Epoch: 0001 train_loss= 2.08585 train_acc= 0.11860 val_loss= 2.08077 val_acc= 0.20690 time= 0.64461
Epoch: 0002 train_loss= 2.08411 train_acc= 0.13477 val_loss= 2.07802 val_acc= 0.20690 time= 0.00000
Epoch: 0003 train_loss= 2.08281 train_acc= 0.13747 val_loss= 2.07630 val_acc= 0.20690 time= 0.01563
Epoch: 0004 train_loss= 2.08109 train_acc= 0.14016 val_loss= 2.07470 val_acc= 0.20690 time= 0.01563
Epoch: 0005 train_loss= 2.07988 train_acc= 0.13747 val_loss= 2.07329 val_acc= 0.20690 time= 0.00000
Epoch: 0006 train_loss= 2.07875 train_acc= 0.14016 val_loss= 2.07194 val_acc= 0.20690 time= 0.01563
Epoch: 0007 train_loss= 2.07749 train_acc= 0.14016 val_loss= 2.07050 val_acc= 0.20690 time= 0.00000
Epoch: 0008 train_loss= 2.07601 train_acc= 0.13747 val_loss= 2.06925 val_acc= 0.20690 time= 0.01562
Epoch: 0009 train_loss= 2.07453 train_acc= 0.14286 val_loss= 2.06809 val_acc= 0.20690 time= 0.00000
Epoch: 0010 train_loss= 2.07345 train_acc= 0.14825 val_loss= 2.06708 val_acc= 0.20690 time= 0.01563
Epoch: 0011 train_loss= 2.07118 train_acc= 0.13747 val_loss= 2.06626 val_acc= 0.20690 time= 0.01563
Epoch: 0012 train_loss= 2.07057 train_acc= 0.13208 val_loss= 2.06574 val_acc= 0.20690 time= 0.00000
Epoch: 0013 train_loss= 2.06947 train_acc= 0.13747 val_loss= 2.06553 val_acc= 0.13793 time= 0.01563
Epoch: 0014 train_loss= 2.06680 train_acc= 0.15364 val_loss= 2.06562 val_acc= 0.13793 time= 0.00000
Epoch: 0015 train_loss= 2.06667 train_acc= 0.17251 val_loss= 2.06594 val_acc= 0.13793 time= 0.01563
Epoch: 0016 train_loss= 2.06449 train_acc= 0.14286 val_loss= 2.06657 val_acc= 0.13793 time= 0.01563
Epoch: 0017 train_loss= 2.06297 train_acc= 0.15903 val_loss= 2.06722 val_acc= 0.13793 time= 0.00000
Early stopping...
Optimization Finished!
Test set results: cost= 2.08317 accuracy= 0.15254 time= 0.00000 
