Karthik Rangasai

Hello @ethanwharris , I think `UnfreezeMilestines` strategy is somewhat close to the `Gradual Unfreezing` idea from this paper [Universal Language Model Fine-tuning for Text Classification](https://arxiv.org/abs/1801.06146) by Jeremy Howard and Sebastian...

Great. Sounds good. I will try to get some work done on this then.

Hello @Borda , We had spoken about 1. the Kaggle API key getting outdated and updating it 2. enrolling the lightinig kaggle testing account into the competition. Downloading and sharing...

Hello @galtay , Could you please review this PR ?

Hello @hakunanatasha , When I ran the tests locally, all of them passed. Let me check once again though to verify.

Hello @hakunanatasha , I ran the tests again and removed some unwanted lines of code. All the tests pass.

@hakunanatasha , could you please review the changes to the PR

#self-assign