Cryptic error thrown


(Yog Mehta) #1

I was trying to run my learner:
m = md.get_learner(emb_sz, len(df.columns)-len(cat_vars), 0.04, 1, [1000,500], [0.03,0.06])

And the console threw this error:
RuntimeError: cuda runtime error (59) : device-side assert triggered at /pytorch/torch/lib/THC/generic/THCStorage.cu:58

Can anybody explain where I went wrong? Or how I might correct this error?