Epoch: 0001 train_loss= 2.08138 train_acc= 0.11698 val_loss= 2.08523 val_acc= 0.10345 time= 0.55431
Epoch: 0002 train_loss= 2.07733 train_acc= 0.15094 val_loss= 2.08463 val_acc= 0.03448 time= 0.01562
Epoch: 0003 train_loss= 2.07519 train_acc= 0.18113 val_loss= 2.08413 val_acc= 0.03448 time= 0.00000
Epoch: 0004 train_loss= 2.07278 train_acc= 0.16226 val_loss= 2.08380 val_acc= 0.03448 time= 0.00000
Epoch: 0005 train_loss= 2.07254 train_acc= 0.17736 val_loss= 2.08365 val_acc= 0.03448 time= 0.00000
Epoch: 0006 train_loss= 2.07048 train_acc= 0.18491 val_loss= 2.08366 val_acc= 0.03448 time= 0.01563
Epoch: 0007 train_loss= 2.07005 train_acc= 0.15094 val_loss= 2.08383 val_acc= 0.03448 time= 0.00000
Epoch: 0008 train_loss= 2.06780 train_acc= 0.13962 val_loss= 2.08416 val_acc= 0.03448 time= 0.01563
Epoch: 0009 train_loss= 2.06520 train_acc= 0.15849 val_loss= 2.08466 val_acc= 0.03448 time= 0.00000
Epoch: 0010 train_loss= 2.06560 train_acc= 0.16604 val_loss= 2.08527 val_acc= 0.03448 time= 0.00000
Epoch: 0011 train_loss= 2.06502 train_acc= 0.15094 val_loss= 2.08595 val_acc= 0.03448 time= 0.00000
Epoch: 0012 train_loss= 2.06390 train_acc= 0.16604 val_loss= 2.08675 val_acc= 0.03448 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 2.08451 accuracy= 0.08475 time= 0.00000 
