Epoch: 0001 train_loss= 2.08554 train_acc= 0.08176 val_loss= 2.09127 val_acc= 0.03448 time= 0.29803
Epoch: 0002 train_loss= 2.08380 train_acc= 0.09434 val_loss= 2.09062 val_acc= 0.06897 time= 0.00500
Epoch: 0003 train_loss= 2.07948 train_acc= 0.16981 val_loss= 2.09020 val_acc= 0.06897 time= 0.00400
Epoch: 0004 train_loss= 2.07541 train_acc= 0.18239 val_loss= 2.09007 val_acc= 0.06897 time= 0.00400
Epoch: 0005 train_loss= 2.07238 train_acc= 0.18239 val_loss= 2.09041 val_acc= 0.06897 time= 0.00608
Epoch: 0006 train_loss= 2.07225 train_acc= 0.18239 val_loss= 2.09103 val_acc= 0.06897 time= 0.00000
Epoch: 0007 train_loss= 2.06569 train_acc= 0.18239 val_loss= 2.09200 val_acc= 0.06897 time= 0.00000
Epoch: 0008 train_loss= 2.06596 train_acc= 0.18239 val_loss= 2.09337 val_acc= 0.06897 time= 0.00000
Epoch: 0009 train_loss= 2.06471 train_acc= 0.18239 val_loss= 2.09504 val_acc= 0.06897 time= 0.01562
Epoch: 0010 train_loss= 2.06038 train_acc= 0.18239 val_loss= 2.09705 val_acc= 0.06897 time= 0.00000
Epoch: 0011 train_loss= 2.06180 train_acc= 0.18239 val_loss= 2.09944 val_acc= 0.06897 time= 0.00000
Epoch: 0012 train_loss= 2.05563 train_acc= 0.18239 val_loss= 2.10222 val_acc= 0.06897 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 2.07560 accuracy= 0.11864 time= 0.00000 
