Epoch: 0001 train_loss= 2.08699 train_acc= 0.15094 val_loss= 2.08350 val_acc= 0.17241 time= 0.10938
Epoch: 0002 train_loss= 2.08597 train_acc= 0.14465 val_loss= 2.08334 val_acc= 0.17241 time= 0.00000
Epoch: 0003 train_loss= 2.08389 train_acc= 0.15094 val_loss= 2.08353 val_acc= 0.17241 time= 0.01563
Epoch: 0004 train_loss= 2.08281 train_acc= 0.14465 val_loss= 2.08291 val_acc= 0.17241 time= 0.00000
Epoch: 0005 train_loss= 2.08191 train_acc= 0.13836 val_loss= 2.08229 val_acc= 0.17241 time= 0.01563
Epoch: 0006 train_loss= 2.08146 train_acc= 0.16352 val_loss= 2.08206 val_acc= 0.17241 time= 0.00000
Epoch: 0007 train_loss= 2.07994 train_acc= 0.16352 val_loss= 2.08206 val_acc= 0.17241 time= 0.01563
Epoch: 0008 train_loss= 2.07935 train_acc= 0.15094 val_loss= 2.08238 val_acc= 0.17241 time= 0.01563
Epoch: 0009 train_loss= 2.07861 train_acc= 0.13208 val_loss= 2.08300 val_acc= 0.17241 time= 0.00000
Epoch: 0010 train_loss= 2.07759 train_acc= 0.13208 val_loss= 2.08389 val_acc= 0.17241 time= 0.01563
Epoch: 0011 train_loss= 2.07731 train_acc= 0.11321 val_loss= 2.08495 val_acc= 0.00000 time= 0.00000
Epoch: 0012 train_loss= 2.07690 train_acc= 0.10063 val_loss= 2.08624 val_acc= 0.00000 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 2.08352 accuracy= 0.11864 time= 0.00000 
