How to differentiate between Mse(training) and Mse(testing) ??

Hello, i would like to know how to differentiate between Mse(training) and Mse(testing) during training phases this is my part of my ANN's code :

net.divideMode = 'sample';  % Divide up every sample
net.divideParam.trainRatio = 70/100;
net.divideParam.valRatio = 20/100;
net.divideParam.testRatio = 10/100; 
net.performFcn = 'mse'
MSEt(j,H) = mse(net,targets,outputs);%mean square error
*my question is  that MSE calculated is for training error or for testing error ??

Help please*

Answer 1

[Greg Heath]

In order to obtain the break down of mse into its trn/val/tst parts you have to obtain the training record, tr from training;

[ net tr Y E Xf Af ] = train ( net, X ,T, Xi, Ai );

 help train
 doc train

Hope this helps.

Greg