early-stopping-pytorch.py, shouldn't the script save previous model?

[brucewlee]

Hi. Thanks for your resources :) They are giving great help to my research.

BTW, isn't it correct to save the previous model when the loss decreases? It seems like your current early-stopping-pytorch.py script is intended to save the current model, not the previous one.

[bioinformatica]

self.best_score = score
self.save_checkpoint(val_loss, model)

def save_checkpoint(self, val_loss, model):
'''Saves model when validation loss decrease.'''
if self.verbose:
self.trace_func(f'Validation loss decreased ({self.val_loss_min:.6f} --> {val_loss:.6f}). Saving model ...')
torch.save(model.state_dict(), self.path)

save the best model