['--alg', 'ddpg', '--env', 'Swimmer-v3', '--learn', 'brac', '--traj', 'medium', '--seed', '3', '--data', '100000']
epoch: 0 training_loss 4.243116302490234 test_loss: 2.9421058654785157
epoch: 1 training_loss 2.318891654014587 test_loss: 1.8779394149780273
epoch: 2 training_loss 1.46488368332386 test_loss: 1.1321815490722655
epoch: 3 training_loss 0.8806372556090355 test_loss: 0.6544028282165527
epoch: 4 training_loss 0.4164573059603572 test_loss: 0.21674714088439942
epoch: 5 training_loss 0.1120383583707735 test_loss: -0.04951373338699341
epoch: 6 training_loss -0.16302636640146376 test_loss: -0.26775388717651366
epoch: 7 training_loss -0.43920128015801313 test_loss: -0.484678840637207
epoch: 8 training_loss -0.5580882232775912 test_loss: -0.7329922199249268
epoch: 9 training_loss -0.6910926060378552 test_loss: -0.7352396488189697
epoch: 10 training_loss -0.9028130584955215 test_loss: -0.9179755210876465
epoch: 11 training_loss -1.096141438782215 test_loss: -1.1563178062438966
epoch: 12 training_loss -1.269215576648712 test_loss: -1.2747917175292969
epoch: 13 training_loss -1.4364849543571472 test_loss: -1.480850601196289
epoch: 14 training_loss -1.617326059937477 test_loss: -1.6076274871826173
epoch: 15 training_loss -1.7816839414834975 test_loss: -1.811307716369629
epoch: 16 training_loss -1.8353362953662873 test_loss: -1.9257200241088868
epoch: 17 training_loss -1.9839488327503205 test_loss: -2.1002613067626954
epoch: 18 training_loss -2.154029837846756 test_loss: -2.256856346130371
epoch: 19 training_loss -2.2510708820819856 test_loss: -2.2507131576538084
epoch: 20 training_loss -2.3236493599414825 test_loss: -2.169548225402832
epoch: 21 training_loss -2.3623357892036436 test_loss: -2.3771732330322264
epoch: 22 training_loss -2.4616916382312777 test_loss: -2.5364328384399415
epoch: 23 training_loss -2.5111018192768095 test_loss: -2.6613903045654297
epoch: 24 training_loss -2.6128648781776427 test_loss: -2.6522626876831055
epoch: 25 training_loss -2.646611586809158 test_loss: -2.6627685546875
epoch: 26 training_loss -2.699467217922211 test_loss: -2.8105979919433595
epoch: 27 training_loss -2.7444624388217926 test_loss: -2.864333724975586
epoch: 28 training_loss -2.8792414975166323 test_loss: -2.9221487045288086
epoch: 29 training_loss -2.972881555557251 test_loss: -3.146321487426758
epoch: 30 training_loss -2.96460832118988 test_loss: -2.99794921875
epoch: 31 training_loss -2.9984046626091003 test_loss: -3.1913366317749023
epoch: 32 training_loss -3.093496227264404 test_loss: -3.1360851287841798
epoch: 33 training_loss -3.189356367588043 test_loss: -3.1654300689697266
epoch: 34 training_loss -3.200633897781372 test_loss: -3.32955322265625
epoch: 35 training_loss -3.208267285823822 test_loss: -3.387051010131836
epoch: 36 training_loss -3.215744502544403 test_loss: -3.210527038574219
epoch: 37 training_loss -3.288086986541748 test_loss: -3.351068115234375
epoch: 38 training_loss -3.3885293292999266 test_loss: -3.3317138671875
epoch: 39 training_loss -3.3978129768371583 test_loss: -3.381357192993164
epoch: 40 training_loss -3.4541389870643617 test_loss: -3.42833251953125
epoch: 41 training_loss -3.4656660032272337 test_loss: -3.4128448486328127
epoch: 42 training_loss -3.5222335290908813 test_loss: -3.5444362640380858
epoch: 43 training_loss -3.555797574520111 test_loss: -3.5207870483398436
epoch: 44 training_loss -3.5118502378463745 test_loss: -3.590849685668945
epoch: 45 training_loss -3.579678077697754 test_loss: -3.624667739868164
epoch: 46 training_loss -3.6052489066123963 test_loss: -3.4153278350830076
epoch: 47 training_loss -3.648568346500397 test_loss: -3.7462406158447266
epoch: 48 training_loss -3.7299807715415954 test_loss: -3.855305862426758
epoch: 49 training_loss -3.681748263835907 test_loss: -3.6089237213134764
epoch: 50 training_loss -3.792143635749817 test_loss: -3.788692092895508
epoch: 51 training_loss -3.8285516023635866 test_loss: -3.8466602325439454
epoch: 52 training_loss -3.8234939408302306 test_loss: -3.7270652770996096
epoch: 53 training_loss -3.858945195674896 test_loss: -3.8563163757324217
epoch: 54 training_loss -3.8622081208229067 test_loss: -3.921477508544922
epoch: 55 training_loss -3.945118978023529 test_loss: -4.013123321533203
epoch: 56 training_loss -3.939829497337341 test_loss: -4.035617828369141
epoch: 57 training_loss -3.9404408931732178 test_loss: -4.076748657226562
epoch: 58 training_loss -4.007985243797302 test_loss: -4.037743377685547
epoch: 59 training_loss -4.053831946849823 test_loss: -3.9778881072998047
epoch: 60 training_loss -3.900825009346008 test_loss: -4.085860061645508
epoch: 61 training_loss -4.024609041213989 test_loss: -4.026660919189453
epoch: 62 training_loss -4.051944406032562 test_loss: -4.102235412597656
epoch: 63 training_loss -4.089726173877716 test_loss: -4.198220825195312
epoch: 64 training_loss -4.123831844329834 test_loss: -4.220176315307617
epoch: 65 training_loss -4.139223201274872 test_loss: -4.118879318237305
epoch: 66 training_loss -4.183506605625152 test_loss: -4.193988418579101
epoch: 67 training_loss -4.272239007949829 test_loss: -4.313518142700195
epoch: 68 training_loss -4.234609134197235 test_loss: -4.190410995483399
epoch: 69 training_loss -4.255394406318665 test_loss: -4.266673278808594
epoch: 70 training_loss -4.225876410007476 test_loss: -4.226285171508789
epoch: 71 training_loss -4.225038733482361 test_loss: -4.256048202514648
epoch: 72 training_loss -4.302548761367798 test_loss: -4.3476402282714846
epoch: 73 training_loss -4.295370275974274 test_loss: -4.300461196899414
epoch: 74 training_loss -4.263772304058075 test_loss: -4.332454681396484
epoch: 75 training_loss -4.356587390899659 test_loss: -4.349191665649414
epoch: 76 training_loss -4.378114650249481 test_loss: -4.3923828125
epoch: 77 training_loss -4.357462701797485 test_loss: -4.495437240600586
epoch: 78 training_loss -4.371146969795227 test_loss: -4.354523468017578
epoch: 79 training_loss -4.416969902515412 test_loss: -4.465920639038086
epoch: 80 training_loss -4.4322398352622985 test_loss: -4.504339981079101
epoch: 81 training_loss -4.433688046932221 test_loss: -4.365912628173828
epoch: 82 training_loss -4.2489202165603634 test_loss: -3.9469635009765627
epoch: 83 training_loss -4.4741973781585695 test_loss: -4.55773811340332
epoch: 84 training_loss -4.496399326324463 test_loss: -4.5141654968261715
epoch: 85 training_loss -4.545864405632019 test_loss: -4.605440902709961
epoch: 86 training_loss -4.622937068939209 test_loss: -4.669991302490234
epoch: 87 training_loss -4.570602171421051 test_loss: -4.550436401367188
epoch: 88 training_loss -4.507620825767517 test_loss: -4.517570495605469
epoch: 89 training_loss -4.640747754573822 test_loss: -4.637147521972656
epoch: 90 training_loss -4.609347712993622 test_loss: -4.730845260620117
epoch: 91 training_loss -4.67807059764862 test_loss: -4.71697883605957
epoch: 92 training_loss -4.718015217781067 test_loss: -4.534766769409179
epoch: 93 training_loss -4.5880640029907225 test_loss: -4.827629852294922
epoch: 94 training_loss -4.816402113437652 test_loss: -4.7816917419433596
epoch: 95 training_loss -4.708600125312805 test_loss: -4.71683349609375
epoch: 96 training_loss -4.785344514846802 test_loss: -4.865643310546875
epoch: 97 training_loss -4.805153861045837 test_loss: -4.7287742614746096
epoch: 98 training_loss -4.806607666015625 test_loss: -4.770964813232422
epoch: 99 training_loss -4.833747653961182 test_loss: -4.850233840942383
epoch: 100 training_loss -4.759232106208802 test_loss: -4.902507400512695
epoch: 101 training_loss -4.91882776260376 test_loss: -4.915911865234375
epoch: 102 training_loss -4.9205911922454835 test_loss: -4.926595687866211
epoch: 103 training_loss -4.873543217182159 test_loss: -4.848913192749023
epoch: 104 training_loss -4.932755513191223 test_loss: -4.824383926391602
epoch: 105 training_loss -4.900171251296997 test_loss: -4.575827026367188
epoch: 106 training_loss -4.826932830810547 test_loss: -4.889822387695313
epoch: 107 training_loss -5.0273237228393555 test_loss: -4.984896087646485
epoch: 108 training_loss -4.978712701797486 test_loss: -5.055500030517578
epoch: 109 training_loss -4.974857850074768 test_loss: -4.860134124755859
epoch: 110 training_loss -5.07464521408081 test_loss: -5.07257080078125
epoch: 111 training_loss -5.066559481620788 test_loss: -4.964474487304687
epoch: 112 training_loss -5.048794627189636 test_loss: -5.035152816772461
epoch: 113 training_loss -5.0756880474090575 test_loss: -5.132183837890625
epoch: 114 training_loss -5.094875631332397 test_loss: -4.921478271484375
epoch: 115 training_loss -5.136298637390137 test_loss: -5.040123367309571
epoch: 116 training_loss -5.111412019729614 test_loss: -5.170981979370117
epoch: 117 training_loss -5.1281268644332885 test_loss: -5.175935363769531
epoch: 118 training_loss -5.15352246761322 test_loss: -5.007955932617188
epoch: 119 training_loss -5.116760792732239 test_loss: -5.127419662475586
epoch: 120 training_loss -5.152418808937073 test_loss: -5.08259391784668
epoch: 121 training_loss -5.1786871957778935 test_loss: -5.07864990234375
epoch: 122 training_loss -5.216280236244201 test_loss: -5.1982990264892575
epoch: 123 training_loss -5.224509420394898 test_loss: -5.197140121459961
epoch: 124 training_loss -5.2561680126190184 test_loss: -5.221908187866211
epoch: 125 training_loss -5.214742245674134 test_loss: -5.321561050415039
epoch: 126 training_loss -5.249467463493347 test_loss: -5.2073417663574215
epoch: 127 training_loss -5.288525404930115 test_loss: -5.281575012207031
epoch: 128 training_loss -5.276276125907898 test_loss: -5.300341415405273
epoch: 129 training_loss -5.293636207580566 test_loss: -5.25952033996582
epoch: 130 training_loss -5.23999930858612 test_loss: -5.214046859741211
epoch: 131 training_loss -5.279889965057373 test_loss: -5.180093002319336
epoch: 132 training_loss -5.348352708816528 test_loss: -5.47002944946289
epoch: 133 training_loss -5.37829773902893 test_loss: -5.35197639465332
epoch: 134 training_loss -5.397027611732483 test_loss: -5.409200668334961
epoch: 135 training_loss -5.374215054512024 test_loss: -5.197638320922851
epoch: 136 training_loss -5.275376234054566 test_loss: -5.313162612915039
epoch: 137 training_loss -5.373740601539612 test_loss: -5.348067855834961
epoch: 138 training_loss -5.413826675415039 test_loss: -5.237164306640625
epoch: 139 training_loss -5.269625296592713 test_loss: -5.277202224731445
epoch: 140 training_loss -5.258731865882874 test_loss: -5.376572799682617
epoch: 141 training_loss -5.445233588218689 test_loss: -5.424927139282227
epoch: 142 training_loss -5.438527898788452 test_loss: -5.420999908447266
epoch: 143 training_loss -5.423906087875366 test_loss: -5.414022827148438
epoch: 144 training_loss -5.391617975234985 test_loss: -5.429441452026367
epoch: 145 training_loss -5.2345565009117125 test_loss: -5.423625946044922
epoch: 146 training_loss -5.4726641607284545 test_loss: -5.428780364990234
epoch: 147 training_loss -5.43377338886261 test_loss: -5.435393142700195
epoch: 148 training_loss -5.488457684516907 test_loss: -5.453400039672852
epoch: 149 training_loss -5.512704758644104 test_loss: -5.3968048095703125
36.61757398707765
episode: 0 training return: tensor(-496201.5000, device='cuda:0')
episode: 1 training return: tensor(-137574.5312, device='cuda:0')
episode: 2 training return: tensor(-283544.1875, device='cuda:0')
episode: 3 training return: tensor(-3827422., device='cuda:0')
epoch: 1 test_true_pfm: -23.419563358830676
episode: 4 training return: tensor(-354385.2812, device='cuda:0')
episode: 5 training return: tensor(-135147.3750, device='cuda:0')
episode: 6 training return: tensor(-1757834.7500, device='cuda:0')
episode: 7 training return: tensor(-131380., device='cuda:0')
epoch: 2 test_true_pfm: -19.982782491637913
episode: 8 training return: tensor(-6177341.5000, device='cuda:0')
episode: 9 training return: tensor(-1908431.1250, device='cuda:0')
episode: 10 training return: tensor(-1962127.3750, device='cuda:0')
episode: 11 training return: tensor(-921249.6250, device='cuda:0')
epoch: 3 test_true_pfm: -15.330903915687221
episode: 12 training return: tensor(-398684.3750, device='cuda:0')
episode: 13 training return: tensor(-1162034.7500, device='cuda:0')
episode: 14 training return: tensor(-3773.0723, device='cuda:0')
episode: 15 training return: tensor(-86786.5859, device='cuda:0')
epoch: 4 test_true_pfm: -12.874147349364737
episode: 16 training return: tensor(-46501.1328, device='cuda:0')
episode: 17 training return: tensor(-749.5295, device='cuda:0')
episode: 18 training return: tensor(-3093.2224, device='cuda:0')
episode: 19 training return: tensor(-13828.4453, device='cuda:0')
epoch: 5 test_true_pfm: -23.196867691774237
episode: 20 training return: tensor(-335223.2188, device='cuda:0')
episode: 21 training return: tensor(-797.4780, device='cuda:0')
episode: 22 training return: tensor(-1.1034e+13, device='cuda:0')
episode: 23 training return: tensor(-51701.4062, device='cuda:0')
epoch: 6 test_true_pfm: -16.77479744144991
episode: 24 training return: tensor(-3055.5361, device='cuda:0')
episode: 25 training return: tensor(-11675.7227, device='cuda:0')
episode: 26 training return: tensor(-8254., device='cuda:0')
episode: 27 training return: tensor(-8810.9834, device='cuda:0')
epoch: 7 test_true_pfm: -20.69657847788936
episode: 28 training return: tensor(-421935.6875, device='cuda:0')
episode: 29 training return: tensor(-10538.4023, device='cuda:0')
episode: 30 training return: tensor(-29167.5215, device='cuda:0')
episode: 31 training return: tensor(-18566.6992, device='cuda:0')
epoch: 8 test_true_pfm: -19.609363090815073
episode: 32 training return: tensor(-4244.0054, device='cuda:0')
episode: 33 training return: tensor(-20796860., device='cuda:0')
episode: 34 training return: tensor(-7461487.5000, device='cuda:0')
episode: 35 training return: tensor(-5651.9863, device='cuda:0')
epoch: 9 test_true_pfm: -20.456793780946192
episode: 36 training return: tensor(-7822.1060, device='cuda:0')
episode: 37 training return: tensor(-5664277., device='cuda:0')
episode: 38 training return: tensor(-3961068., device='cuda:0')
episode: 39 training return: tensor(-190213.8906, device='cuda:0')
epoch: 10 test_true_pfm: -18.667399355507147
episode: 40 training return: tensor(-9049.3438, device='cuda:0')
episode: 41 training return: tensor(-8436.7188, device='cuda:0')
episode: 42 training return: tensor(-4611.9893, device='cuda:0')
episode: 43 training return: tensor(-8136.7422, device='cuda:0')
epoch: 11 test_true_pfm: -17.455612995621177
episode: 44 training return: tensor(-9791.1162, device='cuda:0')
episode: 45 training return: tensor(-2291.4170, device='cuda:0')
episode: 46 training return: tensor(-106776.0312, device='cuda:0')
episode: 47 training return: tensor(-3131.2432, device='cuda:0')
epoch: 12 test_true_pfm: -19.836015147773054
episode: 48 training return: tensor(-2496.7578, device='cuda:0')
episode: 49 training return: tensor(-215098.4375, device='cuda:0')
episode: 50 training return: tensor(-5788.7021, device='cuda:0')
episode: 51 training return: tensor(-197871.0938, device='cuda:0')
epoch: 13 test_true_pfm: -28.154208006079443
episode: 52 training return: tensor(-6.0244e+08, device='cuda:0')
episode: 53 training return: tensor(-84347840., device='cuda:0')
episode: 54 training return: tensor(-1.0426e+08, device='cuda:0')
episode: 55 training return: tensor(-1.1521e+08, device='cuda:0')
epoch: 14 test_true_pfm: -25.891381418881444
episode: 56 training return: tensor(-85987120., device='cuda:0')
episode: 57 training return: tensor(-28621006., device='cuda:0')
episode: 58 training return: tensor(-70467504., device='cuda:0')
episode: 59 training return: tensor(-57338560., device='cuda:0')
epoch: 15 test_true_pfm: -24.98848139659709
episode: 60 training return: tensor(-95904328., device='cuda:0')
episode: 61 training return: tensor(-65808672., device='cuda:0')
episode: 62 training return: tensor(-79228648., device='cuda:0')
episode: 63 training return: tensor(-20218376., device='cuda:0')
epoch: 16 test_true_pfm: -13.756614332142366
episode: 64 training return: tensor(-5.2705e+15, device='cuda:0')
episode: 65 training return: tensor(-1.2007e+16, device='cuda:0')
episode: 66 training return: tensor(-99829336., device='cuda:0')
episode: 67 training return: tensor(-1.6857e+16, device='cuda:0')
epoch: 17 test_true_pfm: -14.936742595419275
episode: 68 training return: tensor(-22776498., device='cuda:0')
episode: 69 training return: tensor(-26928708., device='cuda:0')
episode: 70 training return: tensor(-690660.8750, device='cuda:0')
episode: 71 training return: tensor(-914548.1875, device='cuda:0')
epoch: 18 test_true_pfm: -18.37075982414378
episode: 72 training return: tensor(-773932.8750, device='cuda:0')
episode: 73 training return: tensor(-962682., device='cuda:0')
episode: 74 training return: tensor(-760094.5625, device='cuda:0')
episode: 75 training return: tensor(-1240209.8750, device='cuda:0')
epoch: 19 test_true_pfm: -20.392040112186056
episode: 76 training return: tensor(-1132723., device='cuda:0')
episode: 77 training return: tensor(-2099223.2500, device='cuda:0')
episode: 78 training return: tensor(-1164020.7500, device='cuda:0')
episode: 79 training return: tensor(-902021.6875, device='cuda:0')
epoch: 20 test_true_pfm: -19.273692779095423
episode: 80 training return: tensor(-741874.8750, device='cuda:0')
episode: 81 training return: tensor(-1408480.8750, device='cuda:0')
episode: 82 training return: tensor(-653863.1250, device='cuda:0')
episode: 83 training return: tensor(-1264959.8750, device='cuda:0')
epoch: 21 test_true_pfm: -18.50577181310172
episode: 84 training return: tensor(-1078020.7500, device='cuda:0')
episode: 85 training return: tensor(-1287271.6250, device='cuda:0')
episode: 86 training return: tensor(-856093.6250, device='cuda:0')
episode: 87 training return: tensor(-1273634.2500, device='cuda:0')
epoch: 22 test_true_pfm: -20.437410370949003
episode: 88 training return: tensor(-5759863.5000, device='cuda:0')
episode: 89 training return: tensor(-1201388.3750, device='cuda:0')
episode: 90 training return: tensor(-965051.6875, device='cuda:0')
episode: 91 training return: tensor(-1213508.2500, device='cuda:0')
epoch: 23 test_true_pfm: -17.71507189977691
episode: 92 training return: tensor(-907669.3750, device='cuda:0')
episode: 93 training return: tensor(-830790.6875, device='cuda:0')
episode: 94 training return: tensor(-1132231.1250, device='cuda:0')
episode: 95 training return: tensor(-1474023., device='cuda:0')
epoch: 24 test_true_pfm: -19.518203265480402
episode: 96 training return: tensor(-901606.0625, device='cuda:0')
episode: 97 training return: tensor(-873335.2500, device='cuda:0')
episode: 98 training return: tensor(-859849.5625, device='cuda:0')
episode: 99 training return: tensor(-4329885., device='cuda:0')
epoch: 25 test_true_pfm: -18.68522559833977
episode: 100 training return: tensor(-695845.8125, device='cuda:0')
episode: 101 training return: tensor(-1149546., device='cuda:0')
episode: 102 training return: tensor(-1520786.2500, device='cuda:0')
episode: 103 training return: tensor(-917717.1875, device='cuda:0')
epoch: 26 test_true_pfm: -19.098854205090863
episode: 104 training return: tensor(-934477.4375, device='cuda:0')
episode: 105 training return: tensor(-918488.4375, device='cuda:0')
episode: 106 training return: tensor(-989971.6875, device='cuda:0')
episode: 107 training return: tensor(-973019.4375, device='cuda:0')
epoch: 27 test_true_pfm: -16.98327544213382
episode: 108 training return: tensor(-824802.6250, device='cuda:0')
episode: 109 training return: tensor(-1044692.1250, device='cuda:0')
episode: 110 training return: tensor(-904237.8125, device='cuda:0')
episode: 111 training return: tensor(-1008649.5000, device='cuda:0')
epoch: 28 test_true_pfm: -16.751378617523013
episode: 112 training return: tensor(-1025705.4375, device='cuda:0')
episode: 113 training return: tensor(-1112585.6250, device='cuda:0')
episode: 114 training return: tensor(-886104.2500, device='cuda:0')
episode: 115 training return: tensor(-854019.9375, device='cuda:0')
epoch: 29 test_true_pfm: -20.565847999697667
episode: 116 training return: tensor(-2071586.2500, device='cuda:0')
episode: 117 training return: tensor(-1182721.1250, device='cuda:0')
episode: 118 training return: tensor(-712297.8750, device='cuda:0')
episode: 119 training return: tensor(-1212275.6250, device='cuda:0')
epoch: 30 test_true_pfm: -16.524889456146067
episode: 120 training return: tensor(-810354.5000, device='cuda:0')
episode: 121 training return: tensor(-1067726.1250, device='cuda:0')
episode: 122 training return: tensor(-1048328.6875, device='cuda:0')
episode: 123 training return: tensor(-2144046.2500, device='cuda:0')
epoch: 31 test_true_pfm: -17.54674780095301
episode: 124 training return: tensor(-1029534.1250, device='cuda:0')
episode: 125 training return: tensor(-950497., device='cuda:0')
episode: 126 training return: tensor(-799725.3750, device='cuda:0')
episode: 127 training return: tensor(-975669.3125, device='cuda:0')
epoch: 32 test_true_pfm: -20.10493134322781
episode: 128 training return: tensor(-869966.5625, device='cuda:0')
episode: 129 training return: tensor(-1183493.3750, device='cuda:0')
episode: 130 training return: tensor(-681455.7500, device='cuda:0')
episode: 131 training return: tensor(-2203184., device='cuda:0')
epoch: 33 test_true_pfm: -16.83449227940661
episode: 132 training return: tensor(-1092813.7500, device='cuda:0')
episode: 133 training return: tensor(-2327484.7500, device='cuda:0')
episode: 134 training return: tensor(-669274.8750, device='cuda:0')
episode: 135 training return: tensor(-1434875., device='cuda:0')
epoch: 34 test_true_pfm: -17.07799924201509
episode: 136 training return: tensor(-984803.1250, device='cuda:0')
episode: 137 training return: tensor(-842332.0625, device='cuda:0')
episode: 138 training return: tensor(-760144.3125, device='cuda:0')
episode: 139 training return: tensor(-825596.8750, device='cuda:0')
epoch: 35 test_true_pfm: -18.935887785795693
episode: 140 training return: tensor(-955234.5625, device='cuda:0')
episode: 141 training return: tensor(-1528930.6250, device='cuda:0')
episode: 142 training return: tensor(-854133.5000, device='cuda:0')
episode: 143 training return: tensor(-1357604.3750, device='cuda:0')
epoch: 36 test_true_pfm: -22.831947981443165
episode: 144 training return: tensor(-691690.4375, device='cuda:0')
episode: 145 training return: tensor(-709309.7500, device='cuda:0')
episode: 146 training return: tensor(-1292491.5000, device='cuda:0')
episode: 147 training return: tensor(-5892772.5000, device='cuda:0')
epoch: 37 test_true_pfm: -18.21699522197562
episode: 148 training return: tensor(-1138992.5000, device='cuda:0')
episode: 149 training return: tensor(-753220.1875, device='cuda:0')
episode: 150 training return: tensor(-1000098.5000, device='cuda:0')
episode: 151 training return: tensor(-776489.1875, device='cuda:0')
epoch: 38 test_true_pfm: -17.091078604834184
episode: 152 training return: tensor(-668317.5625, device='cuda:0')
episode: 153 training return: tensor(-1700929.7500, device='cuda:0')
episode: 154 training return: tensor(-1165500.6250, device='cuda:0')
episode: 155 training return: tensor(-1173794.5000, device='cuda:0')
epoch: 39 test_true_pfm: -20.936281304036225
episode: 156 training return: tensor(-5338947., device='cuda:0')
episode: 157 training return: tensor(-803944.5000, device='cuda:0')
episode: 158 training return: tensor(-689274.1875, device='cuda:0')
episode: 159 training return: tensor(-917545.3750, device='cuda:0')
epoch: 40 test_true_pfm: -20.39974084626874
episode: 160 training return: tensor(-1124264.7500, device='cuda:0')
episode: 161 training return: tensor(-1404700.5000, device='cuda:0')
episode: 162 training return: tensor(-800791.5625, device='cuda:0')
episode: 163 training return: tensor(-1271666.5000, device='cuda:0')
epoch: 41 test_true_pfm: -22.703404770339716
episode: 164 training return: tensor(-3904713.5000, device='cuda:0')
episode: 165 training return: tensor(-1044524.3125, device='cuda:0')
episode: 166 training return: tensor(-1020919.8750, device='cuda:0')
episode: 167 training return: tensor(-921956.8125, device='cuda:0')
epoch: 42 test_true_pfm: -17.507854781854157
episode: 168 training return: tensor(-901711.8750, device='cuda:0')
episode: 169 training return: tensor(-766574.7500, device='cuda:0')
episode: 170 training return: tensor(-986090.6250, device='cuda:0')
episode: 171 training return: tensor(-861141.2500, device='cuda:0')
epoch: 43 test_true_pfm: -19.84589200829007
episode: 172 training return: tensor(-827992.6875, device='cuda:0')
episode: 173 training return: tensor(-5256968., device='cuda:0')
episode: 174 training return: tensor(-1037238.7500, device='cuda:0')
episode: 175 training return: tensor(-995033., device='cuda:0')
epoch: 44 test_true_pfm: -17.413799645181918
episode: 176 training return: tensor(-1019906.1250, device='cuda:0')
episode: 177 training return: tensor(-973720.8750, device='cuda:0')
episode: 178 training return: tensor(-772999.3750, device='cuda:0')
episode: 179 training return: tensor(-7584886.5000, device='cuda:0')
epoch: 45 test_true_pfm: -17.7586251653803
episode: 180 training return: tensor(-1099043., device='cuda:0')
episode: 181 training return: tensor(-1917460.8750, device='cuda:0')
episode: 182 training return: tensor(-753895.3125, device='cuda:0')
episode: 183 training return: tensor(-926747.6875, device='cuda:0')
epoch: 46 test_true_pfm: -18.619124834605792
episode: 184 training return: tensor(-953660.5625, device='cuda:0')
episode: 185 training return: tensor(-942228.7500, device='cuda:0')
episode: 186 training return: tensor(-1482587.7500, device='cuda:0')
episode: 187 training return: tensor(-2741735., device='cuda:0')
epoch: 47 test_true_pfm: -21.541416973951094
episode: 188 training return: tensor(-845709.2500, device='cuda:0')
episode: 189 training return: tensor(-1316065.7500, device='cuda:0')
episode: 190 training return: tensor(-1604872.7500, device='cuda:0')
episode: 191 training return: tensor(-1168510., device='cuda:0')
epoch: 48 test_true_pfm: -22.01994220193425
episode: 192 training return: tensor(-886408.8750, device='cuda:0')
episode: 193 training return: tensor(-3171352.5000, device='cuda:0')
episode: 194 training return: tensor(-849743.5625, device='cuda:0')
episode: 195 training return: tensor(-1064209.7500, device='cuda:0')
epoch: 49 test_true_pfm: -19.583481090434862
episode: 196 training return: tensor(-983697.8125, device='cuda:0')
episode: 197 training return: tensor(-722034.2500, device='cuda:0')
episode: 198 training return: tensor(-915114.8125, device='cuda:0')
episode: 199 training return: tensor(-747559.0625, device='cuda:0')
epoch: 50 test_true_pfm: -21.909456991730774
episode: 200 training return: tensor(-940229.8750, device='cuda:0')
episode: 201 training return: tensor(-6070755., device='cuda:0')
episode: 202 training return: tensor(-768294.3125, device='cuda:0')
episode: 203 training return: tensor(-44545004., device='cuda:0')
epoch: 51 test_true_pfm: -21.410816181796136
episode: 204 training return: tensor(-3221152.2500, device='cuda:0')
episode: 205 training return: tensor(-69406440., device='cuda:0')
episode: 206 training return: tensor(-8716796., device='cuda:0')
episode: 207 training return: tensor(-976270.8750, device='cuda:0')
epoch: 52 test_true_pfm: -20.29897754816485
episode: 208 training return: tensor(-882026.8750, device='cuda:0')
episode: 209 training return: tensor(-3374494.2500, device='cuda:0')
episode: 210 training return: tensor(-6007266., device='cuda:0')
episode: 211 training return: tensor(-14140717., device='cuda:0')
epoch: 53 test_true_pfm: -23.929640169702786
episode: 212 training return: tensor(-22944940., device='cuda:0')
episode: 213 training return: tensor(-4107300.5000, device='cuda:0')
episode: 214 training return: tensor(-1557944.2500, device='cuda:0')
episode: 215 training return: tensor(-2481376., device='cuda:0')
epoch: 54 test_true_pfm: -25.874599306969845
episode: 216 training return: tensor(-11033772., device='cuda:0')
episode: 217 training return: tensor(-14524943., device='cuda:0')
episode: 218 training return: tensor(-1406901.8750, device='cuda:0')
episode: 219 training return: tensor(-4347045., device='cuda:0')
epoch: 55 test_true_pfm: -21.00400684712476
episode: 220 training return: tensor(-1184586.3750, device='cuda:0')
episode: 221 training return: tensor(-5228154., device='cuda:0')
episode: 222 training return: tensor(-923346.6250, device='cuda:0')
episode: 223 training return: tensor(-2472000., device='cuda:0')
epoch: 56 test_true_pfm: -25.684889292279205
episode: 224 training return: tensor(-2194528.5000, device='cuda:0')
episode: 225 training return: tensor(-1076352.6250, device='cuda:0')
episode: 226 training return: tensor(-9882387., device='cuda:0')
episode: 227 training return: tensor(-1006386.8125, device='cuda:0')
epoch: 57 test_true_pfm: -24.397214167662106
episode: 228 training return: tensor(-995983.5625, device='cuda:0')
episode: 229 training return: tensor(-6982818., device='cuda:0')
episode: 230 training return: tensor(-1921627.1250, device='cuda:0')
episode: 231 training return: tensor(-2621816.2500, device='cuda:0')
epoch: 58 test_true_pfm: -24.36184955733931
episode: 232 training return: tensor(-1687226.6250, device='cuda:0')
episode: 233 training return: tensor(-1038367.2500, device='cuda:0')
episode: 234 training return: tensor(-1840982.3750, device='cuda:0')
episode: 235 training return: tensor(-2925186.7500, device='cuda:0')
epoch: 59 test_true_pfm: -25.965756214835444
episode: 236 training return: tensor(-1664701.5000, device='cuda:0')
episode: 237 training return: tensor(-2638644.7500, device='cuda:0')
episode: 238 training return: tensor(-1473322.8750, device='cuda:0')
episode: 239 training return: tensor(-1229333.8750, device='cuda:0')
epoch: 60 test_true_pfm: -25.95700293259564
episode: 240 training return: tensor(-1510919.8750, device='cuda:0')
episode: 241 training return: tensor(-1528638.6250, device='cuda:0')
episode: 242 training return: tensor(-2081394.8750, device='cuda:0')
episode: 243 training return: tensor(-1193233.2500, device='cuda:0')
epoch: 61 test_true_pfm: -26.708834215283012
episode: 244 training return: tensor(-2396433.7500, device='cuda:0')
episode: 245 training return: tensor(-1224640.7500, device='cuda:0')
episode: 246 training return: tensor(-1566700.7500, device='cuda:0')
episode: 247 training return: tensor(-1799687.8750, device='cuda:0')
epoch: 62 test_true_pfm: -23.23136454544463
episode: 248 training return: tensor(-951999.7500, device='cuda:0')
episode: 249 training return: tensor(-1638393.2500, device='cuda:0')
episode: 250 training return: tensor(-3608920.5000, device='cuda:0')
episode: 251 training return: tensor(-5537768.5000, device='cuda:0')
epoch: 63 test_true_pfm: -25.6222898383618
episode: 252 training return: tensor(-1667596.8750, device='cuda:0')
episode: 253 training return: tensor(-1380430.2500, device='cuda:0')
episode: 254 training return: tensor(-1038391.1875, device='cuda:0')
episode: 255 training return: tensor(-1310004.6250, device='cuda:0')
epoch: 64 test_true_pfm: -23.999386840124846
episode: 256 training return: tensor(-1218685., device='cuda:0')
episode: 257 training return: tensor(-1238135.2500, device='cuda:0')
episode: 258 training return: tensor(-1302152.7500, device='cuda:0')
episode: 259 training return: tensor(-5077421.5000, device='cuda:0')
epoch: 65 test_true_pfm: -23.119923799199746
episode: 260 training return: tensor(-1855277.3750, device='cuda:0')
episode: 261 training return: tensor(-1265187.3750, device='cuda:0')
episode: 262 training return: tensor(-1116075.1250, device='cuda:0')
episode: 263 training return: tensor(-977847.6250, device='cuda:0')
epoch: 66 test_true_pfm: -22.902066684931853
episode: 264 training return: tensor(-1018623.5000, device='cuda:0')
episode: 265 training return: tensor(-6686533., device='cuda:0')
episode: 266 training return: tensor(-1581530.7500, device='cuda:0')
episode: 267 training return: tensor(-1118129.7500, device='cuda:0')
epoch: 67 test_true_pfm: -25.47828147401049
episode: 268 training return: tensor(-1464364.1250, device='cuda:0')
episode: 269 training return: tensor(-1203881.3750, device='cuda:0')
episode: 270 training return: tensor(-927876.0625, device='cuda:0')
episode: 271 training return: tensor(-1405138.5000, device='cuda:0')
epoch: 68 test_true_pfm: -24.592646033686556
episode: 272 training return: tensor(-1240841., device='cuda:0')
episode: 273 training return: tensor(-1639002.7500, device='cuda:0')
episode: 274 training return: tensor(-1783908.6250, device='cuda:0')
episode: 275 training return: tensor(-1468542.7500, device='cuda:0')
epoch: 69 test_true_pfm: -26.423398361833883
episode: 276 training return: tensor(-1329760., device='cuda:0')
episode: 277 training return: tensor(-1109632., device='cuda:0')
episode: 278 training return: tensor(-2052003.1250, device='cuda:0')
episode: 279 training return: tensor(-1089663.1250, device='cuda:0')
epoch: 70 test_true_pfm: -26.928589739787064
episode: 280 training return: tensor(-3048789.2500, device='cuda:0')
episode: 281 training return: tensor(-3975157.5000, device='cuda:0')
episode: 282 training return: tensor(-7048093., device='cuda:0')
episode: 283 training return: tensor(-1314584.2500, device='cuda:0')
epoch: 71 test_true_pfm: -25.941368976742524
episode: 284 training return: tensor(-1571357.7500, device='cuda:0')
episode: 285 training return: tensor(-1174080.3750, device='cuda:0')
episode: 286 training return: tensor(-1240221.3750, device='cuda:0')
episode: 287 training return: tensor(-3171137., device='cuda:0')
epoch: 72 test_true_pfm: -23.690982168488354
episode: 288 training return: tensor(-1493864.3750, device='cuda:0')
episode: 289 training return: tensor(-1587645.2500, device='cuda:0')
episode: 290 training return: tensor(-1371880.5000, device='cuda:0')
episode: 291 training return: tensor(-938893.0625, device='cuda:0')
epoch: 73 test_true_pfm: -24.505964319608672
episode: 292 training return: tensor(-1542856.2500, device='cuda:0')
episode: 293 training return: tensor(-1056703.1250, device='cuda:0')
episode: 294 training return: tensor(-1532614.7500, device='cuda:0')
episode: 295 training return: tensor(-1476912.2500, device='cuda:0')
epoch: 74 test_true_pfm: -24.510938599121975
episode: 296 training return: tensor(-945219.6250, device='cuda:0')
episode: 297 training return: tensor(-1127661.8750, device='cuda:0')
episode: 298 training return: tensor(-1822607.3750, device='cuda:0')
episode: 299 training return: tensor(-5411444.5000, device='cuda:0')
epoch: 75 test_true_pfm: -23.915463807377048
episode: 300 training return: tensor(-1892986., device='cuda:0')
episode: 301 training return: tensor(-2164982.7500, device='cuda:0')
episode: 302 training return: tensor(-4788339., device='cuda:0')
episode: 303 training return: tensor(-2722304.2500, device='cuda:0')
epoch: 76 test_true_pfm: -21.34477365236542
episode: 304 training return: tensor(-1120893.6250, device='cuda:0')
episode: 305 training return: tensor(-788642.3125, device='cuda:0')
episode: 306 training return: tensor(-3745489., device='cuda:0')
episode: 307 training return: tensor(-3084431., device='cuda:0')
epoch: 77 test_true_pfm: -22.822098132276643
episode: 308 training return: tensor(-4191783.2500, device='cuda:0')
episode: 309 training return: tensor(-1085282.2500, device='cuda:0')
episode: 310 training return: tensor(-1016675.5625, device='cuda:0')
episode: 311 training return: tensor(-1413256.2500, device='cuda:0')
epoch: 78 test_true_pfm: -24.75254138628643
episode: 312 training return: tensor(-1074336.3750, device='cuda:0')
episode: 313 training return: tensor(-2382186., device='cuda:0')
episode: 314 training return: tensor(-2235832.7500, device='cuda:0')
episode: 315 training return: tensor(-1340313., device='cuda:0')
epoch: 79 test_true_pfm: -23.139012677828763
episode: 316 training return: tensor(-1602904.3750, device='cuda:0')
episode: 317 training return: tensor(-1401131.7500, device='cuda:0')
episode: 318 training return: tensor(-16374360., device='cuda:0')
episode: 319 training return: tensor(-14388718., device='cuda:0')
epoch: 80 test_true_pfm: -22.24082019359354
episode: 320 training return: tensor(-802981.1250, device='cuda:0')
episode: 321 training return: tensor(-1085794.7500, device='cuda:0')
episode: 322 training return: tensor(-3683993.2500, device='cuda:0')
episode: 323 training return: tensor(-4167868.5000, device='cuda:0')
epoch: 81 test_true_pfm: -20.032565203292407
episode: 324 training return: tensor(-5670735., device='cuda:0')
episode: 325 training return: tensor(-13063172., device='cuda:0')
episode: 326 training return: tensor(-53793968., device='cuda:0')
episode: 327 training return: tensor(-2336954.2500, device='cuda:0')
epoch: 82 test_true_pfm: -21.094637759068938
episode: 328 training return: tensor(-1074654.2500, device='cuda:0')
episode: 329 training return: tensor(-1086379.2500, device='cuda:0')
episode: 330 training return: tensor(-2735055.2500, device='cuda:0')
episode: 331 training return: tensor(-1644313.8750, device='cuda:0')
epoch: 83 test_true_pfm: -21.56214206762494
episode: 332 training return: tensor(-861965.6875, device='cuda:0')
episode: 333 training return: tensor(-35676028., device='cuda:0')
episode: 334 training return: tensor(-720539.1875, device='cuda:0')
episode: 335 training return: tensor(-982563.3125, device='cuda:0')
epoch: 84 test_true_pfm: -20.591683465298114
episode: 336 training return: tensor(-862954.1250, device='cuda:0')
episode: 337 training return: tensor(-1063061.2500, device='cuda:0')
episode: 338 training return: tensor(-1192580.5000, device='cuda:0')
episode: 339 training return: tensor(-1050311.5000, device='cuda:0')
epoch: 85 test_true_pfm: -17.70935690864274
episode: 340 training return: tensor(-799636.3125, device='cuda:0')
episode: 341 training return: tensor(-857608.9375, device='cuda:0')
episode: 342 training return: tensor(-835610.1250, device='cuda:0')
episode: 343 training return: tensor(-1500131.2500, device='cuda:0')
epoch: 86 test_true_pfm: -20.823241138961045
episode: 344 training return: tensor(-1326470.2500, device='cuda:0')
episode: 345 training return: tensor(-675507.2500, device='cuda:0')
episode: 346 training return: tensor(-1183895.1250, device='cuda:0')
episode: 347 training return: tensor(-7486424., device='cuda:0')
epoch: 87 test_true_pfm: -20.490249905288916
episode: 348 training return: tensor(-838284.8750, device='cuda:0')
episode: 349 training return: tensor(-3306985.2500, device='cuda:0')
episode: 350 training return: tensor(-1913287.7500, device='cuda:0')
episode: 351 training return: tensor(-1155897.7500, device='cuda:0')
epoch: 88 test_true_pfm: -19.66579511256823
episode: 352 training return: tensor(-976726.1250, device='cuda:0')
episode: 353 training return: tensor(-1132752.1250, device='cuda:0')
episode: 354 training return: tensor(-733559.6250, device='cuda:0')
episode: 355 training return: tensor(-1482423.3750, device='cuda:0')
epoch: 89 test_true_pfm: -20.350897511806703
episode: 356 training return: tensor(-887458., device='cuda:0')
episode: 357 training return: tensor(-968027.2500, device='cuda:0')
episode: 358 training return: tensor(-1160523.5000, device='cuda:0')
episode: 359 training return: tensor(-1097597., device='cuda:0')
epoch: 90 test_true_pfm: -15.891249114656148
episode: 360 training return: tensor(-947523., device='cuda:0')
episode: 361 training return: tensor(-966377.4375, device='cuda:0')
episode: 362 training return: tensor(-855797.2500, device='cuda:0')
episode: 363 training return: tensor(-703369.9375, device='cuda:0')
epoch: 91 test_true_pfm: -17.773807243935547
episode: 364 training return: tensor(-853046.2500, device='cuda:0')
episode: 365 training return: tensor(-913249.3125, device='cuda:0')
episode: 366 training return: tensor(-1039715.9375, device='cuda:0')
episode: 367 training return: tensor(-974589.3125, device='cuda:0')
epoch: 92 test_true_pfm: -22.638097274351487
episode: 368 training return: tensor(-958224.1250, device='cuda:0')
episode: 369 training return: tensor(-972185.6875, device='cuda:0')
episode: 370 training return: tensor(-11337759., device='cuda:0')
episode: 371 training return: tensor(-768745.9375, device='cuda:0')
epoch: 93 test_true_pfm: -16.5010719703767
episode: 372 training return: tensor(-864424.8750, device='cuda:0')
episode: 373 training return: tensor(-858932.2500, device='cuda:0')
episode: 374 training return: tensor(-905773.5625, device='cuda:0')
episode: 375 training return: tensor(-2082409.1250, device='cuda:0')
epoch: 94 test_true_pfm: -22.509113310894115
episode: 376 training return: tensor(-911757.2500, device='cuda:0')
episode: 377 training return: tensor(-946582.8750, device='cuda:0')
episode: 378 training return: tensor(-774926.6250, device='cuda:0')
episode: 379 training return: tensor(-839840.0625, device='cuda:0')
epoch: 95 test_true_pfm: -22.670706568500105
episode: 380 training return: tensor(-964480.1250, device='cuda:0')
episode: 381 training return: tensor(-675856.9375, device='cuda:0')
episode: 382 training return: tensor(-742013.8125, device='cuda:0')
episode: 383 training return: tensor(-896538.0625, device='cuda:0')
epoch: 96 test_true_pfm: -20.328123258929374
episode: 384 training return: tensor(-2218116., device='cuda:0')
episode: 385 training return: tensor(-1188777.8750, device='cuda:0')
episode: 386 training return: tensor(-1495583.3750, device='cuda:0')
episode: 387 training return: tensor(-1505507.3750, device='cuda:0')
epoch: 97 test_true_pfm: -20.151703668375838
episode: 388 training return: tensor(-779807.6875, device='cuda:0')
episode: 389 training return: tensor(-1988368.3750, device='cuda:0')
episode: 390 training return: tensor(-977451., device='cuda:0')
episode: 391 training return: tensor(-1225112.6250, device='cuda:0')
epoch: 98 test_true_pfm: -17.778808743621035
episode: 392 training return: tensor(-755164.3125, device='cuda:0')
episode: 393 training return: tensor(-707084.6250, device='cuda:0')
episode: 394 training return: tensor(-797101.3125, device='cuda:0')
episode: 395 training return: tensor(-942537.8125, device='cuda:0')
epoch: 99 test_true_pfm: -20.464965285508526
episode: 396 training return: tensor(-912604.9375, device='cuda:0')
episode: 397 training return: tensor(-758543., device='cuda:0')
episode: 398 training return: tensor(-1072798.3750, device='cuda:0')
episode: 399 training return: tensor(-1297185.6250, device='cuda:0')
epoch: 100 test_true_pfm: -22.068579458678737
episode: 400 training return: tensor(-740672.4375, device='cuda:0')
episode: 401 training return: tensor(-941406.0625, device='cuda:0')
episode: 402 training return: tensor(-1091080.6250, device='cuda:0')
episode: 403 training return: tensor(-842586.8125, device='cuda:0')
epoch: 101 test_true_pfm: -21.298030793440187
episode: 404 training return: tensor(-725747.2500, device='cuda:0')
episode: 405 training return: tensor(-28550644., device='cuda:0')
episode: 406 training return: tensor(-810856.7500, device='cuda:0')
episode: 407 training return: tensor(-882054.6250, device='cuda:0')
epoch: 102 test_true_pfm: -21.571427354198043
episode: 408 training return: tensor(-6765202.5000, device='cuda:0')
episode: 409 training return: tensor(-1187346.6250, device='cuda:0')
episode: 410 training return: tensor(-911433.1250, device='cuda:0')
episode: 411 training return: tensor(-1064328., device='cuda:0')
epoch: 103 test_true_pfm: -19.952647878241418
episode: 412 training return: tensor(-874395.1250, device='cuda:0')
episode: 413 training return: tensor(-1062139.7500, device='cuda:0')
episode: 414 training return: tensor(-12413832., device='cuda:0')
episode: 415 training return: tensor(-768935.6250, device='cuda:0')
epoch: 104 test_true_pfm: -23.40946118544147
episode: 416 training return: tensor(-794849.1875, device='cuda:0')
episode: 417 training return: tensor(-783151.8750, device='cuda:0')
episode: 418 training return: tensor(-2555195.2500, device='cuda:0')
episode: 419 training return: tensor(-1030959.5625, device='cuda:0')
epoch: 105 test_true_pfm: -20.48130830816557
episode: 420 training return: tensor(-931147.8125, device='cuda:0')
episode: 421 training return: tensor(-1013745.7500, device='cuda:0')
episode: 422 training return: tensor(-52425156., device='cuda:0')
episode: 423 training return: tensor(-1031156.3750, device='cuda:0')
epoch: 106 test_true_pfm: -21.104878500706622
episode: 424 training return: tensor(-1423356.5000, device='cuda:0')
episode: 425 training return: tensor(-862181.7500, device='cuda:0')
episode: 426 training return: tensor(-794284.6250, device='cuda:0')
episode: 427 training return: tensor(-944829.1875, device='cuda:0')
epoch: 107 test_true_pfm: -16.89069633697326
episode: 428 training return: tensor(-1571125.2500, device='cuda:0')
episode: 429 training return: tensor(-2970120., device='cuda:0')
episode: 430 training return: tensor(-744821., device='cuda:0')
episode: 431 training return: tensor(-1088929.7500, device='cuda:0')
epoch: 108 test_true_pfm: -17.130622032032
episode: 432 training return: tensor(-1457371.2500, device='cuda:0')
episode: 433 training return: tensor(-739687.0625, device='cuda:0')
episode: 434 training return: tensor(-715373.3125, device='cuda:0')
episode: 435 training return: tensor(-1235176., device='cuda:0')
epoch: 109 test_true_pfm: -20.526515192110804
episode: 436 training return: tensor(-903042.3125, device='cuda:0')
episode: 437 training return: tensor(-1719644.7500, device='cuda:0')
episode: 438 training return: tensor(-1286753., device='cuda:0')
episode: 439 training return: tensor(-648735., device='cuda:0')
epoch: 110 test_true_pfm: -20.098281787441653
episode: 440 training return: tensor(-915583.8750, device='cuda:0')
episode: 441 training return: tensor(-912491.4375, device='cuda:0')
episode: 442 training return: tensor(-2153847.5000, device='cuda:0')
episode: 443 training return: tensor(-2012883.5000, device='cuda:0')
epoch: 111 test_true_pfm: -21.276453410591095
episode: 444 training return: tensor(-3745226., device='cuda:0')
episode: 445 training return: tensor(-761352., device='cuda:0')
episode: 446 training return: tensor(-988372.1875, device='cuda:0')
episode: 447 training return: tensor(-794408.3750, device='cuda:0')
epoch: 112 test_true_pfm: -19.12671802527611
episode: 448 training return: tensor(-827514.3750, device='cuda:0')
episode: 449 training return: tensor(-853120.1875, device='cuda:0')
episode: 450 training return: tensor(-753183.1875, device='cuda:0')
episode: 451 training return: tensor(-1345434.5000, device='cuda:0')
epoch: 113 test_true_pfm: -18.404238607906333
episode: 452 training return: tensor(-1299706., device='cuda:0')
episode: 453 training return: tensor(-884862.8750, device='cuda:0')
episode: 454 training return: tensor(-867438.9375, device='cuda:0')
episode: 455 training return: tensor(-10252770., device='cuda:0')
epoch: 114 test_true_pfm: -21.1999548321267
episode: 456 training return: tensor(-901951.2500, device='cuda:0')
episode: 457 training return: tensor(-770184.4375, device='cuda:0')
episode: 458 training return: tensor(-869247.2500, device='cuda:0')
episode: 459 training return: tensor(-17921464., device='cuda:0')
epoch: 115 test_true_pfm: -17.663249619859158
episode: 460 training return: tensor(-896795.8750, device='cuda:0')
episode: 461 training return: tensor(-1338136.7500, device='cuda:0')
episode: 462 training return: tensor(-760033.6250, device='cuda:0')
episode: 463 training return: tensor(-2072518.1250, device='cuda:0')
epoch: 116 test_true_pfm: -24.02555173524319
episode: 464 training return: tensor(-4736033., device='cuda:0')
episode: 465 training return: tensor(-1040879.3750, device='cuda:0')
episode: 466 training return: tensor(-1590609.5000, device='cuda:0')
episode: 467 training return: tensor(-5489896., device='cuda:0')
epoch: 117 test_true_pfm: -16.98407887731418
episode: 468 training return: tensor(-1316973.6250, device='cuda:0')
episode: 469 training return: tensor(-793258.5625, device='cuda:0')
episode: 470 training return: tensor(-834277.5625, device='cuda:0')
episode: 471 training return: tensor(-2612544.2500, device='cuda:0')
epoch: 118 test_true_pfm: -25.760447296114855
episode: 472 training return: tensor(-1777191.6250, device='cuda:0')
episode: 473 training return: tensor(-981342.5000, device='cuda:0')
episode: 474 training return: tensor(-923228.6250, device='cuda:0')
episode: 475 training return: tensor(-934833.7500, device='cuda:0')
epoch: 119 test_true_pfm: -21.21746983333154
episode: 476 training return: tensor(-861709.6250, device='cuda:0')
episode: 477 training return: tensor(-939194.5625, device='cuda:0')
episode: 478 training return: tensor(-1013468.1250, device='cuda:0')
episode: 479 training return: tensor(-918969.8750, device='cuda:0')
epoch: 120 test_true_pfm: -18.873631635358628
episode: 480 training return: tensor(-962532.4375, device='cuda:0')
episode: 481 training return: tensor(-953592.7500, device='cuda:0')
episode: 482 training return: tensor(-978130.5000, device='cuda:0')
episode: 483 training return: tensor(-932812.2500, device='cuda:0')
epoch: 121 test_true_pfm: -20.338649417054302
episode: 484 training return: tensor(-989354.1250, device='cuda:0')
episode: 485 training return: tensor(-1031952.6875, device='cuda:0')
episode: 486 training return: tensor(-940044.3750, device='cuda:0')
episode: 487 training return: tensor(-942936.5625, device='cuda:0')
epoch: 122 test_true_pfm: -19.11524589826543
episode: 488 training return: tensor(-897223.8125, device='cuda:0')
episode: 489 training return: tensor(-897381.0625, device='cuda:0')
episode: 490 training return: tensor(-905496.6250, device='cuda:0')
episode: 491 training return: tensor(-933113.1875, device='cuda:0')
epoch: 123 test_true_pfm: -19.01707121144987
episode: 492 training return: tensor(-960236.1875, device='cuda:0')
episode: 493 training return: tensor(-1009904.7500, device='cuda:0')
episode: 494 training return: tensor(-976202.9375, device='cuda:0')
episode: 495 training return: tensor(-972811.3750, device='cuda:0')
epoch: 124 test_true_pfm: -19.39775157591353
episode: 496 training return: tensor(-939428.8125, device='cuda:0')
episode: 497 training return: tensor(-932892.2500, device='cuda:0')
episode: 498 training return: tensor(-1030101.7500, device='cuda:0')
episode: 499 training return: tensor(-902340.0625, device='cuda:0')
epoch: 125 test_true_pfm: -18.824661448635172
episode: 500 training return: tensor(-1004938.3750, device='cuda:0')
episode: 501 training return: tensor(-941894.6250, device='cuda:0')
episode: 502 training return: tensor(-963647.5625, device='cuda:0')
episode: 503 training return: tensor(-1037351.4375, device='cuda:0')
epoch: 126 test_true_pfm: -18.774866419362887
episode: 504 training return: tensor(-965023.6875, device='cuda:0')
episode: 505 training return: tensor(-999187.1250, device='cuda:0')
episode: 506 training return: tensor(-856210.5000, device='cuda:0')
episode: 507 training return: tensor(-954880.5000, device='cuda:0')
epoch: 127 test_true_pfm: -18.531901072624326
episode: 508 training return: tensor(-929307.8125, device='cuda:0')
episode: 509 training return: tensor(-1078291.7500, device='cuda:0')
episode: 510 training return: tensor(-983426.4375, device='cuda:0')
episode: 511 training return: tensor(-1037725.1875, device='cuda:0')
epoch: 128 test_true_pfm: -20.813132726906595
episode: 512 training return: tensor(-932936.6875, device='cuda:0')
episode: 513 training return: tensor(-959143., device='cuda:0')
episode: 514 training return: tensor(-954465.7500, device='cuda:0')
episode: 515 training return: tensor(-905939.6250, device='cuda:0')
epoch: 129 test_true_pfm: -19.461689100894308
episode: 516 training return: tensor(-992835.8125, device='cuda:0')
episode: 517 training return: tensor(-994291.2500, device='cuda:0')
episode: 518 training return: tensor(-1149764.1250, device='cuda:0')
episode: 519 training return: tensor(-930103.6250, device='cuda:0')
epoch: 130 test_true_pfm: -18.28577776781491
episode: 520 training return: tensor(-1012940.3125, device='cuda:0')
episode: 521 training return: tensor(-916052.8750, device='cuda:0')
episode: 522 training return: tensor(-893266.6875, device='cuda:0')
episode: 523 training return: tensor(-975579.5000, device='cuda:0')
epoch: 131 test_true_pfm: -18.85278951755372
episode: 524 training return: tensor(-1044759.1875, device='cuda:0')
episode: 525 training return: tensor(-992897.6250, device='cuda:0')
episode: 526 training return: tensor(-1074792.8750, device='cuda:0')
episode: 527 training return: tensor(-960123.8750, device='cuda:0')
epoch: 132 test_true_pfm: -18.95020680937916
episode: 528 training return: tensor(-977029.0625, device='cuda:0')
episode: 529 training return: tensor(-1049966.2500, device='cuda:0')
episode: 530 training return: tensor(-985244.3125, device='cuda:0')
episode: 531 training return: tensor(-1052696.3750, device='cuda:0')
epoch: 133 test_true_pfm: -18.498308571092405
episode: 532 training return: tensor(-960110.7500, device='cuda:0')
episode: 533 training return: tensor(-977721.3750, device='cuda:0')
episode: 534 training return: tensor(-944862.4375, device='cuda:0')
episode: 535 training return: tensor(-904601.9375, device='cuda:0')
epoch: 134 test_true_pfm: -18.949907994692573
episode: 536 training return: tensor(-928692.8125, device='cuda:0')
episode: 537 training return: tensor(-968928.0625, device='cuda:0')
episode: 538 training return: tensor(-1036535.6250, device='cuda:0')
episode: 539 training return: tensor(-892815.7500, device='cuda:0')
epoch: 135 test_true_pfm: -18.847664599418277
episode: 540 training return: tensor(-897459.9375, device='cuda:0')
episode: 541 training return: tensor(-963543.9375, device='cuda:0')
episode: 542 training return: tensor(-890836.5625, device='cuda:0')
episode: 543 training return: tensor(-941774., device='cuda:0')
epoch: 136 test_true_pfm: -19.717559702181166
episode: 544 training return: tensor(-965530.0625, device='cuda:0')
episode: 545 training return: tensor(-876943.2500, device='cuda:0')
episode: 546 training return: tensor(-1003019.1875, device='cuda:0')
episode: 547 training return: tensor(-864915.4375, device='cuda:0')
epoch: 137 test_true_pfm: -18.868631412050263
episode: 548 training return: tensor(-1009185.8125, device='cuda:0')
episode: 549 training return: tensor(-981016.2500, device='cuda:0')
episode: 550 training return: tensor(-1052174.1250, device='cuda:0')
episode: 551 training return: tensor(-897857.3125, device='cuda:0')
epoch: 138 test_true_pfm: -18.11278348771715
episode: 552 training return: tensor(-916962.3750, device='cuda:0')
episode: 553 training return: tensor(-939087.5000, device='cuda:0')
episode: 554 training return: tensor(-872798.7500, device='cuda:0')
episode: 555 training return: tensor(-992169.6875, device='cuda:0')
epoch: 139 test_true_pfm: -19.142191696614425
episode: 556 training return: tensor(-836836.8750, device='cuda:0')
episode: 557 training return: tensor(-918489.0625, device='cuda:0')
episode: 558 training return: tensor(-932731.8750, device='cuda:0')
episode: 559 training return: tensor(-972088.5000, device='cuda:0')
epoch: 140 test_true_pfm: -20.099923272963302
episode: 560 training return: tensor(-1047334.2500, device='cuda:0')
episode: 561 training return: tensor(-978653.6250, device='cuda:0')
episode: 562 training return: tensor(-896842., device='cuda:0')
episode: 563 training return: tensor(-1053146.7500, device='cuda:0')
epoch: 141 test_true_pfm: -20.694461036622265
episode: 564 training return: tensor(-899478., device='cuda:0')
episode: 565 training return: tensor(-971485., device='cuda:0')
episode: 566 training return: tensor(-1142799., device='cuda:0')
episode: 567 training return: tensor(-1009800.7500, device='cuda:0')
epoch: 142 test_true_pfm: -19.654347768199834
episode: 568 training return: tensor(-988618.6250, device='cuda:0')
episode: 569 training return: tensor(-970080.8750, device='cuda:0')
episode: 570 training return: tensor(-1024288.0625, device='cuda:0')
episode: 571 training return: tensor(-778972.3125, device='cuda:0')
epoch: 143 test_true_pfm: -19.17151023936676
episode: 572 training return: tensor(-927627.5000, device='cuda:0')
episode: 573 training return: tensor(-899580.3750, device='cuda:0')
episode: 574 training return: tensor(-1000172.8125, device='cuda:0')
episode: 575 training return: tensor(-813487.4375, device='cuda:0')
epoch: 144 test_true_pfm: -18.787597331728723
episode: 576 training return: tensor(-939415.9375, device='cuda:0')
episode: 577 training return: tensor(-1067623., device='cuda:0')
episode: 578 training return: tensor(-907720.9375, device='cuda:0')
episode: 579 training return: tensor(-897723.6875, device='cuda:0')
epoch: 145 test_true_pfm: -19.97350478822783
episode: 580 training return: tensor(-842790.6250, device='cuda:0')
episode: 581 training return: tensor(-927004.1875, device='cuda:0')
episode: 582 training return: tensor(-981156.9375, device='cuda:0')
episode: 583 training return: tensor(-1024960.1250, device='cuda:0')
epoch: 146 test_true_pfm: -21.359817296211265
episode: 584 training return: tensor(-945994.0625, device='cuda:0')
episode: 585 training return: tensor(-970663.7500, device='cuda:0')
episode: 586 training return: tensor(-850124.3125, device='cuda:0')
episode: 587 training return: tensor(-954130.1250, device='cuda:0')
epoch: 147 test_true_pfm: -22.444554172134097
episode: 588 training return: tensor(-941711.2500, device='cuda:0')
episode: 589 training return: tensor(-8115415., device='cuda:0')
episode: 590 training return: tensor(-9210728., device='cuda:0')
episode: 591 training return: tensor(-868355.0625, device='cuda:0')
epoch: 148 test_true_pfm: -22.630171717374242
episode: 592 training return: tensor(-941588.2500, device='cuda:0')
episode: 593 training return: tensor(-7534681., device='cuda:0')
episode: 594 training return: tensor(-973967.3750, device='cuda:0')
episode: 595 training return: tensor(-978238.8750, device='cuda:0')
epoch: 149 test_true_pfm: -25.666306615377817
episode: 596 training return: tensor(-922365.4375, device='cuda:0')
episode: 597 training return: tensor(-2027032.5000, device='cuda:0')
episode: 598 training return: tensor(-1031334.1875, device='cuda:0')
episode: 599 training return: tensor(-2096422.3750, device='cuda:0')
epoch: 150 test_true_pfm: -24.40736302854222
