guided_summarization icon indicating copy to clipboard operation
guided_summarization copied to clipboard

Published 20 hours ago • verified publisher icon neulab

Advice on training the model

Open Shashi456 opened this issue 2 years ago • 1 comments

Hello,

I started training the model on keyword based guidance (oracle keywords) on a 2x 2080 TI system and trained it for around 36 hours, and tested it. The models seems to be consistently generating gibberish output. (The model trained for about 17 epochs until this stage(

Do you have any advice on how many epochs the model needs to converge? and if this is the same for sentence guided signals as well? Do you have any other advice on model training?

Shashi456 avatar Mar 01 '22 04:03 Shashi456

Hi, 5 epochs should be enough. I think you can first debug by using sentence-guided signals.

zdou0830 avatar Mar 01 '22 18:03 zdou0830