Epoch: 0001 train_loss= 2.08463 train_acc= 0.13208 val_loss= 2.08511 val_acc= 0.06897 time= 0.26564
Epoch: 0002 train_loss= 2.08245 train_acc= 0.12579 val_loss= 2.08435 val_acc= 0.06897 time= 0.00000
Epoch: 0003 train_loss= 2.08204 train_acc= 0.11950 val_loss= 2.08348 val_acc= 0.06897 time= 0.00000
Epoch: 0004 train_loss= 2.08281 train_acc= 0.12579 val_loss= 2.08260 val_acc= 0.06897 time= 0.01563
Epoch: 0005 train_loss= 2.08149 train_acc= 0.13836 val_loss= 2.08177 val_acc= 0.06897 time= 0.00000
Epoch: 0006 train_loss= 2.08074 train_acc= 0.14465 val_loss= 2.08089 val_acc= 0.06897 time= 0.00000
Epoch: 0007 train_loss= 2.07737 train_acc= 0.12579 val_loss= 2.08000 val_acc= 0.10345 time= 0.00000
Epoch: 0008 train_loss= 2.07765 train_acc= 0.13836 val_loss= 2.07905 val_acc= 0.10345 time= 0.01563
Epoch: 0009 train_loss= 2.07576 train_acc= 0.15094 val_loss= 2.07814 val_acc= 0.17241 time= 0.01096
Epoch: 0010 train_loss= 2.07638 train_acc= 0.12579 val_loss= 2.07724 val_acc= 0.17241 time= 0.00600
Epoch: 0011 train_loss= 2.07348 train_acc= 0.15094 val_loss= 2.07632 val_acc= 0.20690 time= 0.00600
Epoch: 0012 train_loss= 2.07346 train_acc= 0.16981 val_loss= 2.07542 val_acc= 0.20690 time= 0.00400
Epoch: 0013 train_loss= 2.07353 train_acc= 0.15723 val_loss= 2.07448 val_acc= 0.20690 time= 0.00400
Epoch: 0014 train_loss= 2.07197 train_acc= 0.13836 val_loss= 2.07357 val_acc= 0.20690 time= 0.00500
Epoch: 0015 train_loss= 2.07324 train_acc= 0.16352 val_loss= 2.07254 val_acc= 0.20690 time= 0.00500
Epoch: 0016 train_loss= 2.07025 train_acc= 0.14465 val_loss= 2.07147 val_acc= 0.20690 time= 0.00400
Epoch: 0017 train_loss= 2.06799 train_acc= 0.14465 val_loss= 2.07049 val_acc= 0.13793 time= 0.00500
Epoch: 0018 train_loss= 2.06427 train_acc= 0.22642 val_loss= 2.06956 val_acc= 0.17241 time= 0.00112
Epoch: 0019 train_loss= 2.06561 train_acc= 0.20755 val_loss= 2.06874 val_acc= 0.13793 time= 0.00000
Epoch: 0020 train_loss= 2.06447 train_acc= 0.19497 val_loss= 2.06800 val_acc= 0.10345 time= 0.00000
Epoch: 0021 train_loss= 2.06467 train_acc= 0.15723 val_loss= 2.06730 val_acc= 0.10345 time= 0.01562
Epoch: 0022 train_loss= 2.06330 train_acc= 0.17610 val_loss= 2.06674 val_acc= 0.10345 time= 0.00000
Epoch: 0023 train_loss= 2.06130 train_acc= 0.18239 val_loss= 2.06631 val_acc= 0.10345 time= 0.00000
Epoch: 0024 train_loss= 2.06218 train_acc= 0.14465 val_loss= 2.06610 val_acc= 0.10345 time= 0.01563
Epoch: 0025 train_loss= 2.06143 train_acc= 0.16981 val_loss= 2.06609 val_acc= 0.10345 time= 0.00000
Epoch: 0026 train_loss= 2.06085 train_acc= 0.18239 val_loss= 2.06622 val_acc= 0.10345 time= 0.00000
Epoch: 0027 train_loss= 2.06006 train_acc= 0.17610 val_loss= 2.06643 val_acc= 0.10345 time= 0.01563
Epoch: 0028 train_loss= 2.05996 train_acc= 0.19497 val_loss= 2.06672 val_acc= 0.10345 time= 0.00000
Epoch: 0029 train_loss= 2.06074 train_acc= 0.17610 val_loss= 2.06691 val_acc= 0.10345 time= 0.00000
Early stopping...
Optimization Finished!
Test set results: cost= 2.11699 accuracy= 0.13559 time= 0.00000 
