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

Model Convergence Indicator #1

Open
already-taken-m17 opened this issue Dec 1, 2016 · 1 comment
Open

Model Convergence Indicator #1

already-taken-m17 opened this issue Dec 1, 2016 · 1 comment

Comments

@already-taken-m17
Copy link

Hi,
During the training, how the number of epochs are getting decided ?
As I see, no part of training data has been reserved for evaluation during training of model. So, how can I be assured that model has converged during training ?

@orenmel
Copy link
Owner

orenmel commented Dec 2, 2016

Correct. As in word2vec, there is no such validation set built into the training process, but indeed it would probably be useful to have this (as done when training language models, etc.). I guess that if the train set is large enough then you can look at the train error without too much of a risk of over-fitting.

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