Skip to content
This repository has been archived by the owner on May 2, 2023. It is now read-only.

BERT CVE Model doesn't optimally converge over epochs #9

Open
dipanjanS opened this issue Aug 19, 2019 · 0 comments
Open

BERT CVE Model doesn't optimally converge over epochs #9

dipanjanS opened this issue Aug 19, 2019 · 0 comments

Comments

@dipanjanS
Copy link
Collaborator

Current BERT model for probable CVEs works decently but some how doesn't seem to converge optimally as we increase the epochs.

False positives suddenly increase\fluctuate over epochs. The idea is to:

  • Remove data bias
  • Train with lower learning rate, better optimizers (https://arxiv.org/abs/1904.00962v1)
  • Validate predictions of trained model with last 2-3 weeks of triaged data

This would be a blocker into retraining the BERT model also because we need to know some level of optimal configuration before we start retraining

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

No branches or pull requests

1 participant