Epoch: 0001 train_loss= 2.32443 train_acc= 0.13477 val_loss= 2.12988 val_acc= 0.10345 time= 0.96882
Epoch: 0002 train_loss= 2.13071 train_acc= 0.13747 val_loss= 2.12890 val_acc= 0.10345 time= 0.01563
Epoch: 0003 train_loss= 2.14099 train_acc= 0.13747 val_loss= 2.12817 val_acc= 0.10345 time= 0.00000
Epoch: 0004 train_loss= 2.11201 train_acc= 0.16981 val_loss= 2.12430 val_acc= 0.10345 time= 0.01562
Epoch: 0005 train_loss= 2.20313 train_acc= 0.13747 val_loss= 2.12038 val_acc= 0.10345 time= 0.01563
Epoch: 0006 train_loss= 2.07668 train_acc= 0.16712 val_loss= 2.11988 val_acc= 0.20690 time= 0.01563
Epoch: 0007 train_loss= 2.07021 train_acc= 0.19407 val_loss= 2.11813 val_acc= 0.20690 time= 0.01563
Epoch: 0008 train_loss= 2.07655 train_acc= 0.18598 val_loss= 2.11413 val_acc= 0.20690 time= 0.01563
Epoch: 0009 train_loss= 2.10934 train_acc= 0.15633 val_loss= 2.11104 val_acc= 0.20690 time= 0.01607
Epoch: 0010 train_loss= 2.06355 train_acc= 0.17790 val_loss= 2.10720 val_acc= 0.20690 time= 0.01200
Epoch: 0011 train_loss= 2.04884 train_acc= 0.17251 val_loss= 2.10417 val_acc= 0.20690 time= 0.01400
Epoch: 0012 train_loss= 2.05193 train_acc= 0.16442 val_loss= 2.10203 val_acc= 0.20690 time= 0.00810
Epoch: 0013 train_loss= 2.04565 train_acc= 0.19677 val_loss= 2.09922 val_acc= 0.20690 time= 0.01563
Epoch: 0014 train_loss= 2.03320 train_acc= 0.18868 val_loss= 2.09707 val_acc= 0.20690 time= 0.01563
Epoch: 0015 train_loss= 2.04445 train_acc= 0.20216 val_loss= 2.09520 val_acc= 0.20690 time= 0.00000
Epoch: 0016 train_loss= 2.04470 train_acc= 0.18329 val_loss= 2.09351 val_acc= 0.20690 time= 0.01563
Epoch: 0017 train_loss= 2.04594 train_acc= 0.17251 val_loss= 2.09353 val_acc= 0.20690 time= 0.01562
Epoch: 0018 train_loss= 2.03617 train_acc= 0.18598 val_loss= 2.09528 val_acc= 0.17241 time= 0.01563
Epoch: 0019 train_loss= 2.04774 train_acc= 0.17790 val_loss= 2.09554 val_acc= 0.17241 time= 0.01563
Epoch: 0020 train_loss= 2.03119 train_acc= 0.18329 val_loss= 2.09501 val_acc= 0.17241 time= 0.01563
Epoch: 0021 train_loss= 2.04279 train_acc= 0.18598 val_loss= 2.09441 val_acc= 0.17241 time= 0.00000
Epoch: 0022 train_loss= 2.03646 train_acc= 0.20755 val_loss= 2.09386 val_acc= 0.17241 time= 0.01563
Epoch: 0023 train_loss= 2.03954 train_acc= 0.19137 val_loss= 2.09374 val_acc= 0.20690 time= 0.01562
Epoch: 0024 train_loss= 2.03258 train_acc= 0.19946 val_loss= 2.09347 val_acc= 0.20690 time= 0.01563
Epoch: 0025 train_loss= 2.03186 train_acc= 0.20216 val_loss= 2.09297 val_acc= 0.20690 time= 0.01563
Epoch: 0026 train_loss= 2.03176 train_acc= 0.21024 val_loss= 2.09230 val_acc= 0.24138 time= 0.01563
Epoch: 0027 train_loss= 2.03140 train_acc= 0.20755 val_loss= 2.09203 val_acc= 0.24138 time= 0.01563
Epoch: 0028 train_loss= 2.02552 train_acc= 0.19137 val_loss= 2.09160 val_acc= 0.24138 time= 0.00000
Epoch: 0029 train_loss= 2.02447 train_acc= 0.15903 val_loss= 2.09182 val_acc= 0.24138 time= 0.01563
Epoch: 0030 train_loss= 2.02845 train_acc= 0.18329 val_loss= 2.09167 val_acc= 0.24138 time= 0.01562
Epoch: 0031 train_loss= 2.02889 train_acc= 0.19407 val_loss= 2.09161 val_acc= 0.24138 time= 0.01563
Epoch: 0032 train_loss= 2.02414 train_acc= 0.18329 val_loss= 2.09122 val_acc= 0.20690 time= 0.01563
Epoch: 0033 train_loss= 2.02006 train_acc= 0.19137 val_loss= 2.09093 val_acc= 0.20690 time= 0.01563
Epoch: 0034 train_loss= 2.02477 train_acc= 0.19407 val_loss= 2.09029 val_acc= 0.24138 time= 0.01563
Epoch: 0035 train_loss= 2.02805 train_acc= 0.18598 val_loss= 2.09003 val_acc= 0.24138 time= 0.01563
Epoch: 0036 train_loss= 2.02905 train_acc= 0.18598 val_loss= 2.08943 val_acc= 0.20690 time= 0.01563
Epoch: 0037 train_loss= 2.03322 train_acc= 0.17520 val_loss= 2.08879 val_acc= 0.20690 time= 0.01563
Epoch: 0038 train_loss= 2.01505 train_acc= 0.22102 val_loss= 2.08842 val_acc= 0.20690 time= 0.01563
Epoch: 0039 train_loss= 2.03509 train_acc= 0.18329 val_loss= 2.08736 val_acc= 0.17241 time= 0.00000
Epoch: 0040 train_loss= 2.01767 train_acc= 0.20755 val_loss= 2.08701 val_acc= 0.13793 time= 0.01563
Epoch: 0041 train_loss= 2.02197 train_acc= 0.21024 val_loss= 2.08762 val_acc= 0.13793 time= 0.01563
Epoch: 0042 train_loss= 2.01505 train_acc= 0.22102 val_loss= 2.08847 val_acc= 0.13793 time= 0.01563
Epoch: 0043 train_loss= 2.02660 train_acc= 0.19946 val_loss= 2.08623 val_acc= 0.10345 time= 0.01563
Epoch: 0044 train_loss= 2.02355 train_acc= 0.20485 val_loss= 2.08221 val_acc= 0.10345 time= 0.01904
Epoch: 0045 train_loss= 2.02325 train_acc= 0.20216 val_loss= 2.07975 val_acc= 0.10345 time= 0.01300
Epoch: 0046 train_loss= 2.03672 train_acc= 0.21024 val_loss= 2.07512 val_acc= 0.17241 time= 0.01300
Epoch: 0047 train_loss= 2.02321 train_acc= 0.19946 val_loss= 2.07290 val_acc= 0.17241 time= 0.01500
Epoch: 0048 train_loss= 2.01132 train_acc= 0.19677 val_loss= 2.07048 val_acc= 0.20690 time= 0.01600
Epoch: 0049 train_loss= 2.02894 train_acc= 0.20485 val_loss= 2.06847 val_acc= 0.20690 time= 0.01700
Epoch: 0050 train_loss= 2.02040 train_acc= 0.19407 val_loss= 2.06729 val_acc= 0.20690 time= 0.01500
Epoch: 0051 train_loss= 2.01680 train_acc= 0.19407 val_loss= 2.06626 val_acc= 0.20690 time= 0.01700
Epoch: 0052 train_loss= 2.01867 train_acc= 0.19407 val_loss= 2.06552 val_acc= 0.20690 time= 0.01500
Epoch: 0053 train_loss= 2.02540 train_acc= 0.19407 val_loss= 2.06525 val_acc= 0.20690 time= 0.01400
Epoch: 0054 train_loss= 2.01882 train_acc= 0.21563 val_loss= 2.06616 val_acc= 0.24138 time= 0.01500
Epoch: 0055 train_loss= 2.00786 train_acc= 0.20485 val_loss= 2.06712 val_acc= 0.24138 time= 0.01400
Epoch: 0056 train_loss= 2.01651 train_acc= 0.19946 val_loss= 2.06803 val_acc= 0.20690 time= 0.01300
Epoch: 0057 train_loss= 2.00659 train_acc= 0.22102 val_loss= 2.06823 val_acc= 0.17241 time= 0.01400
Early stopping...
Optimization Finished!
Test set results: cost= 2.28402 accuracy= 0.11864 time= 0.00600 
