Epoch: 0001 train_loss= 0.69511 train_acc= 0.49221 val_loss= 0.69394 val_acc= 0.48387 time= 0.90880
Epoch: 0002 train_loss= 0.69322 train_acc= 0.51169 val_loss= 0.69358 val_acc= 0.54839 time= 0.00309
Epoch: 0003 train_loss= 0.69422 train_acc= 0.48701 val_loss= 0.69336 val_acc= 0.53226 time= 0.00000
Epoch: 0004 train_loss= 0.69399 train_acc= 0.50390 val_loss= 0.69325 val_acc= 0.53226 time= 0.01100
Epoch: 0005 train_loss= 0.69260 train_acc= 0.50390 val_loss= 0.69319 val_acc= 0.53226 time= 0.00000
Epoch: 0006 train_loss= 0.69456 train_acc= 0.49870 val_loss= 0.69316 val_acc= 0.53226 time= 0.00000
Epoch: 0007 train_loss= 0.69280 train_acc= 0.51688 val_loss= 0.69315 val_acc= 0.53226 time= 0.01563
Epoch: 0008 train_loss= 0.69291 train_acc= 0.50390 val_loss= 0.69312 val_acc= 0.53226 time= 0.00000
Epoch: 0009 train_loss= 0.69439 train_acc= 0.52468 val_loss= 0.69308 val_acc= 0.53226 time= 0.01563
Epoch: 0010 train_loss= 0.69276 train_acc= 0.51429 val_loss= 0.69301 val_acc= 0.53226 time= 0.00000
Epoch: 0011 train_loss= 0.69321 train_acc= 0.52078 val_loss= 0.69295 val_acc= 0.53226 time= 0.00000
Epoch: 0012 train_loss= 0.69227 train_acc= 0.52727 val_loss= 0.69289 val_acc= 0.53226 time= 0.01563
Epoch: 0013 train_loss= 0.69350 train_acc= 0.49610 val_loss= 0.69283 val_acc= 0.53226 time= 0.00000
Epoch: 0014 train_loss= 0.69370 train_acc= 0.51429 val_loss= 0.69276 val_acc= 0.53226 time= 0.00000
Epoch: 0015 train_loss= 0.69242 train_acc= 0.51169 val_loss= 0.69270 val_acc= 0.53226 time= 0.01563
Epoch: 0016 train_loss= 0.69375 train_acc= 0.51299 val_loss= 0.69264 val_acc= 0.53226 time= 0.00000
Epoch: 0017 train_loss= 0.69430 train_acc= 0.51818 val_loss= 0.69259 val_acc= 0.53226 time= 0.00000
Epoch: 0018 train_loss= 0.69303 train_acc= 0.50130 val_loss= 0.69255 val_acc= 0.53226 time= 0.01563
Epoch: 0019 train_loss= 0.69334 train_acc= 0.50390 val_loss= 0.69251 val_acc= 0.53226 time= 0.00000
Epoch: 0020 train_loss= 0.69325 train_acc= 0.50909 val_loss= 0.69247 val_acc= 0.53226 time= 0.01563
Epoch: 0021 train_loss= 0.69356 train_acc= 0.51429 val_loss= 0.69245 val_acc= 0.53226 time= 0.00000
Epoch: 0022 train_loss= 0.69128 train_acc= 0.51688 val_loss= 0.69242 val_acc= 0.53226 time= 0.00000
Epoch: 0023 train_loss= 0.69371 train_acc= 0.50909 val_loss= 0.69240 val_acc= 0.53226 time= 0.01563
Epoch: 0024 train_loss= 0.69483 train_acc= 0.49091 val_loss= 0.69236 val_acc= 0.53226 time= 0.00000
Epoch: 0025 train_loss= 0.69266 train_acc= 0.52338 val_loss= 0.69231 val_acc= 0.53226 time= 0.00000
Epoch: 0026 train_loss= 0.69237 train_acc= 0.51299 val_loss= 0.69224 val_acc= 0.53226 time= 0.01563
Epoch: 0027 train_loss= 0.69291 train_acc= 0.50909 val_loss= 0.69215 val_acc= 0.54839 time= 0.00000
Epoch: 0028 train_loss= 0.69230 train_acc= 0.52727 val_loss= 0.69208 val_acc= 0.54839 time= 0.00000
Epoch: 0029 train_loss= 0.69203 train_acc= 0.50519 val_loss= 0.69202 val_acc= 0.54839 time= 0.01563
Epoch: 0030 train_loss= 0.69197 train_acc= 0.51039 val_loss= 0.69195 val_acc= 0.54839 time= 0.00000
Epoch: 0031 train_loss= 0.69628 train_acc= 0.50779 val_loss= 0.69193 val_acc= 0.54839 time= 0.00000
Epoch: 0032 train_loss= 0.69395 train_acc= 0.50649 val_loss= 0.69190 val_acc= 0.54839 time= 0.01563
Epoch: 0033 train_loss= 0.69255 train_acc= 0.51299 val_loss= 0.69187 val_acc= 0.54839 time= 0.01055
Epoch: 0034 train_loss= 0.69630 train_acc= 0.51039 val_loss= 0.69187 val_acc= 0.54839 time= 0.00600
Epoch: 0035 train_loss= 0.69291 train_acc= 0.50519 val_loss= 0.69188 val_acc= 0.54839 time= 0.00600
Epoch: 0036 train_loss= 0.69414 train_acc= 0.51688 val_loss= 0.69191 val_acc= 0.54839 time= 0.00700
Epoch: 0037 train_loss= 0.69223 train_acc= 0.51169 val_loss= 0.69193 val_acc= 0.54839 time= 0.00600
Epoch: 0038 train_loss= 0.69224 train_acc= 0.52078 val_loss= 0.69196 val_acc= 0.54839 time= 0.00500
Early stopping...
Optimization Finished!
Test set results: cost= 0.69357 accuracy= 0.54032 time= 0.00300 
