Zhang ZiHan
Zhang ZiHan
I train ResNet34 with the identical setting, the result is identical to the CoLab experiment. The weight decay 0.005 is not the optimal value for ResNet32 (ResNet32 feature dim=64 while...
Thanks a lot! I just tried the NLS during the whole training process and it didn't work. Thanks for the details.
I want to reproduce the experiments of Openchat v3.2 super on Webshop (78.6% success rate). I installed the Webshop and Openchat environment and they work well. However, the success rate...
i also met this problem, have you solved that?
Thanks for your quick reply. I have changed the waitFor to 15000ms, it still return ``` {'status': 'completed', 'current': 1, 'total': 1, 'data': [], 'partial_data': []} ``` Could this be...