Scribd
Upload
14 views3 pages

Quiz Capitulo3

Uploaded by

Ana Gabriela Medina Améstica
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
14 views3 pages

Quiz Capitulo3

Uploaded by

Ana Gabriela Medina Améstica
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 3

End-of-chapter quiz

Ask a Question

1. The emotion dataset contains Twitter messages labeled with emotions. Search for it in the
Hub, and read the dataset card. Which of these is not one of its basic emotions?

Joy

Love

Confusion: Correct! Correct! Confusion is not one of the six basic emotions.

Surprise

2. Search for the ar_sarcasm dataset in the Hub. Which task does it support?

Sentiment classification: Correct! That's right! You can tell thanks to the tags.

Machine translation

Named entity recognition

Question answering

3. How does the BERT model expect a pair of sentences to be processed?

Tokens_of_sentence_1 [SEP] Tokens_of_sentence_2

[CLS] Tokens_of_sentence_1 Tokens_of_sentence_2

[CLS] Tokens_of_sentence_1 [SEP] Tokens_of_sentence_2 [SEP] Correct! That's correct!

[CLS] Tokens_of_sentence_1 [SEP] Tokens_of_sentence_2

4. What are the benefits of the Dataset.map() method?

The results of the function are cached, so it won't take any time if we re-execute the code.

Correct! That is indeed one of the neat benefits of this method! It's not the only one, though...

It can apply multiprocessing to go faster than applying the function on each element of the
dataset.

Correct! This is a neat feature of this method, but it's not the only one!

It does not load the whole dataset into memory, saving the results as soon as one element is
processed.

Correct! That's one advantage of this method. There are others, though!
5. What does dynamic padding mean?

It's when you pad the inputs for each batch to the maximum length in the whole dataset.

It's when you pad your inputs when the batch is created, to the maximum length of the
sentences inside that batch.

Correct! That's correct! The "dynamic" part comes from the fact that the size of each batch is
determined at the time of creation, and all your batches might have different shapes as a result.

It's when you pad your inputs so that each sentence has the same number of tokens as the
previous one in the dataset.

6. What is the purpose of a collate function?

It ensures all the sequences in the dataset have the same length.

It puts together all the samples in a batch.

Correct! Correct! You can pass the collate function as an argument of a DataLoader. We used the
DataCollatorWithPadding function, which pads all items in a batch so they have the same length.

It preprocesses the whole dataset.

It truncates the sequences in the dataset.

7. What happens when you instantiate one of the AutoModelForXxx classes with a pretrained
language model (such as bert-base-uncased ) that corresponds to a different task than the one
for which it was trained?

Nothing, but you get a warning.

The head of the pretrained model is discarded and a new head suitable for the task is inserted
instead.

Correct! Correct. For example, when we used AutoModelForSequenceClassification with bert-


base-uncased, we got warnings when instantiating the model. The pretrained head is not used for
the sequence classification task, so it's discarded and a new head is instantiated with random
weights.

The head of the pretrained model is discarded.

Nothing, since the model can still be fine-tuned for the different task.

8. What’s the purpose of TrainingArguments ?

It contains all the hyperparameters used for training and evaluation with the Trainer.
Correct! Correct!

It specifies the size of the model.

It just contains the hyperparameters used for evaluation.

It just contains the hyperparameters used for training.

9. Why should you use the 🤗 Accelerate library?

It provides access to faster models.

It provides a high-level API so I don't have to implement my own training loop.

It makes our training loops work on distributed strategies.

Correct! Correct! With Accelerate, your training loops will work for multiple GPUs and TPUs.

It provides more optimization functions.

You might also like