Abdessalem Boukil

@jaspock Thanks for your input, it helped make the training script work. However the problem I am facing now is that the loss is barely converging, despite the small size...

An update, I have a working training script here: https://github.com/maroxtn/mt5-M2M-comparison

Sorry for the lack of details. Here is a colab notebook to reproduce the error: https://colab.research.google.com/drive/18XR3g3qDMmPTn25fveGhdUn6RjBNORmb?usp=sharing What I also tried with that: ``` sudo apt-get install fluidsynth pip install pyfluidsynth...

I'm encountering the same issue here, I thought the problem was with my code. However downgrading tqdm to version 4.28.0 solved the issue for me.