- add validation every_epoch flag
- Add print statement for all inputs shapes
- valid_batch_size always 1
- model checkpinting according to valid ppl
- verify sequence_loss procedure (and loss.mean().backward())
- add print(train_loss) at end of epoch
- lr default=1e-5
- batch_size=max w/o cuda error
-
Notifications
You must be signed in to change notification settings - Fork 0
arch-raven/Dialogue-Generation
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
No description, website, or topics provided.
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published