79.87670949632039
episode: 0 training return: tensor(-1965.1012, device='cuda:0')
episode: 1 training return: tensor(-1432.8405, device='cuda:0')
episode: 2 training return: tensor(-1678.7804, device='cuda:0')
episode: 3 training return: tensor(-1205.7972, device='cuda:0')
epoch: 1 test_true_pfm: -38.52177227846992
episode: 4 training return: tensor(-1428.9146, device='cuda:0')
episode: 5 training return: tensor(-1222.7839, device='cuda:0')
episode: 6 training return: tensor(-1795.6522, device='cuda:0')
episode: 7 training return: tensor(-1482.9581, device='cuda:0')
epoch: 2 test_true_pfm: -29.19211641544003
episode: 8 training return: tensor(-1225.0732, device='cuda:0')
episode: 9 training return: tensor(-1206.6825, device='cuda:0')
episode: 10 training return: tensor(-1136.1813, device='cuda:0')
episode: 11 training return: tensor(-1163.2617, device='cuda:0')
epoch: 3 test_true_pfm: -19.49906788518736
episode: 12 training return: tensor(-1142.3474, device='cuda:0')
episode: 13 training return: tensor(-1133.5925, device='cuda:0')
episode: 14 training return: tensor(-1154.0999, device='cuda:0')
episode: 15 training return: tensor(-1148.0300, device='cuda:0')
epoch: 4 test_true_pfm: -23.940187899900653
episode: 16 training return: tensor(-1138.0354, device='cuda:0')
episode: 17 training return: tensor(-1159.1012, device='cuda:0')
episode: 18 training return: tensor(-1153.0026, device='cuda:0')
episode: 19 training return: tensor(-1151.9609, device='cuda:0')
epoch: 5 test_true_pfm: -7.416607209199554
episode: 20 training return: tensor(-1146.8009, device='cuda:0')
episode: 21 training return: tensor(-1139.0406, device='cuda:0')
episode: 22 training return: tensor(-1154.1421, device='cuda:0')
episode: 23 training return: tensor(-1136.5978, device='cuda:0')
epoch: 6 test_true_pfm: -2.333733588667918
episode: 24 training return: tensor(-1140.8335, device='cuda:0')
episode: 25 training return: tensor(-1116.5859, device='cuda:0')
episode: 26 training return: tensor(-1156.9504, device='cuda:0')
episode: 27 training return: tensor(-1161.0245, device='cuda:0')
epoch: 7 test_true_pfm: -2.555128085705359
episode: 28 training return: tensor(-1130.5981, device='cuda:0')
episode: 29 training return: tensor(-1140.9285, device='cuda:0')
episode: 30 training return: tensor(-1104.5950, device='cuda:0')
episode: 31 training return: tensor(-1140.0703, device='cuda:0')
epoch: 8 test_true_pfm: -1.8846370549035223
episode: 32 training return: tensor(-1143.2534, device='cuda:0')
episode: 33 training return: tensor(-1154.7534, device='cuda:0')
episode: 34 training return: tensor(-1150.1282, device='cuda:0')
episode: 35 training return: tensor(-1144.9834, device='cuda:0')
epoch: 9 test_true_pfm: -1.1682307161506598
episode: 36 training return: tensor(-1149.1135, device='cuda:0')
episode: 37 training return: tensor(-1144.2302, device='cuda:0')
episode: 38 training return: tensor(-1126.1316, device='cuda:0')
episode: 39 training return: tensor(-1143.6252, device='cuda:0')
epoch: 10 test_true_pfm: -1.7344168260508759
episode: 40 training return: tensor(-1158.2767, device='cuda:0')
episode: 41 training return: tensor(-1149.1992, device='cuda:0')
episode: 42 training return: tensor(-1138.6873, device='cuda:0')
episode: 43 training return: tensor(-1154.7454, device='cuda:0')
epoch: 11 test_true_pfm: -1.788491379964693
episode: 44 training return: tensor(-1139.0271, device='cuda:0')
episode: 45 training return: tensor(-1141.6249, device='cuda:0')
episode: 46 training return: tensor(-1163.1521, device='cuda:0')
episode: 47 training return: tensor(-1146.5964, device='cuda:0')
epoch: 12 test_true_pfm: -1.3306387770026173
episode: 48 training return: tensor(-1149.3391, device='cuda:0')
episode: 49 training return: tensor(-1148.2065, device='cuda:0')
episode: 50 training return: tensor(-1154.3994, device='cuda:0')
episode: 51 training return: tensor(-1141.1058, device='cuda:0')
epoch: 13 test_true_pfm: -1.425474595483026
episode: 52 training return: tensor(-1136.6721, device='cuda:0')
episode: 53 training return: tensor(-1134.2759, device='cuda:0')
episode: 54 training return: tensor(-1117.0217, device='cuda:0')
episode: 55 training return: tensor(-1132.8243, device='cuda:0')
epoch: 14 test_true_pfm: -1.8314798463998205
episode: 56 training return: tensor(-1134.3490, device='cuda:0')
episode: 57 training return: tensor(-1141.3229, device='cuda:0')
episode: 58 training return: tensor(-1141.0718, device='cuda:0')
episode: 59 training return: tensor(-1133.2845, device='cuda:0')
epoch: 15 test_true_pfm: -1.9353272737273814
episode: 60 training return: tensor(-1140.4678, device='cuda:0')
episode: 61 training return: tensor(-1138.4858, device='cuda:0')
episode: 62 training return: tensor(-1140.5105, device='cuda:0')
episode: 63 training return: tensor(-1140.3684, device='cuda:0')
epoch: 16 test_true_pfm: -2.5103802213013577
episode: 64 training return: tensor(-1135.5055, device='cuda:0')
episode: 65 training return: tensor(-1115.1094, device='cuda:0')
episode: 66 training return: tensor(-1125.3108, device='cuda:0')
episode: 67 training return: tensor(-1158.0396, device='cuda:0')
epoch: 17 test_true_pfm: -1.4509857253375198
episode: 68 training return: tensor(-1124.4501, device='cuda:0')
episode: 69 training return: tensor(-1141.6550, device='cuda:0')
episode: 70 training return: tensor(-1148.9156, device='cuda:0')
episode: 71 training return: tensor(-1144.6875, device='cuda:0')
epoch: 18 test_true_pfm: -2.388720900763957
episode: 72 training return: tensor(-1138.0137, device='cuda:0')
episode: 73 training return: tensor(-1134.7350, device='cuda:0')
episode: 74 training return: tensor(-1141.9690, device='cuda:0')
episode: 75 training return: tensor(-1153.7216, device='cuda:0')
epoch: 19 test_true_pfm: -2.200662928301259
episode: 76 training return: tensor(-1123.9576, device='cuda:0')
episode: 77 training return: tensor(-1143.6602, device='cuda:0')
episode: 78 training return: tensor(-1133.9716, device='cuda:0')
episode: 79 training return: tensor(-1127.1107, device='cuda:0')
epoch: 20 test_true_pfm: -1.9798480896036779
episode: 80 training return: tensor(-1131.4202, device='cuda:0')
episode: 81 training return: tensor(-1126.9359, device='cuda:0')
episode: 82 training return: tensor(-1133.3654, device='cuda:0')
episode: 83 training return: tensor(-1127.5538, device='cuda:0')
epoch: 21 test_true_pfm: -0.8280069015866434
episode: 84 training return: tensor(-1142.7692, device='cuda:0')
episode: 85 training return: tensor(-1129.5364, device='cuda:0')
episode: 86 training return: tensor(-1128.1691, device='cuda:0')
episode: 87 training return: tensor(-1139.9460, device='cuda:0')
epoch: 22 test_true_pfm: -2.5418196883700395
episode: 88 training return: tensor(-1138.3235, device='cuda:0')
episode: 89 training return: tensor(-1140.2063, device='cuda:0')
episode: 90 training return: tensor(-1144.5010, device='cuda:0')
episode: 91 training return: tensor(-1140.4447, device='cuda:0')
epoch: 23 test_true_pfm: -2.761431217264825
episode: 92 training return: tensor(-1140.6582, device='cuda:0')
episode: 93 training return: tensor(-1137.9493, device='cuda:0')
episode: 94 training return: tensor(-1148.3545, device='cuda:0')
episode: 95 training return: tensor(-1135.4171, device='cuda:0')
epoch: 24 test_true_pfm: -3.242416570369022
episode: 96 training return: tensor(-1148.9347, device='cuda:0')
episode: 97 training return: tensor(-1131.3048, device='cuda:0')
episode: 98 training return: tensor(-1146.0192, device='cuda:0')
episode: 99 training return: tensor(-1138.1066, device='cuda:0')
epoch: 25 test_true_pfm: -3.241075514533307
episode: 100 training return: tensor(-1130.1541, device='cuda:0')
episode: 101 training return: tensor(-1134.7415, device='cuda:0')
episode: 102 training return: tensor(-1148.6234, device='cuda:0')
episode: 103 training return: tensor(-1138.5081, device='cuda:0')
epoch: 26 test_true_pfm: -2.5900723305706013
episode: 104 training return: tensor(-1139.4907, device='cuda:0')
episode: 105 training return: tensor(-1125.2256, device='cuda:0')
episode: 106 training return: tensor(-1134.8043, device='cuda:0')
episode: 107 training return: tensor(-1139.8722, device='cuda:0')
epoch: 27 test_true_pfm: -1.7660780221342358
episode: 108 training return: tensor(-1136.1069, device='cuda:0')
episode: 109 training return: tensor(-1137.6637, device='cuda:0')
episode: 110 training return: tensor(-1134.8245, device='cuda:0')
episode: 111 training return: tensor(-1147.5931, device='cuda:0')
epoch: 28 test_true_pfm: -1.8186521265638111
episode: 112 training return: tensor(-1146.4059, device='cuda:0')
episode: 113 training return: tensor(-1144.2974, device='cuda:0')
episode: 114 training return: tensor(-1127.0448, device='cuda:0')
episode: 115 training return: tensor(-1135.7244, device='cuda:0')
epoch: 29 test_true_pfm: -2.9713703800143154
episode: 116 training return: tensor(-1140.3499, device='cuda:0')
episode: 117 training return: tensor(-1135.4055, device='cuda:0')
episode: 118 training return: tensor(-1121.0085, device='cuda:0')
episode: 119 training return: tensor(-1141.3657, device='cuda:0')
epoch: 30 test_true_pfm: -2.619428079521209
episode: 120 training return: tensor(-1125.8215, device='cuda:0')
episode: 121 training return: tensor(-1123.5525, device='cuda:0')
episode: 122 training return: tensor(-1152.5964, device='cuda:0')
episode: 123 training return: tensor(-1135.3527, device='cuda:0')
epoch: 31 test_true_pfm: -3.8758368315425016
episode: 124 training return: tensor(-1135.6387, device='cuda:0')
episode: 125 training return: tensor(-1118.5836, device='cuda:0')
episode: 126 training return: tensor(-1128.4525, device='cuda:0')
episode: 127 training return: tensor(-1136.7513, device='cuda:0')
epoch: 32 test_true_pfm: -2.3460516618630236
episode: 128 training return: tensor(-1130.2133, device='cuda:0')
episode: 129 training return: tensor(-1154.2767, device='cuda:0')
episode: 130 training return: tensor(-1128.3759, device='cuda:0')
episode: 131 training return: tensor(-1142.3212, device='cuda:0')
epoch: 33 test_true_pfm: -2.600586674887577
episode: 132 training return: tensor(-1124.0543, device='cuda:0')
episode: 133 training return: tensor(-1118.3563, device='cuda:0')
episode: 134 training return: tensor(-1138.5842, device='cuda:0')
episode: 135 training return: tensor(-1139.2214, device='cuda:0')
epoch: 34 test_true_pfm: -3.1479088541672957
episode: 136 training return: tensor(-1130.0856, device='cuda:0')
episode: 137 training return: tensor(-1139.1737, device='cuda:0')
episode: 138 training return: tensor(-1124.4673, device='cuda:0')
episode: 139 training return: tensor(-1135.9612, device='cuda:0')
epoch: 35 test_true_pfm: -2.290163985677548
episode: 140 training return: tensor(-1130.3569, device='cuda:0')
episode: 141 training return: tensor(-1131.1410, device='cuda:0')
episode: 142 training return: tensor(-1127.3483, device='cuda:0')
episode: 143 training return: tensor(-1124.8002, device='cuda:0')
epoch: 36 test_true_pfm: -3.185506605208499
episode: 144 training return: tensor(-1129.5623, device='cuda:0')
episode: 145 training return: tensor(-1122.3372, device='cuda:0')
episode: 146 training return: tensor(-1134.6173, device='cuda:0')
episode: 147 training return: tensor(-1118.8840, device='cuda:0')
epoch: 37 test_true_pfm: -2.0297095144709996
episode: 148 training return: tensor(-1124.7739, device='cuda:0')
episode: 149 training return: tensor(-1129.7819, device='cuda:0')
episode: 150 training return: tensor(-1115.5376, device='cuda:0')
episode: 151 training return: tensor(-1137.6448, device='cuda:0')
epoch: 38 test_true_pfm: -1.7280910469782154
episode: 152 training return: tensor(-1127.3079, device='cuda:0')
episode: 153 training return: tensor(-1134.6642, device='cuda:0')
episode: 154 training return: tensor(-1130.3838, device='cuda:0')
episode: 155 training return: tensor(-1129.2629, device='cuda:0')
epoch: 39 test_true_pfm: -2.2937409625658285
episode: 156 training return: tensor(-1132.2239, device='cuda:0')
episode: 157 training return: tensor(-1130.2125, device='cuda:0')
episode: 158 training return: tensor(-1135.5001, device='cuda:0')
episode: 159 training return: tensor(-1127.7625, device='cuda:0')
epoch: 40 test_true_pfm: -3.061740010764342
episode: 160 training return: tensor(-1139.2594, device='cuda:0')
episode: 161 training return: tensor(-1137.0906, device='cuda:0')
episode: 162 training return: tensor(-1129.8319, device='cuda:0')
episode: 163 training return: tensor(-1126.1394, device='cuda:0')
epoch: 41 test_true_pfm: -2.782894730902532
episode: 164 training return: tensor(-1123.5905, device='cuda:0')
episode: 165 training return: tensor(-1148.8291, device='cuda:0')
episode: 166 training return: tensor(-1120.9973, device='cuda:0')
episode: 167 training return: tensor(-1116.0248, device='cuda:0')
epoch: 42 test_true_pfm: -3.105405305626148
episode: 168 training return: tensor(-1123.3398, device='cuda:0')
episode: 169 training return: tensor(-1133.5215, device='cuda:0')
episode: 170 training return: tensor(-1134.1963, device='cuda:0')
episode: 171 training return: tensor(-1122.1821, device='cuda:0')
epoch: 43 test_true_pfm: -2.180121413312118
episode: 172 training return: tensor(-1118.1571, device='cuda:0')
episode: 173 training return: tensor(-1125.4932, device='cuda:0')
episode: 174 training return: tensor(-1123.4551, device='cuda:0')
episode: 175 training return: tensor(-1136.8474, device='cuda:0')
epoch: 44 test_true_pfm: -2.119168332805769
episode: 176 training return: tensor(-1127.2478, device='cuda:0')
episode: 177 training return: tensor(-1120.0958, device='cuda:0')
episode: 178 training return: tensor(-1130.2468, device='cuda:0')
episode: 179 training return: tensor(-1120.2517, device='cuda:0')
epoch: 45 test_true_pfm: -3.0166195012951516
episode: 180 training return: tensor(-1128.0317, device='cuda:0')
episode: 181 training return: tensor(-1124.0964, device='cuda:0')
episode: 182 training return: tensor(-1116.3274, device='cuda:0')
episode: 183 training return: tensor(-1130.5955, device='cuda:0')
epoch: 46 test_true_pfm: -1.715624236443231
episode: 184 training return: tensor(-1137.7788, device='cuda:0')
episode: 185 training return: tensor(-1138.3763, device='cuda:0')
episode: 186 training return: tensor(-1132.8920, device='cuda:0')
episode: 187 training return: tensor(-1124.8561, device='cuda:0')
epoch: 47 test_true_pfm: -1.5713098602303124
episode: 188 training return: tensor(-1141.1858, device='cuda:0')
episode: 189 training return: tensor(-1126.7795, device='cuda:0')
episode: 190 training return: tensor(-1127.4473, device='cuda:0')
episode: 191 training return: tensor(-1141.5109, device='cuda:0')
epoch: 48 test_true_pfm: -2.4092706881247703
episode: 192 training return: tensor(-1119.1219, device='cuda:0')
episode: 193 training return: tensor(-1152.5825, device='cuda:0')
episode: 194 training return: tensor(-1120.1136, device='cuda:0')
episode: 195 training return: tensor(-1122.5096, device='cuda:0')
epoch: 49 test_true_pfm: -2.4167219011253382
episode: 196 training return: tensor(-1114.3093, device='cuda:0')
episode: 197 training return: tensor(-1122.9713, device='cuda:0')
episode: 198 training return: tensor(-1130.7416, device='cuda:0')
episode: 199 training return: tensor(-1118.8677, device='cuda:0')
epoch: 50 test_true_pfm: -2.0864539053059654
episode: 200 training return: tensor(-1125.7549, device='cuda:0')
episode: 201 training return: tensor(-1130.2458, device='cuda:0')
episode: 202 training return: tensor(-1139.6252, device='cuda:0')
episode: 203 training return: tensor(-1126.9296, device='cuda:0')
epoch: 51 test_true_pfm: -2.365096815777988
episode: 204 training return: tensor(-1128.7072, device='cuda:0')
episode: 205 training return: tensor(-1146.6206, device='cuda:0')
episode: 206 training return: tensor(-1118.7283, device='cuda:0')
episode: 207 training return: tensor(-1136.0906, device='cuda:0')
epoch: 52 test_true_pfm: -2.91809777436954
episode: 208 training return: tensor(-1128.0199, device='cuda:0')
episode: 209 training return: tensor(-1144.0421, device='cuda:0')
episode: 210 training return: tensor(-1138.0758, device='cuda:0')
episode: 211 training return: tensor(-1124.6343, device='cuda:0')
epoch: 53 test_true_pfm: -2.060140702807695
episode: 212 training return: tensor(-1132.1597, device='cuda:0')
episode: 213 training return: tensor(-1128.5250, device='cuda:0')
episode: 214 training return: tensor(-1129.8938, device='cuda:0')
episode: 215 training return: tensor(-1121.0370, device='cuda:0')
epoch: 54 test_true_pfm: -1.8533857475450908
episode: 216 training return: tensor(-1131.9883, device='cuda:0')
episode: 217 training return: tensor(-1128.7129, device='cuda:0')
episode: 218 training return: tensor(-1124.7583, device='cuda:0')
episode: 219 training return: tensor(-1138.8622, device='cuda:0')
epoch: 55 test_true_pfm: -2.441908664360454
episode: 220 training return: tensor(-1128.9373, device='cuda:0')
episode: 221 training return: tensor(-1143.7267, device='cuda:0')
episode: 222 training return: tensor(-1121.3810, device='cuda:0')
episode: 223 training return: tensor(-1132.6873, device='cuda:0')
epoch: 56 test_true_pfm: -2.144705307505563
episode: 224 training return: tensor(-1122.2830, device='cuda:0')
episode: 225 training return: tensor(-1119.7797, device='cuda:0')
episode: 226 training return: tensor(-1121.7620, device='cuda:0')
episode: 227 training return: tensor(-1125.7922, device='cuda:0')
epoch: 57 test_true_pfm: -1.6643494245019117
episode: 228 training return: tensor(-1133.1287, device='cuda:0')
episode: 229 training return: tensor(-1117.7117, device='cuda:0')
episode: 230 training return: tensor(-1126.2673, device='cuda:0')
episode: 231 training return: tensor(-1131.9556, device='cuda:0')
epoch: 58 test_true_pfm: -1.6073567581288277
episode: 232 training return: tensor(-1123.6096, device='cuda:0')
episode: 233 training return: tensor(-1123.5006, device='cuda:0')
episode: 234 training return: tensor(-1124.0671, device='cuda:0')
episode: 235 training return: tensor(-1135.4785, device='cuda:0')
epoch: 59 test_true_pfm: -1.7415493437086014
episode: 236 training return: tensor(-1165.1625, device='cuda:0')
episode: 237 training return: tensor(-1125.3788, device='cuda:0')
episode: 238 training return: tensor(-1123.4006, device='cuda:0')
episode: 239 training return: tensor(-1126.4602, device='cuda:0')
epoch: 60 test_true_pfm: -1.5147256756338636
episode: 240 training return: tensor(-1130.0696, device='cuda:0')
episode: 241 training return: tensor(-1124.8287, device='cuda:0')
episode: 242 training return: tensor(-1123.1869, device='cuda:0')
episode: 243 training return: tensor(-1118.1271, device='cuda:0')
epoch: 61 test_true_pfm: -3.2390400925982905
episode: 244 training return: tensor(-1140.0272, device='cuda:0')
episode: 245 training return: tensor(-1131.4225, device='cuda:0')
episode: 246 training return: tensor(-1121.6382, device='cuda:0')
episode: 247 training return: tensor(-1119.6100, device='cuda:0')
epoch: 62 test_true_pfm: -1.1553975801331957
episode: 248 training return: tensor(-1129.9958, device='cuda:0')
episode: 249 training return: tensor(-1118.0356, device='cuda:0')
episode: 250 training return: tensor(-1128.6562, device='cuda:0')
episode: 251 training return: tensor(-1123.1938, device='cuda:0')
epoch: 63 test_true_pfm: -1.1819454493874113
episode: 252 training return: tensor(-1122.8975, device='cuda:0')
episode: 253 training return: tensor(-1135.0796, device='cuda:0')
episode: 254 training return: tensor(-1126.2463, device='cuda:0')
episode: 255 training return: tensor(-1138.4333, device='cuda:0')
epoch: 64 test_true_pfm: -1.5956811584621338
episode: 256 training return: tensor(-1133.8202, device='cuda:0')
episode: 257 training return: tensor(-1123.9972, device='cuda:0')
episode: 258 training return: tensor(-1124.9956, device='cuda:0')
episode: 259 training return: tensor(-1121.1031, device='cuda:0')
epoch: 65 test_true_pfm: -1.20515938857248
episode: 260 training return: tensor(-1173.1776, device='cuda:0')
episode: 261 training return: tensor(-1126.8677, device='cuda:0')
episode: 262 training return: tensor(-1119.7380, device='cuda:0')
episode: 263 training return: tensor(-1119.0490, device='cuda:0')
epoch: 66 test_true_pfm: -2.3970467197094396
episode: 264 training return: tensor(-1118.6132, device='cuda:0')
episode: 265 training return: tensor(-1114.5583, device='cuda:0')
episode: 266 training return: tensor(-1121.1815, device='cuda:0')
episode: 267 training return: tensor(-1125.5104, device='cuda:0')
epoch: 67 test_true_pfm: -1.3361033901430577
episode: 268 training return: tensor(-1119.8319, device='cuda:0')
episode: 269 training return: tensor(-1134.6641, device='cuda:0')
episode: 270 training return: tensor(-1131.9702, device='cuda:0')
episode: 271 training return: tensor(-1133.3578, device='cuda:0')
epoch: 68 test_true_pfm: -1.9755005793493587
episode: 272 training return: tensor(-1134.2556, device='cuda:0')
episode: 273 training return: tensor(-1123.8224, device='cuda:0')
episode: 274 training return: tensor(-1125.4185, device='cuda:0')
episode: 275 training return: tensor(-1125.7699, device='cuda:0')
epoch: 69 test_true_pfm: -1.8199100339460943
episode: 276 training return: tensor(-1126.1333, device='cuda:0')
episode: 277 training return: tensor(-1129.4224, device='cuda:0')
episode: 278 training return: tensor(-1136.3618, device='cuda:0')
episode: 279 training return: tensor(-1128.1373, device='cuda:0')
epoch: 70 test_true_pfm: -2.065505923968004
episode: 280 training return: tensor(-1123.9698, device='cuda:0')
episode: 281 training return: tensor(-1131.1107, device='cuda:0')
episode: 282 training return: tensor(-1113.5668, device='cuda:0')
episode: 283 training return: tensor(-1125.0673, device='cuda:0')
epoch: 71 test_true_pfm: -2.3206561349138863
episode: 284 training return: tensor(-1124.1980, device='cuda:0')
episode: 285 training return: tensor(-1131.5448, device='cuda:0')
episode: 286 training return: tensor(-1129.2074, device='cuda:0')
