Epoch: 0001 train_loss= 2.11403 train_acc= 0.07925 val_loss= 2.11257 val_acc= 0.13793 time= 0.36208
Epoch: 0002 train_loss= 2.10379 train_acc= 0.10189 val_loss= 2.10621 val_acc= 0.13793 time= 0.00800
Epoch: 0003 train_loss= 2.13341 train_acc= 0.07925 val_loss= 2.10113 val_acc= 0.06897 time= 0.00900
Epoch: 0004 train_loss= 2.09173 train_acc= 0.12830 val_loss= 2.09706 val_acc= 0.03448 time= 0.00900
Epoch: 0005 train_loss= 2.08487 train_acc= 0.12830 val_loss= 2.09389 val_acc= 0.06897 time= 0.01000
Epoch: 0006 train_loss= 2.07317 train_acc= 0.18868 val_loss= 2.09171 val_acc= 0.06897 time= 0.00700
Epoch: 0007 train_loss= 2.07583 train_acc= 0.16981 val_loss= 2.09053 val_acc= 0.10345 time= 0.00900
Epoch: 0008 train_loss= 2.07131 train_acc= 0.17736 val_loss= 2.08949 val_acc= 0.10345 time= 0.00800
Epoch: 0009 train_loss= 2.07214 train_acc= 0.16226 val_loss= 2.08866 val_acc= 0.06897 time= 0.00900
Epoch: 0010 train_loss= 2.07750 train_acc= 0.14340 val_loss= 2.08769 val_acc= 0.06897 time= 0.00900
Epoch: 0011 train_loss= 2.06707 train_acc= 0.15849 val_loss= 2.08708 val_acc= 0.06897 time= 0.00800
Epoch: 0012 train_loss= 2.06328 train_acc= 0.19623 val_loss= 2.08665 val_acc= 0.06897 time= 0.00800
Epoch: 0013 train_loss= 2.06640 train_acc= 0.14340 val_loss= 2.08634 val_acc= 0.06897 time= 0.00800
Epoch: 0014 train_loss= 2.06289 train_acc= 0.16981 val_loss= 2.08571 val_acc= 0.06897 time= 0.00900
Epoch: 0015 train_loss= 2.05756 train_acc= 0.16604 val_loss= 2.08486 val_acc= 0.06897 time= 0.00800
Epoch: 0016 train_loss= 2.05962 train_acc= 0.16981 val_loss= 2.08395 val_acc= 0.06897 time= 0.00800
Epoch: 0017 train_loss= 2.05710 train_acc= 0.16981 val_loss= 2.08283 val_acc= 0.06897 time= 0.00900
Epoch: 0018 train_loss= 2.05588 train_acc= 0.16226 val_loss= 2.08172 val_acc= 0.06897 time= 0.00800
Epoch: 0019 train_loss= 2.05396 train_acc= 0.15094 val_loss= 2.08048 val_acc= 0.06897 time= 0.00800
Epoch: 0020 train_loss= 2.05761 train_acc= 0.15849 val_loss= 2.07956 val_acc= 0.06897 time= 0.00900
Epoch: 0021 train_loss= 2.05582 train_acc= 0.15472 val_loss= 2.07881 val_acc= 0.06897 time= 0.00800
Epoch: 0022 train_loss= 2.05686 train_acc= 0.15472 val_loss= 2.07844 val_acc= 0.03448 time= 0.00800
Epoch: 0023 train_loss= 2.05318 train_acc= 0.18868 val_loss= 2.07813 val_acc= 0.06897 time= 0.00800
Epoch: 0024 train_loss= 2.04955 train_acc= 0.16981 val_loss= 2.07782 val_acc= 0.06897 time= 0.00800
Epoch: 0025 train_loss= 2.04536 train_acc= 0.17358 val_loss= 2.07745 val_acc= 0.10345 time= 0.00700
Epoch: 0026 train_loss= 2.04342 train_acc= 0.20755 val_loss= 2.07760 val_acc= 0.10345 time= 0.00900
Epoch: 0027 train_loss= 2.04557 train_acc= 0.16604 val_loss= 2.07798 val_acc= 0.10345 time= 0.00800
Epoch: 0028 train_loss= 2.04194 train_acc= 0.17358 val_loss= 2.07865 val_acc= 0.10345 time= 0.00800
Epoch: 0029 train_loss= 2.04611 train_acc= 0.19623 val_loss= 2.07982 val_acc= 0.10345 time= 0.00800
Early stopping...
Optimization Finished!
Test set results: cost= 2.07171 accuracy= 0.06780 time= 0.00300 
