Hi! I got a few question regarding the graphs visualized on the Tensorboard:
Why there is no Validation Loss graph but instead EvalStat graph
visualized there? Since during training i provide both Training set and
Validation set.
Why there is Evaluation Stat graph there? since i never provide Testing set
during the training?
What is the purpose of having EvalStat graph and what can we know
from that graph?
Among loss_decoder, loss_postnet and stop_loss, which one
should be really important and to be focused on ?
How can i know that my current models is overfitting or not since no
Validation graph provided??
Don’t “overfit” to names. If you mentally replace the name “Validation” with “Evaluation”, you solve your problems. In short, check Eval stats for validation.
If you are looking for the final voice performance of the model, “loss_postnet” is the target. But for the best, they all should converge.