yunzhe-tao opened a new issue #11597: Large Word LM Training URL: https://github.com/apache/incubator-mxnet/issues/11597 Hi, I noticed that the large_word_lm model in the folder example/rnn/ has been modified recently. However, the perplexity increases at this version. Could anyone explain the differences between two versions? Moreover, I ran the codes on p3.8xlarge instance and found that the validation process takes much more time than before. Why is it? Previously the whole validation takes only about 10 minutes, but now it's more than 2 hours. Thanks.
---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: [email protected] With regards, Apache Git Services
