Epoch: 0001 train_loss= 2.08248 train_acc= 0.10063 val_loss= 2.08816 val_acc= 0.27586 time= 0.12524
Epoch: 0002 train_loss= 2.08248 train_acc= 0.11950 val_loss= 2.08872 val_acc= 0.27586 time= 0.00000
Epoch: 0003 train_loss= 2.07839 train_acc= 0.13836 val_loss= 2.08961 val_acc= 0.24138 time= 0.01538
Epoch: 0004 train_loss= 2.07281 train_acc= 0.16352 val_loss= 2.09115 val_acc= 0.17241 time= 0.00000
Epoch: 0005 train_loss= 2.07261 train_acc= 0.13836 val_loss= 2.09305 val_acc= 0.20690 time= 0.01563
Epoch: 0006 train_loss= 2.07034 train_acc= 0.17610 val_loss= 2.09498 val_acc= 0.20690 time= 0.00000
Epoch: 0007 train_loss= 2.06250 train_acc= 0.16352 val_loss= 2.09638 val_acc= 0.20690 time= 0.00000
Epoch: 0008 train_loss= 2.06190 train_acc= 0.14465 val_loss= 2.09807 val_acc= 0.20690 time= 0.01563
Epoch: 0009 train_loss= 2.06374 train_acc= 0.20126 val_loss= 2.09968 val_acc= 0.20690 time= 0.01563
Epoch: 0010 train_loss= 2.05268 train_acc= 0.17610 val_loss= 2.10075 val_acc= 0.20690 time= 0.00000
Epoch: 0011 train_loss= 2.04830 train_acc= 0.16981 val_loss= 2.10233 val_acc= 0.20690 time= 0.01658
Epoch: 0012 train_loss= 2.04730 train_acc= 0.16352 val_loss= 2.10411 val_acc= 0.17241 time= 0.00800
Early stopping...
Optimization Finished!
Test set results: cost= 2.03274 accuracy= 0.23729 time= 0.00200 
