Epoch: 0001 train_loss= 2.08627 train_acc= 0.10243 val_loss= 2.08434 val_acc= 0.17241 time= 0.68029
Epoch: 0002 train_loss= 2.08513 train_acc= 0.09704 val_loss= 2.08247 val_acc= 0.20690 time= 0.00800
Epoch: 0003 train_loss= 2.08405 train_acc= 0.12668 val_loss= 2.08124 val_acc= 0.20690 time= 0.00900
Epoch: 0004 train_loss= 2.08329 train_acc= 0.12938 val_loss= 2.08017 val_acc= 0.20690 time= 0.00800
Epoch: 0005 train_loss= 2.08233 train_acc= 0.14016 val_loss= 2.07909 val_acc= 0.20690 time= 0.00800
Epoch: 0006 train_loss= 2.08151 train_acc= 0.13477 val_loss= 2.07806 val_acc= 0.20690 time= 0.00800
Epoch: 0007 train_loss= 2.08054 train_acc= 0.14016 val_loss= 2.07706 val_acc= 0.20690 time= 0.00305
Epoch: 0008 train_loss= 2.07967 train_acc= 0.13477 val_loss= 2.07611 val_acc= 0.06897 time= 0.00000
Epoch: 0009 train_loss= 2.07848 train_acc= 0.14286 val_loss= 2.07519 val_acc= 0.06897 time= 0.01563
Epoch: 0010 train_loss= 2.07749 train_acc= 0.16442 val_loss= 2.07433 val_acc= 0.06897 time= 0.01563
Epoch: 0011 train_loss= 2.07642 train_acc= 0.15364 val_loss= 2.07365 val_acc= 0.06897 time= 0.00000
Epoch: 0012 train_loss= 2.07540 train_acc= 0.15633 val_loss= 2.07312 val_acc= 0.06897 time= 0.01563
Epoch: 0013 train_loss= 2.07419 train_acc= 0.15364 val_loss= 2.07277 val_acc= 0.06897 time= 0.00000
Epoch: 0014 train_loss= 2.07296 train_acc= 0.15633 val_loss= 2.07273 val_acc= 0.06897 time= 0.01563
Epoch: 0015 train_loss= 2.07155 train_acc= 0.15633 val_loss= 2.07297 val_acc= 0.06897 time= 0.01563
Epoch: 0016 train_loss= 2.07101 train_acc= 0.15633 val_loss= 2.07342 val_acc= 0.06897 time= 0.00000
Epoch: 0017 train_loss= 2.07256 train_acc= 0.15633 val_loss= 2.07404 val_acc= 0.06897 time= 0.01572
Epoch: 0018 train_loss= 2.06909 train_acc= 0.15633 val_loss= 2.07496 val_acc= 0.06897 time= 0.00000
Early stopping...
Optimization Finished!
Test set results: cost= 2.08161 accuracy= 0.18644 time= 0.00000 
