Epoch: 0001 train_loss= 2.08603 train_acc= 0.11321 val_loss= 2.08580 val_acc= 0.06897 time= 0.10954
Epoch: 0002 train_loss= 2.08411 train_acc= 0.11321 val_loss= 2.08532 val_acc= 0.06897 time= 0.00000
Epoch: 0003 train_loss= 2.08234 train_acc= 0.10692 val_loss= 2.08521 val_acc= 0.20690 time= 0.01563
Epoch: 0004 train_loss= 2.07990 train_acc= 0.15723 val_loss= 2.08524 val_acc= 0.20690 time= 0.00000
Epoch: 0005 train_loss= 2.07819 train_acc= 0.13836 val_loss= 2.08532 val_acc= 0.20690 time= 0.01563
Epoch: 0006 train_loss= 2.07559 train_acc= 0.14465 val_loss= 2.08568 val_acc= 0.20690 time= 0.00000
Epoch: 0007 train_loss= 2.07352 train_acc= 0.13836 val_loss= 2.08623 val_acc= 0.20690 time= 0.01563
Epoch: 0008 train_loss= 2.07034 train_acc= 0.15094 val_loss= 2.08704 val_acc= 0.20690 time= 0.01563
Epoch: 0009 train_loss= 2.06783 train_acc= 0.17610 val_loss= 2.08810 val_acc= 0.10345 time= 0.00000
Epoch: 0010 train_loss= 2.06517 train_acc= 0.20126 val_loss= 2.08943 val_acc= 0.10345 time= 0.00000
Epoch: 0011 train_loss= 2.06124 train_acc= 0.18239 val_loss= 2.09112 val_acc= 0.10345 time= 0.01563
Epoch: 0012 train_loss= 2.05993 train_acc= 0.18239 val_loss= 2.09324 val_acc= 0.10345 time= 0.00000
Early stopping...
Optimization Finished!
Test set results: cost= 2.09844 accuracy= 0.16949 time= 0.01563 
