Epoch: 0001 train_loss= 2.08563 train_acc= 0.10189 val_loss= 2.11517 val_acc= 0.06897 time= 0.15626
Epoch: 0002 train_loss= 2.08511 train_acc= 0.13962 val_loss= 2.11687 val_acc= 0.06897 time= 0.01562
Epoch: 0003 train_loss= 2.07423 train_acc= 0.15472 val_loss= 2.11895 val_acc= 0.06897 time= 0.00000
Epoch: 0004 train_loss= 2.07352 train_acc= 0.13962 val_loss= 2.12161 val_acc= 0.06897 time= 0.01563
Epoch: 0005 train_loss= 2.07688 train_acc= 0.15849 val_loss= 2.12434 val_acc= 0.06897 time= 0.00000
Epoch: 0006 train_loss= 2.06509 train_acc= 0.16226 val_loss= 2.12690 val_acc= 0.06897 time= 0.01563
Epoch: 0007 train_loss= 2.05863 train_acc= 0.15472 val_loss= 2.12878 val_acc= 0.13793 time= 0.01563
Epoch: 0008 train_loss= 2.06055 train_acc= 0.15094 val_loss= 2.13062 val_acc= 0.13793 time= 0.00000
Epoch: 0009 train_loss= 2.06378 train_acc= 0.17358 val_loss= 2.13382 val_acc= 0.13793 time= 0.01563
Epoch: 0010 train_loss= 2.05302 train_acc= 0.17736 val_loss= 2.13760 val_acc= 0.13793 time= 0.01563
Epoch: 0011 train_loss= 2.04708 train_acc= 0.15472 val_loss= 2.14084 val_acc= 0.13793 time= 0.00000
Epoch: 0012 train_loss= 2.05224 train_acc= 0.17736 val_loss= 2.14439 val_acc= 0.13793 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 2.06085 accuracy= 0.05085 time= 0.00000 
