vkramgovind

Thanks for the quick reply. Will close the issue then.

Hi , I tried with configuration suggested. Still BLEU seems to be stuck around 2.2 after 3rd Epoch. Transformer base seems to work well for Single GPU. Any other pointers...

Hi.. I have attached train.log and valid.log . Please let me know if there is anything else you need [train.log](https://github.com/marian-nmt/marian/files/2652042/train.log) [valid.log](https://github.com/marian-nmt/marian/files/2652043/valid.log)

Data is from the example only..average-attention was a little faster in inference compared to default in case of Transformer base. So I straight away tried average-attention for the Transformer-big