Training stopped after 5 epochs while Semimtr finetuning
wulinunu opened this issue · 2 comments
wulinunu commented
A problem occurred when trying to train the Semimtr:
The training stage will automatically stop after 5 epochs no matter what value of epoch I set in the config file 'configs/semimtr_finetune.yaml'.
However, if I set epoch to less than 5, then everything seems to work just fine.
aaberdam commented
You should also increase the periods of the scheduler in the configuration file. By default, they set to be: [ 3, 1, 1 ]
.
Let me know if it works for you.
wulinunu commented
Oh I see. That works.
Thank you!