PyTorchText
                                
                                
                                
                                    PyTorchText copied to clipboard
                            
                            
                            
                        use max-epoch5 v.s. early stop
Hi, I am new to DL and i wonder what's the reason behind using small epoch (5) and not using early stop?
Thanks,
Actually I use another kind of early stop:
- if val acc rises: save the model, keep training
 - if val acc drops: load previous best model, decay lr
 
see here
5 epochs are not enough, Usually, I will finetune another 2 epochs with smaller lr.