Epoch: 0001 train_loss= 2.08510 train_acc= 0.11321 val_loss= 2.09276 val_acc= 0.06897 time= 0.77576
Epoch: 0002 train_loss= 2.08271 train_acc= 0.12129 val_loss= 2.09121 val_acc= 0.06897 time= 0.00600
Epoch: 0003 train_loss= 2.08064 train_acc= 0.11860 val_loss= 2.08987 val_acc= 0.13793 time= 0.00500
Epoch: 0004 train_loss= 2.07854 train_acc= 0.12938 val_loss= 2.08870 val_acc= 0.13793 time= 0.00600
Epoch: 0005 train_loss= 2.07702 train_acc= 0.13747 val_loss= 2.08763 val_acc= 0.13793 time= 0.00600
Epoch: 0006 train_loss= 2.07429 train_acc= 0.14555 val_loss= 2.08664 val_acc= 0.13793 time= 0.00600
Epoch: 0007 train_loss= 2.07250 train_acc= 0.13477 val_loss= 2.08577 val_acc= 0.13793 time= 0.00600
Epoch: 0008 train_loss= 2.07007 train_acc= 0.14555 val_loss= 2.08496 val_acc= 0.13793 time= 0.00500
Epoch: 0009 train_loss= 2.06979 train_acc= 0.14286 val_loss= 2.08412 val_acc= 0.13793 time= 0.00600
Epoch: 0010 train_loss= 2.06717 train_acc= 0.14555 val_loss= 2.08313 val_acc= 0.13793 time= 0.00600
Epoch: 0011 train_loss= 2.06421 train_acc= 0.14825 val_loss= 2.08224 val_acc= 0.13793 time= 0.00625
Epoch: 0012 train_loss= 2.06437 train_acc= 0.15094 val_loss= 2.08131 val_acc= 0.13793 time= 0.00600
Epoch: 0013 train_loss= 2.06275 train_acc= 0.14825 val_loss= 2.08023 val_acc= 0.13793 time= 0.00600
Epoch: 0014 train_loss= 2.05993 train_acc= 0.15094 val_loss= 2.07890 val_acc= 0.13793 time= 0.00600
Epoch: 0015 train_loss= 2.05873 train_acc= 0.16442 val_loss= 2.07725 val_acc= 0.20690 time= 0.00600
Epoch: 0016 train_loss= 2.05836 train_acc= 0.17251 val_loss= 2.07524 val_acc= 0.20690 time= 0.00500
Epoch: 0017 train_loss= 2.05720 train_acc= 0.15903 val_loss= 2.07284 val_acc= 0.20690 time= 0.00500
Epoch: 0018 train_loss= 2.05558 train_acc= 0.17251 val_loss= 2.07016 val_acc= 0.20690 time= 0.00700
Epoch: 0019 train_loss= 2.05295 train_acc= 0.16981 val_loss= 2.06720 val_acc= 0.20690 time= 0.00500
Epoch: 0020 train_loss= 2.05412 train_acc= 0.16981 val_loss= 2.06389 val_acc= 0.20690 time= 0.00600
Epoch: 0021 train_loss= 2.05297 train_acc= 0.16981 val_loss= 2.06008 val_acc= 0.20690 time= 0.00500
Epoch: 0022 train_loss= 2.04910 train_acc= 0.16981 val_loss= 2.05575 val_acc= 0.20690 time= 0.00500
Epoch: 0023 train_loss= 2.05050 train_acc= 0.16981 val_loss= 2.05112 val_acc= 0.20690 time= 0.00600
Epoch: 0024 train_loss= 2.04794 train_acc= 0.16981 val_loss= 2.04694 val_acc= 0.20690 time= 0.00600
Epoch: 0025 train_loss= 2.04941 train_acc= 0.16981 val_loss= 2.04333 val_acc= 0.20690 time= 0.00500
Epoch: 0026 train_loss= 2.04831 train_acc= 0.16981 val_loss= 2.04014 val_acc= 0.20690 time= 0.00500
Epoch: 0027 train_loss= 2.04765 train_acc= 0.16981 val_loss= 2.03740 val_acc= 0.20690 time= 0.00600
Epoch: 0028 train_loss= 2.05091 train_acc= 0.16981 val_loss= 2.03542 val_acc= 0.20690 time= 0.00600
Epoch: 0029 train_loss= 2.04933 train_acc= 0.16712 val_loss= 2.03417 val_acc= 0.20690 time= 0.00500
Epoch: 0030 train_loss= 2.04825 train_acc= 0.16981 val_loss= 2.03376 val_acc= 0.20690 time= 0.00600
Epoch: 0031 train_loss= 2.05071 train_acc= 0.16981 val_loss= 2.03381 val_acc= 0.20690 time= 0.00500
Epoch: 0032 train_loss= 2.04765 train_acc= 0.16981 val_loss= 2.03390 val_acc= 0.20690 time= 0.00600
Epoch: 0033 train_loss= 2.04930 train_acc= 0.16712 val_loss= 2.03412 val_acc= 0.20690 time= 0.00500
Epoch: 0034 train_loss= 2.04764 train_acc= 0.16981 val_loss= 2.03470 val_acc= 0.20690 time= 0.00500
Epoch: 0035 train_loss= 2.04498 train_acc= 0.16981 val_loss= 2.03550 val_acc= 0.20690 time= 0.00700
Epoch: 0036 train_loss= 2.04646 train_acc= 0.16981 val_loss= 2.03618 val_acc= 0.20690 time= 0.00600
Early stopping...
Optimization Finished!
Test set results: cost= 2.08035 accuracy= 0.13559 time= 0.00300 
