Epoch: 0001 train_loss= 2.08738 train_acc= 0.10063 val_loss= 2.08499 val_acc= 0.13793 time= 0.14107
Epoch: 0002 train_loss= 2.08438 train_acc= 0.15094 val_loss= 2.08289 val_acc= 0.13793 time= 0.01519
Epoch: 0003 train_loss= 2.08173 train_acc= 0.15094 val_loss= 2.08079 val_acc= 0.13793 time= 0.00000
Epoch: 0004 train_loss= 2.07904 train_acc= 0.15094 val_loss= 2.07860 val_acc= 0.13793 time= 0.01562
Epoch: 0005 train_loss= 2.07597 train_acc= 0.15094 val_loss= 2.07649 val_acc= 0.13793 time= 0.01563
Epoch: 0006 train_loss= 2.07312 train_acc= 0.15094 val_loss= 2.07458 val_acc= 0.13793 time= 0.00000
Epoch: 0007 train_loss= 2.07079 train_acc= 0.15094 val_loss= 2.07281 val_acc= 0.13793 time= 0.01563
Epoch: 0008 train_loss= 2.06873 train_acc= 0.15094 val_loss= 2.07117 val_acc= 0.13793 time= 0.00000
Epoch: 0009 train_loss= 2.06544 train_acc= 0.15094 val_loss= 2.06972 val_acc= 0.13793 time= 0.01563
Epoch: 0010 train_loss= 2.06434 train_acc= 0.15094 val_loss= 2.06842 val_acc= 0.13793 time= 0.01563
Epoch: 0011 train_loss= 2.06085 train_acc= 0.15094 val_loss= 2.06731 val_acc= 0.13793 time= 0.00000
Epoch: 0012 train_loss= 2.05850 train_acc= 0.15094 val_loss= 2.06648 val_acc= 0.13793 time= 0.01563
Epoch: 0013 train_loss= 2.05688 train_acc= 0.15094 val_loss= 2.06601 val_acc= 0.13793 time= 0.01563
Epoch: 0014 train_loss= 2.05451 train_acc= 0.15094 val_loss= 2.06580 val_acc= 0.13793 time= 0.00000
Epoch: 0015 train_loss= 2.05153 train_acc= 0.16981 val_loss= 2.06589 val_acc= 0.20690 time= 0.01563
Epoch: 0016 train_loss= 2.05031 train_acc= 0.18239 val_loss= 2.06625 val_acc= 0.20690 time= 0.01563
Epoch: 0017 train_loss= 2.04872 train_acc= 0.18239 val_loss= 2.06690 val_acc= 0.20690 time= 0.00000
Epoch: 0018 train_loss= 2.04659 train_acc= 0.20126 val_loss= 2.06779 val_acc= 0.20690 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 2.12865 accuracy= 0.13559 time= 0.00000 
