Eze Lanza (Eze)

> > 可以借助wandb。另外根据我们的经验，比较重要的参数是weight decay, lr, 和模型规模相关参数（d_model, ...) > > 非常感谢您的回答！ 我使用wandb进行训练过程可视化。但依然没有取得很好的效果。 data:ETTh1 model：informer seq_len:96 label_len:48 pred_len:24 使用wandb可视化了大约三十多组数据，主要测试的参数为 > > * 'd_model': [1024,512, 256,128] > * 'n_heads': [2,4,8,16] > * 'e_layers':...

I'm having the same error. The input expected for the encoder is 1x512 dimension, and you're providing 640x4, this is what this error means. I don't know where to modify,...

It only works on my Gaudi 2 environment separately, but I'm still getting that error when I'm running the docker compose file from ```cd GenAIExamples/ChatQnA/docker_compose/intel/hpu/gaudi/ docker compose up -d```

These are the step I followed, and I have the same feedback from multiple devs when they try to run this example. I even tried with a new, fresh instance...

@eero-t this is what I meant that the compose file has to be updated/modified

Exactly, but it should be solved on the backend (within the container). I think since it’s a security issue i imagine it should have to be sent as env when...