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

Transformer Example Update - AutoModelforSequenceClassification #2190

Merged
merged 8 commits into from
Sep 17, 2021
Merged

Transformer Example Update - AutoModelforSequenceClassification #2190

Changes from 1 commit
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
1bcf76e
changed AutoModel to AutoModelforSequenceClassification
Ishan-Kumar2 Sep 9, 2021
a881bad
moved argument expansion to inside model
Ishan-Kumar2 Sep 9, 2021
9ed5299
update README
Ishan-Kumar2 Sep 9, 2021
d5fdba1
minor fix
Ishan-Kumar2 Sep 12, 2021
b15e8ec
minor fix to eval loop
Ishan-Kumar2 Sep 12, 2021
0fd0ffe
updated default batch size
Ishan-Kumar2 Sep 16, 2021
14c07cf
revert eval batchsize
Ishan-Kumar2 Sep 16, 2021
d6e80fc
Merge branch 'master' into transformers_ex_refactor
sdesrozis Sep 17, 2021
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
Prev Previous commit
Next Next commit
minor fix
  • Loading branch information
@Ishan-Kumar2
Ishan-Kumar2 committed Sep 12, 2021
commit d5fdba1b7bbdc16460b3a96e9c9f7494be7095a9
2 changes: 1 addition & 1 deletion examples/contrib/transformers/main.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -307,7 +307,7 @@ def train_step(engine, batch):
labels = batch[1].view(-1, 1)

if labels.device != device:
input_batch = {k: v.to(device, non_blocking=True, dtype=torch.long) for k, v in batch.items()}
input_batch = {k: v.to(device, non_blocking=True, dtype=torch.long) for k, v in batch[0].items()}
labels = labels.to(device, non_blocking=True, dtype=torch.float)

model.train()
Expand Down