Epoch: 0001 train_loss= 2.08693 train_acc= 0.09057 val_loss= 2.08976 val_acc= 0.13793 time= 0.34421
Epoch: 0002 train_loss= 2.08575 train_acc= 0.10189 val_loss= 2.08787 val_acc= 0.13793 time= 0.00000
Epoch: 0003 train_loss= 2.08453 train_acc= 0.15849 val_loss= 2.08607 val_acc= 0.10345 time= 0.01519
Epoch: 0004 train_loss= 2.08355 train_acc= 0.13208 val_loss= 2.08504 val_acc= 0.10345 time= 0.00000
Epoch: 0005 train_loss= 2.08235 train_acc= 0.13585 val_loss= 2.08475 val_acc= 0.10345 time= 0.01563
Epoch: 0006 train_loss= 2.08178 train_acc= 0.13585 val_loss= 2.08446 val_acc= 0.10345 time= 0.00000
Epoch: 0007 train_loss= 2.08150 train_acc= 0.13585 val_loss= 2.08415 val_acc= 0.10345 time= 0.01563
Epoch: 0008 train_loss= 2.08070 train_acc= 0.13585 val_loss= 2.08383 val_acc= 0.10345 time= 0.00000
Epoch: 0009 train_loss= 2.08036 train_acc= 0.13208 val_loss= 2.08349 val_acc= 0.10345 time= 0.01562
Epoch: 0010 train_loss= 2.07932 train_acc= 0.13585 val_loss= 2.08314 val_acc= 0.10345 time= 0.00000
Epoch: 0011 train_loss= 2.07900 train_acc= 0.13585 val_loss= 2.08277 val_acc= 0.10345 time= 0.01563
Epoch: 0012 train_loss= 2.07846 train_acc= 0.13208 val_loss= 2.08238 val_acc= 0.10345 time= 0.00000
Epoch: 0013 train_loss= 2.07765 train_acc= 0.13585 val_loss= 2.08197 val_acc= 0.10345 time= 0.01563
Epoch: 0014 train_loss= 2.07714 train_acc= 0.13585 val_loss= 2.08154 val_acc= 0.10345 time= 0.00000
Epoch: 0015 train_loss= 2.07649 train_acc= 0.13585 val_loss= 2.08108 val_acc= 0.10345 time= 0.01563
Epoch: 0016 train_loss= 2.07608 train_acc= 0.13208 val_loss= 2.08058 val_acc= 0.10345 time= 0.00000
Epoch: 0017 train_loss= 2.07611 train_acc= 0.13585 val_loss= 2.08005 val_acc= 0.10345 time= 0.01563
Epoch: 0018 train_loss= 2.07459 train_acc= 0.13585 val_loss= 2.07952 val_acc= 0.10345 time= 0.00000
Epoch: 0019 train_loss= 2.07449 train_acc= 0.13585 val_loss= 2.07894 val_acc= 0.10345 time= 0.01563
Epoch: 0020 train_loss= 2.07259 train_acc= 0.13585 val_loss= 2.07835 val_acc= 0.10345 time= 0.00000
Epoch: 0021 train_loss= 2.07195 train_acc= 0.13962 val_loss= 2.07773 val_acc= 0.10345 time= 0.01563
Epoch: 0022 train_loss= 2.07146 train_acc= 0.14340 val_loss= 2.07708 val_acc= 0.10345 time= 0.00000
Epoch: 0023 train_loss= 2.07090 train_acc= 0.14717 val_loss= 2.07644 val_acc= 0.10345 time= 0.01563
Epoch: 0024 train_loss= 2.06868 train_acc= 0.13962 val_loss= 2.07565 val_acc= 0.20690 time= 0.00000
Epoch: 0025 train_loss= 2.07000 train_acc= 0.16604 val_loss= 2.07466 val_acc= 0.20690 time= 0.01563
Epoch: 0026 train_loss= 2.06892 train_acc= 0.17736 val_loss= 2.07357 val_acc= 0.20690 time= 0.00000
Epoch: 0027 train_loss= 2.06910 train_acc= 0.17358 val_loss= 2.07235 val_acc= 0.20690 time= 0.01563
Epoch: 0028 train_loss= 2.06549 train_acc= 0.18113 val_loss= 2.07094 val_acc= 0.20690 time= 0.00000
Epoch: 0029 train_loss= 2.06781 train_acc= 0.18113 val_loss= 2.06941 val_acc= 0.20690 time= 0.01563
Epoch: 0030 train_loss= 2.06739 train_acc= 0.18113 val_loss= 2.06765 val_acc= 0.20690 time= 0.00000
Epoch: 0031 train_loss= 2.06691 train_acc= 0.18113 val_loss= 2.06509 val_acc= 0.20690 time= 0.01563
Epoch: 0032 train_loss= 2.06521 train_acc= 0.18113 val_loss= 2.06201 val_acc= 0.20690 time= 0.00000
Epoch: 0033 train_loss= 2.06327 train_acc= 0.18113 val_loss= 2.05850 val_acc= 0.20690 time= 0.01563
Epoch: 0034 train_loss= 2.06150 train_acc= 0.18113 val_loss= 2.05471 val_acc= 0.20690 time= 0.00000
Epoch: 0035 train_loss= 2.06383 train_acc= 0.18113 val_loss= 2.05084 val_acc= 0.20690 time= 0.01563
Epoch: 0036 train_loss= 2.06238 train_acc= 0.18113 val_loss= 2.04682 val_acc= 0.20690 time= 0.00000
Epoch: 0037 train_loss= 2.05773 train_acc= 0.18113 val_loss= 2.04280 val_acc= 0.20690 time= 0.01563
Epoch: 0038 train_loss= 2.06112 train_acc= 0.18113 val_loss= 2.03885 val_acc= 0.20690 time= 0.00000
Epoch: 0039 train_loss= 2.05918 train_acc= 0.18113 val_loss= 2.03539 val_acc= 0.20690 time= 0.01563
Epoch: 0040 train_loss= 2.05931 train_acc= 0.18113 val_loss= 2.03231 val_acc= 0.20690 time= 0.00000
Epoch: 0041 train_loss= 2.05938 train_acc= 0.18113 val_loss= 2.02980 val_acc= 0.20690 time= 0.01563
Epoch: 0042 train_loss= 2.05909 train_acc= 0.18113 val_loss= 2.02799 val_acc= 0.20690 time= 0.00000
Epoch: 0043 train_loss= 2.06013 train_acc= 0.18113 val_loss= 2.02671 val_acc= 0.20690 time= 0.01563
Epoch: 0044 train_loss= 2.05893 train_acc= 0.18113 val_loss= 2.02587 val_acc= 0.20690 time= 0.00000
Epoch: 0045 train_loss= 2.05968 train_acc= 0.18113 val_loss= 2.02524 val_acc= 0.20690 time= 0.01563
Epoch: 0046 train_loss= 2.06024 train_acc= 0.18113 val_loss= 2.02498 val_acc= 0.20690 time= 0.00000
Epoch: 0047 train_loss= 2.05785 train_acc= 0.18113 val_loss= 2.02486 val_acc= 0.20690 time= 0.01563
Epoch: 0048 train_loss= 2.05694 train_acc= 0.18113 val_loss= 2.02501 val_acc= 0.20690 time= 0.00000
Epoch: 0049 train_loss= 2.05702 train_acc= 0.18113 val_loss= 2.02539 val_acc= 0.20690 time= 0.01563
Epoch: 0050 train_loss= 2.05751 train_acc= 0.18113 val_loss= 2.02586 val_acc= 0.20690 time= 0.00000
Epoch: 0051 train_loss= 2.05787 train_acc= 0.18113 val_loss= 2.02637 val_acc= 0.20690 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 2.06846 accuracy= 0.16949 time= 0.00000 
