Is Anyone have problem with "deterministic" setting?

[I8Robot]

If don't change the deterministic to false in soma_train_conf.yaml, there will have a use_deterministic_algorithms error.
ERROR:
RuntimeError: median CUDA with indices output does not have a deterministic implementation, but you set 'torch.use_deterministic_algorithms(True)'. You can turn off determinism just for this operation, or you can use the 'warn_only=True' option, if that's acceptable for your application. You can also file an issue at https://github.com/pytorch/pytorch/issues to help us prioritize adding deterministic support for this operation.

My specification :
Ubuntu 22.04.4 LTS
python 3.7
pytorch version 1.5.10
torch 1.13.1