Epoch: 0001 train_loss= 2.08699 train_acc= 0.18113 val_loss= 2.08347 val_acc= 0.20690 time= 0.23801
Epoch: 0002 train_loss= 2.08372 train_acc= 0.18491 val_loss= 2.08032 val_acc= 0.20690 time= 0.01563
Epoch: 0003 train_loss= 2.08015 train_acc= 0.18491 val_loss= 2.07744 val_acc= 0.20690 time= 0.01563
Epoch: 0004 train_loss= 2.07662 train_acc= 0.18491 val_loss= 2.07502 val_acc= 0.20690 time= 0.00000
Epoch: 0005 train_loss= 2.07328 train_acc= 0.18491 val_loss= 2.07328 val_acc= 0.20690 time= 0.01563
Epoch: 0006 train_loss= 2.06978 train_acc= 0.18491 val_loss= 2.07211 val_acc= 0.20690 time= 0.01563
Epoch: 0007 train_loss= 2.06708 train_acc= 0.18491 val_loss= 2.07161 val_acc= 0.20690 time= 0.00000
Epoch: 0008 train_loss= 2.06416 train_acc= 0.18491 val_loss= 2.07178 val_acc= 0.20690 time= 0.01563
Epoch: 0009 train_loss= 2.06053 train_acc= 0.18491 val_loss= 2.07272 val_acc= 0.20690 time= 0.01563
Epoch: 0010 train_loss= 2.05903 train_acc= 0.18491 val_loss= 2.07442 val_acc= 0.20690 time= 0.00000
Epoch: 0011 train_loss= 2.05661 train_acc= 0.18491 val_loss= 2.07672 val_acc= 0.20690 time= 0.01563
Epoch: 0012 train_loss= 2.05550 train_acc= 0.18491 val_loss= 2.07958 val_acc= 0.20690 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 2.09239 accuracy= 0.08475 time= 0.00000 
