Epoch: 0001 train_loss= 2.09243 train_acc= 0.14465 val_loss= 2.06941 val_acc= 0.17241 time= 0.07849
Epoch: 0002 train_loss= 2.08677 train_acc= 0.17610 val_loss= 2.06793 val_acc= 0.17241 time= 0.00000
Epoch: 0003 train_loss= 2.07609 train_acc= 0.17610 val_loss= 2.06703 val_acc= 0.10345 time= 0.01526
Epoch: 0004 train_loss= 2.07289 train_acc= 0.17610 val_loss= 2.06648 val_acc= 0.06897 time= 0.00000
Epoch: 0005 train_loss= 2.07183 train_acc= 0.19497 val_loss= 2.06626 val_acc= 0.06897 time= 0.01563
Epoch: 0006 train_loss= 2.06071 train_acc= 0.19497 val_loss= 2.06575 val_acc= 0.10345 time= 0.00000
Epoch: 0007 train_loss= 2.06212 train_acc= 0.12579 val_loss= 2.06493 val_acc= 0.10345 time= 0.01563
Epoch: 0008 train_loss= 2.04882 train_acc= 0.18239 val_loss= 2.06426 val_acc= 0.10345 time= 0.00000
Epoch: 0009 train_loss= 2.04909 train_acc= 0.17610 val_loss= 2.06370 val_acc= 0.06897 time= 0.01563
Epoch: 0010 train_loss= 2.04611 train_acc= 0.17610 val_loss= 2.06323 val_acc= 0.06897 time= 0.00000
Epoch: 0011 train_loss= 2.03922 train_acc= 0.18239 val_loss= 2.06276 val_acc= 0.10345 time= 0.01562
Epoch: 0012 train_loss= 2.04513 train_acc= 0.16352 val_loss= 2.06218 val_acc= 0.06897 time= 0.01563
Epoch: 0013 train_loss= 2.03846 train_acc= 0.16352 val_loss= 2.06178 val_acc= 0.17241 time= 0.00000
Epoch: 0014 train_loss= 2.03692 train_acc= 0.17610 val_loss= 2.06203 val_acc= 0.20690 time= 0.01563
Epoch: 0015 train_loss= 2.04303 train_acc= 0.17610 val_loss= 2.06283 val_acc= 0.20690 time= 0.00000
Epoch: 0016 train_loss= 2.02719 train_acc= 0.17610 val_loss= 2.06441 val_acc= 0.24138 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 2.09875 accuracy= 0.13559 time= 0.00000 
