How to prevent to early stop of the model

[buptgarden]

Hello, I am train the mode with python150 dataset , I find the model with early stop in some epoch. It can't run as the setting of NUM_TRAIN_EPOCHS . I feel puzzle when I find the train model only will stop when run out of data . So, how can I stop the early stop of the trainning ?

[urialon]

Hi @IHaveNoEnglishName , Sorry for the delay.

Early stopping is not implemented, so you can simply set NUM_TRAIN_EPOCHS to 999999 and kill the process manually when you want to stop.

Does that answer your question, or did I miss anything?