Rowan Zellers

sorry for taking a while to get to this one! I believe it's actually the same, since iirc there's an extra layer normalization somewhere else in the openai code. that...

sorry about that, the discrimination side isn't as well documented right now. You can fetch the dataset I used for discrimination (using the generations from Grover-Mega) here: https://github.com/rowanz/grover/tree/master/generation_examples Right now,...

hi @SandeepBhutani, Yep, you'll need to run discriminative training on top of those checkpoints.

thanks for the suggestion! I'm a little hesitant because there are a couple of dependencies that I don't think I can capture via PyPI, namely the cuda drivers 😱. If...

sorry, I'm not sure I can help much based on the level of detail that you provided... I've never run into this error myself, so it's possible this could be...

Sorry, i've never encountered this error while training the model a variety of setups. There could be a few things going on. one thing to double check - are you...

Hi Mihir, thanks for the note! yeah, I don't support running this repo as a module right now, since i tend to run individual subcomponents. If you think that would...

sorry for the delay -- are you trying with 3 GPUs or just 1?

hi there, good question! looking at it again, I'm not sure what I was doing there. unfortunately I don't have too much time to investigate this at the moment, but...

hey! sorry for the delay in response. I think this trains a baseline model, rather than motifnet. Did you try using this command? ``` python models/train_rels.py -m sgcls -model motifnet...