training_results_4.txt

batch_size 100, epochs 20, learning rate 5e-05, coeff kld 1.0, coeff kd0.1
train epoch 0, iteration 0, loss -1.4628989696502686
validation epoch 0, iteration 0, loss 2.3304070419311524
train epoch 0, iteration 50, loss -2.185535430908203
train epoch 0, iteration 100, loss -2.6167900562286377
validation epoch 0, iteration 100, loss 1.4933358322143555
train epoch 0, iteration 150, loss -3.0943899154663086
train epoch 0, iteration 200, loss -3.261019706726074
validation epoch 0, iteration 200, loss 1.027989549255371
train epoch 0, iteration 250, loss -3.6068296432495117
train epoch 0, iteration 300, loss -3.7937307357788086
validation epoch 0, iteration 300, loss 0.774350813293457
train epoch 0, iteration 350, loss -3.977644205093384
train epoch 0, iteration 400, loss -4.083950996398926
validation epoch 0, iteration 400, loss 0.6374060615539551
train epoch 0, iteration 450, loss -4.28731107711792
train epoch 0, iteration 500, loss -4.291780948638916
validation epoch 0, iteration 500, loss 0.5501952907562256
train epoch 0, iteration 550, loss -4.385025978088379
train epoch 1, iteration 0, loss -4.511828899383545
validation epoch 1, iteration 0, loss 0.49093224296569826
train epoch 1, iteration 50, loss -4.607491970062256
train epoch 1, iteration 100, loss -4.703230381011963
validation epoch 1, iteration 100, loss 0.4541106460571289
train epoch 1, iteration 150, loss -4.554227828979492
train epoch 1, iteration 200, loss -4.723016738891602
validation epoch 1, iteration 200, loss 0.4274974321365356
train epoch 1, iteration 250, loss -4.887784004211426
train epoch 1, iteration 300, loss -4.629098892211914
validation epoch 1, iteration 300, loss 0.4075149789810181
train epoch 1, iteration 350, loss -4.892836093902588
train epoch 1, iteration 400, loss -4.86621618270874
validation epoch 1, iteration 400, loss 0.39343089904785156
train epoch 1, iteration 450, loss -4.902673721313477
train epoch 1, iteration 500, loss -4.968939304351807
validation epoch 1, iteration 500, loss 0.38044742546081545
train epoch 1, iteration 550, loss -4.958748817443848
train epoch 2, iteration 0, loss -5.069705009460449
validation epoch 2, iteration 0, loss 0.36816547298431396
train epoch 2, iteration 50, loss -5.118947505950928
train epoch 2, iteration 100, loss -5.242410182952881
validation epoch 2, iteration 100, loss 0.35954637985229493
train epoch 2, iteration 150, loss -5.252483367919922
train epoch 2, iteration 200, loss -5.301260948181152
validation epoch 2, iteration 200, loss 0.3528047788619995
train epoch 2, iteration 250, loss -5.195025444030762
train epoch 2, iteration 300, loss -5.392702102661133
validation epoch 2, iteration 300, loss 0.34469941635131834
train epoch 2, iteration 350, loss -5.377352714538574
train epoch 2, iteration 400, loss -5.399631500244141
validation epoch 2, iteration 400, loss 0.33700328464508056
train epoch 2, iteration 450, loss -5.43740701675415
train epoch 2, iteration 500, loss -5.266648769378662
validation epoch 2, iteration 500, loss 0.3326132411956787
train epoch 2, iteration 550, loss -5.472346305847168
train epoch 3, iteration 0, loss -5.518528461456299
validation epoch 3, iteration 0, loss 0.3265012643814087
train epoch 3, iteration 50, loss -5.458791732788086
train epoch 3, iteration 100, loss -5.389316082000732
validation epoch 3, iteration 100, loss 0.32089921073913574
train epoch 3, iteration 150, loss -5.487395763397217
train epoch 3, iteration 200, loss -5.518479824066162
validation epoch 3, iteration 200, loss 0.3174689866065979
train epoch 3, iteration 250, loss -5.595519065856934
train epoch 3, iteration 300, loss -5.612948894500732
validation epoch 3, iteration 300, loss 0.30986913356781004
train epoch 3, iteration 350, loss -5.517746448516846
train epoch 3, iteration 400, loss -5.64829158782959
validation epoch 3, iteration 400, loss 0.30473430995941164
train epoch 3, iteration 450, loss -5.7534708976745605
train epoch 3, iteration 500, loss -5.777453422546387
validation epoch 3, iteration 500, loss 0.2975935022354126
train epoch 3, iteration 550, loss -5.564565658569336
train epoch 4, iteration 0, loss -5.735930919647217
validation epoch 4, iteration 0, loss 0.2950155598640442
train epoch 4, iteration 50, loss -5.808049201965332
train epoch 4, iteration 100, loss -5.845757007598877
validation epoch 4, iteration 100, loss 0.28988148651123047
train epoch 4, iteration 150, loss -5.85590934753418
train epoch 4, iteration 200, loss -5.819192886352539
validation epoch 4, iteration 200, loss 0.285243027305603
train epoch 4, iteration 250, loss -5.861352443695068
train epoch 4, iteration 300, loss -5.885369300842285
validation epoch 4, iteration 300, loss 0.2802545739173889
train epoch 4, iteration 350, loss -5.920321941375732
train epoch 4, iteration 400, loss -5.911571025848389
validation epoch 4, iteration 400, loss 0.275831907081604
train epoch 4, iteration 450, loss -5.975128650665283
train epoch 4, iteration 500, loss -6.05881404876709
validation epoch 4, iteration 500, loss 0.2747173014640808
train epoch 4, iteration 550, loss -6.069207191467285
train epoch 5, iteration 0, loss -5.926552772521973
validation epoch 5, iteration 0, loss 0.26957765493392943
train epoch 5, iteration 50, loss -6.030980110168457
train epoch 5, iteration 100, loss -6.045607089996338
validation epoch 5, iteration 100, loss 0.26427816572189333
train epoch 5, iteration 150, loss -6.116491317749023
train epoch 5, iteration 200, loss -6.128604412078857
validation epoch 5, iteration 200, loss 0.26392447767257693
train epoch 5, iteration 250, loss -6.11085319519043
train epoch 5, iteration 300, loss -6.1300835609436035
validation epoch 5, iteration 300, loss 0.2589313265800476
train epoch 5, iteration 350, loss -6.1209235191345215
train epoch 5, iteration 400, loss -6.114326000213623
validation epoch 5, iteration 400, loss 0.2567297103881836
train epoch 5, iteration 450, loss -6.281443119049072
train epoch 5, iteration 500, loss -6.215927600860596
validation epoch 5, iteration 500, loss 0.25167129287719725
train epoch 5, iteration 550, loss -6.1410627365112305
train epoch 6, iteration 0, loss -6.174037933349609
validation epoch 6, iteration 0, loss 0.2471798593521118
train epoch 6, iteration 50, loss -6.227602481842041
train epoch 6, iteration 100, loss -6.2930588722229
validation epoch 6, iteration 100, loss 0.24652800607681274
train epoch 6, iteration 150, loss -6.409376621246338
train epoch 6, iteration 200, loss -6.200093746185303
validation epoch 6, iteration 200, loss 0.24163800859451293
train epoch 6, iteration 250, loss -6.215313911437988
train epoch 6, iteration 300, loss -6.374815464019775
validation epoch 6, iteration 300, loss 0.24103642110824586
train epoch 6, iteration 350, loss -6.38955545425415
train epoch 6, iteration 400, loss -6.378422737121582
validation epoch 6, iteration 400, loss 0.2366472677230835
train epoch 6, iteration 450, loss -6.371236801147461
train epoch 6, iteration 500, loss -6.456579208374023
validation epoch 6, iteration 500, loss 0.23368361415863037
train epoch 6, iteration 550, loss -6.468822956085205
train epoch 7, iteration 0, loss -6.461745738983154
validation epoch 7, iteration 0, loss 0.2308976806640625
train epoch 7, iteration 50, loss -6.448482990264893
train epoch 7, iteration 100, loss -6.386987686157227
validation epoch 7, iteration 100, loss 0.22925016527175904
train epoch 7, iteration 150, loss -6.506495475769043
train epoch 7, iteration 200, loss -6.449230194091797
validation epoch 7, iteration 200, loss 0.2259226375579834
train epoch 7, iteration 250, loss -6.452174663543701
train epoch 7, iteration 300, loss -6.554157257080078
validation epoch 7, iteration 300, loss 0.22254526166915894
train epoch 7, iteration 350, loss -6.556105613708496
train epoch 7, iteration 400, loss -6.521121025085449
validation epoch 7, iteration 400, loss 0.21991798782348632
train epoch 7, iteration 450, loss -6.630686283111572
train epoch 7, iteration 500, loss -6.631582260131836
validation epoch 7, iteration 500, loss 0.2204140588760376
train epoch 7, iteration 550, loss -6.451493263244629
train epoch 8, iteration 0, loss -6.6395416259765625
validation epoch 8, iteration 0, loss 0.21804924354553223
train epoch 8, iteration 50, loss -6.575711250305176
train epoch 8, iteration 100, loss -6.618554592132568
validation epoch 8, iteration 100, loss 0.21633989362716674
train epoch 8, iteration 150, loss -6.605379104614258
train epoch 8, iteration 200, loss -6.623338222503662
validation epoch 8, iteration 200, loss 0.21322539672851562
train epoch 8, iteration 250, loss -6.744997501373291
train epoch 8, iteration 300, loss -6.698851585388184
validation epoch 8, iteration 300, loss 0.20895151910781862
train epoch 8, iteration 350, loss -6.745121479034424
train epoch 8, iteration 400, loss -6.741675853729248
validation epoch 8, iteration 400, loss 0.20788978595733643
train epoch 8, iteration 450, loss -6.731369495391846
train epoch 8, iteration 500, loss -6.669680118560791
validation epoch 8, iteration 500, loss 0.2048502188682556
train epoch 8, iteration 550, loss -6.7602105140686035
train epoch 9, iteration 0, loss -6.736696243286133
validation epoch 9, iteration 0, loss 0.20423992557525636
train epoch 9, iteration 50, loss -6.765185832977295
train epoch 9, iteration 100, loss -6.869357109069824
validation epoch 9, iteration 100, loss 0.20340191402435304
train epoch 9, iteration 150, loss -6.78419828414917
train epoch 9, iteration 200, loss -6.771018981933594
validation epoch 9, iteration 200, loss 0.20027134799957275
train epoch 9, iteration 250, loss -6.831057071685791
train epoch 9, iteration 300, loss -6.885773658752441
validation epoch 9, iteration 300, loss 0.19789945707321166
train epoch 9, iteration 350, loss -6.847071170806885
train epoch 9, iteration 400, loss -6.871266841888428
validation epoch 9, iteration 400, loss 0.19616088275909424
train epoch 9, iteration 450, loss -6.8716959953308105
train epoch 9, iteration 500, loss -6.866950035095215
validation epoch 9, iteration 500, loss 0.19525909719467163
train epoch 9, iteration 550, loss -6.952884197235107
train epoch 10, iteration 0, loss -6.955913543701172
validation epoch 10, iteration 0, loss 0.19435686321258544
train epoch 10, iteration 50, loss -6.916347026824951
train epoch 10, iteration 100, loss -6.935521602630615
validation epoch 10, iteration 100, loss 0.19077639150619508
train epoch 10, iteration 150, loss -7.005374431610107
train epoch 10, iteration 200, loss -6.975936412811279
validation epoch 10, iteration 200, loss 0.19014845299720765
train epoch 10, iteration 250, loss -7.002256870269775
train epoch 10, iteration 300, loss -7.032391548156738
validation epoch 10, iteration 300, loss 0.19078654518127441
train epoch 10, iteration 350, loss -7.073795318603516
train epoch 10, iteration 400, loss -7.011958122253418
validation epoch 10, iteration 400, loss 0.18807009902000427
train epoch 10, iteration 450, loss -7.061474323272705
train epoch 10, iteration 500, loss -7.016116142272949
validation epoch 10, iteration 500, loss 0.18692666606903077
train epoch 10, iteration 550, loss -7.070005416870117
train epoch 11, iteration 0, loss -7.084863662719727
validation epoch 11, iteration 0, loss 0.18554010248184205
train epoch 11, iteration 50, loss -6.971772193908691
train epoch 11, iteration 100, loss -7.0668768882751465
validation epoch 11, iteration 100, loss 0.18512255239486694
train epoch 11, iteration 150, loss -7.079649925231934
train epoch 11, iteration 200, loss -7.121644496917725
validation epoch 11, iteration 200, loss 0.1825265112400055
train epoch 11, iteration 250, loss -7.017441749572754
train epoch 11, iteration 300, loss -7.146275043487549
validation epoch 11, iteration 300, loss 0.18154267549514772
train epoch 11, iteration 350, loss -7.144844055175781
train epoch 11, iteration 400, loss -7.140236854553223
validation epoch 11, iteration 400, loss 0.1809679277420044
train epoch 11, iteration 450, loss -7.194940090179443
train epoch 11, iteration 500, loss -7.0985918045043945
validation epoch 11, iteration 500, loss 0.18183787603378296
train epoch 11, iteration 550, loss -7.166686058044434
train epoch 12, iteration 0, loss -7.180776596069336
validation epoch 12, iteration 0, loss 0.1786402940750122
train epoch 12, iteration 50, loss -7.146398067474365
train epoch 12, iteration 100, loss -7.248493671417236
validation epoch 12, iteration 100, loss 0.17881529531478882
train epoch 12, iteration 150, loss -7.271069526672363
train epoch 12, iteration 200, loss -7.184361934661865
validation epoch 12, iteration 200, loss 0.17721774463653564
train epoch 12, iteration 250, loss -7.193194389343262
train epoch 12, iteration 300, loss -7.280644416809082
validation epoch 12, iteration 300, loss 0.17407514362335205
train epoch 12, iteration 350, loss -7.142693996429443
train epoch 12, iteration 400, loss -7.295604705810547
validation epoch 12, iteration 400, loss 0.1723844946861267
train epoch 12, iteration 450, loss -7.266312599182129
train epoch 12, iteration 500, loss -7.295431613922119
validation epoch 12, iteration 500, loss 0.17162316970825195
train epoch 12, iteration 550, loss -7.282637119293213
train epoch 13, iteration 0, loss -7.311875343322754
validation epoch 13, iteration 0, loss 0.17237155122756959
train epoch 13, iteration 50, loss -7.321512222290039
train epoch 13, iteration 100, loss -7.298182487487793
validation epoch 13, iteration 100, loss 0.1707719307899475
train epoch 13, iteration 150, loss -7.378393650054932
train epoch 13, iteration 200, loss -7.36244535446167
validation epoch 13, iteration 200, loss 0.16882521572113038
train epoch 13, iteration 250, loss -7.257751941680908
train epoch 13, iteration 300, loss -7.4017486572265625
validation epoch 13, iteration 300, loss 0.169834792470932
train epoch 13, iteration 350, loss -7.259993553161621
train epoch 13, iteration 400, loss -7.399552822113037
validation epoch 13, iteration 400, loss 0.16875281229019165
train epoch 13, iteration 450, loss -7.380742073059082
train epoch 13, iteration 500, loss -7.297906875610352
validation epoch 13, iteration 500, loss 0.16676820216178895
train epoch 13, iteration 550, loss -7.362351894378662
train epoch 14, iteration 0, loss -7.4414567947387695
validation epoch 14, iteration 0, loss 0.16557851581573485
train epoch 14, iteration 50, loss -7.3770904541015625
train epoch 14, iteration 100, loss -7.3416361808776855
validation epoch 14, iteration 100, loss 0.16745097122192382
train epoch 14, iteration 150, loss -7.4948039054870605
train epoch 14, iteration 200, loss -7.501307010650635
validation epoch 14, iteration 200, loss 0.16770916986465453
train epoch 14, iteration 250, loss -7.465132713317871
train epoch 14, iteration 300, loss -7.462818145751953
validation epoch 14, iteration 300, loss 0.1633938277244568
train epoch 14, iteration 350, loss -7.524635314941406
train epoch 14, iteration 400, loss -7.5000200271606445
validation epoch 14, iteration 400, loss 0.16550106725692748
train epoch 14, iteration 450, loss -7.556066036224365
train epoch 14, iteration 500, loss -7.525626182556152
validation epoch 14, iteration 500, loss 0.1603415198802948
train epoch 14, iteration 550, loss -7.481273651123047
train epoch 15, iteration 0, loss -7.516364574432373
validation epoch 15, iteration 0, loss 0.16151165351867675
train epoch 15, iteration 50, loss -7.484051704406738
train epoch 15, iteration 100, loss -7.514545917510986
validation epoch 15, iteration 100, loss 0.16046455926895142
train epoch 15, iteration 150, loss -7.500998020172119
train epoch 15, iteration 200, loss -7.56790828704834
validation epoch 15, iteration 200, loss 0.1606443977832794
train epoch 15, iteration 250, loss -7.501270771026611
train epoch 15, iteration 300, loss -7.516714096069336
validation epoch 15, iteration 300, loss 0.16112163019180298
train epoch 15, iteration 350, loss -7.461143970489502
train epoch 15, iteration 400, loss -7.5480170249938965
validation epoch 15, iteration 400, loss 0.15835418677330018
train epoch 15, iteration 450, loss -7.567783355712891
train epoch 15, iteration 500, loss -7.626298427581787
validation epoch 15, iteration 500, loss 0.15679810819625856
train epoch 15, iteration 550, loss -7.525123596191406
train epoch 16, iteration 0, loss -7.534162521362305
validation epoch 16, iteration 0, loss 0.15725885829925537
train epoch 16, iteration 50, loss -7.630160331726074
train epoch 16, iteration 100, loss -7.628406524658203
validation epoch 16, iteration 100, loss 0.15726545495986938
train epoch 16, iteration 150, loss -7.600445747375488
train epoch 16, iteration 200, loss -7.564030647277832
validation epoch 16, iteration 200, loss 0.15785807633399965
train epoch 16, iteration 250, loss -7.679696559906006
train epoch 16, iteration 300, loss -7.656528472900391
validation epoch 16, iteration 300, loss 0.1561799503326416
train epoch 16, iteration 350, loss -7.683084011077881
train epoch 16, iteration 400, loss -7.659872055053711
validation epoch 16, iteration 400, loss 0.15399082884788512
train epoch 16, iteration 450, loss -7.623642444610596
train epoch 16, iteration 500, loss -7.712148189544678
validation epoch 16, iteration 500, loss 0.15644470858573914
train epoch 16, iteration 550, loss -7.69417667388916
train epoch 17, iteration 0, loss -7.6654133796691895
validation epoch 17, iteration 0, loss 0.1542289405822754
train epoch 17, iteration 50, loss -7.620699882507324
train epoch 17, iteration 100, loss -7.642889499664307
validation epoch 17, iteration 100, loss 0.15420993223190307
train epoch 17, iteration 150, loss -7.626218795776367
train epoch 17, iteration 200, loss -7.7242631912231445
validation epoch 17, iteration 200, loss 0.15530907669067384
train epoch 17, iteration 250, loss -7.720007419586182
train epoch 17, iteration 300, loss -7.729181289672852
validation epoch 17, iteration 300, loss 0.15202906770706176
train epoch 17, iteration 350, loss -7.717782974243164
train epoch 17, iteration 400, loss -7.771949768066406
validation epoch 17, iteration 400, loss 0.15263185439109803
train epoch 17, iteration 450, loss -7.733894348144531
train epoch 17, iteration 500, loss -7.743658065795898
validation epoch 17, iteration 500, loss 0.1522386113166809
train epoch 17, iteration 550, loss -7.744875431060791
train epoch 18, iteration 0, loss -7.741959571838379
validation epoch 18, iteration 0, loss 0.15172442870140077
train epoch 18, iteration 50, loss -7.805287837982178
train epoch 18, iteration 100, loss -7.773956775665283
validation epoch 18, iteration 100, loss 0.15352025990486146
train epoch 18, iteration 150, loss -7.773783206939697
train epoch 18, iteration 200, loss -7.718197345733643
validation epoch 18, iteration 200, loss 0.1488477972984314
train epoch 18, iteration 250, loss -7.68657922744751
train epoch 18, iteration 300, loss -7.750718593597412
validation epoch 18, iteration 300, loss 0.14923653268814088
train epoch 18, iteration 350, loss -7.7528157234191895
train epoch 18, iteration 400, loss -7.855215549468994
validation epoch 18, iteration 400, loss 0.15116800961494445
train epoch 18, iteration 450, loss -7.7992143630981445
train epoch 18, iteration 500, loss -7.808616638183594
validation epoch 18, iteration 500, loss 0.1502827313899994
train epoch 18, iteration 550, loss -7.780680179595947
train epoch 19, iteration 0, loss -7.838714122772217
validation epoch 19, iteration 0, loss 0.14897474331855773
train epoch 19, iteration 50, loss -7.758431434631348
train epoch 19, iteration 100, loss -7.761359214782715
validation epoch 19, iteration 100, loss 0.14696234188079835
train epoch 19, iteration 150, loss -7.7923583984375
train epoch 19, iteration 200, loss -7.855258941650391
validation epoch 19, iteration 200, loss 0.14869386143684388
train epoch 19, iteration 250, loss -7.823734760284424
train epoch 19, iteration 300, loss -7.863986492156982
validation epoch 19, iteration 300, loss 0.1462991591453552
train epoch 19, iteration 350, loss -7.912228107452393
train epoch 19, iteration 400, loss -7.868411064147949
validation epoch 19, iteration 400, loss 0.14624630584716797
train epoch 19, iteration 450, loss -7.816517353057861
train epoch 19, iteration 500, loss -7.857224941253662
validation epoch 19, iteration 500, loss 0.14803501100540162
train epoch 19, iteration 550, loss -7.8919525146484375