Epoch: 0001 train_loss= 2.08702 train_acc= 0.12938 val_loss= 2.07069 val_acc= 0.13793 time= 0.26564
Epoch: 0002 train_loss= 2.07095 train_acc= 0.12129 val_loss= 2.06225 val_acc= 0.13793 time= 0.01563
Epoch: 0003 train_loss= 2.06816 train_acc= 0.15094 val_loss= 2.05552 val_acc= 0.20690 time= 0.01563
Epoch: 0004 train_loss= 2.06511 train_acc= 0.15094 val_loss= 2.04823 val_acc= 0.17241 time= 0.00000
Epoch: 0005 train_loss= 2.06441 train_acc= 0.16442 val_loss= 2.04183 val_acc= 0.13793 time= 0.01563
Epoch: 0006 train_loss= 2.06021 train_acc= 0.17520 val_loss= 2.03792 val_acc= 0.17241 time= 0.01563
Epoch: 0007 train_loss= 2.06165 train_acc= 0.16173 val_loss= 2.03485 val_acc= 0.17241 time= 0.00000
Epoch: 0008 train_loss= 2.05668 train_acc= 0.16712 val_loss= 2.03344 val_acc= 0.17241 time= 0.01563
Epoch: 0009 train_loss= 2.06648 train_acc= 0.18059 val_loss= 2.03185 val_acc= 0.17241 time= 0.01563
Epoch: 0010 train_loss= 2.05905 train_acc= 0.17251 val_loss= 2.03149 val_acc= 0.17241 time= 0.00000
Epoch: 0011 train_loss= 2.05623 train_acc= 0.15903 val_loss= 2.03102 val_acc= 0.17241 time= 0.01563
Epoch: 0012 train_loss= 2.05975 train_acc= 0.17251 val_loss= 2.03248 val_acc= 0.17241 time= 0.01563
Epoch: 0013 train_loss= 2.06165 train_acc= 0.17790 val_loss= 2.03501 val_acc= 0.17241 time= 0.00000
Epoch: 0014 train_loss= 2.05685 train_acc= 0.17520 val_loss= 2.03731 val_acc= 0.17241 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 2.04264 accuracy= 0.11864 time= 0.00000 
