Interpreting NER training metrics in CLI mode

[eswar3]

As a first time user, I found the below information very much useful which i referenced from
#2185

P.Loss : Parser loss
N.Loss : NER loss 
UAS : Unlabelled attachment score for parser 
NER P. : NER Precision on development data
NER R. : NER recall on development data
NER F. : NER F on development data
Tag % :Tag accuracy on development data 
T Token % : Tokenization accuracy on development data (irrelevant if you use the .iob format, which prevents you from learning from incorrectly tokenized text).

I think it will be useful to add info this in documentation

[lock]

This thread has been automatically locked since there has not been any recent activity after it was closed. Please open a new issue for related bugs.