Epoch: 0001 train_loss= 2.16622 train_acc= 0.16981 val_loss= 2.11114 val_acc= 0.06897 time= 0.34384
Epoch: 0002 train_loss= 2.06654 train_acc= 0.15094 val_loss= 2.09022 val_acc= 0.06897 time= 0.01562
Epoch: 0003 train_loss= 2.07496 train_acc= 0.15723 val_loss= 2.07533 val_acc= 0.06897 time= 0.00000
Epoch: 0004 train_loss= 2.05946 train_acc= 0.19497 val_loss= 2.06195 val_acc= 0.24138 time= 0.01562
Epoch: 0005 train_loss= 2.05967 train_acc= 0.18868 val_loss= 2.05255 val_acc= 0.27586 time= 0.01563
Epoch: 0006 train_loss= 2.03752 train_acc= 0.18868 val_loss= 2.04677 val_acc= 0.27586 time= 0.01562
Epoch: 0007 train_loss= 2.03721 train_acc= 0.18239 val_loss= 2.04581 val_acc= 0.27586 time= 0.00000
Epoch: 0008 train_loss= 2.03687 train_acc= 0.17610 val_loss= 2.04719 val_acc= 0.27586 time= 0.01563
Epoch: 0009 train_loss= 2.05192 train_acc= 0.19497 val_loss= 2.04897 val_acc= 0.27586 time= 0.01563
Epoch: 0010 train_loss= 2.03515 train_acc= 0.18239 val_loss= 2.05051 val_acc= 0.17241 time= 0.01563
Epoch: 0011 train_loss= 2.01758 train_acc= 0.18868 val_loss= 2.05137 val_acc= 0.03448 time= 0.00000
Epoch: 0012 train_loss= 2.01574 train_acc= 0.16352 val_loss= 2.05352 val_acc= 0.00000 time= 0.01563
Epoch: 0013 train_loss= 2.03121 train_acc= 0.17610 val_loss= 2.05524 val_acc= 0.00000 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 2.09849 accuracy= 0.13559 time= 0.00000 
