Running out of memory during training #1202
Closed
Deathawaits4
started this conversation in
General
Replies: 1 comment
|
i have training going for 43,000 steps without an issue, you will have to do a bit more to help pin down the problem since it is not widespread. if you're using gradient checkpointing interval logic, this is probably the reason for the OOM. or the SOAP optimiser. but there's a lot that can go wrong. |
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
Hei, i noticed that for some reason the training runs oom at some point. It trained fine for 553 steps and then got an OOM. I did not run anything else apart from the training.
I think there is a memory leak happening somewhere
All reactions