Clemens Rosenbaum

NLP models that do sequence comparison (the NLI groups comes to mind) are oftentimes implemented with a different encoder object for each compared part. In these cases, the standard flambe...

The problem with the per batch level are things like AUC. If we are using the batch as negatives (as is quite common), computing the AUC per batch will be...

That's a great idea! However, while we're at it: would it be possible to make this more general, and more user-controllable? I.e., could we maybe have some general "results-writer" that...

Hi. I am aware of this problem. It was the consequence of a major rewrite I did to speed up the code (from loop-based routes within a batch to mask-based...

Hi Andrew! Thanks for that question. The example is slightly misleading, as `actions` is None anyways. Here's the full explanation as to what the different actions are: `actions`, is `None`,...