Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Update retrain.py #77

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Update retrain.py #77

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
11 changes: 7 additions & 4 deletions bert_pytorch/trainer/pretrain.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -59,8 +59,11 @@ def __init__(self, bert: BERT, vocab_size: int,
self.optim_schedule = ScheduledOptim(self.optim, self.bert.hidden, n_warmup_steps=warmup_steps)

# Using Negative Log Likelihood Loss function for predicting the masked_token
self.criterion = nn.NLLLoss(ignore_index=0)

self.criterion_mask_lm = nn.NLLLoss(ignore_index=0)

# Using Negative Log Likelihood Loss function for predicting the is_next
self.criterion_is_next = nn.NLLLoss()

self.log_freq = log_freq

print("Total Parameters:", sum([p.nelement() for p in self.model.parameters()]))
Expand Down Expand Up @@ -102,10 +105,10 @@ def iteration(self, epoch, data_loader, train=True):
next_sent_output, mask_lm_output = self.model.forward(data["bert_input"], data["segment_label"])

# 2-1. NLL(negative log likelihood) loss of is_next classification result
next_loss = self.criterion(next_sent_output, data["is_next"])
next_loss = self.criterion_is_next(next_sent_output, data["is_next"])

# 2-2. NLLLoss of predicting masked token word
mask_loss = self.criterion(mask_lm_output.transpose(1, 2), data["bert_label"])
mask_loss = self.criterion_mask_lm(mask_lm_output.transpose(1, 2), data["bert_label"])

# 2-3. Adding next_loss and mask_loss : 3.4 Pre-training Procedure
loss = next_loss + mask_loss
Expand Down