Epoch: 0001 train_loss= 2.08749 train_acc= 0.08176 val_loss= 2.08504 val_acc= 0.20690 time= 0.14063
Epoch: 0002 train_loss= 2.08522 train_acc= 0.15723 val_loss= 2.08263 val_acc= 0.20690 time= 0.01563
Epoch: 0003 train_loss= 2.08334 train_acc= 0.15723 val_loss= 2.08048 val_acc= 0.20690 time= 0.00000
Epoch: 0004 train_loss= 2.08159 train_acc= 0.15723 val_loss= 2.07826 val_acc= 0.20690 time= 0.01563
Epoch: 0005 train_loss= 2.08015 train_acc= 0.16981 val_loss= 2.07609 val_acc= 0.20690 time= 0.01563
Epoch: 0006 train_loss= 2.07875 train_acc= 0.15723 val_loss= 2.07411 val_acc= 0.20690 time= 0.01226
Epoch: 0007 train_loss= 2.07748 train_acc= 0.16352 val_loss= 2.07232 val_acc= 0.20690 time= 0.00100
Epoch: 0008 train_loss= 2.07658 train_acc= 0.15723 val_loss= 2.07080 val_acc= 0.20690 time= 0.01566
Epoch: 0009 train_loss= 2.07551 train_acc= 0.15723 val_loss= 2.06945 val_acc= 0.20690 time= 0.00000
Epoch: 0010 train_loss= 2.07521 train_acc= 0.16352 val_loss= 2.06837 val_acc= 0.20690 time= 0.01563
Epoch: 0011 train_loss= 2.07448 train_acc= 0.16352 val_loss= 2.06748 val_acc= 0.20690 time= 0.01563
Epoch: 0012 train_loss= 2.07352 train_acc= 0.15723 val_loss= 2.06681 val_acc= 0.20690 time= 0.00000
Epoch: 0013 train_loss= 2.07300 train_acc= 0.15723 val_loss= 2.06636 val_acc= 0.20690 time= 0.01562
Epoch: 0014 train_loss= 2.07247 train_acc= 0.15723 val_loss= 2.06615 val_acc= 0.20690 time= 0.00000
Epoch: 0015 train_loss= 2.07216 train_acc= 0.15723 val_loss= 2.06622 val_acc= 0.20690 time= 0.01563
Epoch: 0016 train_loss= 2.07038 train_acc= 0.16352 val_loss= 2.06653 val_acc= 0.20690 time= 0.01563
Epoch: 0017 train_loss= 2.06916 train_acc= 0.15723 val_loss= 2.06693 val_acc= 0.20690 time= 0.00000
Epoch: 0018 train_loss= 2.06952 train_acc= 0.15723 val_loss= 2.06755 val_acc= 0.20690 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 2.06637 accuracy= 0.15254 time= 0.00000 
