Open ElderWanng opened 3 years ago
I'm really interested in your great work. Just curious, If it is possible that combine BART with loss truncation? Cuz the vanilla LSTM with attention is kind of out-of-date.
Hi @ElderWanng you can take a pretrained model and continue training it with loss truncation - we find it works quite well.
I'm really interested in your great work. Just curious, If it is possible that combine BART with loss truncation? Cuz the vanilla LSTM with attention is kind of out-of-date.