search

HannesStark / EquiBind

EquiBind: geometric deep learning for fast predictions of the 3D structure in which a small molecule binds to a protein
MIT License
477 stars 109 forks source link

How to continue a training from the checkpoint #63

Closed Nailo closed 2 years ago

Nailo commented 2 years ago

Because I run EquiBind on a server with GPU, but it has time limitation. So I must use checkpoint for my training. How can I continue my training by using the checkpoint?

Thank you

HannesStark commented 2 years ago

You can do that using the checkpoint argument in the .yml file!

Nailo commented 2 years ago

Thank you, Hannes. I found that I was getting the error because I added the parameter #PBS_NGPUS.