Open JoshuaMathias opened 2 years ago
I noticed that when epoch 4 is reached, the loss increases significantly due to the se parameter starting to take effect. I realized this is likely when self-ensembling starts, not when it finished. So I renamed it to _se_epochstart.
I did a review of parameters and variables related to the number of epochs:
I also noticed that the number of epochs that are actually run is 31, matching the default for mm.
To avoid confusion, I'm doing the following:
Commit with changes: https://github.com/JoshuaMathias/Domain-Agnostic-Sentence-Specificity-Prediction/commit/485f441011441979d2862301d6abc4b5aebb7cfe