Epoch: 0001 train_loss= 2.12444 train_acc= 0.13962 val_loss= 2.08697 val_acc= 0.17241 time= 0.63069
Epoch: 0002 train_loss= 2.07463 train_acc= 0.10943 val_loss= 2.08156 val_acc= 0.13793 time= 0.01563
Epoch: 0003 train_loss= 2.09024 train_acc= 0.11698 val_loss= 2.07833 val_acc= 0.13793 time= 0.01563
Epoch: 0004 train_loss= 2.06825 train_acc= 0.15094 val_loss= 2.07854 val_acc= 0.13793 time= 0.00000
Epoch: 0005 train_loss= 2.04783 train_acc= 0.15094 val_loss= 2.07690 val_acc= 0.10345 time= 0.03125
Epoch: 0006 train_loss= 2.06272 train_acc= 0.15849 val_loss= 2.07340 val_acc= 0.10345 time= 0.02324
Epoch: 0007 train_loss= 2.05542 train_acc= 0.15849 val_loss= 2.06839 val_acc= 0.17241 time= 0.01562
Epoch: 0008 train_loss= 2.04950 train_acc= 0.17736 val_loss= 2.06456 val_acc= 0.24138 time= 0.01525
Epoch: 0009 train_loss= 2.04893 train_acc= 0.16981 val_loss= 2.06244 val_acc= 0.27586 time= 0.01563
Epoch: 0010 train_loss= 2.03502 train_acc= 0.18113 val_loss= 2.06127 val_acc= 0.24138 time= 0.01562
Epoch: 0011 train_loss= 2.04926 train_acc= 0.18491 val_loss= 2.06275 val_acc= 0.24138 time= 0.01563
Epoch: 0012 train_loss= 2.05093 train_acc= 0.17358 val_loss= 2.06459 val_acc= 0.27586 time= 0.01563
Epoch: 0013 train_loss= 2.04671 train_acc= 0.19623 val_loss= 2.06748 val_acc= 0.24138 time= 0.01563
Epoch: 0014 train_loss= 2.04746 train_acc= 0.19245 val_loss= 2.06793 val_acc= 0.20690 time= 0.01563
Epoch: 0015 train_loss= 2.04362 train_acc= 0.18491 val_loss= 2.06494 val_acc= 0.20690 time= 0.01563
Epoch: 0016 train_loss= 2.03305 train_acc= 0.19623 val_loss= 2.06366 val_acc= 0.20690 time= 0.00000
Epoch: 0017 train_loss= 2.03022 train_acc= 0.19245 val_loss= 2.06435 val_acc= 0.17241 time= 0.01563
Epoch: 0018 train_loss= 2.03422 train_acc= 0.18113 val_loss= 2.06597 val_acc= 0.17241 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 2.09513 accuracy= 0.15254 time= 0.01563 
