Epoch: 0001 train_loss= 2.08824 train_acc= 0.11321 val_loss= 2.09692 val_acc= 0.20690 time= 0.07813
Epoch: 0002 train_loss= 2.09010 train_acc= 0.13836 val_loss= 2.09287 val_acc= 0.24138 time= 0.01563
Epoch: 0003 train_loss= 2.08603 train_acc= 0.08805 val_loss= 2.09003 val_acc= 0.24138 time= 0.00000
Epoch: 0004 train_loss= 2.05964 train_acc= 0.16352 val_loss= 2.08747 val_acc= 0.20690 time= 0.01563
Epoch: 0005 train_loss= 2.06514 train_acc= 0.20755 val_loss= 2.08522 val_acc= 0.20690 time= 0.00000
Epoch: 0006 train_loss= 2.05942 train_acc= 0.18239 val_loss= 2.08374 val_acc= 0.20690 time= 0.01563
Epoch: 0007 train_loss= 2.06254 train_acc= 0.16981 val_loss= 2.08273 val_acc= 0.20690 time= 0.00000
Epoch: 0008 train_loss= 2.05023 train_acc= 0.20126 val_loss= 2.08219 val_acc= 0.20690 time= 0.01563
Epoch: 0009 train_loss= 2.04530 train_acc= 0.16981 val_loss= 2.08210 val_acc= 0.20690 time= 0.01563
Epoch: 0010 train_loss= 2.04583 train_acc= 0.18239 val_loss= 2.08283 val_acc= 0.20690 time= 0.00000
Epoch: 0011 train_loss= 2.04471 train_acc= 0.17610 val_loss= 2.08436 val_acc= 0.20690 time= 0.01563
Epoch: 0012 train_loss= 2.03837 train_acc= 0.19497 val_loss= 2.08650 val_acc= 0.20690 time= 0.00000
Early stopping...
Optimization Finished!
Test set results: cost= 2.07390 accuracy= 0.18644 time= 0.01563 
