Epoch: 0001 train_loss= 2.10130 train_acc= 0.11590 val_loss= 2.10238 val_acc= 0.13793 time= 0.70216
Epoch: 0002 train_loss= 2.09928 train_acc= 0.10782 val_loss= 2.10336 val_acc= 0.10345 time= 0.00900
Epoch: 0003 train_loss= 2.09011 train_acc= 0.13477 val_loss= 2.10320 val_acc= 0.13793 time= 0.01000
Epoch: 0004 train_loss= 2.07907 train_acc= 0.15633 val_loss= 2.10214 val_acc= 0.13793 time= 0.00800
Epoch: 0005 train_loss= 2.08690 train_acc= 0.16981 val_loss= 2.10106 val_acc= 0.13793 time= 0.00700
Epoch: 0006 train_loss= 2.07726 train_acc= 0.16173 val_loss= 2.09888 val_acc= 0.13793 time= 0.00900
Epoch: 0007 train_loss= 2.07743 train_acc= 0.18329 val_loss= 2.09674 val_acc= 0.13793 time= 0.00700
Epoch: 0008 train_loss= 2.07243 train_acc= 0.16981 val_loss= 2.09501 val_acc= 0.13793 time= 0.00900
Epoch: 0009 train_loss= 2.06533 train_acc= 0.15364 val_loss= 2.09220 val_acc= 0.10345 time= 0.00928
Epoch: 0010 train_loss= 2.06636 train_acc= 0.18059 val_loss= 2.08817 val_acc= 0.10345 time= 0.00900
Epoch: 0011 train_loss= 2.06767 train_acc= 0.14016 val_loss= 2.08298 val_acc= 0.13793 time= 0.00900
Epoch: 0012 train_loss= 2.06034 train_acc= 0.16981 val_loss= 2.07772 val_acc= 0.17241 time= 0.00900
Epoch: 0013 train_loss= 2.05761 train_acc= 0.18868 val_loss= 2.07325 val_acc= 0.17241 time= 0.00900
Epoch: 0014 train_loss= 2.06109 train_acc= 0.17790 val_loss= 2.06854 val_acc= 0.13793 time= 0.00900
Epoch: 0015 train_loss= 2.05997 train_acc= 0.16712 val_loss= 2.06467 val_acc= 0.17241 time= 0.00900
Epoch: 0016 train_loss= 2.05355 train_acc= 0.16442 val_loss= 2.06106 val_acc= 0.20690 time= 0.01000
Epoch: 0017 train_loss= 2.05349 train_acc= 0.21024 val_loss= 2.05755 val_acc= 0.24138 time= 0.00900
Epoch: 0018 train_loss= 2.05788 train_acc= 0.19946 val_loss= 2.05309 val_acc= 0.24138 time= 0.00900
Epoch: 0019 train_loss= 2.04404 train_acc= 0.18868 val_loss= 2.04886 val_acc= 0.27586 time= 0.00800
Epoch: 0020 train_loss= 2.05411 train_acc= 0.17251 val_loss= 2.04531 val_acc= 0.27586 time= 0.00900
Epoch: 0021 train_loss= 2.05091 train_acc= 0.17520 val_loss= 2.04210 val_acc= 0.27586 time= 0.00800
Epoch: 0022 train_loss= 2.04451 train_acc= 0.16981 val_loss= 2.03926 val_acc= 0.27586 time= 0.00900
Epoch: 0023 train_loss= 2.04391 train_acc= 0.17251 val_loss= 2.03784 val_acc= 0.24138 time= 0.00900
Epoch: 0024 train_loss= 2.05297 train_acc= 0.18868 val_loss= 2.03762 val_acc= 0.20690 time= 0.00900
Epoch: 0025 train_loss= 2.05034 train_acc= 0.19677 val_loss= 2.03794 val_acc= 0.20690 time= 0.01000
Epoch: 0026 train_loss= 2.04346 train_acc= 0.19137 val_loss= 2.03769 val_acc= 0.20690 time= 0.00900
Epoch: 0027 train_loss= 2.05246 train_acc= 0.16712 val_loss= 2.03877 val_acc= 0.20690 time= 0.00900
Epoch: 0028 train_loss= 2.04830 train_acc= 0.16981 val_loss= 2.04237 val_acc= 0.20690 time= 0.00900
Early stopping...
Optimization Finished!
Test set results: cost= 2.07419 accuracy= 0.16949 time= 0.00300 
