Epoch: 0001 train_loss= 2.11300 train_acc= 0.13836 val_loss= 2.10643 val_acc= 0.06897 time= 0.26983
Epoch: 0002 train_loss= 2.08250 train_acc= 0.14465 val_loss= 2.10865 val_acc= 0.06897 time= 0.01562
Epoch: 0003 train_loss= 2.06262 train_acc= 0.18868 val_loss= 2.10967 val_acc= 0.06897 time= 0.01563
Epoch: 0004 train_loss= 2.06402 train_acc= 0.18868 val_loss= 2.10646 val_acc= 0.06897 time= 0.01563
Epoch: 0005 train_loss= 2.04922 train_acc= 0.18868 val_loss= 2.10435 val_acc= 0.06897 time= 0.01563
Epoch: 0006 train_loss= 2.06903 train_acc= 0.18868 val_loss= 2.09811 val_acc= 0.06897 time= 0.01563
Epoch: 0007 train_loss= 2.04215 train_acc= 0.18868 val_loss= 2.09200 val_acc= 0.06897 time= 0.01690
Epoch: 0008 train_loss= 2.03781 train_acc= 0.19497 val_loss= 2.08485 val_acc= 0.10345 time= 0.01100
Epoch: 0009 train_loss= 2.03369 train_acc= 0.21384 val_loss= 2.07870 val_acc= 0.10345 time= 0.01300
Epoch: 0010 train_loss= 2.02764 train_acc= 0.16352 val_loss= 2.07436 val_acc= 0.10345 time= 0.01007
Epoch: 0011 train_loss= 2.02525 train_acc= 0.16981 val_loss= 2.07241 val_acc= 0.10345 time= 0.01563
Epoch: 0012 train_loss= 2.02347 train_acc= 0.17610 val_loss= 2.07166 val_acc= 0.13793 time= 0.00000
Epoch: 0013 train_loss= 2.02148 train_acc= 0.14465 val_loss= 2.07246 val_acc= 0.17241 time= 0.01563
Epoch: 0014 train_loss= 2.01670 train_acc= 0.18239 val_loss= 2.07461 val_acc= 0.17241 time= 0.01563
Epoch: 0015 train_loss= 2.03402 train_acc= 0.16981 val_loss= 2.07812 val_acc= 0.13793 time= 0.01563
Epoch: 0016 train_loss= 2.01943 train_acc= 0.18239 val_loss= 2.08286 val_acc= 0.13793 time= 0.01562
Early stopping...
Optimization Finished!
Test set results: cost= 2.08200 accuracy= 0.10169 time= 0.00000 
