Epoch: 0001 train_loss= 2.08708 train_acc= 0.13962 val_loss= 2.08665 val_acc= 0.03448 time= 0.46878
Epoch: 0002 train_loss= 2.08459 train_acc= 0.13585 val_loss= 2.08582 val_acc= 0.03448 time= 0.01563
Epoch: 0003 train_loss= 2.08285 train_acc= 0.12830 val_loss= 2.08508 val_acc= 0.03448 time= 0.01563
Epoch: 0004 train_loss= 2.08076 train_acc= 0.15094 val_loss= 2.08440 val_acc= 0.03448 time= 0.00000
Epoch: 0005 train_loss= 2.07891 train_acc= 0.17358 val_loss= 2.08369 val_acc= 0.06897 time= 0.00000
Epoch: 0006 train_loss= 2.07784 train_acc= 0.13962 val_loss= 2.08303 val_acc= 0.17241 time= 0.01563
Epoch: 0007 train_loss= 2.07647 train_acc= 0.17358 val_loss= 2.08257 val_acc= 0.17241 time= 0.00000
Epoch: 0008 train_loss= 2.07545 train_acc= 0.16226 val_loss= 2.08254 val_acc= 0.17241 time= 0.01563
Epoch: 0009 train_loss= 2.07489 train_acc= 0.15472 val_loss= 2.08242 val_acc= 0.17241 time= 0.00000
Epoch: 0010 train_loss= 2.07327 train_acc= 0.16604 val_loss= 2.08219 val_acc= 0.17241 time= 0.01562
Epoch: 0011 train_loss= 2.07284 train_acc= 0.15849 val_loss= 2.08185 val_acc= 0.17241 time= 0.00000
Epoch: 0012 train_loss= 2.07198 train_acc= 0.16226 val_loss= 2.08136 val_acc= 0.17241 time= 0.01563
Epoch: 0013 train_loss= 2.07146 train_acc= 0.16604 val_loss= 2.08084 val_acc= 0.17241 time= 0.00000
Epoch: 0014 train_loss= 2.07141 train_acc= 0.16604 val_loss= 2.08008 val_acc= 0.17241 time= 0.01563
Epoch: 0015 train_loss= 2.07164 train_acc= 0.15094 val_loss= 2.07938 val_acc= 0.17241 time= 0.00000
Epoch: 0016 train_loss= 2.07074 train_acc= 0.16226 val_loss= 2.07862 val_acc= 0.17241 time= 0.01563
Epoch: 0017 train_loss= 2.06976 train_acc= 0.14340 val_loss= 2.07809 val_acc= 0.17241 time= 0.00000
Epoch: 0018 train_loss= 2.06884 train_acc= 0.16604 val_loss= 2.07761 val_acc= 0.17241 time= 0.01563
Epoch: 0019 train_loss= 2.06699 train_acc= 0.16226 val_loss= 2.07728 val_acc= 0.17241 time= 0.00000
Epoch: 0020 train_loss= 2.06663 train_acc= 0.16604 val_loss= 2.07694 val_acc= 0.17241 time= 0.01563
Epoch: 0021 train_loss= 2.06732 train_acc= 0.16226 val_loss= 2.07647 val_acc= 0.17241 time= 0.01563
Epoch: 0022 train_loss= 2.06613 train_acc= 0.16604 val_loss= 2.07609 val_acc= 0.17241 time= 0.00000
Epoch: 0023 train_loss= 2.06728 train_acc= 0.15849 val_loss= 2.07566 val_acc= 0.17241 time= 0.00000
Epoch: 0024 train_loss= 2.06502 train_acc= 0.16226 val_loss= 2.07548 val_acc= 0.17241 time= 0.02069
Epoch: 0025 train_loss= 2.06486 train_acc= 0.16604 val_loss= 2.07540 val_acc= 0.17241 time= 0.01100
Epoch: 0026 train_loss= 2.06475 train_acc= 0.16981 val_loss= 2.07540 val_acc= 0.17241 time= 0.00000
Epoch: 0027 train_loss= 2.06536 train_acc= 0.15849 val_loss= 2.07533 val_acc= 0.17241 time= 0.01563
Epoch: 0028 train_loss= 2.06498 train_acc= 0.16226 val_loss= 2.07517 val_acc= 0.17241 time= 0.00000
Epoch: 0029 train_loss= 2.06448 train_acc= 0.16226 val_loss= 2.07483 val_acc= 0.17241 time= 0.01563
Epoch: 0030 train_loss= 2.06436 train_acc= 0.16226 val_loss= 2.07446 val_acc= 0.17241 time= 0.00000
Epoch: 0031 train_loss= 2.06311 train_acc= 0.17358 val_loss= 2.07397 val_acc= 0.17241 time= 0.01563
Epoch: 0032 train_loss= 2.06418 train_acc= 0.16226 val_loss= 2.07365 val_acc= 0.17241 time= 0.00000
Epoch: 0033 train_loss= 2.06158 train_acc= 0.16226 val_loss= 2.07322 val_acc= 0.17241 time= 0.01563
Epoch: 0034 train_loss= 2.06350 train_acc= 0.15849 val_loss= 2.07319 val_acc= 0.17241 time= 0.00000
Epoch: 0035 train_loss= 2.06368 train_acc= 0.16981 val_loss= 2.07316 val_acc= 0.17241 time= 0.01562
Epoch: 0036 train_loss= 2.06213 train_acc= 0.16981 val_loss= 2.07299 val_acc= 0.17241 time= 0.00000
Epoch: 0037 train_loss= 2.06242 train_acc= 0.16604 val_loss= 2.07272 val_acc= 0.17241 time= 0.01563
Epoch: 0038 train_loss= 2.06134 train_acc= 0.17358 val_loss= 2.07246 val_acc= 0.17241 time= 0.00000
Epoch: 0039 train_loss= 2.06165 train_acc= 0.17358 val_loss= 2.07209 val_acc= 0.17241 time= 0.01563
Epoch: 0040 train_loss= 2.06210 train_acc= 0.16226 val_loss= 2.07208 val_acc= 0.17241 time= 0.00000
Epoch: 0041 train_loss= 2.06242 train_acc= 0.16226 val_loss= 2.07204 val_acc= 0.17241 time= 0.01563
Epoch: 0042 train_loss= 2.06148 train_acc= 0.16604 val_loss= 2.07234 val_acc= 0.17241 time= 0.00000
Epoch: 0043 train_loss= 2.06061 train_acc= 0.16604 val_loss= 2.07242 val_acc= 0.17241 time= 0.01563
Epoch: 0044 train_loss= 2.06192 train_acc= 0.16226 val_loss= 2.07214 val_acc= 0.17241 time= 0.00000
Epoch: 0045 train_loss= 2.06190 train_acc= 0.16604 val_loss= 2.07175 val_acc= 0.17241 time= 0.01563
Epoch: 0046 train_loss= 2.06113 train_acc= 0.16981 val_loss= 2.07126 val_acc= 0.17241 time= 0.00000
Epoch: 0047 train_loss= 2.06178 train_acc= 0.16604 val_loss= 2.07083 val_acc= 0.17241 time= 0.01562
Epoch: 0048 train_loss= 2.06147 train_acc= 0.16604 val_loss= 2.07061 val_acc= 0.17241 time= 0.00000
Epoch: 0049 train_loss= 2.06121 train_acc= 0.16604 val_loss= 2.07044 val_acc= 0.17241 time= 0.01563
Epoch: 0050 train_loss= 2.06079 train_acc= 0.15849 val_loss= 2.07025 val_acc= 0.17241 time= 0.00000
Epoch: 0051 train_loss= 2.06116 train_acc= 0.16604 val_loss= 2.07037 val_acc= 0.17241 time= 0.01563
Epoch: 0052 train_loss= 2.06058 train_acc= 0.16981 val_loss= 2.07094 val_acc= 0.17241 time= 0.00000
Epoch: 0053 train_loss= 2.05991 train_acc= 0.16604 val_loss= 2.07172 val_acc= 0.17241 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 2.03993 accuracy= 0.15254 time= 0.00000 
