Training progress appear to be stuck

While fine tuning resnet 50, the training progress seems to be stuck. Can somebody help me with what can be possible problem?
Is it problem with the dataset and how to know which sample is causing this issue. Thanks in advance

Now it is not even starting… I know there is some problem with the data but how to find what is creating this issue? Any help will be appreciated.

Solved it, it was due to vs code issue. There was an issue with the progress bar in jupyter notebook but the code was running successfully in the background.
This thread Using Visual Studio Code with fastai (VSCode bug) - Part 1 (2020) - fast.ai Course Forums helped to solve the problem

tl;dr Add this to your code

from IPython.display import clear_output, DisplayHandle
def update_patch(self, obj):
    clear_output(wait=True)
    self.display(obj)
DisplayHandle.update = update_patch
1 Like