3 Commits
Author SHA1 Message Date
Piotr Czapla 40ca6c200e Refactor and temporary fix the pretrain_lm by adding learn.lr_find
For some reason this fixes the training issue. I though I've nailed it down but i haven't. :/ .
2018-11-10 00:32:29 +01:00
Piotr Czapla eb1da0b630 Updated README.md 2018-11-08 21:05:48 +01:00
Piotr Czapla 2f09109d5d Initial commit 2018-11-08 19:52:07 +01:00