Closed tkarthikeyan132 closed 8 months ago
Hi @tkarthikeyan132,
Thank you for your interest in our work. Please share the script you are running and the command you are using for reproducing the issue. Thanks
Hi @mmaaz60,
I haven't changed the script and I run the torchrun command,
I changed nproc_per_node to 2 and the cuda error went away. Thanks
while I was running the training code, i faced this issue NOTE: I have 2 A100 gpus and 8 cpus