SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

fix #1017

Browse Source
This commit is contained in:
thomwolf
2019-08-21 22:22:17 +02:00
parent 2f9397139d
commit e00b4ff1de
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
README.md
View File

@@ -393,8 +393,8 @@ for batch in train_data:
loss = model(batch) loss = model(batch)
loss.backward() loss.backward()
torch.nn.utils.clip_grad_norm_(model.parameters(), max_grad_norm) # Gradient clipping is not in AdamW anymore (so you can use amp without issue) torch.nn.utils.clip_grad_norm_(model.parameters(), max_grad_norm) # Gradient clipping is not in AdamW anymore (so you can use amp without issue)
scheduler.step()
optimizer.step() optimizer.step()
scheduler.step()
optimizer.zero_grad() optimizer.zero_grad()
``` ```