training_results_2.txt

batch_size 100, epochs 20, learning rate 5e-05, coeff kld 10.0, coeff kd
train epoch 0, iteration 0, loss -29.039718627929688
validation epoch 0, iteration 0, loss 2.3275520751953125
train epoch 0, iteration 50, loss -33.28472900390625
train epoch 0, iteration 100, loss -36.61419677734375
validation epoch 0, iteration 100, loss 1.6700791397094727
train epoch 0, iteration 150, loss -40.614742279052734
train epoch 0, iteration 200, loss -41.10204315185547
validation epoch 0, iteration 200, loss 1.1863704902648926
train epoch 0, iteration 250, loss -42.156005859375
train epoch 0, iteration 300, loss -44.42305374145508
validation epoch 0, iteration 300, loss 0.902183065032959
train epoch 0, iteration 350, loss -45.6060676574707
train epoch 0, iteration 400, loss -46.37647247314453
validation epoch 0, iteration 400, loss 0.7746402992248536
train epoch 0, iteration 450, loss -47.14263153076172
train epoch 0, iteration 500, loss -48.95524978637695
validation epoch 0, iteration 500, loss 0.6906402732849121
train epoch 0, iteration 550, loss -48.872520446777344
train epoch 1, iteration 0, loss -50.03925704956055
validation epoch 1, iteration 0, loss 0.6564342533111572
train epoch 1, iteration 50, loss -50.51865005493164
train epoch 1, iteration 100, loss -51.026451110839844
validation epoch 1, iteration 100, loss 0.6201973609924316
train epoch 1, iteration 150, loss -51.56855392456055
train epoch 1, iteration 200, loss -51.71886444091797
validation epoch 1, iteration 200, loss 0.5976101615905761
train epoch 1, iteration 250, loss -52.52827072143555
train epoch 1, iteration 300, loss -52.642967224121094
validation epoch 1, iteration 300, loss 0.5724206466674805
train epoch 1, iteration 350, loss -53.365272521972656
train epoch 1, iteration 400, loss -54.069190979003906
validation epoch 1, iteration 400, loss 0.557735290145874
train epoch 1, iteration 450, loss -54.294395446777344
train epoch 1, iteration 500, loss -55.113494873046875
validation epoch 1, iteration 500, loss 0.5445579235076904
train epoch 1, iteration 550, loss -55.47344970703125
train epoch 2, iteration 0, loss -55.558998107910156
validation epoch 2, iteration 0, loss 0.540273371887207
train epoch 2, iteration 50, loss -56.422786712646484
train epoch 2, iteration 100, loss -55.9769287109375
validation epoch 2, iteration 100, loss 0.5176151416778565
train epoch 2, iteration 150, loss -56.72385787963867
train epoch 2, iteration 200, loss -57.38581466674805
validation epoch 2, iteration 200, loss 0.5080976577758789
train epoch 2, iteration 250, loss -56.90837860107422
train epoch 2, iteration 300, loss -58.86956024169922
validation epoch 2, iteration 300, loss 0.49577931632995603
train epoch 2, iteration 350, loss -57.959651947021484
train epoch 2, iteration 400, loss -58.52008819580078
validation epoch 2, iteration 400, loss 0.48733782234191897
train epoch 2, iteration 450, loss -59.28629684448242
train epoch 2, iteration 500, loss -58.64875793457031
validation epoch 2, iteration 500, loss 0.4838860286712646
train epoch 2, iteration 550, loss -59.05296325683594
train epoch 3, iteration 0, loss -59.83729934692383
validation epoch 3, iteration 0, loss 0.46069240074157713
train epoch 3, iteration 50, loss -60.15956115722656
train epoch 3, iteration 100, loss -60.33870315551758
validation epoch 3, iteration 100, loss 0.45272079811096194
train epoch 3, iteration 150, loss -60.355323791503906
train epoch 3, iteration 200, loss -61.198455810546875
validation epoch 3, iteration 200, loss 0.4483846481323242
train epoch 3, iteration 250, loss -60.952781677246094
train epoch 3, iteration 300, loss -62.064762115478516
validation epoch 3, iteration 300, loss 0.44954725914001464
train epoch 3, iteration 350, loss -60.885311126708984
train epoch 3, iteration 400, loss -61.51742935180664
validation epoch 3, iteration 400, loss 0.4395431142807007
train epoch 3, iteration 450, loss -62.22098159790039
train epoch 3, iteration 500, loss -62.55570983886719
validation epoch 3, iteration 500, loss 0.4317232208251953
train epoch 3, iteration 550, loss -62.415348052978516
train epoch 4, iteration 0, loss -62.96910095214844
validation epoch 4, iteration 0, loss 0.4212305892944336
train epoch 4, iteration 50, loss -63.15620803833008
train epoch 4, iteration 100, loss -62.728878021240234
validation epoch 4, iteration 100, loss 0.41671694564819334
train epoch 4, iteration 150, loss -63.239112854003906
train epoch 4, iteration 200, loss -63.59419631958008
validation epoch 4, iteration 200, loss 0.4096402400970459
train epoch 4, iteration 250, loss -63.36222457885742
train epoch 4, iteration 300, loss -63.98875427246094
validation epoch 4, iteration 300, loss 0.4100170997619629
train epoch 4, iteration 350, loss -63.982147216796875
train epoch 4, iteration 400, loss -64.65872955322266
validation epoch 4, iteration 400, loss 0.3990028232574463
train epoch 4, iteration 450, loss -64.79833221435547
train epoch 4, iteration 500, loss -64.9539566040039
validation epoch 4, iteration 500, loss 0.3967505748748779
train epoch 4, iteration 550, loss -65.65756225585938
train epoch 5, iteration 0, loss -65.11632537841797
validation epoch 5, iteration 0, loss 0.39264954414367675
train epoch 5, iteration 50, loss -65.87782287597656
train epoch 5, iteration 100, loss -65.91278839111328
validation epoch 5, iteration 100, loss 0.3825026052474976
train epoch 5, iteration 150, loss -65.64688873291016
train epoch 5, iteration 200, loss -66.3297119140625
validation epoch 5, iteration 200, loss 0.3789698028564453
train epoch 5, iteration 250, loss -66.55262756347656
train epoch 5, iteration 300, loss -66.59317779541016
validation epoch 5, iteration 300, loss 0.3735303922653198
train epoch 5, iteration 350, loss -66.93162536621094
train epoch 5, iteration 400, loss -67.07599639892578
validation epoch 5, iteration 400, loss 0.37191442623138427
train epoch 5, iteration 450, loss -66.95763397216797
train epoch 5, iteration 500, loss -67.20275115966797
validation epoch 5, iteration 500, loss 0.3646418062210083
train epoch 5, iteration 550, loss -67.44876861572266
train epoch 6, iteration 0, loss -68.09638977050781
validation epoch 6, iteration 0, loss 0.3602829761505127
train epoch 6, iteration 50, loss -68.0323486328125
train epoch 6, iteration 100, loss -67.94241333007812
validation epoch 6, iteration 100, loss 0.3637443948745728
train epoch 6, iteration 150, loss -68.45247650146484
train epoch 6, iteration 200, loss -68.70459747314453
validation epoch 6, iteration 200, loss 0.36102605209350586
train epoch 6, iteration 250, loss -68.72627258300781
train epoch 6, iteration 300, loss -69.26770782470703
validation epoch 6, iteration 300, loss 0.35467066497802735
train epoch 6, iteration 350, loss -69.23076629638672
train epoch 6, iteration 400, loss -69.02735137939453
validation epoch 6, iteration 400, loss 0.3491843803405762
train epoch 6, iteration 450, loss -69.4421157836914
train epoch 6, iteration 500, loss -69.25975036621094
validation epoch 6, iteration 500, loss 0.3441500331878662
train epoch 6, iteration 550, loss -69.53943634033203
train epoch 7, iteration 0, loss -69.9249496459961
validation epoch 7, iteration 0, loss 0.3428260995864868
train epoch 7, iteration 50, loss -70.0068359375
train epoch 7, iteration 100, loss -69.9371337890625
validation epoch 7, iteration 100, loss 0.3393008237838745
train epoch 7, iteration 150, loss -69.95753479003906
train epoch 7, iteration 200, loss -70.27202606201172
validation epoch 7, iteration 200, loss 0.3420561256408691
train epoch 7, iteration 250, loss -70.60485076904297
train epoch 7, iteration 300, loss -70.47959899902344
validation epoch 7, iteration 300, loss 0.3362012716293335
train epoch 7, iteration 350, loss -71.29582977294922
train epoch 7, iteration 400, loss -70.42691040039062
validation epoch 7, iteration 400, loss 0.3336081741333008
train epoch 7, iteration 450, loss -71.22738647460938
train epoch 7, iteration 500, loss -71.65608978271484
validation epoch 7, iteration 500, loss 0.33002974014282227
train epoch 7, iteration 550, loss -71.15745544433594
train epoch 8, iteration 0, loss -71.36495971679688
validation epoch 8, iteration 0, loss 0.33303371906280516
train epoch 8, iteration 50, loss -71.28382873535156
train epoch 8, iteration 100, loss -71.86337280273438
validation epoch 8, iteration 100, loss 0.3335883029937744
train epoch 8, iteration 150, loss -71.82172393798828
train epoch 8, iteration 200, loss -72.50149536132812
validation epoch 8, iteration 200, loss 0.3297873764038086
train epoch 8, iteration 250, loss -71.89471435546875
train epoch 8, iteration 300, loss -72.14103698730469
validation epoch 8, iteration 300, loss 0.3256505170822144
train epoch 8, iteration 350, loss -72.0065689086914
train epoch 8, iteration 400, loss -72.19791412353516
validation epoch 8, iteration 400, loss 0.3264281671524048
train epoch 8, iteration 450, loss -72.39370727539062
train epoch 8, iteration 500, loss -73.04667663574219
validation epoch 8, iteration 500, loss 0.32209362087249754
train epoch 8, iteration 550, loss -73.14413452148438
train epoch 9, iteration 0, loss -73.07728576660156
validation epoch 9, iteration 0, loss 0.3236269947052002
train epoch 9, iteration 50, loss -72.92418670654297
train epoch 9, iteration 100, loss -73.1417007446289
validation epoch 9, iteration 100, loss 0.31760076694488526
train epoch 9, iteration 150, loss -73.52393341064453
train epoch 9, iteration 200, loss -73.22869873046875
validation epoch 9, iteration 200, loss 0.3133824188232422
train epoch 9, iteration 250, loss -73.72280883789062
train epoch 9, iteration 300, loss -73.94587707519531
validation epoch 9, iteration 300, loss 0.3134779972076416
train epoch 9, iteration 350, loss -73.0490951538086
train epoch 9, iteration 400, loss -73.9576187133789
validation epoch 9, iteration 400, loss 0.3129449544906616
train epoch 9, iteration 450, loss -74.46983337402344
train epoch 9, iteration 500, loss -73.88584899902344
validation epoch 9, iteration 500, loss 0.3115038974761963
train epoch 9, iteration 550, loss -74.5403823852539
train epoch 10, iteration 0, loss -74.367919921875
validation epoch 10, iteration 0, loss 0.3148034713745117
train epoch 10, iteration 50, loss -74.28993225097656
train epoch 10, iteration 100, loss -74.87057495117188
validation epoch 10, iteration 100, loss 0.30954333839416504
train epoch 10, iteration 150, loss -75.24705505371094
train epoch 10, iteration 200, loss -74.94634246826172
validation epoch 10, iteration 200, loss 0.3116119638442993
train epoch 10, iteration 250, loss -75.12537384033203
train epoch 10, iteration 300, loss -75.36888122558594
validation epoch 10, iteration 300, loss 0.303086961555481
train epoch 10, iteration 350, loss -75.22636413574219
train epoch 10, iteration 400, loss -75.45222473144531
validation epoch 10, iteration 400, loss 0.3049979614257812
train epoch 10, iteration 450, loss -75.7098617553711
train epoch 10, iteration 500, loss -75.54512786865234
validation epoch 10, iteration 500, loss 0.30336694831848143
train epoch 10, iteration 550, loss -75.71892547607422
train epoch 11, iteration 0, loss -75.74748992919922
validation epoch 11, iteration 0, loss 0.30248821239471435
train epoch 11, iteration 50, loss -76.4116439819336
train epoch 11, iteration 100, loss -75.88079071044922
validation epoch 11, iteration 100, loss 0.3032063594818115
train epoch 11, iteration 150, loss -76.30792236328125
train epoch 11, iteration 200, loss -76.26873779296875
validation epoch 11, iteration 200, loss 0.29573305892944335
train epoch 11, iteration 250, loss -76.52066040039062
train epoch 11, iteration 300, loss -76.22770690917969
validation epoch 11, iteration 300, loss 0.30277682609558104
train epoch 11, iteration 350, loss -77.06935119628906
train epoch 11, iteration 400, loss -76.9688491821289
validation epoch 11, iteration 400, loss 0.3041645679473877
train epoch 11, iteration 450, loss -76.36434936523438
train epoch 11, iteration 500, loss -77.01570129394531
validation epoch 11, iteration 500, loss 0.2996085065841675
train epoch 11, iteration 550, loss -76.86402893066406
train epoch 12, iteration 0, loss -77.49440002441406
validation epoch 12, iteration 0, loss 0.29424144134521485
train epoch 12, iteration 50, loss -77.40958404541016
train epoch 12, iteration 100, loss -76.97518157958984
validation epoch 12, iteration 100, loss 0.2942125764846802
train epoch 12, iteration 150, loss -77.44261932373047
train epoch 12, iteration 200, loss -77.8096694946289
validation epoch 12, iteration 200, loss 0.2963070446014404
train epoch 12, iteration 250, loss -77.47932434082031
train epoch 12, iteration 300, loss -78.04558563232422
validation epoch 12, iteration 300, loss 0.2998527105331421
train epoch 12, iteration 350, loss -78.0377197265625
train epoch 12, iteration 400, loss -77.63651275634766
validation epoch 12, iteration 400, loss 0.2973513936042786
train epoch 12, iteration 450, loss -78.16268157958984
train epoch 12, iteration 500, loss -78.4801254272461
validation epoch 12, iteration 500, loss 0.2908968879699707
train epoch 12, iteration 550, loss -78.21820831298828
train epoch 13, iteration 0, loss -78.07762908935547
validation epoch 13, iteration 0, loss 0.29154749221801757
train epoch 13, iteration 50, loss -78.55082702636719
train epoch 13, iteration 100, loss -78.40005493164062
validation epoch 13, iteration 100, loss 0.29101698303222656
train epoch 13, iteration 150, loss -78.75640869140625
train epoch 13, iteration 200, loss -78.75433349609375
validation epoch 13, iteration 200, loss 0.2908977481842041
train epoch 13, iteration 250, loss -78.21884155273438
train epoch 13, iteration 300, loss -78.82921600341797
validation epoch 13, iteration 300, loss 0.2948525510787964
train epoch 13, iteration 350, loss -78.7391586303711
train epoch 13, iteration 400, loss -79.04946899414062
validation epoch 13, iteration 400, loss 0.2883228748321533
train epoch 13, iteration 450, loss -78.67616271972656
train epoch 13, iteration 500, loss -79.17381286621094
validation epoch 13, iteration 500, loss 0.2942079116821289
train epoch 13, iteration 550, loss -79.1607666015625
train epoch 14, iteration 0, loss -79.32266998291016
validation epoch 14, iteration 0, loss 0.28735710887908933
train epoch 14, iteration 50, loss -79.37100219726562
train epoch 14, iteration 100, loss -79.58113861083984
validation epoch 14, iteration 100, loss 0.2851725044250488
train epoch 14, iteration 150, loss -79.656982421875
train epoch 14, iteration 200, loss -79.93302154541016
validation epoch 14, iteration 200, loss 0.2875028560638428
train epoch 14, iteration 250, loss -79.3353271484375
train epoch 14, iteration 300, loss -79.89585876464844
validation epoch 14, iteration 300, loss 0.2877085023880005
train epoch 14, iteration 350, loss -79.65546417236328
train epoch 14, iteration 400, loss -80.02029418945312
validation epoch 14, iteration 400, loss 0.2790762107849121
train epoch 14, iteration 450, loss -79.63980102539062
train epoch 14, iteration 500, loss -79.77854919433594
validation epoch 14, iteration 500, loss 0.2836779903411865
train epoch 14, iteration 550, loss -79.92090606689453
train epoch 15, iteration 0, loss -79.91327667236328
validation epoch 15, iteration 0, loss 0.27921123600006104
train epoch 15, iteration 50, loss -80.25481414794922
train epoch 15, iteration 100, loss -80.40357208251953
validation epoch 15, iteration 100, loss 0.28051226387023925
train epoch 15, iteration 150, loss -80.23179626464844
train epoch 15, iteration 200, loss -80.45762634277344
validation epoch 15, iteration 200, loss 0.28041059799194334
train epoch 15, iteration 250, loss -80.73342895507812
train epoch 15, iteration 300, loss -80.38780975341797
validation epoch 15, iteration 300, loss 0.2798736072540283
train epoch 15, iteration 350, loss -80.46482849121094
train epoch 15, iteration 400, loss -80.62101745605469
validation epoch 15, iteration 400, loss 0.282552885055542
train epoch 15, iteration 450, loss -80.05806732177734
train epoch 15, iteration 500, loss -80.8329849243164
validation epoch 15, iteration 500, loss 0.2791264246940613
train epoch 15, iteration 550, loss -80.57636260986328
train epoch 16, iteration 0, loss -80.46138000488281
validation epoch 16, iteration 0, loss 0.28366797008514405
train epoch 16, iteration 50, loss -81.15791320800781
train epoch 16, iteration 100, loss -80.84580993652344
validation epoch 16, iteration 100, loss 0.27812068176269533
train epoch 16, iteration 150, loss -80.888671875
train epoch 16, iteration 200, loss -80.90155029296875
validation epoch 16, iteration 200, loss 0.28147929916381836
train epoch 16, iteration 250, loss -81.2659683227539
train epoch 16, iteration 300, loss -80.99457550048828
validation epoch 16, iteration 300, loss 0.2818575811386108
train epoch 16, iteration 350, loss -80.6457748413086
train epoch 16, iteration 400, loss -81.23025512695312
validation epoch 16, iteration 400, loss 0.2819396459579468
train epoch 16, iteration 450, loss -81.08196258544922
train epoch 16, iteration 500, loss -81.32498931884766
validation epoch 16, iteration 500, loss 0.2744912084579468
train epoch 16, iteration 550, loss -81.62141418457031
train epoch 17, iteration 0, loss -81.41429138183594
validation epoch 17, iteration 0, loss 0.2759786992073059
train epoch 17, iteration 50, loss -81.3111572265625
train epoch 17, iteration 100, loss -81.3995132446289
validation epoch 17, iteration 100, loss 0.2767674850463867
train epoch 17, iteration 150, loss -81.70758056640625
train epoch 17, iteration 200, loss -81.67986297607422
validation epoch 17, iteration 200, loss 0.282815531539917
train epoch 17, iteration 250, loss -81.71780395507812
train epoch 17, iteration 300, loss -81.86424255371094
validation epoch 17, iteration 300, loss 0.2746976474761963
train epoch 17, iteration 350, loss -82.11662292480469
train epoch 17, iteration 400, loss -81.88111877441406
validation epoch 17, iteration 400, loss 0.2778561908721924
train epoch 17, iteration 450, loss -81.6761245727539
train epoch 17, iteration 500, loss -81.67705535888672
validation epoch 17, iteration 500, loss 0.27827129526138306
train epoch 17, iteration 550, loss -82.22111511230469
train epoch 18, iteration 0, loss -81.69242095947266
validation epoch 18, iteration 0, loss 0.2872662517547607
train epoch 18, iteration 50, loss -81.95159149169922
train epoch 18, iteration 100, loss -81.73448181152344
validation epoch 18, iteration 100, loss 0.2745142427444458
train epoch 18, iteration 150, loss -81.52478790283203
train epoch 18, iteration 200, loss -82.09646606445312
validation epoch 18, iteration 200, loss 0.2783947416305542
train epoch 18, iteration 250, loss -82.28756713867188
train epoch 18, iteration 300, loss -82.17082214355469
validation epoch 18, iteration 300, loss 0.27671960830688475
train epoch 18, iteration 350, loss -82.35209655761719
train epoch 18, iteration 400, loss -82.45249938964844
validation epoch 18, iteration 400, loss 0.2796595287322998
train epoch 18, iteration 450, loss -82.32691955566406
train epoch 18, iteration 500, loss -82.25640106201172
validation epoch 18, iteration 500, loss 0.27578485927581786
train epoch 18, iteration 550, loss -82.02395629882812
train epoch 19, iteration 0, loss -82.81449127197266
validation epoch 19, iteration 0, loss 0.2709491580963135
train epoch 19, iteration 50, loss -82.41424560546875
train epoch 19, iteration 100, loss -82.73214721679688
validation epoch 19, iteration 100, loss 0.2745610605239868
train epoch 19, iteration 150, loss -82.4301986694336
train epoch 19, iteration 200, loss -82.34114837646484
validation epoch 19, iteration 200, loss 0.27448534288406373
train epoch 19, iteration 250, loss -82.51254272460938
train epoch 19, iteration 300, loss -82.53854370117188
validation epoch 19, iteration 300, loss 0.2756910329818726
train epoch 19, iteration 350, loss -82.5135498046875
train epoch 19, iteration 400, loss -82.91426086425781
validation epoch 19, iteration 400, loss 0.2737843994140625
train epoch 19, iteration 450, loss -82.8497543334961
train epoch 19, iteration 500, loss -83.02447509765625
validation epoch 19, iteration 500, loss 0.27024597511291504
train epoch 19, iteration 550, loss -82.88203430175781