epoch: 0 training_loss 0.4197836981713772 test_loss: 0.3254331350326538 test_wrong: 0.1578125
epoch: 1 training_loss 0.2846056424081326 test_loss: 0.26312568187713625 test_wrong: 0.103125
epoch: 2 training_loss 0.22862714007496834 test_loss: 0.19808754920959473 test_wrong: 0.0765625
epoch: 3 training_loss 0.21347117967903614 test_loss: 0.19910848140716553 test_wrong: 0.0984375
epoch: 4 training_loss 0.19466286182403564 test_loss: 0.2004307508468628 test_wrong: 0.075
epoch: 5 training_loss 0.17584889262914657 test_loss: 0.18500092029571533 test_wrong: 0.075
epoch: 6 training_loss 0.18038504034280778 test_loss: 0.16548022031784057 test_wrong: 0.0625
epoch: 7 training_loss 0.16171428844332694 test_loss: 0.17411788702011108 test_wrong: 0.0671875
epoch: 8 training_loss 0.15863799244165422 test_loss: 0.15725711584091187 test_wrong: 0.0640625
epoch: 9 training_loss 0.15631702587008475 test_loss: 0.15039219856262206 test_wrong: 0.0515625
epoch: 10 training_loss 0.1597111401706934 test_loss: 0.15708274841308595 test_wrong: 0.053125
epoch: 11 training_loss 0.14608399208635092 test_loss: 0.13032499551773072 test_wrong: 0.0453125
epoch: 12 training_loss 0.15828128922730683 test_loss: 0.131229031085968 test_wrong: 0.0453125
epoch: 13 training_loss 0.14460654132068157 test_loss: 0.1463216781616211 test_wrong: 0.0578125
epoch: 14 training_loss 0.15026436306536198 test_loss: 0.14404220581054689 test_wrong: 0.0453125
epoch: 15 training_loss 0.15011198811233042 test_loss: 0.12436240911483765 test_wrong: 0.0515625
epoch: 16 training_loss 0.14621235564351082 test_loss: 0.15331157445907592 test_wrong: 0.0640625
epoch: 17 training_loss 0.14272661067545414 test_loss: 0.14468683004379274 test_wrong: 0.0515625
epoch: 18 training_loss 0.14179131276905538 test_loss: 0.15535564422607423 test_wrong: 0.059375
epoch: 19 training_loss 0.13120377413928508 test_loss: 0.14198579788208007 test_wrong: 0.05625
epoch: 20 training_loss 0.13509420845657588 test_loss: 0.13652929067611694 test_wrong: 0.05
epoch: 21 training_loss 0.13758377995342017 test_loss: 0.12152377367019654 test_wrong: 0.0421875
epoch: 22 training_loss 0.1427960667014122 test_loss: 0.12566572427749634 test_wrong: 0.046875
epoch: 23 training_loss 0.13409603461623193 test_loss: 0.14589556455612182 test_wrong: 0.05625
epoch: 24 training_loss 0.13827313125133514 test_loss: 0.12826651334762573 test_wrong: 0.0515625
epoch: 25 training_loss 0.1290587041527033 test_loss: 0.11896872520446777 test_wrong: 0.0390625
epoch: 26 training_loss 0.13061165533959865 test_loss: 0.13502789735794068 test_wrong: 0.0515625
epoch: 27 training_loss 0.13171321123838425 test_loss: 0.14427706003189086 test_wrong: 0.0640625
epoch: 28 training_loss 0.13407457649707794 test_loss: 0.15058331489562987 test_wrong: 0.0609375
epoch: 29 training_loss 0.12885346081107854 test_loss: 0.1353984594345093 test_wrong: 0.053125
epoch: 30 training_loss 0.13641732312738897 test_loss: 0.127576744556427 test_wrong: 0.0484375
epoch: 31 training_loss 0.1288749112933874 test_loss: 0.13200581073760986 test_wrong: 0.0546875
epoch: 32 training_loss 0.13739927373826505 test_loss: 0.12883299589157104 test_wrong: 0.046875
epoch: 33 training_loss 0.1342324537783861 test_loss: 0.12113622426986695 test_wrong: 0.0515625
epoch: 34 training_loss 0.12859525170177222 test_loss: 0.15193666219711305 test_wrong: 0.05
epoch: 35 training_loss 0.13602718632668256 test_loss: 0.13791807889938354 test_wrong: 0.0515625
epoch: 36 training_loss 0.13008320201188325 test_loss: 0.1539330244064331 test_wrong: 0.0609375
epoch: 37 training_loss 0.13386257879436017 test_loss: 0.14869422912597657 test_wrong: 0.0546875
epoch: 38 training_loss 0.12966880843043327 test_loss: 0.12151371240615845 test_wrong: 0.034375
epoch: 39 training_loss 0.12562478344887495 test_loss: 0.12490687370300294 test_wrong: 0.0421875
epoch: 40 training_loss 0.13360331121832134 test_loss: 0.12518739700317383 test_wrong: 0.0328125
epoch: 41 training_loss 0.13272038798779248 test_loss: 0.135128653049469 test_wrong: 0.053125
epoch: 42 training_loss 0.12441459059715271 test_loss: 0.1404141902923584 test_wrong: 0.0609375
epoch: 43 training_loss 0.13223458364605903 test_loss: 0.12150306701660156 test_wrong: 0.040625
epoch: 44 training_loss 0.12594840187579392 test_loss: 0.12494735717773438 test_wrong: 0.05
epoch: 45 training_loss 0.12949192985892297 test_loss: 0.1494097113609314 test_wrong: 0.0515625
epoch: 46 training_loss 0.12314411688596011 test_loss: 0.15185248851776123 test_wrong: 0.0609375
epoch: 47 training_loss 0.13110416647046805 test_loss: 0.12386106252670288 test_wrong: 0.0421875
epoch: 48 training_loss 0.1296456429734826 test_loss: 0.13734405040740966 test_wrong: 0.0484375
epoch: 49 training_loss 0.1300579199194908 test_loss: 0.14589998722076417 test_wrong: 0.0484375
episode: 0 training return: tensor(-499.9767, device='cuda:0', grad_fn=<AddBackward0>)
episode: 1 training return: tensor(-499.9754, device='cuda:0', grad_fn=<AddBackward0>)
episode: 2 training return: tensor(-499.9771, device='cuda:0', grad_fn=<AddBackward0>)
episode: 3 training return: tensor(-499.9738, device='cuda:0', grad_fn=<AddBackward0>)
epoch: 1 test_true_pfm: -0.45396024686926073
episode: 4 training return: tensor(-499.9770, device='cuda:0', grad_fn=<AddBackward0>)
episode: 5 training return: tensor(-499.9762, device='cuda:0', grad_fn=<AddBackward0>)
episode: 6 training return: tensor(-499.9747, device='cuda:0', grad_fn=<AddBackward0>)
episode: 7 training return: tensor(-499.9762, device='cuda:0', grad_fn=<AddBackward0>)
epoch: 2 test_true_pfm: -0.8894795900719145
episode: 8 training return: tensor(-499.9765, device='cuda:0', grad_fn=<AddBackward0>)
episode: 9 training return: tensor(-499.9756, device='cuda:0', grad_fn=<AddBackward0>)
episode: 10 training return: tensor(-499.9769, device='cuda:0', grad_fn=<AddBackward0>)
episode: 11 training return: tensor(-499.9775, device='cuda:0', grad_fn=<AddBackward0>)
epoch: 3 test_true_pfm: -0.30037344479043143
episode: 12 training return: tensor(-499.9772, device='cuda:0', grad_fn=<AddBackward0>)
episode: 13 training return: tensor(-499.9762, device='cuda:0', grad_fn=<AddBackward0>)
episode: 14 training return: tensor(-499.9766, device='cuda:0', grad_fn=<AddBackward0>)
episode: 15 training return: tensor(-499.9776, device='cuda:0', grad_fn=<AddBackward0>)
epoch: 4 test_true_pfm: -0.9793143618486493
episode: 16 training return: tensor(-499.9779, device='cuda:0', grad_fn=<AddBackward0>)
episode: 17 training return: tensor(-499.9764, device='cuda:0', grad_fn=<AddBackward0>)
episode: 18 training return: tensor(-499.9762, device='cuda:0', grad_fn=<AddBackward0>)
episode: 19 training return: tensor(-499.9771, device='cuda:0', grad_fn=<AddBackward0>)
epoch: 5 test_true_pfm: -0.19436368102741455
episode: 20 training return: tensor(-499.9768, device='cuda:0', grad_fn=<AddBackward0>)
episode: 21 training return: tensor(-499.9760, device='cuda:0', grad_fn=<AddBackward0>)
episode: 22 training return: tensor(-499.9765, device='cuda:0', grad_fn=<AddBackward0>)
episode: 23 training return: tensor(-499.9758, device='cuda:0', grad_fn=<AddBackward0>)
epoch: 6 test_true_pfm: 0.46704318547685464
episode: 24 training return: tensor(-499.9763, device='cuda:0', grad_fn=<AddBackward0>)
episode: 25 training return: tensor(-499.9785, device='cuda:0', grad_fn=<AddBackward0>)
episode: 26 training return: tensor(-499.9765, device='cuda:0', grad_fn=<AddBackward0>)
episode: 27 training return: tensor(-499.9759, device='cuda:0', grad_fn=<AddBackward0>)
epoch: 7 test_true_pfm: -0.36681975614422074
episode: 28 training return: tensor(-499.9762, device='cuda:0', grad_fn=<AddBackward0>)
episode: 29 training return: tensor(-499.9761, device='cuda:0', grad_fn=<AddBackward0>)
episode: 30 training return: tensor(-499.9764, device='cuda:0', grad_fn=<AddBackward0>)
episode: 31 training return: tensor(-499.9776, device='cuda:0', grad_fn=<AddBackward0>)
epoch: 8 test_true_pfm: -0.4800606093013275
episode: 32 training return: tensor(-499.9771, device='cuda:0', grad_fn=<AddBackward0>)
episode: 33 training return: tensor(-499.9771, device='cuda:0', grad_fn=<AddBackward0>)
episode: 34 training return: tensor(-499.9765, device='cuda:0', grad_fn=<AddBackward0>)
episode: 35 training return: tensor(-499.9768, device='cuda:0', grad_fn=<AddBackward0>)
epoch: 9 test_true_pfm: -0.015824409909419208
episode: 36 training return: tensor(-499.9756, device='cuda:0', grad_fn=<AddBackward0>)
episode: 37 training return: tensor(-499.9772, device='cuda:0', grad_fn=<AddBackward0>)
episode: 38 training return: tensor(-499.9766, device='cuda:0', grad_fn=<AddBackward0>)
episode: 39 training return: tensor(-499.9776, device='cuda:0', grad_fn=<AddBackward0>)
epoch: 10 test_true_pfm: -1.0857833363756642
episode: 40 training return: tensor(-499.9783, device='cuda:0', grad_fn=<AddBackward0>)
episode: 41 training return: tensor(-499.9776, device='cuda:0', grad_fn=<AddBackward0>)
episode: 42 training return: tensor(-499.9753, device='cuda:0', grad_fn=<AddBackward0>)
episode: 43 training return: tensor(-499.9767, device='cuda:0', grad_fn=<AddBackward0>)
epoch: 11 test_true_pfm: 0.2575599976429786
episode: 44 training return: tensor(-499.9770, device='cuda:0', grad_fn=<AddBackward0>)
episode: 45 training return: tensor(-499.9756, device='cuda:0', grad_fn=<AddBackward0>)
episode: 46 training return: tensor(-499.9772, device='cuda:0', grad_fn=<AddBackward0>)
episode: 47 training return: tensor(-499.9771, device='cuda:0', grad_fn=<AddBackward0>)
epoch: 12 test_true_pfm: 0.03128178312862643
episode: 48 training return: tensor(-499.9758, device='cuda:0', grad_fn=<AddBackward0>)
episode: 49 training return: tensor(-499.9776, device='cuda:0', grad_fn=<AddBackward0>)
episode: 50 training return: tensor(-499.9769, device='cuda:0', grad_fn=<AddBackward0>)
episode: 51 training return: tensor(-499.9777, device='cuda:0', grad_fn=<AddBackward0>)
epoch: 13 test_true_pfm: -0.5135011647357964
episode: 52 training return: tensor(-499.9763, device='cuda:0', grad_fn=<AddBackward0>)
episode: 53 training return: tensor(-499.9771, device='cuda:0', grad_fn=<AddBackward0>)
episode: 54 training return: tensor(-499.9769, device='cuda:0', grad_fn=<AddBackward0>)
episode: 55 training return: tensor(-499.9758, device='cuda:0', grad_fn=<AddBackward0>)
epoch: 14 test_true_pfm: -0.6742656952619522
episode: 56 training return: tensor(-499.9759, device='cuda:0', grad_fn=<AddBackward0>)
episode: 57 training return: tensor(-499.9759, device='cuda:0', grad_fn=<AddBackward0>)
episode: 58 training return: tensor(-499.9755, device='cuda:0', grad_fn=<AddBackward0>)
episode: 59 training return: tensor(-499.9773, device='cuda:0', grad_fn=<AddBackward0>)
epoch: 15 test_true_pfm: -0.268064810326971
episode: 60 training return: tensor(-499.9771, device='cuda:0', grad_fn=<AddBackward0>)
episode: 61 training return: tensor(-499.9759, device='cuda:0', grad_fn=<AddBackward0>)
episode: 62 training return: tensor(-499.9764, device='cuda:0', grad_fn=<AddBackward0>)
episode: 63 training return: tensor(-499.9775, device='cuda:0', grad_fn=<AddBackward0>)
epoch: 16 test_true_pfm: -0.8529590677845512
episode: 64 training return: tensor(-499.9781, device='cuda:0', grad_fn=<AddBackward0>)
episode: 65 training return: tensor(-499.9764, device='cuda:0', grad_fn=<AddBackward0>)
episode: 66 training return: tensor(-499.9770, device='cuda:0', grad_fn=<AddBackward0>)
episode: 67 training return: tensor(-499.9755, device='cuda:0', grad_fn=<AddBackward0>)
epoch: 17 test_true_pfm: -0.7079059240663893
episode: 68 training return: tensor(-499.9753, device='cuda:0', grad_fn=<AddBackward0>)
episode: 69 training return: tensor(-499.9771, device='cuda:0', grad_fn=<AddBackward0>)
episode: 70 training return: tensor(-499.9772, device='cuda:0', grad_fn=<AddBackward0>)
episode: 71 training return: tensor(-499.9763, device='cuda:0', grad_fn=<AddBackward0>)
epoch: 18 test_true_pfm: -0.17062704059268974
episode: 72 training return: tensor(-499.9758, device='cuda:0', grad_fn=<AddBackward0>)
episode: 73 training return: tensor(-499.9767, device='cuda:0', grad_fn=<AddBackward0>)
episode: 74 training return: tensor(-499.9756, device='cuda:0', grad_fn=<AddBackward0>)
episode: 75 training return: tensor(-499.9759, device='cuda:0', grad_fn=<AddBackward0>)
epoch: 19 test_true_pfm: -0.45374622036284357
episode: 76 training return: tensor(-499.9786, device='cuda:0', grad_fn=<AddBackward0>)
episode: 77 training return: tensor(-499.9760, device='cuda:0', grad_fn=<AddBackward0>)
episode: 78 training return: tensor(-499.9763, device='cuda:0', grad_fn=<AddBackward0>)
episode: 79 training return: tensor(-499.9785, device='cuda:0', grad_fn=<AddBackward0>)
epoch: 20 test_true_pfm: -1.0718082183874114
episode: 80 training return: tensor(-499.9780, device='cuda:0', grad_fn=<AddBackward0>)
episode: 81 training return: tensor(-499.9758, device='cuda:0', grad_fn=<AddBackward0>)
episode: 82 training return: tensor(-499.9755, device='cuda:0', grad_fn=<AddBackward0>)
episode: 83 training return: tensor(-499.9768, device='cuda:0', grad_fn=<AddBackward0>)
epoch: 21 test_true_pfm: -0.04259563158669962
episode: 84 training return: tensor(-499.9761, device='cuda:0', grad_fn=<AddBackward0>)
episode: 85 training return: tensor(-499.9755, device='cuda:0', grad_fn=<AddBackward0>)
episode: 86 training return: tensor(-499.9767, device='cuda:0', grad_fn=<AddBackward0>)
episode: 87 training return: tensor(-499.9772, device='cuda:0', grad_fn=<AddBackward0>)
epoch: 22 test_true_pfm: 0.039685331133897606
episode: 88 training return: tensor(-499.9778, device='cuda:0', grad_fn=<AddBackward0>)
episode: 89 training return: tensor(-499.9759, device='cuda:0', grad_fn=<AddBackward0>)
episode: 90 training return: tensor(-499.9757, device='cuda:0', grad_fn=<AddBackward0>)
episode: 91 training return: tensor(-499.9774, device='cuda:0', grad_fn=<AddBackward0>)
epoch: 23 test_true_pfm: -0.4322569842712288
episode: 92 training return: tensor(-499.9764, device='cuda:0', grad_fn=<AddBackward0>)
episode: 93 training return: tensor(-499.9779, device='cuda:0', grad_fn=<AddBackward0>)
episode: 94 training return: tensor(-499.9753, device='cuda:0', grad_fn=<AddBackward0>)
episode: 95 training return: tensor(-499.9767, device='cuda:0', grad_fn=<AddBackward0>)
epoch: 24 test_true_pfm: -0.5646839088004878
episode: 96 training return: tensor(-499.9772, device='cuda:0', grad_fn=<AddBackward0>)
episode: 97 training return: tensor(-499.9756, device='cuda:0', grad_fn=<AddBackward0>)
episode: 98 training return: tensor(-499.9777, device='cuda:0', grad_fn=<AddBackward0>)
episode: 99 training return: tensor(-499.9779, device='cuda:0', grad_fn=<AddBackward0>)
epoch: 25 test_true_pfm: -0.8243661736354829
episode: 100 training return: tensor(-499.9766, device='cuda:0', grad_fn=<AddBackward0>)
episode: 101 training return: tensor(-499.9776, device='cuda:0', grad_fn=<AddBackward0>)
episode: 102 training return: tensor(-499.9775, device='cuda:0', grad_fn=<AddBackward0>)
episode: 103 training return: tensor(-499.9767, device='cuda:0', grad_fn=<AddBackward0>)
epoch: 26 test_true_pfm: -0.4289392192946752
episode: 104 training return: tensor(-499.9765, device='cuda:0', grad_fn=<AddBackward0>)
episode: 105 training return: tensor(-499.9760, device='cuda:0', grad_fn=<AddBackward0>)
episode: 106 training return: tensor(-499.9776, device='cuda:0', grad_fn=<AddBackward0>)
episode: 107 training return: tensor(-499.9770, device='cuda:0', grad_fn=<AddBackward0>)
epoch: 27 test_true_pfm: -0.08877457843346388
episode: 108 training return: tensor(-499.9791, device='cuda:0', grad_fn=<AddBackward0>)
episode: 109 training return: tensor(-499.9786, device='cuda:0', grad_fn=<AddBackward0>)
episode: 110 training return: tensor(-499.9773, device='cuda:0', grad_fn=<AddBackward0>)
episode: 111 training return: tensor(-499.9760, device='cuda:0', grad_fn=<AddBackward0>)
epoch: 28 test_true_pfm: -0.27114412770288154
episode: 112 training return: tensor(-499.9769, device='cuda:0', grad_fn=<AddBackward0>)
episode: 113 training return: tensor(-499.9747, device='cuda:0', grad_fn=<AddBackward0>)
episode: 114 training return: tensor(-499.9778, device='cuda:0', grad_fn=<AddBackward0>)
episode: 115 training return: tensor(-499.9778, device='cuda:0', grad_fn=<AddBackward0>)
epoch: 29 test_true_pfm: -0.053630323481348635
episode: 116 training return: tensor(-499.9761, device='cuda:0', grad_fn=<AddBackward0>)
episode: 117 training return: tensor(-499.9760, device='cuda:0', grad_fn=<AddBackward0>)
episode: 118 training return: tensor(-499.9770, device='cuda:0', grad_fn=<AddBackward0>)
episode: 119 training return: tensor(-499.9758, device='cuda:0', grad_fn=<AddBackward0>)
epoch: 30 test_true_pfm: 0.0039127716823761744
episode: 120 training return: tensor(-499.9760, device='cuda:0', grad_fn=<AddBackward0>)
episode: 121 training return: tensor(-499.9779, device='cuda:0', grad_fn=<AddBackward0>)
episode: 122 training return: tensor(-499.9774, device='cuda:0', grad_fn=<AddBackward0>)
episode: 123 training return: tensor(-499.9763, device='cuda:0', grad_fn=<AddBackward0>)
epoch: 31 test_true_pfm: -0.027155461114359996
episode: 124 training return: tensor(-499.9779, device='cuda:0', grad_fn=<AddBackward0>)
episode: 125 training return: tensor(-499.9784, device='cuda:0', grad_fn=<AddBackward0>)
episode: 126 training return: tensor(-499.9769, device='cuda:0', grad_fn=<AddBackward0>)
episode: 127 training return: tensor(-499.9778, device='cuda:0', grad_fn=<AddBackward0>)
epoch: 32 test_true_pfm: -0.7737157967877873
episode: 128 training return: tensor(-499.9760, device='cuda:0', grad_fn=<AddBackward0>)
episode: 129 training return: tensor(-499.9761, device='cuda:0', grad_fn=<AddBackward0>)
episode: 130 training return: tensor(-499.9771, device='cuda:0', grad_fn=<AddBackward0>)
episode: 131 training return: tensor(-499.9769, device='cuda:0', grad_fn=<AddBackward0>)
epoch: 33 test_true_pfm: -0.07114587343609649
episode: 132 training return: tensor(-499.9786, device='cuda:0', grad_fn=<AddBackward0>)
episode: 133 training return: tensor(-499.9773, device='cuda:0', grad_fn=<AddBackward0>)
episode: 134 training return: tensor(-499.9786, device='cuda:0', grad_fn=<AddBackward0>)
episode: 135 training return: tensor(-499.9773, device='cuda:0', grad_fn=<AddBackward0>)
epoch: 34 test_true_pfm: 0.0635772557256916
episode: 136 training return: tensor(-499.9767, device='cuda:0', grad_fn=<AddBackward0>)
episode: 137 training return: tensor(-499.9770, device='cuda:0', grad_fn=<AddBackward0>)
episode: 138 training return: tensor(-499.9777, device='cuda:0', grad_fn=<AddBackward0>)
episode: 139 training return: tensor(-499.9772, device='cuda:0', grad_fn=<AddBackward0>)
epoch: 35 test_true_pfm: 0.024956605946002314
episode: 140 training return: tensor(-499.9765, device='cuda:0', grad_fn=<AddBackward0>)
episode: 141 training return: tensor(-499.9772, device='cuda:0', grad_fn=<AddBackward0>)
episode: 142 training return: tensor(-499.9775, device='cuda:0', grad_fn=<AddBackward0>)
episode: 143 training return: tensor(-499.9767, device='cuda:0', grad_fn=<AddBackward0>)
epoch: 36 test_true_pfm: -0.2543218352343845
episode: 144 training return: tensor(-499.9767, device='cuda:0', grad_fn=<AddBackward0>)
episode: 145 training return: tensor(-499.9770, device='cuda:0', grad_fn=<AddBackward0>)
episode: 146 training return: tensor(-499.9763, device='cuda:0', grad_fn=<AddBackward0>)
episode: 147 training return: tensor(-499.9777, device='cuda:0', grad_fn=<AddBackward0>)
epoch: 37 test_true_pfm: -0.16722980486924655
episode: 148 training return: tensor(-499.9760, device='cuda:0', grad_fn=<AddBackward0>)
episode: 149 training return: tensor(-499.9782, device='cuda:0', grad_fn=<AddBackward0>)
episode: 150 training return: tensor(-499.9774, device='cuda:0', grad_fn=<AddBackward0>)
episode: 151 training return: tensor(-499.9764, device='cuda:0', grad_fn=<AddBackward0>)
epoch: 38 test_true_pfm: -0.46842177988699746
episode: 152 training return: tensor(-499.9771, device='cuda:0', grad_fn=<AddBackward0>)
episode: 153 training return: tensor(-499.9772, device='cuda:0', grad_fn=<AddBackward0>)
episode: 154 training return: tensor(-499.9773, device='cuda:0', grad_fn=<AddBackward0>)
episode: 155 training return: tensor(-499.9764, device='cuda:0', grad_fn=<AddBackward0>)
epoch: 39 test_true_pfm: 0.08946011894840611
episode: 156 training return: tensor(-499.9768, device='cuda:0', grad_fn=<AddBackward0>)
episode: 157 training return: tensor(-499.9753, device='cuda:0', grad_fn=<AddBackward0>)
episode: 158 training return: tensor(-499.9770, device='cuda:0', grad_fn=<AddBackward0>)
episode: 159 training return: tensor(-499.9767, device='cuda:0', grad_fn=<AddBackward0>)
epoch: 40 test_true_pfm: -0.3022087177802259
episode: 160 training return: tensor(-499.9763, device='cuda:0', grad_fn=<AddBackward0>)
episode: 161 training return: tensor(-499.9754, device='cuda:0', grad_fn=<AddBackward0>)
episode: 162 training return: tensor(-499.9775, device='cuda:0', grad_fn=<AddBackward0>)
episode: 163 training return: tensor(-499.9774, device='cuda:0', grad_fn=<AddBackward0>)
epoch: 41 test_true_pfm: -0.7059223760679867
episode: 164 training return: tensor(-499.9771, device='cuda:0', grad_fn=<AddBackward0>)
episode: 165 training return: tensor(-499.9756, device='cuda:0', grad_fn=<AddBackward0>)
episode: 166 training return: tensor(-499.9772, device='cuda:0', grad_fn=<AddBackward0>)
episode: 167 training return: tensor(-499.9749, device='cuda:0', grad_fn=<AddBackward0>)
epoch: 42 test_true_pfm: -0.1781492977511975
episode: 168 training return: tensor(-499.9771, device='cuda:0', grad_fn=<AddBackward0>)
episode: 169 training return: tensor(-499.9759, device='cuda:0', grad_fn=<AddBackward0>)
episode: 170 training return: tensor(-499.9764, device='cuda:0', grad_fn=<AddBackward0>)
episode: 171 training return: tensor(-499.9763, device='cuda:0', grad_fn=<AddBackward0>)
epoch: 43 test_true_pfm: 0.5698769745086638
episode: 172 training return: tensor(-499.9775, device='cuda:0', grad_fn=<AddBackward0>)
episode: 173 training return: tensor(-499.9769, device='cuda:0', grad_fn=<AddBackward0>)
episode: 174 training return: tensor(-499.9760, device='cuda:0', grad_fn=<AddBackward0>)
episode: 175 training return: tensor(-499.9758, device='cuda:0', grad_fn=<AddBackward0>)
epoch: 44 test_true_pfm: -0.18458531498210198
episode: 176 training return: tensor(-499.9766, device='cuda:0', grad_fn=<AddBackward0>)
episode: 177 training return: tensor(-499.9767, device='cuda:0', grad_fn=<AddBackward0>)
episode: 178 training return: tensor(-499.9774, device='cuda:0', grad_fn=<AddBackward0>)
episode: 179 training return: tensor(-499.9780, device='cuda:0', grad_fn=<AddBackward0>)
epoch: 45 test_true_pfm: -0.5478161509864744
episode: 180 training return: tensor(-499.9767, device='cuda:0', grad_fn=<AddBackward0>)
episode: 181 training return: tensor(-499.9781, device='cuda:0', grad_fn=<AddBackward0>)
episode: 182 training return: tensor(-499.9774, device='cuda:0', grad_fn=<AddBackward0>)
episode: 183 training return: tensor(-499.9771, device='cuda:0', grad_fn=<AddBackward0>)
epoch: 46 test_true_pfm: 0.1355478835558546
episode: 184 training return: tensor(-499.9789, device='cuda:0', grad_fn=<AddBackward0>)
episode: 185 training return: tensor(-499.9770, device='cuda:0', grad_fn=<AddBackward0>)
episode: 186 training return: tensor(-499.9776, device='cuda:0', grad_fn=<AddBackward0>)
episode: 187 training return: tensor(-499.9774, device='cuda:0', grad_fn=<AddBackward0>)
epoch: 47 test_true_pfm: -0.24009503207432478
episode: 188 training return: tensor(-499.9781, device='cuda:0', grad_fn=<AddBackward0>)
episode: 189 training return: tensor(-499.9761, device='cuda:0', grad_fn=<AddBackward0>)
episode: 190 training return: tensor(-499.9757, device='cuda:0', grad_fn=<AddBackward0>)
episode: 191 training return: tensor(-499.9768, device='cuda:0', grad_fn=<AddBackward0>)
epoch: 48 test_true_pfm: -0.5190729211066142
episode: 192 training return: tensor(-499.9762, device='cuda:0', grad_fn=<AddBackward0>)
episode: 193 training return: tensor(-499.9774, device='cuda:0', grad_fn=<AddBackward0>)
episode: 194 training return: tensor(-499.9771, device='cuda:0', grad_fn=<AddBackward0>)
episode: 195 training return: tensor(-499.9760, device='cuda:0', grad_fn=<AddBackward0>)
epoch: 49 test_true_pfm: -0.9307891252991896
episode: 196 training return: tensor(-499.9756, device='cuda:0', grad_fn=<AddBackward0>)
episode: 197 training return: tensor(-499.9769, device='cuda:0', grad_fn=<AddBackward0>)
episode: 198 training return: tensor(-499.9783, device='cuda:0', grad_fn=<AddBackward0>)
episode: 199 training return: tensor(-499.9785, device='cuda:0', grad_fn=<AddBackward0>)
epoch: 50 test_true_pfm: -0.4284564088787877
episode: 200 training return: tensor(-499.9747, device='cuda:0', grad_fn=<AddBackward0>)
episode: 201 training return: tensor(-499.9770, device='cuda:0', grad_fn=<AddBackward0>)
episode: 202 training return: tensor(-499.9759, device='cuda:0', grad_fn=<AddBackward0>)
episode: 203 training return: tensor(-499.9760, device='cuda:0', grad_fn=<AddBackward0>)
epoch: 51 test_true_pfm: -0.13332244511666022
episode: 204 training return: tensor(-499.9763, device='cuda:0', grad_fn=<AddBackward0>)
episode: 205 training return: tensor(-499.9774, device='cuda:0', grad_fn=<AddBackward0>)
episode: 206 training return: tensor(-499.9779, device='cuda:0', grad_fn=<AddBackward0>)
episode: 207 training return: tensor(-499.9765, device='cuda:0', grad_fn=<AddBackward0>)
epoch: 52 test_true_pfm: 0.2525007599731722
episode: 208 training return: tensor(-499.9770, device='cuda:0', grad_fn=<AddBackward0>)
episode: 209 training return: tensor(-499.9762, device='cuda:0', grad_fn=<AddBackward0>)
episode: 210 training return: tensor(-499.9745, device='cuda:0', grad_fn=<AddBackward0>)
episode: 211 training return: tensor(-499.9785, device='cuda:0', grad_fn=<AddBackward0>)
epoch: 53 test_true_pfm: -0.32651511579554876
episode: 212 training return: tensor(-499.9768, device='cuda:0', grad_fn=<AddBackward0>)
episode: 213 training return: tensor(-499.9758, device='cuda:0', grad_fn=<AddBackward0>)
episode: 214 training return: tensor(-499.9745, device='cuda:0', grad_fn=<AddBackward0>)
episode: 215 training return: tensor(-499.9778, device='cuda:0', grad_fn=<AddBackward0>)
epoch: 54 test_true_pfm: -0.2140776281855192
episode: 216 training return: tensor(-499.9762, device='cuda:0', grad_fn=<AddBackward0>)
episode: 217 training return: tensor(-499.9776, device='cuda:0', grad_fn=<AddBackward0>)
episode: 218 training return: tensor(-499.9767, device='cuda:0', grad_fn=<AddBackward0>)
episode: 219 training return: tensor(-499.9760, device='cuda:0', grad_fn=<AddBackward0>)
epoch: 55 test_true_pfm: -0.10153024505381221
episode: 220 training return: tensor(-499.9760, device='cuda:0', grad_fn=<AddBackward0>)
episode: 221 training return: tensor(-499.9767, device='cuda:0', grad_fn=<AddBackward0>)
