Epoch: 0001 train_loss= 2.08719 train_acc= 0.12129 val_loss= 2.08476 val_acc= 0.13793 time= 0.79735
Epoch: 0002 train_loss= 2.08456 train_acc= 0.18059 val_loss= 2.08296 val_acc= 0.13793 time= 0.01563
Epoch: 0003 train_loss= 2.08222 train_acc= 0.16712 val_loss= 2.08143 val_acc= 0.13793 time= 0.00000
Epoch: 0004 train_loss= 2.08014 train_acc= 0.16981 val_loss= 2.08012 val_acc= 0.13793 time= 0.01563
Epoch: 0005 train_loss= 2.07837 train_acc= 0.16442 val_loss= 2.07912 val_acc= 0.13793 time= 0.01563
Epoch: 0006 train_loss= 2.07671 train_acc= 0.15903 val_loss= 2.07844 val_acc= 0.13793 time= 0.00000
Epoch: 0007 train_loss= 2.07508 train_acc= 0.16442 val_loss= 2.07801 val_acc= 0.13793 time= 0.01563
Epoch: 0008 train_loss= 2.07328 train_acc= 0.16442 val_loss= 2.07782 val_acc= 0.13793 time= 0.00000
Epoch: 0009 train_loss= 2.07294 train_acc= 0.16442 val_loss= 2.07778 val_acc= 0.13793 time= 0.01563
Epoch: 0010 train_loss= 2.07152 train_acc= 0.16442 val_loss= 2.07783 val_acc= 0.13793 time= 0.00000
Epoch: 0011 train_loss= 2.06956 train_acc= 0.16442 val_loss= 2.07802 val_acc= 0.13793 time= 0.01563
Epoch: 0012 train_loss= 2.06942 train_acc= 0.16442 val_loss= 2.07828 val_acc= 0.13793 time= 0.00000
Epoch: 0013 train_loss= 2.06802 train_acc= 0.16712 val_loss= 2.07850 val_acc= 0.13793 time= 0.01563
Epoch: 0014 train_loss= 2.06739 train_acc= 0.16442 val_loss= 2.07874 val_acc= 0.13793 time= 0.00000
Early stopping...
Optimization Finished!
Test set results: cost= 2.06216 accuracy= 0.16949 time= 0.01562 
