Learning rate curve going backwards for cnn

Question

I'm working on recognizing the numbers 3 and 7 using MNIST data set. I'm using cnn_learner() function from fastai library. When I plotted the learning rate, the curve started going backwards after a certain value on X-axis. Can someone please explain what does it signify?

it shows how the loss values change with learning rates changes. at the point where the model has a lesser learning rate,(less than 0.001) model loss is increased up to 1.thats means your model is overfitting and over-training — Dhanushka Sandaruwan, Jul 17 '20 at 18:10

score 0 · Answer 1 · answered Jul 19 '20 at 10:15

The curve's behavior is normal as weird as it seems to look. This curve represents multiple learning rate values with respect to the loss. It helps you in determining, at what learning rate value, will you loss be minimum or maximum.

This is a method of finding the best learning rate for your model. You must choose a value that reduces your loss. However, if you choose a learning rate value to be too small just by thinking the loss would be the minimum, then your model will train damn slow.

You can use the following link to get more understanding of finding the optimal learning rate for your model.

Learning rate finder

Learning rate curve going backwards for cnn

1 Answers1