Griffin Adams

is there a solution here? I am getting a training loss of 0 for every epoch and after the first epoch, the results are pretty nice but after the second,...

It looks like you can run https://github.com/PyTorchLightning/lightning-transformers/blob/master/lightning_transformers/cli/predict.py for inference. I can't find example call args in the docs, however

Thanks for replying! I'm cross referencing this post on allennllp https://github.com/allenai/allennlp/issues/4503 Please see my solution [resolve_coref_clusters.py](https://github.com/griff4692/aqa/blob/squad/preprocessing/resolve_coref_clusters.py)

Hi - is there an update on the availability of the code. Even if just the caffe trained weights would be great!

I am also having this issue as well - is there a simple way to fix this?

I also had a question about `loss_func = torch.nn.MarginRankingLoss(margin * i)` In the paper, it says `is the margin multiplied by the difference in rank between the candidates` It appears...

Ahh thanks Yixin - Yes, I've noticed it's the same pairwise calculation from MatchSum. I see with `TotalLoss` -- just wanted to make sure it was meant to be an...

Any fixes that work?

Is there a resolution to this? I'm having the same issue

> I'm facing the same issue where it hangs at "Enabling DeepSpeed FP16." It is happening at random, and I'm unable to pin-point any one factor that is causing it....