> For the complete documentation index, see [llms.txt](https://machine-learning.paperspace.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://machine-learning.paperspace.com/wiki/convergence.md).

# Convergence

![Source: Stanford](https://2327526407-files.gitbook.io/~/files/v0/b/gitbook-legacy-files/o/assets%2F-LvBP1svpACTB1R1x_U4%2F-LvHJ32JL_4hyT9PVdc0%2F-LvHS7f9OSX0EwNd4h-f%2Fimage.png?alt=media\&token=997ff482-2d34-485c-90fe-ba5db69230a6)

A machine learning model reaches convergence when it achieves a state during training in which [loss](/wiki/accuracy-and-loss.md#loss) settles to within an error range around the final value.  In other words, a model converges when additional training will not improve the model.