checkpoint['g_best_state'] is corresponding to the model weights with the lowest validation error, why you just use checkpoint['g_state'], which is the final g_state saved in the training. The final g_state is not guaranteed to be the best one. Hope someone could give an explanation. Thanks!
checkpoint['g_best_state'] is corresponding to the model weights with the lowest validation error, why you just use checkpoint['g_state'], which is the final g_state saved in the training. The final g_state is not guaranteed to be the best one. Hope someone could give an explanation. Thanks!