dnrops
/
transformers
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Small typo in `trange` 

I seriously don't understand why they defined num_train_epochs as a float in the originial tf code.
I Will change it at the end to avoir merge conflicts for now.
This commit is contained in:
VictorSanh 2018-11-03 08:25:15 -04:00
parent 5676d6f799
commit 391a4ec2f3
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
run_classifier_pytorch.py
View File

@ -514,7 +514,7 @@ def main():
model.train()
nb_tr_examples = 0
for epoch in trange(args.num_train_epochs, desc="Epoch"):
for epoch in trange(int(args.num_train_epochs), desc="Epoch"):
for input_ids, input_mask, segment_ids, label_ids in tqdm(train_dataloader, desc="Iteration"):
input_ids = input_ids.to(device)
input_mask = input_mask.float().to(device)