Closed arthur-thuy closed 1 year ago
I'm sorry, I noticed that the ModelWrapper.train_and_test_on_datasets()
function allows for early stopping with the patience
and min_epoch_for_es
arguments. I didn't see it at first because this function or early stopping functionality was not used in any of the examples.
I do have a follow-up request when using a validation set for early stopping; I will open a new issue.
Is your feature request related to a problem? Please describe. In the
ModelWrapper.train_on_dataset()
function, the number ofepoch
s to train for needs to be specified. When tuning the learning convergence, it is challenging to decide on this value as the amount of training data increases throughout the active learning process.Describe the solution you'd like Use early stopping in the
ModelWrapper.train_on_dataset()
function, which interrupts training as the validation loss stops decreasing.Describe alternatives you've considered Similar to the
Model.fit()
function in Keras, theModelWrapper.train_on_dataset()
function could takecallbacks
andvalidation_data
arguments.Additional context Note that early stopping at this level is different from early stopping at the level of the active learning process, which stops labelling new instances when the current labelled set contains all the information necessary.