deepnlp
deepnlp copied to clipboard
train processs
hi, i would like to know what is the ending condition during training in textsum task?
Hi @stevenzhou1990 Sorry for the late reply. Actually it's a good point, I didn't add a max-epoch or perplexity constraint to stop the training process while babysitting the model training process. I stopped the training when the perplexity dropped below a threshold and I tried to run the test examples every now and then to determine if the training process is done. But it's a good point to add one stopping criteria, I will try to add one sometime later.