training_results_3.txt

batch_size 100, epochs 20, learning rate 5e-05, coeff kld 1.0, coeff kd
train epoch 0, iteration 0, loss 1.167377233505249
validation epoch 0, iteration 0, loss 2.3044667877197265
train epoch 0, iteration 50, loss -0.01147913932800293
train epoch 0, iteration 100, loss -1.3347291946411133
validation epoch 0, iteration 100, loss 1.4419353637695314
train epoch 0, iteration 150, loss -1.7246707677841187
train epoch 0, iteration 200, loss -2.246326446533203
validation epoch 0, iteration 200, loss 0.9828682876586914
train epoch 0, iteration 250, loss -2.5392167568206787
train epoch 0, iteration 300, loss -2.9157395362854004
validation epoch 0, iteration 300, loss 0.7771785472869873
train epoch 0, iteration 350, loss -3.094954490661621
train epoch 0, iteration 400, loss -3.119601249694824
validation epoch 0, iteration 400, loss 0.6526244457244873
train epoch 0, iteration 450, loss -3.208909511566162
train epoch 0, iteration 500, loss -3.4826231002807617
validation epoch 0, iteration 500, loss 0.5880819541931153
train epoch 0, iteration 550, loss -3.4818694591522217
train epoch 1, iteration 0, loss -3.3094959259033203
validation epoch 1, iteration 0, loss 0.5445559257507324
train epoch 1, iteration 50, loss -3.701582908630371
train epoch 1, iteration 100, loss -3.8739500045776367
validation epoch 1, iteration 100, loss 0.5136238716125489
train epoch 1, iteration 150, loss -3.8572733402252197
train epoch 1, iteration 200, loss -3.6499557495117188
validation epoch 1, iteration 200, loss 0.497144490814209
train epoch 1, iteration 250, loss -4.021006107330322
train epoch 1, iteration 300, loss -3.839996576309204
validation epoch 1, iteration 300, loss 0.479593327331543
train epoch 1, iteration 350, loss -4.003590106964111
train epoch 1, iteration 400, loss -4.05293083190918
validation epoch 1, iteration 400, loss 0.4607105297088623
train epoch 1, iteration 450, loss -4.114543914794922
train epoch 1, iteration 500, loss -4.218067169189453
validation epoch 1, iteration 500, loss 0.4502840648651123
train epoch 1, iteration 550, loss -4.244938850402832
train epoch 2, iteration 0, loss -4.116677761077881
validation epoch 2, iteration 0, loss 0.443727303314209
train epoch 2, iteration 50, loss -4.187822341918945
train epoch 2, iteration 100, loss -4.2955641746521
validation epoch 2, iteration 100, loss 0.43429202404022216
train epoch 2, iteration 150, loss -4.365623474121094
train epoch 2, iteration 200, loss -4.371597766876221
validation epoch 2, iteration 200, loss 0.4212966131210327
train epoch 2, iteration 250, loss -4.289975643157959
train epoch 2, iteration 300, loss -4.344804286956787
validation epoch 2, iteration 300, loss 0.4129140392303467
train epoch 2, iteration 350, loss -4.569256782531738
train epoch 2, iteration 400, loss -4.359555721282959
validation epoch 2, iteration 400, loss 0.3999727903366089
train epoch 2, iteration 450, loss -4.587426662445068
train epoch 2, iteration 500, loss -4.469425201416016
validation epoch 2, iteration 500, loss 0.3949582099914551
train epoch 2, iteration 550, loss -4.476658821105957
train epoch 3, iteration 0, loss -4.587646961212158
validation epoch 3, iteration 0, loss 0.3939518226623535
train epoch 3, iteration 50, loss -4.5166497230529785
train epoch 3, iteration 100, loss -4.709198951721191
validation epoch 3, iteration 100, loss 0.3813387405395508
train epoch 3, iteration 150, loss -4.712251663208008
train epoch 3, iteration 200, loss -4.752548694610596
validation epoch 3, iteration 200, loss 0.3763149505615234
train epoch 3, iteration 250, loss -4.8275556564331055
train epoch 3, iteration 300, loss -4.798132419586182
validation epoch 3, iteration 300, loss 0.3735986289978027
train epoch 3, iteration 350, loss -4.694460868835449
train epoch 3, iteration 400, loss -4.703403949737549
validation epoch 3, iteration 400, loss 0.3636737216949463
train epoch 3, iteration 450, loss -4.792061805725098
train epoch 3, iteration 500, loss -4.882228851318359
validation epoch 3, iteration 500, loss 0.35967221355438234
train epoch 3, iteration 550, loss -4.688337326049805
train epoch 4, iteration 0, loss -4.898070812225342
validation epoch 4, iteration 0, loss 0.3503024038314819
train epoch 4, iteration 50, loss -4.988593578338623
train epoch 4, iteration 100, loss -5.003087043762207
validation epoch 4, iteration 100, loss 0.34734667339324954
train epoch 4, iteration 150, loss -4.947480201721191
train epoch 4, iteration 200, loss -4.829344749450684
validation epoch 4, iteration 200, loss 0.3407144781112671
train epoch 4, iteration 250, loss -5.211061954498291
train epoch 4, iteration 300, loss -5.059401512145996
validation epoch 4, iteration 300, loss 0.33458927879333494
train epoch 4, iteration 350, loss -4.869389057159424
train epoch 4, iteration 400, loss -5.10087251663208
validation epoch 4, iteration 400, loss 0.3296343633651733
train epoch 4, iteration 450, loss -5.077521324157715
train epoch 4, iteration 500, loss -5.05587911605835
validation epoch 4, iteration 500, loss 0.32529541568756104
train epoch 4, iteration 550, loss -5.2508721351623535
train epoch 5, iteration 0, loss -5.263072967529297
validation epoch 5, iteration 0, loss 0.32104587154388425
train epoch 5, iteration 50, loss -5.372756481170654
train epoch 5, iteration 100, loss -5.23806095123291
validation epoch 5, iteration 100, loss 0.31461651935577395
train epoch 5, iteration 150, loss -5.288668155670166
train epoch 5, iteration 200, loss -5.4235615730285645
validation epoch 5, iteration 200, loss 0.31374511165618896
train epoch 5, iteration 250, loss -5.3107008934021
train epoch 5, iteration 300, loss -5.294454574584961
validation epoch 5, iteration 300, loss 0.30907416343688965
train epoch 5, iteration 350, loss -5.263647556304932
train epoch 5, iteration 400, loss -5.362866401672363
validation epoch 5, iteration 400, loss 0.30816491298675536
train epoch 5, iteration 450, loss -5.354348182678223
train epoch 5, iteration 500, loss -5.433272838592529
validation epoch 5, iteration 500, loss 0.30728915100097653
train epoch 5, iteration 550, loss -5.467287540435791
train epoch 6, iteration 0, loss -5.485496997833252
validation epoch 6, iteration 0, loss 0.2957380718231201
train epoch 6, iteration 50, loss -5.400988578796387
train epoch 6, iteration 100, loss -5.57142448425293
validation epoch 6, iteration 100, loss 0.29865086002349855
train epoch 6, iteration 150, loss -5.477263927459717
train epoch 6, iteration 200, loss -5.429980754852295
validation epoch 6, iteration 200, loss 0.29376538467407226
train epoch 6, iteration 250, loss -5.369499206542969
train epoch 6, iteration 300, loss -5.421423435211182
validation epoch 6, iteration 300, loss 0.28945805263519286
train epoch 6, iteration 350, loss -5.500643253326416
train epoch 6, iteration 400, loss -5.731788635253906
validation epoch 6, iteration 400, loss 0.28549644222259524
train epoch 6, iteration 450, loss -5.474998474121094
train epoch 6, iteration 500, loss -5.675848484039307
validation epoch 6, iteration 500, loss 0.2863707030296326
train epoch 6, iteration 550, loss -5.710326671600342
train epoch 7, iteration 0, loss -5.70430326461792
validation epoch 7, iteration 0, loss 0.28106940212249754
train epoch 7, iteration 50, loss -5.615236759185791
train epoch 7, iteration 100, loss -5.756471157073975
validation epoch 7, iteration 100, loss 0.27672815265655515
train epoch 7, iteration 150, loss -5.680889129638672
train epoch 7, iteration 200, loss -5.808945655822754
validation epoch 7, iteration 200, loss 0.27982008666992186
train epoch 7, iteration 250, loss -5.683535099029541
train epoch 7, iteration 300, loss -5.733193397521973
validation epoch 7, iteration 300, loss 0.2706785696029663
train epoch 7, iteration 350, loss -5.68504524230957
train epoch 7, iteration 400, loss -5.72700834274292
validation epoch 7, iteration 400, loss 0.27453217239379885
train epoch 7, iteration 450, loss -5.788069725036621
train epoch 7, iteration 500, loss -5.734593391418457
validation epoch 7, iteration 500, loss 0.27408978843688964
train epoch 7, iteration 550, loss -5.906826019287109
train epoch 8, iteration 0, loss -5.7440667152404785
validation epoch 8, iteration 0, loss 0.26945857734680173
train epoch 8, iteration 50, loss -5.712010860443115
train epoch 8, iteration 100, loss -5.7761383056640625
validation epoch 8, iteration 100, loss 0.266743341255188
train epoch 8, iteration 150, loss -5.814653396606445
train epoch 8, iteration 200, loss -5.751369476318359
validation epoch 8, iteration 200, loss 0.26355077419281003
train epoch 8, iteration 250, loss -5.91827392578125
train epoch 8, iteration 300, loss -5.8785247802734375
validation epoch 8, iteration 300, loss 0.2602805461883545
train epoch 8, iteration 350, loss -5.74257230758667
train epoch 8, iteration 400, loss -6.004997253417969
validation epoch 8, iteration 400, loss 0.26032311115264894
train epoch 8, iteration 450, loss -5.960284233093262
train epoch 8, iteration 500, loss -6.024448394775391
validation epoch 8, iteration 500, loss 0.2568216661453247
train epoch 8, iteration 550, loss -5.847795009613037
train epoch 9, iteration 0, loss -6.0088934898376465
validation epoch 9, iteration 0, loss 0.2530045207977295
train epoch 9, iteration 50, loss -5.87808084487915
train epoch 9, iteration 100, loss -5.948899269104004
validation epoch 9, iteration 100, loss 0.25596356477737425
train epoch 9, iteration 150, loss -6.018251419067383
train epoch 9, iteration 200, loss -6.103662490844727
validation epoch 9, iteration 200, loss 0.2511299377441406
train epoch 9, iteration 250, loss -6.083556652069092
train epoch 9, iteration 300, loss -5.963860034942627
validation epoch 9, iteration 300, loss 0.2499182010650635
train epoch 9, iteration 350, loss -6.004027843475342
train epoch 9, iteration 400, loss -5.9926252365112305
validation epoch 9, iteration 400, loss 0.24502382221221924
train epoch 9, iteration 450, loss -6.052377223968506
train epoch 9, iteration 500, loss -6.120858669281006
validation epoch 9, iteration 500, loss 0.24581831197738646
train epoch 9, iteration 550, loss -6.048893451690674
train epoch 10, iteration 0, loss -6.105403900146484
validation epoch 10, iteration 0, loss 0.2484443875312805
train epoch 10, iteration 50, loss -6.118085861206055
train epoch 10, iteration 100, loss -6.107926368713379
validation epoch 10, iteration 100, loss 0.24784913539886474
train epoch 10, iteration 150, loss -5.999056816101074
train epoch 10, iteration 200, loss -6.1449294090271
validation epoch 10, iteration 200, loss 0.24415512924194335
train epoch 10, iteration 250, loss -6.083878517150879
train epoch 10, iteration 300, loss -6.175149440765381
validation epoch 10, iteration 300, loss 0.24327757034301759
train epoch 10, iteration 350, loss -6.162589073181152
train epoch 10, iteration 400, loss -6.249789714813232
validation epoch 10, iteration 400, loss 0.2430033122062683
train epoch 10, iteration 450, loss -6.141493320465088
train epoch 10, iteration 500, loss -6.253790855407715
validation epoch 10, iteration 500, loss 0.23638973550796508
train epoch 10, iteration 550, loss -6.2134108543396
train epoch 11, iteration 0, loss -6.104068756103516
validation epoch 11, iteration 0, loss 0.24020546674728394
train epoch 11, iteration 50, loss -6.261847019195557
train epoch 11, iteration 100, loss -6.142935752868652
validation epoch 11, iteration 100, loss 0.23541756076812745
train epoch 11, iteration 150, loss -6.255965709686279
train epoch 11, iteration 200, loss -6.1950531005859375
validation epoch 11, iteration 200, loss 0.23495088720321655
train epoch 11, iteration 250, loss -6.294167995452881
train epoch 11, iteration 300, loss -6.296424865722656
validation epoch 11, iteration 300, loss 0.23194413585662843
train epoch 11, iteration 350, loss -6.356257438659668
train epoch 11, iteration 400, loss -6.229992389678955
validation epoch 11, iteration 400, loss 0.2354341767311096
train epoch 11, iteration 450, loss -6.2645487785339355
train epoch 11, iteration 500, loss -6.389191627502441
validation epoch 11, iteration 500, loss 0.23234950132369994
train epoch 11, iteration 550, loss -6.304930686950684
train epoch 12, iteration 0, loss -6.3820295333862305
validation epoch 12, iteration 0, loss 0.22793271074295043
train epoch 12, iteration 50, loss -6.339960098266602
train epoch 12, iteration 100, loss -6.40284538269043
validation epoch 12, iteration 100, loss 0.23124329080581665
train epoch 12, iteration 150, loss -6.270582675933838
train epoch 12, iteration 200, loss -6.405305862426758
validation epoch 12, iteration 200, loss 0.22862931089401245
train epoch 12, iteration 250, loss -6.469307899475098
train epoch 12, iteration 300, loss -6.431178092956543
validation epoch 12, iteration 300, loss 0.23256013584136964
train epoch 12, iteration 350, loss -6.482540130615234
train epoch 12, iteration 400, loss -6.361112594604492
validation epoch 12, iteration 400, loss 0.22687407636642457
train epoch 12, iteration 450, loss -6.504904747009277
train epoch 12, iteration 500, loss -6.433293342590332
validation epoch 12, iteration 500, loss 0.2278984935760498
train epoch 12, iteration 550, loss -6.293159008026123
train epoch 13, iteration 0, loss -6.3318328857421875
validation epoch 13, iteration 0, loss 0.22371323461532594
train epoch 13, iteration 50, loss -6.444521903991699
train epoch 13, iteration 100, loss -6.500786304473877
validation epoch 13, iteration 100, loss 0.22488706064224243
train epoch 13, iteration 150, loss -6.500704288482666
train epoch 13, iteration 200, loss -6.529712200164795
validation epoch 13, iteration 200, loss 0.22471706790924073
train epoch 13, iteration 250, loss -6.578198432922363
train epoch 13, iteration 300, loss -6.428021430969238
validation epoch 13, iteration 300, loss 0.22051548671722412
train epoch 13, iteration 350, loss -6.532614707946777
train epoch 13, iteration 400, loss -6.532231330871582
validation epoch 13, iteration 400, loss 0.22081366233825683
train epoch 13, iteration 450, loss -6.456570625305176
train epoch 13, iteration 500, loss -6.57181978225708
validation epoch 13, iteration 500, loss 0.2189312918663025
train epoch 13, iteration 550, loss -6.515581130981445
train epoch 14, iteration 0, loss -6.572943210601807
validation epoch 14, iteration 0, loss 0.21843430404663086
train epoch 14, iteration 50, loss -6.494901657104492
train epoch 14, iteration 100, loss -6.617425918579102
validation epoch 14, iteration 100, loss 0.21923270092010497
train epoch 14, iteration 150, loss -6.6086273193359375
train epoch 14, iteration 200, loss -6.534257411956787
validation epoch 14, iteration 200, loss 0.22222324237823488
train epoch 14, iteration 250, loss -6.622442245483398
train epoch 14, iteration 300, loss -6.64208984375
validation epoch 14, iteration 300, loss 0.22143223323822023
train epoch 14, iteration 350, loss -6.645895004272461
train epoch 14, iteration 400, loss -6.575638771057129
validation epoch 14, iteration 400, loss 0.2136172089576721
train epoch 14, iteration 450, loss -6.715345859527588
train epoch 14, iteration 500, loss -6.660941123962402
validation epoch 14, iteration 500, loss 0.21751608905792236
train epoch 14, iteration 550, loss -6.677851676940918
train epoch 15, iteration 0, loss -6.468520641326904
validation epoch 15, iteration 0, loss 0.21376212854385376
train epoch 15, iteration 50, loss -6.704090595245361
train epoch 15, iteration 100, loss -6.7269439697265625
validation epoch 15, iteration 100, loss 0.21482198219299317
train epoch 15, iteration 150, loss -6.660860061645508
train epoch 15, iteration 200, loss -6.758810997009277
validation epoch 15, iteration 200, loss 0.21402506170272828
train epoch 15, iteration 250, loss -6.57561731338501
train epoch 15, iteration 300, loss -6.721937656402588
validation epoch 15, iteration 300, loss 0.213981632232666
train epoch 15, iteration 350, loss -6.758734226226807
train epoch 15, iteration 400, loss -6.808712005615234
validation epoch 15, iteration 400, loss 0.20917816219329835
train epoch 15, iteration 450, loss -6.696573257446289
train epoch 15, iteration 500, loss -6.610930442810059
validation epoch 15, iteration 500, loss 0.2099449993133545
train epoch 15, iteration 550, loss -6.806334495544434
train epoch 16, iteration 0, loss -6.674689292907715
validation epoch 16, iteration 0, loss 0.2125829119682312
train epoch 16, iteration 50, loss -6.726754188537598
train epoch 16, iteration 100, loss -6.722573280334473
validation epoch 16, iteration 100, loss 0.21073468313217164
train epoch 16, iteration 150, loss -6.679788112640381
train epoch 16, iteration 200, loss -6.765979766845703
validation epoch 16, iteration 200, loss 0.20949257621765136
train epoch 16, iteration 250, loss -6.7370991706848145
train epoch 16, iteration 300, loss -6.740999221801758
validation epoch 16, iteration 300, loss 0.21124608936309813
train epoch 16, iteration 350, loss -6.776535511016846
train epoch 16, iteration 400, loss -6.683974742889404
validation epoch 16, iteration 400, loss 0.21310284004211424
train epoch 16, iteration 450, loss -6.812846660614014
train epoch 16, iteration 500, loss -6.852713584899902
validation epoch 16, iteration 500, loss 0.20951751441955566
train epoch 16, iteration 550, loss -6.718315601348877
train epoch 17, iteration 0, loss -6.752810478210449
validation epoch 17, iteration 0, loss 0.20535049743652345
train epoch 17, iteration 50, loss -6.962609767913818
train epoch 17, iteration 100, loss -6.892909526824951
validation epoch 17, iteration 100, loss 0.21120638160705565
train epoch 17, iteration 150, loss -6.87742280960083
train epoch 17, iteration 200, loss -6.840347766876221
validation epoch 17, iteration 200, loss 0.2072507248878479
train epoch 17, iteration 250, loss -6.858875274658203
train epoch 17, iteration 300, loss -6.76360559463501
validation epoch 17, iteration 300, loss 0.2053620774269104
train epoch 17, iteration 350, loss -6.9045562744140625
train epoch 17, iteration 400, loss -6.902143478393555
validation epoch 17, iteration 400, loss 0.20481196374893187
train epoch 17, iteration 450, loss -6.819754600524902
train epoch 17, iteration 500, loss -6.755962371826172
validation epoch 17, iteration 500, loss 0.202500821685791
train epoch 17, iteration 550, loss -7.034702301025391
train epoch 18, iteration 0, loss -6.948291301727295
validation epoch 18, iteration 0, loss 0.20288945178985596
train epoch 18, iteration 50, loss -7.006838798522949
train epoch 18, iteration 100, loss -6.854168891906738
validation epoch 18, iteration 100, loss 0.20071406021118163
train epoch 18, iteration 150, loss -6.77987813949585
train epoch 18, iteration 200, loss -6.78524112701416
validation epoch 18, iteration 200, loss 0.2030822498321533
train epoch 18, iteration 250, loss -6.917473793029785
train epoch 18, iteration 300, loss -6.99234676361084
validation epoch 18, iteration 300, loss 0.2039331829071045
train epoch 18, iteration 350, loss -6.788854598999023
train epoch 18, iteration 400, loss -7.001659393310547
validation epoch 18, iteration 400, loss 0.19894623832702638
train epoch 18, iteration 450, loss -6.856626510620117
train epoch 18, iteration 500, loss -6.963882923126221
validation epoch 18, iteration 500, loss 0.19913866472244263
train epoch 18, iteration 550, loss -6.947048187255859
train epoch 19, iteration 0, loss -6.811797142028809
validation epoch 19, iteration 0, loss 0.20457419013977052
train epoch 19, iteration 50, loss -6.9192280769348145
train epoch 19, iteration 100, loss -6.948354721069336
validation epoch 19, iteration 100, loss 0.2016668281555176
train epoch 19, iteration 150, loss -6.985383987426758
train epoch 19, iteration 200, loss -7.03183126449585
validation epoch 19, iteration 200, loss 0.1981516463279724
train epoch 19, iteration 250, loss -6.9785380363464355
train epoch 19, iteration 300, loss -6.908799171447754
validation epoch 19, iteration 300, loss 0.20339015607833863
train epoch 19, iteration 350, loss -6.903390407562256
train epoch 19, iteration 400, loss -7.104977607727051
validation epoch 19, iteration 400, loss 0.20135330810546875
train epoch 19, iteration 450, loss -7.08050537109375
train epoch 19, iteration 500, loss -6.9644622802734375
validation epoch 19, iteration 500, loss 0.19840303506851195
train epoch 19, iteration 550, loss -6.93333101272583