-
Notifications
You must be signed in to change notification settings - Fork 512
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
Different seeds lead to very different results in unsup BERT #63
Comments
Hi, For the unsupervised model, the performance could be affected by different random seeds, hardwares, validation steps, etc. We have been using the default seed of Huggingface's transformers. |
Thank you for your answer.
|
Hi, Thanks for the suggestion. We are also planning to add more trials and take the average for more accurate results. It's indeed probably the case that you need to re-tune the hyper-parameters when changing the seeds. |
Thank you |
Hello, thank you for sharing code.
I found the result of unsup BERT seems unstable to different seeds. I can reproduce the result of 76~ with the default seed, but when changing to different the seeds, the results seems worse than default seed. (I use '--seed' flag to set seed)
Have you encountered this problem?
The text was updated successfully, but these errors were encountered: