I am training a deep network for a regression task.The loss drops initially but then stops changing.Even after many epochs it never improves.The model is clearly underperforming.
Decode Trail Latest Questions
I upgraded to a GPU with much more VRAM.I increased the batch size to use the available memory.Now the training is noticeably slower per epoch.There are no errors, but performance feels worse than before.
The system performs well in offline tests.Under real user traffic, errors appear.Latency increases and predictions degrade.The same model is running.