Raymond Cheng
1 min readJul 22, 2020

--

This is a warning, not an error I suppose! From a quick Internet search, I found this warning means that some of the weights in the pretrained checkpoint, bert-based-uncased, will not be used for BERTForSequenceClassification. Some weights will be discarded. So TLDR, you can disregard the message and train the sequence classification model without any problems.

Check this link for more detailed explanation: https://github.com/huggingface/transformers/issues/5421

Sign up to discover human stories that deepen your understanding of the world.

Free

Distraction-free reading. No ads.

Organize your knowledge with lists and highlights.

Tell your story. Find your audience.

Membership

Read member-only stories

Support writers you read most

Earn money for your writing

Listen to audio narrations

Read offline with the Medium app

--

--

Raymond Cheng
Raymond Cheng

Written by Raymond Cheng

Master’s Student at Carnegie Mellon, Top Writer in AI, Top 1000 Writer, Blogging on ML | Data Science | NLP. Linkedin: https://www.linkedin.com/in/itsuncheng/

No responses yet

Write a response