epoch: 0 training_loss 0.16789154995232822 test_loss: 0.11284692287445068
epoch: 1 training_loss 0.1076462385430932 test_loss: 0.12529023885726928
epoch: 2 training_loss 0.10163750927895307 test_loss: 0.1063427209854126
epoch: 3 training_loss 0.10169062446802854 test_loss: 0.11576668024063111
epoch: 4 training_loss 0.1024967734515667 test_loss: 0.08865011334419251
epoch: 5 training_loss 0.09678609784692525 test_loss: 0.09200968742370605
epoch: 6 training_loss 0.09925578434020281 test_loss: 0.10983887910842896
epoch: 7 training_loss 0.09488446589559317 test_loss: 0.10065276622772217
epoch: 8 training_loss 0.09529372787103058 test_loss: 0.11141501665115357
epoch: 9 training_loss 0.09153694473206997 test_loss: 0.09587549567222595
epoch: 10 training_loss 0.09324742823839188 test_loss: 0.09090530276298522
epoch: 11 training_loss 0.0896242144331336 test_loss: 0.08387681245803832
epoch: 12 training_loss 0.09481618337333203 test_loss: 0.10110573768615723
epoch: 13 training_loss 0.09370123606175185 test_loss: 0.09808016419410706
epoch: 14 training_loss 0.0938009325414896 test_loss: 0.0917130947113037
epoch: 15 training_loss 0.09003242250531912 test_loss: 0.0738642930984497
epoch: 16 training_loss 0.09704999379813671 test_loss: 0.0973289966583252
epoch: 17 training_loss 0.08844329120591282 test_loss: 0.0936048686504364
epoch: 18 training_loss 0.09456523820757866 test_loss: 0.09765712022781373
epoch: 19 training_loss 0.09687350239604711 test_loss: 0.08482804894447327
epoch: 20 training_loss 0.09087886301800609 test_loss: 0.09887003302574157
epoch: 21 training_loss 0.0885780781134963 test_loss: 0.08503442406654357
epoch: 22 training_loss 0.09046872947365045 test_loss: 0.10607825517654419
epoch: 23 training_loss 0.08579706400632858 test_loss: 0.09339776635169983
epoch: 24 training_loss 0.08917342834174632 test_loss: 0.08954595923423767
epoch: 25 training_loss 0.09317378111183644 test_loss: 0.09247901439666747
epoch: 26 training_loss 0.09025580178946256 test_loss: 0.0787006676197052
epoch: 27 training_loss 0.09384499698877334 test_loss: 0.08832838535308837
epoch: 28 training_loss 0.09273962333798408 test_loss: 0.07687007784843444
epoch: 29 training_loss 0.09139823865145445 test_loss: 0.08800539374351501
epoch: 30 training_loss 0.09110680181533098 test_loss: 0.08304184675216675
epoch: 31 training_loss 0.09004443418234587 test_loss: 0.10223636627197266
epoch: 32 training_loss 0.09001585174351931 test_loss: 0.09078842401504517
epoch: 33 training_loss 0.08895891677588225 test_loss: 0.10532897710800171
epoch: 34 training_loss 0.08852064929902553 test_loss: 0.0892212450504303
epoch: 35 training_loss 0.09204504247754812 test_loss: 0.09751176834106445
epoch: 36 training_loss 0.09371075894683599 test_loss: 0.08972880840301514
epoch: 37 training_loss 0.09212722145020961 test_loss: 0.09535289406776429
epoch: 38 training_loss 0.09149482049047947 test_loss: 0.0916300356388092
epoch: 39 training_loss 0.09427160080522298 test_loss: 0.10466276407241822
epoch: 40 training_loss 0.09295034669339657 test_loss: 0.10031009912490844
epoch: 41 training_loss 0.09007908701896668 test_loss: 0.10632075071334839
epoch: 42 training_loss 0.08338877618312836 test_loss: 0.07849990129470825
epoch: 43 training_loss 0.09121191833168268 test_loss: 0.1034539818763733
epoch: 44 training_loss 0.09366435702890158 test_loss: 0.08254892826080322
epoch: 45 training_loss 0.08935406588017941 test_loss: 0.1001559853553772
epoch: 46 training_loss 0.09075840696692467 test_loss: 0.09106749296188354
epoch: 47 training_loss 0.09169574556872248 test_loss: 0.06849915981292724
epoch: 48 training_loss 0.08659007137641311 test_loss: 0.07533383965492249
epoch: 49 training_loss 0.09458952963352203 test_loss: 0.08517693877220153
epoch: 50 training_loss 0.08908954989165067 test_loss: 0.0949836552143097
epoch: 51 training_loss 0.09147185280919075 test_loss: 0.09136794805526734
epoch: 52 training_loss 0.08825670581310988 test_loss: 0.11120209693908692
epoch: 53 training_loss 0.0930018413066864 test_loss: 0.09161323308944702
epoch: 54 training_loss 0.08795861970633269 test_loss: 0.10262882709503174
epoch: 55 training_loss 0.08939798254519701 test_loss: 0.10094308853149414
epoch: 56 training_loss 0.08834149431437253 test_loss: 0.085296893119812
epoch: 57 training_loss 0.08654593043029309 test_loss: 0.10175442695617676
epoch: 58 training_loss 0.0845557013899088 test_loss: 0.07814084887504577
epoch: 59 training_loss 0.08990725196897983 test_loss: 0.09800276756286622
epoch: 60 training_loss 0.08521161517128348 test_loss: 0.07487376928329467
epoch: 61 training_loss 0.0880848502367735 test_loss: 0.1066247820854187
epoch: 62 training_loss 0.08676005538553 test_loss: 0.09872876405715943
epoch: 63 training_loss 0.09173726418986916 test_loss: 0.09026663899421691
epoch: 64 training_loss 0.08377969259396195 test_loss: 0.09437984228134155
epoch: 65 training_loss 0.08163913019001484 test_loss: 0.0860123336315155
epoch: 66 training_loss 0.09211736194789409 test_loss: 0.09744263291358948
epoch: 67 training_loss 0.08755451237782835 test_loss: 0.09632506966590881
epoch: 68 training_loss 0.08964330703020096 test_loss: 0.09382275938987732
epoch: 69 training_loss 0.08569432444870471 test_loss: 0.07673864364624024
epoch: 70 training_loss 0.08914717510342599 test_loss: 0.08452969789505005
epoch: 71 training_loss 0.08817799590528011 test_loss: 0.09985648989677429
epoch: 72 training_loss 0.09279478367418051 test_loss: 0.09179737567901611
epoch: 73 training_loss 0.08937892824411392 test_loss: 0.09912164211273193
epoch: 74 training_loss 0.09148943938314914 test_loss: 0.08769173622131347
epoch: 75 training_loss 0.08570382807403804 test_loss: 0.0816178023815155
epoch: 76 training_loss 0.08901433121412992 test_loss: 0.09144818186759948
epoch: 77 training_loss 0.08876030094921589 test_loss: 0.0794168770313263
epoch: 78 training_loss 0.0843697140365839 test_loss: 0.08495954871177673
epoch: 79 training_loss 0.0863954846188426 test_loss: 0.09757550954818725
epoch: 80 training_loss 0.08794009573757648 test_loss: 0.11061187982559204
epoch: 81 training_loss 0.08971258856356144 test_loss: 0.09312304258346557
epoch: 82 training_loss 0.09105614375323057 test_loss: 0.0941500186920166
epoch: 83 training_loss 0.08836303770542145 test_loss: 0.09063661694526673
epoch: 84 training_loss 0.08705339852720499 test_loss: 0.09566612243652343
epoch: 85 training_loss 0.0912393406406045 test_loss: 0.10204312801361085
epoch: 86 training_loss 0.08450240766629577 test_loss: 0.08539193272590637
epoch: 87 training_loss 0.0855780834145844 test_loss: 0.07688804268836975
epoch: 88 training_loss 0.08734878761693836 test_loss: 0.08948644995689392
epoch: 89 training_loss 0.08744642857462168 test_loss: 0.09144812822341919
epoch: 90 training_loss 0.08026548124849796 test_loss: 0.09727530479431153
epoch: 91 training_loss 0.08715380482375622 test_loss: 0.07555333375930787
epoch: 92 training_loss 0.0886481049656868 test_loss: 0.08382962346076965
epoch: 93 training_loss 0.08945696594193578 test_loss: 0.0841200053691864
epoch: 94 training_loss 0.08506758600473403 test_loss: 0.09823682308197021
epoch: 95 training_loss 0.08945845112204552 test_loss: 0.09977332949638366
epoch: 96 training_loss 0.08533370960503817 test_loss: 0.08707126975059509
epoch: 97 training_loss 0.08706362053751945 test_loss: 0.09185000658035278
epoch: 98 training_loss 0.08661542888730764 test_loss: 0.10328463315963746
epoch: 99 training_loss 0.08662250872701406 test_loss: 0.07515015602111816
epoch: 100 training_loss 0.09406190749257803 test_loss: 0.09153462052345276
epoch: 101 training_loss 0.09082006368786097 test_loss: 0.09449263215065003
epoch: 102 training_loss 0.08670095309615135 test_loss: 0.09294057488441468
epoch: 103 training_loss 0.09085394425317644 test_loss: 0.08657665848731995
epoch: 104 training_loss 0.0899825806543231 test_loss: 0.1016356348991394
epoch: 105 training_loss 0.08396198522299528 test_loss: 0.07924252152442932
epoch: 106 training_loss 0.08992031384259462 test_loss: 0.09496386051177978
epoch: 107 training_loss 0.0878136895224452 test_loss: 0.08681680560112
epoch: 108 training_loss 0.08980208083987236 test_loss: 0.10325888395309449
epoch: 109 training_loss 0.08742961779236794 test_loss: 0.0915306031703949
epoch: 110 training_loss 0.08766296584159136 test_loss: 0.10489424467086791
epoch: 111 training_loss 0.08841714709997177 test_loss: 0.09551594257354737
epoch: 112 training_loss 0.08828960038721562 test_loss: 0.09282812476158142
epoch: 113 training_loss 0.08778274785727262 test_loss: 0.09486485719680786
epoch: 114 training_loss 0.09214795783162116 test_loss: 0.07776042222976684
epoch: 115 training_loss 0.08643126714974642 test_loss: 0.07899230718612671
epoch: 116 training_loss 0.0905896726436913 test_loss: 0.11140264272689819
epoch: 117 training_loss 0.0837038542702794 test_loss: 0.08154731392860412
epoch: 118 training_loss 0.09332067735493182 test_loss: 0.09307407736778259
epoch: 119 training_loss 0.08677713224664331 test_loss: 0.08782718181610108
epoch: 0 training_loss 20.03296259880066 test_loss: 13.047740173339843
epoch: 1 training_loss 10.260026025772095 test_loss: 8.393525695800781
epoch: 2 training_loss 7.588093128204346 test_loss: 6.849669647216797
epoch: 3 training_loss 6.365199742317199 test_loss: 5.768308639526367
epoch: 4 training_loss 5.364001989364624 test_loss: 5.114240646362305
epoch: 5 training_loss 4.803221752643585 test_loss: 4.394174957275391
epoch: 6 training_loss 4.458350486755371 test_loss: 4.208362197875976
epoch: 7 training_loss 4.13866215467453 test_loss: 4.05232048034668
epoch: 8 training_loss 3.855992681980133 test_loss: 3.8724014282226564
epoch: 9 training_loss 3.669966652393341 test_loss: 3.5224327087402343
epoch: 10 training_loss 3.5545790457725523 test_loss: 3.3899227142333985
epoch: 11 training_loss 3.359552938938141 test_loss: 3.3423084259033202
epoch: 12 training_loss 3.1797174787521363 test_loss: 2.992510223388672
epoch: 13 training_loss 3.133723750114441 test_loss: 3.002120018005371
epoch: 14 training_loss 3.045417227745056 test_loss: 3.1405832290649416
epoch: 15 training_loss 2.93419704914093 test_loss: 2.8578752517700194
epoch: 16 training_loss 2.7895160365104674 test_loss: 2.603919792175293
epoch: 17 training_loss 2.720272946357727 test_loss: 2.53234920501709
epoch: 18 training_loss 2.6077262783050537 test_loss: 2.4749734878540037
epoch: 19 training_loss 2.5675575733184814 test_loss: 2.4548498153686524
epoch: 20 training_loss 2.469583297967911 test_loss: 2.4710474014282227
epoch: 21 training_loss 2.3470099472999575 test_loss: 2.4568248748779298
epoch: 22 training_loss 2.281982797384262 test_loss: 2.2173171997070313
epoch: 23 training_loss 2.259451434612274 test_loss: 2.117541694641113
epoch: 24 training_loss 2.1923822379112243 test_loss: 2.195431137084961
epoch: 25 training_loss 2.086347576379776 test_loss: 2.032805252075195
epoch: 26 training_loss 2.1235974717140196 test_loss: 2.1545177459716798
epoch: 27 training_loss 2.041600193977356 test_loss: 1.8769758224487305
epoch: 28 training_loss 1.9950105905532838 test_loss: 1.9099369049072266
epoch: 29 training_loss 1.9754998421669006 test_loss: 1.7647066116333008
epoch: 30 training_loss 1.8898978352546691 test_loss: 1.6860761642456055
epoch: 31 training_loss 1.8506107079982757 test_loss: 1.8290918350219727
epoch: 32 training_loss 1.8110090494155884 test_loss: 1.762852096557617
epoch: 33 training_loss 1.7904240465164185 test_loss: 1.7237060546875
epoch: 34 training_loss 1.6859008002281188 test_loss: 1.8536897659301759
epoch: 35 training_loss 1.8036468470096587 test_loss: 2.011099433898926
epoch: 36 training_loss 1.766682312488556 test_loss: 1.738442611694336
epoch: 37 training_loss 1.6491361570358276 test_loss: 1.4605236053466797
epoch: 38 training_loss 1.622631846666336 test_loss: 1.5842908859252929
epoch: 39 training_loss 1.5829960739612579 test_loss: 1.6031221389770507
epoch: 40 training_loss 1.5482065820693969 test_loss: 1.5508127212524414
epoch: 41 training_loss 1.547722851037979 test_loss: 1.4997079849243165
epoch: 42 training_loss 1.4601907861232757 test_loss: 1.3989906311035156
epoch: 43 training_loss 1.4573714745044708 test_loss: 1.4008005142211915
epoch: 44 training_loss 1.4640200662612914 test_loss: 1.3905086517333984
epoch: 45 training_loss 1.4525398981571198 test_loss: 1.570211696624756
epoch: 46 training_loss 1.4151037061214446 test_loss: 1.3090974807739257
epoch: 47 training_loss 1.4615986442565918 test_loss: 1.4220807075500488
epoch: 48 training_loss 1.3659972631931305 test_loss: 1.4945326805114747
epoch: 49 training_loss 1.3973335355520249 test_loss: 1.9486103057861328
epoch: 50 training_loss 1.4030548906326294 test_loss: 1.3606743812561035
epoch: 51 training_loss 1.3605417954921721 test_loss: 1.3561758995056152
epoch: 52 training_loss 1.3868091678619385 test_loss: 1.2455694198608398
epoch: 53 training_loss 1.3569223511219024 test_loss: 1.4437016487121581
epoch: 54 training_loss 1.3467590868473054 test_loss: 1.1735700607299804
epoch: 55 training_loss 1.3504998111724853 test_loss: 1.3858657836914063
epoch: 56 training_loss 1.293513503074646 test_loss: 1.4195469856262206
epoch: 57 training_loss 1.2814222115278244 test_loss: 1.1629486083984375
epoch: 58 training_loss 1.3005507481098175 test_loss: 1.208540439605713
epoch: 59 training_loss 1.2638551157712936 test_loss: 1.1473869323730468
epoch: 60 training_loss 1.2475824397802353 test_loss: 1.170712947845459
epoch: 61 training_loss 1.2690264797210693 test_loss: 1.3680919647216796
epoch: 62 training_loss 1.227862793803215 test_loss: 1.1322846412658691
epoch: 63 training_loss 1.263381021618843 test_loss: 1.1747000694274903
epoch: 64 training_loss 1.2431074714660644 test_loss: 1.1734599113464355
epoch: 65 training_loss 1.2209646248817443 test_loss: 1.0816802024841308
epoch: 66 training_loss 1.274568955898285 test_loss: 1.366961669921875
epoch: 67 training_loss 1.1781456619501114 test_loss: 1.1802366256713868
epoch: 68 training_loss 1.2697844004631043 test_loss: 1.363704013824463
epoch: 69 training_loss 1.1806276220083236 test_loss: 1.2826372146606446
epoch: 70 training_loss 1.1421592873334885 test_loss: 1.155618667602539
epoch: 71 training_loss 1.1430316466093062 test_loss: 1.161301612854004
epoch: 72 training_loss 1.2084034073352814 test_loss: 1.1641695976257325
epoch: 73 training_loss 1.1328092604875564 test_loss: 1.078524684906006
epoch: 74 training_loss 1.1099281108379364 test_loss: 1.1297237396240234
epoch: 75 training_loss 1.1192642229795455 test_loss: 1.0518857002258302
epoch: 76 training_loss 1.1284255629777908 test_loss: 1.0297254562377929
epoch: 77 training_loss 1.1286939495801926 test_loss: 1.110341453552246
epoch: 78 training_loss 1.1066256594657897 test_loss: 0.99801025390625
epoch: 79 training_loss 1.071195570230484 test_loss: 1.0291647911071777
epoch: 80 training_loss 1.0918402940034866 test_loss: 1.1273314476013183
epoch: 81 training_loss 1.1093000209331512 test_loss: 1.2078351974487305
epoch: 82 training_loss 1.0641731691360474 test_loss: 1.0650578498840333
epoch: 83 training_loss 1.0367197912931443 test_loss: 0.9906191825866699
epoch: 84 training_loss 1.0582359504699708 test_loss: 1.132791519165039
epoch: 85 training_loss 1.0470367765426636 test_loss: 0.9883564949035645
epoch: 86 training_loss 1.0147355055809022 test_loss: 1.0388840675354003
epoch: 87 training_loss 1.0405769151449205 test_loss: 1.0707406044006347
epoch: 88 training_loss 1.0438025218248368 test_loss: 0.9845944404602051
epoch: 89 training_loss 1.064296788573265 test_loss: 1.007764720916748
epoch: 90 training_loss 1.0223257184028625 test_loss: 0.9880890846252441
epoch: 91 training_loss 1.0642361450195312 test_loss: 0.8934348106384278
epoch: 92 training_loss 0.9836070692539215 test_loss: 0.973232650756836
epoch: 93 training_loss 1.061991613507271 test_loss: 0.9107994079589844
epoch: 94 training_loss 1.014092474579811 test_loss: 0.9035361289978028
epoch: 95 training_loss 0.9458767658472061 test_loss: 1.0788055419921876
epoch: 96 training_loss 1.0435308641195298 test_loss: 0.8989398956298829
epoch: 97 training_loss 1.0389345759153366 test_loss: 1.2990979194641112
epoch: 98 training_loss 0.9616785502433777 test_loss: 0.9148503303527832
epoch: 99 training_loss 0.9322840023040772 test_loss: 0.9804529190063477
epoch: 100 training_loss 0.9633788645267487 test_loss: 0.9448870658874512
epoch: 101 training_loss 1.0131301426887511 test_loss: 1.046288013458252
epoch: 102 training_loss 0.9967168545722962 test_loss: 1.0554926872253418
epoch: 103 training_loss 0.9246143293380737 test_loss: 0.8192444801330566
epoch: 104 training_loss 0.9208395314216614 test_loss: 0.9106284141540527
epoch: 105 training_loss 0.9659541839361191 test_loss: 0.8548079490661621
epoch: 106 training_loss 0.9288822346925736 test_loss: 0.8558768272399903
epoch: 107 training_loss 0.9439161264896393 test_loss: 0.9770853996276856
epoch: 108 training_loss 0.9745014142990113 test_loss: 0.9781147956848144
epoch: 109 training_loss 0.9387812024354935 test_loss: 0.9106493949890136
epoch: 110 training_loss 0.968971152305603 test_loss: 1.0597246170043946
epoch: 111 training_loss 0.9704133081436157 test_loss: 1.187146282196045
epoch: 112 training_loss 0.9632570171356201 test_loss: 0.8899971961975097
epoch: 113 training_loss 0.9395066702365875 test_loss: 0.824619197845459
epoch: 114 training_loss 0.9311471611261368 test_loss: 0.9867318153381348
epoch: 115 training_loss 0.8455474764108658 test_loss: 0.8921419143676758
epoch: 116 training_loss 0.8708846521377563 test_loss: 0.8442886352539063
epoch: 117 training_loss 0.8936499834060669 test_loss: 0.9461433410644531
epoch: 118 training_loss 0.8926443761587143 test_loss: 0.9007826805114746
epoch: 119 training_loss 0.8922241562604905 test_loss: 0.8235031127929687
142.41000771635572
episode: 0 training return: tensor(104.4480, device='cuda:0')
episode: 1 training return: tensor(122.8182, device='cuda:0')
episode: 2 training return: tensor(124.7525, device='cuda:0')
episode: 3 training return: tensor(122.8029, device='cuda:0')
epoch: 1 test_true_pfm: 141.4546372759528 sim_pfm: 119.59387136680888
episode: 4 training return: tensor(127.0071, device='cuda:0')
episode: 5 training return: tensor(120.7793, device='cuda:0')
episode: 6 training return: tensor(119.1807, device='cuda:0')
episode: 7 training return: tensor(111.8890, device='cuda:0')
epoch: 2 test_true_pfm: 137.11872300764503 sim_pfm: 114.74796044271207
episode: 8 training return: tensor(112.7052, device='cuda:0')
episode: 9 training return: tensor(120.1647, device='cuda:0')
episode: 10 training return: tensor(126.6099, device='cuda:0')
episode: 11 training return: tensor(131.2131, device='cuda:0')
epoch: 3 test_true_pfm: 140.5290806416616 sim_pfm: 125.78637030627578
episode: 12 training return: tensor(107.0874, device='cuda:0')
episode: 13 training return: tensor(127.0037, device='cuda:0')
episode: 14 training return: tensor(118.2513, device='cuda:0')
episode: 15 training return: tensor(131.4272, device='cuda:0')
epoch: 4 test_true_pfm: 139.4132294332964 sim_pfm: 120.98573974811006
episode: 16 training return: tensor(111.6590, device='cuda:0')
episode: 17 training return: tensor(117.5265, device='cuda:0')
episode: 18 training return: tensor(130.2473, device='cuda:0')
episode: 19 training return: tensor(128.7118, device='cuda:0')
epoch: 5 test_true_pfm: 139.04352605681976 sim_pfm: 120.85728270964464
episode: 20 training return: tensor(130.8898, device='cuda:0')
episode: 21 training return: tensor(124.3471, device='cuda:0')
episode: 22 training return: tensor(133.0589, device='cuda:0')
episode: 23 training return: tensor(142.0570, device='cuda:0')
epoch: 6 test_true_pfm: 138.56335721871946 sim_pfm: 129.97827563721222
episode: 24 training return: tensor(130.6055, device='cuda:0')
episode: 25 training return: tensor(129.8801, device='cuda:0')
episode: 26 training return: tensor(121.5175, device='cuda:0')
episode: 27 training return: tensor(127.1379, device='cuda:0')
epoch: 7 test_true_pfm: 142.6964767401686 sim_pfm: 129.09769468767917
episode: 28 training return: tensor(124.9137, device='cuda:0')
episode: 29 training return: tensor(126.8337, device='cuda:0')
episode: 30 training return: tensor(131.9368, device='cuda:0')
episode: 31 training return: tensor(122.3255, device='cuda:0')
epoch: 8 test_true_pfm: 141.99083999051783 sim_pfm: 130.26689016944147
episode: 32 training return: tensor(127.9997, device='cuda:0')
episode: 33 training return: tensor(132.0625, device='cuda:0')
episode: 34 training return: tensor(127.0242, device='cuda:0')
episode: 35 training return: tensor(132.3887, device='cuda:0')
epoch: 9 test_true_pfm: 141.06684248168207 sim_pfm: 135.61087394813075
episode: 36 training return: tensor(134.8040, device='cuda:0')
episode: 37 training return: tensor(127.0144, device='cuda:0')
episode: 38 training return: tensor(133.1241, device='cuda:0')
episode: 39 training return: tensor(135.6936, device='cuda:0')
epoch: 10 test_true_pfm: 139.99730156529614 sim_pfm: 126.38940240647644
episode: 40 training return: tensor(128.9276, device='cuda:0')
episode: 41 training return: tensor(127.5453, device='cuda:0')
episode: 42 training return: tensor(138.7242, device='cuda:0')
episode: 43 training return: tensor(134.0469, device='cuda:0')
epoch: 11 test_true_pfm: 142.46825583552555 sim_pfm: 132.41907987210433
episode: 44 training return: tensor(128.1287, device='cuda:0')
episode: 45 training return: tensor(142.1692, device='cuda:0')
episode: 46 training return: tensor(108.4497, device='cuda:0')
episode: 47 training return: tensor(132.8222, device='cuda:0')
epoch: 12 test_true_pfm: 141.80235390860844 sim_pfm: 134.4175021929259
episode: 48 training return: tensor(134.9393, device='cuda:0')
episode: 49 training return: tensor(143.4616, device='cuda:0')
episode: 50 training return: tensor(132.7204, device='cuda:0')
episode: 51 training return: tensor(127.8109, device='cuda:0')
epoch: 13 test_true_pfm: 139.19294512416704 sim_pfm: 143.46238917094888
episode: 52 training return: tensor(136.7077, device='cuda:0')
episode: 53 training return: tensor(138.1663, device='cuda:0')
episode: 54 training return: tensor(140.2003, device='cuda:0')
episode: 55 training return: tensor(142.0385, device='cuda:0')
epoch: 14 test_true_pfm: 143.48572171071868 sim_pfm: 138.05583058272606
episode: 56 training return: tensor(144.3456, device='cuda:0')
episode: 57 training return: tensor(140.3675, device='cuda:0')
episode: 58 training return: tensor(146.5576, device='cuda:0')
episode: 59 training return: tensor(120.5630, device='cuda:0')
epoch: 15 test_true_pfm: 145.95296636619702 sim_pfm: 141.98033382020077
episode: 60 training return: tensor(140.6620, device='cuda:0')
episode: 61 training return: tensor(138.6271, device='cuda:0')
episode: 62 training return: tensor(137.5839, device='cuda:0')
episode: 63 training return: tensor(143.9808, device='cuda:0')
epoch: 16 test_true_pfm: 137.79352289813698 sim_pfm: 139.121899947396
episode: 64 training return: tensor(129.4648, device='cuda:0')
episode: 65 training return: tensor(144.7804, device='cuda:0')
episode: 66 training return: tensor(147.9695, device='cuda:0')
episode: 67 training return: tensor(136.6089, device='cuda:0')
epoch: 17 test_true_pfm: 142.05670935799188 sim_pfm: 145.64319119947032
episode: 68 training return: tensor(137.0686, device='cuda:0')
episode: 69 training return: tensor(150.6445, device='cuda:0')
episode: 70 training return: tensor(132.5541, device='cuda:0')
episode: 71 training return: tensor(149.3590, device='cuda:0')
epoch: 18 test_true_pfm: 146.12130897089065 sim_pfm: 146.31041840346296
episode: 72 training return: tensor(141.1439, device='cuda:0')
episode: 73 training return: tensor(147.3705, device='cuda:0')
episode: 74 training return: tensor(141.0674, device='cuda:0')
episode: 75 training return: tensor(149.8696, device='cuda:0')
epoch: 19 test_true_pfm: 143.5823508368871 sim_pfm: 148.51488950554048
episode: 76 training return: tensor(127.5695, device='cuda:0')
episode: 77 training return: tensor(147.6371, device='cuda:0')
episode: 78 training return: tensor(145.1292, device='cuda:0')
episode: 79 training return: tensor(145.3954, device='cuda:0')
epoch: 20 test_true_pfm: 141.55499903249978 sim_pfm: 146.57943394926843
episode: 80 training return: tensor(146.5332, device='cuda:0')
episode: 81 training return: tensor(146.5040, device='cuda:0')
episode: 82 training return: tensor(146.8047, device='cuda:0')
episode: 83 training return: tensor(156.6290, device='cuda:0')
epoch: 21 test_true_pfm: 142.18778623389682 sim_pfm: 141.22619478840497
episode: 84 training return: tensor(149.5909, device='cuda:0')
episode: 85 training return: tensor(150.3690, device='cuda:0')
episode: 86 training return: tensor(139.6459, device='cuda:0')
episode: 87 training return: tensor(152.0304, device='cuda:0')
epoch: 22 test_true_pfm: 140.4161356002124 sim_pfm: 139.551485358621
episode: 88 training return: tensor(130.2589, device='cuda:0')
episode: 89 training return: tensor(142.2086, device='cuda:0')
episode: 90 training return: tensor(142.3854, device='cuda:0')
episode: 91 training return: tensor(137.9456, device='cuda:0')
epoch: 23 test_true_pfm: 140.06856727146948 sim_pfm: 143.45305806640536
episode: 92 training return: tensor(141.8426, device='cuda:0')
episode: 93 training return: tensor(143.2119, device='cuda:0')
episode: 94 training return: tensor(139.1053, device='cuda:0')
episode: 95 training return: tensor(149.4898, device='cuda:0')
epoch: 24 test_true_pfm: 141.242429579335 sim_pfm: 142.42893982059906
episode: 96 training return: tensor(141.8644, device='cuda:0')
episode: 97 training return: tensor(136.4612, device='cuda:0')
episode: 98 training return: tensor(139.6819, device='cuda:0')
episode: 99 training return: tensor(150.8656, device='cuda:0')
epoch: 25 test_true_pfm: 137.25190026838624 sim_pfm: 150.8426414309186
episode: 100 training return: tensor(146.1760, device='cuda:0')
episode: 101 training return: tensor(136.8253, device='cuda:0')
episode: 102 training return: tensor(149.8002, device='cuda:0')
episode: 103 training return: tensor(143.5903, device='cuda:0')
epoch: 26 test_true_pfm: 143.56639741263444 sim_pfm: 143.71666008822504
episode: 104 training return: tensor(149.0373, device='cuda:0')
episode: 105 training return: tensor(147.9874, device='cuda:0')
episode: 106 training return: tensor(137.8963, device='cuda:0')
episode: 107 training return: tensor(134.7048, device='cuda:0')
epoch: 27 test_true_pfm: 140.50571277165483 sim_pfm: 146.8713584874582
episode: 108 training return: tensor(134.5585, device='cuda:0')
episode: 109 training return: tensor(146.3116, device='cuda:0')
episode: 110 training return: tensor(136.5673, device='cuda:0')
episode: 111 training return: tensor(135.0306, device='cuda:0')
epoch: 28 test_true_pfm: 139.69172422655174 sim_pfm: 139.22456237661535
episode: 112 training return: tensor(142.4395, device='cuda:0')
episode: 113 training return: tensor(144.9063, device='cuda:0')
episode: 114 training return: tensor(152.4451, device='cuda:0')
episode: 115 training return: tensor(154.8562, device='cuda:0')
epoch: 29 test_true_pfm: 131.53019163566927 sim_pfm: 140.1155884539825
episode: 116 training return: tensor(143.8378, device='cuda:0')
episode: 117 training return: tensor(147.0496, device='cuda:0')
episode: 118 training return: tensor(144.6801, device='cuda:0')
episode: 119 training return: tensor(147.8488, device='cuda:0')
epoch: 30 test_true_pfm: 136.08557161170552 sim_pfm: 146.30853539046365
episode: 120 training return: tensor(149.7632, device='cuda:0')
episode: 121 training return: tensor(151.0748, device='cuda:0')
episode: 122 training return: tensor(140.8336, device='cuda:0')
episode: 123 training return: tensor(148.8619, device='cuda:0')
epoch: 31 test_true_pfm: 144.0295475650974 sim_pfm: 141.59244730932406
episode: 124 training return: tensor(148.5894, device='cuda:0')
episode: 125 training return: tensor(132.1541, device='cuda:0')
episode: 126 training return: tensor(142.8571, device='cuda:0')
episode: 127 training return: tensor(133.3392, device='cuda:0')
epoch: 32 test_true_pfm: 137.94055261718054 sim_pfm: 147.6965793918702
episode: 128 training return: tensor(151.7967, device='cuda:0')
episode: 129 training return: tensor(147.9734, device='cuda:0')
episode: 130 training return: tensor(150.1613, device='cuda:0')
episode: 131 training return: tensor(147.7394, device='cuda:0')
epoch: 33 test_true_pfm: 141.96389848172979 sim_pfm: 152.92196995219564
episode: 132 training return: tensor(152.3286, device='cuda:0')
episode: 133 training return: tensor(148.9119, device='cuda:0')
episode: 134 training return: tensor(149.2287, device='cuda:0')
episode: 135 training return: tensor(141.5913, device='cuda:0')
epoch: 34 test_true_pfm: 141.23391133965728 sim_pfm: 141.56591483298106
episode: 136 training return: tensor(151.4460, device='cuda:0')
episode: 137 training return: tensor(142.3873, device='cuda:0')
episode: 138 training return: tensor(136.4708, device='cuda:0')
episode: 139 training return: tensor(148.5856, device='cuda:0')
epoch: 35 test_true_pfm: 143.20095277959533 sim_pfm: 143.69852053374052
episode: 140 training return: tensor(138.9059, device='cuda:0')
episode: 141 training return: tensor(148.9431, device='cuda:0')
episode: 142 training return: tensor(145.7607, device='cuda:0')
episode: 143 training return: tensor(145.8312, device='cuda:0')
epoch: 36 test_true_pfm: 141.62385233571678 sim_pfm: 144.1075797222089
episode: 144 training return: tensor(140.4660, device='cuda:0')
episode: 145 training return: tensor(150.5284, device='cuda:0')
episode: 146 training return: tensor(140.3850, device='cuda:0')
episode: 147 training return: tensor(121.1508, device='cuda:0')
epoch: 37 test_true_pfm: 140.42506908890533 sim_pfm: 141.64045300284633
episode: 148 training return: tensor(141.0705, device='cuda:0')
episode: 149 training return: tensor(152.6481, device='cuda:0')
episode: 150 training return: tensor(147.1111, device='cuda:0')
episode: 151 training return: tensor(142.5030, device='cuda:0')
epoch: 38 test_true_pfm: 136.67073807240246 sim_pfm: 145.39926205551018
episode: 152 training return: tensor(139.1402, device='cuda:0')
episode: 153 training return: tensor(147.4932, device='cuda:0')
episode: 154 training return: tensor(149.6862, device='cuda:0')
episode: 155 training return: tensor(137.8344, device='cuda:0')
epoch: 39 test_true_pfm: 137.7536539416946 sim_pfm: 148.2711493308074
episode: 156 training return: tensor(144.1311, device='cuda:0')
episode: 157 training return: tensor(152.8548, device='cuda:0')
episode: 158 training return: tensor(144.1115, device='cuda:0')
episode: 159 training return: tensor(144.8091, device='cuda:0')
epoch: 40 test_true_pfm: 140.39013179500344 sim_pfm: 147.15909426242578
episode: 160 training return: tensor(145.7955, device='cuda:0')
episode: 161 training return: tensor(136.9566, device='cuda:0')
episode: 162 training return: tensor(147.8292, device='cuda:0')
episode: 163 training return: tensor(134.1696, device='cuda:0')
epoch: 41 test_true_pfm: 139.3823115553022 sim_pfm: 143.26133773821638
episode: 164 training return: tensor(145.1783, device='cuda:0')
episode: 165 training return: tensor(149.5467, device='cuda:0')
episode: 166 training return: tensor(150.9992, device='cuda:0')
episode: 167 training return: tensor(133.4184, device='cuda:0')
epoch: 42 test_true_pfm: 141.01012099934172 sim_pfm: 143.90262231312227
episode: 168 training return: tensor(146.1280, device='cuda:0')
episode: 169 training return: tensor(133.6163, device='cuda:0')
episode: 170 training return: tensor(137.4407, device='cuda:0')
episode: 171 training return: tensor(151.3896, device='cuda:0')
epoch: 43 test_true_pfm: 140.13499356356184 sim_pfm: 143.0868346064526
episode: 172 training return: tensor(148.5511, device='cuda:0')
episode: 173 training return: tensor(143.2643, device='cuda:0')
episode: 174 training return: tensor(148.4445, device='cuda:0')
episode: 175 training return: tensor(146.6802, device='cuda:0')
epoch: 44 test_true_pfm: 141.75140563610972 sim_pfm: 142.26144144329592
episode: 176 training return: tensor(137.4397, device='cuda:0')
episode: 177 training return: tensor(135.7124, device='cuda:0')
episode: 178 training return: tensor(148.5353, device='cuda:0')
episode: 179 training return: tensor(148.9489, device='cuda:0')
epoch: 45 test_true_pfm: 139.71917347056558 sim_pfm: 149.23164853611962
episode: 180 training return: tensor(153.5432, device='cuda:0')
episode: 181 training return: tensor(149.7909, device='cuda:0')
episode: 182 training return: tensor(131.8874, device='cuda:0')
episode: 183 training return: tensor(150.7581, device='cuda:0')
epoch: 46 test_true_pfm: 141.47611317816487 sim_pfm: 146.7294692294614
episode: 184 training return: tensor(146.5321, device='cuda:0')
episode: 185 training return: tensor(136.6773, device='cuda:0')
episode: 186 training return: tensor(135.5846, device='cuda:0')
episode: 187 training return: tensor(136.8759, device='cuda:0')
epoch: 47 test_true_pfm: 136.873283167041 sim_pfm: 138.25295591083122
episode: 188 training return: tensor(144.7059, device='cuda:0')
episode: 189 training return: tensor(137.7677, device='cuda:0')
episode: 190 training return: tensor(148.7108, device='cuda:0')
episode: 191 training return: tensor(133.3884, device='cuda:0')
epoch: 48 test_true_pfm: 140.0414857299586 sim_pfm: 144.53609843036392
episode: 192 training return: tensor(149.4784, device='cuda:0')
episode: 193 training return: tensor(151.3388, device='cuda:0')
episode: 194 training return: tensor(151.6761, device='cuda:0')
episode: 195 training return: tensor(145.9065, device='cuda:0')
epoch: 49 test_true_pfm: 140.67875158853124 sim_pfm: 153.14682219834066
episode: 196 training return: tensor(149.9985, device='cuda:0')
episode: 197 training return: tensor(148.7039, device='cuda:0')
episode: 198 training return: tensor(148.7508, device='cuda:0')
episode: 199 training return: tensor(132.5658, device='cuda:0')
epoch: 50 test_true_pfm: 141.69751984081944 sim_pfm: 145.67730813164962
episode: 200 training return: tensor(144.5764, device='cuda:0')
episode: 201 training return: tensor(141.9426, device='cuda:0')
episode: 202 training return: tensor(129.4153, device='cuda:0')
episode: 203 training return: tensor(138.3017, device='cuda:0')
epoch: 51 test_true_pfm: 136.58020345343718 sim_pfm: 146.8757166099327
episode: 204 training return: tensor(141.5515, device='cuda:0')
episode: 205 training return: tensor(136.8210, device='cuda:0')
episode: 206 training return: tensor(144.1222, device='cuda:0')
episode: 207 training return: tensor(147.8813, device='cuda:0')
epoch: 52 test_true_pfm: 129.8157227278312 sim_pfm: 148.47346663183998
episode: 208 training return: tensor(142.7881, device='cuda:0')
episode: 209 training return: tensor(138.4728, device='cuda:0')
episode: 210 training return: tensor(134.3524, device='cuda:0')
episode: 211 training return: tensor(131.6479, device='cuda:0')
epoch: 53 test_true_pfm: 142.22592659397162 sim_pfm: 147.5915011017176
episode: 212 training return: tensor(153.9463, device='cuda:0')
episode: 213 training return: tensor(147.3211, device='cuda:0')
episode: 214 training return: tensor(154.8961, device='cuda:0')
episode: 215 training return: tensor(145.3225, device='cuda:0')
epoch: 54 test_true_pfm: 141.6124369816318 sim_pfm: 144.69370530320447
episode: 216 training return: tensor(154.7007, device='cuda:0')
episode: 217 training return: tensor(150.2956, device='cuda:0')
episode: 218 training return: tensor(137.6000, device='cuda:0')
episode: 219 training return: tensor(137.0047, device='cuda:0')
epoch: 55 test_true_pfm: 142.33675684446874 sim_pfm: 149.68094637367176
episode: 220 training return: tensor(139.9528, device='cuda:0')
episode: 221 training return: tensor(139.5158, device='cuda:0')
episode: 222 training return: tensor(146.8491, device='cuda:0')
episode: 223 training return: tensor(147.3286, device='cuda:0')
epoch: 56 test_true_pfm: 144.64065937976247 sim_pfm: 145.67217874985073
episode: 224 training return: tensor(142.3801, device='cuda:0')
episode: 225 training return: tensor(135.0294, device='cuda:0')
episode: 226 training return: tensor(154.6196, device='cuda:0')
episode: 227 training return: tensor(145.2085, device='cuda:0')
epoch: 57 test_true_pfm: 141.85720839417516 sim_pfm: 140.9026463006856
episode: 228 training return: tensor(144.8431, device='cuda:0')
episode: 229 training return: tensor(149.3154, device='cuda:0')
episode: 230 training return: tensor(150.2314, device='cuda:0')
episode: 231 training return: tensor(142.9191, device='cuda:0')
epoch: 58 test_true_pfm: 141.94245736365554 sim_pfm: 148.37736206797416
episode: 232 training return: tensor(146.8612, device='cuda:0')
episode: 233 training return: tensor(152.4059, device='cuda:0')
episode: 234 training return: tensor(130.9204, device='cuda:0')
episode: 235 training return: tensor(133.6633, device='cuda:0')
epoch: 59 test_true_pfm: 140.94012979554526 sim_pfm: 143.54325979705317
episode: 236 training return: tensor(149.4020, device='cuda:0')
episode: 237 training return: tensor(150.8393, device='cuda:0')
episode: 238 training return: tensor(146.2001, device='cuda:0')
episode: 239 training return: tensor(144.2273, device='cuda:0')
epoch: 60 test_true_pfm: 144.48058808194628 sim_pfm: 148.09131136398645
episode: 240 training return: tensor(152.6767, device='cuda:0')
episode: 241 training return: tensor(134.9081, device='cuda:0')
episode: 242 training return: tensor(144.9252, device='cuda:0')
episode: 243 training return: tensor(152.2805, device='cuda:0')
epoch: 61 test_true_pfm: 135.5418173718594 sim_pfm: 151.00777759529302
episode: 244 training return: tensor(148.1676, device='cuda:0')
episode: 245 training return: tensor(153.7280, device='cuda:0')
episode: 246 training return: tensor(151.3872, device='cuda:0')
episode: 247 training return: tensor(147.8216, device='cuda:0')
epoch: 62 test_true_pfm: 140.1521491360789 sim_pfm: 144.47922082642327
episode: 248 training return: tensor(144.0797, device='cuda:0')
episode: 249 training return: tensor(141.5338, device='cuda:0')
episode: 250 training return: tensor(150.8507, device='cuda:0')
episode: 251 training return: tensor(143.8638, device='cuda:0')
epoch: 63 test_true_pfm: 139.56133267567708 sim_pfm: 152.77278537960373
episode: 252 training return: tensor(136.0929, device='cuda:0')
episode: 253 training return: tensor(144.7501, device='cuda:0')
episode: 254 training return: tensor(152.8526, device='cuda:0')
episode: 255 training return: tensor(145.1461, device='cuda:0')
epoch: 64 test_true_pfm: 140.40135870336692 sim_pfm: 145.17238124343567
episode: 256 training return: tensor(145.2645, device='cuda:0')
episode: 257 training return: tensor(149.1605, device='cuda:0')
episode: 258 training return: tensor(144.9114, device='cuda:0')
episode: 259 training return: tensor(157.3595, device='cuda:0')
epoch: 65 test_true_pfm: 145.1092494433983 sim_pfm: 149.78600106238156
episode: 260 training return: tensor(139.9976, device='cuda:0')
episode: 261 training return: tensor(154.2074, device='cuda:0')
episode: 262 training return: tensor(137.2205, device='cuda:0')
episode: 263 training return: tensor(151.0610, device='cuda:0')
epoch: 66 test_true_pfm: 143.41089503972995 sim_pfm: 149.11153657121469
episode: 264 training return: tensor(134.9258, device='cuda:0')
episode: 265 training return: tensor(135.0651, device='cuda:0')
episode: 266 training return: tensor(151.2311, device='cuda:0')
episode: 267 training return: tensor(137.0916, device='cuda:0')
epoch: 67 test_true_pfm: 138.95472199349268 sim_pfm: 145.73659471322898
episode: 268 training return: tensor(140.6356, device='cuda:0')
episode: 269 training return: tensor(148.0366, device='cuda:0')
episode: 270 training return: tensor(150.9121, device='cuda:0')
episode: 271 training return: tensor(149.2800, device='cuda:0')
epoch: 68 test_true_pfm: 132.79584363035582 sim_pfm: 149.49059789963067
episode: 272 training return: tensor(141.2164, device='cuda:0')
episode: 273 training return: tensor(149.4742, device='cuda:0')
episode: 274 training return: tensor(142.7213, device='cuda:0')
episode: 275 training return: tensor(146.7079, device='cuda:0')
epoch: 69 test_true_pfm: 143.9062983724737 sim_pfm: 148.15364611757104
episode: 276 training return: tensor(152.9348, device='cuda:0')
episode: 277 training return: tensor(152.1527, device='cuda:0')
episode: 278 training return: tensor(150.7931, device='cuda:0')
episode: 279 training return: tensor(153.1742, device='cuda:0')
epoch: 70 test_true_pfm: 142.13863150591268 sim_pfm: 149.28524035792216
episode: 280 training return: tensor(151.4435, device='cuda:0')
episode: 281 training return: tensor(149.1283, device='cuda:0')
episode: 282 training return: tensor(139.8226, device='cuda:0')
episode: 283 training return: tensor(139.8875, device='cuda:0')
epoch: 71 test_true_pfm: 139.96462373365307 sim_pfm: 144.8507041547855
episode: 284 training return: tensor(145.6461, device='cuda:0')
episode: 285 training return: tensor(152.6355, device='cuda:0')
episode: 286 training return: tensor(145.4316, device='cuda:0')
episode: 287 training return: tensor(151.8017, device='cuda:0')
epoch: 72 test_true_pfm: 137.90772590353177 sim_pfm: 153.06366494008688
episode: 288 training return: tensor(149.2357, device='cuda:0')
episode: 289 training return: tensor(144.4476, device='cuda:0')
episode: 290 training return: tensor(137.1544, device='cuda:0')
episode: 291 training return: tensor(149.9448, device='cuda:0')
epoch: 73 test_true_pfm: 138.05819273721983 sim_pfm: 149.8950188827992
episode: 292 training return: tensor(137.7743, device='cuda:0')
episode: 293 training return: tensor(148.9036, device='cuda:0')
episode: 294 training return: tensor(146.2751, device='cuda:0')
episode: 295 training return: tensor(152.3354, device='cuda:0')
epoch: 74 test_true_pfm: 139.87719905364534 sim_pfm: 145.55115952515627
episode: 296 training return: tensor(143.0667, device='cuda:0')
episode: 297 training return: tensor(151.2884, device='cuda:0')
episode: 298 training return: tensor(149.5518, device='cuda:0')
episode: 299 training return: tensor(150.7847, device='cuda:0')
epoch: 75 test_true_pfm: 140.78035086435867 sim_pfm: 151.32048447044798
episode: 300 training return: tensor(145.4550, device='cuda:0')
episode: 301 training return: tensor(134.0746, device='cuda:0')
episode: 302 training return: tensor(143.0132, device='cuda:0')
episode: 303 training return: tensor(131.8851, device='cuda:0')
epoch: 76 test_true_pfm: 137.79296390650126 sim_pfm: 147.22378598236827
episode: 304 training return: tensor(139.5610, device='cuda:0')
episode: 305 training return: tensor(152.8792, device='cuda:0')
episode: 306 training return: tensor(151.4934, device='cuda:0')
episode: 307 training return: tensor(148.2164, device='cuda:0')
epoch: 77 test_true_pfm: 139.8561618233587 sim_pfm: 149.7185239607119
episode: 308 training return: tensor(137.0083, device='cuda:0')
episode: 309 training return: tensor(148.9409, device='cuda:0')
episode: 310 training return: tensor(147.3620, device='cuda:0')
episode: 311 training return: tensor(151.7112, device='cuda:0')
epoch: 78 test_true_pfm: 140.421692043013 sim_pfm: 148.78058679777314
episode: 312 training return: tensor(153.2036, device='cuda:0')
episode: 313 training return: tensor(150.5372, device='cuda:0')
episode: 314 training return: tensor(144.7227, device='cuda:0')
episode: 315 training return: tensor(138.5250, device='cuda:0')
epoch: 79 test_true_pfm: 142.4731128130695 sim_pfm: 151.1342781389365
episode: 316 training return: tensor(152.2212, device='cuda:0')
episode: 317 training return: tensor(141.6255, device='cuda:0')
episode: 318 training return: tensor(153.5247, device='cuda:0')
episode: 319 training return: tensor(139.3388, device='cuda:0')
epoch: 80 test_true_pfm: 136.0811076828853 sim_pfm: 147.8461761465005
episode: 320 training return: tensor(148.6039, device='cuda:0')
episode: 321 training return: tensor(157.0546, device='cuda:0')
episode: 322 training return: tensor(143.8582, device='cuda:0')
episode: 323 training return: tensor(149.3801, device='cuda:0')
epoch: 81 test_true_pfm: 141.43680293126985 sim_pfm: 149.85746575804077
episode: 324 training return: tensor(151.1133, device='cuda:0')
episode: 325 training return: tensor(145.0915, device='cuda:0')
episode: 326 training return: tensor(157.5239, device='cuda:0')
episode: 327 training return: tensor(142.2815, device='cuda:0')
epoch: 82 test_true_pfm: 141.4900700803158 sim_pfm: 149.23110649829613
episode: 328 training return: tensor(154.8403, device='cuda:0')
episode: 329 training return: tensor(147.1163, device='cuda:0')
episode: 330 training return: tensor(142.4313, device='cuda:0')
episode: 331 training return: tensor(152.7289, device='cuda:0')
epoch: 83 test_true_pfm: 139.29882269558175 sim_pfm: 148.74445720816146
episode: 332 training return: tensor(148.4675, device='cuda:0')
episode: 333 training return: tensor(155.3790, device='cuda:0')
episode: 334 training return: tensor(152.0513, device='cuda:0')
episode: 335 training return: tensor(156.3488, device='cuda:0')
epoch: 84 test_true_pfm: 139.61020824480866 sim_pfm: 147.13306032763793
episode: 336 training return: tensor(150.3315, device='cuda:0')
episode: 337 training return: tensor(144.7490, device='cuda:0')
episode: 338 training return: tensor(156.5219, device='cuda:0')
episode: 339 training return: tensor(151.0561, device='cuda:0')
epoch: 85 test_true_pfm: 133.83202660288703 sim_pfm: 146.00853693587706
episode: 340 training return: tensor(152.7057, device='cuda:0')
episode: 341 training return: tensor(147.4911, device='cuda:0')
episode: 342 training return: tensor(147.7558, device='cuda:0')
episode: 343 training return: tensor(156.7774, device='cuda:0')
epoch: 86 test_true_pfm: 140.955246417644 sim_pfm: 149.96428985578822
episode: 344 training return: tensor(156.3018, device='cuda:0')
episode: 345 training return: tensor(142.8435, device='cuda:0')
episode: 346 training return: tensor(150.1153, device='cuda:0')
episode: 347 training return: tensor(150.3543, device='cuda:0')
epoch: 87 test_true_pfm: 141.40775824760124 sim_pfm: 149.49984411199694
episode: 348 training return: tensor(152.9800, device='cuda:0')
episode: 349 training return: tensor(152.6737, device='cuda:0')
episode: 350 training return: tensor(142.0310, device='cuda:0')
episode: 351 training return: tensor(140.2145, device='cuda:0')
epoch: 88 test_true_pfm: 144.35878630303426 sim_pfm: 143.93608938498656
episode: 352 training return: tensor(149.1386, device='cuda:0')
episode: 353 training return: tensor(152.6280, device='cuda:0')
episode: 354 training return: tensor(152.3482, device='cuda:0')
episode: 355 training return: tensor(148.2562, device='cuda:0')
epoch: 89 test_true_pfm: 140.0565634284841 sim_pfm: 141.00601455675786
episode: 356 training return: tensor(149.0579, device='cuda:0')
episode: 357 training return: tensor(154.5824, device='cuda:0')
episode: 358 training return: tensor(144.1967, device='cuda:0')
episode: 359 training return: tensor(150.4544, device='cuda:0')
epoch: 90 test_true_pfm: 139.39588889083595 sim_pfm: 150.96762381827574
episode: 360 training return: tensor(150.4288, device='cuda:0')
episode: 361 training return: tensor(158.1088, device='cuda:0')
episode: 362 training return: tensor(146.8349, device='cuda:0')
episode: 363 training return: tensor(155.0764, device='cuda:0')
epoch: 91 test_true_pfm: 140.7392884870327 sim_pfm: 150.76550113867853
episode: 364 training return: tensor(149.5773, device='cuda:0')
episode: 365 training return: tensor(149.4558, device='cuda:0')
episode: 366 training return: tensor(152.4470, device='cuda:0')
episode: 367 training return: tensor(142.0125, device='cuda:0')
epoch: 92 test_true_pfm: 139.4129215902182 sim_pfm: 151.69361097210202
episode: 368 training return: tensor(150.8693, device='cuda:0')
episode: 369 training return: tensor(147.3222, device='cuda:0')
episode: 370 training return: tensor(143.1318, device='cuda:0')
episode: 371 training return: tensor(146.5585, device='cuda:0')
epoch: 93 test_true_pfm: 140.2280937535632 sim_pfm: 144.85218981373473
episode: 372 training return: tensor(153.1225, device='cuda:0')
episode: 373 training return: tensor(144.8603, device='cuda:0')
episode: 374 training return: tensor(147.0729, device='cuda:0')
episode: 375 training return: tensor(136.3420, device='cuda:0')
epoch: 94 test_true_pfm: 140.18878818887055 sim_pfm: 149.46561898340588
episode: 376 training return: tensor(141.7055, device='cuda:0')
episode: 377 training return: tensor(139.2188, device='cuda:0')
episode: 378 training return: tensor(136.9011, device='cuda:0')
episode: 379 training return: tensor(145.5217, device='cuda:0')
epoch: 95 test_true_pfm: 142.3565715381222 sim_pfm: 148.72556752096278
episode: 380 training return: tensor(151.2934, device='cuda:0')
episode: 381 training return: tensor(148.8996, device='cuda:0')
episode: 382 training return: tensor(150.3632, device='cuda:0')
episode: 383 training return: tensor(134.1721, device='cuda:0')
epoch: 96 test_true_pfm: 142.81735120166542 sim_pfm: 147.21369850087794
episode: 384 training return: tensor(150.6699, device='cuda:0')
episode: 385 training return: tensor(149.0237, device='cuda:0')
episode: 386 training return: tensor(150.6006, device='cuda:0')
episode: 387 training return: tensor(151.2639, device='cuda:0')
epoch: 97 test_true_pfm: 139.11666754154209 sim_pfm: 149.32954364965553
episode: 388 training return: tensor(149.8947, device='cuda:0')
episode: 389 training return: tensor(141.9004, device='cuda:0')
episode: 390 training return: tensor(151.0840, device='cuda:0')
episode: 391 training return: tensor(150.5782, device='cuda:0')
epoch: 98 test_true_pfm: 143.2528775858757 sim_pfm: 146.57545121745207
episode: 392 training return: tensor(149.9664, device='cuda:0')
episode: 393 training return: tensor(144.1049, device='cuda:0')
episode: 394 training return: tensor(150.0290, device='cuda:0')
episode: 395 training return: tensor(148.2230, device='cuda:0')
epoch: 99 test_true_pfm: 142.88257099645966 sim_pfm: 150.94425914450548
episode: 396 training return: tensor(151.2926, device='cuda:0')
episode: 397 training return: tensor(148.1782, device='cuda:0')
episode: 398 training return: tensor(152.0175, device='cuda:0')
episode: 399 training return: tensor(138.5781, device='cuda:0')
epoch: 100 test_true_pfm: 137.89062561938118 sim_pfm: 148.5106753213331
episode: 400 training return: tensor(138.7406, device='cuda:0')
episode: 401 training return: tensor(153.5019, device='cuda:0')
episode: 402 training return: tensor(144.2828, device='cuda:0')
episode: 403 training return: tensor(154.7645, device='cuda:0')
epoch: 101 test_true_pfm: 139.3215771508632 sim_pfm: 150.37508544716403
episode: 404 training return: tensor(150.9924, device='cuda:0')
episode: 405 training return: tensor(141.2856, device='cuda:0')
episode: 406 training return: tensor(142.1550, device='cuda:0')
episode: 407 training return: tensor(154.0018, device='cuda:0')
epoch: 102 test_true_pfm: 135.459907050815 sim_pfm: 149.74864145776957
episode: 408 training return: tensor(144.1237, device='cuda:0')
episode: 409 training return: tensor(146.7035, device='cuda:0')
episode: 410 training return: tensor(152.1495, device='cuda:0')
episode: 411 training return: tensor(140.9274, device='cuda:0')
epoch: 103 test_true_pfm: 143.40704771331633 sim_pfm: 152.52908347815975
episode: 412 training return: tensor(141.8402, device='cuda:0')
episode: 413 training return: tensor(150.0382, device='cuda:0')
episode: 414 training return: tensor(151.3191, device='cuda:0')
episode: 415 training return: tensor(144.3594, device='cuda:0')
epoch: 104 test_true_pfm: 138.3559769397225 sim_pfm: 150.9921458005265
episode: 416 training return: tensor(153.1755, device='cuda:0')
episode: 417 training return: tensor(135.5298, device='cuda:0')
episode: 418 training return: tensor(151.6045, device='cuda:0')
episode: 419 training return: tensor(153.5400, device='cuda:0')
epoch: 105 test_true_pfm: 140.3359043371641 sim_pfm: 146.1976693811477
episode: 420 training return: tensor(133.9888, device='cuda:0')
episode: 421 training return: tensor(149.4831, device='cuda:0')
episode: 422 training return: tensor(148.4032, device='cuda:0')
episode: 423 training return: tensor(152.6502, device='cuda:0')
epoch: 106 test_true_pfm: 141.62881916304121 sim_pfm: 146.3064202513313
episode: 424 training return: tensor(151.5266, device='cuda:0')
episode: 425 training return: tensor(151.7938, device='cuda:0')
episode: 426 training return: tensor(151.5772, device='cuda:0')
episode: 427 training return: tensor(153.7451, device='cuda:0')
epoch: 107 test_true_pfm: 137.5476907807114 sim_pfm: 145.65338253072113
episode: 428 training return: tensor(152.3333, device='cuda:0')
episode: 429 training return: tensor(151.6113, device='cuda:0')
episode: 430 training return: tensor(151.6959, device='cuda:0')
episode: 431 training return: tensor(154.9972, device='cuda:0')
epoch: 108 test_true_pfm: 142.11086649706468 sim_pfm: 149.03535728855059
episode: 432 training return: tensor(149.0140, device='cuda:0')
episode: 433 training return: tensor(150.7255, device='cuda:0')
episode: 434 training return: tensor(149.5093, device='cuda:0')
episode: 435 training return: tensor(136.3224, device='cuda:0')
epoch: 109 test_true_pfm: 141.12425758382412 sim_pfm: 150.56256992657435
episode: 436 training return: tensor(152.3793, device='cuda:0')
episode: 437 training return: tensor(151.0254, device='cuda:0')
episode: 438 training return: tensor(154.2280, device='cuda:0')
episode: 439 training return: tensor(149.0341, device='cuda:0')
epoch: 110 test_true_pfm: 143.65261076944404 sim_pfm: 149.69233770881547
episode: 440 training return: tensor(148.4380, device='cuda:0')
episode: 441 training return: tensor(152.5369, device='cuda:0')
episode: 442 training return: tensor(150.8039, device='cuda:0')
episode: 443 training return: tensor(146.5502, device='cuda:0')
epoch: 111 test_true_pfm: 141.5611332073864 sim_pfm: 144.40109770559357
episode: 444 training return: tensor(151.2533, device='cuda:0')
episode: 445 training return: tensor(151.1812, device='cuda:0')
episode: 446 training return: tensor(151.1945, device='cuda:0')
episode: 447 training return: tensor(152.5649, device='cuda:0')
epoch: 112 test_true_pfm: 144.0642227451667 sim_pfm: 148.61542615831712
episode: 448 training return: tensor(151.4918, device='cuda:0')
episode: 449 training return: tensor(155.0258, device='cuda:0')
episode: 450 training return: tensor(148.4218, device='cuda:0')
episode: 451 training return: tensor(153.7507, device='cuda:0')
epoch: 113 test_true_pfm: 141.0591268492297 sim_pfm: 146.38255468664573
episode: 452 training return: tensor(145.0745, device='cuda:0')
episode: 453 training return: tensor(147.8251, device='cuda:0')
episode: 454 training return: tensor(145.5723, device='cuda:0')
episode: 455 training return: tensor(148.1117, device='cuda:0')
epoch: 114 test_true_pfm: 141.15196415728602 sim_pfm: 145.33662887998508
episode: 456 training return: tensor(149.6455, device='cuda:0')
episode: 457 training return: tensor(152.6267, device='cuda:0')
episode: 458 training return: tensor(138.8633, device='cuda:0')
episode: 459 training return: tensor(146.9448, device='cuda:0')
epoch: 115 test_true_pfm: 143.49628176658916 sim_pfm: 151.4920354967413
episode: 460 training return: tensor(155.7211, device='cuda:0')
episode: 461 training return: tensor(149.6757, device='cuda:0')
episode: 462 training return: tensor(140.4058, device='cuda:0')
episode: 463 training return: tensor(136.7331, device='cuda:0')
epoch: 116 test_true_pfm: 144.8455452077059 sim_pfm: 146.5479591309908
episode: 464 training return: tensor(148.0587, device='cuda:0')
episode: 465 training return: tensor(149.8741, device='cuda:0')
episode: 466 training return: tensor(139.9577, device='cuda:0')
episode: 467 training return: tensor(145.2913, device='cuda:0')
epoch: 117 test_true_pfm: 140.44553133362223 sim_pfm: 146.5422656507464
episode: 468 training return: tensor(146.9814, device='cuda:0')
episode: 469 training return: tensor(152.2298, device='cuda:0')
episode: 470 training return: tensor(155.4602, device='cuda:0')
episode: 471 training return: tensor(152.2218, device='cuda:0')
epoch: 118 test_true_pfm: 139.76732822677897 sim_pfm: 147.41092251176596
episode: 472 training return: tensor(152.6688, device='cuda:0')
episode: 473 training return: tensor(150.8727, device='cuda:0')
episode: 474 training return: tensor(154.9315, device='cuda:0')
episode: 475 training return: tensor(156.6066, device='cuda:0')
epoch: 119 test_true_pfm: 140.71818107260782 sim_pfm: 145.6467695014493
episode: 476 training return: tensor(142.3360, device='cuda:0')
episode: 477 training return: tensor(140.9340, device='cuda:0')
episode: 478 training return: tensor(152.2602, device='cuda:0')
episode: 479 training return: tensor(152.6546, device='cuda:0')
epoch: 120 test_true_pfm: 140.06263706694207 sim_pfm: 148.16268857275136
episode: 480 training return: tensor(145.9965, device='cuda:0')
episode: 481 training return: tensor(149.9985, device='cuda:0')
episode: 482 training return: tensor(148.9310, device='cuda:0')
episode: 483 training return: tensor(140.0034, device='cuda:0')
epoch: 121 test_true_pfm: 141.93666369512184 sim_pfm: 151.47953962393223
episode: 484 training return: tensor(144.7252, device='cuda:0')
episode: 485 training return: tensor(143.9120, device='cuda:0')
episode: 486 training return: tensor(135.5121, device='cuda:0')
episode: 487 training return: tensor(155.8589, device='cuda:0')
epoch: 122 test_true_pfm: 140.05614973652268 sim_pfm: 144.56103300355608
episode: 488 training return: tensor(147.6038, device='cuda:0')
episode: 489 training return: tensor(155.9160, device='cuda:0')
episode: 490 training return: tensor(144.9499, device='cuda:0')
episode: 491 training return: tensor(149.7188, device='cuda:0')
epoch: 123 test_true_pfm: 142.9750952223938 sim_pfm: 144.1275863316958
episode: 492 training return: tensor(138.9350, device='cuda:0')
episode: 493 training return: tensor(150.7285, device='cuda:0')
episode: 494 training return: tensor(147.2039, device='cuda:0')
episode: 495 training return: tensor(153.0565, device='cuda:0')
epoch: 124 test_true_pfm: 144.08178487489295 sim_pfm: 151.61876456105966
episode: 496 training return: tensor(148.6620, device='cuda:0')
episode: 497 training return: tensor(153.3414, device='cuda:0')
episode: 498 training return: tensor(143.9120, device='cuda:0')
episode: 499 training return: tensor(149.2215, device='cuda:0')
epoch: 125 test_true_pfm: 144.33218248877859 sim_pfm: 146.57693694522604
episode: 500 training return: tensor(145.0933, device='cuda:0')
episode: 501 training return: tensor(150.5833, device='cuda:0')
episode: 502 training return: tensor(147.1964, device='cuda:0')
episode: 503 training return: tensor(152.8658, device='cuda:0')
epoch: 126 test_true_pfm: 136.13014785231616 sim_pfm: 148.98011007753666
episode: 504 training return: tensor(151.8467, device='cuda:0')
episode: 505 training return: tensor(150.6261, device='cuda:0')
episode: 506 training return: tensor(142.0360, device='cuda:0')
episode: 507 training return: tensor(149.9664, device='cuda:0')
epoch: 127 test_true_pfm: 138.71438831115591 sim_pfm: 146.07040677925107
episode: 508 training return: tensor(151.8583, device='cuda:0')
episode: 509 training return: tensor(148.3230, device='cuda:0')
episode: 510 training return: tensor(152.1863, device='cuda:0')
episode: 511 training return: tensor(149.1473, device='cuda:0')
epoch: 128 test_true_pfm: 137.60876908752766 sim_pfm: 147.59949056965417
episode: 512 training return: tensor(138.7142, device='cuda:0')
episode: 513 training return: tensor(137.4772, device='cuda:0')
episode: 514 training return: tensor(139.9214, device='cuda:0')
episode: 515 training return: tensor(146.3712, device='cuda:0')
epoch: 129 test_true_pfm: 140.9273927338524 sim_pfm: 149.23135293684317
episode: 516 training return: tensor(148.9373, device='cuda:0')
episode: 517 training return: tensor(147.8459, device='cuda:0')
episode: 518 training return: tensor(143.4717, device='cuda:0')
episode: 519 training return: tensor(148.7224, device='cuda:0')
epoch: 130 test_true_pfm: 141.32407176840434 sim_pfm: 151.9021739106567
episode: 520 training return: tensor(134.1625, device='cuda:0')
episode: 521 training return: tensor(149.6212, device='cuda:0')
episode: 522 training return: tensor(150.8060, device='cuda:0')
episode: 523 training return: tensor(156.0328, device='cuda:0')
epoch: 131 test_true_pfm: 143.81921926873056 sim_pfm: 146.91101497924538
episode: 524 training return: tensor(144.2012, device='cuda:0')
episode: 525 training return: tensor(143.4151, device='cuda:0')
episode: 526 training return: tensor(140.9914, device='cuda:0')
episode: 527 training return: tensor(143.8625, device='cuda:0')
epoch: 132 test_true_pfm: 140.00902417246743 sim_pfm: 153.99128766037174
episode: 528 training return: tensor(134.7141, device='cuda:0')
episode: 529 training return: tensor(152.0701, device='cuda:0')
episode: 530 training return: tensor(151.3519, device='cuda:0')
episode: 531 training return: tensor(154.5926, device='cuda:0')
epoch: 133 test_true_pfm: 142.66964296800836 sim_pfm: 152.01243218560703
episode: 532 training return: tensor(156.7759, device='cuda:0')
episode: 533 training return: tensor(133.9324, device='cuda:0')
episode: 534 training return: tensor(149.1781, device='cuda:0')
episode: 535 training return: tensor(150.1679, device='cuda:0')
epoch: 134 test_true_pfm: 144.72734692613466 sim_pfm: 149.40133842726937
episode: 536 training return: tensor(154.9575, device='cuda:0')
episode: 537 training return: tensor(145.5038, device='cuda:0')
episode: 538 training return: tensor(133.6409, device='cuda:0')
episode: 539 training return: tensor(152.3750, device='cuda:0')
epoch: 135 test_true_pfm: 136.2205950056814 sim_pfm: 149.57560990897474
episode: 540 training return: tensor(137.3327, device='cuda:0')
episode: 541 training return: tensor(140.5040, device='cuda:0')
episode: 542 training return: tensor(143.2616, device='cuda:0')
episode: 543 training return: tensor(131.6734, device='cuda:0')
epoch: 136 test_true_pfm: 136.83656193230928 sim_pfm: 146.90833989993553
episode: 544 training return: tensor(155.0739, device='cuda:0')
episode: 545 training return: tensor(141.6280, device='cuda:0')
episode: 546 training return: tensor(138.7601, device='cuda:0')
episode: 547 training return: tensor(139.4806, device='cuda:0')
epoch: 137 test_true_pfm: 142.06026567050506 sim_pfm: 146.67291384827695
episode: 548 training return: tensor(147.1535, device='cuda:0')
episode: 549 training return: tensor(153.4475, device='cuda:0')
episode: 550 training return: tensor(151.0516, device='cuda:0')
episode: 551 training return: tensor(148.2675, device='cuda:0')
epoch: 138 test_true_pfm: 142.64098276223353 sim_pfm: 151.29694609147265
episode: 552 training return: tensor(152.7974, device='cuda:0')
episode: 553 training return: tensor(133.2813, device='cuda:0')
episode: 554 training return: tensor(154.1894, device='cuda:0')
episode: 555 training return: tensor(146.1615, device='cuda:0')
epoch: 139 test_true_pfm: 136.71807682310697 sim_pfm: 147.70318788206788
episode: 556 training return: tensor(153.5329, device='cuda:0')
episode: 557 training return: tensor(152.8504, device='cuda:0')
episode: 558 training return: tensor(157.6734, device='cuda:0')
episode: 559 training return: tensor(147.8274, device='cuda:0')
epoch: 140 test_true_pfm: 140.12391789268685 sim_pfm: 147.17794501383906
episode: 560 training return: tensor(156.8184, device='cuda:0')
episode: 561 training return: tensor(151.1944, device='cuda:0')
episode: 562 training return: tensor(155.9485, device='cuda:0')
episode: 563 training return: tensor(153.6771, device='cuda:0')
epoch: 141 test_true_pfm: 143.08853021515628 sim_pfm: 151.91902486720355
episode: 564 training return: tensor(143.2344, device='cuda:0')
episode: 565 training return: tensor(152.5275, device='cuda:0')
episode: 566 training return: tensor(134.1341, device='cuda:0')
episode: 567 training return: tensor(153.5763, device='cuda:0')
epoch: 142 test_true_pfm: 139.3671505926644 sim_pfm: 149.4458473945211
episode: 568 training return: tensor(149.5795, device='cuda:0')
episode: 569 training return: tensor(151.7750, device='cuda:0')
episode: 570 training return: tensor(152.3397, device='cuda:0')
episode: 571 training return: tensor(152.7515, device='cuda:0')
epoch: 143 test_true_pfm: 142.51299346518434 sim_pfm: 146.33236239560065
episode: 572 training return: tensor(146.7407, device='cuda:0')
episode: 573 training return: tensor(154.0811, device='cuda:0')
episode: 574 training return: tensor(129.7174, device='cuda:0')
episode: 575 training return: tensor(156.8891, device='cuda:0')
epoch: 144 test_true_pfm: 143.12882367448697 sim_pfm: 143.105816019373
episode: 576 training return: tensor(137.6943, device='cuda:0')
episode: 577 training return: tensor(153.0593, device='cuda:0')
episode: 578 training return: tensor(156.2192, device='cuda:0')
episode: 579 training return: tensor(149.8636, device='cuda:0')
epoch: 145 test_true_pfm: 142.76389966084778 sim_pfm: 149.27548754744348
episode: 580 training return: tensor(154.4837, device='cuda:0')
episode: 581 training return: tensor(146.8715, device='cuda:0')
episode: 582 training return: tensor(136.2418, device='cuda:0')
episode: 583 training return: tensor(154.7581, device='cuda:0')
epoch: 146 test_true_pfm: 142.7597066655143 sim_pfm: 151.3015626231616
episode: 584 training return: tensor(157.7104, device='cuda:0')
episode: 585 training return: tensor(152.3573, device='cuda:0')
episode: 586 training return: tensor(154.8686, device='cuda:0')
episode: 587 training return: tensor(148.4837, device='cuda:0')
epoch: 147 test_true_pfm: 143.18860377104699 sim_pfm: 154.48551124166698
episode: 588 training return: tensor(147.8020, device='cuda:0')
episode: 589 training return: tensor(149.5095, device='cuda:0')
episode: 590 training return: tensor(149.7811, device='cuda:0')
episode: 591 training return: tensor(148.6139, device='cuda:0')
epoch: 148 test_true_pfm: 138.80553774847803 sim_pfm: 150.3251308034465
episode: 592 training return: tensor(155.2319, device='cuda:0')
episode: 593 training return: tensor(148.9487, device='cuda:0')
episode: 594 training return: tensor(154.0531, device='cuda:0')
episode: 595 training return: tensor(151.4797, device='cuda:0')
epoch: 149 test_true_pfm: 144.82387979767847 sim_pfm: 155.69594400015194
episode: 596 training return: tensor(145.0988, device='cuda:0')
episode: 597 training return: tensor(152.7824, device='cuda:0')
episode: 598 training return: tensor(153.4001, device='cuda:0')
episode: 599 training return: tensor(143.6077, device='cuda:0')
epoch: 150 test_true_pfm: 141.77701665201636 sim_pfm: 142.96436872722697
