I encountered an oscillating training loss curve problem. So I followed some tutorials and tried to solve it.
I did a learning rate test, and the LR ranges from 1E-7 to 0.1. The network I used is ResNet-50, and the optimizer is Adam.
Below is the LRTest result I got.
What I expected is a curve that first decreases slowly, then decreases steeply, and at last goes up. But I got this different result. I don't know what this trend of curve means. What should I do to select an appropriate learning rate?