Closed 008karan closed 4 years ago
Hi!
As I see the console log, you've change the batch size from 16 to 64, and epoch from 10 to 1, so the total steps become 70. But in main.py
, --save_steps
is 200, which is smaller than 70, so the model wasn't saved. I recommend you to change --save_steps
option:)
@008karan
I'll close this issue. If you have any additional issues, feel free to raise new issue:)
looks like i m able to train but model is not being save and not able to perform evaluation. training comand:
model_dir
is empty after training and hence it cant find model in it.