Daisy-123

I tried the command, but get the same error! `CUDA_LAUNCH_BLOCKING=1 CUDA_VISIBLE_DEVICES=0 fairseq-train article_tw2en_1203_zhen_join/ -a transformer_wmt_en_de_big --optimizer adam -s zh -t en --label-smoothing 0.1 --dropout 0.3 --max-tokens 4000 --min-lr '1e-09' --lr-scheduler...

According to my experience,s this question is about environment. Pytorch version have to match your cuda version. Follow the command line : https://pytorch.org/get-started/previous-versions/ Sometimes if you using pip to install...

* Full log : **WARNING (theano.tensor.blas): Using NumPy C-API based implementation for BLAS functions. Traceback (most recent call last): File "train.py", line 222, in test_data, id_to_tag, dico_tags) File "/mnt/Storage01/blue90211/tagger-master/utils.py", line...

I try to set --update-freq 3 , but the training loss still decrease slowly . 2GPU / freq=3 ----------------------------------- epoch | train_loss | valid _loss ----------------------------------- 1 | 7.516 |...