Csanád Póda

I'm having the same issue, increaing `max_length `or tweaking `repetition_penalty `doesn't help. It mostly won't last 15 rounds until it starts exclusively returning EOS tokens. Even setting max_length to like...

I'm having the same issue, except I'm running Label Studio from a Conda virtual env on Windows 11, and the ML backend on a WSL instance of Ubuntu because I...

@lhoestq Would this work either with an Azure Blob Storage Container or its respective Azure Machine Learning Datastore? If yes, what would that look like in code? I've tried a...

> Hi @csanadpoda , yes, we used fp16 ( https://github.com/clovaai/donut/blob/master/train.py#L127 ). Hope this helps ;) Yes I'm using the same, I guess the resolution increase is the issue with me...

Well yeah not having the main branch compatible with your software is a bit confusing haha Works fine when cloning from official, thanks!

OK I've noticed I haven't specified the checkpoint path in the config yaml. Now I have, I pointed it to the `artifacts.ckpt` file, but now I'm getting an error `ValueError:...

> Try using warmup_steps > 15% and max_epochs > 50, I had good reults with this: > > ``` > warmup_steps: 1500 > num_training_samples_per_epoch: 800 > max_epochs: 100 > max_steps:...

The whole module is a bit deprecated, the PyTorch version they add in the README is not compatible with the latest consumer GPUs (f.E. a 4090), and newer PyTorch versions...

> Try it on colab to see if it works. I actually tried it in WSL and it works.... Seems to be in issue with either Windows 11 or the...

> num_workers: 0 That would mean significant performance loss though.