

Swapping question and context order.

The tokenizer takes the question and context variables as inputs to prepare the model input.

5fill in blank

hard

Fill all three blanks to extract the answer span from model outputs.

NLP

answer_start = torch.argmax(outputs.start_logits, dim=[1])
answer_end = torch.argmax(outputs.end_logits, dim=[2])
answer = tokenizer.convert_tokens_to_string(tokenizer.convert_ids_to_tokens(inputs.input_ids[0][answer_start:answer_end+[3]]))

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

A0

B1

Attempts:

3 left

💡 Hint

Common Mistakes

Using dim=0 which is batch dimension.

Not adding 1 to the end index causing incomplete answer.

The logits are 2D tensors; argmax is taken over dimension 1 (sequence length). The answer span includes the end token, so add 1.

Practice

1. What is the main purpose of fine-tuning a custom QA model?

easy

A. To reduce the training time of the model

B. To make the model answer questions better on your specific data

C. To increase the model's size and complexity

D. To change the model's language to another one

Solution

1. Step 1: Understand fine-tuning goal

   Fine-tuning adjusts a model to perform better on a specific task or dataset.

2. Step 2: Relate to QA models

   For QA, fine-tuning helps the model answer questions accurately on your own data.

3. Final Answer:

   To make the model answer questions better on your specific data -> Option B

4. Quick Check:

   Fine-tuning = better task-specific answers [OK]

Hint: Fine-tuning adapts model to your data for better answers [OK]

Common Mistakes:

• Thinking fine-tuning changes model size
• Confusing fine-tuning with faster training
• Assuming it changes the model's language

2. Which of the following is the correct way to prepare data for fine-tuning a QA model?

easy

A. A dataset with questions, contexts, and answers

B. A dataset with only questions and answers

C. A dataset with only contexts and answers

D. A dataset with random text and no labels

Solution

1. Step 1: Identify required data components

   QA models need questions, contexts (where answers are found), and answers to learn properly.

2. Step 2: Check options

   Only the dataset with questions, contexts, and answers includes all three necessary parts for training.

3. Final Answer:

   A dataset with questions, contexts, and answers -> Option A

4. Quick Check:

   QA data = questions + contexts + answers [OK]

Hint: QA fine-tuning needs question, context, and answer triplets [OK]

Common Mistakes:

• Omitting context in the dataset
• Using unlabeled or random text
• Ignoring the answer field

3. Given the following code snippet for fine-tuning a QA model using Hugging Face Trainer, what will be the output metric after training?

from transformers import Trainer, TrainingArguments
training_args = TrainingArguments(output_dir='./results', num_train_epochs=1)
trainer = Trainer(model=model, args=training_args, train_dataset=train_dataset, eval_dataset=eval_dataset)
metrics = trainer.train()
print(metrics.metrics['eval_accuracy'])

medium

A. An integer count of training steps

B. A syntax error due to missing eval_accuracy metric

C. A float value representing evaluation accuracy

D. A KeyError because eval_accuracy is not computed by default

Solution

1. Step 1: Understand default metrics in Trainer

   By default, Trainer does not compute 'eval_accuracy' unless a compute_metrics function is provided.

2. Step 2: Analyze printed output

   Since no compute_metrics is defined, 'eval_accuracy' key won't exist, so accessing it causes a KeyError.

3. Final Answer:

   A KeyError because eval_accuracy is not computed by default -> Option D

4. Quick Check:

   Default Trainer lacks eval_accuracy metric [OK]

Hint: Without compute_metrics, eval_accuracy is not available [OK]

Common Mistakes:

• Assuming eval_accuracy is always computed
• Expecting a syntax error instead of missing metric
• Confusing training steps count with accuracy

4. You tried fine-tuning a QA model but got this error: ValueError: Expected input batch to have 3 elements (input_ids, attention_mask, token_type_ids). What is the most likely cause?

medium

A. You forgot to set num_train_epochs in TrainingArguments

B. The model architecture is incompatible with QA tasks

C. Your dataset does not return token_type_ids in __getitem__

D. You used the wrong optimizer in Trainer

Solution

1. Step 1: Understand the error message

   The error says the input batch misses token_type_ids, which are needed for some QA models.

2. Step 2: Check dataset output

   If the dataset's __getitem__ method does not return token_type_ids, the model input is incomplete causing this error.

3. Final Answer:

   Your dataset does not return token_type_ids in __getitem__ -> Option C

4. Quick Check:

   Missing token_type_ids in data causes input error [OK]

Hint: Check dataset returns all required inputs including token_type_ids [OK]

Common Mistakes:

• Blaming TrainingArguments settings
• Assuming model architecture is wrong
• Thinking optimizer causes input shape errors

5. You want to fine-tune a QA model on a small dataset but avoid overfitting. Which strategy is best to apply during fine-tuning?

hard

A. Use early stopping and lower learning rate

B. Increase number of epochs to 100

C. Remove the context from training data

D. Use a larger batch size without changing learning rate

Solution

1. Step 1: Identify overfitting risk factors

   Small datasets can cause models to memorize instead of generalize, leading to overfitting.

2. Step 2: Choose strategies to reduce overfitting

   Early stopping stops training when performance stops improving; lower learning rate helps gradual learning.

3. Final Answer:

   Use early stopping and lower learning rate -> Option A

4. Quick Check:

   Early stopping + low LR reduces overfitting [OK]

Hint: Stop early and slow learning to prevent overfitting [OK]

Common Mistakes:

• Training too many epochs on small data
• Removing context which is essential
• Increasing batch size without adjusting learning rate