Early stopping does not count consecutive steps on pytorch branch
jmhb0 opened this issue · comments
Hey Hiro,
The paper says this about early stopping:
training was terminated when the validation loss did not improve for more than 12 consecutive epochs.
Here is the relevant code in cytoself/trainer/basetrainer.py
if _vloss < best_vloss:
best_vloss = _vloss
self.best_model = deepcopy(self.model)
# Save the best model checkpoint
self.save_checkpoint()
else:
count_lr_no_improve += 1
count_early_stop += 1
I believe you need to add count_early_stop=0
in the if
branch to reset the counter.
Hi @jmhb0 sorry for my late reply and thank you for the bug report!
Yes, you're right and I have pushed a fix for this issue.
Thanks !