question about training the model?

[vhzy]

Hi,thanks for open source your code. I run the code on my server with 62G memory.After running for a while, the training was interrupted. I found a similar phenomenon in the previous issue: https://github.com/yashkant/sam-textvqa/issues/2#issuecomment-796336799 I wonder how much memory is needed to train this model? Also,should I convert the dataset into npy files?