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.

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

Do you have an instruction manual for the pytorch version? #82

Open
Felixgithub2017 opened this issue Jan 3, 2020 · 2 comments
Open

Comments

@Felixgithub2017
Copy link

Some commands for additional parameters are not working in the pytorch version, so, do you have an pytorch-oriented manual?

For example:

--parameters=batch_size=15000,device_list=[0,1],update_cycle=2,train_steps=2000000,keep_checkpoint_max=5,shared_embedding_and_softmax_weights=True,shared_source_target_embedding=True

raise ValueError("Could not parse hparam %s in %s" % (name, values))
ValueError: Could not parse hparam shared_embedding_and_softmax_weights in batch_size=15000,device_list=[0,1],update_cycle=2,train_steps=2000000,keep_checkpoint_max=5,shared_embedding_and_softmax_weights=True,shared_source_target_embedding=True

@Felixgithub2017
Copy link
Author

image
The initial loss is inf, and turned to normal after around 200 steps

@Playinf
Copy link
Collaborator

Playinf commented Jan 6, 2020

In the above example, you should set shared_embedding_and_softmax=true instead of shared_embedding_and_softmax=True. The document of PyTorch implementation will be uploaded soon. We have tested our implementation on several datasets, but we do not observe inf loss problem.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants