ACProp-Optimizer
ACProp-Optimizer copied to clipboard
Implementation for ACProp ( Momentum centering and asynchronous update for adaptive gradient methdos, NeurIPS 2021)
Results
1
ACProp-Optimizer issues
Sort by
recently updated
recently updated
newest added
I use acprop to train transformer, but it breaks down and keeps 0 bleu. Are there some bugs in the code? the transformer is from https://github.com/juntang-zhuang/fairseq-adabelief lr=5e-4 and 2e-5, eps=1e-16