Ahad Suleymanli comments

Repositories
Issues
Comments

Results 2 comments of


                                            Ahad Suleymanli

Training from scratch on TPU

Here to share some of my experience using an RTX 2080TI. Used a learning rate of 1e-4, batch size 12 on the first 150k steps that took around 30 hours....

DistilBERTurk TF checkpoints

Thanks a lot! this will help :D