epoch: 0 training_loss 6.742049655914307 test_loss: 2.5148563385009766
epoch: 1 training_loss 0.24619271855801345 test_loss: -1.5943551063537598
epoch: 2 training_loss -2.5148607122898103 test_loss: -3.4891307830810545
epoch: 3 training_loss -3.981329684257507 test_loss: -4.721726608276367
epoch: 4 training_loss -5.026044993400574 test_loss: -5.500765609741211
epoch: 5 training_loss -5.85082522392273 test_loss: -6.331614685058594
epoch: 6 training_loss -6.533839693069458 test_loss: -6.659506988525391
epoch: 7 training_loss -7.06178849697113 test_loss: -7.26177749633789
epoch: 8 training_loss -7.58591730594635 test_loss: -7.8237770080566404
epoch: 9 training_loss -7.998613548278809 test_loss: -8.077895355224609
epoch: 10 training_loss -8.315149846076965 test_loss: -8.54039306640625
epoch: 11 training_loss -8.64888171672821 test_loss: -8.62210464477539
epoch: 12 training_loss -9.044431762695313 test_loss: -9.104798889160156
epoch: 13 training_loss -9.344731760025024 test_loss: -9.329864501953125
epoch: 14 training_loss -9.631467933654784 test_loss: -9.635151672363282
epoch: 15 training_loss -9.760899095535278 test_loss: -10.01119155883789
epoch: 16 training_loss -9.992587547302247 test_loss: -10.142729949951171
epoch: 17 training_loss -10.176102428436279 test_loss: -10.236488342285156
epoch: 18 training_loss -10.402558012008667 test_loss: -10.433650970458984
epoch: 19 training_loss -10.524997062683106 test_loss: -10.596764373779298
epoch: 20 training_loss -10.68140679359436 test_loss: -10.81695327758789
epoch: 21 training_loss -10.881299152374268 test_loss: -10.991394805908204
epoch: 22 training_loss -10.976899538040161 test_loss: -10.954635620117188
epoch: 23 training_loss -11.091638927459718 test_loss: -11.10153579711914
epoch: 24 training_loss -11.20896113395691 test_loss: -11.175447845458985
epoch: 25 training_loss -11.298158369064332 test_loss: -11.255390167236328
epoch: 26 training_loss -11.403112363815307 test_loss: -11.316102600097656
epoch: 27 training_loss -11.54324670791626 test_loss: -11.46526870727539
epoch: 28 training_loss -11.660958118438721 test_loss: -11.669630432128907
epoch: 29 training_loss -11.665862979888916 test_loss: -11.581915283203125
4822.595143925368
episode: 0 training return: tensor(-1177.2343, device='cuda:0')
episode: 1 training return: tensor(-1206.8204, device='cuda:0')
episode: 2 training return: tensor(-1134.7347, device='cuda:0')
episode: 3 training return: tensor(-1195.7626, device='cuda:0')
epoch: 1 test_true_pfm: -12.160751781488353
episode: 4 training return: tensor(-1197.5231, device='cuda:0')
episode: 5 training return: tensor(-1179.8774, device='cuda:0')
episode: 6 training return: tensor(-1205.6494, device='cuda:0')
episode: 7 training return: tensor(-1212.7264, device='cuda:0')
epoch: 2 test_true_pfm: -23.76796442979797
episode: 8 training return: tensor(-1198.1096, device='cuda:0')
episode: 9 training return: tensor(-1201.7079, device='cuda:0')
episode: 10 training return: tensor(-1112.5219, device='cuda:0')
episode: 11 training return: tensor(-1120.5938, device='cuda:0')
epoch: 3 test_true_pfm: -27.4075254501806
episode: 12 training return: tensor(-1121.3751, device='cuda:0')
episode: 13 training return: tensor(-1139.9921, device='cuda:0')
episode: 14 training return: tensor(-1124.4535, device='cuda:0')
episode: 15 training return: tensor(-1130.8722, device='cuda:0')
epoch: 4 test_true_pfm: -15.487801034558496
episode: 16 training return: tensor(-1106.5017, device='cuda:0')
episode: 17 training return: tensor(-1136.5739, device='cuda:0')
episode: 18 training return: tensor(-1110.2716, device='cuda:0')
episode: 19 training return: tensor(-1096.2164, device='cuda:0')
epoch: 5 test_true_pfm: -8.882992492039403
episode: 20 training return: tensor(-1119.3967, device='cuda:0')
episode: 21 training return: tensor(-1109.5513, device='cuda:0')
episode: 22 training return: tensor(-1117.7369, device='cuda:0')
episode: 23 training return: tensor(-1112.1525, device='cuda:0')
epoch: 6 test_true_pfm: 0.49805867805174125
episode: 24 training return: tensor(-1122.0770, device='cuda:0')
episode: 25 training return: tensor(-1122.7678, device='cuda:0')
episode: 26 training return: tensor(-1121.7885, device='cuda:0')
episode: 27 training return: tensor(-1116.6628, device='cuda:0')
epoch: 7 test_true_pfm: 6.322129366151292
episode: 28 training return: tensor(-1090.9895, device='cuda:0')
episode: 29 training return: tensor(-1111.8519, device='cuda:0')
episode: 30 training return: tensor(-1114.6071, device='cuda:0')
episode: 31 training return: tensor(-1102.6150, device='cuda:0')
epoch: 8 test_true_pfm: 5.68833164031106
episode: 32 training return: tensor(-1085.8141, device='cuda:0')
episode: 33 training return: tensor(-1111.2449, device='cuda:0')
episode: 34 training return: tensor(-1117.2109, device='cuda:0')
episode: 35 training return: tensor(-1117.3209, device='cuda:0')
epoch: 9 test_true_pfm: 6.547861704115443
episode: 36 training return: tensor(-1107.5382, device='cuda:0')
episode: 37 training return: tensor(-1086.2129, device='cuda:0')
episode: 38 training return: tensor(-1088.0728, device='cuda:0')
episode: 39 training return: tensor(-1121.9348, device='cuda:0')
epoch: 10 test_true_pfm: 7.738598462512076
episode: 40 training return: tensor(-1118.3698, device='cuda:0')
episode: 41 training return: tensor(-1099.1984, device='cuda:0')
episode: 42 training return: tensor(-1111.1948, device='cuda:0')
episode: 43 training return: tensor(-1110.5692, device='cuda:0')
epoch: 11 test_true_pfm: 5.52045539618641
episode: 44 training return: tensor(-1101.7792, device='cuda:0')
episode: 45 training return: tensor(-1085.0605, device='cuda:0')
episode: 46 training return: tensor(-1091.9124, device='cuda:0')
episode: 47 training return: tensor(-1119.5892, device='cuda:0')
epoch: 12 test_true_pfm: 8.792098336043663
episode: 48 training return: tensor(-1118.3604, device='cuda:0')
episode: 49 training return: tensor(-1120.1106, device='cuda:0')
episode: 50 training return: tensor(-1118.6748, device='cuda:0')
episode: 51 training return: tensor(-1113.8423, device='cuda:0')
epoch: 13 test_true_pfm: 6.801227045372625
episode: 52 training return: tensor(-1110.2220, device='cuda:0')
episode: 53 training return: tensor(-1098.7524, device='cuda:0')
episode: 54 training return: tensor(-1084.1940, device='cuda:0')
episode: 55 training return: tensor(-1095.4651, device='cuda:0')
epoch: 14 test_true_pfm: 7.288204467192837
episode: 56 training return: tensor(-1093.6559, device='cuda:0')
episode: 57 training return: tensor(-1083.0996, device='cuda:0')
episode: 58 training return: tensor(-1086.9557, device='cuda:0')
episode: 59 training return: tensor(-1111.1694, device='cuda:0')
epoch: 15 test_true_pfm: 7.452263833113238
episode: 60 training return: tensor(-1125.7290, device='cuda:0')
episode: 61 training return: tensor(-1118.7039, device='cuda:0')
episode: 62 training return: tensor(-1087.9120, device='cuda:0')
episode: 63 training return: tensor(-1104.4679, device='cuda:0')
epoch: 16 test_true_pfm: 7.369812863231874
episode: 64 training return: tensor(-1096.5154, device='cuda:0')
episode: 65 training return: tensor(-1108.0646, device='cuda:0')
episode: 66 training return: tensor(-1116.8016, device='cuda:0')
episode: 67 training return: tensor(-1115.6499, device='cuda:0')
epoch: 17 test_true_pfm: 6.845929380316715
episode: 68 training return: tensor(-1118.2896, device='cuda:0')
episode: 69 training return: tensor(-1120.8563, device='cuda:0')
episode: 70 training return: tensor(-1115.6511, device='cuda:0')
episode: 71 training return: tensor(-1092.1176, device='cuda:0')
epoch: 18 test_true_pfm: 7.547810160382816
episode: 72 training return: tensor(-1086.0206, device='cuda:0')
episode: 73 training return: tensor(-1106.0011, device='cuda:0')
episode: 74 training return: tensor(-1083.8533, device='cuda:0')
episode: 75 training return: tensor(-1083.3243, device='cuda:0')
epoch: 19 test_true_pfm: 7.425859015791009
episode: 76 training return: tensor(-1120.6841, device='cuda:0')
episode: 77 training return: tensor(-1100.3893, device='cuda:0')
episode: 78 training return: tensor(-1087.4841, device='cuda:0')
episode: 79 training return: tensor(-1086.7572, device='cuda:0')
epoch: 20 test_true_pfm: 7.085806553142348
episode: 80 training return: tensor(-1107.1625, device='cuda:0')
episode: 81 training return: tensor(-1116.3300, device='cuda:0')
episode: 82 training return: tensor(-1118.6852, device='cuda:0')
episode: 83 training return: tensor(-1109.2648, device='cuda:0')
epoch: 21 test_true_pfm: 6.784466817349096
episode: 84 training return: tensor(-1083.6832, device='cuda:0')
episode: 85 training return: tensor(-1085.2467, device='cuda:0')
episode: 86 training return: tensor(-1089.3632, device='cuda:0')
episode: 87 training return: tensor(-1087.6466, device='cuda:0')
epoch: 22 test_true_pfm: 8.644982007477582
episode: 88 training return: tensor(-1118.6974, device='cuda:0')
episode: 89 training return: tensor(-1086.5977, device='cuda:0')
episode: 90 training return: tensor(-1087.3102, device='cuda:0')
episode: 91 training return: tensor(-1086.3322, device='cuda:0')
epoch: 23 test_true_pfm: 7.436617579764355
episode: 92 training return: tensor(-1087.7510, device='cuda:0')
episode: 93 training return: tensor(-1082.0979, device='cuda:0')
episode: 94 training return: tensor(-1083.5813, device='cuda:0')
episode: 95 training return: tensor(-1083.4534, device='cuda:0')
epoch: 24 test_true_pfm: 6.979817798175677
episode: 96 training return: tensor(-1084.6171, device='cuda:0')
episode: 97 training return: tensor(-1086.4448, device='cuda:0')
episode: 98 training return: tensor(-1085.8625, device='cuda:0')
episode: 99 training return: tensor(-1080.1744, device='cuda:0')
epoch: 25 test_true_pfm: 8.303884383626645
episode: 100 training return: tensor(-1093.4899, device='cuda:0')
episode: 101 training return: tensor(-1085.3840, device='cuda:0')
episode: 102 training return: tensor(-1108.9000, device='cuda:0')
episode: 103 training return: tensor(-1087.9681, device='cuda:0')
epoch: 26 test_true_pfm: 6.395718909431545
episode: 104 training return: tensor(-1118.2941, device='cuda:0')
episode: 105 training return: tensor(-1112.6002, device='cuda:0')
episode: 106 training return: tensor(-1086.2225, device='cuda:0')
episode: 107 training return: tensor(-1087.0935, device='cuda:0')
epoch: 27 test_true_pfm: 7.500682163701089
episode: 108 training return: tensor(-1116.7864, device='cuda:0')
episode: 109 training return: tensor(-1085.7606, device='cuda:0')
episode: 110 training return: tensor(-1081.1683, device='cuda:0')
episode: 111 training return: tensor(-1087.6400, device='cuda:0')
epoch: 28 test_true_pfm: 6.305986999082864
episode: 112 training return: tensor(-1110.4211, device='cuda:0')
episode: 113 training return: tensor(-1083.7549, device='cuda:0')
episode: 114 training return: tensor(-1086.4020, device='cuda:0')
episode: 115 training return: tensor(-1082.5266, device='cuda:0')
epoch: 29 test_true_pfm: 8.757529664183346
episode: 116 training return: tensor(-1087.6472, device='cuda:0')
episode: 117 training return: tensor(-1083.2294, device='cuda:0')
episode: 118 training return: tensor(-1088.3586, device='cuda:0')
episode: 119 training return: tensor(-1117.8707, device='cuda:0')
epoch: 30 test_true_pfm: 6.621180275801925
episode: 120 training return: tensor(-1115.3535, device='cuda:0')
episode: 121 training return: tensor(-1118.8562, device='cuda:0')
episode: 122 training return: tensor(-1091.6117, device='cuda:0')
episode: 123 training return: tensor(-1081.3738, device='cuda:0')
epoch: 31 test_true_pfm: 6.670117711872094
episode: 124 training return: tensor(-1087.5405, device='cuda:0')
episode: 125 training return: tensor(-1088.1655, device='cuda:0')
episode: 126 training return: tensor(-1087.5991, device='cuda:0')
episode: 127 training return: tensor(-1088.6536, device='cuda:0')
epoch: 32 test_true_pfm: 7.422639372440415
episode: 128 training return: tensor(-1089.0034, device='cuda:0')
episode: 129 training return: tensor(-1082.6405, device='cuda:0')
episode: 130 training return: tensor(-1083.8795, device='cuda:0')
episode: 131 training return: tensor(-1084.0941, device='cuda:0')
epoch: 33 test_true_pfm: 8.133187290590326
episode: 132 training return: tensor(-1084.3639, device='cuda:0')
episode: 133 training return: tensor(-1085.2667, device='cuda:0')
episode: 134 training return: tensor(-1084.1418, device='cuda:0')
episode: 135 training return: tensor(-1083.6772, device='cuda:0')
epoch: 34 test_true_pfm: 7.064193621654742
episode: 136 training return: tensor(-1118.6599, device='cuda:0')
episode: 137 training return: tensor(-1086.4823, device='cuda:0')
episode: 138 training return: tensor(-1084.5166, device='cuda:0')
episode: 139 training return: tensor(-1086.2281, device='cuda:0')
epoch: 35 test_true_pfm: 7.9921024251103105
episode: 140 training return: tensor(-1086.2466, device='cuda:0')
episode: 141 training return: tensor(-1081.2184, device='cuda:0')
episode: 142 training return: tensor(-1083.2894, device='cuda:0')
episode: 143 training return: tensor(-1083.9010, device='cuda:0')
epoch: 36 test_true_pfm: 7.355002150069196
episode: 144 training return: tensor(-1113.0948, device='cuda:0')
episode: 145 training return: tensor(-1100.5634, device='cuda:0')
episode: 146 training return: tensor(-1083.4916, device='cuda:0')
episode: 147 training return: tensor(-1081.3499, device='cuda:0')
epoch: 37 test_true_pfm: 7.923247891532328
episode: 148 training return: tensor(-1083.2871, device='cuda:0')
episode: 149 training return: tensor(-1083.5687, device='cuda:0')
episode: 150 training return: tensor(-1084.1831, device='cuda:0')
episode: 151 training return: tensor(-1086.6073, device='cuda:0')
epoch: 38 test_true_pfm: 7.383881975906629
episode: 152 training return: tensor(-1084.4706, device='cuda:0')
episode: 153 training return: tensor(-1083.6804, device='cuda:0')
episode: 154 training return: tensor(-1083.8977, device='cuda:0')
episode: 155 training return: tensor(-1116.6448, device='cuda:0')
epoch: 39 test_true_pfm: 6.873320682107729
episode: 156 training return: tensor(-1085.4486, device='cuda:0')
episode: 157 training return: tensor(-1083.8711, device='cuda:0')
episode: 158 training return: tensor(-1120.3021, device='cuda:0')
episode: 159 training return: tensor(-1086.9050, device='cuda:0')
epoch: 40 test_true_pfm: 8.851293235847615
episode: 160 training return: tensor(-1084.2959, device='cuda:0')
episode: 161 training return: tensor(-1083.3928, device='cuda:0')
episode: 162 training return: tensor(-1085.5012, device='cuda:0')
episode: 163 training return: tensor(-1085.3866, device='cuda:0')
epoch: 41 test_true_pfm: 7.666287270924201
episode: 164 training return: tensor(-1086.3357, device='cuda:0')
episode: 165 training return: tensor(-1079.9967, device='cuda:0')
episode: 166 training return: tensor(-1116.1553, device='cuda:0')
episode: 167 training return: tensor(-1082.0416, device='cuda:0')
epoch: 42 test_true_pfm: 7.3797695527091305
episode: 168 training return: tensor(-1087.6903, device='cuda:0')
