# How to update learning rate during Flux training in a better manner?

**URL:** <https://discourse.julialang.org/t/how-to-update-learning-rate-during-flux-training-in-a-better-manner/53101>\
**Category:** New to Julia\
**Tags:** flux\
**Created:** [January 10, 2021, 4:35am UTC](https://discourse.julialang.org/t/how-to-update-learning-rate-during-flux-training-in-a-better-manner/53101 "2021-01-10T04:35:12Z")\
**Posts on this page:** 1\
**Showing post:** 8

<div class="post-metadata">

**Author:** ![ToucheSir](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/touchesir/32/14411_2.png) [@ToucheSir](https://discourse.julialang.org/u/ToucheSir)\
**Post date:** [December 23, 2023, 5:37am UTC](https://discourse.julialang.org/t/how-to-update-learning-rate-during-flux-training-in-a-better-manner/53101/8 "2023-12-23T05:37:16Z")

</div>

The error comes from trying to mix old style optimization rules (`Optimiser` and `ExpDecay`) with the new-style Optimisers.jl API Flux favours now. [Optimisation Rules · Flux](https://fluxml.ai/Flux.jl/stable/training/optimisers/#man-optimisers) has a warning about this.

If you’re fine with writing a couple more lines to turn that `train!` call into a custom training loop, then see my runnable example of how to schedule parameters using the new optimization interface + ParameterSchedulers.jl in [Learning rate scheduler with the new interface of Flux - #5 by ToucheSir](https://discourse.julialang.org/t/learning-rate-scheduler-with-the-new-interface-of-flux/107142/5).

---

_[View the full topic](https://discourse.julialang.org/t/how-to-update-learning-rate-during-flux-training-in-a-better-manner/53101)._