Training loss stuck in the starting epochs but then starts decreasing. What could be the reason for it?

Question

Training loss stuck in the starting epochs but then starts decreasing. What could be the reason for it?

Deshwal

2022年4月10日 14:00

I am training a model where I found a unique problem that for starting 4 epochs, my loss did not change with the epochs but after that, it started changing. Could it be because of the high learning rate, local minima or something else like some regularisation parameter is high??

Topic mlp deep-learning neural-network classification machine-learning

Category Data Science

Brian Spiering · Accepted Answer · 2021年2月26日 02:22

1

Brian Spiering answered at 2021年2月26日 02:22

It could be any of those factors. The root cause can be found through experimentation. Hold everything constant and change a single factor. Then systematically change each factor while holding all other factors constant.

Training loss stuck in the starting epochs but then starts decreasing. What could be the reason for it?

About