Flair: early stop according to dev set performance

Created on 2 Jan 2020  路  3Comments  路  Source: flairNLP/flair

Hello,

Thank you for your fantastic work of creating flair model. I have got a question here.

Is it possible to early stop according to the dev set performance (say, f1 score of WNUT-17 dev set) instead of the training loss?

Best Regards

question

All 3 comments

Hi,

I think it should be already like that. Try to have look at #1250 and related.

Hi @ciaochiaociao, @lucaventurini is right, if you set train_with_dev=False in the ModelTrainer (which is the default), annealing is done against dev F1 score. Only if you set train_with_dev=True you anneal using training loss.

Thank you all. I did use an example that turns on train_with_dev. After turning it off, it works as what I want.

Was this page helpful?
0 / 5 - 0 ratings

Related issues

mnishant2 picture mnishant2  路  3Comments

prematurelyoptimized picture prematurelyoptimized  路  3Comments

happypanda5 picture happypanda5  路  3Comments

frtacoa picture frtacoa  路  3Comments

gopalkalpande picture gopalkalpande  路  3Comments