Epoch: 0001 train_loss= 2.09033 train_acc= 0.13208 val_loss= 2.06886 val_acc= 0.20690 time= 0.26564
Epoch: 0002 train_loss= 2.08635 train_acc= 0.12579 val_loss= 2.06989 val_acc= 0.20690 time= 0.00000
Epoch: 0003 train_loss= 2.08490 train_acc= 0.11950 val_loss= 2.07019 val_acc= 0.20690 time= 0.00000
Epoch: 0004 train_loss= 2.08292 train_acc= 0.13208 val_loss= 2.07037 val_acc= 0.20690 time= 0.01563
Epoch: 0005 train_loss= 2.07902 train_acc= 0.13836 val_loss= 2.07015 val_acc= 0.20690 time= 0.00000
Epoch: 0006 train_loss= 2.07775 train_acc= 0.11950 val_loss= 2.06994 val_acc= 0.13793 time= 0.00000
Epoch: 0007 train_loss= 2.07680 train_acc= 0.11950 val_loss= 2.06969 val_acc= 0.17241 time= 0.01563
Epoch: 0008 train_loss= 2.07289 train_acc= 0.15094 val_loss= 2.06945 val_acc= 0.24138 time= 0.00000
Epoch: 0009 train_loss= 2.07041 train_acc= 0.16352 val_loss= 2.06919 val_acc= 0.24138 time= 0.00000
Epoch: 0010 train_loss= 2.06949 train_acc= 0.16352 val_loss= 2.06911 val_acc= 0.24138 time= 0.01563
Epoch: 0011 train_loss= 2.06752 train_acc= 0.15723 val_loss= 2.06912 val_acc= 0.24138 time= 0.00000
Epoch: 0012 train_loss= 2.06200 train_acc= 0.15723 val_loss= 2.06916 val_acc= 0.24138 time= 0.00000
Epoch: 0013 train_loss= 2.06639 train_acc= 0.14465 val_loss= 2.06958 val_acc= 0.24138 time= 0.00000
Epoch: 0014 train_loss= 2.06268 train_acc= 0.15094 val_loss= 2.07034 val_acc= 0.24138 time= 0.00000
Early stopping...
Optimization Finished!
Test set results: cost= 2.09465 accuracy= 0.10169 time= 0.00000 
