adding logs and csv files

julia/logs/csv_27_09_2019_115637.csv

@@ -0,0 +1,49 @@
+epoch, loss(train), loss(val)
+1, 0.092186, 0.091151
+2, 0.068392, 0.066910
+3, 0.063479, 0.062398
+4, 0.061129, 0.059985
+5, 0.059844, 0.059023
+6, 0.059218, 0.058697
+7, 0.058431, 0.058154
+8, 0.057979, 0.057793
+9, 0.058390, 0.058197
+10, 0.058588, 0.058616
+11, 0.058626, 0.058856
+12, 0.058593, 0.058821
+13, 0.058297, 0.058489
+14, 0.057800, 0.057884
+15, 0.057357, 0.057428
+16, 0.057339, 0.057450
+17, 0.057337, 0.057483
+18, 0.056986, 0.057022
+19, 0.056294, 0.056174
+20, 0.055564, 0.055293
+21, 0.055027, 0.054647
+22, 0.054641, 0.054187
+23, 0.054234, 0.053847
+24, 0.053876, 0.053614
+25, 0.053533, 0.053425
+26, 0.053382, 0.053361
+27, 0.053396, 0.053335
+28, 0.053311, 0.053309
+29, 0.053375, 0.053297
+30, 0.053489, 0.053303
+31, 0.053513, 0.053279
+32, 0.053605, 0.053266
+33, 0.053688, 0.053264
+34, 0.053541, 0.053130
+35, 0.053334, 0.052947
+36, 0.052945, 0.052701
+37, 0.052590, 0.052501
+38, 0.052227, 0.052327
+39, 0.052034, 0.052233
+40, 0.051949, 0.052178
+41, 0.051855, 0.052129
+42, 0.051765, 0.052072
+43, 0.051708, 0.052032
+44, 0.051694, 0.051999
+45, 0.051639, 0.051972
+46, 0.051627, 0.051953
+47, 0.051582, 0.051937
+48, 0.051525, 0.051921

julia/logs/csv_27_09_2019_121316.csv

@@ -0,0 +1,186 @@
+epoch, loss(train), loss(val)
+1, 0.081076, 0.080157
+2, 0.066463, 0.065666
+3, 0.062919, 0.061976
+4, 0.060628, 0.059808
+5, 0.059844, 0.059490
+6, 0.058894, 0.058886
+7, 0.058105, 0.058281
+8, 0.058455, 0.058729
+9, 0.058922, 0.059131
+10, 0.058956, 0.059306
+11, 0.058469, 0.058933
+12, 0.058072, 0.058506
+13, 0.057307, 0.057784
+14, 0.057222, 0.057702
+15, 0.057362, 0.057717
+16, 0.057522, 0.057944
+17, 0.057647, 0.058053
+18, 0.057541, 0.057957
+19, 0.057042, 0.057471
+20, 0.056091, 0.056579
+21, 0.054991, 0.055530
+22, 0.054226, 0.054662
+23, 0.053777, 0.054135
+24, 0.053539, 0.053836
+25, 0.053446, 0.053619
+26, 0.053313, 0.053470
+27, 0.053191, 0.053353
+28, 0.052992, 0.053204
+29, 0.052857, 0.053072
+30, 0.052719, 0.052959
+31, 0.052611, 0.052836
+32, 0.052661, 0.052784
+33, 0.052623, 0.052703
+34, 0.052687, 0.052694
+35, 0.052638, 0.052621
+36, 0.052712, 0.052623
+37, 0.052754, 0.052622
+38, 0.052624, 0.052540
+39, 0.052501, 0.052471
+40, 0.052327, 0.052386
+41, 0.052139, 0.052290
+42, 0.051910, 0.052190
+43, 0.051775, 0.052131
+44, 0.051657, 0.052084
+45, 0.051575, 0.052054
+46, 0.051527, 0.052025
+47, 0.051509, 0.052006
+48, 0.051462, 0.051982
+49, 0.051404, 0.051955
+50, 0.051383, 0.051947
+51, 0.051343, 0.051926
+52, 0.051307, 0.051916
+53, 0.051265, 0.051910
+54, 0.051228, 0.051908
+55, 0.051189, 0.051919
+56, 0.051161, 0.051932
+57, 0.051141, 0.051949
+58, 0.051128, 0.051980
+59, 0.051120, 0.052005
+60, 0.051108, 0.052011
+61, 0.051099, 0.052020
+62, 0.051082, 0.052008
+63, 0.051070, 0.052010
+64, 0.051047, 0.051978
+65, 0.051030, 0.051959
+66, 0.051010, 0.051929
+67, 0.050991, 0.051898
+68, 0.050976, 0.051871
+69, 0.050964, 0.051857
+70, 0.050952, 0.051838
+71, 0.050941, 0.051816
+72, 0.050934, 0.051809
+73, 0.050927, 0.051804
+74, 0.050920, 0.051786
+75, 0.050914, 0.051782
+76, 0.050908, 0.051770
+77, 0.050903, 0.051765
+78, 0.050898, 0.051756
+79, 0.050894, 0.051756
+80, 0.050890, 0.051747
+81, 0.050886, 0.051748
+82, 0.050883, 0.051741
+83, 0.050879, 0.051741
+84, 0.050876, 0.051734
+85, 0.050874, 0.051729
+86, 0.050871, 0.051728
+87, 0.050868, 0.051726
+88, 0.050866, 0.051722
+89, 0.050864, 0.051722
+90, 0.050862, 0.051717
+91, 0.050860, 0.051716
+92, 0.050858, 0.051717
+93, 0.050857, 0.051714
+94, 0.050855, 0.051716
+95, 0.050854, 0.051711
+96, 0.050853, 0.051714
+97, 0.050852, 0.051707
+98, 0.050850, 0.051708
+99, 0.050849, 0.051707
+100, 0.050848, 0.051707
+101, 0.050848, 0.051707
+102, 0.050847, 0.051705
+103, 0.050846, 0.051703
+104, 0.050845, 0.051702
+105, 0.050845, 0.051702
+106, 0.050844, 0.051700
+107, 0.050844, 0.051701
+108, 0.050843, 0.051700
+109, 0.050843, 0.051700
+110, 0.050842, 0.051699
+111, 0.050842, 0.051699
+112, 0.050841, 0.051699
+113, 0.050841, 0.051697
+114, 0.050841, 0.051696
+115, 0.050840, 0.051697
+116, 0.050840, 0.051698
+117, 0.050840, 0.051695
+118, 0.050840, 0.051696
+119, 0.050839, 0.051695
+120, 0.050839, 0.051695
+121, 0.050839, 0.051695
+122, 0.050839, 0.051694
+123, 0.050839, 0.051694
+124, 0.050839, 0.051694
+125, 0.050838, 0.051694
+126, 0.050838, 0.051694
+127, 0.050838, 0.051694
+128, 0.050838, 0.051693
+129, 0.050838, 0.051693
+130, 0.050838, 0.051693
+131, 0.050838, 0.051693
+132, 0.050838, 0.051693
+133, 0.050838, 0.051693
+134, 0.050838, 0.051693
+135, 0.050838, 0.051693
+136, 0.050838, 0.051693
+137, 0.050838, 0.051693
+138, 0.050838, 0.051693
+139, 0.050837, 0.051692
+140, 0.050837, 0.051692
+141, 0.050837, 0.051692
+142, 0.050837, 0.051692
+143, 0.050837, 0.051692
+144, 0.050837, 0.051691
+145, 0.050837, 0.051691
+146, 0.050837, 0.051691
+147, 0.050837, 0.051691
+148, 0.050837, 0.051691
+149, 0.050837, 0.051691
+150, 0.050837, 0.051691
+151, 0.050837, 0.051691
+152, 0.050837, 0.051691
+153, 0.050837, 0.051691
+154, 0.050837, 0.051691
+155, 0.050837, 0.051691
+156, 0.050837, 0.051691
+157, 0.050837, 0.051691
+158, 0.050837, 0.051691
+159, 0.050837, 0.051691
+160, 0.050837, 0.051691
+161, 0.050837, 0.051691
+162, 0.050837, 0.051691
+163, 0.050837, 0.051691
+164, 0.050837, 0.051691
+165, 0.050837, 0.051691
+166, 0.050837, 0.051691
+167, 0.050837, 0.051691
+168, 0.050837, 0.051691
+169, 0.050837, 0.051691
+170, 0.050837, 0.051690
+171, 0.050837, 0.051691
+172, 0.050837, 0.051691
+173, 0.050837, 0.051691
+174, 0.050837, 0.051691
+175, 0.050837, 0.051691
+176, 0.050837, 0.051691
+177, 0.050837, 0.051690
+178, 0.050837, 0.051690
+179, 0.050837, 0.051690
+180, 0.050837, 0.051690
+181, 0.050837, 0.051690
+182, 0.050837, 0.051691
+183, 0.050837, 0.051691
+184, 0.050837, 0.051690
+185, 0.050837, 0.051690

julia/logs/csv_27_09_2019_131458.csv

@@ -0,0 +1,179 @@
+epoch, loss(train), loss(val)
+1, 0.088105, 0.086994
+2, 0.069016, 0.067319
+3, 0.063493, 0.062490
+4, 0.061166, 0.060324
+5, 0.059111, 0.058802
+6, 0.058217, 0.058072
+7, 0.057673, 0.057601
+8, 0.057304, 0.057162
+9, 0.057062, 0.057025
+10, 0.057418, 0.057427
+11, 0.057644, 0.057757
+12, 0.057245, 0.057434
+13, 0.056343, 0.056625
+14, 0.056089, 0.056457
+15, 0.056293, 0.056731
+16, 0.057241, 0.057628
+17, 0.058247, 0.058648
+18, 0.058864, 0.059277
+19, 0.058467, 0.058816
+20, 0.056868, 0.057285
+21, 0.055204, 0.055681
+22, 0.054202, 0.054688
+23, 0.053643, 0.054081
+24, 0.053434, 0.053787
+25, 0.053255, 0.053631
+26, 0.053279, 0.053585
+27, 0.053285, 0.053530
+28, 0.053115, 0.053377
+29, 0.052885, 0.053194
+30, 0.052647, 0.053007
+31, 0.052432, 0.052852
+32, 0.052234, 0.052709
+33, 0.052098, 0.052580
+34, 0.052016, 0.052496
+35, 0.052007, 0.052426
+36, 0.052028, 0.052371
+37, 0.052057, 0.052324
+38, 0.052117, 0.052293
+39, 0.052214, 0.052288
+40, 0.052251, 0.052291
+41, 0.052255, 0.052270
+42, 0.052318, 0.052298
+43, 0.052147, 0.052220
+44, 0.051987, 0.052156
+45, 0.051803, 0.052075
+46, 0.051691, 0.052033
+47, 0.051588, 0.051987
+48, 0.051484, 0.051949
+49, 0.051444, 0.051918
+50, 0.051383, 0.051890
+51, 0.051326, 0.051866
+52, 0.051305, 0.051856
+53, 0.051260, 0.051832
+54, 0.051201, 0.051819
+55, 0.051167, 0.051810
+56, 0.051128, 0.051802
+57, 0.051077, 0.051806
+58, 0.051048, 0.051810
+59, 0.051017, 0.051813
+60, 0.050985, 0.051836
+61, 0.050961, 0.051862
+62, 0.050945, 0.051891
+63, 0.050936, 0.051925
+64, 0.050925, 0.051931
+65, 0.050917, 0.051942
+66, 0.050912, 0.051960
+67, 0.050904, 0.051971
+68, 0.050889, 0.051948
+69, 0.050875, 0.051924
+70, 0.050863, 0.051906
+71, 0.050853, 0.051900
+72, 0.050842, 0.051879
+73, 0.050831, 0.051857
+74, 0.050825, 0.051850
+75, 0.050815, 0.051819
+76, 0.050810, 0.051824
+77, 0.050803, 0.051799
+78, 0.050798, 0.051791
+79, 0.050794, 0.051790
+80, 0.050789, 0.051775
+81, 0.050785, 0.051775
+82, 0.050781, 0.051772
+83, 0.050777, 0.051764
+84, 0.050774, 0.051762
+85, 0.050772, 0.051758
+86, 0.050769, 0.051756
+87, 0.050766, 0.051754
+88, 0.050764, 0.051743
+89, 0.050761, 0.051744
+90, 0.050759, 0.051742
+91, 0.050757, 0.051739
+92, 0.050756, 0.051735
+93, 0.050754, 0.051730
+94, 0.050753, 0.051730
+95, 0.050751, 0.051732
+96, 0.050750, 0.051725
+97, 0.050749, 0.051720
+98, 0.050748, 0.051723
+99, 0.050747, 0.051725
+100, 0.050746, 0.051722
+101, 0.050745, 0.051723
+102, 0.050744, 0.051720
+103, 0.050744, 0.051720
+104, 0.050743, 0.051720
+105, 0.050743, 0.051715
+106, 0.050742, 0.051718
+107, 0.050741, 0.051720
+108, 0.050741, 0.051719
+109, 0.050740, 0.051717
+110, 0.050740, 0.051715
+111, 0.050739, 0.051716
+112, 0.050739, 0.051715
+113, 0.050739, 0.051714
+114, 0.050738, 0.051714
+115, 0.050738, 0.051713
+116, 0.050738, 0.051712
+117, 0.050737, 0.051713
+118, 0.050737, 0.051714
+119, 0.050737, 0.051713
+120, 0.050737, 0.051713
+121, 0.050736, 0.051712
+122, 0.050736, 0.051713
+123, 0.050736, 0.051714
+124, 0.050736, 0.051713
+125, 0.050736, 0.051713
+126, 0.050736, 0.051711
+127, 0.050736, 0.051710
+128, 0.050736, 0.051710
+129, 0.050736, 0.051711
+130, 0.050736, 0.051710
+131, 0.050735, 0.051710
+132, 0.050735, 0.051709
+133, 0.050735, 0.051709
+134, 0.050735, 0.051709
+135, 0.050735, 0.051709
+136, 0.050735, 0.051709
+137, 0.050735, 0.051709
+138, 0.050735, 0.051709
+139, 0.050735, 0.051709
+140, 0.050735, 0.051709
+141, 0.050735, 0.051709
+142, 0.050735, 0.051709
+143, 0.050735, 0.051709
+144, 0.050735, 0.051708
+145, 0.050735, 0.051708
+146, 0.050735, 0.051708
+147, 0.050735, 0.051708
+148, 0.050735, 0.051708
+149, 0.050735, 0.051708
+150, 0.050735, 0.051708
+151, 0.050735, 0.051708
+152, 0.050735, 0.051708
+153, 0.050735, 0.051708
+154, 0.050735, 0.051708
+155, 0.050735, 0.051708
+156, 0.050735, 0.051708
+157, 0.050735, 0.051708
+158, 0.050735, 0.051707
+159, 0.050735, 0.051708
+160, 0.050735, 0.051707
+161, 0.050735, 0.051707
+162, 0.050735, 0.051707
+163, 0.050735, 0.051707
+164, 0.050735, 0.051707
+165, 0.050735, 0.051707
+166, 0.050735, 0.051707
+167, 0.050735, 0.051707
+168, 0.050735, 0.051707
+169, 0.050735, 0.051707
+170, 0.050735, 0.051707
+171, 0.050735, 0.051707
+172, 0.050735, 0.051707
+173, 0.050735, 0.051707
+174, 0.050735, 0.051707
+175, 0.050735, 0.051707
+176, 0.050735, 0.051707
+177, 0.050735, 0.051707
+178, 0.050735, 0.051707

julia/logs/csv_27_09_2019_141435.csv

@@ -0,0 +1,122 @@
+epoch, loss(train), loss(val)
+1, 0.083907, 0.081955
+2, 0.068132, 0.065991
+3, 0.064358, 0.062997
+4, 0.061868, 0.060734
+5, 0.060204, 0.059312
+6, 0.059414, 0.058558
+7, 0.059107, 0.058340
+8, 0.058650, 0.058108
+9, 0.058586, 0.058022
+10, 0.058222, 0.057530
+11, 0.057032, 0.056690
+12, 0.056028, 0.056090
+13, 0.055813, 0.055851
+14, 0.055829, 0.055917
+15, 0.055897, 0.055976
+16, 0.056135, 0.056123
+17, 0.056230, 0.056183
+18, 0.056125, 0.056139
+19, 0.055650, 0.055800
+20, 0.054972, 0.055264
+21, 0.054440, 0.054758
+22, 0.053841, 0.054197
+23, 0.053537, 0.053910
+24, 0.053408, 0.053739
+25, 0.053226, 0.053595
+26, 0.053119, 0.053496
+27, 0.052935, 0.053418
+28, 0.052792, 0.053326
+29, 0.052685, 0.053225
+30, 0.052581, 0.053122
+31, 0.052482, 0.052982
+32, 0.052412, 0.052856
+33, 0.052346, 0.052704
+34, 0.052295, 0.052583
+35, 0.052348, 0.052517
+36, 0.052433, 0.052474
+37, 0.052447, 0.052436
+38, 0.052484, 0.052398
+39, 0.052436, 0.052350
+40, 0.052317, 0.052269
+41, 0.052149, 0.052165
+42, 0.051951, 0.052058
+43, 0.051784, 0.051979
+44, 0.051669, 0.051930
+45, 0.051619, 0.051897
+46, 0.051569, 0.051867
+47, 0.051530, 0.051850
+48, 0.051510, 0.051823
+49, 0.051496, 0.051809
+50, 0.051463, 0.051780
+51, 0.051449, 0.051762
+52, 0.051398, 0.051743
+53, 0.051360, 0.051725
+54, 0.051305, 0.051718
+55, 0.051258, 0.051707
+56, 0.051204, 0.051714
+57, 0.051156, 0.051728
+58, 0.051121, 0.051750
+59, 0.051093, 0.051791
+60, 0.051078, 0.051821
+61, 0.051071, 0.051861
+62, 0.051062, 0.051875
+63, 0.051061, 0.051915
+64, 0.051050, 0.051913
+65, 0.051034, 0.051904
+66, 0.051013, 0.051877
+67, 0.050995, 0.051856
+68, 0.050979, 0.051836
+69, 0.050962, 0.051815
+70, 0.050948, 0.051795
+71, 0.050935, 0.051775
+72, 0.050922, 0.051754
+73, 0.050911, 0.051733
+74, 0.050903, 0.051725
+75, 0.050895, 0.051708
+76, 0.050888, 0.051702
+77, 0.050882, 0.051694
+78, 0.050876, 0.051685
+79, 0.050870, 0.051676
+80, 0.050866, 0.051670
+81, 0.050862, 0.051671
+82, 0.050857, 0.051659
+83, 0.050854, 0.051658
+84, 0.050850, 0.051653
+85, 0.050846, 0.051647
+86, 0.050843, 0.051643
+87, 0.050840, 0.051639
+88, 0.050838, 0.051637
+89, 0.050836, 0.051631
+90, 0.050833, 0.051629
+91, 0.050832, 0.051632
+92, 0.050830, 0.051625
+93, 0.050828, 0.051624
+94, 0.050826, 0.051620
+95, 0.050825, 0.051621
+96, 0.050824, 0.051618
+97, 0.050822, 0.051618
+98, 0.050821, 0.051615
+99, 0.050820, 0.051617
+100, 0.050819, 0.051613
+101, 0.050818, 0.051613
+102, 0.050817, 0.051612
+103, 0.050816, 0.051608
+104, 0.050815, 0.051608
+105, 0.050815, 0.051608
+106, 0.050814, 0.051608
+107, 0.050814, 0.051607
+108, 0.050813, 0.051606
+109, 0.050812, 0.051606
+110, 0.050812, 0.051606
+111, 0.050812, 0.051606
+112, 0.050811, 0.051607
+113, 0.050811, 0.051604
+114, 0.050810, 0.051604
+115, 0.050810, 0.051604
+116, 0.050810, 0.051603
+117, 0.050809, 0.051603
+118, 0.050809, 0.051603
+119, 0.050809, 0.051602
+120, 0.050809, 0.051603
+121, 0.050808, 0.051602

julia/logs/csv_27_09_2019_145521.csv

@@ -0,0 +1,294 @@
+epoch, loss(train), loss(val)
+1, 0.089365, 0.089866
+2, 0.068522, 0.067475
+3, 0.064660, 0.063543
+4, 0.060944, 0.060222
+5, 0.059607, 0.059185
+6, 0.059017, 0.058908
+7, 0.058705, 0.058627
+8, 0.057935, 0.057949
+9, 0.057351, 0.057564
+10, 0.057105, 0.057496
+11, 0.057331, 0.057902
+12, 0.057670, 0.058274
+13, 0.057249, 0.057841
+14, 0.056559, 0.057023
+15, 0.056072, 0.056385
+16, 0.055778, 0.056150
+17, 0.055711, 0.056225
+18, 0.056003, 0.056527
+19, 0.056290, 0.056798
+20, 0.056202, 0.056684
+21, 0.055960, 0.056379
+22, 0.055332, 0.055604
+23, 0.054427, 0.054705
+24, 0.053469, 0.053835
+25, 0.052888, 0.053347
+26, 0.052713, 0.053128
+27, 0.052674, 0.053046
+28, 0.052746, 0.053070
+29, 0.052882, 0.053139
+30, 0.053056, 0.053216
+31, 0.053288, 0.053299
+32, 0.053367, 0.053294
+33, 0.053364, 0.053223
+34, 0.053219, 0.053042
+35, 0.052854, 0.052749
+36, 0.052477, 0.052477
+37, 0.052089, 0.052239
+38, 0.051860, 0.052100
+39, 0.051728, 0.052022
+40, 0.051652, 0.051964
+41, 0.051576, 0.051914
+42, 0.051482, 0.051847
+43, 0.051408, 0.051786
+44, 0.051326, 0.051744
+45, 0.051266, 0.051715
+46, 0.051217, 0.051692
+47, 0.051178, 0.051682
+48, 0.051143, 0.051676
+49, 0.051100, 0.051670
+50, 0.051068, 0.051674
+51, 0.051037, 0.051669
+52, 0.051013, 0.051687
+53, 0.050992, 0.051694
+54, 0.050976, 0.051701
+55, 0.050966, 0.051729
+56, 0.050953, 0.051729
+57, 0.050937, 0.051726
+58, 0.050921, 0.051718
+59, 0.050908, 0.051713
+60, 0.050892, 0.051699
+61, 0.050871, 0.051670
+62, 0.050855, 0.051652
+63, 0.050837, 0.051624
+64, 0.050821, 0.051595
+65, 0.050809, 0.051581
+66, 0.050798, 0.051564
+67, 0.050787, 0.051544
+68, 0.050780, 0.051538
+69, 0.050771, 0.051531
+70, 0.050765, 0.051523
+71, 0.050759, 0.051518
+72, 0.050751, 0.051504
+73, 0.050746, 0.051499
+74, 0.050740, 0.051495
+75, 0.050735, 0.051488
+76, 0.050731, 0.051485
+77, 0.050727, 0.051479
+78, 0.050722, 0.051469
+79, 0.050718, 0.051463
+80, 0.050715, 0.051465
+81, 0.050712, 0.051464
+82, 0.050708, 0.051460
+83, 0.050705, 0.051456
+84, 0.050702, 0.051454
+85, 0.050700, 0.051448
+86, 0.050697, 0.051446
+87, 0.050695, 0.051446
+88, 0.050693, 0.051441
+89, 0.050691, 0.051438
+90, 0.050689, 0.051439
+91, 0.050687, 0.051436
+92, 0.050686, 0.051437
+93, 0.050685, 0.051436
+94, 0.050683, 0.051432
+95, 0.050682, 0.051432
+96, 0.050680, 0.051430
+97, 0.050679, 0.051429
+98, 0.050678, 0.051428
+99, 0.050677, 0.051427
+100, 0.050677, 0.051429
+101, 0.050676, 0.051427
+102, 0.050675, 0.051424
+103, 0.050674, 0.051422
+104, 0.050674, 0.051424
+105, 0.050673, 0.051424
+106, 0.050673, 0.051425
+107, 0.050672, 0.051423
+108, 0.050672, 0.051423
+109, 0.050671, 0.051424
+110, 0.050671, 0.051423
+111, 0.050670, 0.051422
+112, 0.050670, 0.051422
+113, 0.050670, 0.051421
+114, 0.050669, 0.051421
+115, 0.050669, 0.051422
+116, 0.050669, 0.051422
+117, 0.050669, 0.051421
+118, 0.050668, 0.051421
+119, 0.050668, 0.051420
+120, 0.050668, 0.051420
+121, 0.050668, 0.051419
+122, 0.050668, 0.051419
+123, 0.050667, 0.051419
+124, 0.050667, 0.051419
+125, 0.050667, 0.051419
+126, 0.050667, 0.051419
+127, 0.050667, 0.051419
+128, 0.050667, 0.051419
+129, 0.050667, 0.051419
+130, 0.050667, 0.051419
+131, 0.050667, 0.051419
+132, 0.050667, 0.051419
+133, 0.050667, 0.051418
+134, 0.050666, 0.051418
+135, 0.050666, 0.051418
+136, 0.050666, 0.051418
+137, 0.050666, 0.051418
+138, 0.050666, 0.051418
+139, 0.050666, 0.051418
+140, 0.050666, 0.051418
+141, 0.050666, 0.051417
+142, 0.050666, 0.051417
+143, 0.050666, 0.051418
+144, 0.050666, 0.051418
+145, 0.050666, 0.051417
+146, 0.050666, 0.051417
+147, 0.050666, 0.051417
+148, 0.050666, 0.051417
+149, 0.050666, 0.051417
+150, 0.050666, 0.051417
+151, 0.050666, 0.051417
+152, 0.050666, 0.051417
+153, 0.050666, 0.051417
+154, 0.050666, 0.051417
+155, 0.050666, 0.051417
+156, 0.050666, 0.051417
+157, 0.050666, 0.051417
+158, 0.050666, 0.051417
+159, 0.050666, 0.051417
+160, 0.050666, 0.051417
+161, 0.050666, 0.051417
+162, 0.050666, 0.051417
+163, 0.050666, 0.051417
+164, 0.050666, 0.051417
+165, 0.050666, 0.051417
+166, 0.050666, 0.051417
+167, 0.050666, 0.051417
+168, 0.050666, 0.051417
+169, 0.050666, 0.051417
+170, 0.050666, 0.051417
+171, 0.050666, 0.051417
+172, 0.050666, 0.051417
+173, 0.050666, 0.051417
+174, 0.050666, 0.051417
+175, 0.050666, 0.051417
+176, 0.050666, 0.051417
+177, 0.050666, 0.051417
+178, 0.050666, 0.051417
+179, 0.050666, 0.051417
+180, 0.050666, 0.051417
+181, 0.050666, 0.051417
+182, 0.050666, 0.051417
+183, 0.050666, 0.051417
+184, 0.050666, 0.051417
+185, 0.050666, 0.051417
+186, 0.050666, 0.051417
+187, 0.050666, 0.051417
+188, 0.050666, 0.051417
+189, 0.050666, 0.051417
+190, 0.050666, 0.051417
+191, 0.050666, 0.051417
+192, 0.050666, 0.051417
+193, 0.050666, 0.051417
+194, 0.050666, 0.051417
+195, 0.050666, 0.051417
+196, 0.050666, 0.051417
+197, 0.050666, 0.051417
+198, 0.050666, 0.051417
+199, 0.050666, 0.051417
+200, 0.050666, 0.051417
+201, 0.050666, 0.051417
+202, 0.050666, 0.051417
+203, 0.050666, 0.051417
+204, 0.050666, 0.051417
+205, 0.050666, 0.051417
+206, 0.050666, 0.051417
+207, 0.050666, 0.051417
+208, 0.050666, 0.051417
+209, 0.050666, 0.051417
+210, 0.050666, 0.051417
+211, 0.050666, 0.051417
+212, 0.050666, 0.051417
+213, 0.050666, 0.051417
+214, 0.050666, 0.051417
+215, 0.050666, 0.051417
+216, 0.050666, 0.051417
+217, 0.050666, 0.051417
+218, 0.050666, 0.051417
+219, 0.050666, 0.051417
+220, 0.050666, 0.051417
+221, 0.050666, 0.051417
+222, 0.050666, 0.051417
+223, 0.050666, 0.051417
+224, 0.050666, 0.051417
+225, 0.050666, 0.051417
+226, 0.050666, 0.051417
+227, 0.050666, 0.051417
+228, 0.050666, 0.051417
+229, 0.050666, 0.051417
+230, 0.050666, 0.051417
+231, 0.050666, 0.051417
+232, 0.050666, 0.051417
+233, 0.050666, 0.051417
+234, 0.050666, 0.051417
+235, 0.050666, 0.051417
+236, 0.050666, 0.051417
+237, 0.050666, 0.051417
+238, 0.050666, 0.051417
+239, 0.050666, 0.051417
+240, 0.050666, 0.051417
+241, 0.050666, 0.051417
+242, 0.050666, 0.051417
+243, 0.050666, 0.051417
+244, 0.050666, 0.051417
+245, 0.050666, 0.051417
+246, 0.050666, 0.051417
+247, 0.050666, 0.051417
+248, 0.050666, 0.051417
+249, 0.050666, 0.051417
+250, 0.050666, 0.051417
+251, 0.050666, 0.051417
+252, 0.050666, 0.051417
+253, 0.050666, 0.051417
+254, 0.050666, 0.051417
+255, 0.050666, 0.051417
+256, 0.050666, 0.051417
+257, 0.050666, 0.051417
+258, 0.050666, 0.051417
+259, 0.050666, 0.051417
+260, 0.050666, 0.051417
+261, 0.050666, 0.051417
+262, 0.050666, 0.051417
+263, 0.050666, 0.051417
+264, 0.050666, 0.051417
+265, 0.050666, 0.051417
+266, 0.050666, 0.051417
+267, 0.050666, 0.051417
+268, 0.050666, 0.051417
+269, 0.050666, 0.051417
+270, 0.050666, 0.051417
+271, 0.050666, 0.051417
+272, 0.050666, 0.051417
+273, 0.050666, 0.051417
+274, 0.050666, 0.051417
+275, 0.050666, 0.051417
+276, 0.050666, 0.051417
+277, 0.050666, 0.051417
+278, 0.050666, 0.051417
+279, 0.050666, 0.051417
+280, 0.050666, 0.051417
+281, 0.050666, 0.051417
+282, 0.050666, 0.051417
+283, 0.050666, 0.051417
+284, 0.050666, 0.051417
+285, 0.050666, 0.051417
+286, 0.050666, 0.051417
+287, 0.050666, 0.051417
+288, 0.050666, 0.051417
+289, 0.050666, 0.051417
+290, 0.050666, 0.051417
+291, 0.050666, 0.051417
+292, 0.050666, 0.051417
+293, 0.050666, 0.051417

julia/logs/csv_27_09_2019_165125.csv

@@ -0,0 +1,534 @@
+epoch, loss(train), loss(val)
+1, 0.089663, 0.088737
+2, 0.070667, 0.068928
+3, 0.063542, 0.062128
+4, 0.060417, 0.059723
+5, 0.059493, 0.059026
+6, 0.058942, 0.058448
+7, 0.058415, 0.057891
+8, 0.057964, 0.057296
+9, 0.057504, 0.056888
+10, 0.056998, 0.056621
+11, 0.056863, 0.056618
+12, 0.056772, 0.056483
+13, 0.056706, 0.056282
+14, 0.056430, 0.055929
+15, 0.056260, 0.055614
+16, 0.055839, 0.055432
+17, 0.055648, 0.055394
+18, 0.055889, 0.055650
+19, 0.056102, 0.055804
+20, 0.055990, 0.055733
+21, 0.056002, 0.055650
+22, 0.055604, 0.055251
+23, 0.054814, 0.054507
+24, 0.054289, 0.053961
+25, 0.054040, 0.053693
+26, 0.054076, 0.053621
+27, 0.054120, 0.053601
+28, 0.054555, 0.053849
+29, 0.055195, 0.054283
+30, 0.055647, 0.054590
+31, 0.055832, 0.054655
+32, 0.055375, 0.054319
+33, 0.054487, 0.053729
+34, 0.053432, 0.053076
+35, 0.052729, 0.052693
+36, 0.052390, 0.052524
+37, 0.052178, 0.052437
+38, 0.052099, 0.052385
+39, 0.052070, 0.052320
+40, 0.052017, 0.052243
+41, 0.051925, 0.052159
+42, 0.051824, 0.052056
+43, 0.051765, 0.051970
+44, 0.051683, 0.051933
+45, 0.051606, 0.051889
+46, 0.051533, 0.051864
+47, 0.051464, 0.051846
+48, 0.051401, 0.051838
+49, 0.051325, 0.051843
+50, 0.051266, 0.051860
+51, 0.051222, 0.051899
+52, 0.051193, 0.051918
+53, 0.051176, 0.051968
+54, 0.051162, 0.052006
+55, 0.051134, 0.051998
+56, 0.051111, 0.051992
+57, 0.051075, 0.051958
+58, 0.051050, 0.051941
+59, 0.051010, 0.051883
+60, 0.050980, 0.051837
+61, 0.050952, 0.051785
+62, 0.050934, 0.051770
+63, 0.050916, 0.051740
+64, 0.050899, 0.051707
+65, 0.050887, 0.051699
+66, 0.050875, 0.051674
+67, 0.050866, 0.051669
+68, 0.050856, 0.051652
+69, 0.050847, 0.051641
+70, 0.050839, 0.051635
+1, 0.088789, 0.087691
+2, 0.068032, 0.067004
+3, 0.063522, 0.062396
+4, 0.061677, 0.060596
+5, 0.060235, 0.059540
+6, 0.060055, 0.059479
+7, 0.059696, 0.058983
+8, 0.058420, 0.057931
+9, 0.057890, 0.057784
+10, 0.057887, 0.057939
+11, 0.058021, 0.058248
+12, 0.057937, 0.058021
+13, 0.057402, 0.057456
+14, 0.056914, 0.057007
+15, 0.056709, 0.056965
+16, 0.056852, 0.057157
+17, 0.057367, 0.057542
+18, 0.057601, 0.057665
+19, 0.057731, 0.057718
+20, 0.057218, 0.057077
+21, 0.056135, 0.056025
+22, 0.055024, 0.054987
+23, 0.054295, 0.054281
+24, 0.053959, 0.053951
+25, 0.053691, 0.053717
+26, 0.053627, 0.053622
+27, 0.053773, 0.053724
+28, 0.054236, 0.053973
+29, 0.054522, 0.054070
+30, 0.054943, 0.054246
+31, 0.055004, 0.054189
+32, 0.054876, 0.053994
+33, 0.054486, 0.053667
+34, 0.053800, 0.053187
+35, 0.053172, 0.052797
+36, 0.052741, 0.052563
+37, 0.052461, 0.052420
+38, 0.052257, 0.052302
+39, 0.052129, 0.052214
+40, 0.052035, 0.052163
+41, 0.051944, 0.052115
+42, 0.051880, 0.052084
+43, 0.051804, 0.052055
+44, 0.051738, 0.052032
+45, 0.051650, 0.052006
+46, 0.051562, 0.051986
+47, 0.051479, 0.051978
+48, 0.051412, 0.051979
+49, 0.051361, 0.051999
+50, 0.051323, 0.052038
+51, 0.051302, 0.052081
+52, 0.051278, 0.052096
+53, 0.051261, 0.052118
+54, 0.051239, 0.052120
+55, 0.051207, 0.052095
+1, 0.090615, 0.089994
+2, 0.069812, 0.068600
+3, 0.064214, 0.063470
+4, 0.061411, 0.061059
+5, 0.060100, 0.059814
+6, 0.059087, 0.059043
+7, 0.058686, 0.058661
+8, 0.058388, 0.058214
+9, 0.058066, 0.057698
+10, 0.057511, 0.057332
+11, 0.057068, 0.057097
+12, 0.057114, 0.057160
+13, 0.056885, 0.056944
+14, 0.056694, 0.056566
+15, 0.056233, 0.056134
+16, 0.055359, 0.055511
+17, 0.055256, 0.055431
+18, 0.055643, 0.055726
+19, 0.056205, 0.056171
+20, 0.056926, 0.056773
+21, 0.057006, 0.056768
+22, 0.056528, 0.056344
+23, 0.055433, 0.055290
+24, 0.054533, 0.054371
+25, 0.054282, 0.054007
+26, 0.054135, 0.053829
+27, 0.054173, 0.053806
+28, 0.054269, 0.053833
+29, 0.054556, 0.054030
+30, 0.054662, 0.054104
+31, 0.054619, 0.054089
+32, 0.054174, 0.053796
+33, 0.053649, 0.053463
+34, 0.052997, 0.053043
+35, 0.052595, 0.052792
+36, 0.052346, 0.052621
+37, 0.052151, 0.052500
+38, 0.052059, 0.052406
+39, 0.052001, 0.052335
+40, 0.051941, 0.052277
+41, 0.051894, 0.052226
+42, 0.051868, 0.052181
+43, 0.051789, 0.052130
+44, 0.051722, 0.052078
+45, 0.051639, 0.052052
+46, 0.051541, 0.052007
+47, 0.051465, 0.052000
+48, 0.051404, 0.051979
+49, 0.051339, 0.051980
+50, 0.051292, 0.051991
+51, 0.051249, 0.051991
+52, 0.051222, 0.052008
+53, 0.051198, 0.052018
+54, 0.051173, 0.052017
+55, 0.051146, 0.052003
+56, 0.051118, 0.051979
+57, 0.051087, 0.051948
+58, 0.051059, 0.051916
+59, 0.051032, 0.051880
+60, 0.051009, 0.051852
+1, 0.087576, 0.086033
+2, 0.068133, 0.066643
+3, 0.062122, 0.060931
+4, 0.058892, 0.058234
+5, 0.057786, 0.057269
+6, 0.057601, 0.057197
+7, 0.056949, 0.056568
+8, 0.056481, 0.056139
+9, 0.056194, 0.055886
+10, 0.055974, 0.055750
+11, 0.055800, 0.055777
+12, 0.055692, 0.055731
+13, 0.055691, 0.055779
+14, 0.055478, 0.055565
+15, 0.055101, 0.055146
+16, 0.054910, 0.054922
+17, 0.054790, 0.054875
+18, 0.054960, 0.055119
+19, 0.055063, 0.055270
+20, 0.054944, 0.055221
+21, 0.054798, 0.055048
+22, 0.054379, 0.054582
+23, 0.053794, 0.053956
+24, 0.053113, 0.053302
+25, 0.052780, 0.052874
+26, 0.052543, 0.052660
+27, 0.052278, 0.052454
+28, 0.052146, 0.052352
+29, 0.052045, 0.052292
+30, 0.051909, 0.052243
+31, 0.051838, 0.052235
+32, 0.051793, 0.052183
+33, 0.051737, 0.052164
+34, 0.051672, 0.052101
+35, 0.051629, 0.052036
+36, 0.051564, 0.051960
+37, 0.051538, 0.051894
+38, 0.051462, 0.051794
+39, 0.051404, 0.051718
+40, 0.051335, 0.051661
+41, 0.051274, 0.051597
+42, 0.051173, 0.051555
+43, 0.051112, 0.051520
+44, 0.051043, 0.051497
+45, 0.050990, 0.051464
+46, 0.050939, 0.051442
+47, 0.050889, 0.051419
+48, 0.050855, 0.051395
+49, 0.050825, 0.051377
+50, 0.050809, 0.051350
+51, 0.050787, 0.051347
+52, 0.050774, 0.051326
+53, 0.050761, 0.051317
+54, 0.050748, 0.051308
+55, 0.050737, 0.051294
+1, 0.085913, 0.084972
+2, 0.067994, 0.067212
+3, 0.064593, 0.063531
+4, 0.062117, 0.061084
+5, 0.060363, 0.060003
+6, 0.059131, 0.058921
+7, 0.058338, 0.058271
+8, 0.057717, 0.057788
+9, 0.057529, 0.057686
+10, 0.057496, 0.057720
+11, 0.057429, 0.057801
+12, 0.057253, 0.057779
+13, 0.056893, 0.057320
+14, 0.056243, 0.056562
+15, 0.056184, 0.056340
+16, 0.056221, 0.056419
+17, 0.056585, 0.056762
+18, 0.056598, 0.056918
+19, 0.056542, 0.056837
+20, 0.056023, 0.056362
+21, 0.055122, 0.055430
+22, 0.054322, 0.054565
+23, 0.053714, 0.053932
+24, 0.053428, 0.053591
+25, 0.053074, 0.053378
+26, 0.052950, 0.053381
+27, 0.052878, 0.053369
+28, 0.052749, 0.053334
+29, 0.052654, 0.053279
+30, 0.052551, 0.053160
+31, 0.052434, 0.052998
+32, 0.052321, 0.052879
+33, 0.052148, 0.052693
+34, 0.052083, 0.052561
+35, 0.051987, 0.052415
+36, 0.051942, 0.052319
+37, 0.051942, 0.052249
+38, 0.051861, 0.052164
+39, 0.051847, 0.052113
+40, 0.051747, 0.052048
+41, 0.051614, 0.051969
+42, 0.051501, 0.051891
+43, 0.051425, 0.051849
+44, 0.051336, 0.051807
+45, 0.051292, 0.051769
+46, 0.051229, 0.051732
+47, 0.051206, 0.051705
+48, 0.051182, 0.051671
+49, 0.051149, 0.051648
+50, 0.051119, 0.051630
+51, 0.051105, 0.051612
+52, 0.051082, 0.051598
+53, 0.051052, 0.051591
+54, 0.051018, 0.051580
+1, 0.080744, 0.079622
+2, 0.066512, 0.064695
+3, 0.062622, 0.061448
+4, 0.060374, 0.059260
+5, 0.058809, 0.058090
+6, 0.057931, 0.057646
+7, 0.057441, 0.057309
+8, 0.057106, 0.056946
+9, 0.056751, 0.056449
+10, 0.056720, 0.056406
+11, 0.056405, 0.056351
+12, 0.056383, 0.056457
+13, 0.056200, 0.056471
+14, 0.055845, 0.056025
+15, 0.055829, 0.055832
+16, 0.055686, 0.055626
+17, 0.055622, 0.055737
+18, 0.055771, 0.055958
+19, 0.055711, 0.056073
+20, 0.055973, 0.056337
+21, 0.055825, 0.056190
+22, 0.055313, 0.055599
+23, 0.054893, 0.055099
+24, 0.054391, 0.054471
+25, 0.053839, 0.053866
+26, 0.053508, 0.053500
+27, 0.053171, 0.053214
+28, 0.052970, 0.053028
+29, 0.052803, 0.052932
+30, 0.052774, 0.052891
+31, 0.052981, 0.052950
+32, 0.053209, 0.053051
+33, 0.053366, 0.053110
+34, 0.053671, 0.053226
+35, 0.053941, 0.053339
+36, 0.053890, 0.053279
+37, 0.053691, 0.053105
+38, 0.053180, 0.052768
+39, 0.052641, 0.052439
+40, 0.052294, 0.052223
+41, 0.052021, 0.052078
+42, 0.051852, 0.051986
+43, 0.051764, 0.051918
+44, 0.051702, 0.051857
+45, 0.051609, 0.051782
+46, 0.051520, 0.051719
+47, 0.051464, 0.051675
+48, 0.051390, 0.051640
+49, 0.051337, 0.051621
+50, 0.051246, 0.051601
+51, 0.051194, 0.051589
+52, 0.051123, 0.051589
+53, 0.051061, 0.051593
+54, 0.051009, 0.051610
+55, 0.050970, 0.051631
+56, 0.050941, 0.051682
+57, 0.050926, 0.051712
+58, 0.050924, 0.051774
+59, 0.050913, 0.051794
+60, 0.050901, 0.051803
+61, 0.050880, 0.051795
+62, 0.050853, 0.051767
+63, 0.050823, 0.051729
+1, 0.079464, 0.077783
+2, 0.067149, 0.066139
+3, 0.062640, 0.061764
+4, 0.060908, 0.059928
+5, 0.058845, 0.058380
+6, 0.058177, 0.057776
+7, 0.057540, 0.057122
+8, 0.056814, 0.056477
+9, 0.056360, 0.056050
+10, 0.056028, 0.055813
+11, 0.055597, 0.055646
+12, 0.055225, 0.055342
+13, 0.055302, 0.055394
+14, 0.055238, 0.055283
+15, 0.055095, 0.055047
+16, 0.054809, 0.054673
+17, 0.054337, 0.054301
+18, 0.053958, 0.054079
+19, 0.053873, 0.054106
+20, 0.054026, 0.054221
+21, 0.054201, 0.054455
+22, 0.054305, 0.054560
+23, 0.054394, 0.054562
+24, 0.054172, 0.054326
+25, 0.053743, 0.053848
+26, 0.053142, 0.053302
+27, 0.052741, 0.052896
+28, 0.052561, 0.052737
+29, 0.052489, 0.052637
+30, 0.052407, 0.052581
+31, 0.052487, 0.052619
+32, 0.052642, 0.052717
+33, 0.052745, 0.052786
+34, 0.052957, 0.052931
+35, 0.053042, 0.052976
+36, 0.053068, 0.052970
+37, 0.052881, 0.052853
+38, 0.052606, 0.052675
+39, 0.052210, 0.052439
+40, 0.051897, 0.052271
+41, 0.051670, 0.052125
+42, 0.051492, 0.052033
+43, 0.051401, 0.051973
+44, 0.051340, 0.051914
+45, 0.051286, 0.051879
+46, 0.051234, 0.051821
+47, 0.051182, 0.051773
+48, 0.051136, 0.051725
+49, 0.051084, 0.051684
+50, 0.051037, 0.051649
+51, 0.050997, 0.051624
+52, 0.050962, 0.051611
+53, 0.050926, 0.051608
+54, 0.050892, 0.051609
+55, 0.050861, 0.051612
+56, 0.050835, 0.051619
+57, 0.050810, 0.051647
+58, 0.050793, 0.051664
+59, 0.050780, 0.051697
+60, 0.050769, 0.051714
+61, 0.050759, 0.051723
+62, 0.050747, 0.051723
+63, 0.050739, 0.051730
+64, 0.050730, 0.051738
+65, 0.050708, 0.051697
+1, 0.085294, 0.084576
+2, 0.067979, 0.066454
+3, 0.064692, 0.063468
+4, 0.060204, 0.059563
+5, 0.059113, 0.058688
+6, 0.058466, 0.058163
+7, 0.058073, 0.057866
+8, 0.057293, 0.057096
+9, 0.056591, 0.056324
+10, 0.056213, 0.056077
+11, 0.055718, 0.055704
+12, 0.055250, 0.055418
+13, 0.055137, 0.055309
+14, 0.055121, 0.055232
+15, 0.055151, 0.055145
+16, 0.055220, 0.055140
+17, 0.054638, 0.054753
+18, 0.054304, 0.054612
+19, 0.054102, 0.054496
+20, 0.054121, 0.054624
+21, 0.054457, 0.054914
+22, 0.054731, 0.055191
+23, 0.054807, 0.055170
+24, 0.054750, 0.055053
+25, 0.054323, 0.054540
+26, 0.053600, 0.053798
+27, 0.053148, 0.053314
+28, 0.052852, 0.053044
+29, 0.052607, 0.052848
+30, 0.052449, 0.052746
+31, 0.052500, 0.052788
+32, 0.052512, 0.052785
+33, 0.052571, 0.052789
+34, 0.052684, 0.052806
+35, 0.052755, 0.052841
+36, 0.052775, 0.052819
+37, 0.052677, 0.052722
+38, 0.052491, 0.052566
+39, 0.052202, 0.052362
+40, 0.051935, 0.052191
+41, 0.051739, 0.052059
+42, 0.051572, 0.051957
+43, 0.051486, 0.051892
+44, 0.051410, 0.051844
+45, 0.051352, 0.051801
+46, 0.051312, 0.051755
+47, 0.051259, 0.051708
+48, 0.051191, 0.051682
+49, 0.051153, 0.051656
+50, 0.051126, 0.051639
+51, 0.051106, 0.051628
+52, 0.051067, 0.051622
+53, 0.051033, 0.051616
+54, 0.051009, 0.051614
+55, 0.050979, 0.051613
+56, 0.050938, 0.051623
+57, 0.050908, 0.051627
+58, 0.050878, 0.051646
+59, 0.050853, 0.051660
+60, 0.050829, 0.051672
+1, 0.087630, 0.086648
+2, 0.068650, 0.067234
+3, 0.064484, 0.062984
+4, 0.062109, 0.060795
+5, 0.059852, 0.059078
+6, 0.059096, 0.058652
+7, 0.058634, 0.058505
+8, 0.058904, 0.058879
+9, 0.058865, 0.058817
+10, 0.058145, 0.058074
+11, 0.057094, 0.057320
+12, 0.056686, 0.057000
+13, 0.056440, 0.056806
+14, 0.056780, 0.056969
+15, 0.057121, 0.057249
+16, 0.057089, 0.057170
+17, 0.056695, 0.056844
+18, 0.056033, 0.056204
+19, 0.055199, 0.055399
+20, 0.054661, 0.054834
+21, 0.054271, 0.054396
+22, 0.054036, 0.054124
+23, 0.054021, 0.054075
+24, 0.053884, 0.054009
+25, 0.053809, 0.053988
+26, 0.053688, 0.053978
+27, 0.053466, 0.053863
+28, 0.053356, 0.053755
+29, 0.053260, 0.053652
+30, 0.053242, 0.053502
+31, 0.053209, 0.053376
+32, 0.053310, 0.053301
+33, 0.053360, 0.053194
+34, 0.053411, 0.053129
+35, 0.053490, 0.053088
+36, 0.053329, 0.052931
+37, 0.053057, 0.052750
+38, 0.052699, 0.052533
+39, 0.052314, 0.052344
+40, 0.052103, 0.052243
+41, 0.051960, 0.052185
+42, 0.051858, 0.052141
+43, 0.051790, 0.052123
+44, 0.051754, 0.052102
+45, 0.051746, 0.052096
+46, 0.051733, 0.052079
+47, 0.051714, 0.052058
+48, 0.051704, 0.052038
+49, 0.051654, 0.052020
+50, 0.051591, 0.051994
+51, 0.051546, 0.051980

julia/logs/log_27_09_2019.log

@@ -0,0 +1,572 @@
+
+--------[27_09_2019 16:51:25]--------
+second stage Hyperparameter Tuning with 1 net
+
+Configuration learning_rate=0.03, decay_step=20
+[16:52:47] INIT Loss(val): 0.148451 Accuarcy: 0.112245
+[16:54:51] Epoch   1: Loss(train): 0.089663 Loss(val): 0.088737
+[16:55:10] Epoch   2: Loss(train): 0.070667 Loss(val): 0.068928
+[16:55:27] Epoch   3: Loss(train): 0.063542 Loss(val): 0.062128
+[16:55:43] Epoch   4: Loss(train): 0.060417 Loss(val): 0.059723
+[16:56:01] Epoch   5: Loss(train): 0.059493 Loss(val): 0.059026
+[16:56:19] Epoch   6: Loss(train): 0.058942 Loss(val): 0.058448
+[16:56:36] Epoch   7: Loss(train): 0.058415 Loss(val): 0.057891
+[16:56:56] Epoch   8: Loss(train): 0.057964 Loss(val): 0.057296
+[16:57:13] Epoch   9: Loss(train): 0.057504 Loss(val): 0.056888
+[16:57:31] Epoch  10: Loss(train): 0.056998 Loss(val): 0.056621
+[16:57:48] Epoch  11: Loss(train): 0.056863 Loss(val): 0.056618
+[16:58:07] Epoch  12: Loss(train): 0.056772 Loss(val): 0.056483
+[16:58:23] Epoch  13: Loss(train): 0.056706 Loss(val): 0.056282
+[16:58:39] Epoch  14: Loss(train): 0.056430 Loss(val): 0.055929
+[16:58:55] Epoch  15: Loss(train): 0.056260 Loss(val): 0.055614
+[16:59:12] Epoch  16: Loss(train): 0.055839 Loss(val): 0.055432
+[16:59:30] Epoch  17: Loss(train): 0.055648 Loss(val): 0.055394
+[16:59:54] Epoch  18: Loss(train): 0.055889 Loss(val): 0.055650
+[17:00:12] Epoch  19: Loss(train): 0.056102 Loss(val): 0.055804
+[17:00:28] Epoch  20: Loss(train): 0.055990 Loss(val): 0.055733
+[17:00:45] Epoch  21: Loss(train): 0.056002 Loss(val): 0.055650
+[17:01:01] Epoch  22: Loss(train): 0.055604 Loss(val): 0.055251
+[17:01:18] Epoch  23: Loss(train): 0.054814 Loss(val): 0.054507
+[17:01:35] Epoch  24: Loss(train): 0.054289 Loss(val): 0.053961
+[17:01:59] Epoch  25: Loss(train): 0.054040 Loss(val): 0.053693
+[17:02:16] Epoch  26: Loss(train): 0.054076 Loss(val): 0.053621
+[17:02:32] Epoch  27: Loss(train): 0.054120 Loss(val): 0.053601
+[17:02:49] Epoch  28: Loss(train): 0.054555 Loss(val): 0.053849
+[17:03:06] Epoch  29: Loss(train): 0.055195 Loss(val): 0.054283
+[17:03:24] Epoch  30: Loss(train): 0.055647 Loss(val): 0.054590
+[17:03:41] Epoch  31: Loss(train): 0.055832 Loss(val): 0.054655
+[17:03:58] Epoch  32: Loss(train): 0.055375 Loss(val): 0.054319
+[17:04:16] Epoch  33: Loss(train): 0.054487 Loss(val): 0.053729
+[17:04:33] Epoch  34: Loss(train): 0.053432 Loss(val): 0.053076
+[17:04:50] Epoch  35: Loss(train): 0.052729 Loss(val): 0.052693
+[17:05:08] Epoch  36: Loss(train): 0.052390 Loss(val): 0.052524
+[17:05:25] Epoch  37: Loss(train): 0.052178 Loss(val): 0.052437
+[17:05:43] Epoch  38: Loss(train): 0.052099 Loss(val): 0.052385
+[17:06:00] Epoch  39: Loss(train): 0.052070 Loss(val): 0.052320
+[17:06:17] Epoch  40: Loss(train): 0.052017 Loss(val): 0.052243
+[17:06:35] Epoch  41: Loss(train): 0.051925 Loss(val): 0.052159
+[17:06:52] Epoch  42: Loss(train): 0.051824 Loss(val): 0.052056
+[17:07:10] Epoch  43: Loss(train): 0.051765 Loss(val): 0.051970
+[17:07:27] Epoch  44: Loss(train): 0.051683 Loss(val): 0.051933
+[17:07:45] Epoch  45: Loss(train): 0.051606 Loss(val): 0.051889
+[17:08:01] Epoch  46: Loss(train): 0.051533 Loss(val): 0.051864
+[17:08:18] Epoch  47: Loss(train): 0.051464 Loss(val): 0.051846
+[17:08:35] Epoch  48: Loss(train): 0.051401 Loss(val): 0.051838
+[17:08:52] Epoch  49: Loss(train): 0.051325 Loss(val): 0.051843
+[17:09:09] Epoch  50: Loss(train): 0.051266 Loss(val): 0.051860
+[17:09:26] Epoch  51: Loss(train): 0.051222 Loss(val): 0.051899
+[17:09:43] Epoch  52: Loss(train): 0.051193 Loss(val): 0.051918
+[17:10:01] Epoch  53: Loss(train): 0.051176 Loss(val): 0.051968
+[17:10:18] Epoch  54: Loss(train): 0.051162 Loss(val): 0.052006
+[17:10:35] Epoch  55: Loss(train): 0.051134 Loss(val): 0.051998
+[17:10:52] Epoch  56: Loss(train): 0.051111 Loss(val): 0.051992
+[17:11:10] Epoch  57: Loss(train): 0.051075 Loss(val): 0.051958
+[17:11:28] Epoch  58: Loss(train): 0.051050 Loss(val): 0.051941
+[17:11:45] Epoch  59: Loss(train): 0.051010 Loss(val): 0.051883
+[17:12:03] Epoch  60: Loss(train): 0.050980 Loss(val): 0.051837
+[17:12:20] Epoch  61: Loss(train): 0.050952 Loss(val): 0.051785
+[17:12:37] Epoch  62: Loss(train): 0.050934 Loss(val): 0.051770
+[17:12:55] Epoch  63: Loss(train): 0.050916 Loss(val): 0.051740
+[17:13:12] Epoch  64: Loss(train): 0.050899 Loss(val): 0.051707
+[17:13:29] Epoch  65: Loss(train): 0.050887 Loss(val): 0.051699
+[17:13:48] Epoch  66: Loss(train): 0.050875 Loss(val): 0.051674
+[17:14:05] Epoch  67: Loss(train): 0.050866 Loss(val): 0.051669
+[17:14:22] Epoch  68: Loss(train): 0.050856 Loss(val): 0.051652
+[17:14:40] Epoch  69: Loss(train): 0.050847 Loss(val): 0.051641
+[17:14:57] Epoch  70: Loss(train): 0.050839 Loss(val): 0.051635
+Converged at Loss(train): 0.051801, Loss(val): 0.052561 in epoch 70 with accuracy(val): 0.654473
+
+Configuration learning_rate=0.03, decay_step=40
+[17:15:12] INIT Loss(val): 0.149915 Accuarcy: 0.098707
+[17:15:33] Epoch   1: Loss(train): 0.088789 Loss(val): 0.087691
+[17:15:50] Epoch   2: Loss(train): 0.068032 Loss(val): 0.067004
+[17:16:08] Epoch   3: Loss(train): 0.063522 Loss(val): 0.062396
+[17:16:26] Epoch   4: Loss(train): 0.061677 Loss(val): 0.060596
+[17:16:43] Epoch   5: Loss(train): 0.060235 Loss(val): 0.059540
+[17:17:01] Epoch   6: Loss(train): 0.060055 Loss(val): 0.059479
+[17:17:18] Epoch   7: Loss(train): 0.059696 Loss(val): 0.058983
+[17:17:36] Epoch   8: Loss(train): 0.058420 Loss(val): 0.057931
+[17:17:53] Epoch   9: Loss(train): 0.057890 Loss(val): 0.057784
+[17:18:11] Epoch  10: Loss(train): 0.057887 Loss(val): 0.057939
+[17:18:28] Epoch  11: Loss(train): 0.058021 Loss(val): 0.058248
+[17:18:45] Epoch  12: Loss(train): 0.057937 Loss(val): 0.058021
+[17:19:03] Epoch  13: Loss(train): 0.057402 Loss(val): 0.057456
+[17:19:20] Epoch  14: Loss(train): 0.056914 Loss(val): 0.057007
+[17:19:37] Epoch  15: Loss(train): 0.056709 Loss(val): 0.056965
+[17:19:55] Epoch  16: Loss(train): 0.056852 Loss(val): 0.057157
+[17:20:13] Epoch  17: Loss(train): 0.057367 Loss(val): 0.057542
+[17:20:31] Epoch  18: Loss(train): 0.057601 Loss(val): 0.057665
+[17:20:49] Epoch  19: Loss(train): 0.057731 Loss(val): 0.057718
+[17:21:07] Epoch  20: Loss(train): 0.057218 Loss(val): 0.057077
+[17:21:24] Epoch  21: Loss(train): 0.056135 Loss(val): 0.056025
+[17:21:43] Epoch  22: Loss(train): 0.055024 Loss(val): 0.054987
+[17:22:00] Epoch  23: Loss(train): 0.054295 Loss(val): 0.054281
+[17:22:18] Epoch  24: Loss(train): 0.053959 Loss(val): 0.053951
+[17:22:36] Epoch  25: Loss(train): 0.053691 Loss(val): 0.053717
+[17:22:53] Epoch  26: Loss(train): 0.053627 Loss(val): 0.053622
+[17:23:11] Epoch  27: Loss(train): 0.053773 Loss(val): 0.053724
+[17:23:29] Epoch  28: Loss(train): 0.054236 Loss(val): 0.053973
+[17:23:47] Epoch  29: Loss(train): 0.054522 Loss(val): 0.054070
+[17:24:04] Epoch  30: Loss(train): 0.054943 Loss(val): 0.054246
+[17:24:22] Epoch  31: Loss(train): 0.055004 Loss(val): 0.054189
+[17:24:40] Epoch  32: Loss(train): 0.054876 Loss(val): 0.053994
+[17:24:57] Epoch  33: Loss(train): 0.054486 Loss(val): 0.053667
+[17:25:15] Epoch  34: Loss(train): 0.053800 Loss(val): 0.053187
+[17:25:33] Epoch  35: Loss(train): 0.053172 Loss(val): 0.052797
+[17:25:51] Epoch  36: Loss(train): 0.052741 Loss(val): 0.052563
+[17:26:09] Epoch  37: Loss(train): 0.052461 Loss(val): 0.052420
+[17:26:27] Epoch  38: Loss(train): 0.052257 Loss(val): 0.052302
+[17:26:46] Epoch  39: Loss(train): 0.052129 Loss(val): 0.052214
+[17:27:14] Epoch  40: Loss(train): 0.052035 Loss(val): 0.052163
+[17:27:44] Epoch  41: Loss(train): 0.051944 Loss(val): 0.052115
+[17:28:14] Epoch  42: Loss(train): 0.051880 Loss(val): 0.052084
+[17:28:31] Epoch  43: Loss(train): 0.051804 Loss(val): 0.052055
+[17:28:51] Epoch  44: Loss(train): 0.051738 Loss(val): 0.052032
+[17:29:18] Epoch  45: Loss(train): 0.051650 Loss(val): 0.052006
+[17:29:47] Epoch  46: Loss(train): 0.051562 Loss(val): 0.051986
+[17:30:09] Epoch  47: Loss(train): 0.051479 Loss(val): 0.051978
+[17:30:29] Epoch  48: Loss(train): 0.051412 Loss(val): 0.051979
+[17:30:54] Epoch  49: Loss(train): 0.051361 Loss(val): 0.051999
+[17:31:19] Epoch  50: Loss(train): 0.051323 Loss(val): 0.052038
+[17:31:38] Epoch  51: Loss(train): 0.051302 Loss(val): 0.052081
+[17:31:56] Epoch  52: Loss(train): 0.051278 Loss(val): 0.052096
+[17:32:15] Epoch  53: Loss(train): 0.051261 Loss(val): 0.052118
+[17:32:46] Epoch  54: Loss(train): 0.051239 Loss(val): 0.052120
+[17:33:13] Epoch  55: Loss(train): 0.051207 Loss(val): 0.052095
+Converged at Loss(train): 0.052161, Loss(val): 0.053005 in epoch 55 with accuracy(val): 0.645272
+
+Configuration learning_rate=0.03, decay_step=60
+[17:33:32] INIT Loss(val): 0.165520 Accuarcy: 0.073197
+[17:33:53] Epoch   1: Loss(train): 0.090615 Loss(val): 0.089994
+[17:34:11] Epoch   2: Loss(train): 0.069812 Loss(val): 0.068600
+[17:34:30] Epoch   3: Loss(train): 0.064214 Loss(val): 0.063470
+[17:34:49] Epoch   4: Loss(train): 0.061411 Loss(val): 0.061059
+[17:35:10] Epoch   5: Loss(train): 0.060100 Loss(val): 0.059814
+[17:35:31] Epoch   6: Loss(train): 0.059087 Loss(val): 0.059043
+[17:35:52] Epoch   7: Loss(train): 0.058686 Loss(val): 0.058661
+[17:36:10] Epoch   8: Loss(train): 0.058388 Loss(val): 0.058214
+[17:36:30] Epoch   9: Loss(train): 0.058066 Loss(val): 0.057698
+[17:36:51] Epoch  10: Loss(train): 0.057511 Loss(val): 0.057332
+[17:37:16] Epoch  11: Loss(train): 0.057068 Loss(val): 0.057097
+[17:37:35] Epoch  12: Loss(train): 0.057114 Loss(val): 0.057160
+[17:37:55] Epoch  13: Loss(train): 0.056885 Loss(val): 0.056944
+[17:38:15] Epoch  14: Loss(train): 0.056694 Loss(val): 0.056566
+[17:38:35] Epoch  15: Loss(train): 0.056233 Loss(val): 0.056134
+[17:38:55] Epoch  16: Loss(train): 0.055359 Loss(val): 0.055511
+[17:39:15] Epoch  17: Loss(train): 0.055256 Loss(val): 0.055431
+[17:39:35] Epoch  18: Loss(train): 0.055643 Loss(val): 0.055726
+[17:39:54] Epoch  19: Loss(train): 0.056205 Loss(val): 0.056171
+[17:40:14] Epoch  20: Loss(train): 0.056926 Loss(val): 0.056773
+[17:40:34] Epoch  21: Loss(train): 0.057006 Loss(val): 0.056768
+[17:40:53] Epoch  22: Loss(train): 0.056528 Loss(val): 0.056344
+[17:41:12] Epoch  23: Loss(train): 0.055433 Loss(val): 0.055290
+[17:41:31] Epoch  24: Loss(train): 0.054533 Loss(val): 0.054371
+[17:41:50] Epoch  25: Loss(train): 0.054282 Loss(val): 0.054007
+[17:42:10] Epoch  26: Loss(train): 0.054135 Loss(val): 0.053829
+[17:42:29] Epoch  27: Loss(train): 0.054173 Loss(val): 0.053806
+[17:42:48] Epoch  28: Loss(train): 0.054269 Loss(val): 0.053833
+[17:43:07] Epoch  29: Loss(train): 0.054556 Loss(val): 0.054030
+[17:43:27] Epoch  30: Loss(train): 0.054662 Loss(val): 0.054104
+[17:43:47] Epoch  31: Loss(train): 0.054619 Loss(val): 0.054089
+[17:44:06] Epoch  32: Loss(train): 0.054174 Loss(val): 0.053796
+[17:44:25] Epoch  33: Loss(train): 0.053649 Loss(val): 0.053463
+[17:44:44] Epoch  34: Loss(train): 0.052997 Loss(val): 0.053043
+[17:45:03] Epoch  35: Loss(train): 0.052595 Loss(val): 0.052792
+[17:45:22] Epoch  36: Loss(train): 0.052346 Loss(val): 0.052621
+[17:45:41] Epoch  37: Loss(train): 0.052151 Loss(val): 0.052500
+[17:46:00] Epoch  38: Loss(train): 0.052059 Loss(val): 0.052406
+[17:46:19] Epoch  39: Loss(train): 0.052001 Loss(val): 0.052335
+[17:46:38] Epoch  40: Loss(train): 0.051941 Loss(val): 0.052277
+[17:46:57] Epoch  41: Loss(train): 0.051894 Loss(val): 0.052226
+[17:47:17] Epoch  42: Loss(train): 0.051868 Loss(val): 0.052181
+[17:47:36] Epoch  43: Loss(train): 0.051789 Loss(val): 0.052130
+[17:47:55] Epoch  44: Loss(train): 0.051722 Loss(val): 0.052078
+[17:48:13] Epoch  45: Loss(train): 0.051639 Loss(val): 0.052052
+[17:48:33] Epoch  46: Loss(train): 0.051541 Loss(val): 0.052007
+[17:48:52] Epoch  47: Loss(train): 0.051465 Loss(val): 0.052000
+[17:49:12] Epoch  48: Loss(train): 0.051404 Loss(val): 0.051979
+[17:49:31] Epoch  49: Loss(train): 0.051339 Loss(val): 0.051980
+[17:49:51] Epoch  50: Loss(train): 0.051292 Loss(val): 0.051991
+[17:50:11] Epoch  51: Loss(train): 0.051249 Loss(val): 0.051991
+[17:50:30] Epoch  52: Loss(train): 0.051222 Loss(val): 0.052008
+[17:50:50] Epoch  53: Loss(train): 0.051198 Loss(val): 0.052018
+[17:51:09] Epoch  54: Loss(train): 0.051173 Loss(val): 0.052017
+[17:51:29] Epoch  55: Loss(train): 0.051146 Loss(val): 0.052003
+[17:51:48] Epoch  56: Loss(train): 0.051118 Loss(val): 0.051979
+[17:52:08] Epoch  57: Loss(train): 0.051087 Loss(val): 0.051948
+[17:52:27] Epoch  58: Loss(train): 0.051059 Loss(val): 0.051916
+[17:52:48] Epoch  59: Loss(train): 0.051032 Loss(val): 0.051880
+[17:53:08] Epoch  60: Loss(train): 0.051009 Loss(val): 0.051852
+Converged at Loss(train): 0.051977, Loss(val): 0.052759 in epoch 60 with accuracy(val): 0.642109
+
+Configuration learning_rate=0.01, decay_step=20
+[17:53:25] INIT Loss(val): 0.187323 Accuarcy: 0.077789
+[17:53:47] Epoch   1: Loss(train): 0.087576 Loss(val): 0.086033
+[17:54:07] Epoch   2: Loss(train): 0.068133 Loss(val): 0.066643
+[17:54:26] Epoch   3: Loss(train): 0.062122 Loss(val): 0.060931
+[17:54:46] Epoch   4: Loss(train): 0.058892 Loss(val): 0.058234
+[17:55:05] Epoch   5: Loss(train): 0.057786 Loss(val): 0.057269
+[17:55:24] Epoch   6: Loss(train): 0.057601 Loss(val): 0.057197
+[17:55:44] Epoch   7: Loss(train): 0.056949 Loss(val): 0.056568
+[17:56:03] Epoch   8: Loss(train): 0.056481 Loss(val): 0.056139
+[17:56:23] Epoch   9: Loss(train): 0.056194 Loss(val): 0.055886
+[17:56:43] Epoch  10: Loss(train): 0.055974 Loss(val): 0.055750
+[17:57:03] Epoch  11: Loss(train): 0.055800 Loss(val): 0.055777
+[17:57:22] Epoch  12: Loss(train): 0.055692 Loss(val): 0.055731
+[17:57:42] Epoch  13: Loss(train): 0.055691 Loss(val): 0.055779
+[17:58:02] Epoch  14: Loss(train): 0.055478 Loss(val): 0.055565
+[17:58:22] Epoch  15: Loss(train): 0.055101 Loss(val): 0.055146
+[17:58:42] Epoch  16: Loss(train): 0.054910 Loss(val): 0.054922
+[17:59:01] Epoch  17: Loss(train): 0.054790 Loss(val): 0.054875
+[17:59:21] Epoch  18: Loss(train): 0.054960 Loss(val): 0.055119
+[17:59:41] Epoch  19: Loss(train): 0.055063 Loss(val): 0.055270
+[18:00:02] Epoch  20: Loss(train): 0.054944 Loss(val): 0.055221
+[18:00:23] Epoch  21: Loss(train): 0.054798 Loss(val): 0.055048
+[18:00:44] Epoch  22: Loss(train): 0.054379 Loss(val): 0.054582
+[18:01:05] Epoch  23: Loss(train): 0.053794 Loss(val): 0.053956
+[18:01:31] Epoch  24: Loss(train): 0.053113 Loss(val): 0.053302
+[18:01:56] Epoch  25: Loss(train): 0.052780 Loss(val): 0.052874
+[18:02:22] Epoch  26: Loss(train): 0.052543 Loss(val): 0.052660
+[18:02:56] Epoch  27: Loss(train): 0.052278 Loss(val): 0.052454
+[18:03:31] Epoch  28: Loss(train): 0.052146 Loss(val): 0.052352
+[18:03:55] Epoch  29: Loss(train): 0.052045 Loss(val): 0.052292
+[18:04:17] Epoch  30: Loss(train): 0.051909 Loss(val): 0.052243
+[18:04:38] Epoch  31: Loss(train): 0.051838 Loss(val): 0.052235
+[18:05:01] Epoch  32: Loss(train): 0.051793 Loss(val): 0.052183
+[18:05:34] Epoch  33: Loss(train): 0.051737 Loss(val): 0.052164
+[18:06:03] Epoch  34: Loss(train): 0.051672 Loss(val): 0.052101
+[18:06:27] Epoch  35: Loss(train): 0.051629 Loss(val): 0.052036
+[18:07:02] Epoch  36: Loss(train): 0.051564 Loss(val): 0.051960
+[18:07:36] Epoch  37: Loss(train): 0.051538 Loss(val): 0.051894
+[18:08:09] Epoch  38: Loss(train): 0.051462 Loss(val): 0.051794
+[18:08:38] Epoch  39: Loss(train): 0.051404 Loss(val): 0.051718
+[18:09:02] Epoch  40: Loss(train): 0.051335 Loss(val): 0.051661
+[18:09:22] Epoch  41: Loss(train): 0.051274 Loss(val): 0.051597
+[18:09:44] Epoch  42: Loss(train): 0.051173 Loss(val): 0.051555
+[18:10:09] Epoch  43: Loss(train): 0.051112 Loss(val): 0.051520
+[18:10:30] Epoch  44: Loss(train): 0.051043 Loss(val): 0.051497
+[18:10:52] Epoch  45: Loss(train): 0.050990 Loss(val): 0.051464
+[18:11:13] Epoch  46: Loss(train): 0.050939 Loss(val): 0.051442
+[18:11:34] Epoch  47: Loss(train): 0.050889 Loss(val): 0.051419
+[18:11:55] Epoch  48: Loss(train): 0.050855 Loss(val): 0.051395
+[18:12:22] Epoch  49: Loss(train): 0.050825 Loss(val): 0.051377
+[18:12:44] Epoch  50: Loss(train): 0.050809 Loss(val): 0.051350
+[18:13:13] Epoch  51: Loss(train): 0.050787 Loss(val): 0.051347
+[18:13:35] Epoch  52: Loss(train): 0.050774 Loss(val): 0.051326
+[18:13:57] Epoch  53: Loss(train): 0.050761 Loss(val): 0.051317
+[18:14:18] Epoch  54: Loss(train): 0.050748 Loss(val): 0.051308
+[18:14:40] Epoch  55: Loss(train): 0.050737 Loss(val): 0.051294
+Converged at Loss(train): 0.051697, Loss(val): 0.052241 in epoch 55 with accuracy(val): 0.656922
+
+Configuration learning_rate=0.01, decay_step=40
+[18:15:00] INIT Loss(val): 0.177921 Accuarcy: 0.078452
+[18:15:25] Epoch   1: Loss(train): 0.085913 Loss(val): 0.084972
+[18:15:47] Epoch   2: Loss(train): 0.067994 Loss(val): 0.067212
+[18:16:08] Epoch   3: Loss(train): 0.064593 Loss(val): 0.063531
+[18:16:29] Epoch   4: Loss(train): 0.062117 Loss(val): 0.061084
+[18:16:49] Epoch   5: Loss(train): 0.060363 Loss(val): 0.060003
+[18:17:10] Epoch   6: Loss(train): 0.059131 Loss(val): 0.058921
+[18:17:31] Epoch   7: Loss(train): 0.058338 Loss(val): 0.058271
+[18:17:52] Epoch   8: Loss(train): 0.057717 Loss(val): 0.057788
+[18:18:15] Epoch   9: Loss(train): 0.057529 Loss(val): 0.057686
+[18:18:35] Epoch  10: Loss(train): 0.057496 Loss(val): 0.057720
+[18:18:56] Epoch  11: Loss(train): 0.057429 Loss(val): 0.057801
+[18:19:17] Epoch  12: Loss(train): 0.057253 Loss(val): 0.057779
+[18:19:40] Epoch  13: Loss(train): 0.056893 Loss(val): 0.057320
+[18:20:02] Epoch  14: Loss(train): 0.056243 Loss(val): 0.056562
+[18:20:22] Epoch  15: Loss(train): 0.056184 Loss(val): 0.056340
+[18:20:45] Epoch  16: Loss(train): 0.056221 Loss(val): 0.056419
+[18:21:06] Epoch  17: Loss(train): 0.056585 Loss(val): 0.056762
+[18:21:28] Epoch  18: Loss(train): 0.056598 Loss(val): 0.056918
+[18:21:49] Epoch  19: Loss(train): 0.056542 Loss(val): 0.056837
+[18:22:10] Epoch  20: Loss(train): 0.056023 Loss(val): 0.056362
+[18:22:34] Epoch  21: Loss(train): 0.055122 Loss(val): 0.055430
+[18:22:55] Epoch  22: Loss(train): 0.054322 Loss(val): 0.054565
+[18:23:15] Epoch  23: Loss(train): 0.053714 Loss(val): 0.053932
+[18:24:01] Epoch  24: Loss(train): 0.053428 Loss(val): 0.053591
+[18:24:44] Epoch  25: Loss(train): 0.053074 Loss(val): 0.053378
+[18:25:28] Epoch  26: Loss(train): 0.052950 Loss(val): 0.053381
+[18:26:12] Epoch  27: Loss(train): 0.052878 Loss(val): 0.053369
+[18:26:55] Epoch  28: Loss(train): 0.052749 Loss(val): 0.053334
+[18:27:39] Epoch  29: Loss(train): 0.052654 Loss(val): 0.053279
+[18:28:23] Epoch  30: Loss(train): 0.052551 Loss(val): 0.053160
+[18:29:07] Epoch  31: Loss(train): 0.052434 Loss(val): 0.052998
+[18:29:51] Epoch  32: Loss(train): 0.052321 Loss(val): 0.052879
+[18:30:34] Epoch  33: Loss(train): 0.052148 Loss(val): 0.052693
+[18:31:20] Epoch  34: Loss(train): 0.052083 Loss(val): 0.052561
+[18:32:09] Epoch  35: Loss(train): 0.051987 Loss(val): 0.052415
+[18:33:10] Epoch  36: Loss(train): 0.051942 Loss(val): 0.052319
+[18:34:01] Epoch  37: Loss(train): 0.051942 Loss(val): 0.052249
+[18:35:10] Epoch  38: Loss(train): 0.051861 Loss(val): 0.052164
+[18:36:23] Epoch  39: Loss(train): 0.051847 Loss(val): 0.052113
+[18:37:32] Epoch  40: Loss(train): 0.051747 Loss(val): 0.052048
+[18:38:32] Epoch  41: Loss(train): 0.051614 Loss(val): 0.051969
+[18:39:30] Epoch  42: Loss(train): 0.051501 Loss(val): 0.051891
+[18:40:41] Epoch  43: Loss(train): 0.051425 Loss(val): 0.051849
+[18:41:25] Epoch  44: Loss(train): 0.051336 Loss(val): 0.051807
+[18:42:13] Epoch  45: Loss(train): 0.051292 Loss(val): 0.051769
+[18:43:09] Epoch  46: Loss(train): 0.051229 Loss(val): 0.051732
+[18:43:55] Epoch  47: Loss(train): 0.051206 Loss(val): 0.051705
+[18:44:47] Epoch  48: Loss(train): 0.051182 Loss(val): 0.051671
+[18:45:34] Epoch  49: Loss(train): 0.051149 Loss(val): 0.051648
+[18:46:25] Epoch  50: Loss(train): 0.051119 Loss(val): 0.051630
+[18:47:15] Epoch  51: Loss(train): 0.051105 Loss(val): 0.051612
+[18:48:02] Epoch  52: Loss(train): 0.051082 Loss(val): 0.051598
+[18:48:48] Epoch  53: Loss(train): 0.051052 Loss(val): 0.051591
+[18:49:37] Epoch  54: Loss(train): 0.051018 Loss(val): 0.051580
+Converged at Loss(train): 0.051932, Loss(val): 0.052555 in epoch 54 with accuracy(val): 0.645799
+
+Configuration learning_rate=0.01, decay_step=60
+[18:50:03] INIT Loss(val): 0.131412 Accuarcy: 0.101854
+[18:50:48] Epoch   1: Loss(train): 0.080744 Loss(val): 0.079622
+[18:51:38] Epoch   2: Loss(train): 0.066512 Loss(val): 0.064695
+[18:52:26] Epoch   3: Loss(train): 0.062622 Loss(val): 0.061448
+[18:53:13] Epoch   4: Loss(train): 0.060374 Loss(val): 0.059260
+[18:54:00] Epoch   5: Loss(train): 0.058809 Loss(val): 0.058090
+[18:54:47] Epoch   6: Loss(train): 0.057931 Loss(val): 0.057646
+[18:55:35] Epoch   7: Loss(train): 0.057441 Loss(val): 0.057309
+[18:56:22] Epoch   8: Loss(train): 0.057106 Loss(val): 0.056946
+[18:57:08] Epoch   9: Loss(train): 0.056751 Loss(val): 0.056449
+[18:57:55] Epoch  10: Loss(train): 0.056720 Loss(val): 0.056406
+[18:58:42] Epoch  11: Loss(train): 0.056405 Loss(val): 0.056351
+[18:59:30] Epoch  12: Loss(train): 0.056383 Loss(val): 0.056457
+[19:00:17] Epoch  13: Loss(train): 0.056200 Loss(val): 0.056471
+[19:01:04] Epoch  14: Loss(train): 0.055845 Loss(val): 0.056025
+[19:01:52] Epoch  15: Loss(train): 0.055829 Loss(val): 0.055832
+[19:02:39] Epoch  16: Loss(train): 0.055686 Loss(val): 0.055626
+[19:03:25] Epoch  17: Loss(train): 0.055622 Loss(val): 0.055737
+[19:04:14] Epoch  18: Loss(train): 0.055771 Loss(val): 0.055958
+[19:05:05] Epoch  19: Loss(train): 0.055711 Loss(val): 0.056073
+[19:06:15] Epoch  20: Loss(train): 0.055973 Loss(val): 0.056337
+[19:07:04] Epoch  21: Loss(train): 0.055825 Loss(val): 0.056190
+[19:07:52] Epoch  22: Loss(train): 0.055313 Loss(val): 0.055599
+[19:08:41] Epoch  23: Loss(train): 0.054893 Loss(val): 0.055099
+[19:09:42] Epoch  24: Loss(train): 0.054391 Loss(val): 0.054471
+[19:10:44] Epoch  25: Loss(train): 0.053839 Loss(val): 0.053866
+[19:11:36] Epoch  26: Loss(train): 0.053508 Loss(val): 0.053500
+[19:12:40] Epoch  27: Loss(train): 0.053171 Loss(val): 0.053214
+[19:13:37] Epoch  28: Loss(train): 0.052970 Loss(val): 0.053028
+[19:14:26] Epoch  29: Loss(train): 0.052803 Loss(val): 0.052932
+[19:15:16] Epoch  30: Loss(train): 0.052774 Loss(val): 0.052891
+[19:16:07] Epoch  31: Loss(train): 0.052981 Loss(val): 0.052950
+[19:17:00] Epoch  32: Loss(train): 0.053209 Loss(val): 0.053051
+[19:18:01] Epoch  33: Loss(train): 0.053366 Loss(val): 0.053110
+[19:19:03] Epoch  34: Loss(train): 0.053671 Loss(val): 0.053226
+[19:19:51] Epoch  35: Loss(train): 0.053941 Loss(val): 0.053339
+[19:20:42] Epoch  36: Loss(train): 0.053890 Loss(val): 0.053279
+[19:21:33] Epoch  37: Loss(train): 0.053691 Loss(val): 0.053105
+[19:22:22] Epoch  38: Loss(train): 0.053180 Loss(val): 0.052768
+[19:23:23] Epoch  39: Loss(train): 0.052641 Loss(val): 0.052439
+[19:24:15] Epoch  40: Loss(train): 0.052294 Loss(val): 0.052223
+[19:25:05] Epoch  41: Loss(train): 0.052021 Loss(val): 0.052078
+[19:25:57] Epoch  42: Loss(train): 0.051852 Loss(val): 0.051986
+[19:26:46] Epoch  43: Loss(train): 0.051764 Loss(val): 0.051918
+[19:27:36] Epoch  44: Loss(train): 0.051702 Loss(val): 0.051857
+[19:28:29] Epoch  45: Loss(train): 0.051609 Loss(val): 0.051782
+[19:29:18] Epoch  46: Loss(train): 0.051520 Loss(val): 0.051719
+[19:30:08] Epoch  47: Loss(train): 0.051464 Loss(val): 0.051675
+[19:30:57] Epoch  48: Loss(train): 0.051390 Loss(val): 0.051640
+[19:31:47] Epoch  49: Loss(train): 0.051337 Loss(val): 0.051621
+[19:32:37] Epoch  50: Loss(train): 0.051246 Loss(val): 0.051601
+[19:33:26] Epoch  51: Loss(train): 0.051194 Loss(val): 0.051589
+[19:34:16] Epoch  52: Loss(train): 0.051123 Loss(val): 0.051589
+[19:35:06] Epoch  53: Loss(train): 0.051061 Loss(val): 0.051593
+[19:35:56] Epoch  54: Loss(train): 0.051009 Loss(val): 0.051610
+[19:37:03] Epoch  55: Loss(train): 0.050970 Loss(val): 0.051631
+[19:38:13] Epoch  56: Loss(train): 0.050941 Loss(val): 0.051682
+[19:39:31] Epoch  57: Loss(train): 0.050926 Loss(val): 0.051712
+[19:40:44] Epoch  58: Loss(train): 0.050924 Loss(val): 0.051774
+[19:41:48] Epoch  59: Loss(train): 0.050913 Loss(val): 0.051794
+[19:42:38] Epoch  60: Loss(train): 0.050901 Loss(val): 0.051803
+[19:43:59] Epoch  61: Loss(train): 0.050880 Loss(val): 0.051795
+[19:45:01] Epoch  62: Loss(train): 0.050853 Loss(val): 0.051767
+[19:46:02] Epoch  63: Loss(train): 0.050823 Loss(val): 0.051729
+Converged at Loss(train): 0.051745, Loss(val): 0.052544 in epoch 63 with accuracy(val): 0.647007
+
+Configuration learning_rate=0.003, decay_step=20
+[19:46:27] INIT Loss(val): 0.197653 Accuarcy: 0.091241
+[19:47:20] Epoch   1: Loss(train): 0.079464 Loss(val): 0.077783
+[19:48:20] Epoch   2: Loss(train): 0.067149 Loss(val): 0.066139
+[19:49:25] Epoch   3: Loss(train): 0.062640 Loss(val): 0.061764
+[19:50:18] Epoch   4: Loss(train): 0.060908 Loss(val): 0.059928
+[19:51:14] Epoch   5: Loss(train): 0.058845 Loss(val): 0.058380
+[19:52:13] Epoch   6: Loss(train): 0.058177 Loss(val): 0.057776
+[19:53:06] Epoch   7: Loss(train): 0.057540 Loss(val): 0.057122
+[19:53:59] Epoch   8: Loss(train): 0.056814 Loss(val): 0.056477
+[19:54:56] Epoch   9: Loss(train): 0.056360 Loss(val): 0.056050
+[19:55:52] Epoch  10: Loss(train): 0.056028 Loss(val): 0.055813
+[19:56:48] Epoch  11: Loss(train): 0.055597 Loss(val): 0.055646
+[19:57:44] Epoch  12: Loss(train): 0.055225 Loss(val): 0.055342
+[19:58:37] Epoch  13: Loss(train): 0.055302 Loss(val): 0.055394
+[19:59:31] Epoch  14: Loss(train): 0.055238 Loss(val): 0.055283
+[20:00:26] Epoch  15: Loss(train): 0.055095 Loss(val): 0.055047
+[20:01:19] Epoch  16: Loss(train): 0.054809 Loss(val): 0.054673
+[20:02:12] Epoch  17: Loss(train): 0.054337 Loss(val): 0.054301
+[20:03:06] Epoch  18: Loss(train): 0.053958 Loss(val): 0.054079
+[20:03:59] Epoch  19: Loss(train): 0.053873 Loss(val): 0.054106
+[20:04:51] Epoch  20: Loss(train): 0.054026 Loss(val): 0.054221
+[20:05:45] Epoch  21: Loss(train): 0.054201 Loss(val): 0.054455
+[20:06:38] Epoch  22: Loss(train): 0.054305 Loss(val): 0.054560
+[20:07:32] Epoch  23: Loss(train): 0.054394 Loss(val): 0.054562
+[20:08:25] Epoch  24: Loss(train): 0.054172 Loss(val): 0.054326
+[20:09:19] Epoch  25: Loss(train): 0.053743 Loss(val): 0.053848
+[20:10:12] Epoch  26: Loss(train): 0.053142 Loss(val): 0.053302
+[20:11:06] Epoch  27: Loss(train): 0.052741 Loss(val): 0.052896
+[20:11:59] Epoch  28: Loss(train): 0.052561 Loss(val): 0.052737
+[20:13:15] Epoch  29: Loss(train): 0.052489 Loss(val): 0.052637
+[20:14:12] Epoch  30: Loss(train): 0.052407 Loss(val): 0.052581
+[20:15:14] Epoch  31: Loss(train): 0.052487 Loss(val): 0.052619
+[20:16:17] Epoch  32: Loss(train): 0.052642 Loss(val): 0.052717
+[20:17:31] Epoch  33: Loss(train): 0.052745 Loss(val): 0.052786
+[20:18:41] Epoch  34: Loss(train): 0.052957 Loss(val): 0.052931
+[20:19:53] Epoch  35: Loss(train): 0.053042 Loss(val): 0.052976
+[20:20:52] Epoch  36: Loss(train): 0.053068 Loss(val): 0.052970
+[20:21:49] Epoch  37: Loss(train): 0.052881 Loss(val): 0.052853
+[20:22:59] Epoch  38: Loss(train): 0.052606 Loss(val): 0.052675
+[20:24:06] Epoch  39: Loss(train): 0.052210 Loss(val): 0.052439
+[20:25:05] Epoch  40: Loss(train): 0.051897 Loss(val): 0.052271
+[20:26:08] Epoch  41: Loss(train): 0.051670 Loss(val): 0.052125
+[20:27:04] Epoch  42: Loss(train): 0.051492 Loss(val): 0.052033
+[20:28:03] Epoch  43: Loss(train): 0.051401 Loss(val): 0.051973
+[20:28:59] Epoch  44: Loss(train): 0.051340 Loss(val): 0.051914
+[20:30:00] Epoch  45: Loss(train): 0.051286 Loss(val): 0.051879
+[20:31:02] Epoch  46: Loss(train): 0.051234 Loss(val): 0.051821
+[20:31:59] Epoch  47: Loss(train): 0.051182 Loss(val): 0.051773
+[20:32:55] Epoch  48: Loss(train): 0.051136 Loss(val): 0.051725
+[20:33:51] Epoch  49: Loss(train): 0.051084 Loss(val): 0.051684
+[20:34:47] Epoch  50: Loss(train): 0.051037 Loss(val): 0.051649
+[20:35:43] Epoch  51: Loss(train): 0.050997 Loss(val): 0.051624
+[20:36:43] Epoch  52: Loss(train): 0.050962 Loss(val): 0.051611
+[20:37:39] Epoch  53: Loss(train): 0.050926 Loss(val): 0.051608
+[20:38:34] Epoch  54: Loss(train): 0.050892 Loss(val): 0.051609
+[20:39:31] Epoch  55: Loss(train): 0.050861 Loss(val): 0.051612
+[20:40:26] Epoch  56: Loss(train): 0.050835 Loss(val): 0.051619
+[20:41:23] Epoch  57: Loss(train): 0.050810 Loss(val): 0.051647
+[20:42:18] Epoch  58: Loss(train): 0.050793 Loss(val): 0.051664
+[20:43:13] Epoch  59: Loss(train): 0.050780 Loss(val): 0.051697
+[20:44:09] Epoch  60: Loss(train): 0.050769 Loss(val): 0.051714
+[20:45:06] Epoch  61: Loss(train): 0.050759 Loss(val): 0.051723
+[20:46:02] Epoch  62: Loss(train): 0.050747 Loss(val): 0.051723
+[20:47:04] Epoch  63: Loss(train): 0.050739 Loss(val): 0.051730
+[20:48:21] Epoch  64: Loss(train): 0.050730 Loss(val): 0.051738
+[20:49:22] Epoch  65: Loss(train): 0.050708 Loss(val): 0.051697
+Converged at Loss(train): 0.051663, Loss(val): 0.052587 in epoch 65 with accuracy(val): 0.643129
+
+Configuration learning_rate=0.003, decay_step=40
+[20:49:52] INIT Loss(val): 0.131267 Accuarcy: 0.083214
+[20:50:53] Epoch   1: Loss(train): 0.085294 Loss(val): 0.084576
+[20:52:03] Epoch   2: Loss(train): 0.067979 Loss(val): 0.066454
+[20:53:25] Epoch   3: Loss(train): 0.064692 Loss(val): 0.063468
+[20:54:50] Epoch   4: Loss(train): 0.060204 Loss(val): 0.059563
+[20:55:54] Epoch   5: Loss(train): 0.059113 Loss(val): 0.058688
+[20:56:51] Epoch   6: Loss(train): 0.058466 Loss(val): 0.058163
+[20:57:49] Epoch   7: Loss(train): 0.058073 Loss(val): 0.057866
+[20:58:55] Epoch   8: Loss(train): 0.057293 Loss(val): 0.057096
+[20:59:57] Epoch   9: Loss(train): 0.056591 Loss(val): 0.056324
+[21:01:01] Epoch  10: Loss(train): 0.056213 Loss(val): 0.056077
+[21:02:04] Epoch  11: Loss(train): 0.055718 Loss(val): 0.055704
+[21:03:08] Epoch  12: Loss(train): 0.055250 Loss(val): 0.055418
+[21:04:14] Epoch  13: Loss(train): 0.055137 Loss(val): 0.055309
+[21:05:16] Epoch  14: Loss(train): 0.055121 Loss(val): 0.055232
+[21:06:19] Epoch  15: Loss(train): 0.055151 Loss(val): 0.055145
+[21:07:20] Epoch  16: Loss(train): 0.055220 Loss(val): 0.055140
+[21:08:20] Epoch  17: Loss(train): 0.054638 Loss(val): 0.054753
+[21:09:19] Epoch  18: Loss(train): 0.054304 Loss(val): 0.054612
+[21:10:20] Epoch  19: Loss(train): 0.054102 Loss(val): 0.054496
+[21:11:21] Epoch  20: Loss(train): 0.054121 Loss(val): 0.054624
+[21:12:20] Epoch  21: Loss(train): 0.054457 Loss(val): 0.054914
+[21:13:20] Epoch  22: Loss(train): 0.054731 Loss(val): 0.055191
+[21:14:20] Epoch  23: Loss(train): 0.054807 Loss(val): 0.055170
+[21:15:19] Epoch  24: Loss(train): 0.054750 Loss(val): 0.055053
+[21:16:20] Epoch  25: Loss(train): 0.054323 Loss(val): 0.054540
+[21:17:19] Epoch  26: Loss(train): 0.053600 Loss(val): 0.053798
+[21:18:17] Epoch  27: Loss(train): 0.053148 Loss(val): 0.053314
+[21:19:16] Epoch  28: Loss(train): 0.052852 Loss(val): 0.053044
+[21:20:15] Epoch  29: Loss(train): 0.052607 Loss(val): 0.052848
+[21:21:39] Epoch  30: Loss(train): 0.052449 Loss(val): 0.052746
+[21:23:03] Epoch  31: Loss(train): 0.052500 Loss(val): 0.052788
+[21:24:22] Epoch  32: Loss(train): 0.052512 Loss(val): 0.052785
+[21:25:49] Epoch  33: Loss(train): 0.052571 Loss(val): 0.052789
+[21:26:54] Epoch  34: Loss(train): 0.052684 Loss(val): 0.052806
+[21:28:20] Epoch  35: Loss(train): 0.052755 Loss(val): 0.052841
+[21:29:30] Epoch  36: Loss(train): 0.052775 Loss(val): 0.052819
+[21:30:48] Epoch  37: Loss(train): 0.052677 Loss(val): 0.052722
+[21:32:02] Epoch  38: Loss(train): 0.052491 Loss(val): 0.052566
+[21:33:11] Epoch  39: Loss(train): 0.052202 Loss(val): 0.052362
+[21:34:15] Epoch  40: Loss(train): 0.051935 Loss(val): 0.052191
+[21:35:18] Epoch  41: Loss(train): 0.051739 Loss(val): 0.052059
+[21:36:22] Epoch  42: Loss(train): 0.051572 Loss(val): 0.051957
+[21:37:25] Epoch  43: Loss(train): 0.051486 Loss(val): 0.051892
+[21:38:29] Epoch  44: Loss(train): 0.051410 Loss(val): 0.051844
+[21:39:35] Epoch  45: Loss(train): 0.051352 Loss(val): 0.051801
+[21:40:38] Epoch  46: Loss(train): 0.051312 Loss(val): 0.051755
+[21:41:45] Epoch  47: Loss(train): 0.051259 Loss(val): 0.051708
+[21:42:48] Epoch  48: Loss(train): 0.051191 Loss(val): 0.051682
+[21:43:52] Epoch  49: Loss(train): 0.051153 Loss(val): 0.051656
+[21:44:55] Epoch  50: Loss(train): 0.051126 Loss(val): 0.051639
+[21:45:56] Epoch  51: Loss(train): 0.051106 Loss(val): 0.051628
+[21:46:59] Epoch  52: Loss(train): 0.051067 Loss(val): 0.051622
+[21:48:02] Epoch  53: Loss(train): 0.051033 Loss(val): 0.051616
+[21:49:05] Epoch  54: Loss(train): 0.051009 Loss(val): 0.051614
+[21:50:07] Epoch  55: Loss(train): 0.050979 Loss(val): 0.051613
+[21:51:08] Epoch  56: Loss(train): 0.050938 Loss(val): 0.051623
+[21:52:11] Epoch  57: Loss(train): 0.050908 Loss(val): 0.051627
+[21:53:14] Epoch  58: Loss(train): 0.050878 Loss(val): 0.051646
+[21:54:23] Epoch  59: Loss(train): 0.050853 Loss(val): 0.051660
+[21:55:29] Epoch  60: Loss(train): 0.050829 Loss(val): 0.051672
+Converged at Loss(train): 0.051769, Loss(val): 0.052593 in epoch 60 with accuracy(val): 0.647092
+
+Configuration learning_rate=0.003, decay_step=60
+[21:56:01] INIT Loss(val): 0.128400 Accuarcy: 0.091173
+[21:57:04] Epoch   1: Loss(train): 0.087630 Loss(val): 0.086648
+[21:58:09] Epoch   2: Loss(train): 0.068650 Loss(val): 0.067234
+[21:59:13] Epoch   3: Loss(train): 0.064484 Loss(val): 0.062984
+[22:00:15] Epoch   4: Loss(train): 0.062109 Loss(val): 0.060795
+[22:01:20] Epoch   5: Loss(train): 0.059852 Loss(val): 0.059078
+[22:02:26] Epoch   6: Loss(train): 0.059096 Loss(val): 0.058652
+[22:03:28] Epoch   7: Loss(train): 0.058634 Loss(val): 0.058505
+[22:04:30] Epoch   8: Loss(train): 0.058904 Loss(val): 0.058879
+[22:05:33] Epoch   9: Loss(train): 0.058865 Loss(val): 0.058817
+[22:06:40] Epoch  10: Loss(train): 0.058145 Loss(val): 0.058074
+[22:07:45] Epoch  11: Loss(train): 0.057094 Loss(val): 0.057320
+[22:08:57] Epoch  12: Loss(train): 0.056686 Loss(val): 0.057000
+[22:10:03] Epoch  13: Loss(train): 0.056440 Loss(val): 0.056806
+[22:11:07] Epoch  14: Loss(train): 0.056780 Loss(val): 0.056969
+[22:12:15] Epoch  15: Loss(train): 0.057121 Loss(val): 0.057249
+[22:13:19] Epoch  16: Loss(train): 0.057089 Loss(val): 0.057170
+[22:14:23] Epoch  17: Loss(train): 0.056695 Loss(val): 0.056844
+[22:15:28] Epoch  18: Loss(train): 0.056033 Loss(val): 0.056204
+[22:16:41] Epoch  19: Loss(train): 0.055199 Loss(val): 0.055399
+[22:17:51] Epoch  20: Loss(train): 0.054661 Loss(val): 0.054834
+[22:18:59] Epoch  21: Loss(train): 0.054271 Loss(val): 0.054396
+[22:20:05] Epoch  22: Loss(train): 0.054036 Loss(val): 0.054124
+[22:21:12] Epoch  23: Loss(train): 0.054021 Loss(val): 0.054075
+[22:22:18] Epoch  24: Loss(train): 0.053884 Loss(val): 0.054009
+[22:23:23] Epoch  25: Loss(train): 0.053809 Loss(val): 0.053988
+[22:24:28] Epoch  26: Loss(train): 0.053688 Loss(val): 0.053978
+[22:25:32] Epoch  27: Loss(train): 0.053466 Loss(val): 0.053863
+[22:26:35] Epoch  28: Loss(train): 0.053356 Loss(val): 0.053755
+[22:27:42] Epoch  29: Loss(train): 0.053260 Loss(val): 0.053652
+[22:28:47] Epoch  30: Loss(train): 0.053242 Loss(val): 0.053502
+[22:29:52] Epoch  31: Loss(train): 0.053209 Loss(val): 0.053376
+[22:30:55] Epoch  32: Loss(train): 0.053310 Loss(val): 0.053301
+[22:32:02] Epoch  33: Loss(train): 0.053360 Loss(val): 0.053194
+[22:33:11] Epoch  34: Loss(train): 0.053411 Loss(val): 0.053129
+[22:34:18] Epoch  35: Loss(train): 0.053490 Loss(val): 0.053088
+[22:35:25] Epoch  36: Loss(train): 0.053329 Loss(val): 0.052931
+[22:36:35] Epoch  37: Loss(train): 0.053057 Loss(val): 0.052750
+[22:37:46] Epoch  38: Loss(train): 0.052699 Loss(val): 0.052533
+[22:38:57] Epoch  39: Loss(train): 0.052314 Loss(val): 0.052344
+[22:40:06] Epoch  40: Loss(train): 0.052103 Loss(val): 0.052243
+[22:41:26] Epoch  41: Loss(train): 0.051960 Loss(val): 0.052185
+[22:42:35] Epoch  42: Loss(train): 0.051858 Loss(val): 0.052141
+[22:43:43] Epoch  43: Loss(train): 0.051790 Loss(val): 0.052123
+[22:44:48] Epoch  44: Loss(train): 0.051754 Loss(val): 0.052102
+[22:45:55] Epoch  45: Loss(train): 0.051746 Loss(val): 0.052096
+[22:47:15] Epoch  46: Loss(train): 0.051733 Loss(val): 0.052079
+[22:48:27] Epoch  47: Loss(train): 0.051714 Loss(val): 0.052058
+[22:49:37] Epoch  48: Loss(train): 0.051704 Loss(val): 0.052038
+[22:50:50] Epoch  49: Loss(train): 0.051654 Loss(val): 0.052020
+[22:51:58] Epoch  50: Loss(train): 0.051591 Loss(val): 0.051994
+[22:53:08] Epoch  51: Loss(train): 0.051546 Loss(val): 0.051980
+Converged at Loss(train): 0.052474, Loss(val): 0.052877 in epoch 51 with accuracy(val): 0.638793

julia/logs/log_29_09_2019.log

@@ -0,0 +1,648 @@
+
+--------[29_09_2019 16:52:06]--------
+second stage Hyperparameter Tuning with 1 net
+
+Configuration learning_rate=0.3, decay_step=20
+[16:53:20] INIT Loss(val): 0.180713 Accuarcy: 0.083435
+[16:55:33] Epoch   1: Loss(train): 0.106532 Loss(val): 0.109270
+[16:56:20] Epoch   2: Loss(train): 0.095428 Loss(val): 0.097530
+[16:57:06] Epoch   3: Loss(train): 0.090024 Loss(val): 0.091654
+[16:57:52] Epoch   4: Loss(train): 0.086840 Loss(val): 0.088290
+[16:58:38] Epoch   5: Loss(train): 0.085175 Loss(val): 0.086443
+[16:59:24] Epoch   6: Loss(train): 0.084256 Loss(val): 0.085231
+[17:00:09] Epoch   7: Loss(train): 0.083388 Loss(val): 0.084379
+[17:00:54] Epoch   8: Loss(train): 0.082766 Loss(val): 0.083685
+[17:01:40] Epoch   9: Loss(train): 0.082271 Loss(val): 0.083217
+[17:02:25] Epoch  10: Loss(train): 0.081836 Loss(val): 0.082803
+[17:03:10] Epoch  11: Loss(train): 0.081547 Loss(val): 0.082447
+[17:03:56] Epoch  12: Loss(train): 0.081178 Loss(val): 0.082092
+[17:04:42] Epoch  13: Loss(train): 0.080869 Loss(val): 0.081751
+[17:05:27] Epoch  14: Loss(train): 0.080644 Loss(val): 0.081556
+[17:06:12] Epoch  15: Loss(train): 0.080391 Loss(val): 0.081279
+[17:06:57] Epoch  16: Loss(train): 0.080222 Loss(val): 0.081098
+[17:07:43] Epoch  17: Loss(train): 0.080038 Loss(val): 0.080880
+[17:08:28] Epoch  18: Loss(train): 0.079911 Loss(val): 0.080777
+[17:09:14] Epoch  19: Loss(train): 0.079714 Loss(val): 0.080606
+[17:09:59] Epoch  20: Loss(train): 0.079589 Loss(val): 0.080480
+[17:10:45] Epoch  21: Loss(train): 0.079406 Loss(val): 0.080328
+[17:11:31] Epoch  22: Loss(train): 0.079339 Loss(val): 0.080205
+[17:12:16] Epoch  23: Loss(train): 0.079207 Loss(val): 0.080088
+[17:13:02] Epoch  24: Loss(train): 0.079084 Loss(val): 0.079978
+[17:13:48] Epoch  25: Loss(train): 0.079040 Loss(val): 0.079932
+[17:14:35] Epoch  26: Loss(train): 0.078889 Loss(val): 0.079799
+[17:15:26] Epoch  27: Loss(train): 0.078822 Loss(val): 0.079725
+[17:16:19] Epoch  28: Loss(train): 0.078742 Loss(val): 0.079628
+[17:17:12] Epoch  29: Loss(train): 0.078611 Loss(val): 0.079555
+[17:18:01] Epoch  30: Loss(train): 0.078586 Loss(val): 0.079513
+[17:18:51] Epoch  31: Loss(train): 0.078523 Loss(val): 0.079450
+[17:19:43] Epoch  32: Loss(train): 0.078456 Loss(val): 0.079391
+[17:20:29] Epoch  33: Loss(train): 0.078401 Loss(val): 0.079339
+[17:21:16] Epoch  34: Loss(train): 0.078364 Loss(val): 0.079309
+[17:22:03] Epoch  35: Loss(train): 0.078296 Loss(val): 0.079267
+[17:22:49] Epoch  36: Loss(train): 0.078242 Loss(val): 0.079220
+[17:23:36] Epoch  37: Loss(train): 0.078217 Loss(val): 0.079206
+[17:24:27] Epoch  38: Loss(train): 0.078172 Loss(val): 0.079159
+[17:25:13] Epoch  39: Loss(train): 0.078125 Loss(val): 0.079112
+[17:25:59] Epoch  40: Loss(train): 0.078090 Loss(val): 0.079078
+[17:26:47] Epoch  41: Loss(train): 0.078064 Loss(val): 0.079061
+[17:27:34] Epoch  42: Loss(train): 0.078024 Loss(val): 0.079030
+[17:28:21] Epoch  43: Loss(train): 0.077999 Loss(val): 0.079014
+[17:29:07] Epoch  44: Loss(train): 0.077969 Loss(val): 0.079004
+[17:29:54] Epoch  45: Loss(train): 0.077942 Loss(val): 0.078974
+[17:30:40] Epoch  46: Loss(train): 0.077913 Loss(val): 0.078955
+[17:31:26] Epoch  47: Loss(train): 0.077897 Loss(val): 0.078943
+[17:32:14] Epoch  48: Loss(train): 0.077872 Loss(val): 0.078943
+[17:33:00] Epoch  49: Loss(train): 0.077860 Loss(val): 0.078925
+[17:33:46] Epoch  50: Loss(train): 0.077845 Loss(val): 0.078909
+Converged at Loss(train): 0.082486, Loss(val): 0.083474 in epoch 50 with accuracy(val): 0.445493
+
+Configuration learning_rate=0.3, decay_step=40
+[17:34:11] INIT Loss(val): 0.154576 Accuarcy: 0.089405
+[17:34:58] Epoch   1: Loss(train): 0.106738 Loss(val): 0.110443
+[17:35:46] Epoch   2: Loss(train): 0.094961 Loss(val): 0.097940
+[17:36:33] Epoch   3: Loss(train): 0.089637 Loss(val): 0.092018
+[17:37:20] Epoch   4: Loss(train): 0.086759 Loss(val): 0.088715
+[17:38:07] Epoch   5: Loss(train): 0.085159 Loss(val): 0.086774
+[17:38:54] Epoch   6: Loss(train): 0.084000 Loss(val): 0.085421
+[17:39:40] Epoch   7: Loss(train): 0.083180 Loss(val): 0.084470
+[17:40:26] Epoch   8: Loss(train): 0.082572 Loss(val): 0.083797
+[17:41:13] Epoch   9: Loss(train): 0.082123 Loss(val): 0.083295
+[17:41:59] Epoch  10: Loss(train): 0.081630 Loss(val): 0.082839
+[17:42:45] Epoch  11: Loss(train): 0.081291 Loss(val): 0.082452
+[17:43:32] Epoch  12: Loss(train): 0.080972 Loss(val): 0.082084
+[17:44:18] Epoch  13: Loss(train): 0.080653 Loss(val): 0.081747
+[17:45:04] Epoch  14: Loss(train): 0.080442 Loss(val): 0.081523
+[17:45:50] Epoch  15: Loss(train): 0.080123 Loss(val): 0.081291
+[17:46:37] Epoch  16: Loss(train): 0.079901 Loss(val): 0.081047
+[17:47:24] Epoch  17: Loss(train): 0.079744 Loss(val): 0.080816
+[17:48:12] Epoch  18: Loss(train): 0.079591 Loss(val): 0.080666
+[17:48:58] Epoch  19: Loss(train): 0.079401 Loss(val): 0.080512
+[17:49:45] Epoch  20: Loss(train): 0.079236 Loss(val): 0.080347
+[17:50:33] Epoch  21: Loss(train): 0.079109 Loss(val): 0.080221
+[17:51:24] Epoch  22: Loss(train): 0.078977 Loss(val): 0.080101
+[17:52:12] Epoch  23: Loss(train): 0.078854 Loss(val): 0.080001
+[17:52:59] Epoch  24: Loss(train): 0.078805 Loss(val): 0.079867
+[17:53:46] Epoch  25: Loss(train): 0.078686 Loss(val): 0.079800
+[17:54:36] Epoch  26: Loss(train): 0.078619 Loss(val): 0.079673
+[17:55:28] Epoch  27: Loss(train): 0.078528 Loss(val): 0.079612
+[17:56:15] Epoch  28: Loss(train): 0.078430 Loss(val): 0.079535
+[17:57:02] Epoch  29: Loss(train): 0.078359 Loss(val): 0.079456
+[17:57:50] Epoch  30: Loss(train): 0.078281 Loss(val): 0.079384
+[17:58:44] Epoch  31: Loss(train): 0.078242 Loss(val): 0.079335
+[17:59:33] Epoch  32: Loss(train): 0.078183 Loss(val): 0.079284
+[18:00:24] Epoch  33: Loss(train): 0.078123 Loss(val): 0.079225
+[18:01:13] Epoch  34: Loss(train): 0.078082 Loss(val): 0.079195
+[18:02:00] Epoch  35: Loss(train): 0.078023 Loss(val): 0.079155
+[18:02:49] Epoch  36: Loss(train): 0.077983 Loss(val): 0.079103
+[18:03:38] Epoch  37: Loss(train): 0.077936 Loss(val): 0.079066
+[18:04:26] Epoch  38: Loss(train): 0.077902 Loss(val): 0.079045
+[18:05:14] Epoch  39: Loss(train): 0.077875 Loss(val): 0.079019
+[18:06:03] Epoch  40: Loss(train): 0.077839 Loss(val): 0.078968
+[18:06:51] Epoch  41: Loss(train): 0.077803 Loss(val): 0.078962
+[18:07:39] Epoch  42: Loss(train): 0.077777 Loss(val): 0.078970
+[18:08:27] Epoch  43: Loss(train): 0.077755 Loss(val): 0.078905
+[18:09:15] Epoch  44: Loss(train): 0.077733 Loss(val): 0.078915
+[18:10:03] Epoch  45: Loss(train): 0.077713 Loss(val): 0.078907
+[18:10:52] Epoch  46: Loss(train): 0.077690 Loss(val): 0.078885
+[18:11:39] Epoch  47: Loss(train): 0.077666 Loss(val): 0.078863
+[18:12:27] Epoch  48: Loss(train): 0.077652 Loss(val): 0.078851
+[18:13:15] Epoch  49: Loss(train): 0.077632 Loss(val): 0.078827
+[18:14:03] Epoch  50: Loss(train): 0.077617 Loss(val): 0.078828
+[18:14:50] Epoch  51: Loss(train): 0.077603 Loss(val): 0.078800
+[18:15:38] Epoch  52: Loss(train): 0.077587 Loss(val): 0.078780
+[18:16:25] Epoch  53: Loss(train): 0.077573 Loss(val): 0.078771
+[18:17:13] Epoch  54: Loss(train): 0.077561 Loss(val): 0.078770
+[18:18:00] Epoch  55: Loss(train): 0.077551 Loss(val): 0.078766
+[18:18:48] Epoch  56: Loss(train): 0.077541 Loss(val): 0.078755
+[18:19:35] Epoch  57: Loss(train): 0.077533 Loss(val): 0.078769
+[18:20:22] Epoch  58: Loss(train): 0.077520 Loss(val): 0.078739
+[18:21:09] Epoch  59: Loss(train): 0.077514 Loss(val): 0.078746
+[18:21:57] Epoch  60: Loss(train): 0.077504 Loss(val): 0.078725
+[18:22:44] Epoch  61: Loss(train): 0.077499 Loss(val): 0.078735
+[18:23:32] Epoch  62: Loss(train): 0.077492 Loss(val): 0.078728
+[18:24:20] Epoch  63: Loss(train): 0.077485 Loss(val): 0.078724
+[18:25:08] Epoch  64: Loss(train): 0.077478 Loss(val): 0.078721
+[18:25:56] Epoch  65: Loss(train): 0.077468 Loss(val): 0.078695
+[18:26:45] Epoch  66: Loss(train): 0.077468 Loss(val): 0.078714
+[18:27:40] Epoch  67: Loss(train): 0.077462 Loss(val): 0.078705
+[18:28:28] Epoch  68: Loss(train): 0.077458 Loss(val): 0.078700
+[18:29:17] Epoch  69: Loss(train): 0.077453 Loss(val): 0.078694
+[18:30:11] Epoch  70: Loss(train): 0.077454 Loss(val): 0.078712
+[18:31:04] Epoch  71: Loss(train): 0.077449 Loss(val): 0.078707
+[18:32:01] Epoch  72: Loss(train): 0.077444 Loss(val): 0.078695
+[18:32:56] Epoch  73: Loss(train): 0.077440 Loss(val): 0.078689
+[18:33:45] Epoch  74: Loss(train): 0.077438 Loss(val): 0.078692
+[18:34:34] Epoch  75: Loss(train): 0.077435 Loss(val): 0.078691
+[18:35:26] Epoch  76: Loss(train): 0.077430 Loss(val): 0.078680
+[18:36:16] Epoch  77: Loss(train): 0.077427 Loss(val): 0.078679
+[18:37:05] Epoch  78: Loss(train): 0.077426 Loss(val): 0.078680
+[18:37:54] Epoch  79: Loss(train): 0.077424 Loss(val): 0.078680
+[18:38:48] Epoch  80: Loss(train): 0.077420 Loss(val): 0.078671
+[18:39:36] Epoch  81: Loss(train): 0.077419 Loss(val): 0.078675
+[18:40:28] Epoch  82: Loss(train): 0.077415 Loss(val): 0.078664
+[18:41:17] Epoch  83: Loss(train): 0.077414 Loss(val): 0.078668
+[18:42:06] Epoch  84: Loss(train): 0.077410 Loss(val): 0.078661
+[18:42:55] Epoch  85: Loss(train): 0.077410 Loss(val): 0.078663
+[18:43:45] Epoch  86: Loss(train): 0.077409 Loss(val): 0.078667
+[18:44:33] Epoch  87: Loss(train): 0.077407 Loss(val): 0.078664
+[18:45:23] Epoch  88: Loss(train): 0.077406 Loss(val): 0.078664
+[18:46:12] Epoch  89: Loss(train): 0.077404 Loss(val): 0.078660
+[18:47:02] Epoch  90: Loss(train): 0.077403 Loss(val): 0.078663
+[18:47:51] Epoch  91: Loss(train): 0.077401 Loss(val): 0.078657
+[18:48:41] Epoch  92: Loss(train): 0.077399 Loss(val): 0.078655
+[18:49:30] Epoch  93: Loss(train): 0.077399 Loss(val): 0.078657
+[18:50:19] Epoch  94: Loss(train): 0.077399 Loss(val): 0.078657
+[18:51:08] Epoch  95: Loss(train): 0.077398 Loss(val): 0.078657
+[18:51:57] Epoch  96: Loss(train): 0.077397 Loss(val): 0.078658
+[18:52:46] Epoch  97: Loss(train): 0.077397 Loss(val): 0.078657
+[18:53:36] Epoch  98: Loss(train): 0.077394 Loss(val): 0.078651
+[18:54:25] Epoch  99: Loss(train): 0.077394 Loss(val): 0.078652
+[18:55:14] Epoch 100: Loss(train): 0.077393 Loss(val): 0.078650
+[18:56:04] Epoch 101: Loss(train): 0.077392 Loss(val): 0.078649
+[18:56:53] Epoch 102: Loss(train): 0.077391 Loss(val): 0.078646
+[18:57:42] Epoch 103: Loss(train): 0.077390 Loss(val): 0.078645
+[18:58:32] Epoch 104: Loss(train): 0.077389 Loss(val): 0.078644
+[18:59:22] Epoch 105: Loss(train): 0.077389 Loss(val): 0.078644
+[19:00:12] Epoch 106: Loss(train): 0.077388 Loss(val): 0.078642
+[19:01:09] Epoch 107: Loss(train): 0.077388 Loss(val): 0.078642
+[19:01:59] Epoch 108: Loss(train): 0.077388 Loss(val): 0.078644
+[19:02:49] Epoch 109: Loss(train): 0.077387 Loss(val): 0.078643
+[19:03:39] Epoch 110: Loss(train): 0.077387 Loss(val): 0.078643
+[19:04:32] Epoch 111: Loss(train): 0.077386 Loss(val): 0.078641
+[19:05:30] Epoch 112: Loss(train): 0.077386 Loss(val): 0.078641
+[19:06:25] Epoch 113: Loss(train): 0.077386 Loss(val): 0.078642
+[19:07:16] Epoch 114: Loss(train): 0.077386 Loss(val): 0.078641
+[19:08:06] Epoch 115: Loss(train): 0.077385 Loss(val): 0.078641
+[19:08:55] Epoch 116: Loss(train): 0.077385 Loss(val): 0.078641
+[19:09:46] Epoch 117: Loss(train): 0.077385 Loss(val): 0.078641
+[19:10:37] Epoch 118: Loss(train): 0.077385 Loss(val): 0.078641
+[19:11:27] Epoch 119: Loss(train): 0.077385 Loss(val): 0.078642
+[19:12:21] Epoch 120: Loss(train): 0.077384 Loss(val): 0.078641
+[19:13:14] Epoch 121: Loss(train): 0.077384 Loss(val): 0.078641
+[19:14:03] Epoch 122: Loss(train): 0.077384 Loss(val): 0.078641
+[19:14:54] Epoch 123: Loss(train): 0.077384 Loss(val): 0.078641
+[19:15:46] Epoch 124: Loss(train): 0.077384 Loss(val): 0.078641
+[19:16:37] Epoch 125: Loss(train): 0.077384 Loss(val): 0.078640
+[19:17:28] Epoch 126: Loss(train): 0.077384 Loss(val): 0.078640
+[19:18:20] Epoch 127: Loss(train): 0.077384 Loss(val): 0.078641
+[19:19:11] Epoch 128: Loss(train): 0.077384 Loss(val): 0.078640
+[19:20:01] Epoch 129: Loss(train): 0.077383 Loss(val): 0.078640
+[19:20:52] Epoch 130: Loss(train): 0.077383 Loss(val): 0.078640
+[19:21:44] Epoch 131: Loss(train): 0.077383 Loss(val): 0.078639
+[19:22:36] Epoch 132: Loss(train): 0.077383 Loss(val): 0.078640
+[19:23:26] Epoch 133: Loss(train): 0.077383 Loss(val): 0.078640
+[19:24:17] Epoch 134: Loss(train): 0.077383 Loss(val): 0.078639
+[19:25:07] Epoch 135: Loss(train): 0.077383 Loss(val): 0.078639
+[19:25:58] Epoch 136: Loss(train): 0.077383 Loss(val): 0.078639
+[19:26:48] Epoch 137: Loss(train): 0.077383 Loss(val): 0.078639
+[19:27:40] Epoch 138: Loss(train): 0.077383 Loss(val): 0.078639
+[19:28:31] Epoch 139: Loss(train): 0.077383 Loss(val): 0.078639
+[19:29:22] Epoch 140: Loss(train): 0.077383 Loss(val): 0.078639
+[19:30:13] Epoch 141: Loss(train): 0.077383 Loss(val): 0.078639
+[19:31:04] Epoch 142: Loss(train): 0.077383 Loss(val): 0.078639
+[19:31:55] Epoch 143: Loss(train): 0.077383 Loss(val): 0.078639
+[19:32:46] Epoch 144: Loss(train): 0.077383 Loss(val): 0.078639
+[19:33:36] Epoch 145: Loss(train): 0.077383 Loss(val): 0.078639
+[19:34:26] Epoch 146: Loss(train): 0.077383 Loss(val): 0.078640
+[19:35:22] Epoch 147: Loss(train): 0.077383 Loss(val): 0.078639
+[19:36:17] Epoch 148: Loss(train): 0.077383 Loss(val): 0.078639
+[19:37:15] Epoch 149: Loss(train): 0.077383 Loss(val): 0.078639
+[19:38:16] Epoch 150: Loss(train): 0.077383 Loss(val): 0.078639
+[19:39:07] Epoch 151: Loss(train): 0.077383 Loss(val): 0.078639
+[19:39:59] Epoch 152: Loss(train): 0.077383 Loss(val): 0.078639
+[19:40:50] Epoch 153: Loss(train): 0.077383 Loss(val): 0.078639
+[19:41:45] Epoch 154: Loss(train): 0.077382 Loss(val): 0.078639
+[19:42:36] Epoch 155: Loss(train): 0.077382 Loss(val): 0.078639
+[19:43:33] Epoch 156: Loss(train): 0.077382 Loss(val): 0.078639
+[19:44:26] Epoch 157: Loss(train): 0.077382 Loss(val): 0.078639
+[19:45:19] Epoch 158: Loss(train): 0.077382 Loss(val): 0.078639
+[19:46:10] Epoch 159: Loss(train): 0.077382 Loss(val): 0.078639
+[19:47:03] Epoch 160: Loss(train): 0.077382 Loss(val): 0.078639
+[19:47:57] Epoch 161: Loss(train): 0.077382 Loss(val): 0.078639
+[19:48:48] Epoch 162: Loss(train): 0.077382 Loss(val): 0.078639
+[19:49:40] Epoch 163: Loss(train): 0.077382 Loss(val): 0.078639
+[19:50:32] Epoch 164: Loss(train): 0.077382 Loss(val): 0.078639
+[19:51:23] Epoch 165: Loss(train): 0.077382 Loss(val): 0.078639
+[19:52:18] Epoch 166: Loss(train): 0.077382 Loss(val): 0.078639
+[19:53:09] Epoch 167: Loss(train): 0.077382 Loss(val): 0.078639
+[19:54:00] Epoch 168: Loss(train): 0.077382 Loss(val): 0.078639
+[19:54:52] Epoch 169: Loss(train): 0.077382 Loss(val): 0.078639
+[19:55:44] Epoch 170: Loss(train): 0.077382 Loss(val): 0.078639
+[19:56:35] Epoch 171: Loss(train): 0.077382 Loss(val): 0.078639
+[19:57:27] Epoch 172: Loss(train): 0.077382 Loss(val): 0.078639
+[19:58:18] Epoch 173: Loss(train): 0.077382 Loss(val): 0.078639
+[19:59:09] Epoch 174: Loss(train): 0.077382 Loss(val): 0.078639
+[20:00:01] Epoch 175: Loss(train): 0.077382 Loss(val): 0.078639
+[20:00:54] Epoch 176: Loss(train): 0.077382 Loss(val): 0.078639
+[20:01:47] Epoch 177: Loss(train): 0.077382 Loss(val): 0.078639
+[20:02:39] Epoch 178: Loss(train): 0.077382 Loss(val): 0.078639
+[20:03:32] Epoch 179: Loss(train): 0.077382 Loss(val): 0.078639
+[20:04:24] Epoch 180: Loss(train): 0.077382 Loss(val): 0.078639
+[20:05:17] Epoch 181: Loss(train): 0.077382 Loss(val): 0.078639
+[20:06:10] Epoch 182: Loss(train): 0.077382 Loss(val): 0.078639
+[20:07:11] Epoch 183: Loss(train): 0.077382 Loss(val): 0.078639
+[20:08:09] Epoch 184: Loss(train): 0.077382 Loss(val): 0.078639
+[20:09:13] Epoch 185: Loss(train): 0.077382 Loss(val): 0.078639
+[20:10:11] Epoch 186: Loss(train): 0.077382 Loss(val): 0.078639
+[20:11:09] Epoch 187: Loss(train): 0.077382 Loss(val): 0.078639
+[20:12:05] Epoch 188: Loss(train): 0.077382 Loss(val): 0.078639
+[20:13:04] Epoch 189: Loss(train): 0.077382 Loss(val): 0.078639
+[20:14:00] Epoch 190: Loss(train): 0.077382 Loss(val): 0.078639
+[20:14:52] Epoch 191: Loss(train): 0.077382 Loss(val): 0.078639
+[20:15:49] Epoch 192: Loss(train): 0.077382 Loss(val): 0.078639
+[20:16:44] Epoch 193: Loss(train): 0.077382 Loss(val): 0.078639
+[20:17:37] Epoch 194: Loss(train): 0.077382 Loss(val): 0.078639
+[20:18:30] Epoch 195: Loss(train): 0.077382 Loss(val): 0.078639
+[20:19:27] Epoch 196: Loss(train): 0.077382 Loss(val): 0.078639
+[20:20:21] Epoch 197: Loss(train): 0.077382 Loss(val): 0.078639
+[20:21:13] Epoch 198: Loss(train): 0.077382 Loss(val): 0.078639
+[20:22:06] Epoch 199: Loss(train): 0.077382 Loss(val): 0.078639
+[20:23:01] Epoch 200: Loss(train): 0.077382 Loss(val): 0.078639
+[20:23:56] Epoch 201: Loss(train): 0.077382 Loss(val): 0.078639
+[20:24:49] Epoch 202: Loss(train): 0.077382 Loss(val): 0.078639
+[20:25:42] Epoch 203: Loss(train): 0.077382 Loss(val): 0.078639
+[20:26:36] Epoch 204: Loss(train): 0.077382 Loss(val): 0.078639
+[20:27:28] Epoch 205: Loss(train): 0.077382 Loss(val): 0.078639
+[20:28:22] Epoch 206: Loss(train): 0.077382 Loss(val): 0.078639
+[20:29:16] Epoch 207: Loss(train): 0.077382 Loss(val): 0.078639
+[20:30:10] Epoch 208: Loss(train): 0.077382 Loss(val): 0.078639
+[20:31:03] Epoch 209: Loss(train): 0.077382 Loss(val): 0.078639
+[20:31:55] Epoch 210: Loss(train): 0.077382 Loss(val): 0.078639
+[20:32:49] Epoch 211: Loss(train): 0.077382 Loss(val): 0.078639
+[20:33:42] Epoch 212: Loss(train): 0.077382 Loss(val): 0.078639
+[20:34:35] Epoch 213: Loss(train): 0.077382 Loss(val): 0.078639
+[20:35:28] Epoch 214: Loss(train): 0.077382 Loss(val): 0.078639
+[20:37:07] Epoch 215: Loss(train): 0.077382 Loss(val): 0.078639
+[20:39:39] Epoch 216: Loss(train): 0.077382 Loss(val): 0.078639
+[20:42:07] Epoch 217: Loss(train): 0.077382 Loss(val): 0.078639
+[20:44:41] Epoch 218: Loss(train): 0.077382 Loss(val): 0.078639
+[20:47:12] Epoch 219: Loss(train): 0.077382 Loss(val): 0.078639
+[20:49:23] Epoch 220: Loss(train): 0.077382 Loss(val): 0.078639
+[20:51:26] Epoch 221: Loss(train): 0.077382 Loss(val): 0.078639
+[20:53:30] Epoch 222: Loss(train): 0.077382 Loss(val): 0.078639
+[20:55:28] Epoch 223: Loss(train): 0.077382 Loss(val): 0.078639
+[20:57:30] Epoch 224: Loss(train): 0.077382 Loss(val): 0.078639
+[20:59:28] Epoch 225: Loss(train): 0.077382 Loss(val): 0.078639
+[21:01:23] Epoch 226: Loss(train): 0.077382 Loss(val): 0.078639
+[21:03:18] Epoch 227: Loss(train): 0.077382 Loss(val): 0.078639
+[21:05:13] Epoch 228: Loss(train): 0.077382 Loss(val): 0.078639
+[21:07:08] Epoch 229: Loss(train): 0.077382 Loss(val): 0.078639
+[21:09:06] Epoch 230: Loss(train): 0.077382 Loss(val): 0.078639
+[21:11:45] Epoch 231: Loss(train): 0.077382 Loss(val): 0.078639
+[21:14:17] Epoch 232: Loss(train): 0.077382 Loss(val): 0.078639
+[21:16:50] Epoch 233: Loss(train): 0.077382 Loss(val): 0.078639
+[21:18:55] Epoch 234: Loss(train): 0.077382 Loss(val): 0.078639
+[21:21:14] Epoch 235: Loss(train): 0.077382 Loss(val): 0.078639
+[21:23:20] Epoch 236: Loss(train): 0.077382 Loss(val): 0.078639
+[21:25:19] Epoch 237: Loss(train): 0.077382 Loss(val): 0.078639
+[21:27:31] Epoch 238: Loss(train): 0.077382 Loss(val): 0.078639
+[21:29:41] Epoch 239: Loss(train): 0.077382 Loss(val): 0.078639
+[21:31:41] Epoch 240: Loss(train): 0.077382 Loss(val): 0.078639
+[21:33:47] Epoch 241: Loss(train): 0.077382 Loss(val): 0.078639
+[21:35:49] Epoch 242: Loss(train): 0.077382 Loss(val): 0.078639
+[21:37:51] Epoch 243: Loss(train): 0.077382 Loss(val): 0.078639
+[21:39:51] Epoch 244: Loss(train): 0.077382 Loss(val): 0.078639
+[21:42:19] Epoch 245: Loss(train): 0.077382 Loss(val): 0.078639
+[21:44:40] Epoch 246: Loss(train): 0.077382 Loss(val): 0.078639
+[21:46:46] Epoch 247: Loss(train): 0.077382 Loss(val): 0.078639
+[21:49:01] Epoch 248: Loss(train): 0.077382 Loss(val): 0.078639
+[21:51:19] Epoch 249: Loss(train): 0.077382 Loss(val): 0.078639
+[21:53:26] Epoch 250: Loss(train): 0.077382 Loss(val): 0.078639
+[21:55:35] Epoch 251: Loss(train): 0.077382 Loss(val): 0.078639
+[21:57:42] Epoch 252: Loss(train): 0.077382 Loss(val): 0.078639
+[21:59:52] Epoch 253: Loss(train): 0.077382 Loss(val): 0.078639
+[22:01:59] Epoch 254: Loss(train): 0.077382 Loss(val): 0.078639
+[22:04:11] Epoch 255: Loss(train): 0.077382 Loss(val): 0.078639
+[22:06:13] Epoch 256: Loss(train): 0.077382 Loss(val): 0.078639
+[22:08:20] Epoch 257: Loss(train): 0.077382 Loss(val): 0.078639
+[22:10:22] Epoch 258: Loss(train): 0.077382 Loss(val): 0.078639
+[22:12:25] Epoch 259: Loss(train): 0.077382 Loss(val): 0.078639
+[22:14:28] Epoch 260: Loss(train): 0.077382 Loss(val): 0.078639
+[22:16:51] Epoch 261: Loss(train): 0.077382 Loss(val): 0.078639
+[22:19:19] Epoch 262: Loss(train): 0.077382 Loss(val): 0.078639
+[22:21:37] Epoch 263: Loss(train): 0.077382 Loss(val): 0.078639
+[22:24:16] Epoch 264: Loss(train): 0.077382 Loss(val): 0.078639
+[22:26:31] Epoch 265: Loss(train): 0.077382 Loss(val): 0.078639
+[22:28:42] Epoch 266: Loss(train): 0.077382 Loss(val): 0.078639
+[22:30:51] Epoch 267: Loss(train): 0.077382 Loss(val): 0.078639
+[22:33:05] Epoch 268: Loss(train): 0.077382 Loss(val): 0.078639
+[22:35:15] Epoch 269: Loss(train): 0.077382 Loss(val): 0.078639
+[22:37:29] Epoch 270: Loss(train): 0.077382 Loss(val): 0.078639
+[22:39:37] Epoch 271: Loss(train): 0.077382 Loss(val): 0.078639
+[22:41:48] Epoch 272: Loss(train): 0.077382 Loss(val): 0.078639
+[22:43:53] Epoch 273: Loss(train): 0.077382 Loss(val): 0.078639
+[22:45:58] Epoch 274: Loss(train): 0.077382 Loss(val): 0.078639
+[22:48:04] Epoch 275: Loss(train): 0.077382 Loss(val): 0.078639
+[22:50:17] Epoch 276: Loss(train): 0.077382 Loss(val): 0.078639
+[22:52:25] Epoch 277: Loss(train): 0.077382 Loss(val): 0.078639
+[22:54:34] Epoch 278: Loss(train): 0.077382 Loss(val): 0.078639
+[22:56:40] Epoch 279: Loss(train): 0.077382 Loss(val): 0.078639
+[22:58:46] Epoch 280: Loss(train): 0.077382 Loss(val): 0.078639
+[23:01:05] Epoch 281: Loss(train): 0.077382 Loss(val): 0.078639
+[23:03:23] Epoch 282: Loss(train): 0.077382 Loss(val): 0.078639
+Converged at Loss(train): 0.082034, Loss(val): 0.083194 in epoch 282 with accuracy(val): 0.458486
+
+Configuration learning_rate=0.3, decay_step=60
+[23:04:17] INIT Loss(val): 0.148113 Accuarcy: 0.088044
+[23:06:34] Epoch   1: Loss(train): 0.107054 Loss(val): 0.109363
+[23:08:56] Epoch   2: Loss(train): 0.095789 Loss(val): 0.097876
+[23:11:04] Epoch   3: Loss(train): 0.090508 Loss(val): 0.092148
+[23:13:35] Epoch   4: Loss(train): 0.087590 Loss(val): 0.088927
+[23:17:01] Epoch   5: Loss(train): 0.085521 Loss(val): 0.086741
+[23:20:12] Epoch   6: Loss(train): 0.084280 Loss(val): 0.085431
+[23:22:24] Epoch   7: Loss(train): 0.083406 Loss(val): 0.084504
+[23:24:58] Epoch   8: Loss(train): 0.082772 Loss(val): 0.083805
+[23:27:22] Epoch   9: Loss(train): 0.082204 Loss(val): 0.083247
+[23:29:41] Epoch  10: Loss(train): 0.081678 Loss(val): 0.082771
+[23:32:03] Epoch  11: Loss(train): 0.081268 Loss(val): 0.082301
+[23:34:12] Epoch  12: Loss(train): 0.080904 Loss(val): 0.081968
+[23:36:27] Epoch  13: Loss(train): 0.080724 Loss(val): 0.081766
+[23:38:41] Epoch  14: Loss(train): 0.080442 Loss(val): 0.081502
+[23:40:53] Epoch  15: Loss(train): 0.080174 Loss(val): 0.081228
+[23:43:06] Epoch  16: Loss(train): 0.079994 Loss(val): 0.081023
+[23:46:08] Epoch  17: Loss(train): 0.079753 Loss(val): 0.080801
+[23:48:40] Epoch  18: Loss(train): 0.079578 Loss(val): 0.080634
+[23:51:34] Epoch  19: Loss(train): 0.079432 Loss(val): 0.080512
+[23:54:06] Epoch  20: Loss(train): 0.079271 Loss(val): 0.080309
+[23:56:30] Epoch  21: Loss(train): 0.079122 Loss(val): 0.080194
+[23:58:59] Epoch  22: Loss(train): 0.079044 Loss(val): 0.080105
+[00:01:16] Epoch  23: Loss(train): 0.078923 Loss(val): 0.079973
+[00:03:34] Epoch  24: Loss(train): 0.078793 Loss(val): 0.079894
+[00:05:51] Epoch  25: Loss(train): 0.078695 Loss(val): 0.079780
+[00:08:07] Epoch  26: Loss(train): 0.078608 Loss(val): 0.079694
+[00:10:24] Epoch  27: Loss(train): 0.078494 Loss(val): 0.079601
+[00:12:39] Epoch  28: Loss(train): 0.078417 Loss(val): 0.079530
+[00:15:31] Epoch  29: Loss(train): 0.078361 Loss(val): 0.079450
+[00:18:25] Epoch  30: Loss(train): 0.078333 Loss(val): 0.079394
+[00:21:07] Epoch  31: Loss(train): 0.078235 Loss(val): 0.079327
+[00:24:01] Epoch  32: Loss(train): 0.078153 Loss(val): 0.079252
+[00:26:34] Epoch  33: Loss(train): 0.078107 Loss(val): 0.079232
+[00:29:00] Epoch  34: Loss(train): 0.078064 Loss(val): 0.079163
+[00:31:28] Epoch  35: Loss(train): 0.078004 Loss(val): 0.079139
+[00:33:49] Epoch  36: Loss(train): 0.077960 Loss(val): 0.079076
+[00:36:08] Epoch  37: Loss(train): 0.077932 Loss(val): 0.079059
+[00:38:29] Epoch  38: Loss(train): 0.077874 Loss(val): 0.079005
+[00:40:51] Epoch  39: Loss(train): 0.077841 Loss(val): 0.078978
+[00:43:11] Epoch  40: Loss(train): 0.077795 Loss(val): 0.078931
+[00:45:57] Epoch  41: Loss(train): 0.077764 Loss(val): 0.078925
+[00:49:17] Epoch  42: Loss(train): 0.077733 Loss(val): 0.078916
+[00:52:09] Epoch  43: Loss(train): 0.077707 Loss(val): 0.078873
+[00:54:39] Epoch  44: Loss(train): 0.077685 Loss(val): 0.078852
+[00:57:11] Epoch  45: Loss(train): 0.077660 Loss(val): 0.078848
+[00:59:43] Epoch  46: Loss(train): 0.077632 Loss(val): 0.078837
+[01:02:15] Epoch  47: Loss(train): 0.077619 Loss(val): 0.078815
+[01:04:43] Epoch  48: Loss(train): 0.077599 Loss(val): 0.078788
+[01:07:05] Epoch  49: Loss(train): 0.077581 Loss(val): 0.078782
+[01:09:26] Epoch  50: Loss(train): 0.077557 Loss(val): 0.078758
+[01:11:49] Epoch  51: Loss(train): 0.077544 Loss(val): 0.078751
+[01:14:11] Epoch  52: Loss(train): 0.077522 Loss(val): 0.078734
+[01:17:36] Epoch  53: Loss(train): 0.077510 Loss(val): 0.078726
+[01:20:53] Epoch  54: Loss(train): 0.077499 Loss(val): 0.078728
+[01:23:46] Epoch  55: Loss(train): 0.077487 Loss(val): 0.078702
+[01:26:28] Epoch  56: Loss(train): 0.077474 Loss(val): 0.078712
+[01:29:08] Epoch  57: Loss(train): 0.077465 Loss(val): 0.078715
+[01:31:37] Epoch  58: Loss(train): 0.077457 Loss(val): 0.078715
+[01:34:07] Epoch  59: Loss(train): 0.077445 Loss(val): 0.078696
+[01:36:30] Epoch  60: Loss(train): 0.077437 Loss(val): 0.078695
+[01:38:58] Epoch  61: Loss(train): 0.077429 Loss(val): 0.078679
+[01:41:20] Epoch  62: Loss(train): 0.077426 Loss(val): 0.078690
+[01:43:42] Epoch  63: Loss(train): 0.077418 Loss(val): 0.078677
+[01:46:26] Epoch  64: Loss(train): 0.077412 Loss(val): 0.078690
+[01:49:45] Epoch  65: Loss(train): 0.077403 Loss(val): 0.078668
+[01:52:30] Epoch  66: Loss(train): 0.077400 Loss(val): 0.078670
+[01:55:42] Epoch  67: Loss(train): 0.077396 Loss(val): 0.078664
+[01:58:18] Epoch  68: Loss(train): 0.077391 Loss(val): 0.078665
+[02:00:59] Epoch  69: Loss(train): 0.077385 Loss(val): 0.078659
+[02:03:31] Epoch  70: Loss(train): 0.077380 Loss(val): 0.078658
+[02:06:07] Epoch  71: Loss(train): 0.077376 Loss(val): 0.078658
+[02:08:35] Epoch  72: Loss(train): 0.077374 Loss(val): 0.078661
+[02:11:04] Epoch  73: Loss(train): 0.077371 Loss(val): 0.078655
+[02:13:32] Epoch  74: Loss(train): 0.077368 Loss(val): 0.078656
+[02:15:59] Epoch  75: Loss(train): 0.077364 Loss(val): 0.078651
+[02:18:26] Epoch  76: Loss(train): 0.077361 Loss(val): 0.078648
+[02:21:38] Epoch  77: Loss(train): 0.077359 Loss(val): 0.078647
+[02:24:25] Epoch  78: Loss(train): 0.077356 Loss(val): 0.078647
+[02:27:14] Epoch  79: Loss(train): 0.077351 Loss(val): 0.078638
+[02:30:05] Epoch  80: Loss(train): 0.077349 Loss(val): 0.078634
+[02:32:44] Epoch  81: Loss(train): 0.077346 Loss(val): 0.078634
+[02:35:28] Epoch  82: Loss(train): 0.077344 Loss(val): 0.078633
+[02:38:05] Epoch  83: Loss(train): 0.077345 Loss(val): 0.078639
+[02:40:38] Epoch  84: Loss(train): 0.077343 Loss(val): 0.078638
+[02:43:12] Epoch  85: Loss(train): 0.077342 Loss(val): 0.078642
+[02:45:45] Epoch  86: Loss(train): 0.077339 Loss(val): 0.078636
+[02:48:13] Epoch  87: Loss(train): 0.077338 Loss(val): 0.078637
+[02:50:41] Epoch  88: Loss(train): 0.077337 Loss(val): 0.078637
+[02:53:51] Epoch  89: Loss(train): 0.077335 Loss(val): 0.078632
+[02:56:53] Epoch  90: Loss(train): 0.077334 Loss(val): 0.078630
+[02:59:47] Epoch  91: Loss(train): 0.077332 Loss(val): 0.078628
+[03:02:24] Epoch  92: Loss(train): 0.077331 Loss(val): 0.078627
+[03:05:12] Epoch  93: Loss(train): 0.077330 Loss(val): 0.078627
+[03:07:58] Epoch  94: Loss(train): 0.077328 Loss(val): 0.078623
+[03:10:35] Epoch  95: Loss(train): 0.077327 Loss(val): 0.078619
+[03:13:15] Epoch  96: Loss(train): 0.077327 Loss(val): 0.078623
+[03:15:50] Epoch  97: Loss(train): 0.077327 Loss(val): 0.078625
+[03:18:21] Epoch  98: Loss(train): 0.077326 Loss(val): 0.078626
+[03:20:56] Epoch  99: Loss(train): 0.077326 Loss(val): 0.078625
+[03:23:41] Epoch 100: Loss(train): 0.077325 Loss(val): 0.078622
+[03:26:50] Epoch 101: Loss(train): 0.077324 Loss(val): 0.078623
+[03:30:06] Epoch 102: Loss(train): 0.077324 Loss(val): 0.078622
+[03:33:21] Epoch 103: Loss(train): 0.077323 Loss(val): 0.078622
+[03:36:06] Epoch 104: Loss(train): 0.077323 Loss(val): 0.078622
+[03:38:49] Epoch 105: Loss(train): 0.077322 Loss(val): 0.078622
+[03:41:29] Epoch 106: Loss(train): 0.077321 Loss(val): 0.078619
+[03:44:10] Epoch 107: Loss(train): 0.077320 Loss(val): 0.078616
+[03:46:47] Epoch 108: Loss(train): 0.077319 Loss(val): 0.078615
+[03:49:22] Epoch 109: Loss(train): 0.077319 Loss(val): 0.078616
+[03:51:55] Epoch 110: Loss(train): 0.077319 Loss(val): 0.078615
+[03:54:28] Epoch 111: Loss(train): 0.077318 Loss(val): 0.078614
+[03:57:08] Epoch 112: Loss(train): 0.077319 Loss(val): 0.078616
+[04:00:37] Epoch 113: Loss(train): 0.077318 Loss(val): 0.078615
+[04:03:24] Epoch 114: Loss(train): 0.077318 Loss(val): 0.078617
+[04:06:31] Epoch 115: Loss(train): 0.077319 Loss(val): 0.078618
+[04:09:20] Epoch 116: Loss(train): 0.077319 Loss(val): 0.078618
+[04:12:07] Epoch 117: Loss(train): 0.077318 Loss(val): 0.078617
+[04:14:48] Epoch 118: Loss(train): 0.077318 Loss(val): 0.078617
+[04:17:30] Epoch 119: Loss(train): 0.077318 Loss(val): 0.078617
+[04:20:10] Epoch 120: Loss(train): 0.077317 Loss(val): 0.078616
+[04:22:50] Epoch 121: Loss(train): 0.077317 Loss(val): 0.078617
+[04:25:30] Epoch 122: Loss(train): 0.077317 Loss(val): 0.078618
+[04:28:06] Epoch 123: Loss(train): 0.077318 Loss(val): 0.078618
+[04:30:57] Epoch 124: Loss(train): 0.077318 Loss(val): 0.078619
+[04:33:55] Epoch 125: Loss(train): 0.077317 Loss(val): 0.078619
+[04:36:46] Epoch 126: Loss(train): 0.077317 Loss(val): 0.078619
+[04:39:57] Epoch 127: Loss(train): 0.077317 Loss(val): 0.078618
+[04:42:50] Epoch 128: Loss(train): 0.077317 Loss(val): 0.078618
+[04:45:43] Epoch 129: Loss(train): 0.077317 Loss(val): 0.078618
+[04:48:25] Epoch 130: Loss(train): 0.077317 Loss(val): 0.078618
+[04:51:16] Epoch 131: Loss(train): 0.077317 Loss(val): 0.078618
+[04:53:57] Epoch 132: Loss(train): 0.077317 Loss(val): 0.078617
+[04:56:34] Epoch 133: Loss(train): 0.077317 Loss(val): 0.078617
+[04:59:17] Epoch 134: Loss(train): 0.077316 Loss(val): 0.078617
+[05:01:58] Epoch 135: Loss(train): 0.077316 Loss(val): 0.078617
+[05:05:03] Epoch 136: Loss(train): 0.077316 Loss(val): 0.078617
+[05:08:22] Epoch 137: Loss(train): 0.077316 Loss(val): 0.078616
+[05:11:24] Epoch 138: Loss(train): 0.077316 Loss(val): 0.078616
+[05:14:25] Epoch 139: Loss(train): 0.077316 Loss(val): 0.078616
+[05:17:22] Epoch 140: Loss(train): 0.077316 Loss(val): 0.078616
+[05:20:16] Epoch 141: Loss(train): 0.077316 Loss(val): 0.078616
+[05:23:04] Epoch 142: Loss(train): 0.077316 Loss(val): 0.078615
+[05:25:53] Epoch 143: Loss(train): 0.077316 Loss(val): 0.078615
+[05:28:38] Epoch 144: Loss(train): 0.077316 Loss(val): 0.078615
+[05:31:22] Epoch 145: Loss(train): 0.077316 Loss(val): 0.078615
+[05:34:02] Epoch 146: Loss(train): 0.077316 Loss(val): 0.078615
+[05:36:46] Epoch 147: Loss(train): 0.077316 Loss(val): 0.078615
+[05:40:11] Epoch 148: Loss(train): 0.077316 Loss(val): 0.078615
+[05:43:43] Epoch 149: Loss(train): 0.077316 Loss(val): 0.078615
+[05:46:56] Epoch 150: Loss(train): 0.077316 Loss(val): 0.078615
+[05:49:55] Epoch 151: Loss(train): 0.077315 Loss(val): 0.078615
+[05:52:53] Epoch 152: Loss(train): 0.077315 Loss(val): 0.078615
+[05:55:52] Epoch 153: Loss(train): 0.077315 Loss(val): 0.078615
+[05:58:45] Epoch 154: Loss(train): 0.077315 Loss(val): 0.078615
+[06:01:39] Epoch 155: Loss(train): 0.077315 Loss(val): 0.078615
+[06:04:25] Epoch 156: Loss(train): 0.077315 Loss(val): 0.078615
+[06:07:07] Epoch 157: Loss(train): 0.077315 Loss(val): 0.078615
+[06:09:52] Epoch 158: Loss(train): 0.077315 Loss(val): 0.078615
+[06:12:41] Epoch 159: Loss(train): 0.077315 Loss(val): 0.078615
+Converged at Loss(train): 0.081795, Loss(val): 0.082810 in epoch 159 with accuracy(val): 0.455119
+
+Configuration learning_rate=0.1, decay_step=20
+[06:14:12] INIT Loss(val): 0.151758 Accuarcy: 0.109337
+[06:17:00] Epoch   1: Loss(train): 0.108645 Loss(val): 0.110902
+[06:19:52] Epoch   2: Loss(train): 0.097215 Loss(val): 0.099030
+[06:22:40] Epoch   3: Loss(train): 0.091263 Loss(val): 0.092792
+[06:25:30] Epoch   4: Loss(train): 0.088060 Loss(val): 0.089313
+[06:28:30] Epoch   5: Loss(train): 0.086003 Loss(val): 0.087071
+[06:31:27] Epoch   6: Loss(train): 0.084676 Loss(val): 0.085638
+[06:34:27] Epoch   7: Loss(train): 0.083821 Loss(val): 0.084719
+[06:37:15] Epoch   8: Loss(train): 0.083102 Loss(val): 0.083924
+[06:40:03] Epoch   9: Loss(train): 0.082514 Loss(val): 0.083343
+[06:42:51] Epoch  10: Loss(train): 0.082124 Loss(val): 0.082861
+[06:45:39] Epoch  11: Loss(train): 0.081586 Loss(val): 0.082425
+[06:48:23] Epoch  12: Loss(train): 0.081260 Loss(val): 0.082115
+[06:51:13] Epoch  13: Loss(train): 0.080916 Loss(val): 0.081760
+[06:53:59] Epoch  14: Loss(train): 0.080611 Loss(val): 0.081422
+[06:56:45] Epoch  15: Loss(train): 0.080433 Loss(val): 0.081247
+[06:59:36] Epoch  16: Loss(train): 0.080208 Loss(val): 0.081032
+[07:02:22] Epoch  17: Loss(train): 0.080056 Loss(val): 0.080846
+[07:05:14] Epoch  18: Loss(train): 0.079824 Loss(val): 0.080675
+[07:08:09] Epoch  19: Loss(train): 0.079619 Loss(val): 0.080466
+[07:11:07] Epoch  20: Loss(train): 0.079563 Loss(val): 0.080365
+[07:14:22] Epoch  21: Loss(train): 0.079408 Loss(val): 0.080246
+[07:17:29] Epoch  22: Loss(train): 0.079267 Loss(val): 0.080076
+[07:22:07] Epoch  23: Loss(train): 0.079120 Loss(val): 0.079969
+[07:25:39] Epoch  24: Loss(train): 0.079023 Loss(val): 0.079840
+[07:28:35] Epoch  25: Loss(train): 0.078940 Loss(val): 0.079775
+[07:31:55] Epoch  26: Loss(train): 0.078815 Loss(val): 0.079648
+[07:35:01] Epoch  27: Loss(train): 0.078760 Loss(val): 0.079581
+[07:37:52] Epoch  28: Loss(train): 0.078676 Loss(val): 0.079495
+[07:40:47] Epoch  29: Loss(train): 0.078605 Loss(val): 0.079448
+[07:43:38] Epoch  30: Loss(train): 0.078492 Loss(val): 0.079332
+[07:46:29] Epoch  31: Loss(train): 0.078412 Loss(val): 0.079296
+[07:50:38] Epoch  32: Loss(train): 0.078362 Loss(val): 0.079227
+[07:53:58] Epoch  33: Loss(train): 0.078317 Loss(val): 0.079200
+[07:57:46] Epoch  34: Loss(train): 0.078244 Loss(val): 0.079147
+[08:00:52] Epoch  35: Loss(train): 0.078228 Loss(val): 0.079104
+[08:04:06] Epoch  36: Loss(train): 0.078162 Loss(val): 0.079045
+[08:07:02] Epoch  37: Loss(train): 0.078107 Loss(val): 0.079005
+[08:10:00] Epoch  38: Loss(train): 0.078047 Loss(val): 0.078963
+[08:12:51] Epoch  39: Loss(train): 0.078025 Loss(val): 0.078911
+[08:15:43] Epoch  40: Loss(train): 0.077986 Loss(val): 0.078901
+[08:18:48] Epoch  41: Loss(train): 0.077959 Loss(val): 0.078886
+[08:23:08] Epoch  42: Loss(train): 0.077921 Loss(val): 0.078858
+[08:26:57] Epoch  43: Loss(train): 0.077886 Loss(val): 0.078826
+[08:30:10] Epoch  44: Loss(train): 0.077849 Loss(val): 0.078798
+[08:33:24] Epoch  45: Loss(train): 0.077820 Loss(val): 0.078793
+[08:36:39] Epoch  46: Loss(train): 0.077805 Loss(val): 0.078768
+[08:39:38] Epoch  47: Loss(train): 0.077782 Loss(val): 0.078746
+[08:42:37] Epoch  48: Loss(train): 0.077759 Loss(val): 0.078739
+[08:45:34] Epoch  49: Loss(train): 0.077742 Loss(val): 0.078724
+[08:48:30] Epoch  50: Loss(train): 0.077717 Loss(val): 0.078697
+[08:52:57] Epoch  51: Loss(train): 0.077710 Loss(val): 0.078685
+[08:56:15] Epoch  52: Loss(train): 0.077692 Loss(val): 0.078671
+[09:00:01] Epoch  53: Loss(train): 0.077666 Loss(val): 0.078661
+[09:03:12] Epoch  54: Loss(train): 0.077662 Loss(val): 0.078661
+[09:06:28] Epoch  55: Loss(train): 0.077645 Loss(val): 0.078655
+[09:09:45] Epoch  56: Loss(train): 0.077640 Loss(val): 0.078639
+[09:12:53] Epoch  57: Loss(train): 0.077625 Loss(val): 0.078633
+[09:16:00] Epoch  58: Loss(train): 0.077610 Loss(val): 0.078614
+[09:19:11] Epoch  59: Loss(train): 0.077602 Loss(val): 0.078613
+[09:22:16] Epoch  60: Loss(train): 0.077597 Loss(val): 0.078604
+[09:26:11] Epoch  61: Loss(train): 0.077585 Loss(val): 0.078593
+[09:29:35] Epoch  62: Loss(train): 0.077575 Loss(val): 0.078597
+[09:33:11] Epoch  63: Loss(train): 0.077566 Loss(val): 0.078592
+[09:36:24] Epoch  64: Loss(train): 0.077563 Loss(val): 0.078593
+[09:39:33] Epoch  65: Loss(train): 0.077556 Loss(val): 0.078583
+[09:42:46] Epoch  66: Loss(train): 0.077552 Loss(val): 0.078584
+[09:45:59] Epoch  67: Loss(train): 0.077546 Loss(val): 0.078584
+[09:49:01] Epoch  68: Loss(train): 0.077539 Loss(val): 0.078566
+[09:52:04] Epoch  69: Loss(train): 0.077531 Loss(val): 0.078566
+[09:55:07] Epoch  70: Loss(train): 0.077528 Loss(val): 0.078561
+[09:58:32] Epoch  71: Loss(train): 0.077520 Loss(val): 0.078549
+[10:02:30] Epoch  72: Loss(train): 0.077516 Loss(val): 0.078549
+[10:06:15] Epoch  73: Loss(train): 0.077514 Loss(val): 0.078551
+[10:09:43] Epoch  74: Loss(train): 0.077510 Loss(val): 0.078550
+[10:13:03] Epoch  75: Loss(train): 0.077506 Loss(val): 0.078551
+[10:16:21] Epoch  76: Loss(train): 0.077503 Loss(val): 0.078544
+[10:19:34] Epoch  77: Loss(train): 0.077501 Loss(val): 0.078549
+[10:22:42] Epoch  78: Loss(train): 0.077498 Loss(val): 0.078546
+[10:25:45] Epoch  79: Loss(train): 0.077495 Loss(val): 0.078537
+[10:29:12] Epoch  80: Loss(train): 0.077493 Loss(val): 0.078541
+[10:33:03] Epoch  81: Loss(train): 0.077491 Loss(val): 0.078534
+[10:36:51] Epoch  82: Loss(train): 0.077488 Loss(val): 0.078536
+[10:40:24] Epoch  83: Loss(train): 0.077485 Loss(val): 0.078529
+[10:43:48] Epoch  84: Loss(train): 0.077483 Loss(val): 0.078526
+[10:47:08] Epoch  85: Loss(train): 0.077481 Loss(val): 0.078524
+[10:50:22] Epoch  86: Loss(train): 0.077480 Loss(val): 0.078528
+[10:53:34] Epoch  87: Loss(train): 0.077477 Loss(val): 0.078526
+[10:56:41] Epoch  88: Loss(train): 0.077476 Loss(val): 0.078521
+[10:59:47] Epoch  89: Loss(train): 0.077475 Loss(val): 0.078524
+[11:03:39] Epoch  90: Loss(train): 0.077473 Loss(val): 0.078523
+[11:07:25] Epoch  91: Loss(train): 0.077472 Loss(val): 0.078522
+[11:10:54] Epoch  92: Loss(train): 0.077471 Loss(val): 0.078519
+[11:14:24] Epoch  93: Loss(train): 0.077469 Loss(val): 0.078519
+[11:17:48] Epoch  94: Loss(train): 0.077468 Loss(val): 0.078517
+[11:21:07] Epoch  95: Loss(train): 0.077467 Loss(val): 0.078516
+[11:24:20] Epoch  96: Loss(train): 0.077466 Loss(val): 0.078516
+[11:27:26] Epoch  97: Loss(train): 0.077465 Loss(val): 0.078516
+[11:30:32] Epoch  98: Loss(train): 0.077464 Loss(val): 0.078514
+[11:34:32] Epoch  99: Loss(train): 0.077464 Loss(val): 0.078514
+[11:38:37] Epoch 100: Loss(train): 0.077463 Loss(val): 0.078512
+[11:42:36] Epoch 101: Loss(train): 0.077462 Loss(val): 0.078514
+[11:46:02] Epoch 102: Loss(train): 0.077461 Loss(val): 0.078513
+[11:49:25] Epoch 103: Loss(train): 0.077460 Loss(val): 0.078513
+[11:52:52] Epoch 104: Loss(train): 0.077460 Loss(val): 0.078512
+[11:56:09] Epoch 105: Loss(train): 0.077460 Loss(val): 0.078513
+[11:59:18] Epoch 106: Loss(train): 0.077459 Loss(val): 0.078512
+[12:02:33] Epoch 107: Loss(train): 0.077459 Loss(val): 0.078512
+[12:06:57] Epoch 108: Loss(train): 0.077458 Loss(val): 0.078510
+[12:11:14] Epoch 109: Loss(train): 0.077458 Loss(val): 0.078511
+[12:14:53] Epoch 110: Loss(train): 0.077457 Loss(val): 0.078510
+[12:18:21] Epoch 111: Loss(train): 0.077457 Loss(val): 0.078508
+[12:21:48] Epoch 112: Loss(train): 0.077456 Loss(val): 0.078508
+[12:24:58] Epoch 113: Loss(train): 0.077456 Loss(val): 0.078507
+[12:28:09] Epoch 114: Loss(train): 0.077456 Loss(val): 0.078506
+[12:31:19] Epoch 115: Loss(train): 0.077455 Loss(val): 0.078507
+[12:34:43] Epoch 116: Loss(train): 0.077455 Loss(val): 0.078507
+[12:38:17] Epoch 117: Loss(train): 0.077455 Loss(val): 0.078507
+[12:41:56] Epoch 118: Loss(train): 0.077455 Loss(val): 0.078506
+[12:45:28] Epoch 119: Loss(train): 0.077455 Loss(val): 0.078507
+[12:48:53] Epoch 120: Loss(train): 0.077454 Loss(val): 0.078506
+[12:52:25] Epoch 121: Loss(train): 0.077454 Loss(val): 0.078506
+[12:55:46] Epoch 122: Loss(train): 0.077454 Loss(val): 0.078507
+[12:59:20] Epoch 123: Loss(train): 0.077454 Loss(val): 0.078506
+[13:02:35] Epoch 124: Loss(train): 0.077454 Loss(val): 0.078506
+[13:05:54] Epoch 125: Loss(train): 0.077454 Loss(val): 0.078506
+[13:09:08] Epoch 126: Loss(train): 0.077454 Loss(val): 0.078506
+[13:12:19] Epoch 127: Loss(train): 0.077454 Loss(val): 0.078506
+[13:16:39] Epoch 128: Loss(train): 0.077454 Loss(val): 0.078505
+[13:20:46] Epoch 129: Loss(train): 0.077453 Loss(val): 0.078505
+[13:24:20] Epoch 130: Loss(train): 0.077453 Loss(val): 0.078505
+[13:27:57] Epoch 131: Loss(train): 0.077453 Loss(val): 0.078505
+[13:31:29] Epoch 132: Loss(train): 0.077453 Loss(val): 0.078504
+[13:34:57] Epoch 133: Loss(train): 0.077453 Loss(val): 0.078504
+[13:38:20] Epoch 134: Loss(train): 0.077453 Loss(val): 0.078504
+[13:41:36] Epoch 135: Loss(train): 0.077453 Loss(val): 0.078504
+[13:44:56] Epoch 136: Loss(train): 0.077453 Loss(val): 0.078504
+[13:48:43] Epoch 137: Loss(train): 0.077453 Loss(val): 0.078504
+[13:52:31] Epoch 138: Loss(train): 0.077453 Loss(val): 0.078504
+[13:56:19] Epoch 139: Loss(train): 0.077453 Loss(val): 0.078504