Hang Xu

Same issue here!!! I have also tried ResNet56 on Cifar10 with given hyper-parameters, but only got 41% test accuracy with adam optimizer and 20% test accuracy with sgd optimizer.

> Same issue here!!! I have also tried ResNet56 on Cifar10 with given hyper-parameters, but only got 41% test accuracy with adam optimizer and 20% test accuracy with sgd optimizer....

> @AbdulMoqeet @hangxu0304 Hi, could you have another try with a smaller number of local epochs, e.g. E=1. The large epochs usually make training harder to converge. Yes, I have...

I tried the code from an early [commit](https://github.com/FedML-AI/FedML/tree/50d8a45d27675343a7b05a9b31279f6764d3f2ad), and the accuracy can be reproduced. I guess there might be some inconsistency between the early and latest commit. @chaoyanghe

> @hangxu0304 Could you please share hyperparameters or **wandb report** ? The default hyperparameters (client numbers) are different in both scripts. There is additional parameter (# of local points) in...

This might be true for the standalone version. But in distributed version, each client only needs to update this global model and then upload it to the server. My previous...

> > @AbdulMoqeet @hangxu0304 Hi, could you have another try with a smaller number of local epochs, e.g. E=1. The large epochs usually make training harder to converge. > >...

> @AbdulMoqeet @hangxu0304 @wizard1203 Hi All, what's the final conclusion? I'm trying to check whether gradient clipping is the cause. The experiment is still running. Let's see.

Yes.

@chaoyanghe I think CI only affects the training accuracy, not the test accuracy, right?