Epoch: 0001 train_loss= 2.08527 train_acc= 0.12938 val_loss= 2.08277 val_acc= 0.10345 time= 0.80818
Epoch: 0002 train_loss= 2.08287 train_acc= 0.13208 val_loss= 2.07975 val_acc= 0.10345 time= 0.00900
Epoch: 0003 train_loss= 2.08046 train_acc= 0.13208 val_loss= 2.07664 val_acc= 0.10345 time= 0.00900
Epoch: 0004 train_loss= 2.07771 train_acc= 0.14016 val_loss= 2.07345 val_acc= 0.10345 time= 0.00900
Epoch: 0005 train_loss= 2.07579 train_acc= 0.14825 val_loss= 2.07068 val_acc= 0.13793 time= 0.00900
Epoch: 0006 train_loss= 2.07347 train_acc= 0.16173 val_loss= 2.06776 val_acc= 0.13793 time= 0.00800
Epoch: 0007 train_loss= 2.07130 train_acc= 0.16981 val_loss= 2.06470 val_acc= 0.13793 time= 0.00900
Epoch: 0008 train_loss= 2.06853 train_acc= 0.17251 val_loss= 2.06154 val_acc= 0.13793 time= 0.00900
Epoch: 0009 train_loss= 2.06615 train_acc= 0.17251 val_loss= 2.05838 val_acc= 0.13793 time= 0.01000
Epoch: 0010 train_loss= 2.06311 train_acc= 0.16981 val_loss= 2.05529 val_acc= 0.13793 time= 0.00800
Epoch: 0011 train_loss= 2.06000 train_acc= 0.16981 val_loss= 2.05235 val_acc= 0.13793 time= 0.00900
Epoch: 0012 train_loss= 2.05943 train_acc= 0.16981 val_loss= 2.04961 val_acc= 0.13793 time= 0.01000
Epoch: 0013 train_loss= 2.05651 train_acc= 0.17251 val_loss= 2.04720 val_acc= 0.13793 time= 0.00900
Epoch: 0014 train_loss= 2.05373 train_acc= 0.16981 val_loss= 2.04510 val_acc= 0.13793 time= 0.01000
Epoch: 0015 train_loss= 2.05278 train_acc= 0.16981 val_loss= 2.04331 val_acc= 0.13793 time= 0.00900
Epoch: 0016 train_loss= 2.05199 train_acc= 0.17251 val_loss= 2.04179 val_acc= 0.13793 time= 0.00900
Epoch: 0017 train_loss= 2.05083 train_acc= 0.16981 val_loss= 2.04059 val_acc= 0.13793 time= 0.01000
Epoch: 0018 train_loss= 2.04841 train_acc= 0.16981 val_loss= 2.03958 val_acc= 0.13793 time= 0.00800
Epoch: 0019 train_loss= 2.04926 train_acc= 0.16981 val_loss= 2.03867 val_acc= 0.13793 time= 0.01100
Epoch: 0020 train_loss= 2.04903 train_acc= 0.17251 val_loss= 2.03791 val_acc= 0.13793 time= 0.00800
Epoch: 0021 train_loss= 2.04621 train_acc= 0.17251 val_loss= 2.03731 val_acc= 0.13793 time= 0.01000
Epoch: 0022 train_loss= 2.04640 train_acc= 0.17251 val_loss= 2.03686 val_acc= 0.13793 time= 0.00900
Epoch: 0023 train_loss= 2.04725 train_acc= 0.17520 val_loss= 2.03652 val_acc= 0.13793 time= 0.00900
Epoch: 0024 train_loss= 2.04489 train_acc= 0.16712 val_loss= 2.03632 val_acc= 0.13793 time= 0.00900
Epoch: 0025 train_loss= 2.04453 train_acc= 0.17251 val_loss= 2.03637 val_acc= 0.13793 time= 0.00900
Epoch: 0026 train_loss= 2.04594 train_acc= 0.18329 val_loss= 2.03648 val_acc= 0.17241 time= 0.00800
Epoch: 0027 train_loss= 2.04465 train_acc= 0.17790 val_loss= 2.03664 val_acc= 0.17241 time= 0.00900
Epoch: 0028 train_loss= 2.04614 train_acc= 0.16442 val_loss= 2.03699 val_acc= 0.17241 time= 0.00900
Epoch: 0029 train_loss= 2.04487 train_acc= 0.16442 val_loss= 2.03752 val_acc= 0.17241 time= 0.01000
Early stopping...
Optimization Finished!
Test set results: cost= 2.10480 accuracy= 0.10169 time= 0.00300 
