Validation loss does not decrease about deep-learning-v2-pytorch HOT 2 CLOSED

You can create a condition early stopping function by setting up a threshold and monitor the delta in the training loss. When the training loss is smaller than the threshold, you can stop the training loop. Here's the implementation example from StackOverflow. Or, you can also use some third-party libraries that support early stopping function (see example here).

from deep-learning-v2-pytorch.

Please note that the validation loss shows a general trend of increasing. Obviously, it reduces from one epoch to the next, but the overall validation loss across a few epochs is infact, increasing.

from deep-learning-v2-pytorch.