Epoch: 0001 train_loss= 2.08172 train_acc= 0.15094 val_loss= 2.08432 val_acc= 0.13793 time= 0.90909
Epoch: 0002 train_loss= 2.08066 train_acc= 0.15903 val_loss= 2.08344 val_acc= 0.13793 time= 0.00600
Epoch: 0003 train_loss= 2.07902 train_acc= 0.15633 val_loss= 2.08266 val_acc= 0.13793 time= 0.00500
Epoch: 0004 train_loss= 2.07795 train_acc= 0.15633 val_loss= 2.08193 val_acc= 0.13793 time= 0.00700
Epoch: 0005 train_loss= 2.07584 train_acc= 0.15364 val_loss= 2.08125 val_acc= 0.13793 time= 0.00600
Epoch: 0006 train_loss= 2.07566 train_acc= 0.15633 val_loss= 2.08061 val_acc= 0.13793 time= 0.00600
Epoch: 0007 train_loss= 2.07470 train_acc= 0.15633 val_loss= 2.08003 val_acc= 0.13793 time= 0.00500
Epoch: 0008 train_loss= 2.07250 train_acc= 0.15633 val_loss= 2.07953 val_acc= 0.13793 time= 0.00600
Epoch: 0009 train_loss= 2.07082 train_acc= 0.15633 val_loss= 2.07906 val_acc= 0.13793 time= 0.00700
Epoch: 0010 train_loss= 2.07194 train_acc= 0.15633 val_loss= 2.07867 val_acc= 0.13793 time= 0.00500
Epoch: 0011 train_loss= 2.07118 train_acc= 0.15633 val_loss= 2.07831 val_acc= 0.13793 time= 0.00600
Epoch: 0012 train_loss= 2.06748 train_acc= 0.15633 val_loss= 2.07797 val_acc= 0.13793 time= 0.00500
Epoch: 0013 train_loss= 2.06793 train_acc= 0.15633 val_loss= 2.07762 val_acc= 0.13793 time= 0.00500
Epoch: 0014 train_loss= 2.06795 train_acc= 0.15633 val_loss= 2.07729 val_acc= 0.13793 time= 0.00600
Epoch: 0015 train_loss= 2.06341 train_acc= 0.15633 val_loss= 2.07701 val_acc= 0.13793 time= 0.00600
Epoch: 0016 train_loss= 2.06172 train_acc= 0.15633 val_loss= 2.07668 val_acc= 0.13793 time= 0.00600
Epoch: 0017 train_loss= 2.06248 train_acc= 0.15633 val_loss= 2.07636 val_acc= 0.13793 time= 0.00600
Epoch: 0018 train_loss= 2.06257 train_acc= 0.15633 val_loss= 2.07596 val_acc= 0.13793 time= 0.00500
Epoch: 0019 train_loss= 2.06235 train_acc= 0.15633 val_loss= 2.07554 val_acc= 0.13793 time= 0.00600
Epoch: 0020 train_loss= 2.06094 train_acc= 0.15633 val_loss= 2.07495 val_acc= 0.13793 time= 0.00600
Epoch: 0021 train_loss= 2.06145 train_acc= 0.15633 val_loss= 2.07435 val_acc= 0.13793 time= 0.00600
Epoch: 0022 train_loss= 2.05739 train_acc= 0.15633 val_loss= 2.07362 val_acc= 0.13793 time= 0.00500
Epoch: 0023 train_loss= 2.05776 train_acc= 0.15633 val_loss= 2.07282 val_acc= 0.13793 time= 0.00600
Epoch: 0024 train_loss= 2.05990 train_acc= 0.15633 val_loss= 2.07187 val_acc= 0.13793 time= 0.00500
Epoch: 0025 train_loss= 2.05695 train_acc= 0.15633 val_loss= 2.07092 val_acc= 0.13793 time= 0.00500
Epoch: 0026 train_loss= 2.05745 train_acc= 0.15633 val_loss= 2.07005 val_acc= 0.13793 time= 0.00600
Epoch: 0027 train_loss= 2.05574 train_acc= 0.16442 val_loss= 2.06927 val_acc= 0.13793 time= 0.00500
Epoch: 0028 train_loss= 2.05730 train_acc= 0.15903 val_loss= 2.06860 val_acc= 0.20690 time= 0.00600
Epoch: 0029 train_loss= 2.05631 train_acc= 0.15364 val_loss= 2.06812 val_acc= 0.20690 time= 0.00500
Epoch: 0030 train_loss= 2.05655 train_acc= 0.16712 val_loss= 2.06783 val_acc= 0.20690 time= 0.00600
Epoch: 0031 train_loss= 2.05782 train_acc= 0.17251 val_loss= 2.06763 val_acc= 0.20690 time= 0.00600
Epoch: 0032 train_loss= 2.05741 train_acc= 0.16712 val_loss= 2.06754 val_acc= 0.20690 time= 0.00600
Epoch: 0033 train_loss= 2.05680 train_acc= 0.16712 val_loss= 2.06752 val_acc= 0.20690 time= 0.00600
Epoch: 0034 train_loss= 2.05541 train_acc= 0.16712 val_loss= 2.06766 val_acc= 0.20690 time= 0.00600
Epoch: 0035 train_loss= 2.05513 train_acc= 0.16712 val_loss= 2.06786 val_acc= 0.20690 time= 0.00500
Epoch: 0036 train_loss= 2.05417 train_acc= 0.16712 val_loss= 2.06813 val_acc= 0.20690 time= 0.00600
Epoch: 0037 train_loss= 2.05493 train_acc= 0.16712 val_loss= 2.06842 val_acc= 0.20690 time= 0.00600
Early stopping...
Optimization Finished!
Test set results: cost= 2.06095 accuracy= 0.18644 time= 0.00200 
