Epoch: 0001 train_loss= 2.08608 train_acc= 0.13208 val_loss= 2.08104 val_acc= 0.17241 time= 0.09376
Epoch: 0002 train_loss= 2.08429 train_acc= 0.13208 val_loss= 2.07879 val_acc= 0.17241 time= 0.00000
Epoch: 0003 train_loss= 2.08292 train_acc= 0.12579 val_loss= 2.07699 val_acc= 0.24138 time= 0.01562
Epoch: 0004 train_loss= 2.08266 train_acc= 0.09434 val_loss= 2.07523 val_acc= 0.24138 time= 0.00000
Epoch: 0005 train_loss= 2.08105 train_acc= 0.13208 val_loss= 2.07374 val_acc= 0.24138 time= 0.01563
Epoch: 0006 train_loss= 2.07974 train_acc= 0.13208 val_loss= 2.07256 val_acc= 0.24138 time= 0.00000
Epoch: 0007 train_loss= 2.07916 train_acc= 0.16352 val_loss= 2.07164 val_acc= 0.24138 time= 0.01563
Epoch: 0008 train_loss= 2.07794 train_acc= 0.11321 val_loss= 2.07100 val_acc= 0.06897 time= 0.00000
Epoch: 0009 train_loss= 2.07676 train_acc= 0.14465 val_loss= 2.07055 val_acc= 0.06897 time= 0.01563
Epoch: 0010 train_loss= 2.07551 train_acc= 0.15094 val_loss= 2.07035 val_acc= 0.06897 time= 0.00000
Epoch: 0011 train_loss= 2.07448 train_acc= 0.16352 val_loss= 2.07052 val_acc= 0.06897 time= 0.01562
Epoch: 0012 train_loss= 2.07367 train_acc= 0.16981 val_loss= 2.07102 val_acc= 0.06897 time= 0.00000
Epoch: 0013 train_loss= 2.07156 train_acc= 0.15094 val_loss= 2.07186 val_acc= 0.06897 time= 0.01563
Epoch: 0014 train_loss= 2.07221 train_acc= 0.15723 val_loss= 2.07305 val_acc= 0.06897 time= 0.00000
Early stopping...
Optimization Finished!
Test set results: cost= 2.07995 accuracy= 0.03390 time= 0.00000 
