import os
import random
import torch
from d2l import torch as d2l
The WikiText-2 dataset
d2l.DATA_HUB['wikitext-2'] = (
'https://s3.amazonaws.com/research.metamind.io/wikitext/'
'wikitext-2-v1.zip', '3c914d17d80b1459be871a5039ac23e752a53cbe')
def _read_wiki(data_dir):
file_name = os.path.join(data_dir, 'wiki.train.tokens')
with open(file_name, 'r') as f:
lines = f.readlines()
paragraphs = [line.strip().lower().split(' . ')
for line in lines if len(line.split(' . ')) >= 2]
random.shuffle(paragraphs)
return paragraphs
Generating the Next Sentence Prediction Task
def _get_next_sentence(sentence, next_sentence, paragraphs):
if random.random() < 0.5:
is_next = True
else:
next_sentence = random.choice(random.choice(paragraphs))
is_next = False
return sentence, next_sentence, is_next
def _get_nsp_data_from_paragraph(paragraph, paragraphs, vocab, max_len):
nsp_data_from_paragraph = []
for i in range(len(paragraph) - 1):
tokens_a, tokens_b, is_next = _get_next_sentence(
paragraph[i], paragraph[i + 1], paragraphs)
if len(tokens_a) + len(tokens_b) + 3 > max_len:
continue
tokens, segments = d2l.get_tokens_and_segments(tokens_a, tokens_b)
nsp_data_from_paragraph.append((tokens, segments, is_next))
return nsp_data_from_paragraph
Generating the Masked Language Modeling Task
def _replace_mlm_tokens(tokens, candidate_pred_positions, num_mlm_preds,
vocab):
mlm_input_tokens = [token for token in tokens]
pred_positions_and_labels = []
random.shuffle(candidate_pred_positions)
for mlm_pred_position in candidate_pred_positions:
if len(pred_positions_and_labels) >= num_mlm_preds:
break
masked_token = None
if random.random() < 0.8:
masked_token = '<mask>'
else:
if random.random() < 0.5:
masked_token = tokens[mlm_pred_position]
else:
masked_token = random.randint(0, len(vocab) - 1)
mlm_input_tokens[mlm_pred_position] = masked_token
pred_positions_and_labels.append(
(mlm_pred_position, tokens[mlm_pred_position]))
return mlm_input_tokens, pred_positions_and_labels
def _get_mlm_data_from_tokens(tokens, vocab):
candidate_pred_positions = []
for i, token in enumerate(tokens):
if token in ['<cls>', '<sep>']:
continue
candidate_pred_positions.append(i)
num_mlm_preds = max(1, round(len(tokens) * 0.15))
mlm_input_tokens, pred_positions_and_labels = _replace_mlm_tokens(
tokens, candidate_pred_positions, num_mlm_preds, vocab)
pred_positions_and_labels = sorted(pred_positions_and_labels,
key=lambda x: x[0])
pred_positions = [v[0] for v in pred_positions_and_labels]
mlm_pred_labels = [v[1] for v in pred_positions_and_labels]
return vocab[mlm_input_tokens], pred_positions, vocab[mlm_pred_labels]
Append the special “<mask>” tokens to the inputs
def _pad_bert_inputs(examples, max_len, vocab):
max_num_mlm_preds = round(max_len * 0.15)
all_token_ids, all_segments, valid_lens, = [], [], []
all_pred_positions, all_mlm_weights, all_mlm_labels = [], [], []
nsp_labels = []
for (token_ids, pred_positions, mlm_pred_label_ids, segments,
is_next) in examples:
all_token_ids.append(torch.tensor(token_ids + [vocab['<pad>']] * (
max_len - len(token_ids)), dtype=torch.long))
all_segments.append(torch.tensor(segments + [0] * (
max_len - len(segments)), dtype=torch.long))
valid_lens.append(torch.tensor(len(token_ids), dtype=torch.float32))
all_pred_positions.append(torch.tensor(pred_positions + [0] * (
max_num_mlm_preds - len(pred_positions)), dtype=torch.long))
all_mlm_weights.append(
torch.tensor([1.0] * len(mlm_pred_label_ids) + [0.0] * (
max_num_mlm_preds - len(pred_positions)),
dtype=torch.float32))
all_mlm_labels.append(torch.tensor(mlm_pred_label_ids + [0] * (
max_num_mlm_preds - len(mlm_pred_label_ids)), dtype=torch.long))
nsp_labels.append(torch.tensor(is_next, dtype=torch.long))
return (all_token_ids, all_segments, valid_lens, all_pred_positions,
all_mlm_weights, all_mlm_labels, nsp_labels)
The WikiText-2 dataset for pretraining BERT
class _WikiTextDataset(torch.utils.data.Dataset):
def __init__(self, paragraphs, max_len):
paragraphs = [d2l.tokenize(
paragraph, token='word') for paragraph in paragraphs]
sentences = [sentence for paragraph in paragraphs
for sentence in paragraph]
self.vocab = d2l.Vocab(sentences, min_freq=5, reserved_tokens=[
'<pad>', '<mask>', '<cls>', '<sep>'])
examples = []
for paragraph in paragraphs:
examples.extend(_get_nsp_data_from_paragraph(
paragraph, paragraphs, self.vocab, max_len))
examples = [(_get_mlm_data_from_tokens(tokens, self.vocab)
+ (segments, is_next))
for tokens, segments, is_next in examples]
(self.all_token_ids, self.all_segments, self.valid_lens,
self.all_pred_positions, self.all_mlm_weights,
self.all_mlm_labels, self.nsp_labels) = _pad_bert_inputs(
examples, max_len, self.vocab)
def __getitem__(self, idx):
return (self.all_token_ids[idx], self.all_segments[idx],
self.valid_lens[idx], self.all_pred_positions[idx],
self.all_mlm_weights[idx], self.all_mlm_labels[idx],
self.nsp_labels[idx])
def __len__(self):
return len(self.all_token_ids)
Download and WikiText-2 dataset and generate pretraining examples
def load_data_wiki(batch_size, max_len):
"""Load the WikiText-2 dataset."""
num_workers = d2l.get_dataloader_workers()
data_dir = d2l.download_extract('wikitext-2', 'wikitext-2')
paragraphs = _read_wiki(data_dir)
train_set = _WikiTextDataset(paragraphs, max_len)
train_iter = torch.utils.data.DataLoader(train_set, batch_size,
shuffle=True, num_workers=num_workers)
return train_iter, train_set.vocab
Print out the shapes of a minibatch of BERT pretraining examples
batch_size, max_len = 512, 64
train_iter, vocab = load_data_wiki(batch_size, max_len)
for (tokens_X, segments_X, valid_lens_x, pred_positions_X, mlm_weights_X,
mlm_Y, nsp_y) in train_iter:
print(tokens_X.shape, segments_X.shape, valid_lens_x.shape,
pred_positions_X.shape, mlm_weights_X.shape, mlm_Y.shape,
nsp_y.shape)
break
torch.Size([512, 64]) torch.Size([512, 64]) torch.Size([512]) torch.Size([512, 10]) torch.Size([512, 10]) torch.Size([512, 10]) torch.Size([512])
len(vocab)
20256