Epoch: 0001 train_loss= 2.08978 train_acc= 0.13962 val_loss= 2.08835 val_acc= 0.06897 time= 0.17189
Epoch: 0002 train_loss= 2.08958 train_acc= 0.12830 val_loss= 2.08782 val_acc= 0.03448 time= 0.01562
Epoch: 0003 train_loss= 2.08240 train_acc= 0.15849 val_loss= 2.08793 val_acc= 0.03448 time= 0.01562
Epoch: 0004 train_loss= 2.07121 train_acc= 0.21132 val_loss= 2.08865 val_acc= 0.03448 time= 0.00000
Epoch: 0005 train_loss= 2.06779 train_acc= 0.18113 val_loss= 2.08913 val_acc= 0.03448 time= 0.01563
Epoch: 0006 train_loss= 2.06597 train_acc= 0.18491 val_loss= 2.08951 val_acc= 0.03448 time= 0.01563
Epoch: 0007 train_loss= 2.06447 train_acc= 0.18113 val_loss= 2.09056 val_acc= 0.03448 time= 0.00000
Epoch: 0008 train_loss= 2.05452 train_acc= 0.20000 val_loss= 2.09178 val_acc= 0.03448 time= 0.01563
Epoch: 0009 train_loss= 2.05647 train_acc= 0.19623 val_loss= 2.09342 val_acc= 0.03448 time= 0.01563
Epoch: 0010 train_loss= 2.04720 train_acc= 0.20377 val_loss= 2.09568 val_acc= 0.03448 time= 0.00000
Epoch: 0011 train_loss= 2.04214 train_acc= 0.21132 val_loss= 2.09797 val_acc= 0.03448 time= 0.01563
Epoch: 0012 train_loss= 2.04832 train_acc= 0.18491 val_loss= 2.10045 val_acc= 0.03448 time= 0.01562
Early stopping...
Optimization Finished!
Test set results: cost= 2.08493 accuracy= 0.10169 time= 0.00000 
