# Problem with Training and trying to plot loss function in Flux
**URL:** https://discourse.julialang.org/t/problem-with-training-and-trying-to-plot-loss-function-in-flux/85826
**Category:** New to Julia
**Created:** [August 16, 2022, 1:49pm UTC](https://discourse.julialang.org/t/problem-with-training-and-trying-to-plot-loss-function-in-flux/85826 "2022-08-16T13:49:55Z")
**Posts on this page:** 6
**Page:** 1
### Author:  [@ak47](https://discourse.julialang.org/u/ak47)
#### Post date: [August 16, 2022, 1:49pm UTC](https://discourse.julialang.org/t/problem-with-training-and-trying-to-plot-loss-function-in-flux/85826/1 "2022-08-16T13:49:55Z")
Been testing some basic code and trying to plot its loss function but get some errors. Need your help to move on. Here is the code:
using Flux
actual(x) = 2x + 3
x\_train, x\_test = hcat(0:5…), hcat(6:10…)
y\_train, y\_test = actual.(x\_train), actual.(x\_test)
model = Dense(1, 1)
predict = model
loss(x, y) = Flux.Losses.mse(predict(x), y)
opt = Descent()
data = [(x\_train, y\_train)]
parameters = Flux.params(predict)
Flux.train!(loss, parameters, data, opt)’
**I get error on this last block of code**
epochs = Int64
loss\_on\_train = Float32
loss\_on\_test = Float32
for epoch in 1:2000
Flux.train!(loss, parameters,data, opt)
# we record our training loss
push!(epochs, epoch)
push!(loss\_on\_test, loss(x\_test, y\_test).data)
push!(loss\_on\_train, loss(x\_train, y\_train).data)
end
using Plots
plot(epochs, loss\_on\_train, lab=“Training”, c=:black, lw=2);
plot!(epochs, loss\_on\_test, lab=“Testing”, c=:teal, ls=:dot);
yaxis!(“Loss”, :log);
xaxis!(“Training epoch”)
**Here is the error:**
type Float32 has no field data
---
### Author:  [@gdalle](https://discourse.julialang.org/u/gdalle)
#### Post date: [August 16, 2022, 2:53pm UTC](https://discourse.julialang.org/t/problem-with-training-and-trying-to-plot-loss-function-in-flux/85826/2 "2022-08-16T14:53:37Z")
> [@ak47](#):
>
> push!(loss\_on\_test, loss(x\_test, y\_test).data)
> push!(loss\_on\_train, loss(x\_train, y\_train).data)
Hi @ak47! I’m willing to bet the error comes from these two lines: you don’t need to take the `.data` field of the loss, since it is already a number (`Float32` in this case).
---
### Author:  [@ak47](https://discourse.julialang.org/u/ak47)
#### Post date: [August 17, 2022, 4:57am UTC](https://discourse.julialang.org/t/problem-with-training-and-trying-to-plot-loss-function-in-flux/85826/3 "2022-08-17T04:57:31Z")
Thank you Gdalle. The error goes away but the plot still does not work…
---
### Author:  [@ak47](https://discourse.julialang.org/u/ak47)
#### Post date: [August 17, 2022, 5:47am UTC](https://discourse.julialang.org/t/problem-with-training-and-trying-to-plot-loss-function-in-flux/85826/4 "2022-08-17T05:47:43Z")
Push records only the final loss and that seems the reason why it doesn’t plot. How do I modify this ?
---
### Author:  [@gdalle](https://discourse.julialang.org/u/gdalle)
#### Post date: [August 17, 2022, 10:31am UTC](https://discourse.julialang.org/t/problem-with-training-and-trying-to-plot-loss-function-in-flux/85826/5 "2022-08-17T10:31:00Z")
I’m not sure what’s wrong, it works with the following code for me (which is the same as yours):
```julia
using Flux, Plots
actual(x) = 2x + 3
x_train, x_test = hcat(0:5...), hcat(6:10...)
y_train, y_test = actual.(x_train), actual.(x_test)
model = Dense(1, 1)
predict = model
loss(x, y) = Flux.Losses.mse(predict(x), y)
opt = Descent()
data = [(x_train, y_train)]
parameters = Flux.params(predict)
Flux.train!(loss, parameters, data, opt)
epochs = Int64[]
loss_on_train = Float32[]
loss_on_test = Float32[]
for epoch in 1:2000
Flux.train!(loss, parameters,data, opt)
# we record our training loss
push!(epochs, epoch)
push!(loss_on_test, loss(x_test, y_test))
push!(loss_on_train, loss(x_train, y_train))
end
plot(epochs, loss_on_train, lab="Training", c=:black, lw=2);
plot!(epochs, loss_on_test, lab="Testing", c=:teal, ls=:dot);
yaxis!("Loss", :log);
xaxis!("Training epoch")
```
To make life easier for other people, it’s best to use backticks on Discourse when displaying code (like I just did). Maybe the problem you had came from a copy-pasting issue?
---
### Author:  [@ak47](https://discourse.julialang.org/u/ak47)
#### Post date: [August 17, 2022, 4:13pm UTC](https://discourse.julialang.org/t/problem-with-training-and-trying-to-plot-loss-function-in-flux/85826/6 "2022-08-17T16:13:22Z")
Thanks for your time.