Epoch: 0001 train_loss= 2.11554 train_acc= 0.11321 val_loss= 2.07430 val_acc= 0.10345 time= 0.06208
Epoch: 0002 train_loss= 2.09918 train_acc= 0.09434 val_loss= 2.06974 val_acc= 0.10345 time= 0.01563
Epoch: 0003 train_loss= 2.09752 train_acc= 0.10692 val_loss= 2.06524 val_acc= 0.17241 time= 0.01040
Epoch: 0004 train_loss= 2.08154 train_acc= 0.18239 val_loss= 2.06098 val_acc= 0.31034 time= 0.00800
Epoch: 0005 train_loss= 2.07666 train_acc= 0.15723 val_loss= 2.05744 val_acc= 0.27586 time= 0.00000
Epoch: 0006 train_loss= 2.06988 train_acc= 0.15723 val_loss= 2.05432 val_acc= 0.20690 time= 0.01567
Epoch: 0007 train_loss= 2.06620 train_acc= 0.14465 val_loss= 2.05139 val_acc= 0.20690 time= 0.00000
Epoch: 0008 train_loss= 2.06584 train_acc= 0.15723 val_loss= 2.04915 val_acc= 0.20690 time= 0.01563
Epoch: 0009 train_loss= 2.05784 train_acc= 0.16981 val_loss= 2.04716 val_acc= 0.20690 time= 0.00000
Epoch: 0010 train_loss= 2.05324 train_acc= 0.13208 val_loss= 2.04588 val_acc= 0.20690 time= 0.01563
Epoch: 0011 train_loss= 2.04728 train_acc= 0.21384 val_loss= 2.04505 val_acc= 0.20690 time= 0.01563
Epoch: 0012 train_loss= 2.04845 train_acc= 0.16352 val_loss= 2.04477 val_acc= 0.20690 time= 0.00000
Epoch: 0013 train_loss= 2.05188 train_acc= 0.13836 val_loss= 2.04488 val_acc= 0.20690 time= 0.01563
Epoch: 0014 train_loss= 2.04416 train_acc= 0.18239 val_loss= 2.04547 val_acc= 0.24138 time= 0.00000
Epoch: 0015 train_loss= 2.04058 train_acc= 0.18239 val_loss= 2.04707 val_acc= 0.27586 time= 0.01563
Epoch: 0016 train_loss= 2.03909 train_acc= 0.15723 val_loss= 2.04859 val_acc= 0.31034 time= 0.00000
Early stopping...
Optimization Finished!
Test set results: cost= 2.06146 accuracy= 0.16949 time= 0.01563 
