zyj008

@fazlekarim I have the same problem with you that the y-axis is about half or even more of the x-axis. How did you solve the problem？

Thanks for your reply! I still have other questions. How many hours of BZ dataset you used for training? I found it is hard to converge well when training about...

I met the same problem! I installed tensorflow-gpu 1.11.0 in anaconda. After I type the command "bert-serving-start -model ./chinese_L-12_H-768_A-12 -num_worker=2", there comes an error: File "zmq/backend/cython/socket.pyx", line 547, in zmq.backend.cython.socket.Socket.bind...

I have solved this problem. It may be due to the bad or unstable Internet. I didn't do anything and the problem fixed by itself.

@NexusLee 我确定我啥也没动，然后它自己就好了。所以我猜可能是网络不稳定唉。我是在实验室服务器上的anaconda上装的，我弄成功的是cpu版本的tensorflow1.11.0，gpu版本tensorflow的我后来没弄。 另外，我在katacoda上测试dockerfile的时候，不会报zmq这个错误，但是会在最后一步 read and listening的时候出不来就卡住了。