Epoch: 0001 train_loss= 2.09221 train_acc= 0.14340 val_loss= 2.08984 val_acc= 0.03448 time= 0.60963
Epoch: 0002 train_loss= 2.05659 train_acc= 0.17736 val_loss= 2.08946 val_acc= 0.13793 time= 0.01563
Epoch: 0003 train_loss= 2.06748 train_acc= 0.14340 val_loss= 2.09207 val_acc= 0.13793 time= 0.01563
Epoch: 0004 train_loss= 2.06210 train_acc= 0.18491 val_loss= 2.09645 val_acc= 0.13793 time= 0.01563
Epoch: 0005 train_loss= 2.06417 train_acc= 0.16981 val_loss= 2.10402 val_acc= 0.13793 time= 0.01563
Epoch: 0006 train_loss= 2.05085 train_acc= 0.20755 val_loss= 2.10756 val_acc= 0.17241 time= 0.01563
Epoch: 0007 train_loss= 2.06584 train_acc= 0.16981 val_loss= 2.09926 val_acc= 0.20690 time= 0.01563
Epoch: 0008 train_loss= 2.06099 train_acc= 0.20000 val_loss= 2.08640 val_acc= 0.20690 time= 0.01563
Epoch: 0009 train_loss= 2.06411 train_acc= 0.18868 val_loss= 2.07320 val_acc= 0.17241 time= 0.01563
Epoch: 0010 train_loss= 2.05101 train_acc= 0.19245 val_loss= 2.06270 val_acc= 0.24138 time= 0.01563
Epoch: 0011 train_loss= 2.07441 train_acc= 0.15849 val_loss= 2.05683 val_acc= 0.24138 time= 0.01563
Epoch: 0012 train_loss= 2.07322 train_acc= 0.13585 val_loss= 2.05365 val_acc= 0.24138 time= 0.01563
Epoch: 0013 train_loss= 2.05962 train_acc= 0.16226 val_loss= 2.05402 val_acc= 0.17241 time= 0.01563
Epoch: 0014 train_loss= 2.03763 train_acc= 0.18491 val_loss= 2.05637 val_acc= 0.13793 time= 0.01563
Epoch: 0015 train_loss= 2.04397 train_acc= 0.20000 val_loss= 2.05997 val_acc= 0.06897 time= 0.01563
Epoch: 0016 train_loss= 2.02806 train_acc= 0.20755 val_loss= 2.06361 val_acc= 0.06897 time= 0.00000
Epoch: 0017 train_loss= 2.04944 train_acc= 0.18113 val_loss= 2.06793 val_acc= 0.03448 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 2.06049 accuracy= 0.22034 time= 0.01562 
