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.