Description
Hi djukicn
I have tried run this code using google colab, local PC, even server of my lab, but always getting out of memory. "torch.OutOfMemoryError: CUDA out of memory. Tried to allocate 2.00 GiB. GPU 0 has a total capacity of 10.75 GiB of which 29.81 MiB is free. Including non-PyTorch memory, this process has 10.71 GiB memory in use. Of the allocated memory 10.44 GiB is allocated by PyTorch, and 12.10 MiB is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True to avoid fragmentation. See documentation for Memory Management "
However, when I reduce batch_size, many error came up such as with_emb in ope.py. Do you have any suggesstion for me regarding this issue? thank you in advance.