Epoch: 0001 train_loss= 2.13568 train_acc= 0.11590 val_loss= 2.17674 val_acc= 0.10345 time= 0.91556
Epoch: 0002 train_loss= 2.10866 train_acc= 0.14016 val_loss= 2.15095 val_acc= 0.10345 time= 0.01500
Epoch: 0003 train_loss= 2.10012 train_acc= 0.16442 val_loss= 2.12377 val_acc= 0.10345 time= 0.01500
Epoch: 0004 train_loss= 2.08293 train_acc= 0.14825 val_loss= 2.10681 val_acc= 0.10345 time= 0.01900
Epoch: 0005 train_loss= 2.07517 train_acc= 0.16173 val_loss= 2.09512 val_acc= 0.10345 time= 0.01600
Epoch: 0006 train_loss= 2.06185 train_acc= 0.15094 val_loss= 2.08652 val_acc= 0.10345 time= 0.01700
Epoch: 0007 train_loss= 2.07217 train_acc= 0.18059 val_loss= 2.08000 val_acc= 0.13793 time= 0.01400
Epoch: 0008 train_loss= 2.06863 train_acc= 0.15094 val_loss= 2.07376 val_acc= 0.10345 time= 0.01500
Epoch: 0009 train_loss= 2.06945 train_acc= 0.18059 val_loss= 2.06851 val_acc= 0.10345 time= 0.01600
Epoch: 0010 train_loss= 2.05274 train_acc= 0.17790 val_loss= 2.06200 val_acc= 0.10345 time= 0.01400
Epoch: 0011 train_loss= 2.05445 train_acc= 0.19946 val_loss= 2.05923 val_acc= 0.17241 time= 0.01500
Epoch: 0012 train_loss= 2.06139 train_acc= 0.15633 val_loss= 2.05783 val_acc= 0.20690 time= 0.01300
Epoch: 0013 train_loss= 2.05358 train_acc= 0.16173 val_loss= 2.05534 val_acc= 0.20690 time= 0.01400
Epoch: 0014 train_loss= 2.05076 train_acc= 0.16442 val_loss= 2.05240 val_acc= 0.20690 time= 0.01200
Epoch: 0015 train_loss= 2.04407 train_acc= 0.18329 val_loss= 2.05051 val_acc= 0.17241 time= 0.01400
Epoch: 0016 train_loss= 2.05060 train_acc= 0.15364 val_loss= 2.05113 val_acc= 0.17241 time= 0.01500
Epoch: 0017 train_loss= 2.04909 train_acc= 0.18598 val_loss= 2.05273 val_acc= 0.13793 time= 0.01400
Epoch: 0018 train_loss= 2.04316 train_acc= 0.19137 val_loss= 2.05432 val_acc= 0.13793 time= 0.01400
Epoch: 0019 train_loss= 2.04223 train_acc= 0.18329 val_loss= 2.05734 val_acc= 0.10345 time= 0.01300
Early stopping...
Optimization Finished!
Test set results: cost= 2.14505 accuracy= 0.13559 time= 0.00600 
