Cartik

Hi Henning, i got the latest build from the website and it built fine! Thanks for cygwin and bash level installs. I'm using the same tools to deploy qbsolv. Best...

hi Mike, I cannot share the .qubo file due to IP reasons. What compiler are you using to build qbsolv on windows? qbsolv converges fine for the same qubo file...

Are you using a Cygwin based enviroment to compile?

4Gb of CUDA memory. Best regards, Cartik Sharma "There is plenty of room at the bottom." - Richard Feynman On Sunday, October 20, 2019, 09:52:28 a.m. EDT, Tae-Hwan Jung wrote:...

Also, I'm using trainer.train(get_loss, model_file, True) with 3 params instead of 4. It doesn't take the pretrain_file as a parameter. Could you help me with this?

Fixed this by using an earlier version of ALBERTA https://github.com/graykode/ALBERT-Pytorch/tree/revert-11-feature/fix_seg_pad_bug It takes the pretrain_file now. I'm only getting an error based on cfg.dim size mismatch for embed.tok_embed1.weight: copying a param...