Epoch: 0001 train_loss= 2.08425 train_acc= 0.16442 val_loss= 2.08632 val_acc= 0.10345 time= 0.28169
Epoch: 0002 train_loss= 2.08375 train_acc= 0.14555 val_loss= 2.08485 val_acc= 0.13793 time= 0.01520
Epoch: 0003 train_loss= 2.07841 train_acc= 0.14825 val_loss= 2.08339 val_acc= 0.13793 time= 0.01563
Epoch: 0004 train_loss= 2.07479 train_acc= 0.16442 val_loss= 2.08220 val_acc= 0.13793 time= 0.00000
Epoch: 0005 train_loss= 2.07133 train_acc= 0.16981 val_loss= 2.08068 val_acc= 0.13793 time= 0.01563
Epoch: 0006 train_loss= 2.06747 train_acc= 0.15903 val_loss= 2.07886 val_acc= 0.13793 time= 0.00000
Epoch: 0007 train_loss= 2.06783 train_acc= 0.15094 val_loss= 2.07697 val_acc= 0.10345 time= 0.01563
Epoch: 0008 train_loss= 2.06562 train_acc= 0.16981 val_loss= 2.07524 val_acc= 0.10345 time= 0.00000
Epoch: 0009 train_loss= 2.06878 train_acc= 0.17520 val_loss= 2.07321 val_acc= 0.06897 time= 0.01563
Epoch: 0010 train_loss= 2.06016 train_acc= 0.16173 val_loss= 2.07079 val_acc= 0.06897 time= 0.01563
Epoch: 0011 train_loss= 2.06172 train_acc= 0.15903 val_loss= 2.06829 val_acc= 0.06897 time= 0.00000
Epoch: 0012 train_loss= 2.05247 train_acc= 0.16173 val_loss= 2.06615 val_acc= 0.06897 time= 0.01562
Epoch: 0013 train_loss= 2.05947 train_acc= 0.15364 val_loss= 2.06292 val_acc= 0.06897 time= 0.00000
Epoch: 0014 train_loss= 2.05675 train_acc= 0.15364 val_loss= 2.05999 val_acc= 0.13793 time= 0.01563
Epoch: 0015 train_loss= 2.05561 train_acc= 0.19137 val_loss= 2.05737 val_acc= 0.10345 time= 0.01563
Epoch: 0016 train_loss= 2.05483 train_acc= 0.17790 val_loss= 2.05544 val_acc= 0.13793 time= 0.00000
Epoch: 0017 train_loss= 2.05350 train_acc= 0.19407 val_loss= 2.05290 val_acc= 0.13793 time= 0.01562
Epoch: 0018 train_loss= 2.05346 train_acc= 0.18598 val_loss= 2.05044 val_acc= 0.13793 time= 0.00000
Epoch: 0019 train_loss= 2.05418 train_acc= 0.15903 val_loss= 2.04937 val_acc= 0.13793 time= 0.01563
Epoch: 0020 train_loss= 2.05476 train_acc= 0.18329 val_loss= 2.04904 val_acc= 0.13793 time= 0.00000
Epoch: 0021 train_loss= 2.04761 train_acc= 0.17251 val_loss= 2.04930 val_acc= 0.13793 time= 0.01563
Epoch: 0022 train_loss= 2.05149 train_acc= 0.15633 val_loss= 2.04991 val_acc= 0.13793 time= 0.01563
Epoch: 0023 train_loss= 2.05128 train_acc= 0.15903 val_loss= 2.05163 val_acc= 0.13793 time= 0.00000
Epoch: 0024 train_loss= 2.04760 train_acc= 0.19407 val_loss= 2.05247 val_acc= 0.13793 time= 0.01562
Epoch: 0025 train_loss= 2.04191 train_acc= 0.19677 val_loss= 2.05358 val_acc= 0.13793 time= 0.00000
Early stopping...
Optimization Finished!
Test set results: cost= 2.07837 accuracy= 0.06780 time= 0.01563 
