['--alg', 'sac', '--env', 'Walker2d-v3', '--learn', 'uncertainty', '--traj', 'medium', '--seed', '3', '--data', '100000']
epoch: 0 training_loss 0.24173547089099884 test_loss: 0.17247169017791747
epoch: 1 training_loss 0.14577460885047913 test_loss: 0.12993587255477906
epoch: 2 training_loss 0.13448570989072323 test_loss: 0.1460545301437378
epoch: 3 training_loss 0.1295401579886675 test_loss: 0.11885408163070679
epoch: 4 training_loss 0.11639991763979196 test_loss: 0.131455397605896
epoch: 5 training_loss 0.1106276373565197 test_loss: 0.12483812570571899
epoch: 6 training_loss 0.11216772144660353 test_loss: 0.11967235803604126
epoch: 7 training_loss 0.10036535389721393 test_loss: 0.12743968963623048
epoch: 8 training_loss 0.10623730566352606 test_loss: 0.118026602268219
epoch: 9 training_loss 0.10098330218344927 test_loss: 0.11986901760101318
epoch: 10 training_loss 0.11408984553068877 test_loss: 0.1103630542755127
epoch: 11 training_loss 0.10087819557636976 test_loss: 0.10098289251327515
epoch: 12 training_loss 0.0986698181554675 test_loss: 0.13144433498382568
epoch: 13 training_loss 0.09929644946008921 test_loss: 0.12219785451889038
epoch: 14 training_loss 0.09957389730960131 test_loss: 0.11067303419113159
epoch: 15 training_loss 0.09947897337377071 test_loss: 0.11809390783309937
epoch: 16 training_loss 0.09984175262972712 test_loss: 0.10510852336883544
epoch: 17 training_loss 0.10150801353156566 test_loss: 0.10311481952667237
epoch: 18 training_loss 0.0967906379327178 test_loss: 0.10384255647659302
epoch: 19 training_loss 0.09591002281755209 test_loss: 0.10641413927078247
epoch: 20 training_loss 0.0951675046980381 test_loss: 0.11363487243652344
epoch: 21 training_loss 0.0941238059476018 test_loss: 0.11523077487945557
epoch: 22 training_loss 0.0971476805023849 test_loss: 0.1047478437423706
epoch: 23 training_loss 0.08570833017118275 test_loss: 0.10623334646224976
epoch: 24 training_loss 0.1025708862580359 test_loss: 0.09922090172767639
epoch: 25 training_loss 0.09209842026233674 test_loss: 0.11212824583053589
epoch: 26 training_loss 0.09214434865862131 test_loss: 0.10035659074783325
epoch: 27 training_loss 0.09780602077022195 test_loss: 0.0989646077156067
epoch: 28 training_loss 0.09457693476229906 test_loss: 0.10852571725845336
epoch: 29 training_loss 0.09755751754157245 test_loss: 0.09540528655052186
epoch: 30 training_loss 0.09148298071697354 test_loss: 0.10429805517196655
epoch: 31 training_loss 0.09252712013199925 test_loss: 0.10916706323623657
epoch: 32 training_loss 0.08719713313505054 test_loss: 0.10664457082748413
epoch: 33 training_loss 0.09609488740563393 test_loss: 0.10475070476531982
epoch: 34 training_loss 0.09171382626518607 test_loss: 0.11538912057876587
epoch: 35 training_loss 0.0882381546497345 test_loss: 0.11483235359191894
epoch: 36 training_loss 0.09165760209783912 test_loss: 0.0795220673084259
epoch: 37 training_loss 0.0933082919754088 test_loss: 0.10213261842727661
epoch: 38 training_loss 0.09329210758209229 test_loss: 0.12153413295745849
epoch: 39 training_loss 0.09464491710066796 test_loss: 0.10013532638549805
epoch: 40 training_loss 0.09063877813518047 test_loss: 0.09815832376480102
epoch: 41 training_loss 0.0912913098745048 test_loss: 0.11025081872940064
epoch: 42 training_loss 0.09144981004297734 test_loss: 0.09754413366317749
epoch: 43 training_loss 0.09753216613084077 test_loss: 0.10335861444473267
epoch: 44 training_loss 0.0835960253700614 test_loss: 0.13141511678695678
epoch: 45 training_loss 0.09006506063044072 test_loss: 0.10136760473251342
epoch: 46 training_loss 0.08952691627666354 test_loss: 0.10586854219436645
epoch: 47 training_loss 0.09241501757875085 test_loss: 0.10314433574676514
epoch: 48 training_loss 0.08994835672900081 test_loss: 0.09630442857742309
epoch: 49 training_loss 0.08869579942896962 test_loss: 0.1037756323814392
epoch: 50 training_loss 0.08548711815848947 test_loss: 0.0945429265499115
epoch: 51 training_loss 0.08677179424092174 test_loss: 0.08571400642395019
epoch: 52 training_loss 0.09628328235819936 test_loss: 0.11112010478973389
epoch: 53 training_loss 0.08915863806381821 test_loss: 0.11477912664413452
epoch: 54 training_loss 0.08686163486912847 test_loss: 0.10026957988739013
epoch: 55 training_loss 0.09038371346890926 test_loss: 0.10764174461364746
epoch: 56 training_loss 0.09457509396597744 test_loss: 0.10930217504501342
epoch: 57 training_loss 0.09217283327132464 test_loss: 0.1048453688621521
epoch: 58 training_loss 0.09586090357974171 test_loss: 0.10407140254974365
epoch: 59 training_loss 0.08830428417772054 test_loss: 0.09757165908813477
epoch: 60 training_loss 0.08548619191162288 test_loss: 0.10377706289291382
epoch: 61 training_loss 0.0909120461717248 test_loss: 0.09910305142402649
epoch: 62 training_loss 0.0910307286772877 test_loss: 0.08963078260421753
epoch: 63 training_loss 0.09162900941446424 test_loss: 0.10555578470230102
epoch: 64 training_loss 0.08169218009337782 test_loss: 0.0948430836200714
epoch: 65 training_loss 0.08552630327641964 test_loss: 0.10938034057617188
epoch: 66 training_loss 0.09557842498645186 test_loss: 0.08824233412742614
epoch: 67 training_loss 0.08560652397572995 test_loss: 0.11356836557388306
epoch: 68 training_loss 0.0887597637437284 test_loss: 0.09339425563812256
epoch: 69 training_loss 0.08602876074612141 test_loss: 0.09831414818763733
epoch: 70 training_loss 0.09193494534119964 test_loss: 0.0876676857471466
epoch: 71 training_loss 0.08780546123161911 test_loss: 0.10449895858764649
epoch: 72 training_loss 0.08585010254755616 test_loss: 0.11148266792297364
epoch: 73 training_loss 0.08927626321092248 test_loss: 0.09789770245552062
epoch: 74 training_loss 0.08274088434875011 test_loss: 0.10307779312133789
epoch: 75 training_loss 0.08654496286064386 test_loss: 0.10275841951370239
epoch: 76 training_loss 0.08234064197167754 test_loss: 0.09559653997421265
epoch: 77 training_loss 0.08916101375594736 test_loss: 0.11360694169998169
epoch: 78 training_loss 0.08395662272349 test_loss: 0.09514106512069702
epoch: 79 training_loss 0.0910136947967112 test_loss: 0.09422361254692077
epoch: 80 training_loss 0.08477027861401439 test_loss: 0.10894188880920411
epoch: 81 training_loss 0.08832282189279794 test_loss: 0.09893435835838318
epoch: 82 training_loss 0.08909132357686758 test_loss: 0.11292902231216431
epoch: 83 training_loss 0.08173364343121647 test_loss: 0.09884430766105652
epoch: 84 training_loss 0.08441305024549366 test_loss: 0.09823054671287537
epoch: 85 training_loss 0.08641711384057998 test_loss: 0.09404167532920837
epoch: 86 training_loss 0.08482655090279877 test_loss: 0.10413268804550171
epoch: 87 training_loss 0.08355844559147954 test_loss: 0.1010677695274353
epoch: 88 training_loss 0.07950877036899329 test_loss: 0.10078921318054199
epoch: 89 training_loss 0.08367731666192413 test_loss: 0.10453802347183228
epoch: 90 training_loss 0.07955653328448534 test_loss: 0.08770804405212403
epoch: 91 training_loss 0.08712929544970394 test_loss: 0.11100201606750489
epoch: 92 training_loss 0.08877048825845123 test_loss: 0.09798740148544312
epoch: 93 training_loss 0.08152872394770384 test_loss: 0.09635279178619385
epoch: 94 training_loss 0.07668985935859382 test_loss: 0.090387362241745
epoch: 95 training_loss 0.08775203114375472 test_loss: 0.08739348649978637
epoch: 96 training_loss 0.08173026636242867 test_loss: 0.09512589573860168
epoch: 97 training_loss 0.08173356506973505 test_loss: 0.10296754837036133
epoch: 98 training_loss 0.08141209566965699 test_loss: 0.08908558487892151
epoch: 99 training_loss 0.08065756851807236 test_loss: 0.10496517419815063
epoch: 100 training_loss 0.08428439335897565 test_loss: 0.10821568965911865
epoch: 101 training_loss 0.07762663062661886 test_loss: 0.1091051459312439
epoch: 102 training_loss 0.08216948360204697 test_loss: 0.11241097450256347
epoch: 103 training_loss 0.0838483532704413 test_loss: 0.10129486322402954
epoch: 104 training_loss 0.07761928580701351 test_loss: 0.11029249429702759
epoch: 105 training_loss 0.0902695669978857 test_loss: 0.10197972059249878
epoch: 106 training_loss 0.08423364330083132 test_loss: 0.09806908965110779
epoch: 107 training_loss 0.08485256545245648 test_loss: 0.12273070812225342
epoch: 108 training_loss 0.08710940456017852 test_loss: 0.10766198635101318
epoch: 109 training_loss 0.08002845602110029 test_loss: 0.10174785852432251
epoch: 110 training_loss 0.08540974713861943 test_loss: 0.11762039661407471
epoch: 111 training_loss 0.08289323003962636 test_loss: 0.10403590202331543
epoch: 112 training_loss 0.07778006514534354 test_loss: 0.10079303979873658
epoch: 113 training_loss 0.08380297215655447 test_loss: 0.10582133531570434
epoch: 114 training_loss 0.07693967666476965 test_loss: 0.10535972118377686
epoch: 115 training_loss 0.08399096870794892 test_loss: 0.12296602725982667
epoch: 116 training_loss 0.08155689805746079 test_loss: 0.1033827543258667
epoch: 117 training_loss 0.08799817087128758 test_loss: 0.10665171146392823
epoch: 118 training_loss 0.08792376305907965 test_loss: 0.0965920329093933
epoch: 119 training_loss 0.07928178396075963 test_loss: 0.12130174636840821
epoch: 120 training_loss 0.07732833471149206 test_loss: 0.10375877618789672
epoch: 121 training_loss 0.08665488643571734 test_loss: 0.09095693230628968
epoch: 122 training_loss 0.07857414534315467 test_loss: 0.1017344355583191
epoch: 123 training_loss 0.08528606398031116 test_loss: 0.1057352066040039
epoch: 124 training_loss 0.0790626223012805 test_loss: 0.11344761848449707
epoch: 125 training_loss 0.08571491841226817 test_loss: 0.09160006642341614
epoch: 126 training_loss 0.08783228203654289 test_loss: 0.11174131631851196
epoch: 127 training_loss 0.07732821114361287 test_loss: 0.11287513971328736
epoch: 128 training_loss 0.08714235408231616 test_loss: 0.1106576919555664
epoch: 129 training_loss 0.07970612067729235 test_loss: 0.10965200662612914
epoch: 130 training_loss 0.08422860657796263 test_loss: 0.09984910488128662
epoch: 131 training_loss 0.0797842064127326 test_loss: 0.102615487575531
epoch: 132 training_loss 0.07551908755674958 test_loss: 0.10518039464950561
epoch: 133 training_loss 0.08088404472917318 test_loss: 0.09901354908943176
epoch: 134 training_loss 0.08803906746208667 test_loss: 0.10539814233779907
epoch: 135 training_loss 0.07847838612273335 test_loss: 0.11436474323272705
epoch: 136 training_loss 0.07559698844328523 test_loss: 0.10104727745056152
epoch: 137 training_loss 0.07715785773470998 test_loss: 0.08003706932067871
epoch: 138 training_loss 0.08427915688604116 test_loss: 0.1021493911743164
epoch: 139 training_loss 0.07920179054141045 test_loss: 0.10028953552246093
epoch: 140 training_loss 0.07509862395003437 test_loss: 0.0985608696937561
epoch: 141 training_loss 0.07796753090806305 test_loss: 0.10045647621154785
epoch: 142 training_loss 0.07542950233444572 test_loss: 0.11416587829589844
epoch: 143 training_loss 0.07571068636141717 test_loss: 0.10750890970230102
epoch: 144 training_loss 0.08086686480790377 test_loss: 0.11786137819290161
epoch: 145 training_loss 0.07431301962584257 test_loss: 0.12065238952636718
epoch: 146 training_loss 0.08452272012829781 test_loss: 0.10493284463882446
epoch: 147 training_loss 0.08310246303677558 test_loss: 0.09575675129890442
epoch: 148 training_loss 0.07947101702913642 test_loss: 0.11135050058364868
epoch: 149 training_loss 0.08199661783874035 test_loss: 0.109848153591156
epoch: 0 training_loss 0.26003191612660886 test_loss: 0.17093464136123657
epoch: 1 training_loss 0.16021871395409107 test_loss: 0.1350720167160034
epoch: 2 training_loss 0.14136963739991187 test_loss: 0.12186477184295655
epoch: 3 training_loss 0.12102280497550964 test_loss: 0.1285787582397461
epoch: 4 training_loss 0.12661163568496703 test_loss: 0.17416293621063234
epoch: 5 training_loss 0.11677444066852331 test_loss: 0.10917940139770507
epoch: 6 training_loss 0.12057915955781937 test_loss: 0.10995830297470092
epoch: 7 training_loss 0.10837556883692741 test_loss: 0.12036432027816772
epoch: 8 training_loss 0.10335005218163133 test_loss: 0.10919315814971924
epoch: 9 training_loss 0.10963235601782799 test_loss: 0.10400047302246093
epoch: 10 training_loss 0.10815437622368336 test_loss: 0.10531293153762818
epoch: 11 training_loss 0.10474618446081876 test_loss: 0.1612326979637146
epoch: 12 training_loss 0.10004374535754323 test_loss: 0.12358764410018921
epoch: 13 training_loss 0.10200276613235473 test_loss: 0.09344818592071533
epoch: 14 training_loss 0.1001698388159275 test_loss: 0.0998809278011322
epoch: 15 training_loss 0.11098705096170307 test_loss: 0.09457359313964844
epoch: 16 training_loss 0.09419466853141785 test_loss: 0.10878159999847412
epoch: 17 training_loss 0.09380691591650248 test_loss: 0.10331050157546998
epoch: 18 training_loss 0.09060870513319969 test_loss: 0.09216873049736023
epoch: 19 training_loss 0.09747873654589057 test_loss: 0.10603985786437989
epoch: 20 training_loss 0.0977854530699551 test_loss: 0.0929934561252594
epoch: 21 training_loss 0.09038531663827598 test_loss: 0.11574758291244507
epoch: 22 training_loss 0.09328741924837232 test_loss: 0.09175968170166016
epoch: 23 training_loss 0.0903579712100327 test_loss: 0.09240370988845825
epoch: 24 training_loss 0.09507134065032005 test_loss: 0.09593364000320434
epoch: 25 training_loss 0.09713439093902707 test_loss: 0.10478531122207642
epoch: 26 training_loss 0.09705917716026306 test_loss: 0.10125982761383057
epoch: 27 training_loss 0.09186201522126794 test_loss: 0.10401833057403564
epoch: 28 training_loss 0.08772810250520706 test_loss: 0.0936747670173645
epoch: 29 training_loss 0.0892667474411428 test_loss: 0.09780153036117553
epoch: 30 training_loss 0.08975619627162815 test_loss: 0.08861619830131531
epoch: 31 training_loss 0.08973112735897303 test_loss: 0.09298418164253235
epoch: 32 training_loss 0.08898294184356928 test_loss: 0.07677052617073059
epoch: 33 training_loss 0.08932051112875343 test_loss: 0.09375861883163453
epoch: 34 training_loss 0.08808510622009635 test_loss: 0.11064826250076294
epoch: 35 training_loss 0.08498905977234245 test_loss: 0.09788824915885926
epoch: 36 training_loss 0.0857773520424962 test_loss: 0.08836244940757751
epoch: 37 training_loss 0.08576060179620981 test_loss: 0.10227911472320557
epoch: 38 training_loss 0.08752299858257175 test_loss: 0.09973542094230652
epoch: 39 training_loss 0.08594992084428668 test_loss: 0.10083931684494019
epoch: 40 training_loss 0.08771585144102573 test_loss: 0.09575457572937011
epoch: 41 training_loss 0.09253911204636096 test_loss: 0.09477139115333558
epoch: 42 training_loss 0.08544498551636934 test_loss: 0.11015926599502564
epoch: 43 training_loss 0.08779665625654161 test_loss: 0.09657450914382934
epoch: 44 training_loss 0.08854921036399901 test_loss: 0.10021626949310303
epoch: 45 training_loss 0.0939751511067152 test_loss: 0.09812408089637756
epoch: 46 training_loss 0.0857402130868286 test_loss: 0.0940909206867218
epoch: 47 training_loss 0.08654669936746359 test_loss: 0.10928781032562256
epoch: 48 training_loss 0.08431332007050514 test_loss: 0.08636722564697266
epoch: 49 training_loss 0.08989127503708005 test_loss: 0.08685868382453918
epoch: 50 training_loss 0.08199142158031464 test_loss: 0.08579680323600769
epoch: 51 training_loss 0.08569171909242869 test_loss: 0.09315690398216248
epoch: 52 training_loss 0.08872050942853094 test_loss: 0.10668889284133912
epoch: 53 training_loss 0.09285371841862798 test_loss: 0.09404445886611938
epoch: 54 training_loss 0.09358134984970093 test_loss: 0.09834325909614564
epoch: 55 training_loss 0.09695104129612446 test_loss: 0.08122819662094116
epoch: 56 training_loss 0.09503461964428425 test_loss: 0.09546395540237426
epoch: 57 training_loss 0.087080347109586 test_loss: 0.0914099395275116
epoch: 58 training_loss 0.09252826100215315 test_loss: 0.09085335731506347
epoch: 59 training_loss 0.08675675049424171 test_loss: 0.08970122337341309
epoch: 60 training_loss 0.08116033855825662 test_loss: 0.09131717681884766
epoch: 61 training_loss 0.08914453415200115 test_loss: 0.10582995414733887
epoch: 62 training_loss 0.08523982565850019 test_loss: 0.0950569748878479
epoch: 63 training_loss 0.08655677769333124 test_loss: 0.08591977953910827
epoch: 64 training_loss 0.08905515085905791 test_loss: 0.11032055616378784
epoch: 65 training_loss 0.08813575701788068 test_loss: 0.09061576128005981
epoch: 66 training_loss 0.08592982472851872 test_loss: 0.0893087387084961
epoch: 67 training_loss 0.08552584057673812 test_loss: 0.0862808108329773
epoch: 68 training_loss 0.08557959623634816 test_loss: 0.10104248523712159
epoch: 69 training_loss 0.0908046606555581 test_loss: 0.0899661660194397
epoch: 70 training_loss 0.08513869967311621 test_loss: 0.09036929607391357
epoch: 71 training_loss 0.08109668267890811 test_loss: 0.09924925565719604
epoch: 72 training_loss 0.08265833096578717 test_loss: 0.089405757188797
epoch: 73 training_loss 0.08282713778316975 test_loss: 0.08133849501609802
epoch: 74 training_loss 0.08098983287811279 test_loss: 0.09967131614685058
epoch: 75 training_loss 0.07961224034428596 test_loss: 0.09991504549980164
epoch: 76 training_loss 0.0839172506891191 test_loss: 0.10831223726272583
epoch: 77 training_loss 0.07885176497511566 test_loss: 0.1005982756614685
epoch: 78 training_loss 0.08860653316602111 test_loss: 0.08141599893569947
epoch: 79 training_loss 0.0852948104403913 test_loss: 0.09780075550079345
epoch: 80 training_loss 0.07977406492456794 test_loss: 0.11176407337188721
epoch: 81 training_loss 0.08179962458088993 test_loss: 0.0932938039302826
epoch: 82 training_loss 0.07583514118567108 test_loss: 0.09238945245742798
epoch: 83 training_loss 0.0869736048951745 test_loss: 0.09032831788063049
epoch: 84 training_loss 0.08170315202325583 test_loss: 0.10743318796157837
epoch: 85 training_loss 0.08867877075448632 test_loss: 0.0961880624294281
epoch: 86 training_loss 0.08776051115244626 test_loss: 0.09837104678153992
epoch: 87 training_loss 0.08752140240743757 test_loss: 0.082234126329422
epoch: 88 training_loss 0.09633542954921723 test_loss: 0.10800520181655884
epoch: 89 training_loss 0.08055209214799106 test_loss: 0.09582276940345764
epoch: 90 training_loss 0.08584090379998088 test_loss: 0.0936560571193695
epoch: 91 training_loss 0.08760846046730876 test_loss: 0.09403692483901978
epoch: 92 training_loss 0.08282926058396697 test_loss: 0.09436101913452148
epoch: 93 training_loss 0.08062483010813594 test_loss: 0.0964664340019226
epoch: 94 training_loss 0.07392691276036203 test_loss: 0.10247522592544556
epoch: 95 training_loss 0.08384118804708124 test_loss: 0.08449340462684632
epoch: 96 training_loss 0.0792647123336792 test_loss: 0.07720565795898438
epoch: 97 training_loss 0.08432868020609022 test_loss: 0.07165636420249939
epoch: 98 training_loss 0.08141251420602202 test_loss: 0.0864534318447113
epoch: 99 training_loss 0.07624425480142236 test_loss: 0.09834172129631043
epoch: 100 training_loss 0.08734510043635964 test_loss: 0.09286367893218994
epoch: 101 training_loss 0.07823497250676155 test_loss: 0.09353126883506775
epoch: 102 training_loss 0.0760096051543951 test_loss: 0.09236685037612916
epoch: 103 training_loss 0.07977028189226985 test_loss: 0.09318921566009522
epoch: 104 training_loss 0.07917522566393018 test_loss: 0.08560121059417725
epoch: 105 training_loss 0.08295417742803693 test_loss: 0.11190069913864135
epoch: 106 training_loss 0.07726453425362706 test_loss: 0.09158128499984741
epoch: 107 training_loss 0.07968379067257046 test_loss: 0.09962939620018005
epoch: 108 training_loss 0.07736462669447064 test_loss: 0.08785701990127563
epoch: 109 training_loss 0.08316166887059807 test_loss: 0.09457143545150756
epoch: 110 training_loss 0.07723318681120872 test_loss: 0.09104802012443543
epoch: 111 training_loss 0.07844596834853292 test_loss: 0.0954826831817627
epoch: 112 training_loss 0.07924969205632806 test_loss: 0.0910409927368164
epoch: 113 training_loss 0.07661902099847794 test_loss: 0.09730475544929504
epoch: 114 training_loss 0.08126366125419736 test_loss: 0.09018048644065857
epoch: 115 training_loss 0.08661063106730581 test_loss: 0.09462581276893615
epoch: 116 training_loss 0.08001202572137117 test_loss: 0.09640256762504577
epoch: 117 training_loss 0.08043556824326516 test_loss: 0.0883588433265686
epoch: 118 training_loss 0.07236257369630039 test_loss: 0.07760248184204102
epoch: 119 training_loss 0.07562899792566896 test_loss: 0.09487217664718628
epoch: 120 training_loss 0.08172839749604463 test_loss: 0.10338137149810792
epoch: 121 training_loss 0.078610964352265 test_loss: 0.08795040845870972
epoch: 122 training_loss 0.07605602124705911 test_loss: 0.09734233021736145
epoch: 123 training_loss 0.07954685755074024 test_loss: 0.09240587949752807
epoch: 124 training_loss 0.0791661848500371 test_loss: 0.101260507106781
epoch: 125 training_loss 0.08384571548551321 test_loss: 0.0823593258857727
epoch: 126 training_loss 0.07595549004152417 test_loss: 0.08785326480865478
epoch: 127 training_loss 0.08259463125839829 test_loss: 0.09896241426467896
epoch: 128 training_loss 0.07870190795511008 test_loss: 0.09898272156715393
epoch: 129 training_loss 0.08150928661227226 test_loss: 0.09191057085990906
epoch: 130 training_loss 0.08007298745214939 test_loss: 0.08742655515670776
epoch: 131 training_loss 0.07868574574589729 test_loss: 0.09522473812103271
epoch: 132 training_loss 0.0796526894904673 test_loss: 0.10516560077667236
epoch: 133 training_loss 0.0765719746798277 test_loss: 0.09637977480888367
epoch: 134 training_loss 0.07541463549248874 test_loss: 0.09719989895820617
epoch: 135 training_loss 0.07735758373513818 test_loss: 0.09983534812927246
epoch: 136 training_loss 0.0814229379594326 test_loss: 0.0859022319316864
epoch: 137 training_loss 0.0760227813012898 test_loss: 0.08492323756217957
epoch: 138 training_loss 0.07552150182425976 test_loss: 0.09156384468078613
epoch: 139 training_loss 0.07985680058598518 test_loss: 0.09696188569068909
epoch: 140 training_loss 0.07396354462951421 test_loss: 0.10408694744110107
epoch: 141 training_loss 0.07715143091976642 test_loss: 0.08621534705162048
epoch: 142 training_loss 0.07933367379009723 test_loss: 0.09418113827705384
epoch: 143 training_loss 0.07836798192933202 test_loss: 0.0961345076560974
epoch: 144 training_loss 0.08004622325301171 test_loss: 0.09011622667312622
epoch: 145 training_loss 0.07415565107949078 test_loss: 0.08576334118843079
epoch: 146 training_loss 0.08266936235129833 test_loss: 0.1063309907913208
epoch: 147 training_loss 0.07427665632218122 test_loss: 0.09598935246467591
epoch: 148 training_loss 0.07239516380243004 test_loss: 0.09747557044029236
epoch: 149 training_loss 0.07409123109653593 test_loss: 0.08066856861114502
epoch: 0 training_loss 0.2733984161168337 test_loss: 0.19021884202957154
epoch: 1 training_loss 0.14805913638323545 test_loss: 0.15825085639953612
epoch: 2 training_loss 0.13295962501317263 test_loss: 0.14267774820327758
epoch: 3 training_loss 0.12854245971888303 test_loss: 0.13429073095321656
epoch: 4 training_loss 0.1137619898095727 test_loss: 0.12459603548049927
epoch: 5 training_loss 0.11232535760849714 test_loss: 0.13541072607040405
epoch: 6 training_loss 0.11265553172677756 test_loss: 0.10791563987731934
epoch: 7 training_loss 0.10775914944708348 test_loss: 0.1074021577835083
epoch: 8 training_loss 0.10415089385583996 test_loss: 0.0939712643623352
epoch: 9 training_loss 0.10535055365413427 test_loss: 0.10755196809768677
epoch: 10 training_loss 0.10551795683801174 test_loss: 0.1154211401939392
epoch: 11 training_loss 0.10213043287396431 test_loss: 0.09732741713523865
epoch: 12 training_loss 0.1107603975944221 test_loss: 0.11307048797607422
epoch: 13 training_loss 0.09627768553793431 test_loss: 0.08942942023277282
epoch: 14 training_loss 0.09493725327774882 test_loss: 0.11537290811538696
epoch: 15 training_loss 0.09837682284414768 test_loss: 0.09561659693717957
epoch: 16 training_loss 0.09770581775344908 test_loss: 0.12214078903198242
epoch: 17 training_loss 0.09509335888549686 test_loss: 0.10606184005737304
epoch: 18 training_loss 0.10418627437204123 test_loss: 0.08686608076095581
epoch: 19 training_loss 0.09505479848012328 test_loss: 0.0932261049747467
epoch: 20 training_loss 0.09355588432401418 test_loss: 0.10876609086990356
epoch: 21 training_loss 0.09688010297715664 test_loss: 0.09306836724281312
epoch: 22 training_loss 0.10055131312459707 test_loss: 0.11359692811965942
epoch: 23 training_loss 0.09925782587379217 test_loss: 0.10323295593261719
epoch: 24 training_loss 0.09632508374750615 test_loss: 0.09585543870925903
epoch: 25 training_loss 0.09911047114059329 test_loss: 0.10474094152450561
epoch: 26 training_loss 0.0958851795271039 test_loss: 0.10895458459854127
epoch: 27 training_loss 0.09371530909091234 test_loss: 0.0834309697151184
epoch: 28 training_loss 0.09650844275951385 test_loss: 0.10552241802215576
epoch: 29 training_loss 0.09428230963647366 test_loss: 0.0845612645149231
epoch: 30 training_loss 0.10116716468706727 test_loss: 0.0913993775844574
epoch: 31 training_loss 0.09243733208626509 test_loss: 0.09873842000961304
epoch: 32 training_loss 0.09431313272565603 test_loss: 0.09459561109542847
epoch: 33 training_loss 0.09606701165437698 test_loss: 0.09674973487854004
epoch: 34 training_loss 0.0945161322131753 test_loss: 0.10046453475952148
epoch: 35 training_loss 0.09282043317332864 test_loss: 0.10161291360855103
epoch: 36 training_loss 0.09201424151659011 test_loss: 0.08471920490264892
epoch: 37 training_loss 0.09900399595499039 test_loss: 0.10048812627792358
epoch: 38 training_loss 0.0868280354514718 test_loss: 0.09570052623748779
epoch: 39 training_loss 0.09412775466218591 test_loss: 0.08642889261245727
epoch: 40 training_loss 0.09073936898261309 test_loss: 0.0886385202407837
epoch: 41 training_loss 0.09125709591433406 test_loss: 0.1054187536239624
epoch: 42 training_loss 0.09015896318480372 test_loss: 0.09420807957649231
epoch: 43 training_loss 0.091777768060565 test_loss: 0.0923526108264923
epoch: 44 training_loss 0.09514649583026767 test_loss: 0.08702842593193054
epoch: 45 training_loss 0.08644315938465297 test_loss: 0.10825716257095337
epoch: 46 training_loss 0.08973661251366138 test_loss: 0.09977920055389404
epoch: 47 training_loss 0.09214866073802114 test_loss: 0.09990050196647644
epoch: 48 training_loss 0.09143012760207057 test_loss: 0.10080729722976685
epoch: 49 training_loss 0.09468689678236843 test_loss: 0.0923387885093689
epoch: 50 training_loss 0.09105562251061201 test_loss: 0.09059652090072631
epoch: 51 training_loss 0.09174615893512965 test_loss: 0.09246240854263306
epoch: 52 training_loss 0.08690610848367214 test_loss: 0.091260427236557
epoch: 53 training_loss 0.09356475200504065 test_loss: 0.09877200126647949
epoch: 54 training_loss 0.08863430194556714 test_loss: 0.10301429033279419
epoch: 55 training_loss 0.08533255772665144 test_loss: 0.09973176717758178
epoch: 56 training_loss 0.08816779267042875 test_loss: 0.09239851236343384
epoch: 57 training_loss 0.09096265222877264 test_loss: 0.10659855604171753
epoch: 58 training_loss 0.09065298531204462 test_loss: 0.0851654827594757
epoch: 59 training_loss 0.08349806658923625 test_loss: 0.08506934642791748
epoch: 60 training_loss 0.08895685989409685 test_loss: 0.09406775236129761
epoch: 61 training_loss 0.0875668478757143 test_loss: 0.09865658283233643
epoch: 62 training_loss 0.09217146569862962 test_loss: 0.11049344539642333
epoch: 63 training_loss 0.09174469277262688 test_loss: 0.10029385089874268
epoch: 64 training_loss 0.08003519978374243 test_loss: 0.07759435772895813
epoch: 65 training_loss 0.08523180602118373 test_loss: 0.08611871004104614
epoch: 66 training_loss 0.08880249643698335 test_loss: 0.09598694443702697
epoch: 67 training_loss 0.0866705776937306 test_loss: 0.10635641813278199
epoch: 68 training_loss 0.0874063790217042 test_loss: 0.08874755501747131
epoch: 69 training_loss 0.0862246172875166 test_loss: 0.09800589084625244
epoch: 70 training_loss 0.0809405018016696 test_loss: 0.08401342034339905
epoch: 71 training_loss 0.08659484539180994 test_loss: 0.08515079021453857
epoch: 72 training_loss 0.08621345091611148 test_loss: 0.0988427758216858
epoch: 73 training_loss 0.0874702475592494 test_loss: 0.09655891060829162
epoch: 74 training_loss 0.09042853098362684 test_loss: 0.09033157229423523
epoch: 75 training_loss 0.08121386090293527 test_loss: 0.09284038543701172
epoch: 76 training_loss 0.0846305705420673 test_loss: 0.10310251712799072
epoch: 77 training_loss 0.08762698482722044 test_loss: 0.08426980376243591
epoch: 78 training_loss 0.09055019099265336 test_loss: 0.09262892007827758
epoch: 79 training_loss 0.08658804142847658 test_loss: 0.08179628252983093
epoch: 80 training_loss 0.08499587297439576 test_loss: 0.10507687330245971
epoch: 81 training_loss 0.08635487928986549 test_loss: 0.09865508079528809
epoch: 82 training_loss 0.08117294959723949 test_loss: 0.08577175736427307
epoch: 83 training_loss 0.08902350578457117 test_loss: 0.08978354334831237
epoch: 84 training_loss 0.0916082009114325 test_loss: 0.09388467073440551
epoch: 85 training_loss 0.08124449590221047 test_loss: 0.09703166484832763
epoch: 86 training_loss 0.08183760036714376 test_loss: 0.09042500853538513
epoch: 87 training_loss 0.0877636981010437 test_loss: 0.09387450218200684
epoch: 88 training_loss 0.08364728583022953 test_loss: 0.09150940179824829
epoch: 89 training_loss 0.07918927200138569 test_loss: 0.08236433267593384
epoch: 90 training_loss 0.09144588895142078 test_loss: 0.08811739087104797
epoch: 91 training_loss 0.08387032224796713 test_loss: 0.10498172044754028
epoch: 92 training_loss 0.08476017739623785 test_loss: 0.08541793823242187
epoch: 93 training_loss 0.08615472923964262 test_loss: 0.09714128375053406
epoch: 94 training_loss 0.08662122026085854 test_loss: 0.09319180846214295
epoch: 95 training_loss 0.07928102273494005 test_loss: 0.10634632110595703
epoch: 96 training_loss 0.08640948297455907 test_loss: 0.08382543325424194
epoch: 97 training_loss 0.07854470558464527 test_loss: 0.09537625908851624
epoch: 98 training_loss 0.08957282323390245 test_loss: 0.09560734629631043
epoch: 99 training_loss 0.08368795222602785 test_loss: 0.08694077134132386
epoch: 100 training_loss 0.07557186430320144 test_loss: 0.11136535406112671
epoch: 101 training_loss 0.08059620210900903 test_loss: 0.08416866064071656
epoch: 102 training_loss 0.07515557607635856 test_loss: 0.08374553918838501
epoch: 103 training_loss 0.09172338170930744 test_loss: 0.10405796766281128
epoch: 104 training_loss 0.07841924255713821 test_loss: 0.0952073097229004
epoch: 105 training_loss 0.07618226857855916 test_loss: 0.09588519334793091
epoch: 106 training_loss 0.07899360418319702 test_loss: 0.1066671371459961
epoch: 107 training_loss 0.08221058825030923 test_loss: 0.10503325462341309
epoch: 108 training_loss 0.08360840665176511 test_loss: 0.11341383457183837
epoch: 109 training_loss 0.07467368509620428 test_loss: 0.1084541916847229
epoch: 110 training_loss 0.07965381167829037 test_loss: 0.10320724248886108
epoch: 111 training_loss 0.0792677233926952 test_loss: 0.11079331636428832
epoch: 112 training_loss 0.08556918999180198 test_loss: 0.08913253545761109
epoch: 113 training_loss 0.08353740388993174 test_loss: 0.08676121830940246
epoch: 114 training_loss 0.0817426261678338 test_loss: 0.0856702983379364
epoch: 115 training_loss 0.0796308609098196 test_loss: 0.10656839609146118
epoch: 116 training_loss 0.07600608754903078 test_loss: 0.08384655714035034
epoch: 117 training_loss 0.08388753155246377 test_loss: 0.08132911920547485
epoch: 118 training_loss 0.08261689420789481 test_loss: 0.09553459882736207
epoch: 119 training_loss 0.08374219682067632 test_loss: 0.0908280611038208
epoch: 120 training_loss 0.07935989258810877 test_loss: 0.100806725025177
epoch: 121 training_loss 0.08795801313593983 test_loss: 0.09519320726394653
epoch: 122 training_loss 0.07847691314294934 test_loss: 0.10337617397308349
epoch: 123 training_loss 0.07503259723074734 test_loss: 0.08521940112113953
epoch: 124 training_loss 0.08430939337238669 test_loss: 0.09577106833457946
epoch: 125 training_loss 0.07928074236959219 test_loss: 0.0961661159992218
epoch: 126 training_loss 0.08205591986887156 test_loss: 0.10242277383804321
epoch: 127 training_loss 0.07905753802508116 test_loss: 0.09772107601165772
epoch: 128 training_loss 0.08154735054820776 test_loss: 0.09099124073982238
epoch: 129 training_loss 0.07872616771608591 test_loss: 0.10731515884399415
epoch: 130 training_loss 0.08450801888480783 test_loss: 0.1157418966293335
epoch: 131 training_loss 0.07858564354479312 test_loss: 0.10120980739593506
epoch: 132 training_loss 0.07545532612130046 test_loss: 0.07653775215148925
epoch: 133 training_loss 0.07799388011917471 test_loss: 0.10095125436782837
epoch: 134 training_loss 0.07477564779575914 test_loss: 0.08480083346366882
epoch: 135 training_loss 0.07976272394880653 test_loss: 0.08999159336090087
epoch: 136 training_loss 0.08319445239380002 test_loss: 0.09600365161895752
epoch: 137 training_loss 0.08299834551289678 test_loss: 0.0991459310054779
epoch: 138 training_loss 0.07883246341720224 test_loss: 0.10355926752090454
epoch: 139 training_loss 0.07173559185117483 test_loss: 0.1101271629333496
epoch: 140 training_loss 0.07923881368711591 test_loss: 0.10021144151687622
epoch: 141 training_loss 0.07818557530641555 test_loss: 0.0891743004322052
epoch: 142 training_loss 0.07422871246933938 test_loss: 0.09774856567382813
epoch: 143 training_loss 0.0753290306031704 test_loss: 0.1042291283607483
epoch: 144 training_loss 0.0769932377897203 test_loss: 0.09282276034355164
epoch: 145 training_loss 0.08148651441559196 test_loss: 0.0866900086402893
epoch: 146 training_loss 0.0786298169195652 test_loss: 0.0962839424610138
epoch: 147 training_loss 0.07704525571316481 test_loss: 0.09507975578308106
epoch: 148 training_loss 0.07622420500963926 test_loss: 0.10628256797790528
epoch: 149 training_loss 0.07573982510715722 test_loss: 0.0986589252948761
epoch: 0 training_loss 0.2535826553404331 test_loss: 0.18053003549575805
epoch: 1 training_loss 0.15812248289585112 test_loss: 0.13044304847717286
epoch: 2 training_loss 0.14047631207853556 test_loss: 0.15843108892440796
epoch: 3 training_loss 0.13229925617575644 test_loss: 0.13380110263824463
epoch: 4 training_loss 0.12194273710250854 test_loss: 0.13675429821014404
epoch: 5 training_loss 0.11819718565791845 test_loss: 0.14116724729537963
epoch: 6 training_loss 0.11431502848863602 test_loss: 0.11144407987594604
epoch: 7 training_loss 0.10666836362332105 test_loss: 0.11254792213439942
epoch: 8 training_loss 0.110455442070961 test_loss: 0.10029754638671876
epoch: 9 training_loss 0.10656636755913496 test_loss: 0.1230425477027893
epoch: 10 training_loss 0.10402895089238882 test_loss: 0.1009458065032959
epoch: 11 training_loss 0.0995680508390069 test_loss: 0.1131563663482666
epoch: 12 training_loss 0.10447068789973855 test_loss: 0.1108051896095276
epoch: 13 training_loss 0.10140528125688433 test_loss: 0.10053884983062744
epoch: 14 training_loss 0.09566741889342666 test_loss: 0.11364725828170777
epoch: 15 training_loss 0.10061115624383092 test_loss: 0.0956125795841217
epoch: 16 training_loss 0.08916515938937664 test_loss: 0.09511389136314392
epoch: 17 training_loss 0.09961000407114624 test_loss: 0.10595736503601075
epoch: 18 training_loss 0.09603169959038496 test_loss: 0.10423957109451294
epoch: 19 training_loss 0.09917434325441718 test_loss: 0.09724224209785462
epoch: 20 training_loss 0.09078654250130057 test_loss: 0.1091807246208191
epoch: 21 training_loss 0.09853810148313641 test_loss: 0.13390278816223145
epoch: 22 training_loss 0.0979118798673153 test_loss: 0.11881643533706665
epoch: 23 training_loss 0.09648353304713965 test_loss: 0.09530601501464844
epoch: 24 training_loss 0.09031742313876748 test_loss: 0.09539922475814819
epoch: 25 training_loss 0.09149125665426254 test_loss: 0.10605756044387818
epoch: 26 training_loss 0.09470474135130644 test_loss: 0.09049755334854126
epoch: 27 training_loss 0.09204692259430886 test_loss: 0.08768250346183777
epoch: 28 training_loss 0.08728598028421403 test_loss: 0.11436213254928589
epoch: 29 training_loss 0.09261154230684042 test_loss: 0.09328283071517944
epoch: 30 training_loss 0.09161417048424482 test_loss: 0.10863996744155884
epoch: 31 training_loss 0.093779151532799 test_loss: 0.10346729755401611
epoch: 32 training_loss 0.0906271024234593 test_loss: 0.0899875819683075
epoch: 33 training_loss 0.08611769035458565 test_loss: 0.10852295160293579
epoch: 34 training_loss 0.09616299645975232 test_loss: 0.09992102980613708
epoch: 35 training_loss 0.08626564981415868 test_loss: 0.10950798988342285
epoch: 36 training_loss 0.09240786036476493 test_loss: 0.1005853533744812
epoch: 37 training_loss 0.09181849483400584 test_loss: 0.0945510745048523
epoch: 38 training_loss 0.0830991181731224 test_loss: 0.09638255834579468
epoch: 39 training_loss 0.08438520828261971 test_loss: 0.10495002269744873
epoch: 40 training_loss 0.0919879575446248 test_loss: 0.10315971374511719
epoch: 41 training_loss 0.09207307826727629 test_loss: 0.10676660537719726
epoch: 42 training_loss 0.09193880732171238 test_loss: 0.1029636025428772
epoch: 43 training_loss 0.08441261868923902 test_loss: 0.09788835644721985
epoch: 44 training_loss 0.0875433766283095 test_loss: 0.08716326951980591
epoch: 45 training_loss 0.08105549342930317 test_loss: 0.08928566575050353
epoch: 46 training_loss 0.08534924235194921 test_loss: 0.11044703722000122
epoch: 47 training_loss 0.08345445204526186 test_loss: 0.10859030485153198
epoch: 48 training_loss 0.08391635330393911 test_loss: 0.11945019960403443
epoch: 49 training_loss 0.08619044570252299 test_loss: 0.12164934873580932
epoch: 50 training_loss 0.08968995470553637 test_loss: 0.09979282021522522
epoch: 51 training_loss 0.08625551275908946 test_loss: 0.10116242170333863
epoch: 52 training_loss 0.08701611962169409 test_loss: 0.10858862400054932
epoch: 53 training_loss 0.08985308095812798 test_loss: 0.09883440732955932
epoch: 54 training_loss 0.09191852144896984 test_loss: 0.08620932698249817
epoch: 55 training_loss 0.08507124239578844 test_loss: 0.1088176965713501
epoch: 56 training_loss 0.08283091105520725 test_loss: 0.1181914210319519
epoch: 57 training_loss 0.08745380284264684 test_loss: 0.1130685806274414
epoch: 58 training_loss 0.0782875837944448 test_loss: 0.1027987003326416
epoch: 59 training_loss 0.08511169543489813 test_loss: 0.10535733699798584
epoch: 60 training_loss 0.0857573726028204 test_loss: 0.09465076327323914
epoch: 61 training_loss 0.08808637483045459 test_loss: 0.08964510560035706
epoch: 62 training_loss 0.08474618492648006 test_loss: 0.08842605352401733
epoch: 63 training_loss 0.08238467598333955 test_loss: 0.10843856334686279
epoch: 64 training_loss 0.08425798185169697 test_loss: 0.11424835920333862
epoch: 65 training_loss 0.08665413161739707 test_loss: 0.09503540992736817
epoch: 66 training_loss 0.08748973006382585 test_loss: 0.07804188132286072
epoch: 67 training_loss 0.08039453905075788 test_loss: 0.10078895092010498
epoch: 68 training_loss 0.08508815800771118 test_loss: 0.09967914819717408
epoch: 69 training_loss 0.09077980268746615 test_loss: 0.09859429597854615
epoch: 70 training_loss 0.08891843412071467 test_loss: 0.10179539918899536
epoch: 71 training_loss 0.08350232239812612 test_loss: 0.09248464107513428
epoch: 72 training_loss 0.08959667436778546 test_loss: 0.10244503021240234
epoch: 73 training_loss 0.08091196550987662 test_loss: 0.11085138320922852
epoch: 74 training_loss 0.08854550760239363 test_loss: 0.09981300830841064
epoch: 75 training_loss 0.09187380170449615 test_loss: 0.08936812281608582
epoch: 76 training_loss 0.08847443541511893 test_loss: 0.1017685055732727
epoch: 77 training_loss 0.0882935654744506 test_loss: 0.09054942727088929
epoch: 78 training_loss 0.08460583359003067 test_loss: 0.08344268798828125
epoch: 79 training_loss 0.08631384737789631 test_loss: 0.09054904580116271
epoch: 80 training_loss 0.08717379907146096 test_loss: 0.10130530595779419
epoch: 81 training_loss 0.08596963586285711 test_loss: 0.0961907982826233
epoch: 82 training_loss 0.09013387015089393 test_loss: 0.09760041236877441
epoch: 83 training_loss 0.07887539099901915 test_loss: 0.09874186515808106
epoch: 84 training_loss 0.08863912254571915 test_loss: 0.10667665004730224
epoch: 85 training_loss 0.07899344502016901 test_loss: 0.10879707336425781
epoch: 86 training_loss 0.08002625642344356 test_loss: 0.11744250059127807
epoch: 87 training_loss 0.08458547150716185 test_loss: 0.10874406099319459
epoch: 88 training_loss 0.07761708796024322 test_loss: 0.12124359607696533
epoch: 89 training_loss 0.0829193129390478 test_loss: 0.11729512214660645
epoch: 90 training_loss 0.08050471035763622 test_loss: 0.09502227306365967
epoch: 91 training_loss 0.07801717839203776 test_loss: 0.09589084386825561
epoch: 92 training_loss 0.0799201208166778 test_loss: 0.09660345315933228
epoch: 93 training_loss 0.08302678804844618 test_loss: 0.09906059503555298
epoch: 94 training_loss 0.08214211128652096 test_loss: 0.09968900680541992
epoch: 95 training_loss 0.07984764132648707 test_loss: 0.11407544612884521
epoch: 96 training_loss 0.08365484666079283 test_loss: 0.10982223749160766
epoch: 97 training_loss 0.07728515708819032 test_loss: 0.09118309617042542
epoch: 98 training_loss 0.08270514400675893 test_loss: 0.09275913834571839
epoch: 99 training_loss 0.08377299143001438 test_loss: 0.09470486044883727
epoch: 100 training_loss 0.0821490198932588 test_loss: 0.09242291450500488
epoch: 101 training_loss 0.07978936146944761 test_loss: 0.09808312058448791
epoch: 102 training_loss 0.08388505479320883 test_loss: 0.09491743445396424
epoch: 103 training_loss 0.07421397251076996 test_loss: 0.10069026947021484
epoch: 104 training_loss 0.08138403324410319 test_loss: 0.10576993227005005
epoch: 105 training_loss 0.08922921190038323 test_loss: 0.09078351259231568
epoch: 106 training_loss 0.08878945089876651 test_loss: 0.1024829626083374
epoch: 107 training_loss 0.077381611187011 test_loss: 0.11184518337249756
epoch: 108 training_loss 0.08037013823166489 test_loss: 0.11387026309967041
epoch: 109 training_loss 0.07710691520944238 test_loss: 0.11695696115493774
epoch: 110 training_loss 0.07901582090184092 test_loss: 0.11370885372161865
epoch: 111 training_loss 0.07536187343299389 test_loss: 0.0921140432357788
epoch: 112 training_loss 0.08227109271101654 test_loss: 0.09483983516693115
epoch: 113 training_loss 0.08621654577553273 test_loss: 0.1043252944946289
epoch: 114 training_loss 0.07244936401024461 test_loss: 0.08863741755485535
epoch: 115 training_loss 0.07864623351022601 test_loss: 0.09959878921508789
epoch: 116 training_loss 0.08264554159715772 test_loss: 0.10542773008346558
epoch: 117 training_loss 0.08299426149576902 test_loss: 0.1127294659614563
epoch: 118 training_loss 0.08158463740721345 test_loss: 0.11146491765975952
epoch: 119 training_loss 0.07801356615498661 test_loss: 0.11557611227035522
epoch: 120 training_loss 0.09209888806566596 test_loss: 0.10689362287521362
epoch: 121 training_loss 0.080841773301363 test_loss: 0.09969048500061035
epoch: 122 training_loss 0.0852788121253252 test_loss: 0.10856634378433228
epoch: 123 training_loss 0.07853531116619707 test_loss: 0.11875149011611938
epoch: 124 training_loss 0.07731726188212633 test_loss: 0.10392796993255615
epoch: 125 training_loss 0.08978031602688134 test_loss: 0.10589029788970947
epoch: 126 training_loss 0.07262292617000639 test_loss: 0.0983642041683197
epoch: 127 training_loss 0.08197951760143042 test_loss: 0.100043785572052
epoch: 128 training_loss 0.07444432392716407 test_loss: 0.10742597579956055
epoch: 129 training_loss 0.07833266941830516 test_loss: 0.09516838788986207
epoch: 130 training_loss 0.08442551221698523 test_loss: 0.10541404485702514
epoch: 131 training_loss 0.08059328505769373 test_loss: 0.09731405973434448
epoch: 132 training_loss 0.07959603117778898 test_loss: 0.09609662890434265
epoch: 133 training_loss 0.0754505032300949 test_loss: 0.10353270769119263
epoch: 134 training_loss 0.07899189052172005 test_loss: 0.0936679184436798
epoch: 135 training_loss 0.0807342710904777 test_loss: 0.09415699243545532
epoch: 136 training_loss 0.08153653885237873 test_loss: 0.1029825210571289
epoch: 137 training_loss 0.07647647315636277 test_loss: 0.09368999600410462
epoch: 138 training_loss 0.08425148239359259 test_loss: 0.11176940202713012
epoch: 139 training_loss 0.07421222522854805 test_loss: 0.10122994184494019
epoch: 140 training_loss 0.07519612472504378 test_loss: 0.10000848770141602
epoch: 141 training_loss 0.07900483310222625 test_loss: 0.10228552818298339
epoch: 142 training_loss 0.07877188922837376 test_loss: 0.10654115676879883
epoch: 143 training_loss 0.0812941938266158 test_loss: 0.09672728776931763
epoch: 144 training_loss 0.0761319375038147 test_loss: 0.09157663583755493
epoch: 145 training_loss 0.07669908849522472 test_loss: 0.11024932861328125
epoch: 146 training_loss 0.07892759248614312 test_loss: 0.09359724521636963
epoch: 147 training_loss 0.08303964881226421 test_loss: 0.09849967956542968
epoch: 148 training_loss 0.07512078773230314 test_loss: 0.09473946094512939
epoch: 149 training_loss 0.07616706807166337 test_loss: 0.11068609952926636
episode: 0 training return: -852.337994770493
episode: 1 training return: -827.4357866011854
episode: 2 training return: -842.4530485602143
episode: 3 training return: -830.2760442279723
epoch: 1 test_true_pfm: 313.3238372874218 sim_pfm: -760.2796957689234
episode: 4 training return: -832.2126818852943
episode: 5 training return: -812.5131650222277
episode: 6 training return: -805.3308138068636
episode: 7 training return: -801.4483165699312
epoch: 2 test_true_pfm: 565.2835962639443 sim_pfm: -808.9718596071657
episode: 8 training return: -820.6271061192843
episode: 9 training return: -797.1619115832123
episode: 10 training return: -886.4616258098551
episode: 11 training return: -820.2867454973795
epoch: 3 test_true_pfm: 177.56938642745763 sim_pfm: -958.9824674455294
episode: 12 training return: -747.4035844708702
episode: 13 training return: -779.1848187763824
episode: 14 training return: -752.1150229740084
episode: 15 training return: -881.7778781993928
epoch: 4 test_true_pfm: -373.28062788564125 sim_pfm: -920.0544972791013
episode: 16 training return: -678.4901212000218
episode: 17 training return: -933.6866484504425
episode: 18 training return: -691.5302845374756
episode: 19 training return: -742.8535322276267
epoch: 5 test_true_pfm: 87.6569549993762 sim_pfm: -649.4967576173236
episode: 20 training return: -678.1477303600653
episode: 21 training return: -679.544627275568
episode: 22 training return: -839.5855475101879
episode: 23 training return: -740.9474220802631
epoch: 6 test_true_pfm: 19.539863948084328 sim_pfm: -615.1191021324254
episode: 24 training return: -887.9823000221868
episode: 25 training return: -717.642457437419
episode: 26 training return: -708.3255389231676
episode: 27 training return: -884.3247423995194
epoch: 7 test_true_pfm: -107.43734277620564 sim_pfm: -630.5122367760581
episode: 28 training return: -718.2529463967285
episode: 29 training return: -823.4886415309008
episode: 30 training return: -842.0744441455013
episode: 31 training return: -718.9399679419906
epoch: 8 test_true_pfm: -36.42879606382278 sim_pfm: -642.6359180743065
episode: 32 training return: -764.7873069482431
episode: 33 training return: -799.6984389506081
episode: 34 training return: -812.3889075626377
episode: 35 training return: -855.2158851853837
epoch: 9 test_true_pfm: 186.75073038257804 sim_pfm: -799.8149113869014
episode: 36 training return: -786.1170503251234
episode: 37 training return: -844.8732640587107
episode: 38 training return: -826.4018430519228
episode: 39 training return: -850.0751645392145
epoch: 10 test_true_pfm: 137.29429956937327 sim_pfm: -817.5711640121639
episode: 40 training return: -839.6197654981142
episode: 41 training return: -848.2868559929898
episode: 42 training return: -860.484903629959
episode: 43 training return: -854.6058124954941
epoch: 11 test_true_pfm: 58.03165519857904 sim_pfm: -827.9706987431682
episode: 44 training return: -873.7656376161715
episode: 45 training return: -868.809749012967
episode: 46 training return: -850.8591713925122
episode: 47 training return: -847.8532689775302
epoch: 12 test_true_pfm: 48.82545470744497 sim_pfm: -682.7003351517261
episode: 48 training return: -839.2927804777346
episode: 49 training return: -837.3529063969402
episode: 50 training return: -851.8062690800646
episode: 51 training return: -842.4625792718281
epoch: 13 test_true_pfm: 187.22817318122193 sim_pfm: -763.8727980131797
episode: 52 training return: -825.809741931014
episode: 53 training return: -857.3866570526898
episode: 54 training return: -864.437034179552
episode: 55 training return: -823.0166085185226
epoch: 14 test_true_pfm: 124.86998537446118 sim_pfm: -684.8201859881896
episode: 56 training return: -827.4737364502461
episode: 57 training return: -813.6711232131294
episode: 58 training return: -827.7707067968873
episode: 59 training return: -830.6663420282858
epoch: 15 test_true_pfm: 144.4376314967519 sim_pfm: -756.755950583066
episode: 60 training return: -828.0346032393913
episode: 61 training return: -731.8381225178706
episode: 62 training return: -833.0535318256825
episode: 63 training return: -833.4301058774237
epoch: 16 test_true_pfm: 124.49181849430208 sim_pfm: -720.217561427812
episode: 64 training return: -843.8227470419929
episode: 65 training return: -828.4722629757736
episode: 66 training return: -797.1448245805232
episode: 67 training return: -823.1198554006311
epoch: 17 test_true_pfm: 130.93129554753105 sim_pfm: -724.2568242659331
episode: 68 training return: -821.8057441638224
episode: 69 training return: -825.8111966031803
episode: 70 training return: -848.1130622892181
episode: 71 training return: -838.0607485110676
epoch: 18 test_true_pfm: 132.01969483814773 sim_pfm: -707.5793334194647
episode: 72 training return: -812.1550414476368
episode: 73 training return: -728.3160430655183
episode: 74 training return: -818.7311547778897
episode: 75 training return: -840.7974838279438
epoch: 19 test_true_pfm: 130.7430965149351 sim_pfm: -723.3673979316869
episode: 76 training return: -835.6198717434733
episode: 77 training return: -846.466769341222
episode: 78 training return: -834.0340161685521
episode: 79 training return: -822.3824472288884
epoch: 20 test_true_pfm: 147.21965098860548 sim_pfm: -688.3704055719255
episode: 80 training return: -830.4762719156901
episode: 81 training return: -840.5534493803431
episode: 82 training return: -819.4415851935225
episode: 83 training return: -822.4495244265137
epoch: 21 test_true_pfm: 133.80469323370036 sim_pfm: -705.57396918906
episode: 84 training return: -805.8595973114661
episode: 85 training return: -832.376780430836
episode: 86 training return: -827.0680504861475
episode: 87 training return: -810.7830921248143
epoch: 22 test_true_pfm: 136.6782814562366 sim_pfm: -703.949363104713
episode: 88 training return: -790.4089367397175
episode: 89 training return: -810.8685162393617
episode: 90 training return: -777.0336557591379
episode: 91 training return: -822.2608995927667
epoch: 23 test_true_pfm: 135.2141487743563 sim_pfm: -708.0668467495649
episode: 92 training return: -832.0214395028644
episode: 93 training return: -805.8508220792769
episode: 94 training return: -805.0071169022624
episode: 95 training return: -777.3460083097706
epoch: 24 test_true_pfm: 131.30299491739447 sim_pfm: -705.5611355049091
episode: 96 training return: -798.4910328041022
episode: 97 training return: -825.7996185144567
episode: 98 training return: -808.5492950390233
episode: 99 training return: -769.176651698373
epoch: 25 test_true_pfm: 146.20733450858756 sim_pfm: -720.2800684895491
episode: 100 training return: -760.9091626914992
episode: 101 training return: -865.2035713266682
episode: 102 training return: -772.0086373245978
episode: 103 training return: -753.9600444309585
epoch: 26 test_true_pfm: 110.5159703385146 sim_pfm: -707.704427123885
episode: 104 training return: -769.9366374620702
episode: 105 training return: -724.5633260528833
episode: 106 training return: -752.4865042039262
episode: 107 training return: -679.6823045987924
epoch: 27 test_true_pfm: 33.64938215580724 sim_pfm: -771.5369540122324
episode: 108 training return: -747.0769573291547
episode: 109 training return: -644.4354598532553
episode: 110 training return: -713.0723875374887
episode: 111 training return: -688.7987316277719
epoch: 28 test_true_pfm: -43.70272429671291 sim_pfm: -553.7412969636713
episode: 112 training return: -666.262723790127
episode: 113 training return: -636.1779722896031
episode: 114 training return: -644.2116164881411
episode: 115 training return: -662.7086983894245
epoch: 29 test_true_pfm: 148.94049223960127 sim_pfm: -528.4591210263503
episode: 116 training return: -686.888609825621
episode: 117 training return: -677.2764415125675
episode: 118 training return: -689.7336482494487
episode: 119 training return: -656.3518051206765
epoch: 30 test_true_pfm: 89.4620482165539 sim_pfm: -544.3624516449344
episode: 120 training return: -655.0365521736089
episode: 121 training return: -653.0456996740471
episode: 122 training return: -637.144996340046
episode: 123 training return: -648.3082324904635
epoch: 31 test_true_pfm: 160.12364367340902 sim_pfm: -537.8281163990429
episode: 124 training return: -582.0223766545614
episode: 125 training return: -627.0395717334303
episode: 126 training return: -613.6187624309356
episode: 127 training return: -587.4934042312949
epoch: 32 test_true_pfm: 95.77968759941439 sim_pfm: -675.7440655784053
episode: 128 training return: -643.673532430401
episode: 129 training return: -599.8457860906431
episode: 130 training return: -598.703118367616
episode: 131 training return: -625.6944157230574
epoch: 33 test_true_pfm: 285.0973922665343 sim_pfm: -469.5638295544148
episode: 132 training return: -636.3596383866566
episode: 133 training return: -580.7433874999969
episode: 134 training return: -601.4351543128138
episode: 135 training return: -602.9018368997464
epoch: 34 test_true_pfm: 220.16913388399098 sim_pfm: -489.9549504110626
episode: 136 training return: -612.7597331207451
episode: 137 training return: -618.0337431817858
episode: 138 training return: -606.993364685804
episode: 139 training return: -648.4777360365339
epoch: 35 test_true_pfm: 114.42750122388992 sim_pfm: -498.19207429600243
episode: 140 training return: -671.1268802022421
episode: 141 training return: -569.9495300418735
episode: 142 training return: -539.6614716935566
episode: 143 training return: -683.3933050081669
epoch: 36 test_true_pfm: 27.06449877569558 sim_pfm: -534.5099591371298
episode: 144 training return: -615.911797587043
episode: 145 training return: -581.3070828099719
episode: 146 training return: -601.7032669175055
episode: 147 training return: -617.4075165371261
epoch: 37 test_true_pfm: 274.0686785421348 sim_pfm: -491.4415627057012
episode: 148 training return: -570.2214051594334
episode: 149 training return: -596.1448520996905
episode: 150 training return: -575.9529100520957
episode: 151 training return: -676.3453779569983
epoch: 38 test_true_pfm: 168.80033482018163 sim_pfm: -498.24986725847526
episode: 152 training return: -596.0740744341084
episode: 153 training return: -586.1051133669907
episode: 154 training return: -586.2679801326062
episode: 155 training return: -583.8342132549651
epoch: 39 test_true_pfm: 162.20420389911078 sim_pfm: -504.6102108808095
episode: 156 training return: -597.3839496615744
episode: 157 training return: -681.7521255276258
episode: 158 training return: -616.9230325773588
episode: 159 training return: -575.4014269499472
epoch: 40 test_true_pfm: 283.35266218574463 sim_pfm: -451.42714107406726
episode: 160 training return: -600.8550820672688
episode: 161 training return: -556.4956098707017
episode: 162 training return: -564.3088732579872
episode: 163 training return: -536.0653343797296
epoch: 41 test_true_pfm: 36.1329333668939 sim_pfm: -498.0850539600594
episode: 164 training return: -547.688342318422
episode: 165 training return: -606.7543743228665
episode: 166 training return: -686.9276749893961
episode: 167 training return: -585.2122018063602
epoch: 42 test_true_pfm: 200.54307219709438 sim_pfm: -500.15991282900677
episode: 168 training return: -551.6633349165331
episode: 169 training return: -553.2674720106556
episode: 170 training return: -591.1517087509835
episode: 171 training return: -573.6434553859381
epoch: 43 test_true_pfm: 273.4766415728997 sim_pfm: -477.6476546037656
episode: 172 training return: -566.8908635523715
episode: 173 training return: -605.5636232995766
episode: 174 training return: -614.9984307410169
episode: 175 training return: -616.7351745858348
epoch: 44 test_true_pfm: 108.17650074023321 sim_pfm: -504.30502590142487
episode: 176 training return: -598.0911576562762
episode: 177 training return: -603.5532894677525
episode: 178 training return: -670.0359253114466
episode: 179 training return: -538.2518718605779
epoch: 45 test_true_pfm: 193.67997106712377 sim_pfm: -478.9296357509998
episode: 180 training return: -603.122498465771
episode: 181 training return: -625.2982828638402
episode: 182 training return: -751.582664086479
episode: 183 training return: -548.8039756444998
epoch: 46 test_true_pfm: 84.3347115785782 sim_pfm: -480.5768919910359
episode: 184 training return: -542.2883211708775
episode: 185 training return: -646.3537136874835
episode: 186 training return: -568.0279878151753
episode: 187 training return: -558.3140960981046
epoch: 47 test_true_pfm: 212.43518969974608 sim_pfm: -483.4909780651879
episode: 188 training return: -671.0098434654335
episode: 189 training return: -557.1571845419686
episode: 190 training return: -573.199927400229
episode: 191 training return: -510.6270272631857
epoch: 48 test_true_pfm: 152.3245442679355 sim_pfm: -474.6828877018193
episode: 192 training return: -673.3855239880085
episode: 193 training return: -550.8023361874555
episode: 194 training return: -572.4928531562452
episode: 195 training return: -553.7905190616194
epoch: 49 test_true_pfm: 172.54436836416718 sim_pfm: -463.5596235247296
episode: 196 training return: -583.3145478120908
episode: 197 training return: -627.8239440864647
episode: 198 training return: -522.6216086702548
episode: 199 training return: -552.4265454489513
epoch: 50 test_true_pfm: 64.44303251290434 sim_pfm: -495.6771708662731
episode: 200 training return: -635.7586848665268
episode: 201 training return: -617.681767658097
episode: 202 training return: -577.7744474803378
episode: 203 training return: -549.0527531642912
epoch: 51 test_true_pfm: 245.77091628079052 sim_pfm: -449.08278583381997
episode: 204 training return: -546.2047172528031
episode: 205 training return: -534.0702686363867
episode: 206 training return: -542.111184493269
episode: 207 training return: -521.1928593664114
epoch: 52 test_true_pfm: 196.90851726937194 sim_pfm: -459.5622775877666
episode: 208 training return: -568.6834468358012
episode: 209 training return: -559.17296737614
episode: 210 training return: -646.1499107408882
episode: 211 training return: -623.0915690389211
epoch: 53 test_true_pfm: 262.3449052632828 sim_pfm: -477.2494171002897
episode: 212 training return: -526.0193521390079
episode: 213 training return: -643.0997039067306
episode: 214 training return: -776.9233154517634
episode: 215 training return: -555.3064345453907
epoch: 54 test_true_pfm: 178.332425685524 sim_pfm: -442.7513155332768
episode: 216 training return: -655.4356403019631
episode: 217 training return: -564.4780307478551
episode: 218 training return: -536.997752901707
episode: 219 training return: -567.5635803220259
epoch: 55 test_true_pfm: 111.77677259235266 sim_pfm: -443.41377480756273
episode: 220 training return: -570.4297250753204
episode: 221 training return: -605.385154115175
episode: 222 training return: -581.2276059352572
episode: 223 training return: -531.5763902102649
epoch: 56 test_true_pfm: 262.04745024735547 sim_pfm: -440.38916901382373
episode: 224 training return: -639.872355094875
episode: 225 training return: -550.1380169319241
episode: 226 training return: -557.8585032822236
episode: 227 training return: -563.7691954904051
epoch: 57 test_true_pfm: 171.31845175770079 sim_pfm: -475.84095339126566
episode: 228 training return: -600.8312702084407
episode: 229 training return: -580.6545235372007
episode: 230 training return: -559.7378520449943
episode: 231 training return: -626.2440426675959
epoch: 58 test_true_pfm: 257.1059013261616 sim_pfm: -462.49748625284195
episode: 232 training return: -587.9723697009135
episode: 233 training return: -555.5364232899818
episode: 234 training return: -473.5979542111677
episode: 235 training return: -547.9097604262782
epoch: 59 test_true_pfm: 229.58676227962874 sim_pfm: -467.0316517741307
episode: 236 training return: -530.5956019256937
episode: 237 training return: -522.940157718976
episode: 238 training return: -599.8866547778
episode: 239 training return: -536.2988900804224
epoch: 60 test_true_pfm: 227.3170400968976 sim_pfm: -445.5541646768086
episode: 240 training return: -744.9709797157575
episode: 241 training return: -550.9020710962069
episode: 242 training return: -591.0574937233115
episode: 243 training return: -567.7058923058345
epoch: 61 test_true_pfm: 293.7784089151207 sim_pfm: -429.1309464139931
episode: 244 training return: -515.9345772835989
episode: 245 training return: -551.9010122281529
episode: 246 training return: -562.2394440639016
episode: 247 training return: -561.6938786620437
epoch: 62 test_true_pfm: 298.65078488327293 sim_pfm: -448.76726556807625
episode: 248 training return: -537.8619038928676
episode: 249 training return: -540.9126357019022
episode: 250 training return: -537.3530020499757
episode: 251 training return: -544.4806215394801
epoch: 63 test_true_pfm: 181.0277135198917 sim_pfm: -482.77826358709643
episode: 252 training return: -563.344724989469
episode: 253 training return: -664.3312129265508
episode: 254 training return: -598.796494576743
episode: 255 training return: -522.2677314449058
epoch: 64 test_true_pfm: 254.89229772480545 sim_pfm: -471.1093438477651
episode: 256 training return: -550.5551555447014
episode: 257 training return: -614.424843823095
episode: 258 training return: -600.0640542495788
episode: 259 training return: -531.7520170918799
epoch: 65 test_true_pfm: 400.7226276580313 sim_pfm: -455.5609973866167
episode: 260 training return: -514.0091607831777
episode: 261 training return: -566.0407481370887
episode: 262 training return: -486.7097355296668
episode: 263 training return: -487.46105828984776
epoch: 66 test_true_pfm: 167.5049516074097 sim_pfm: -420.10532176980087
episode: 264 training return: -523.9318469701295
episode: 265 training return: -544.5304832275142
episode: 266 training return: -516.2768862435944
episode: 267 training return: -536.4249411454571
epoch: 67 test_true_pfm: 249.21527322853407 sim_pfm: -476.9133408846901
episode: 268 training return: -523.0873594103157
episode: 269 training return: -540.0986668222737
episode: 270 training return: -572.6864309962118
episode: 271 training return: -514.2652877845874
epoch: 68 test_true_pfm: 221.99653812855652 sim_pfm: -430.90880992065985
episode: 272 training return: -544.1618278958063
episode: 273 training return: -570.0587859600417
episode: 274 training return: -579.7120010136667
episode: 275 training return: -551.5377906383404
epoch: 69 test_true_pfm: 261.84551988159296 sim_pfm: -447.7363861594467
episode: 276 training return: -519.684293829467
episode: 277 training return: -540.8402424111166
episode: 278 training return: -592.3225275322291
episode: 279 training return: -544.8146542923954
epoch: 70 test_true_pfm: 334.9307151669054 sim_pfm: -455.5783860820268
episode: 280 training return: -550.3890973409053
episode: 281 training return: -526.3965963849013
episode: 282 training return: -524.7382200431246
episode: 283 training return: -573.6516563012685
epoch: 71 test_true_pfm: 350.08870157558573 sim_pfm: -425.38848247865644
episode: 284 training return: -528.739966590138
episode: 285 training return: -538.2278859799657
episode: 286 training return: -550.6609450315322
episode: 287 training return: -531.1207450585019
epoch: 72 test_true_pfm: 264.1277014223919 sim_pfm: -437.680416375324
episode: 288 training return: -535.7614671939938
episode: 289 training return: -528.8477157914491
episode: 290 training return: -581.4165434314846
episode: 291 training return: -558.9375213392359
epoch: 73 test_true_pfm: 221.6181241312519 sim_pfm: -476.19886793345603
episode: 292 training return: -518.4003531552153
episode: 293 training return: -624.6564245649713
episode: 294 training return: -528.9389128971088
episode: 295 training return: -589.3232908900213
epoch: 74 test_true_pfm: 181.2116773594236 sim_pfm: -447.38253597932254
episode: 296 training return: -534.5896642531554
episode: 297 training return: -500.06616694213545
episode: 298 training return: -530.1774858745936
episode: 299 training return: -513.3128726991365
epoch: 75 test_true_pfm: 344.0082279593705 sim_pfm: -457.8488043609948
episode: 300 training return: -553.6834681496637
episode: 301 training return: -558.8574847598617
episode: 302 training return: -600.544266492133
episode: 303 training return: -565.2682839618415
epoch: 76 test_true_pfm: 317.0342781674006 sim_pfm: -456.76250127537554
episode: 304 training return: -477.84067557570495
episode: 305 training return: -523.3634290500595
episode: 306 training return: -756.3241816345791
episode: 307 training return: -525.8738051702952
epoch: 77 test_true_pfm: 280.2969628062113 sim_pfm: -441.76958109211523
episode: 308 training return: -539.5179885309602
episode: 309 training return: -556.5538375190645
episode: 310 training return: -565.9431769575372
episode: 311 training return: -491.688094820339
epoch: 78 test_true_pfm: 212.13104640887104 sim_pfm: -437.1916390805547
episode: 312 training return: -533.5244554244317
episode: 313 training return: -562.4572332465489
episode: 314 training return: -614.3607464920647
episode: 315 training return: -513.3455996102781
epoch: 79 test_true_pfm: 293.1025816124277 sim_pfm: -417.21962967017
episode: 316 training return: -512.5794781067682
episode: 317 training return: -523.4030399334408
episode: 318 training return: -578.2121767939735
episode: 319 training return: -539.0861706781236
epoch: 80 test_true_pfm: 253.9343281908781 sim_pfm: -464.228249710836
episode: 320 training return: -540.6454652447969
episode: 321 training return: -575.5817809068199
episode: 322 training return: -514.1148416894262
episode: 323 training return: -535.2257573333559
epoch: 81 test_true_pfm: 325.9746052804338 sim_pfm: -418.7590391597117
episode: 324 training return: -474.0897427184712
episode: 325 training return: -523.2086948462189
episode: 326 training return: -502.7389583783479
episode: 327 training return: -493.9081357817798
epoch: 82 test_true_pfm: 237.0440329188638 sim_pfm: -420.6429150562013
episode: 328 training return: -516.1882580733791
episode: 329 training return: -562.6350852414658
episode: 330 training return: -537.6168359848114
episode: 331 training return: -518.5481917210184
epoch: 83 test_true_pfm: 303.4358558269163 sim_pfm: -424.7147128917048
episode: 332 training return: -522.7077832858414
episode: 333 training return: -586.8358686316781
episode: 334 training return: -537.6651835963394
episode: 335 training return: -561.0957730930201
epoch: 84 test_true_pfm: 63.74731944200442 sim_pfm: -450.41462463431634
episode: 336 training return: -512.3667335231855
episode: 337 training return: -511.50040414795865
episode: 338 training return: -542.9092030301352
episode: 339 training return: -551.1230813414847
epoch: 85 test_true_pfm: 290.02442601172675 sim_pfm: -433.3474394868888
episode: 340 training return: -501.4666730716829
episode: 341 training return: -523.376299933239
episode: 342 training return: -559.4803675290804
episode: 343 training return: -544.6077718651237
epoch: 86 test_true_pfm: 214.96477209797413 sim_pfm: -431.146400408799
episode: 344 training return: -512.9252184545842
episode: 345 training return: -529.6043061290374
episode: 346 training return: -516.0352990299907
episode: 347 training return: -532.0285655489463
epoch: 87 test_true_pfm: 308.2583060850533 sim_pfm: -417.14877957089374
episode: 348 training return: -502.4266744515056
episode: 349 training return: -546.0604004042926
episode: 350 training return: -512.1512397013155
episode: 351 training return: -528.8765175113668
epoch: 88 test_true_pfm: 267.8188905239622 sim_pfm: -420.17697925183984
episode: 352 training return: -533.3113423930679
episode: 353 training return: -517.4066422351373
episode: 354 training return: -520.6440906345069
episode: 355 training return: -480.877756286705
epoch: 89 test_true_pfm: 300.45624486414596 sim_pfm: -436.167618568784
episode: 356 training return: -503.34748281723347
episode: 357 training return: -538.2930556913966
episode: 358 training return: -509.9726010691027
episode: 359 training return: -550.1091392455497
epoch: 90 test_true_pfm: 30.063035584739822 sim_pfm: -450.25635376162137
episode: 360 training return: -542.2968449338723
episode: 361 training return: -504.6975702367976
episode: 362 training return: -518.6344344718392
episode: 363 training return: -529.4842679592131
epoch: 91 test_true_pfm: 324.3176192247295 sim_pfm: -404.90761172154384
episode: 364 training return: -511.69392578393945
episode: 365 training return: -596.5508191097343
episode: 366 training return: -487.9180271649276
episode: 367 training return: -529.0084639958934
epoch: 92 test_true_pfm: 229.94866775215078 sim_pfm: -404.926359103548
episode: 368 training return: -548.7900689440742
episode: 369 training return: -493.407784244388
episode: 370 training return: -545.0574730209174
episode: 371 training return: -509.0870707097265
epoch: 93 test_true_pfm: 235.93246594735857 sim_pfm: -435.9662470639135
episode: 372 training return: -519.068434735545
episode: 373 training return: -491.4407461691285
episode: 374 training return: -548.9692662227793
episode: 375 training return: -533.2738203990485
epoch: 94 test_true_pfm: 240.1803776595896 sim_pfm: -449.3676243774364
episode: 376 training return: -521.479521075945
episode: 377 training return: -491.75667793969563
episode: 378 training return: -551.5203844979976
episode: 379 training return: -557.2434315151418
epoch: 95 test_true_pfm: 333.886023787964 sim_pfm: -422.6878193039341
episode: 380 training return: -542.3236229226783
episode: 381 training return: -533.2206972330739
episode: 382 training return: -512.1379670731247
episode: 383 training return: -517.5871292672168
epoch: 96 test_true_pfm: 132.3713229425264 sim_pfm: -440.20348162615534
episode: 384 training return: -564.8275030657745
episode: 385 training return: -508.1774760017582
episode: 386 training return: -558.6237738395573
episode: 387 training return: -527.0758764945687
epoch: 97 test_true_pfm: 387.8697887918786 sim_pfm: -413.4402460074219
episode: 388 training return: -482.96000521598546
episode: 389 training return: -529.202820396278
episode: 390 training return: -496.46646577477406
episode: 391 training return: -524.0092356940077
epoch: 98 test_true_pfm: 138.24270885689526 sim_pfm: -373.21538348870075
episode: 392 training return: -535.4673906871786
episode: 393 training return: -512.5681776556311
episode: 394 training return: -519.1289063100681
episode: 395 training return: -540.7946642955973
epoch: 99 test_true_pfm: 298.4497603037242 sim_pfm: -427.29418643588843
episode: 396 training return: -531.0765124619091
episode: 397 training return: -523.4565577067729
episode: 398 training return: -552.7899912079416
episode: 399 training return: -568.5551902323515
epoch: 100 test_true_pfm: 127.51319898524359 sim_pfm: -480.36754706090977
episode: 400 training return: -514.3125232412305
episode: 401 training return: -555.0442400477377
episode: 402 training return: -768.3880499120913
episode: 403 training return: -500.45975683354163
epoch: 101 test_true_pfm: 320.1411214874444 sim_pfm: -442.16532813477096
episode: 404 training return: -508.01072863832064
episode: 405 training return: -515.6120533595906
episode: 406 training return: -482.859982781283
episode: 407 training return: -524.488369371236
epoch: 102 test_true_pfm: 446.51920238186614 sim_pfm: -393.2458659373815
episode: 408 training return: -500.0729044819943
episode: 409 training return: -525.746787665085
episode: 410 training return: -731.8282891599428
episode: 411 training return: -515.8565353429676
epoch: 103 test_true_pfm: 195.9369636190322 sim_pfm: -416.99707082030204
episode: 412 training return: -523.2433880745306
episode: 413 training return: -510.11905543660123
episode: 414 training return: -516.1459530565586
episode: 415 training return: -549.9889639449975
epoch: 104 test_true_pfm: 259.63068169258537 sim_pfm: -423.8493597011616
episode: 416 training return: -503.4926939801119
episode: 417 training return: -563.2179511718451
episode: 418 training return: -503.1119345238128
episode: 419 training return: -506.99264937880855
epoch: 105 test_true_pfm: 216.00780835267537 sim_pfm: -392.1064634817808
episode: 420 training return: -493.17932201142014
episode: 421 training return: -548.1952704950243
episode: 422 training return: -519.8000908800514
episode: 423 training return: -491.2910054443328
epoch: 106 test_true_pfm: 310.28074979229757 sim_pfm: -381.62686644796577
episode: 424 training return: -517.4356461013075
episode: 425 training return: -545.3715252965252
episode: 426 training return: -541.4319395426327
episode: 427 training return: -503.96436099282124
epoch: 107 test_true_pfm: 244.250154037903 sim_pfm: -432.04497822446433
episode: 428 training return: -512.6783581140422
episode: 429 training return: -481.9767704927207
episode: 430 training return: -481.3508911029833
episode: 431 training return: -518.5597989998547
epoch: 108 test_true_pfm: 309.0722478005191 sim_pfm: -413.65253938144656
episode: 432 training return: -551.9500259829737
episode: 433 training return: -529.7775020601398
episode: 434 training return: -554.2856920305337
episode: 435 training return: -715.4200468928035
epoch: 109 test_true_pfm: 251.2589596797869 sim_pfm: -441.65005557286605
episode: 436 training return: -537.1925403424937
episode: 437 training return: -519.5457162276571
episode: 438 training return: -528.884086357821
episode: 439 training return: -581.6502169082967
epoch: 110 test_true_pfm: 330.35526468360626 sim_pfm: -400.132601087498
episode: 440 training return: -503.90740104424236
episode: 441 training return: -492.9208890652201
episode: 442 training return: -530.7038928400143
episode: 443 training return: -519.9043151660849
epoch: 111 test_true_pfm: 262.258805492456 sim_pfm: -425.57792635938273
episode: 444 training return: -583.5036015385839
episode: 445 training return: -487.9667476893082
episode: 446 training return: -533.6976150619088
episode: 447 training return: -575.8217004588538
epoch: 112 test_true_pfm: 258.72410723902766 sim_pfm: -414.8249566752817
episode: 448 training return: -507.41266503934264
episode: 449 training return: -502.7620413279064
episode: 450 training return: -514.7833926671263
episode: 451 training return: -520.510795952419
epoch: 113 test_true_pfm: 221.37798294265826 sim_pfm: -391.42978746114585
episode: 452 training return: -535.4821500883837
episode: 453 training return: -546.9224122094449
episode: 454 training return: -550.4870515082063
episode: 455 training return: -503.78752001556666
epoch: 114 test_true_pfm: 241.12694340643668 sim_pfm: -403.4346893044183
episode: 456 training return: -525.7533178133122
episode: 457 training return: -532.9428942659658
episode: 458 training return: -529.4122519311122
episode: 459 training return: -495.88711278249343
epoch: 115 test_true_pfm: 351.76606503976024 sim_pfm: -382.5515134722398
episode: 460 training return: -485.59761895402806
episode: 461 training return: -541.5914945327694
episode: 462 training return: -564.1709507423319
episode: 463 training return: -526.9402512375424
epoch: 116 test_true_pfm: 119.08180282004746 sim_pfm: -432.01832668682056
episode: 464 training return: -546.8100801900558
episode: 465 training return: -551.7598095947614
episode: 466 training return: -540.0908309048514
episode: 467 training return: -549.2613260978111
epoch: 117 test_true_pfm: 237.96476804186045 sim_pfm: -426.74588449542784
episode: 468 training return: -548.9961137611753
episode: 469 training return: -567.5699565002296
episode: 470 training return: -535.6121761689508
episode: 471 training return: -505.0225736655469
epoch: 118 test_true_pfm: 226.92847532221688 sim_pfm: -430.87179286032233
episode: 472 training return: -490.84555679295994
episode: 473 training return: -521.9678064719283
episode: 474 training return: -567.1923518474327
episode: 475 training return: -536.4361832468758
epoch: 119 test_true_pfm: 302.00921231272747 sim_pfm: -415.19257228145625
episode: 476 training return: -507.46877345870394
episode: 477 training return: -564.2857603091381
episode: 478 training return: -522.8366595784366
episode: 479 training return: -523.0492827728314
epoch: 120 test_true_pfm: 208.82246038888084 sim_pfm: -433.4396257584927
episode: 480 training return: -523.6460987067895
episode: 481 training return: -535.51327997103
episode: 482 training return: -507.0593073161847
episode: 483 training return: -545.5603877313464
epoch: 121 test_true_pfm: 169.08395788975255 sim_pfm: -402.7056356100934
episode: 484 training return: -525.8890705228027
episode: 485 training return: -541.8808999069479
episode: 486 training return: -536.2526916525869
episode: 487 training return: -566.2854284205222
epoch: 122 test_true_pfm: 260.69167179056524 sim_pfm: -429.3955522318126
episode: 488 training return: -505.71915983260965
episode: 489 training return: -564.6374349204707
episode: 490 training return: -497.91108258279314
episode: 491 training return: -644.1099827179601
epoch: 123 test_true_pfm: 251.98974969942756 sim_pfm: -424.7358791152554
episode: 492 training return: -552.1797185902443
episode: 493 training return: -571.7213457576798
episode: 494 training return: -525.7938908286973
episode: 495 training return: -513.4873178081214
epoch: 124 test_true_pfm: 146.1083080683727 sim_pfm: -467.30045322348525
episode: 496 training return: -507.25124309027524
episode: 497 training return: -508.0622856883327
episode: 498 training return: -512.7445033078787
episode: 499 training return: -507.6165731358263
epoch: 125 test_true_pfm: 149.96028517180346 sim_pfm: -447.43646012030086
episode: 500 training return: -509.09438922670597
episode: 501 training return: -539.1718023839584
episode: 502 training return: -542.472093416242
episode: 503 training return: -494.708314344126
epoch: 126 test_true_pfm: 196.7635196401582 sim_pfm: -412.09337746023965
episode: 504 training return: -499.26183668597764
episode: 505 training return: -539.7985371731851
episode: 506 training return: -491.8760253730629
episode: 507 training return: -545.2254409374096
epoch: 127 test_true_pfm: 216.37842548695008 sim_pfm: -427.81194278378524
episode: 508 training return: -499.33778867855483
episode: 509 training return: -526.3455807853865
episode: 510 training return: -503.08061806022477
episode: 511 training return: -529.0021631861082
epoch: 128 test_true_pfm: 296.26718716865906 sim_pfm: -387.9022469555473
episode: 512 training return: -570.3151885534248
episode: 513 training return: -518.8773332067266
episode: 514 training return: -499.9728745690955
episode: 515 training return: -505.66160900450643
epoch: 129 test_true_pfm: 269.00758496688286 sim_pfm: -447.68693873094304
episode: 516 training return: -525.2779645806181
episode: 517 training return: -551.5857392086809
episode: 518 training return: -550.1258303267682
episode: 519 training return: -531.2939968471275
epoch: 130 test_true_pfm: 186.68800122073802 sim_pfm: -454.49233078171255
episode: 520 training return: -512.340156731874
episode: 521 training return: -507.9746582907291
episode: 522 training return: -527.8099290214702
episode: 523 training return: -508.7359112873883
epoch: 131 test_true_pfm: 295.2474403602694 sim_pfm: -411.3292248181929
episode: 524 training return: -565.7324331937987
episode: 525 training return: -492.9489752041947
episode: 526 training return: -512.8055282508565
episode: 527 training return: -542.7191190780113
epoch: 132 test_true_pfm: 104.25365893733071 sim_pfm: -443.4974712288518
episode: 528 training return: -518.6330349060133
episode: 529 training return: -526.4680303858502
episode: 530 training return: -520.9644917306794
episode: 531 training return: -565.7741200720056
epoch: 133 test_true_pfm: 207.97608851162386 sim_pfm: -374.6684357053704
episode: 532 training return: -486.8893830379962
episode: 533 training return: -493.68469312507966
episode: 534 training return: -506.46772911051596
episode: 535 training return: -534.8243539225251
epoch: 134 test_true_pfm: 296.48943676301866 sim_pfm: -461.25103807119467
episode: 536 training return: -501.9881125654034
episode: 537 training return: -507.85112496939746
episode: 538 training return: -488.18191372919654
episode: 539 training return: -518.6923569697672
epoch: 135 test_true_pfm: 310.7286803087995 sim_pfm: -379.6550271774657
episode: 540 training return: -504.583868161241
episode: 541 training return: -522.9046754682527
episode: 542 training return: -515.2593269137254
episode: 543 training return: -529.7507885446695
epoch: 136 test_true_pfm: 270.9537876063355 sim_pfm: -410.0302689224804
episode: 544 training return: -541.5724932525461
episode: 545 training return: -513.2691182561927
episode: 546 training return: -510.5347088353162
episode: 547 training return: -506.5634033032438
epoch: 137 test_true_pfm: 228.19720746581837 sim_pfm: -433.256080416236
episode: 548 training return: -520.4200931688365
episode: 549 training return: -523.3614211190352
episode: 550 training return: -481.24329547904193
episode: 551 training return: -516.9969749899589
epoch: 138 test_true_pfm: 258.58405471135103 sim_pfm: -446.0560441624306
episode: 552 training return: -515.6342507198013
episode: 553 training return: -489.60647012355344
episode: 554 training return: -520.165411873475
episode: 555 training return: -562.6341088291538
epoch: 139 test_true_pfm: 163.28964485983275 sim_pfm: -394.7361857850653
episode: 556 training return: -514.8011781778571
episode: 557 training return: -512.9747691050436
episode: 558 training return: -472.9640997704993
episode: 559 training return: -472.40839890263624
epoch: 140 test_true_pfm: 314.0884608677765 sim_pfm: -396.5261013367305
episode: 560 training return: -508.5141027915894
episode: 561 training return: -492.1409785554432
episode: 562 training return: -483.7724926821173
episode: 563 training return: -508.5555947879477
epoch: 141 test_true_pfm: 288.19733347616506 sim_pfm: -403.7931726610943
episode: 564 training return: -493.7373329814444
episode: 565 training return: -526.9551168694107
episode: 566 training return: -499.8634751230997
episode: 567 training return: -525.7725799545873
epoch: 142 test_true_pfm: 258.23465947363644 sim_pfm: -441.09612380728095
episode: 568 training return: -507.20870447000897
episode: 569 training return: -523.5229866136154
episode: 570 training return: -518.8194865842627
episode: 571 training return: -513.8708394949401
epoch: 143 test_true_pfm: 193.3790635292157 sim_pfm: -425.86782154596
episode: 572 training return: -522.998332511069
episode: 573 training return: -513.1370645923656
episode: 574 training return: -554.9723722195383
episode: 575 training return: -471.4656447582215
epoch: 144 test_true_pfm: 312.8937292800775 sim_pfm: -392.4800610857769
episode: 576 training return: -507.00796032367185
episode: 577 training return: -544.9047925664022
episode: 578 training return: -504.43705771224177
episode: 579 training return: -519.62185898685
epoch: 145 test_true_pfm: 227.28039378116088 sim_pfm: -402.54134614053663
episode: 580 training return: -477.01874700041947
episode: 581 training return: -524.8632007482171
episode: 582 training return: -498.43799325427347
episode: 583 training return: -571.3561957378788
epoch: 146 test_true_pfm: 260.6709577986789 sim_pfm: -390.3794045519824
episode: 584 training return: -526.6456257811498
episode: 585 training return: -521.5102599502027
episode: 586 training return: -542.7714738404387
episode: 587 training return: -514.3339895431839
epoch: 147 test_true_pfm: 299.777173448056 sim_pfm: -399.8926318951544
episode: 588 training return: -517.1872503120185
episode: 589 training return: -513.6377494945938
episode: 590 training return: -496.7195475108069
episode: 591 training return: -493.9466529742336
epoch: 148 test_true_pfm: 288.75416888445335 sim_pfm: -370.2742639705887
episode: 592 training return: -456.6135538507664
episode: 593 training return: -532.7007157629766
episode: 594 training return: -490.88032316941593
episode: 595 training return: -491.1372411667272
epoch: 149 test_true_pfm: 251.59889263551636 sim_pfm: -417.7663666247504
episode: 596 training return: -510.0269214405043
episode: 597 training return: -473.2998263237252
episode: 598 training return: -537.0060460070854
episode: 599 training return: -497.05588357027017
epoch: 150 test_true_pfm: 225.79454409987366 sim_pfm: -407.48676985653395
