Epoch: 0001 train_loss= 2.08746 train_acc= 0.06469 val_loss= 2.08523 val_acc= 0.20690 time= 0.34333
Epoch: 0002 train_loss= 2.08524 train_acc= 0.14555 val_loss= 2.08340 val_acc= 0.20690 time= 0.01563
Epoch: 0003 train_loss= 2.08328 train_acc= 0.14286 val_loss= 2.08165 val_acc= 0.20690 time= 0.00000
Epoch: 0004 train_loss= 2.08142 train_acc= 0.15903 val_loss= 2.08008 val_acc= 0.20690 time= 0.01563
Epoch: 0005 train_loss= 2.07959 train_acc= 0.16173 val_loss= 2.07874 val_acc= 0.20690 time= 0.00000
Epoch: 0006 train_loss= 2.07792 train_acc= 0.15094 val_loss= 2.07761 val_acc= 0.20690 time= 0.01563
Epoch: 0007 train_loss= 2.07639 train_acc= 0.14286 val_loss= 2.07670 val_acc= 0.20690 time= 0.00000
Epoch: 0008 train_loss= 2.07543 train_acc= 0.15364 val_loss= 2.07599 val_acc= 0.20690 time= 0.01563
Epoch: 0009 train_loss= 2.07404 train_acc= 0.15094 val_loss= 2.07545 val_acc= 0.20690 time= 0.01563
Epoch: 0010 train_loss= 2.07351 train_acc= 0.15094 val_loss= 2.07509 val_acc= 0.20690 time= 0.00000
Epoch: 0011 train_loss= 2.07202 train_acc= 0.14825 val_loss= 2.07490 val_acc= 0.20690 time= 0.01563
Epoch: 0012 train_loss= 2.07077 train_acc= 0.14555 val_loss= 2.07486 val_acc= 0.20690 time= 0.00000
Epoch: 0013 train_loss= 2.07054 train_acc= 0.15094 val_loss= 2.07495 val_acc= 0.20690 time= 0.01563
Epoch: 0014 train_loss= 2.06975 train_acc= 0.14825 val_loss= 2.07514 val_acc= 0.20690 time= 0.00000
Epoch: 0015 train_loss= 2.06885 train_acc= 0.14825 val_loss= 2.07542 val_acc= 0.20690 time= 0.01563
Epoch: 0016 train_loss= 2.06807 train_acc= 0.14825 val_loss= 2.07574 val_acc= 0.20690 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 2.07223 accuracy= 0.08475 time= 0.00000 
