Open sanxiyn opened 9 years ago
It is an RNG but the seed (starting state) stays the same between runs. You set the seed by adding -seed [some number]
. The default seed is 123.
My question was that the same seed produces different results, if validation frequency is changed.
Sorry for late reply on this. This seems odd because the eval code does not use the RNG as far as I can tell. It seems it shouldn't have effect. I'll have a closer look
It seems that running train.lua with same parameters is deterministic (I get exactly same train_bpc numbers), but -eval_val_every changes training. Why does how often validation is done affect training? Can it be made deterministic?
Is it because of RNG?