# Informer struggling to learn

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Finformer-struggling-to-learn%2F42206%3E%5C
**Category:** Models\
**Created:** [June 6, 2023, 4:46am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Finformer-struggling-to-learn%2F42206 "2023-06-06T04:46:25Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![Matt322](https://avatars.discourse-cdn.com/v4/letter/m/839c29/32.png) [@Matt322](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FMatt322)%5C
**Post date:** [June 6, 2023, 4:46am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Finformer-struggling-to-learn%2F42206%2F1 "2023-06-06T04:46:25Z")

</div>

I am experimenting with using the informer to forecast stock prices, and when I start training, it only ever gets as far as generating a noisy output relatively close to the target, not even a linear approximation:  
 ![informerguess](https://us1.discourse-cdn.com/hellohellohello/original/3X/a/3/a317b0fcb1f70c338494a0693d27913dcb5e891d.png)  
I have experimented with context lengths from 8000 to 1000, lots of different learning rates, normalizing the data, and increasing the d\_model and feed-forward layer dimensions, but nothing seems to improve it beyond the above picture. Any advice would be much appreciated!