# How to show loss value of the neural network after solving by Neural.NNODE?

**URL:** https://discourse.julialang.org/t/how-to-show-loss-value-of-the-neural-network-after-solving-by-neural-nnode/100241
**Category:** Community
**Tags:** question, neural-network
**Created:** [June 12, 2023, 5:35pm UTC](https://discourse.julialang.org/t/how-to-show-loss-value-of-the-neural-network-after-solving-by-neural-nnode/100241 "2023-06-12T17:35:58Z")
**Posts on this page:** 2
**Page:** 1

<div class="post-metadata">

### Author: ![Ethan\_Tran](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/ethan_tran/32/49198_2.png) [@Ethan\_Tran](https://discourse.julialang.org/u/Ethan_Tran)
#### Post date: [June 12, 2023, 5:35pm UTC](https://discourse.julialang.org/t/how-to-show-loss-value-of-the-neural-network-after-solving-by-neural-nnode/100241/1 "2023-06-12T17:35:59Z")

</div>

I am using NeuralPDE to solve the ODE system. Because the iterations of the network are high (I choose 3000), I set the verbose as false as the following code to cut off the displaying of current loss:

```julia
chain = Flux.Chain(Flux.Dense(1, 6, tanh),Flux.Dense(6, 2))
opt = OptimizationOptimisers.Adam(0.03)
sol = solve(prob, NeuralPDE.NNODE(chain, opt), verbose=false, abstol=1f-6, maxiters=3000)

```

In my case how could I access the loss of the network after solving it?  
Thank you all.

---

<div class="post-metadata">

### Author: ![ChrisRackauckas](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/chrisrackauckas/32/77_2.png) [@ChrisRackauckas](https://discourse.julialang.org/u/ChrisRackauckas)
#### Post date: [June 17, 2023, 2:33pm UTC](https://discourse.julialang.org/t/how-to-show-loss-value-of-the-neural-network-after-solving-by-neural-nnode/100241/2 "2023-06-17T14:33:43Z")

</div>

`sol.k.objective`