ZwormZ

Frequent loss is NaN & Training Hangs

17

Thank you for sharing your code! I am trying to train openfold, but the problem of loss being NAN persists, and the whole training hangs when this problem occurs. I...

Hi! I'm using HHFilter 3.3.0 to sample sequences from MSA file which contains tens of thousands of homologous sequences . The command is: `/userhome/anaconda3/envs/proteins/bin/hhfilter -i /userhome/data/TS2/msa/7KVT_B.a2m -o /userhome/data/TS2/7KVT_B_filter.a2m -id 90...

Multi GPU training stucks when run the main.py

1

First of all, great work! I am experienceing the train hangs problem, I have the same conda environment as yours and use 8 V100 GPUs and set train_batch_size =1. I...