how do you realize that network train very good?

[m-tlb]

hi all

I am a student , I want creat a network with backpropagation.my input for training is P1,it has 9 rows and 379 columns and T has 1 row and 379 columns .in following you can see my code:
[pn,ps] = mapstd(P1);
[tn,ts] = mapstd(T);
net=newff(minmax(pn),minmax(tn),[9 12],{'tansig','tansig','purelin'},'trainlm');
net.trainParam.epochs=500;
net.trainParam.goal=1e-8;
net.trainParam.max_fail=6;
net.trainParam.mem_reduc=1;
net.trainParam.min_grad=1e-10;
net.trainParam.mu=0.001;
net.trainParam.mu_dec=0.1;
net.trainParam.mu_inc=10;
net.trainParam.mu_max=1e10;
net.trainParam.show=400;
net.trainParam.showCommandLine=1;
net.trainParam.showWindow=1;
net.trainParam.time=inf;
[net,tr]=train(net,pn,tn);
an = sim(net,pn);
a = mapstd('reverse',an,ts);
Diff=[T;a;abs(T-a)];
pnewn = mapstd('apply',Q1,ps);
anewn = sim(net,pnewn);
Qi is my new test data.it has 9 rows and 30 columns.
unfortunately this program don't give good result.
can you help me?what do I change in my program??????
one important question,how do you realize that network train very good?:-(

please help me.

Best regards