Training loss decrease slowly with different learning rate. Optimizer used is adam. I tried with different scheduling scheme but it follow the same. I started with small dataset. If i need to converge loss i have to go with larger number of epochs but its time consuming.
One important point is, for all learning rates(0.01,0.001,0.0001,0.0008,0.008) loss follow the same pattern. On which parameter should i need to work to reduce loss faster?