Sam Bowman

@zphang, mind taking a look?

There are none that I know of. This is likely possible, but it's not something we've been prioritizing. You're likely better off using 1.3 if it has most of the...

I don't immediately see what's wrong—@W4ngatang would know better. That said, what are you trying to do? If you don't need to match the _exact_ setup of the GLUE paper...

Thanks for letting us know about all of this! (Though the opening strikes me as needlessly aggressive.) Could you let us know what kind of experiments/models you're planning to run?...

Thanks for the note! If you're far enough along that you're definitely going to try to use this code, PRs are welcome. We may beat you to it, but with...

Hi! The results in the paper are test set results (as it says in the caption), and several datasets have non-trivial differences between the dev and test data, so it's...

@W4ngatang - Could you take this one? If you need to exactly match our baselines, jiant won't do that. This paper publishes numbers from the final_glue_runs script, though: https://openreview.net/pdf?id=Bkl87h09FX Sam

The reference to jiant above was to v1.3: https://github.com/nyu-mll/jiant-v1-legacy The new v2.0 is mostly a wrapper around Transformers, so it drops LSTM support. Start with v1.3.

You'll have a much easier time with jiant than with this repo, but if you need an exact reproduction for some reason, ping w4ngatang again.

@zphang, PTAL