epoch: 0 training_loss 0.2744590562582016 test_loss: 0.1957775831222534
epoch: 1 training_loss 0.1747779842466116 test_loss: 0.13872331380844116
epoch: 2 training_loss 0.141711231097579 test_loss: 0.1585003137588501
epoch: 3 training_loss 0.1414854510873556 test_loss: 0.1208570122718811
epoch: 4 training_loss 0.13318195749074221 test_loss: 0.11509957313537597
epoch: 5 training_loss 0.12134315211325884 test_loss: 0.09357210993766785
epoch: 6 training_loss 0.12051076725125313 test_loss: 0.12094424962997437
epoch: 7 training_loss 0.11536302875727415 test_loss: 0.11900296211242675
epoch: 8 training_loss 0.1160546164959669 test_loss: 0.12017483711242676
epoch: 9 training_loss 0.11063192456960678 test_loss: 0.11417514085769653
epoch: 10 training_loss 0.11714353602379561 test_loss: 0.14963585138320923
epoch: 11 training_loss 0.11340019345283509 test_loss: 0.11087204217910766
epoch: 12 training_loss 0.11740646386519074 test_loss: 0.1199496030807495
epoch: 13 training_loss 0.10691648911684752 test_loss: 0.10609297752380371
epoch: 14 training_loss 0.1140161602012813 test_loss: 0.11745983362197876
epoch: 15 training_loss 0.1153464962914586 test_loss: 0.10077253580093384
epoch: 16 training_loss 0.11168455202132463 test_loss: 0.11931334733963013
epoch: 17 training_loss 0.1118229553103447 test_loss: 0.12074912786483764
epoch: 18 training_loss 0.10794894751161337 test_loss: 0.132686984539032
epoch: 19 training_loss 0.11902336969971657 test_loss: 0.11914350986480712
epoch: 20 training_loss 0.11247969664633274 test_loss: 0.1277852773666382
epoch: 21 training_loss 0.1109294293448329 test_loss: 0.11889569759368897
epoch: 22 training_loss 0.11248447373509407 test_loss: 0.10217241048812867
epoch: 23 training_loss 0.11106621850281954 test_loss: 0.09585727453231811
epoch: 24 training_loss 0.11083101212978363 test_loss: 0.12623159885406493
epoch: 25 training_loss 0.11202824596315622 test_loss: 0.1227150797843933
epoch: 26 training_loss 0.1063369408994913 test_loss: 0.1159024715423584
epoch: 27 training_loss 0.10624384641647339 test_loss: 0.12364343404769898
epoch: 28 training_loss 0.1063099979236722 test_loss: 0.13442182540893555
epoch: 29 training_loss 0.11546195738017559 test_loss: 0.11677303314208984
epoch: 30 training_loss 0.10713952928781509 test_loss: 0.10371695756912232
epoch: 31 training_loss 0.10746202424168587 test_loss: 0.12329294681549072
epoch: 32 training_loss 0.10956626746803522 test_loss: 0.08277407884597779
epoch: 33 training_loss 0.11133110579103231 test_loss: 0.14207879304885865
epoch: 34 training_loss 0.11229250479489565 test_loss: 0.13982144594192505
epoch: 35 training_loss 0.10444172784686089 test_loss: 0.101360285282135
epoch: 36 training_loss 0.10885566782206296 test_loss: 0.10717735290527344
epoch: 37 training_loss 0.11101446621119976 test_loss: 0.12246520519256592
epoch: 38 training_loss 0.11204055968672037 test_loss: 0.1352434515953064
epoch: 39 training_loss 0.11652458988130093 test_loss: 0.10854626893997192
epoch: 40 training_loss 0.10995320040732622 test_loss: 0.10057581663131714
epoch: 41 training_loss 0.10499397143721581 test_loss: 0.14198888540267945
epoch: 42 training_loss 0.1046193819399923 test_loss: 0.0919079065322876
epoch: 43 training_loss 0.09983836814761161 test_loss: 0.1296612024307251
epoch: 44 training_loss 0.11238160122185946 test_loss: 0.11578443050384521
epoch: 45 training_loss 0.10916674084961414 test_loss: 0.1154785394668579
epoch: 46 training_loss 0.09977795451879501 test_loss: 0.10080875158309936
epoch: 47 training_loss 0.09783001352101564 test_loss: 0.09974278807640076
epoch: 48 training_loss 0.10934987165033817 test_loss: 0.11179362535476685
epoch: 49 training_loss 0.10511784061789513 test_loss: 0.08855046033859253
epoch: 50 training_loss 0.11155240025371313 test_loss: 0.12083691358566284
epoch: 51 training_loss 0.10562559580430389 test_loss: 0.0982034981250763
epoch: 52 training_loss 0.11058499552309513 test_loss: 0.12953940629959107
epoch: 53 training_loss 0.10576416198164225 test_loss: 0.12472742795944214
epoch: 54 training_loss 0.09783874530345202 test_loss: 0.10281676054000854
epoch: 55 training_loss 0.10911444962024688 test_loss: 0.0936040461063385
epoch: 56 training_loss 0.10016944870352745 test_loss: 0.08433429002761841
epoch: 57 training_loss 0.09943106584250927 test_loss: 0.10383936166763305
epoch: 58 training_loss 0.10925373900681734 test_loss: 0.11850767135620117
epoch: 59 training_loss 0.10265485115349293 test_loss: 0.10813364982604981
epoch: 60 training_loss 0.0996806650608778 test_loss: 0.10297160148620606
epoch: 61 training_loss 0.11363122355192899 test_loss: 0.10866886377334595
epoch: 62 training_loss 0.10984663780778646 test_loss: 0.11527271270751953
epoch: 63 training_loss 0.10814355423673988 test_loss: 0.11773015260696411
epoch: 64 training_loss 0.10945493943989276 test_loss: 0.1151660442352295
epoch: 65 training_loss 0.10569975100457668 test_loss: 0.08810991048812866
epoch: 66 training_loss 0.10693477019667626 test_loss: 0.10291441679000854
epoch: 67 training_loss 0.10998769411817193 test_loss: 0.11983290910720826
epoch: 68 training_loss 0.10088503057137131 test_loss: 0.11050152778625488
epoch: 69 training_loss 0.10920232413336635 test_loss: 0.09187833070755005
epoch: 70 training_loss 0.1097470224648714 test_loss: 0.09847869277000428
epoch: 71 training_loss 0.10646930187940598 test_loss: 0.11249475479125977
epoch: 72 training_loss 0.0995641902834177 test_loss: 0.11457595825195313
epoch: 73 training_loss 0.10598284285515547 test_loss: 0.11288292407989502
epoch: 74 training_loss 0.1049594177864492 test_loss: 0.11877905130386353
epoch: 75 training_loss 0.1090730021893978 test_loss: 0.09096773862838745
epoch: 76 training_loss 0.1069597945548594 test_loss: 0.11580525636672974
epoch: 77 training_loss 0.10925411354750394 test_loss: 0.09326134324073791
epoch: 78 training_loss 0.10508542004972696 test_loss: 0.08970264196395875
epoch: 79 training_loss 0.09961820550262929 test_loss: 0.11304826736450195
epoch: 0 training_loss 50.91128807067871 test_loss: 23.969955444335938
epoch: 1 training_loss 18.607925119400026 test_loss: 15.016891479492188
epoch: 2 training_loss 13.158704099655152 test_loss: 11.664107513427734
epoch: 3 training_loss 10.388231573104859 test_loss: 9.534646606445312
epoch: 4 training_loss 8.778321042060853 test_loss: 8.070858001708984
epoch: 5 training_loss 7.538498392105103 test_loss: 7.057923126220703
epoch: 6 training_loss 6.503439083099365 test_loss: 6.16050910949707
epoch: 7 training_loss 5.867245001792908 test_loss: 6.019155883789063
epoch: 8 training_loss 5.345777688026428 test_loss: 4.982962417602539
epoch: 9 training_loss 5.07003242969513 test_loss: 4.695281219482422
epoch: 10 training_loss 4.638479733467102 test_loss: 4.729867553710937
epoch: 11 training_loss 4.362210330963134 test_loss: 4.368888473510742
epoch: 12 training_loss 4.097001810073852 test_loss: 4.0335243225097654
epoch: 13 training_loss 3.9928705668449402 test_loss: 3.788316345214844
epoch: 14 training_loss 3.754208650588989 test_loss: 4.1387287139892575
epoch: 15 training_loss 3.699218361377716 test_loss: 3.606888198852539
epoch: 16 training_loss 3.5047294449806214 test_loss: 3.5509765625
epoch: 17 training_loss 3.3884993529319765 test_loss: 3.272964096069336
epoch: 18 training_loss 3.2572590637207033 test_loss: 3.458190155029297
epoch: 19 training_loss 3.283667960166931 test_loss: 3.1464487075805665
epoch: 20 training_loss 3.0811316990852355 test_loss: 3.08007698059082
epoch: 21 training_loss 3.042567718029022 test_loss: 3.1298728942871095
epoch: 22 training_loss 2.9657383966445923 test_loss: 2.9994592666625977
epoch: 23 training_loss 2.9540655279159544 test_loss: 2.747890281677246
epoch: 24 training_loss 2.8366404294967653 test_loss: 3.0743892669677733
epoch: 25 training_loss 2.8166743993759153 test_loss: 2.819751167297363
epoch: 26 training_loss 2.743091206550598 test_loss: 2.855548095703125
epoch: 27 training_loss 2.746470537185669 test_loss: 2.8362552642822267
epoch: 28 training_loss 2.575942497253418 test_loss: 2.5576845169067384
epoch: 29 training_loss 2.6435673451423645 test_loss: 2.5370790481567385
epoch: 30 training_loss 2.5393830800056456 test_loss: 2.6278608322143553
epoch: 31 training_loss 2.4601438856124878 test_loss: 2.5359954833984375
epoch: 32 training_loss 2.436947979927063 test_loss: 2.454267120361328
epoch: 33 training_loss 2.386564836502075 test_loss: 2.3888198852539064
epoch: 34 training_loss 2.4290772128105163 test_loss: 2.303326225280762
epoch: 35 training_loss 2.3809187519550323 test_loss: 2.3022182464599608
epoch: 36 training_loss 2.2954331612586976 test_loss: 2.216455078125
epoch: 37 training_loss 2.289739899635315 test_loss: 2.488312530517578
epoch: 38 training_loss 2.2596564304828646 test_loss: 2.408286285400391
epoch: 39 training_loss 2.2317975533008574 test_loss: 2.2536468505859375
epoch: 40 training_loss 2.2369078516960146 test_loss: 2.337006187438965
epoch: 41 training_loss 2.2319627058506013 test_loss: 2.1253570556640624
epoch: 42 training_loss 2.1834677088260652 test_loss: 2.2659053802490234
epoch: 43 training_loss 2.1952643954753874 test_loss: 2.138118362426758
epoch: 44 training_loss 2.116158375740051 test_loss: 2.1470596313476564
epoch: 45 training_loss 2.119671436548233 test_loss: 2.552301788330078
epoch: 46 training_loss 2.0722806775569915 test_loss: 2.0025110244750977
epoch: 47 training_loss 2.0407578575611116 test_loss: 2.084498977661133
epoch: 48 training_loss 2.0884854876995087 test_loss: 2.1605113983154296
epoch: 49 training_loss 2.0461902952194215 test_loss: 2.092719841003418
epoch: 50 training_loss 2.0345766055583954 test_loss: 2.1135976791381834
epoch: 51 training_loss 1.9787101912498475 test_loss: 2.0353843688964846
epoch: 52 training_loss 2.0013761532306673 test_loss: 1.9768726348876953
epoch: 53 training_loss 2.020735697746277 test_loss: 2.05564022064209
epoch: 54 training_loss 1.9674724912643433 test_loss: 2.072551727294922
epoch: 55 training_loss 1.9729802370071412 test_loss: 1.9158006668090821
epoch: 56 training_loss 1.916203759908676 test_loss: 1.9215259552001953
epoch: 57 training_loss 1.899156883955002 test_loss: 1.8212873458862304
epoch: 58 training_loss 1.9277754509449005 test_loss: 1.8804740905761719
epoch: 59 training_loss 1.8861188220977783 test_loss: 1.9875980377197267
epoch: 60 training_loss 1.8731372952461243 test_loss: 1.9442138671875
epoch: 61 training_loss 1.9106044018268584 test_loss: 1.95636043548584
epoch: 62 training_loss 1.8677766954898833 test_loss: 1.9116872787475585
epoch: 63 training_loss 1.8213002014160156 test_loss: 1.8288875579833985
epoch: 64 training_loss 1.8114056289196014 test_loss: 1.8859943389892577
epoch: 65 training_loss 1.8087300729751588 test_loss: 1.791071891784668
epoch: 66 training_loss 1.8398654878139495 test_loss: 1.8851524353027345
epoch: 67 training_loss 1.80051255941391 test_loss: 1.861332893371582
epoch: 68 training_loss 1.8104910635948182 test_loss: 1.7580774307250977
epoch: 69 training_loss 1.7963111448287963 test_loss: 1.7708465576171875
epoch: 70 training_loss 1.7774368059635162 test_loss: 1.8137590408325195
epoch: 71 training_loss 1.7659140467643737 test_loss: 1.7784694671630858
epoch: 72 training_loss 1.791894909143448 test_loss: 1.8138383865356444
epoch: 73 training_loss 1.7569746446609498 test_loss: 1.712059211730957
epoch: 74 training_loss 1.752879627943039 test_loss: 1.7555160522460938
epoch: 75 training_loss 1.7237210404872894 test_loss: 1.7445171356201172
epoch: 76 training_loss 1.7863609981536865 test_loss: 1.6635128021240235
epoch: 77 training_loss 1.7490688705444335 test_loss: 1.868406105041504
epoch: 78 training_loss 1.7100706446170806 test_loss: 1.7303216934204102
epoch: 79 training_loss 1.7216344499588012 test_loss: 1.8931486129760742
5067.584118760582
episode: 0 training return: tensor(-118.1309, device='cuda:0')
episode: 1 training return: tensor(-70.5218, device='cuda:0')
episode: 2 training return: tensor(-129.7976, device='cuda:0')
episode: 3 training return: tensor(-94.9302, device='cuda:0')
epoch: 1 test_true_pfm: 5061.845913650276
episode: 4 training return: tensor(-88.6816, device='cuda:0')
episode: 5 training return: tensor(-131.6214, device='cuda:0')
episode: 6 training return: tensor(-173.1142, device='cuda:0')
episode: 7 training return: tensor(-172.2415, device='cuda:0')
epoch: 2 test_true_pfm: 5105.475258701305
episode: 8 training return: tensor(-126.2422, device='cuda:0')
episode: 9 training return: tensor(-57.3670, device='cuda:0')
episode: 10 training return: tensor(-220.9957, device='cuda:0')
episode: 11 training return: tensor(-157.8736, device='cuda:0')
epoch: 3 test_true_pfm: 5102.96180219168
episode: 12 training return: tensor(-50.1690, device='cuda:0')
episode: 13 training return: tensor(-44.3606, device='cuda:0')
episode: 14 training return: tensor(-165.7216, device='cuda:0')
episode: 15 training return: tensor(-53.1768, device='cuda:0')
epoch: 4 test_true_pfm: 5042.002609105906
episode: 16 training return: tensor(-231.3508, device='cuda:0')
episode: 17 training return: tensor(-171.1884, device='cuda:0')
episode: 18 training return: tensor(-77.1117, device='cuda:0')
episode: 19 training return: tensor(-213.8968, device='cuda:0')
epoch: 5 test_true_pfm: 5117.921858460811
episode: 20 training return: tensor(10.3833, device='cuda:0')
episode: 21 training return: tensor(-79.4085, device='cuda:0')
episode: 22 training return: tensor(-106.4476, device='cuda:0')
episode: 23 training return: tensor(-89.1103, device='cuda:0')
epoch: 6 test_true_pfm: 5169.597143048634
episode: 24 training return: tensor(-100.7674, device='cuda:0')
episode: 25 training return: tensor(-139.8737, device='cuda:0')
episode: 26 training return: tensor(-160.3600, device='cuda:0')
episode: 27 training return: tensor(-151.7533, device='cuda:0')
epoch: 7 test_true_pfm: 5156.695040312643
episode: 28 training return: tensor(-57.0014, device='cuda:0')
episode: 29 training return: tensor(-200.8599, device='cuda:0')
episode: 30 training return: tensor(-84.9246, device='cuda:0')
episode: 31 training return: tensor(-39.5780, device='cuda:0')
epoch: 8 test_true_pfm: 5204.45035092294
episode: 32 training return: tensor(-13.4135, device='cuda:0')
episode: 33 training return: tensor(-48.6877, device='cuda:0')
episode: 34 training return: tensor(-41.2218, device='cuda:0')
episode: 35 training return: tensor(-77.1474, device='cuda:0')
epoch: 9 test_true_pfm: 5078.720800181666
episode: 36 training return: tensor(14.1802, device='cuda:0')
episode: 37 training return: tensor(-79.4694, device='cuda:0')
episode: 38 training return: tensor(-41.9690, device='cuda:0')
episode: 39 training return: tensor(-29.7352, device='cuda:0')
epoch: 10 test_true_pfm: 5172.971664437225
episode: 40 training return: tensor(-37.2863, device='cuda:0')
episode: 41 training return: tensor(-77.6462, device='cuda:0')
episode: 42 training return: tensor(-148.3812, device='cuda:0')
episode: 43 training return: tensor(-145.6588, device='cuda:0')
epoch: 11 test_true_pfm: 5123.356875442059
episode: 44 training return: tensor(-71.1316, device='cuda:0')
episode: 45 training return: tensor(-54.8008, device='cuda:0')
episode: 46 training return: tensor(-90.2043, device='cuda:0')
episode: 47 training return: tensor(-46.4830, device='cuda:0')
epoch: 12 test_true_pfm: 5107.857982622306
episode: 48 training return: tensor(-194.8297, device='cuda:0')
episode: 49 training return: tensor(-59.0091, device='cuda:0')
episode: 50 training return: tensor(-92.0492, device='cuda:0')
episode: 51 training return: tensor(-101.8804, device='cuda:0')
epoch: 13 test_true_pfm: 5140.869681363712
episode: 52 training return: tensor(-180.2443, device='cuda:0')
episode: 53 training return: tensor(-79.7908, device='cuda:0')
episode: 54 training return: tensor(-33.5816, device='cuda:0')
episode: 55 training return: tensor(-122.2100, device='cuda:0')
epoch: 14 test_true_pfm: 5079.649470797094
episode: 56 training return: tensor(-45.3476, device='cuda:0')
episode: 57 training return: tensor(-61.7936, device='cuda:0')
episode: 58 training return: tensor(-137.8900, device='cuda:0')
episode: 59 training return: tensor(-41.2363, device='cuda:0')
epoch: 15 test_true_pfm: 5133.333384046429
episode: 60 training return: tensor(-59.8871, device='cuda:0')
episode: 61 training return: tensor(-5.4435, device='cuda:0')
episode: 62 training return: tensor(20.2545, device='cuda:0')
episode: 63 training return: tensor(-103.1563, device='cuda:0')
epoch: 16 test_true_pfm: 5090.835380439118
episode: 64 training return: tensor(-117.8718, device='cuda:0')
episode: 65 training return: tensor(-132.1374, device='cuda:0')
episode: 66 training return: tensor(-80.2534, device='cuda:0')
episode: 67 training return: tensor(86.9394, device='cuda:0')
epoch: 17 test_true_pfm: 5323.045756716805
episode: 68 training return: tensor(-60.4368, device='cuda:0')
episode: 69 training return: tensor(-102.6193, device='cuda:0')
episode: 70 training return: tensor(-197.6369, device='cuda:0')
episode: 71 training return: tensor(48.6758, device='cuda:0')
epoch: 18 test_true_pfm: 5079.416419688125
episode: 72 training return: tensor(-28.7584, device='cuda:0')
episode: 73 training return: tensor(1.8476, device='cuda:0')
episode: 74 training return: tensor(-38.4299, device='cuda:0')
episode: 75 training return: tensor(-79.3310, device='cuda:0')
epoch: 19 test_true_pfm: 5283.566264876215
episode: 76 training return: tensor(-78.2569, device='cuda:0')
episode: 77 training return: tensor(69.9830, device='cuda:0')
episode: 78 training return: tensor(-71.6690, device='cuda:0')
episode: 79 training return: tensor(-56.4868, device='cuda:0')
epoch: 20 test_true_pfm: 5303.299733464218
episode: 80 training return: tensor(-67.0206, device='cuda:0')
episode: 81 training return: tensor(-94.8013, device='cuda:0')
episode: 82 training return: tensor(-81.4576, device='cuda:0')
episode: 83 training return: tensor(-101.8264, device='cuda:0')
epoch: 21 test_true_pfm: 5340.592445171917
episode: 84 training return: tensor(4.5346, device='cuda:0')
episode: 85 training return: tensor(-8.3219, device='cuda:0')
episode: 86 training return: tensor(18.5586, device='cuda:0')
episode: 87 training return: tensor(-15.1762, device='cuda:0')
epoch: 22 test_true_pfm: 5279.203511213487
episode: 88 training return: tensor(35.6704, device='cuda:0')
episode: 89 training return: tensor(5.9014, device='cuda:0')
episode: 90 training return: tensor(-8.3350, device='cuda:0')
episode: 91 training return: tensor(-1.3601, device='cuda:0')
epoch: 23 test_true_pfm: 5357.270811043148
episode: 92 training return: tensor(-31.2906, device='cuda:0')
episode: 93 training return: tensor(-131.9723, device='cuda:0')
episode: 94 training return: tensor(-45.2604, device='cuda:0')
episode: 95 training return: tensor(-13.4467, device='cuda:0')
epoch: 24 test_true_pfm: 5220.302096942432
episode: 96 training return: tensor(-12.2038, device='cuda:0')
episode: 97 training return: tensor(-32.8685, device='cuda:0')
episode: 98 training return: tensor(84.2803, device='cuda:0')
episode: 99 training return: tensor(89.3877, device='cuda:0')
epoch: 25 test_true_pfm: 5237.505390825157
episode: 100 training return: tensor(-28.1770, device='cuda:0')
episode: 101 training return: tensor(30.6645, device='cuda:0')
episode: 102 training return: tensor(-16.6876, device='cuda:0')
episode: 103 training return: tensor(163.8732, device='cuda:0')
epoch: 26 test_true_pfm: 5289.38396366741
episode: 104 training return: tensor(55.5795, device='cuda:0')
episode: 105 training return: tensor(83.8795, device='cuda:0')
episode: 106 training return: tensor(-22.5527, device='cuda:0')
episode: 107 training return: tensor(41.6209, device='cuda:0')
epoch: 27 test_true_pfm: 5342.862912208263
episode: 108 training return: tensor(15.9050, device='cuda:0')
episode: 109 training return: tensor(-33.5001, device='cuda:0')
episode: 110 training return: tensor(89.4281, device='cuda:0')
episode: 111 training return: tensor(-60.1154, device='cuda:0')
epoch: 28 test_true_pfm: 5346.542382426046
episode: 112 training return: tensor(57.5300, device='cuda:0')
episode: 113 training return: tensor(4.9527, device='cuda:0')
episode: 114 training return: tensor(0.6586, device='cuda:0')
episode: 115 training return: tensor(-70.8912, device='cuda:0')
epoch: 29 test_true_pfm: 5412.970563344599
episode: 116 training return: tensor(19.7976, device='cuda:0')
episode: 117 training return: tensor(75.3305, device='cuda:0')
episode: 118 training return: tensor(-87.1494, device='cuda:0')
episode: 119 training return: tensor(106.9883, device='cuda:0')
epoch: 30 test_true_pfm: 5334.007571808044
episode: 120 training return: tensor(-81.8240, device='cuda:0')
episode: 121 training return: tensor(23.9915, device='cuda:0')
episode: 122 training return: tensor(96.4140, device='cuda:0')
episode: 123 training return: tensor(94.2964, device='cuda:0')
epoch: 31 test_true_pfm: 5323.760507469592
episode: 124 training return: tensor(13.0955, device='cuda:0')
episode: 125 training return: tensor(124.9380, device='cuda:0')
episode: 126 training return: tensor(25.9888, device='cuda:0')
episode: 127 training return: tensor(70.5431, device='cuda:0')
epoch: 32 test_true_pfm: 5300.560509842897
episode: 128 training return: tensor(119.2992, device='cuda:0')
episode: 129 training return: tensor(-0.0799, device='cuda:0')
episode: 130 training return: tensor(207.7794, device='cuda:0')
episode: 131 training return: tensor(-24.3140, device='cuda:0')
epoch: 33 test_true_pfm: 5405.231292976266
episode: 132 training return: tensor(-37.0023, device='cuda:0')
episode: 133 training return: tensor(74.5360, device='cuda:0')
episode: 134 training return: tensor(14.4729, device='cuda:0')
episode: 135 training return: tensor(143.2596, device='cuda:0')
epoch: 34 test_true_pfm: 5268.651685784439
episode: 136 training return: tensor(-64.0248, device='cuda:0')
episode: 137 training return: tensor(20.0876, device='cuda:0')
episode: 138 training return: tensor(117.8286, device='cuda:0')
episode: 139 training return: tensor(131.3523, device='cuda:0')
epoch: 35 test_true_pfm: 5312.306213284595
episode: 140 training return: tensor(58.4716, device='cuda:0')
episode: 141 training return: tensor(9.7080, device='cuda:0')
episode: 142 training return: tensor(51.0181, device='cuda:0')
episode: 143 training return: tensor(59.9678, device='cuda:0')
epoch: 36 test_true_pfm: 5408.070789674401
episode: 144 training return: tensor(100.4329, device='cuda:0')
episode: 145 training return: tensor(39.0891, device='cuda:0')
episode: 146 training return: tensor(5.2610, device='cuda:0')
episode: 147 training return: tensor(98.7072, device='cuda:0')
epoch: 37 test_true_pfm: 5477.811604094066
episode: 148 training return: tensor(66.0199, device='cuda:0')
episode: 149 training return: tensor(15.5228, device='cuda:0')
episode: 150 training return: tensor(69.5477, device='cuda:0')
episode: 151 training return: tensor(62.0594, device='cuda:0')
epoch: 38 test_true_pfm: 5425.319216846835
episode: 152 training return: tensor(134.5973, device='cuda:0')
episode: 153 training return: tensor(88.4517, device='cuda:0')
episode: 154 training return: tensor(16.9717, device='cuda:0')
episode: 155 training return: tensor(49.1018, device='cuda:0')
epoch: 39 test_true_pfm: 5475.014937129711
episode: 156 training return: tensor(22.4514, device='cuda:0')
episode: 157 training return: tensor(57.5515, device='cuda:0')
episode: 158 training return: tensor(-81.7548, device='cuda:0')
episode: 159 training return: tensor(144.1205, device='cuda:0')
epoch: 40 test_true_pfm: 5441.351146455908
episode: 160 training return: tensor(69.9837, device='cuda:0')
episode: 161 training return: tensor(94.3782, device='cuda:0')
episode: 162 training return: tensor(161.6956, device='cuda:0')
episode: 163 training return: tensor(119.6650, device='cuda:0')
epoch: 41 test_true_pfm: 5497.429946861009
episode: 164 training return: tensor(99.4239, device='cuda:0')
episode: 165 training return: tensor(27.9749, device='cuda:0')
episode: 166 training return: tensor(51.7845, device='cuda:0')
episode: 167 training return: tensor(-2.6957, device='cuda:0')
epoch: 42 test_true_pfm: 5401.32410465573
episode: 168 training return: tensor(32.0555, device='cuda:0')
episode: 169 training return: tensor(-34.3213, device='cuda:0')
episode: 170 training return: tensor(151.4298, device='cuda:0')
episode: 171 training return: tensor(108.6830, device='cuda:0')
epoch: 43 test_true_pfm: 5441.2515904431675
episode: 172 training return: tensor(181.2759, device='cuda:0')
episode: 173 training return: tensor(83.4293, device='cuda:0')
episode: 174 training return: tensor(93.3342, device='cuda:0')
episode: 175 training return: tensor(7.0830, device='cuda:0')
epoch: 44 test_true_pfm: 5445.836242796956
episode: 176 training return: tensor(12.4702, device='cuda:0')
episode: 177 training return: tensor(68.2209, device='cuda:0')
episode: 178 training return: tensor(136.8281, device='cuda:0')
episode: 179 training return: tensor(121.4144, device='cuda:0')
epoch: 45 test_true_pfm: 5447.714240845308
episode: 180 training return: tensor(111.5633, device='cuda:0')
episode: 181 training return: tensor(97.8704, device='cuda:0')
episode: 182 training return: tensor(193.0076, device='cuda:0')
episode: 183 training return: tensor(121.3051, device='cuda:0')
epoch: 46 test_true_pfm: 5455.12291423842
episode: 184 training return: tensor(32.2717, device='cuda:0')
episode: 185 training return: tensor(175.6889, device='cuda:0')
episode: 186 training return: tensor(1.7275, device='cuda:0')
episode: 187 training return: tensor(138.4794, device='cuda:0')
epoch: 47 test_true_pfm: 5454.625868053148
episode: 188 training return: tensor(83.2562, device='cuda:0')
episode: 189 training return: tensor(111.9411, device='cuda:0')
episode: 190 training return: tensor(139.9627, device='cuda:0')
episode: 191 training return: tensor(16.0880, device='cuda:0')
epoch: 48 test_true_pfm: 5480.1271486169635
episode: 192 training return: tensor(52.8760, device='cuda:0')
episode: 193 training return: tensor(160.7354, device='cuda:0')
episode: 194 training return: tensor(-44.8899, device='cuda:0')
episode: 195 training return: tensor(57.3510, device='cuda:0')
epoch: 49 test_true_pfm: 5452.898697668771
episode: 196 training return: tensor(112.4651, device='cuda:0')
episode: 197 training return: tensor(26.3160, device='cuda:0')
episode: 198 training return: tensor(121.4374, device='cuda:0')
episode: 199 training return: tensor(95.5416, device='cuda:0')
epoch: 50 test_true_pfm: 5436.588777656201
episode: 200 training return: tensor(118.3963, device='cuda:0')
episode: 201 training return: tensor(165.4794, device='cuda:0')
episode: 202 training return: tensor(12.8310, device='cuda:0')
episode: 203 training return: tensor(107.3708, device='cuda:0')
epoch: 51 test_true_pfm: 4640.768129381529
episode: 204 training return: tensor(149.5919, device='cuda:0')
episode: 205 training return: tensor(81.7008, device='cuda:0')
episode: 206 training return: tensor(81.9438, device='cuda:0')
episode: 207 training return: tensor(213.6548, device='cuda:0')
epoch: 52 test_true_pfm: 5402.833910214011
episode: 208 training return: tensor(-21.5907, device='cuda:0')
episode: 209 training return: tensor(39.4498, device='cuda:0')
episode: 210 training return: tensor(15.0616, device='cuda:0')
episode: 211 training return: tensor(142.6947, device='cuda:0')
epoch: 53 test_true_pfm: 5426.975869902037
episode: 212 training return: tensor(69.1958, device='cuda:0')
episode: 213 training return: tensor(-4.5200, device='cuda:0')
episode: 214 training return: tensor(70.0326, device='cuda:0')
episode: 215 training return: tensor(-70.0016, device='cuda:0')
epoch: 54 test_true_pfm: 5383.110875699024
episode: 216 training return: tensor(101.7346, device='cuda:0')
episode: 217 training return: tensor(-45.5860, device='cuda:0')
episode: 218 training return: tensor(209.2330, device='cuda:0')
episode: 219 training return: tensor(85.0397, device='cuda:0')
epoch: 55 test_true_pfm: 5469.803766206594
episode: 220 training return: tensor(168.0376, device='cuda:0')
episode: 221 training return: tensor(114.3986, device='cuda:0')
episode: 222 training return: tensor(167.0589, device='cuda:0')
episode: 223 training return: tensor(132.1941, device='cuda:0')
epoch: 56 test_true_pfm: 5477.656509028798
episode: 224 training return: tensor(209.8572, device='cuda:0')
episode: 225 training return: tensor(100.1641, device='cuda:0')
episode: 226 training return: tensor(101.8585, device='cuda:0')
episode: 227 training return: tensor(167.0212, device='cuda:0')
epoch: 57 test_true_pfm: 5459.470157867498
episode: 228 training return: tensor(65.7921, device='cuda:0')
episode: 229 training return: tensor(63.1576, device='cuda:0')
episode: 230 training return: tensor(171.7754, device='cuda:0')
episode: 231 training return: tensor(85.0368, device='cuda:0')
epoch: 58 test_true_pfm: 5594.985093291164
episode: 232 training return: tensor(-52.9754, device='cuda:0')
episode: 233 training return: tensor(113.5376, device='cuda:0')
episode: 234 training return: tensor(74.4533, device='cuda:0')
episode: 235 training return: tensor(173.4834, device='cuda:0')
epoch: 59 test_true_pfm: 5468.238669663115
episode: 236 training return: tensor(62.7006, device='cuda:0')
episode: 237 training return: tensor(14.9352, device='cuda:0')
episode: 238 training return: tensor(11.9377, device='cuda:0')
episode: 239 training return: tensor(156.5846, device='cuda:0')
epoch: 60 test_true_pfm: 5481.72987930696
episode: 240 training return: tensor(-43.6880, device='cuda:0')
episode: 241 training return: tensor(136.9729, device='cuda:0')
episode: 242 training return: tensor(59.8058, device='cuda:0')
episode: 243 training return: tensor(92.1758, device='cuda:0')
epoch: 61 test_true_pfm: 5503.375950155468
episode: 244 training return: tensor(79.8091, device='cuda:0')
episode: 245 training return: tensor(49.1530, device='cuda:0')
episode: 246 training return: tensor(97.9113, device='cuda:0')
episode: 247 training return: tensor(148.7919, device='cuda:0')
epoch: 62 test_true_pfm: 4830.347640354675
episode: 248 training return: tensor(53.7354, device='cuda:0')
episode: 249 training return: tensor(173.5737, device='cuda:0')
episode: 250 training return: tensor(47.9583, device='cuda:0')
episode: 251 training return: tensor(160.3189, device='cuda:0')
epoch: 63 test_true_pfm: 5553.999179831892
episode: 252 training return: tensor(56.3788, device='cuda:0')
episode: 253 training return: tensor(80.7892, device='cuda:0')
episode: 254 training return: tensor(35.0705, device='cuda:0')
episode: 255 training return: tensor(-4.7253, device='cuda:0')
epoch: 64 test_true_pfm: 5541.229510915572
episode: 256 training return: tensor(162.7292, device='cuda:0')
episode: 257 training return: tensor(75.5018, device='cuda:0')
episode: 258 training return: tensor(158.9144, device='cuda:0')
episode: 259 training return: tensor(159.7339, device='cuda:0')
epoch: 65 test_true_pfm: 5462.350080550757
episode: 260 training return: tensor(-11.3132, device='cuda:0')
episode: 261 training return: tensor(208.1799, device='cuda:0')
episode: 262 training return: tensor(122.8948, device='cuda:0')
episode: 263 training return: tensor(102.4578, device='cuda:0')
epoch: 66 test_true_pfm: 5496.295732348427
episode: 264 training return: tensor(77.2379, device='cuda:0')
episode: 265 training return: tensor(38.8541, device='cuda:0')
episode: 266 training return: tensor(167.3431, device='cuda:0')
episode: 267 training return: tensor(139.7768, device='cuda:0')
epoch: 67 test_true_pfm: 5431.442757067714
episode: 268 training return: tensor(129.5192, device='cuda:0')
episode: 269 training return: tensor(76.7335, device='cuda:0')
episode: 270 training return: tensor(35.3705, device='cuda:0')
episode: 271 training return: tensor(148.0102, device='cuda:0')
epoch: 68 test_true_pfm: 5549.978480144645
episode: 272 training return: tensor(163.1379, device='cuda:0')
episode: 273 training return: tensor(62.3553, device='cuda:0')
episode: 274 training return: tensor(152.5368, device='cuda:0')
episode: 275 training return: tensor(141.4104, device='cuda:0')
epoch: 69 test_true_pfm: 5465.211991626168
episode: 276 training return: tensor(83.2818, device='cuda:0')
episode: 277 training return: tensor(182.7601, device='cuda:0')
episode: 278 training return: tensor(246.7817, device='cuda:0')
episode: 279 training return: tensor(234.4874, device='cuda:0')
epoch: 70 test_true_pfm: 5526.275258372964
episode: 280 training return: tensor(121.3693, device='cuda:0')
episode: 281 training return: tensor(136.8862, device='cuda:0')
episode: 282 training return: tensor(130.8865, device='cuda:0')
episode: 283 training return: tensor(109.8164, device='cuda:0')
epoch: 71 test_true_pfm: 5556.489220892819
episode: 284 training return: tensor(213.2346, device='cuda:0')
episode: 285 training return: tensor(144.3931, device='cuda:0')
episode: 286 training return: tensor(86.8325, device='cuda:0')
episode: 287 training return: tensor(132.2623, device='cuda:0')
epoch: 72 test_true_pfm: 5577.162603486016
episode: 288 training return: tensor(195.6465, device='cuda:0')
episode: 289 training return: tensor(133.3598, device='cuda:0')
episode: 290 training return: tensor(177.9496, device='cuda:0')
episode: 291 training return: tensor(128.3803, device='cuda:0')
epoch: 73 test_true_pfm: 5613.973257089946
episode: 292 training return: tensor(228.2549, device='cuda:0')
episode: 293 training return: tensor(7.0666, device='cuda:0')
episode: 294 training return: tensor(144.6131, device='cuda:0')
episode: 295 training return: tensor(145.4938, device='cuda:0')
epoch: 74 test_true_pfm: 5491.005926087771
episode: 296 training return: tensor(55.7553, device='cuda:0')
episode: 297 training return: tensor(169.6498, device='cuda:0')
episode: 298 training return: tensor(221.5370, device='cuda:0')
episode: 299 training return: tensor(191.3435, device='cuda:0')
epoch: 75 test_true_pfm: 5493.858470418104
episode: 300 training return: tensor(87.5588, device='cuda:0')
episode: 301 training return: tensor(260.6245, device='cuda:0')
episode: 302 training return: tensor(189.1486, device='cuda:0')
episode: 303 training return: tensor(148.6390, device='cuda:0')
epoch: 76 test_true_pfm: 5678.032543119837
episode: 304 training return: tensor(229.8560, device='cuda:0')
episode: 305 training return: tensor(20.9782, device='cuda:0')
episode: 306 training return: tensor(136.2210, device='cuda:0')
episode: 307 training return: tensor(201.3035, device='cuda:0')
epoch: 77 test_true_pfm: 5535.161209133287
episode: 308 training return: tensor(130.5541, device='cuda:0')
episode: 309 training return: tensor(138.7194, device='cuda:0')
episode: 310 training return: tensor(24.1677, device='cuda:0')
episode: 311 training return: tensor(142.5474, device='cuda:0')
epoch: 78 test_true_pfm: 5596.753112123511
episode: 312 training return: tensor(169.5937, device='cuda:0')
episode: 313 training return: tensor(126.1589, device='cuda:0')
episode: 314 training return: tensor(47.7136, device='cuda:0')
episode: 315 training return: tensor(135.1333, device='cuda:0')
epoch: 79 test_true_pfm: 5576.133656775189
episode: 316 training return: tensor(175.5670, device='cuda:0')
episode: 317 training return: tensor(186.6622, device='cuda:0')
episode: 318 training return: tensor(152.5186, device='cuda:0')
episode: 319 training return: tensor(207.9368, device='cuda:0')
epoch: 80 test_true_pfm: 5550.793168054875
episode: 320 training return: tensor(59.9821, device='cuda:0')
episode: 321 training return: tensor(270.2833, device='cuda:0')
episode: 322 training return: tensor(181.1640, device='cuda:0')
episode: 323 training return: tensor(112.7732, device='cuda:0')
epoch: 81 test_true_pfm: 5570.109732428551
episode: 324 training return: tensor(34.6113, device='cuda:0')
episode: 325 training return: tensor(229.9704, device='cuda:0')
episode: 326 training return: tensor(303.1624, device='cuda:0')
episode: 327 training return: tensor(111.6440, device='cuda:0')
epoch: 82 test_true_pfm: 5595.169250466395
episode: 328 training return: tensor(118.1196, device='cuda:0')
episode: 329 training return: tensor(94.7557, device='cuda:0')
episode: 330 training return: tensor(299.2141, device='cuda:0')
episode: 331 training return: tensor(159.4108, device='cuda:0')
epoch: 83 test_true_pfm: 5535.686040379907
episode: 332 training return: tensor(8.1208, device='cuda:0')
episode: 333 training return: tensor(68.6790, device='cuda:0')
episode: 334 training return: tensor(194.0619, device='cuda:0')
episode: 335 training return: tensor(83.1323, device='cuda:0')
epoch: 84 test_true_pfm: 5513.312735486169
episode: 336 training return: tensor(83.9321, device='cuda:0')
episode: 337 training return: tensor(159.7198, device='cuda:0')
episode: 338 training return: tensor(154.6248, device='cuda:0')
episode: 339 training return: tensor(111.5959, device='cuda:0')
epoch: 85 test_true_pfm: 5656.855532588473
episode: 340 training return: tensor(213.2734, device='cuda:0')
episode: 341 training return: tensor(132.5707, device='cuda:0')
episode: 342 training return: tensor(148.1078, device='cuda:0')
episode: 343 training return: tensor(157.6467, device='cuda:0')
epoch: 86 test_true_pfm: 5665.968189629532
episode: 344 training return: tensor(117.8660, device='cuda:0')
episode: 345 training return: tensor(257.2133, device='cuda:0')
episode: 346 training return: tensor(120.0533, device='cuda:0')
episode: 347 training return: tensor(82.8263, device='cuda:0')
epoch: 87 test_true_pfm: 5625.20196005034
episode: 348 training return: tensor(157.3248, device='cuda:0')
episode: 349 training return: tensor(153.3047, device='cuda:0')
episode: 350 training return: tensor(235.3323, device='cuda:0')
episode: 351 training return: tensor(246.7973, device='cuda:0')
epoch: 88 test_true_pfm: 5624.430397432872
episode: 352 training return: tensor(239.7261, device='cuda:0')
episode: 353 training return: tensor(228.0766, device='cuda:0')
episode: 354 training return: tensor(125.8463, device='cuda:0')
episode: 355 training return: tensor(307.7906, device='cuda:0')
epoch: 89 test_true_pfm: 5641.7020431535375
episode: 356 training return: tensor(207.0918, device='cuda:0')
episode: 357 training return: tensor(55.8858, device='cuda:0')
episode: 358 training return: tensor(144.2147, device='cuda:0')
episode: 359 training return: tensor(176.7051, device='cuda:0')
epoch: 90 test_true_pfm: 5629.207361483878
episode: 360 training return: tensor(114.7617, device='cuda:0')
episode: 361 training return: tensor(205.0812, device='cuda:0')
episode: 362 training return: tensor(120.4815, device='cuda:0')
episode: 363 training return: tensor(206.0608, device='cuda:0')
epoch: 91 test_true_pfm: 5694.714677868105
episode: 364 training return: tensor(105.9611, device='cuda:0')
episode: 365 training return: tensor(175.2454, device='cuda:0')
episode: 366 training return: tensor(230.6254, device='cuda:0')
episode: 367 training return: tensor(216.2362, device='cuda:0')
epoch: 92 test_true_pfm: 5590.182489874863
episode: 368 training return: tensor(183.3676, device='cuda:0')
episode: 369 training return: tensor(180.1703, device='cuda:0')
episode: 370 training return: tensor(270.7327, device='cuda:0')
episode: 371 training return: tensor(174.2610, device='cuda:0')
epoch: 93 test_true_pfm: 5617.782810193489
episode: 372 training return: tensor(167.3422, device='cuda:0')
episode: 373 training return: tensor(224.9192, device='cuda:0')
episode: 374 training return: tensor(110.9667, device='cuda:0')
episode: 375 training return: tensor(250.3067, device='cuda:0')
epoch: 94 test_true_pfm: 5543.798795647736
episode: 376 training return: tensor(9.9371, device='cuda:0')
episode: 377 training return: tensor(248.1320, device='cuda:0')
episode: 378 training return: tensor(224.7012, device='cuda:0')
episode: 379 training return: tensor(172.6830, device='cuda:0')
epoch: 95 test_true_pfm: 5606.048157613214
episode: 380 training return: tensor(215.3713, device='cuda:0')
episode: 381 training return: tensor(212.9075, device='cuda:0')
episode: 382 training return: tensor(151.8932, device='cuda:0')
episode: 383 training return: tensor(283.7237, device='cuda:0')
epoch: 96 test_true_pfm: 5598.679340034557
episode: 384 training return: tensor(112.9691, device='cuda:0')
episode: 385 training return: tensor(241.1311, device='cuda:0')
episode: 386 training return: tensor(197.9055, device='cuda:0')
episode: 387 training return: tensor(170.2732, device='cuda:0')
epoch: 97 test_true_pfm: 5641.132526218771
episode: 388 training return: tensor(123.9468, device='cuda:0')
episode: 389 training return: tensor(164.8091, device='cuda:0')
episode: 390 training return: tensor(163.5722, device='cuda:0')
episode: 391 training return: tensor(199.2228, device='cuda:0')
epoch: 98 test_true_pfm: 5629.824622550506
episode: 392 training return: tensor(209.7116, device='cuda:0')
episode: 393 training return: tensor(241.6875, device='cuda:0')
episode: 394 training return: tensor(194.8182, device='cuda:0')
episode: 395 training return: tensor(143.7514, device='cuda:0')
epoch: 99 test_true_pfm: 5584.708584115734
episode: 396 training return: tensor(1.2211, device='cuda:0')
episode: 397 training return: tensor(185.2629, device='cuda:0')
episode: 398 training return: tensor(243.8002, device='cuda:0')
episode: 399 training return: tensor(206.0514, device='cuda:0')
epoch: 100 test_true_pfm: 5568.270680190952
