diff --git "a/trainer_state.json" "b/trainer_state.json" new file mode 100644--- /dev/null +++ "b/trainer_state.json" @@ -0,0 +1,15211 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 0.4999506172839506, + "global_step": 2531, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.0, + "learning_rate": 1.3157894736842104e-05, + "loss": 5.9854, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 2.631578947368421e-05, + "loss": 6.1201, + "step": 2 + }, + { + "epoch": 0.0, + "learning_rate": 3.9473684210526316e-05, + "loss": 5.2456, + "step": 3 + }, + { + "epoch": 0.0, + "learning_rate": 5.263157894736842e-05, + "loss": 4.261, + "step": 4 + }, + { + "epoch": 0.0, + "learning_rate": 6.578947368421052e-05, + "loss": 4.8225, + "step": 5 + }, + { + "epoch": 0.0, + "learning_rate": 7.894736842105263e-05, + "loss": 5.0859, + "step": 6 + }, + { + "epoch": 0.0, + "learning_rate": 9.210526315789474e-05, + "loss": 5.6763, + "step": 7 + }, + { + "epoch": 0.0, + "learning_rate": 0.00010526315789473683, + "loss": 4.7131, + "step": 8 + }, + { + "epoch": 0.0, + "learning_rate": 0.00011842105263157894, + "loss": 4.0515, + "step": 9 + }, + { + "epoch": 0.0, + "learning_rate": 0.00013157894736842105, + "loss": 3.791, + "step": 10 + }, + { + "epoch": 0.0, + "learning_rate": 0.00014473684210526317, + "loss": 3.7837, + "step": 11 + }, + { + "epoch": 0.0, + "learning_rate": 0.00015789473684210527, + "loss": 3.8374, + "step": 12 + }, + { + "epoch": 0.0, + "learning_rate": 0.00017105263157894739, + "loss": 3.7864, + "step": 13 + }, + { + "epoch": 0.0, + "learning_rate": 0.00018421052631578948, + "loss": 3.584, + "step": 14 + }, + { + "epoch": 0.0, + "learning_rate": 0.00019736842105263157, + "loss": 3.3264, + "step": 15 + }, + { + "epoch": 0.0, + "learning_rate": 0.00021052631578947367, + "loss": 3.1978, + "step": 16 + }, + { + "epoch": 0.0, + "learning_rate": 0.0002236842105263158, + "loss": 3.0579, + "step": 17 + }, + { + "epoch": 0.0, + "learning_rate": 0.00023684210526315788, + "loss": 2.9917, + "step": 18 + }, + { + "epoch": 0.0, + "learning_rate": 0.00025, + "loss": 2.8823, + "step": 19 + }, + { + "epoch": 0.0, + "learning_rate": 0.0002631578947368421, + "loss": 2.7537, + "step": 20 + }, + { + "epoch": 0.0, + "learning_rate": 0.00027631578947368425, + "loss": 2.5837, + "step": 21 + }, + { + "epoch": 0.0, + "learning_rate": 0.00028947368421052634, + "loss": 2.4653, + "step": 22 + }, + { + "epoch": 0.0, + "learning_rate": 0.00030263157894736844, + "loss": 2.3142, + "step": 23 + }, + { + "epoch": 0.0, + "learning_rate": 0.00031578947368421053, + "loss": 2.0485, + "step": 24 + }, + { + "epoch": 0.0, + "learning_rate": 0.0003289473684210527, + "loss": 1.7357, + "step": 25 + }, + { + "epoch": 0.01, + "learning_rate": 0.00034210526315789477, + "loss": 1.4006, + "step": 26 + }, + { + "epoch": 0.01, + "learning_rate": 0.00035526315789473687, + "loss": 1.1166, + "step": 27 + }, + { + "epoch": 0.01, + "learning_rate": 0.00036842105263157896, + "loss": 0.9081, + "step": 28 + }, + { + "epoch": 0.01, + "learning_rate": 0.00038157894736842105, + "loss": 0.7677, + "step": 29 + }, + { + "epoch": 0.01, + "learning_rate": 0.00039473684210526315, + "loss": 0.6236, + "step": 30 + }, + { + "epoch": 0.01, + "learning_rate": 0.00040789473684210524, + "loss": 0.5234, + "step": 31 + }, + { + "epoch": 0.01, + "learning_rate": 0.00042105263157894734, + "loss": 0.4273, + "step": 32 + }, + { + "epoch": 0.01, + "learning_rate": 0.0004342105263157895, + "loss": 0.3505, + "step": 33 + }, + { + "epoch": 0.01, + "learning_rate": 0.0004473684210526316, + "loss": 0.3178, + "step": 34 + }, + { + "epoch": 0.01, + "learning_rate": 0.0004605263157894737, + "loss": 0.2789, + "step": 35 + }, + { + "epoch": 0.01, + "learning_rate": 0.00047368421052631577, + "loss": 0.2599, + "step": 36 + }, + { + "epoch": 0.01, + "learning_rate": 0.0004868421052631579, + "loss": 0.2392, + "step": 37 + }, + { + "epoch": 0.01, + "learning_rate": 0.0005, + "loss": 0.2072, + "step": 38 + }, + { + "epoch": 0.01, + "learning_rate": 0.0005131578947368421, + "loss": 0.2049, + "step": 39 + }, + { + "epoch": 0.01, + "learning_rate": 0.0005263157894736842, + "loss": 0.1989, + "step": 40 + }, + { + "epoch": 0.01, + "learning_rate": 0.0005394736842105263, + "loss": 0.1869, + "step": 41 + }, + { + "epoch": 0.01, + "learning_rate": 0.0005526315789473685, + "loss": 0.1986, + "step": 42 + }, + { + "epoch": 0.01, + "learning_rate": 0.0005657894736842105, + "loss": 0.1924, + "step": 43 + }, + { + "epoch": 0.01, + "learning_rate": 0.0005789473684210527, + "loss": 0.1548, + "step": 44 + }, + { + "epoch": 0.01, + "learning_rate": 0.0005921052631578947, + "loss": 0.1706, + "step": 45 + }, + { + "epoch": 0.01, + "learning_rate": 0.0006052631578947369, + "loss": 0.1895, + "step": 46 + }, + { + "epoch": 0.01, + "learning_rate": 0.000618421052631579, + "loss": 0.1573, + "step": 47 + }, + { + "epoch": 0.01, + "learning_rate": 0.0006315789473684211, + "loss": 0.144, + "step": 48 + }, + { + "epoch": 0.01, + "learning_rate": 0.0006447368421052632, + "loss": 0.153, + "step": 49 + }, + { + "epoch": 0.01, + "learning_rate": 0.0006578947368421054, + "loss": 0.1599, + "step": 50 + }, + { + "epoch": 0.01, + "learning_rate": 0.0006710526315789473, + "loss": 0.1439, + "step": 51 + }, + { + "epoch": 0.01, + "learning_rate": 0.0006842105263157895, + "loss": 0.1413, + "step": 52 + }, + { + "epoch": 0.01, + "learning_rate": 0.0006973684210526315, + "loss": 0.1365, + "step": 53 + }, + { + "epoch": 0.01, + "learning_rate": 0.0007105263157894737, + "loss": 0.1452, + "step": 54 + }, + { + "epoch": 0.01, + "learning_rate": 0.0007236842105263158, + "loss": 0.1419, + "step": 55 + }, + { + "epoch": 0.01, + "learning_rate": 0.0007368421052631579, + "loss": 0.1406, + "step": 56 + }, + { + "epoch": 0.01, + "learning_rate": 0.00075, + "loss": 0.1416, + "step": 57 + }, + { + "epoch": 0.01, + "learning_rate": 0.0007631578947368421, + "loss": 0.14, + "step": 58 + }, + { + "epoch": 0.01, + "learning_rate": 0.0007763157894736842, + "loss": 0.1441, + "step": 59 + }, + { + "epoch": 0.01, + "learning_rate": 0.0007894736842105263, + "loss": 0.1332, + "step": 60 + }, + { + "epoch": 0.01, + "learning_rate": 0.0008026315789473685, + "loss": 0.1357, + "step": 61 + }, + { + "epoch": 0.01, + "learning_rate": 0.0008157894736842105, + "loss": 0.1266, + "step": 62 + }, + { + "epoch": 0.01, + "learning_rate": 0.0008289473684210527, + "loss": 0.1307, + "step": 63 + }, + { + "epoch": 0.01, + "learning_rate": 0.0008421052631578947, + "loss": 0.1331, + "step": 64 + }, + { + "epoch": 0.01, + "learning_rate": 0.0008552631578947369, + "loss": 0.135, + "step": 65 + }, + { + "epoch": 0.01, + "learning_rate": 0.000868421052631579, + "loss": 0.1286, + "step": 66 + }, + { + "epoch": 0.01, + "learning_rate": 0.0008815789473684211, + "loss": 0.1244, + "step": 67 + }, + { + "epoch": 0.01, + "learning_rate": 0.0008947368421052632, + "loss": 0.1275, + "step": 68 + }, + { + "epoch": 0.01, + "learning_rate": 0.0009078947368421054, + "loss": 0.1244, + "step": 69 + }, + { + "epoch": 0.01, + "learning_rate": 0.0009210526315789473, + "loss": 0.1233, + "step": 70 + }, + { + "epoch": 0.01, + "learning_rate": 0.0009342105263157896, + "loss": 0.1264, + "step": 71 + }, + { + "epoch": 0.01, + "learning_rate": 0.0009473684210526315, + "loss": 0.1223, + "step": 72 + }, + { + "epoch": 0.01, + "learning_rate": 0.0009605263157894737, + "loss": 0.1285, + "step": 73 + }, + { + "epoch": 0.01, + "learning_rate": 0.0009736842105263158, + "loss": 0.1221, + "step": 74 + }, + { + "epoch": 0.01, + "learning_rate": 0.000986842105263158, + "loss": 0.1254, + "step": 75 + }, + { + "epoch": 0.02, + "learning_rate": 0.001, + "loss": 0.1248, + "step": 76 + }, + { + "epoch": 0.02, + "learning_rate": 0.000999999590610498, + "loss": 0.1181, + "step": 77 + }, + { + "epoch": 0.02, + "learning_rate": 0.0009999983624426622, + "loss": 0.1217, + "step": 78 + }, + { + "epoch": 0.02, + "learning_rate": 0.000999996315498504, + "loss": 0.1167, + "step": 79 + }, + { + "epoch": 0.02, + "learning_rate": 0.0009999934497813754, + "loss": 0.1181, + "step": 80 + }, + { + "epoch": 0.02, + "learning_rate": 0.000999989765295969, + "loss": 0.1181, + "step": 81 + }, + { + "epoch": 0.02, + "learning_rate": 0.0009999852620483183, + "loss": 0.1163, + "step": 82 + }, + { + "epoch": 0.02, + "learning_rate": 0.0009999799400457977, + "loss": 0.1186, + "step": 83 + }, + { + "epoch": 0.02, + "learning_rate": 0.0009999737992971226, + "loss": 0.1168, + "step": 84 + }, + { + "epoch": 0.02, + "learning_rate": 0.0009999668398123483, + "loss": 0.1151, + "step": 85 + }, + { + "epoch": 0.02, + "learning_rate": 0.0009999590616028718, + "loss": 0.1134, + "step": 86 + }, + { + "epoch": 0.02, + "learning_rate": 0.0009999504646814302, + "loss": 0.1134, + "step": 87 + }, + { + "epoch": 0.02, + "learning_rate": 0.0009999410490621015, + "loss": 0.114, + "step": 88 + }, + { + "epoch": 0.02, + "learning_rate": 0.0009999308147603044, + "loss": 0.1152, + "step": 89 + }, + { + "epoch": 0.02, + "learning_rate": 0.0009999197617927978, + "loss": 0.1184, + "step": 90 + }, + { + "epoch": 0.02, + "learning_rate": 0.000999907890177682, + "loss": 0.1139, + "step": 91 + }, + { + "epoch": 0.02, + "learning_rate": 0.0009998951999343972, + "loss": 0.1158, + "step": 92 + }, + { + "epoch": 0.02, + "learning_rate": 0.0009998816910837245, + "loss": 0.1132, + "step": 93 + }, + { + "epoch": 0.02, + "learning_rate": 0.0009998673636477855, + "loss": 0.1112, + "step": 94 + }, + { + "epoch": 0.02, + "learning_rate": 0.0009998522176500422, + "loss": 0.1134, + "step": 95 + }, + { + "epoch": 0.02, + "learning_rate": 0.0009998362531152968, + "loss": 0.1136, + "step": 96 + }, + { + "epoch": 0.02, + "learning_rate": 0.0009998194700696923, + "loss": 0.1109, + "step": 97 + }, + { + "epoch": 0.02, + "learning_rate": 0.000999801868540712, + "loss": 0.1143, + "step": 98 + }, + { + "epoch": 0.02, + "learning_rate": 0.0009997834485571794, + "loss": 0.1089, + "step": 99 + }, + { + "epoch": 0.02, + "learning_rate": 0.0009997642101492582, + "loss": 0.1129, + "step": 100 + }, + { + "epoch": 0.02, + "learning_rate": 0.0009997441533484528, + "loss": 0.1084, + "step": 101 + }, + { + "epoch": 0.02, + "learning_rate": 0.0009997232781876067, + "loss": 0.11, + "step": 102 + }, + { + "epoch": 0.02, + "learning_rate": 0.0009997015847009046, + "loss": 0.1084, + "step": 103 + }, + { + "epoch": 0.02, + "learning_rate": 0.0009996790729238708, + "loss": 0.1102, + "step": 104 + }, + { + "epoch": 0.02, + "learning_rate": 0.0009996557428933696, + "loss": 0.1083, + "step": 105 + }, + { + "epoch": 0.02, + "learning_rate": 0.0009996315946476054, + "loss": 0.1099, + "step": 106 + }, + { + "epoch": 0.02, + "learning_rate": 0.000999606628226122, + "loss": 0.1108, + "step": 107 + }, + { + "epoch": 0.02, + "learning_rate": 0.0009995808436698036, + "loss": 0.1135, + "step": 108 + }, + { + "epoch": 0.02, + "learning_rate": 0.0009995542410208742, + "loss": 0.1103, + "step": 109 + }, + { + "epoch": 0.02, + "learning_rate": 0.0009995268203228968, + "loss": 0.1098, + "step": 110 + }, + { + "epoch": 0.02, + "learning_rate": 0.0009994985816207745, + "loss": 0.1126, + "step": 111 + }, + { + "epoch": 0.02, + "learning_rate": 0.0009994695249607496, + "loss": 0.1076, + "step": 112 + }, + { + "epoch": 0.02, + "learning_rate": 0.0009994396503904045, + "loss": 0.1095, + "step": 113 + }, + { + "epoch": 0.02, + "learning_rate": 0.0009994089579586601, + "loss": 0.1116, + "step": 114 + }, + { + "epoch": 0.02, + "learning_rate": 0.0009993774477157773, + "loss": 0.1137, + "step": 115 + }, + { + "epoch": 0.02, + "learning_rate": 0.0009993451197133558, + "loss": 0.1104, + "step": 116 + }, + { + "epoch": 0.02, + "learning_rate": 0.0009993119740043348, + "loss": 0.1108, + "step": 117 + }, + { + "epoch": 0.02, + "learning_rate": 0.0009992780106429923, + "loss": 0.1092, + "step": 118 + }, + { + "epoch": 0.02, + "learning_rate": 0.000999243229684945, + "loss": 0.1098, + "step": 119 + }, + { + "epoch": 0.02, + "learning_rate": 0.000999207631187149, + "loss": 0.112, + "step": 120 + }, + { + "epoch": 0.02, + "learning_rate": 0.0009991712152078987, + "loss": 0.1094, + "step": 121 + }, + { + "epoch": 0.02, + "learning_rate": 0.0009991339818068274, + "loss": 0.1109, + "step": 122 + }, + { + "epoch": 0.02, + "learning_rate": 0.0009990959310449072, + "loss": 0.1125, + "step": 123 + }, + { + "epoch": 0.02, + "learning_rate": 0.0009990570629844482, + "loss": 0.1116, + "step": 124 + }, + { + "epoch": 0.02, + "learning_rate": 0.0009990173776890992, + "loss": 0.1093, + "step": 125 + }, + { + "epoch": 0.02, + "learning_rate": 0.0009989768752238471, + "loss": 0.1081, + "step": 126 + }, + { + "epoch": 0.03, + "learning_rate": 0.0009989355556550173, + "loss": 0.1074, + "step": 127 + }, + { + "epoch": 0.03, + "learning_rate": 0.0009988934190502726, + "loss": 0.1086, + "step": 128 + }, + { + "epoch": 0.03, + "learning_rate": 0.0009988504654786141, + "loss": 0.1075, + "step": 129 + }, + { + "epoch": 0.03, + "learning_rate": 0.0009988066950103811, + "loss": 0.1094, + "step": 130 + }, + { + "epoch": 0.03, + "learning_rate": 0.0009987621077172503, + "loss": 0.1079, + "step": 131 + }, + { + "epoch": 0.03, + "learning_rate": 0.0009987167036722357, + "loss": 0.107, + "step": 132 + }, + { + "epoch": 0.03, + "learning_rate": 0.0009986704829496893, + "loss": 0.1068, + "step": 133 + }, + { + "epoch": 0.03, + "learning_rate": 0.0009986234456253, + "loss": 0.1071, + "step": 134 + }, + { + "epoch": 0.03, + "learning_rate": 0.0009985755917760943, + "loss": 0.1091, + "step": 135 + }, + { + "epoch": 0.03, + "learning_rate": 0.0009985269214804356, + "loss": 0.1076, + "step": 136 + }, + { + "epoch": 0.03, + "learning_rate": 0.0009984774348180245, + "loss": 0.1087, + "step": 137 + }, + { + "epoch": 0.03, + "learning_rate": 0.000998427131869898, + "loss": 0.1093, + "step": 138 + }, + { + "epoch": 0.03, + "learning_rate": 0.00099837601271843, + "loss": 0.1138, + "step": 139 + }, + { + "epoch": 0.03, + "learning_rate": 0.0009983240774473314, + "loss": 0.1064, + "step": 140 + }, + { + "epoch": 0.03, + "learning_rate": 0.000998271326141649, + "loss": 0.1102, + "step": 141 + }, + { + "epoch": 0.03, + "learning_rate": 0.0009982177588877665, + "loss": 0.111, + "step": 142 + }, + { + "epoch": 0.03, + "learning_rate": 0.000998163375773403, + "loss": 0.1092, + "step": 143 + }, + { + "epoch": 0.03, + "learning_rate": 0.0009981081768876143, + "loss": 0.1062, + "step": 144 + }, + { + "epoch": 0.03, + "learning_rate": 0.0009980521623207915, + "loss": 0.111, + "step": 145 + }, + { + "epoch": 0.03, + "learning_rate": 0.0009979953321646614, + "loss": 0.111, + "step": 146 + }, + { + "epoch": 0.03, + "learning_rate": 0.0009979376865122875, + "loss": 0.1077, + "step": 147 + }, + { + "epoch": 0.03, + "learning_rate": 0.0009978792254580675, + "loss": 0.1069, + "step": 148 + }, + { + "epoch": 0.03, + "learning_rate": 0.0009978199490977345, + "loss": 0.1084, + "step": 149 + }, + { + "epoch": 0.03, + "learning_rate": 0.0009977598575283573, + "loss": 0.1068, + "step": 150 + }, + { + "epoch": 0.03, + "learning_rate": 0.0009976989508483393, + "loss": 0.1075, + "step": 151 + }, + { + "epoch": 0.03, + "learning_rate": 0.0009976372291574187, + "loss": 0.1098, + "step": 152 + }, + { + "epoch": 0.03, + "learning_rate": 0.0009975746925566685, + "loss": 0.106, + "step": 153 + }, + { + "epoch": 0.03, + "learning_rate": 0.0009975113411484955, + "loss": 0.1053, + "step": 154 + }, + { + "epoch": 0.03, + "learning_rate": 0.000997447175036642, + "loss": 0.1086, + "step": 155 + }, + { + "epoch": 0.03, + "learning_rate": 0.000997382194326183, + "loss": 0.1074, + "step": 156 + }, + { + "epoch": 0.03, + "learning_rate": 0.0009973163991235285, + "loss": 0.1062, + "step": 157 + }, + { + "epoch": 0.03, + "learning_rate": 0.0009972497895364223, + "loss": 0.1078, + "step": 158 + }, + { + "epoch": 0.03, + "learning_rate": 0.000997182365673941, + "loss": 0.1072, + "step": 159 + }, + { + "epoch": 0.03, + "learning_rate": 0.0009971141276464955, + "loss": 0.1098, + "step": 160 + }, + { + "epoch": 0.03, + "learning_rate": 0.0009970450755658292, + "loss": 0.1083, + "step": 161 + }, + { + "epoch": 0.03, + "learning_rate": 0.000996975209545019, + "loss": 0.1054, + "step": 162 + }, + { + "epoch": 0.03, + "learning_rate": 0.0009969045296984744, + "loss": 0.106, + "step": 163 + }, + { + "epoch": 0.03, + "learning_rate": 0.0009968330361419379, + "loss": 0.1072, + "step": 164 + }, + { + "epoch": 0.03, + "learning_rate": 0.0009967607289924844, + "loss": 0.106, + "step": 165 + }, + { + "epoch": 0.03, + "learning_rate": 0.000996687608368521, + "loss": 0.107, + "step": 166 + }, + { + "epoch": 0.03, + "learning_rate": 0.000996613674389787, + "loss": 0.1063, + "step": 167 + }, + { + "epoch": 0.03, + "learning_rate": 0.0009965389271773535, + "loss": 0.1078, + "step": 168 + }, + { + "epoch": 0.03, + "learning_rate": 0.0009964633668536234, + "loss": 0.1047, + "step": 169 + }, + { + "epoch": 0.03, + "learning_rate": 0.000996386993542331, + "loss": 0.1054, + "step": 170 + }, + { + "epoch": 0.03, + "learning_rate": 0.0009963098073685424, + "loss": 0.1076, + "step": 171 + }, + { + "epoch": 0.03, + "learning_rate": 0.0009962318084586542, + "loss": 0.1072, + "step": 172 + }, + { + "epoch": 0.03, + "learning_rate": 0.0009961529969403939, + "loss": 0.108, + "step": 173 + }, + { + "epoch": 0.03, + "learning_rate": 0.0009960733729428204, + "loss": 0.1072, + "step": 174 + }, + { + "epoch": 0.03, + "learning_rate": 0.0009959929365963224, + "loss": 0.1061, + "step": 175 + }, + { + "epoch": 0.03, + "learning_rate": 0.000995911688032619, + "loss": 0.1073, + "step": 176 + }, + { + "epoch": 0.03, + "learning_rate": 0.0009958296273847595, + "loss": 0.1064, + "step": 177 + }, + { + "epoch": 0.04, + "learning_rate": 0.000995746754787123, + "loss": 0.1082, + "step": 178 + }, + { + "epoch": 0.04, + "learning_rate": 0.000995663070375418, + "loss": 0.1071, + "step": 179 + }, + { + "epoch": 0.04, + "learning_rate": 0.000995578574286683, + "loss": 0.1068, + "step": 180 + }, + { + "epoch": 0.04, + "learning_rate": 0.000995493266659285, + "loss": 0.1056, + "step": 181 + }, + { + "epoch": 0.04, + "learning_rate": 0.00099540714763292, + "loss": 0.1056, + "step": 182 + }, + { + "epoch": 0.04, + "learning_rate": 0.0009953202173486133, + "loss": 0.1085, + "step": 183 + }, + { + "epoch": 0.04, + "learning_rate": 0.000995232475948718, + "loss": 0.106, + "step": 184 + }, + { + "epoch": 0.04, + "learning_rate": 0.0009951439235769157, + "loss": 0.1038, + "step": 185 + }, + { + "epoch": 0.04, + "learning_rate": 0.0009950545603782163, + "loss": 0.1046, + "step": 186 + }, + { + "epoch": 0.04, + "learning_rate": 0.0009949643864989568, + "loss": 0.1073, + "step": 187 + }, + { + "epoch": 0.04, + "learning_rate": 0.0009948734020868027, + "loss": 0.1072, + "step": 188 + }, + { + "epoch": 0.04, + "learning_rate": 0.0009947816072907458, + "loss": 0.1063, + "step": 189 + }, + { + "epoch": 0.04, + "learning_rate": 0.0009946890022611058, + "loss": 0.1064, + "step": 190 + }, + { + "epoch": 0.04, + "learning_rate": 0.0009945955871495282, + "loss": 0.109, + "step": 191 + }, + { + "epoch": 0.04, + "learning_rate": 0.0009945013621089865, + "loss": 0.1061, + "step": 192 + }, + { + "epoch": 0.04, + "learning_rate": 0.0009944063272937789, + "loss": 0.1087, + "step": 193 + }, + { + "epoch": 0.04, + "learning_rate": 0.0009943104828595308, + "loss": 0.1056, + "step": 194 + }, + { + "epoch": 0.04, + "learning_rate": 0.000994213828963193, + "loss": 0.105, + "step": 195 + }, + { + "epoch": 0.04, + "learning_rate": 0.0009941163657630418, + "loss": 0.1051, + "step": 196 + }, + { + "epoch": 0.04, + "learning_rate": 0.0009940180934186792, + "loss": 0.1033, + "step": 197 + }, + { + "epoch": 0.04, + "learning_rate": 0.000993919012091031, + "loss": 0.1086, + "step": 198 + }, + { + "epoch": 0.04, + "learning_rate": 0.0009938191219423496, + "loss": 0.1066, + "step": 199 + }, + { + "epoch": 0.04, + "learning_rate": 0.00099371842313621, + "loss": 0.1036, + "step": 200 + }, + { + "epoch": 0.04, + "learning_rate": 0.0009936169158375131, + "loss": 0.1069, + "step": 201 + }, + { + "epoch": 0.04, + "learning_rate": 0.0009935146002124828, + "loss": 0.1076, + "step": 202 + }, + { + "epoch": 0.04, + "learning_rate": 0.0009934114764286667, + "loss": 0.106, + "step": 203 + }, + { + "epoch": 0.04, + "learning_rate": 0.000993307544654936, + "loss": 0.1088, + "step": 204 + }, + { + "epoch": 0.04, + "learning_rate": 0.000993202805061485, + "loss": 0.1061, + "step": 205 + }, + { + "epoch": 0.04, + "learning_rate": 0.000993097257819831, + "loss": 0.1047, + "step": 206 + }, + { + "epoch": 0.04, + "learning_rate": 0.0009929909031028137, + "loss": 0.1047, + "step": 207 + }, + { + "epoch": 0.04, + "learning_rate": 0.000992883741084595, + "loss": 0.1069, + "step": 208 + }, + { + "epoch": 0.04, + "learning_rate": 0.000992775771940659, + "loss": 0.1078, + "step": 209 + }, + { + "epoch": 0.04, + "learning_rate": 0.0009926669958478115, + "loss": 0.1071, + "step": 210 + }, + { + "epoch": 0.04, + "learning_rate": 0.0009925574129841792, + "loss": 0.1077, + "step": 211 + }, + { + "epoch": 0.04, + "learning_rate": 0.0009924470235292112, + "loss": 0.1075, + "step": 212 + }, + { + "epoch": 0.04, + "learning_rate": 0.000992335827663676, + "loss": 0.1066, + "step": 213 + }, + { + "epoch": 0.04, + "learning_rate": 0.0009922238255696636, + "loss": 0.1072, + "step": 214 + }, + { + "epoch": 0.04, + "learning_rate": 0.0009921110174305838, + "loss": 0.1059, + "step": 215 + }, + { + "epoch": 0.04, + "learning_rate": 0.0009919974034311666, + "loss": 0.1055, + "step": 216 + }, + { + "epoch": 0.04, + "learning_rate": 0.000991882983757461, + "loss": 0.1073, + "step": 217 + }, + { + "epoch": 0.04, + "learning_rate": 0.0009917677585968366, + "loss": 0.1118, + "step": 218 + }, + { + "epoch": 0.04, + "learning_rate": 0.000991651728137981, + "loss": 0.1044, + "step": 219 + }, + { + "epoch": 0.04, + "learning_rate": 0.0009915348925709005, + "loss": 0.1104, + "step": 220 + }, + { + "epoch": 0.04, + "learning_rate": 0.0009914172520869206, + "loss": 0.1077, + "step": 221 + }, + { + "epoch": 0.04, + "learning_rate": 0.0009912988068786841, + "loss": 0.1045, + "step": 222 + }, + { + "epoch": 0.04, + "learning_rate": 0.0009911795571401522, + "loss": 0.1056, + "step": 223 + }, + { + "epoch": 0.04, + "learning_rate": 0.0009910595030666026, + "loss": 0.1068, + "step": 224 + }, + { + "epoch": 0.04, + "learning_rate": 0.0009909386448546315, + "loss": 0.1047, + "step": 225 + }, + { + "epoch": 0.04, + "learning_rate": 0.000990816982702151, + "loss": 0.1057, + "step": 226 + }, + { + "epoch": 0.04, + "learning_rate": 0.0009906945168083898, + "loss": 0.1032, + "step": 227 + }, + { + "epoch": 0.05, + "learning_rate": 0.0009905712473738933, + "loss": 0.1083, + "step": 228 + }, + { + "epoch": 0.05, + "learning_rate": 0.000990447174600522, + "loss": 0.1086, + "step": 229 + }, + { + "epoch": 0.05, + "learning_rate": 0.0009903222986914523, + "loss": 0.1065, + "step": 230 + }, + { + "epoch": 0.05, + "learning_rate": 0.0009901966198511756, + "loss": 0.1055, + "step": 231 + }, + { + "epoch": 0.05, + "learning_rate": 0.0009900701382854987, + "loss": 0.1051, + "step": 232 + }, + { + "epoch": 0.05, + "learning_rate": 0.0009899428542015421, + "loss": 0.1051, + "step": 233 + }, + { + "epoch": 0.05, + "learning_rate": 0.0009898147678077413, + "loss": 0.1085, + "step": 234 + }, + { + "epoch": 0.05, + "learning_rate": 0.0009896858793138447, + "loss": 0.1059, + "step": 235 + }, + { + "epoch": 0.05, + "learning_rate": 0.0009895561889309151, + "loss": 0.1071, + "step": 236 + }, + { + "epoch": 0.05, + "learning_rate": 0.0009894256968713277, + "loss": 0.1034, + "step": 237 + }, + { + "epoch": 0.05, + "learning_rate": 0.0009892944033487712, + "loss": 0.1061, + "step": 238 + }, + { + "epoch": 0.05, + "learning_rate": 0.000989162308578246, + "loss": 0.1071, + "step": 239 + }, + { + "epoch": 0.05, + "learning_rate": 0.0009890294127760653, + "loss": 0.105, + "step": 240 + }, + { + "epoch": 0.05, + "learning_rate": 0.0009888957161598533, + "loss": 0.1052, + "step": 241 + }, + { + "epoch": 0.05, + "learning_rate": 0.000988761218948546, + "loss": 0.104, + "step": 242 + }, + { + "epoch": 0.05, + "learning_rate": 0.0009886259213623908, + "loss": 0.1041, + "step": 243 + }, + { + "epoch": 0.05, + "learning_rate": 0.0009884898236229447, + "loss": 0.1032, + "step": 244 + }, + { + "epoch": 0.05, + "learning_rate": 0.0009883529259530764, + "loss": 0.105, + "step": 245 + }, + { + "epoch": 0.05, + "learning_rate": 0.0009882152285769633, + "loss": 0.1058, + "step": 246 + }, + { + "epoch": 0.05, + "learning_rate": 0.0009880767317200928, + "loss": 0.1033, + "step": 247 + }, + { + "epoch": 0.05, + "learning_rate": 0.0009879374356092617, + "loss": 0.1043, + "step": 248 + }, + { + "epoch": 0.05, + "learning_rate": 0.0009877973404725754, + "loss": 0.1056, + "step": 249 + }, + { + "epoch": 0.05, + "learning_rate": 0.000987656446539448, + "loss": 0.1087, + "step": 250 + }, + { + "epoch": 0.05, + "learning_rate": 0.0009875147540406011, + "loss": 0.1045, + "step": 251 + }, + { + "epoch": 0.05, + "learning_rate": 0.0009873722632080648, + "loss": 0.106, + "step": 252 + }, + { + "epoch": 0.05, + "learning_rate": 0.0009872289742751759, + "loss": 0.1069, + "step": 253 + }, + { + "epoch": 0.05, + "learning_rate": 0.0009870848874765782, + "loss": 0.1041, + "step": 254 + }, + { + "epoch": 0.05, + "learning_rate": 0.0009869400030482224, + "loss": 0.1052, + "step": 255 + }, + { + "epoch": 0.05, + "learning_rate": 0.0009867943212273653, + "loss": 0.106, + "step": 256 + }, + { + "epoch": 0.05, + "learning_rate": 0.000986647842252569, + "loss": 0.108, + "step": 257 + }, + { + "epoch": 0.05, + "learning_rate": 0.0009865005663637013, + "loss": 0.1061, + "step": 258 + }, + { + "epoch": 0.05, + "learning_rate": 0.0009863524938019356, + "loss": 0.1059, + "step": 259 + }, + { + "epoch": 0.05, + "learning_rate": 0.0009862036248097484, + "loss": 0.105, + "step": 260 + }, + { + "epoch": 0.05, + "learning_rate": 0.000986053959630922, + "loss": 0.1069, + "step": 261 + }, + { + "epoch": 0.05, + "learning_rate": 0.0009859034985105414, + "loss": 0.104, + "step": 262 + }, + { + "epoch": 0.05, + "learning_rate": 0.000985752241694996, + "loss": 0.1069, + "step": 263 + }, + { + "epoch": 0.05, + "learning_rate": 0.0009856001894319772, + "loss": 0.1065, + "step": 264 + }, + { + "epoch": 0.05, + "learning_rate": 0.000985447341970479, + "loss": 0.1047, + "step": 265 + }, + { + "epoch": 0.05, + "learning_rate": 0.0009852936995607985, + "loss": 0.1065, + "step": 266 + }, + { + "epoch": 0.05, + "learning_rate": 0.0009851392624545343, + "loss": 0.1072, + "step": 267 + }, + { + "epoch": 0.05, + "learning_rate": 0.0009849840309045857, + "loss": 0.1065, + "step": 268 + }, + { + "epoch": 0.05, + "learning_rate": 0.0009848280051651533, + "loss": 0.1087, + "step": 269 + }, + { + "epoch": 0.05, + "learning_rate": 0.0009846711854917384, + "loss": 0.1069, + "step": 270 + }, + { + "epoch": 0.05, + "learning_rate": 0.0009845135721411424, + "loss": 0.1044, + "step": 271 + }, + { + "epoch": 0.05, + "learning_rate": 0.0009843551653714664, + "loss": 0.1052, + "step": 272 + }, + { + "epoch": 0.05, + "learning_rate": 0.0009841959654421104, + "loss": 0.1041, + "step": 273 + }, + { + "epoch": 0.05, + "learning_rate": 0.0009840359726137737, + "loss": 0.1043, + "step": 274 + }, + { + "epoch": 0.05, + "learning_rate": 0.000983875187148454, + "loss": 0.1042, + "step": 275 + }, + { + "epoch": 0.05, + "learning_rate": 0.0009837136093094464, + "loss": 0.1074, + "step": 276 + }, + { + "epoch": 0.05, + "learning_rate": 0.0009835512393613444, + "loss": 0.108, + "step": 277 + }, + { + "epoch": 0.05, + "learning_rate": 0.0009833880775700378, + "loss": 0.1042, + "step": 278 + }, + { + "epoch": 0.06, + "learning_rate": 0.0009832241242027139, + "loss": 0.1069, + "step": 279 + }, + { + "epoch": 0.06, + "learning_rate": 0.0009830593795278554, + "loss": 0.1053, + "step": 280 + }, + { + "epoch": 0.06, + "learning_rate": 0.0009828938438152417, + "loss": 0.1081, + "step": 281 + }, + { + "epoch": 0.06, + "learning_rate": 0.000982727517335947, + "loss": 0.1033, + "step": 282 + }, + { + "epoch": 0.06, + "learning_rate": 0.0009825604003623404, + "loss": 0.1056, + "step": 283 + }, + { + "epoch": 0.06, + "learning_rate": 0.000982392493168086, + "loss": 0.1056, + "step": 284 + }, + { + "epoch": 0.06, + "learning_rate": 0.0009822237960281411, + "loss": 0.1074, + "step": 285 + }, + { + "epoch": 0.06, + "learning_rate": 0.0009820543092187574, + "loss": 0.1068, + "step": 286 + }, + { + "epoch": 0.06, + "learning_rate": 0.0009818840330174793, + "loss": 0.1038, + "step": 287 + }, + { + "epoch": 0.06, + "learning_rate": 0.0009817129677031436, + "loss": 0.1025, + "step": 288 + }, + { + "epoch": 0.06, + "learning_rate": 0.0009815411135558802, + "loss": 0.105, + "step": 289 + }, + { + "epoch": 0.06, + "learning_rate": 0.00098136847085711, + "loss": 0.1052, + "step": 290 + }, + { + "epoch": 0.06, + "learning_rate": 0.0009811950398895457, + "loss": 0.105, + "step": 291 + }, + { + "epoch": 0.06, + "learning_rate": 0.00098102082093719, + "loss": 0.1054, + "step": 292 + }, + { + "epoch": 0.06, + "learning_rate": 0.000980845814285337, + "loss": 0.1028, + "step": 293 + }, + { + "epoch": 0.06, + "learning_rate": 0.0009806700202205701, + "loss": 0.1053, + "step": 294 + }, + { + "epoch": 0.06, + "learning_rate": 0.0009804934390307623, + "loss": 0.1064, + "step": 295 + }, + { + "epoch": 0.06, + "learning_rate": 0.0009803160710050757, + "loss": 0.1029, + "step": 296 + }, + { + "epoch": 0.06, + "learning_rate": 0.0009801379164339603, + "loss": 0.1057, + "step": 297 + }, + { + "epoch": 0.06, + "learning_rate": 0.0009799589756091548, + "loss": 0.1076, + "step": 298 + }, + { + "epoch": 0.06, + "learning_rate": 0.0009797792488236855, + "loss": 0.1062, + "step": 299 + }, + { + "epoch": 0.06, + "learning_rate": 0.000979598736371865, + "loss": 0.104, + "step": 300 + }, + { + "epoch": 0.06, + "learning_rate": 0.000979417438549293, + "loss": 0.1035, + "step": 301 + }, + { + "epoch": 0.06, + "learning_rate": 0.0009792353556528552, + "loss": 0.1056, + "step": 302 + }, + { + "epoch": 0.06, + "learning_rate": 0.0009790524879807229, + "loss": 0.1045, + "step": 303 + }, + { + "epoch": 0.06, + "learning_rate": 0.0009788688358323527, + "loss": 0.1033, + "step": 304 + }, + { + "epoch": 0.06, + "learning_rate": 0.0009786843995084856, + "loss": 0.1048, + "step": 305 + }, + { + "epoch": 0.06, + "learning_rate": 0.0009784991793111465, + "loss": 0.1076, + "step": 306 + }, + { + "epoch": 0.06, + "learning_rate": 0.0009783131755436445, + "loss": 0.1037, + "step": 307 + }, + { + "epoch": 0.06, + "learning_rate": 0.0009781263885105715, + "loss": 0.1025, + "step": 308 + }, + { + "epoch": 0.06, + "learning_rate": 0.000977938818517802, + "loss": 0.1061, + "step": 309 + }, + { + "epoch": 0.06, + "learning_rate": 0.0009777504658724928, + "loss": 0.1064, + "step": 310 + }, + { + "epoch": 0.06, + "learning_rate": 0.0009775613308830825, + "loss": 0.1065, + "step": 311 + }, + { + "epoch": 0.06, + "learning_rate": 0.0009773714138592903, + "loss": 0.1063, + "step": 312 + }, + { + "epoch": 0.06, + "learning_rate": 0.0009771807151121162, + "loss": 0.107, + "step": 313 + }, + { + "epoch": 0.06, + "learning_rate": 0.000976989234953841, + "loss": 0.1053, + "step": 314 + }, + { + "epoch": 0.06, + "learning_rate": 0.0009767969736980242, + "loss": 0.1048, + "step": 315 + }, + { + "epoch": 0.06, + "learning_rate": 0.0009766039316595047, + "loss": 0.1059, + "step": 316 + }, + { + "epoch": 0.06, + "learning_rate": 0.0009764101091544004, + "loss": 0.1055, + "step": 317 + }, + { + "epoch": 0.06, + "learning_rate": 0.0009762155065001067, + "loss": 0.1043, + "step": 318 + }, + { + "epoch": 0.06, + "learning_rate": 0.0009760201240152966, + "loss": 0.1033, + "step": 319 + }, + { + "epoch": 0.06, + "learning_rate": 0.0009758239620199204, + "loss": 0.1068, + "step": 320 + }, + { + "epoch": 0.06, + "learning_rate": 0.0009756270208352047, + "loss": 0.1051, + "step": 321 + }, + { + "epoch": 0.06, + "learning_rate": 0.0009754293007836521, + "loss": 0.1053, + "step": 322 + }, + { + "epoch": 0.06, + "learning_rate": 0.0009752308021890408, + "loss": 0.1062, + "step": 323 + }, + { + "epoch": 0.06, + "learning_rate": 0.0009750315253764235, + "loss": 0.1061, + "step": 324 + }, + { + "epoch": 0.06, + "learning_rate": 0.0009748314706721277, + "loss": 0.1045, + "step": 325 + }, + { + "epoch": 0.06, + "learning_rate": 0.0009746306384037546, + "loss": 0.1062, + "step": 326 + }, + { + "epoch": 0.06, + "learning_rate": 0.0009744290289001787, + "loss": 0.1042, + "step": 327 + }, + { + "epoch": 0.06, + "learning_rate": 0.0009742266424915472, + "loss": 0.1037, + "step": 328 + }, + { + "epoch": 0.06, + "learning_rate": 0.0009740234795092795, + "loss": 0.1057, + "step": 329 + }, + { + "epoch": 0.07, + "learning_rate": 0.0009738195402860669, + "loss": 0.1043, + "step": 330 + }, + { + "epoch": 0.07, + "learning_rate": 0.0009736148251558717, + "loss": 0.1029, + "step": 331 + }, + { + "epoch": 0.07, + "learning_rate": 0.0009734093344539267, + "loss": 0.1064, + "step": 332 + }, + { + "epoch": 0.07, + "learning_rate": 0.000973203068516735, + "loss": 0.1032, + "step": 333 + }, + { + "epoch": 0.07, + "learning_rate": 0.000972996027682069, + "loss": 0.1053, + "step": 334 + }, + { + "epoch": 0.07, + "learning_rate": 0.00097278821228897, + "loss": 0.1044, + "step": 335 + }, + { + "epoch": 0.07, + "learning_rate": 0.0009725796226777477, + "loss": 0.1046, + "step": 336 + }, + { + "epoch": 0.07, + "learning_rate": 0.0009723702591899799, + "loss": 0.106, + "step": 337 + }, + { + "epoch": 0.07, + "learning_rate": 0.0009721601221685112, + "loss": 0.103, + "step": 338 + }, + { + "epoch": 0.07, + "learning_rate": 0.0009719492119574535, + "loss": 0.1046, + "step": 339 + }, + { + "epoch": 0.07, + "learning_rate": 0.0009717375289021842, + "loss": 0.1089, + "step": 340 + }, + { + "epoch": 0.07, + "learning_rate": 0.0009715250733493466, + "loss": 0.1025, + "step": 341 + }, + { + "epoch": 0.07, + "learning_rate": 0.0009713118456468492, + "loss": 0.102, + "step": 342 + }, + { + "epoch": 0.07, + "learning_rate": 0.0009710978461438646, + "loss": 0.1022, + "step": 343 + }, + { + "epoch": 0.07, + "learning_rate": 0.0009708830751908293, + "loss": 0.1051, + "step": 344 + }, + { + "epoch": 0.07, + "learning_rate": 0.0009706675331394433, + "loss": 0.106, + "step": 345 + }, + { + "epoch": 0.07, + "learning_rate": 0.0009704512203426695, + "loss": 0.1061, + "step": 346 + }, + { + "epoch": 0.07, + "learning_rate": 0.0009702341371547321, + "loss": 0.1042, + "step": 347 + }, + { + "epoch": 0.07, + "learning_rate": 0.0009700162839311177, + "loss": 0.1029, + "step": 348 + }, + { + "epoch": 0.07, + "learning_rate": 0.0009697976610285736, + "loss": 0.105, + "step": 349 + }, + { + "epoch": 0.07, + "learning_rate": 0.0009695782688051074, + "loss": 0.1076, + "step": 350 + }, + { + "epoch": 0.07, + "learning_rate": 0.0009693581076199868, + "loss": 0.105, + "step": 351 + }, + { + "epoch": 0.07, + "learning_rate": 0.0009691371778337383, + "loss": 0.1056, + "step": 352 + }, + { + "epoch": 0.07, + "learning_rate": 0.0009689154798081473, + "loss": 0.1066, + "step": 353 + }, + { + "epoch": 0.07, + "learning_rate": 0.0009686930139062572, + "loss": 0.1034, + "step": 354 + }, + { + "epoch": 0.07, + "learning_rate": 0.0009684697804923688, + "loss": 0.1044, + "step": 355 + }, + { + "epoch": 0.07, + "learning_rate": 0.0009682457799320397, + "loss": 0.1052, + "step": 356 + }, + { + "epoch": 0.07, + "learning_rate": 0.0009680210125920838, + "loss": 0.1053, + "step": 357 + }, + { + "epoch": 0.07, + "learning_rate": 0.000967795478840571, + "loss": 0.1047, + "step": 358 + }, + { + "epoch": 0.07, + "learning_rate": 0.0009675691790468255, + "loss": 0.1049, + "step": 359 + }, + { + "epoch": 0.07, + "learning_rate": 0.0009673421135814264, + "loss": 0.1061, + "step": 360 + }, + { + "epoch": 0.07, + "learning_rate": 0.0009671142828162067, + "loss": 0.1042, + "step": 361 + }, + { + "epoch": 0.07, + "learning_rate": 0.0009668856871242524, + "loss": 0.1046, + "step": 362 + }, + { + "epoch": 0.07, + "learning_rate": 0.0009666563268799024, + "loss": 0.1077, + "step": 363 + }, + { + "epoch": 0.07, + "learning_rate": 0.0009664262024587471, + "loss": 0.1027, + "step": 364 + }, + { + "epoch": 0.07, + "learning_rate": 0.0009661953142376287, + "loss": 0.1061, + "step": 365 + }, + { + "epoch": 0.07, + "learning_rate": 0.0009659636625946402, + "loss": 0.1045, + "step": 366 + }, + { + "epoch": 0.07, + "learning_rate": 0.0009657312479091245, + "loss": 0.1051, + "step": 367 + }, + { + "epoch": 0.07, + "learning_rate": 0.0009654980705616741, + "loss": 0.1041, + "step": 368 + }, + { + "epoch": 0.07, + "learning_rate": 0.0009652641309341305, + "loss": 0.1035, + "step": 369 + }, + { + "epoch": 0.07, + "learning_rate": 0.0009650294294095833, + "loss": 0.1048, + "step": 370 + }, + { + "epoch": 0.07, + "learning_rate": 0.00096479396637237, + "loss": 0.1052, + "step": 371 + }, + { + "epoch": 0.07, + "learning_rate": 0.0009645577422080748, + "loss": 0.1042, + "step": 372 + }, + { + "epoch": 0.07, + "learning_rate": 0.0009643207573035287, + "loss": 0.1038, + "step": 373 + }, + { + "epoch": 0.07, + "learning_rate": 0.000964083012046808, + "loss": 0.1043, + "step": 374 + }, + { + "epoch": 0.07, + "learning_rate": 0.0009638445068272345, + "loss": 0.1024, + "step": 375 + }, + { + "epoch": 0.07, + "learning_rate": 0.0009636052420353744, + "loss": 0.1057, + "step": 376 + }, + { + "epoch": 0.07, + "learning_rate": 0.0009633652180630375, + "loss": 0.1025, + "step": 377 + }, + { + "epoch": 0.07, + "learning_rate": 0.000963124435303277, + "loss": 0.1025, + "step": 378 + }, + { + "epoch": 0.07, + "learning_rate": 0.0009628828941503887, + "loss": 0.1045, + "step": 379 + }, + { + "epoch": 0.08, + "learning_rate": 0.0009626405949999103, + "loss": 0.106, + "step": 380 + }, + { + "epoch": 0.08, + "learning_rate": 0.0009623975382486205, + "loss": 0.1063, + "step": 381 + }, + { + "epoch": 0.08, + "learning_rate": 0.0009621537242945392, + "loss": 0.1037, + "step": 382 + }, + { + "epoch": 0.08, + "learning_rate": 0.0009619091535369255, + "loss": 0.1023, + "step": 383 + }, + { + "epoch": 0.08, + "learning_rate": 0.0009616638263762785, + "loss": 0.1073, + "step": 384 + }, + { + "epoch": 0.08, + "learning_rate": 0.0009614177432143353, + "loss": 0.1046, + "step": 385 + }, + { + "epoch": 0.08, + "learning_rate": 0.000961170904454072, + "loss": 0.1049, + "step": 386 + }, + { + "epoch": 0.08, + "learning_rate": 0.0009609233104997006, + "loss": 0.1045, + "step": 387 + }, + { + "epoch": 0.08, + "learning_rate": 0.0009606749617566711, + "loss": 0.1036, + "step": 388 + }, + { + "epoch": 0.08, + "learning_rate": 0.0009604258586316688, + "loss": 0.1064, + "step": 389 + }, + { + "epoch": 0.08, + "learning_rate": 0.0009601760015326144, + "loss": 0.1056, + "step": 390 + }, + { + "epoch": 0.08, + "learning_rate": 0.0009599253908686636, + "loss": 0.1017, + "step": 391 + }, + { + "epoch": 0.08, + "learning_rate": 0.0009596740270502058, + "loss": 0.1038, + "step": 392 + }, + { + "epoch": 0.08, + "learning_rate": 0.000959421910488864, + "loss": 0.1076, + "step": 393 + }, + { + "epoch": 0.08, + "learning_rate": 0.0009591690415974933, + "loss": 0.1012, + "step": 394 + }, + { + "epoch": 0.08, + "learning_rate": 0.0009589154207901815, + "loss": 0.1026, + "step": 395 + }, + { + "epoch": 0.08, + "learning_rate": 0.0009586610484822474, + "loss": 0.1039, + "step": 396 + }, + { + "epoch": 0.08, + "learning_rate": 0.0009584059250902403, + "loss": 0.1039, + "step": 397 + }, + { + "epoch": 0.08, + "learning_rate": 0.0009581500510319395, + "loss": 0.1047, + "step": 398 + }, + { + "epoch": 0.08, + "learning_rate": 0.0009578934267263537, + "loss": 0.105, + "step": 399 + }, + { + "epoch": 0.08, + "learning_rate": 0.0009576360525937201, + "loss": 0.1055, + "step": 400 + }, + { + "epoch": 0.08, + "learning_rate": 0.0009573779290555038, + "loss": 0.1041, + "step": 401 + }, + { + "epoch": 0.08, + "learning_rate": 0.0009571190565343969, + "loss": 0.1042, + "step": 402 + }, + { + "epoch": 0.08, + "learning_rate": 0.0009568594354543183, + "loss": 0.1053, + "step": 403 + }, + { + "epoch": 0.08, + "learning_rate": 0.0009565990662404127, + "loss": 0.1057, + "step": 404 + }, + { + "epoch": 0.08, + "learning_rate": 0.0009563379493190495, + "loss": 0.1027, + "step": 405 + }, + { + "epoch": 0.08, + "learning_rate": 0.000956076085117823, + "loss": 0.1035, + "step": 406 + }, + { + "epoch": 0.08, + "learning_rate": 0.0009558134740655508, + "loss": 0.1024, + "step": 407 + }, + { + "epoch": 0.08, + "learning_rate": 0.0009555501165922742, + "loss": 0.1031, + "step": 408 + }, + { + "epoch": 0.08, + "learning_rate": 0.000955286013129256, + "loss": 0.1044, + "step": 409 + }, + { + "epoch": 0.08, + "learning_rate": 0.0009550211641089808, + "loss": 0.1066, + "step": 410 + }, + { + "epoch": 0.08, + "learning_rate": 0.0009547555699651546, + "loss": 0.103, + "step": 411 + }, + { + "epoch": 0.08, + "learning_rate": 0.0009544892311327029, + "loss": 0.1046, + "step": 412 + }, + { + "epoch": 0.08, + "learning_rate": 0.0009542221480477713, + "loss": 0.1057, + "step": 413 + }, + { + "epoch": 0.08, + "learning_rate": 0.0009539543211477236, + "loss": 0.1018, + "step": 414 + }, + { + "epoch": 0.08, + "learning_rate": 0.0009536857508711419, + "loss": 0.1034, + "step": 415 + }, + { + "epoch": 0.08, + "learning_rate": 0.0009534164376578256, + "loss": 0.1024, + "step": 416 + }, + { + "epoch": 0.08, + "learning_rate": 0.0009531463819487909, + "loss": 0.1048, + "step": 417 + }, + { + "epoch": 0.08, + "learning_rate": 0.0009528755841862695, + "loss": 0.1044, + "step": 418 + }, + { + "epoch": 0.08, + "learning_rate": 0.0009526040448137085, + "loss": 0.103, + "step": 419 + }, + { + "epoch": 0.08, + "learning_rate": 0.0009523317642757694, + "loss": 0.1027, + "step": 420 + }, + { + "epoch": 0.08, + "learning_rate": 0.0009520587430183274, + "loss": 0.1042, + "step": 421 + }, + { + "epoch": 0.08, + "learning_rate": 0.0009517849814884706, + "loss": 0.1037, + "step": 422 + }, + { + "epoch": 0.08, + "learning_rate": 0.0009515104801344994, + "loss": 0.1011, + "step": 423 + }, + { + "epoch": 0.08, + "learning_rate": 0.0009512352394059256, + "loss": 0.1037, + "step": 424 + }, + { + "epoch": 0.08, + "learning_rate": 0.000950959259753472, + "loss": 0.1046, + "step": 425 + }, + { + "epoch": 0.08, + "learning_rate": 0.0009506825416290712, + "loss": 0.1042, + "step": 426 + }, + { + "epoch": 0.08, + "learning_rate": 0.0009504050854858652, + "loss": 0.1049, + "step": 427 + }, + { + "epoch": 0.08, + "learning_rate": 0.0009501268917782046, + "loss": 0.1049, + "step": 428 + }, + { + "epoch": 0.08, + "learning_rate": 0.0009498479609616475, + "loss": 0.1025, + "step": 429 + }, + { + "epoch": 0.08, + "learning_rate": 0.0009495682934929597, + "loss": 0.1046, + "step": 430 + }, + { + "epoch": 0.09, + "learning_rate": 0.0009492878898301125, + "loss": 0.1014, + "step": 431 + }, + { + "epoch": 0.09, + "learning_rate": 0.0009490067504322834, + "loss": 0.1054, + "step": 432 + }, + { + "epoch": 0.09, + "learning_rate": 0.0009487248757598544, + "loss": 0.1051, + "step": 433 + }, + { + "epoch": 0.09, + "learning_rate": 0.0009484422662744117, + "loss": 0.1045, + "step": 434 + }, + { + "epoch": 0.09, + "learning_rate": 0.0009481589224387445, + "loss": 0.1033, + "step": 435 + }, + { + "epoch": 0.09, + "learning_rate": 0.0009478748447168449, + "loss": 0.1043, + "step": 436 + }, + { + "epoch": 0.09, + "learning_rate": 0.0009475900335739068, + "loss": 0.1056, + "step": 437 + }, + { + "epoch": 0.09, + "learning_rate": 0.0009473044894763248, + "loss": 0.1051, + "step": 438 + }, + { + "epoch": 0.09, + "learning_rate": 0.000947018212891694, + "loss": 0.1034, + "step": 439 + }, + { + "epoch": 0.09, + "learning_rate": 0.0009467312042888088, + "loss": 0.1029, + "step": 440 + }, + { + "epoch": 0.09, + "learning_rate": 0.0009464434641376626, + "loss": 0.1035, + "step": 441 + }, + { + "epoch": 0.09, + "learning_rate": 0.0009461549929094464, + "loss": 0.1059, + "step": 442 + }, + { + "epoch": 0.09, + "learning_rate": 0.0009458657910765488, + "loss": 0.1032, + "step": 443 + }, + { + "epoch": 0.09, + "learning_rate": 0.0009455758591125542, + "loss": 0.1027, + "step": 444 + }, + { + "epoch": 0.09, + "learning_rate": 0.0009452851974922436, + "loss": 0.106, + "step": 445 + }, + { + "epoch": 0.09, + "learning_rate": 0.0009449938066915918, + "loss": 0.1052, + "step": 446 + }, + { + "epoch": 0.09, + "learning_rate": 0.0009447016871877682, + "loss": 0.1039, + "step": 447 + }, + { + "epoch": 0.09, + "learning_rate": 0.0009444088394591354, + "loss": 0.1041, + "step": 448 + }, + { + "epoch": 0.09, + "learning_rate": 0.0009441152639852488, + "loss": 0.1017, + "step": 449 + }, + { + "epoch": 0.09, + "learning_rate": 0.0009438209612468552, + "loss": 0.1045, + "step": 450 + }, + { + "epoch": 0.09, + "learning_rate": 0.000943525931725892, + "loss": 0.1031, + "step": 451 + }, + { + "epoch": 0.09, + "learning_rate": 0.0009432301759054877, + "loss": 0.104, + "step": 452 + }, + { + "epoch": 0.09, + "learning_rate": 0.0009429336942699593, + "loss": 0.1042, + "step": 453 + }, + { + "epoch": 0.09, + "learning_rate": 0.0009426364873048128, + "loss": 0.1037, + "step": 454 + }, + { + "epoch": 0.09, + "learning_rate": 0.0009423385554967418, + "loss": 0.1036, + "step": 455 + }, + { + "epoch": 0.09, + "learning_rate": 0.0009420398993336269, + "loss": 0.1048, + "step": 456 + }, + { + "epoch": 0.09, + "learning_rate": 0.000941740519304535, + "loss": 0.1033, + "step": 457 + }, + { + "epoch": 0.09, + "learning_rate": 0.000941440415899718, + "loss": 0.1035, + "step": 458 + }, + { + "epoch": 0.09, + "learning_rate": 0.0009411395896106128, + "loss": 0.1023, + "step": 459 + }, + { + "epoch": 0.09, + "learning_rate": 0.0009408380409298401, + "loss": 0.1026, + "step": 460 + }, + { + "epoch": 0.09, + "learning_rate": 0.000940535770351203, + "loss": 0.1065, + "step": 461 + }, + { + "epoch": 0.09, + "learning_rate": 0.0009402327783696873, + "loss": 0.1068, + "step": 462 + }, + { + "epoch": 0.09, + "learning_rate": 0.00093992906548146, + "loss": 0.1052, + "step": 463 + }, + { + "epoch": 0.09, + "learning_rate": 0.0009396246321838684, + "loss": 0.1045, + "step": 464 + }, + { + "epoch": 0.09, + "learning_rate": 0.0009393194789754398, + "loss": 0.1055, + "step": 465 + }, + { + "epoch": 0.09, + "learning_rate": 0.0009390136063558803, + "loss": 0.105, + "step": 466 + }, + { + "epoch": 0.09, + "learning_rate": 0.0009387070148260741, + "loss": 0.1045, + "step": 467 + }, + { + "epoch": 0.09, + "learning_rate": 0.0009383997048880824, + "loss": 0.1051, + "step": 468 + }, + { + "epoch": 0.09, + "learning_rate": 0.0009380916770451431, + "loss": 0.1071, + "step": 469 + }, + { + "epoch": 0.09, + "learning_rate": 0.0009377829318016697, + "loss": 0.206, + "step": 470 + }, + { + "epoch": 0.09, + "learning_rate": 0.0009374734696632508, + "loss": 0.1064, + "step": 471 + }, + { + "epoch": 0.09, + "learning_rate": 0.000937163291136648, + "loss": 0.1569, + "step": 472 + }, + { + "epoch": 0.09, + "learning_rate": 0.0009368523967297971, + "loss": 0.2904, + "step": 473 + }, + { + "epoch": 0.09, + "learning_rate": 0.0009365407869518054, + "loss": 0.1409, + "step": 474 + }, + { + "epoch": 0.09, + "learning_rate": 0.0009362284623129522, + "loss": 0.1826, + "step": 475 + }, + { + "epoch": 0.09, + "learning_rate": 0.0009359154233246872, + "loss": 0.2115, + "step": 476 + }, + { + "epoch": 0.09, + "learning_rate": 0.0009356016704996297, + "loss": 0.1526, + "step": 477 + }, + { + "epoch": 0.09, + "learning_rate": 0.0009352872043515684, + "loss": 0.1615, + "step": 478 + }, + { + "epoch": 0.09, + "learning_rate": 0.0009349720253954597, + "loss": 0.1506, + "step": 479 + }, + { + "epoch": 0.09, + "learning_rate": 0.0009346561341474274, + "loss": 0.156, + "step": 480 + }, + { + "epoch": 0.1, + "learning_rate": 0.000934339531124762, + "loss": 0.1663, + "step": 481 + }, + { + "epoch": 0.1, + "learning_rate": 0.000934022216845919, + "loss": 0.1549, + "step": 482 + }, + { + "epoch": 0.1, + "learning_rate": 0.0009337041918305192, + "loss": 0.153, + "step": 483 + }, + { + "epoch": 0.1, + "learning_rate": 0.0009333854565993468, + "loss": 0.1541, + "step": 484 + }, + { + "epoch": 0.1, + "learning_rate": 0.0009330660116743494, + "loss": 0.1591, + "step": 485 + }, + { + "epoch": 0.1, + "learning_rate": 0.0009327458575786364, + "loss": 0.1329, + "step": 486 + }, + { + "epoch": 0.1, + "learning_rate": 0.0009324249948364789, + "loss": 0.1389, + "step": 487 + }, + { + "epoch": 0.1, + "learning_rate": 0.0009321034239733082, + "loss": 0.1417, + "step": 488 + }, + { + "epoch": 0.1, + "learning_rate": 0.000931781145515715, + "loss": 0.1353, + "step": 489 + }, + { + "epoch": 0.1, + "learning_rate": 0.0009314581599914494, + "loss": 0.1253, + "step": 490 + }, + { + "epoch": 0.1, + "learning_rate": 0.0009311344679294185, + "loss": 0.1398, + "step": 491 + }, + { + "epoch": 0.1, + "learning_rate": 0.0009308100698596873, + "loss": 0.1234, + "step": 492 + }, + { + "epoch": 0.1, + "learning_rate": 0.000930484966313476, + "loss": 0.123, + "step": 493 + }, + { + "epoch": 0.1, + "learning_rate": 0.0009301591578231609, + "loss": 0.13, + "step": 494 + }, + { + "epoch": 0.1, + "learning_rate": 0.000929832644922272, + "loss": 0.1239, + "step": 495 + }, + { + "epoch": 0.1, + "learning_rate": 0.0009295054281454931, + "loss": 0.1264, + "step": 496 + }, + { + "epoch": 0.1, + "learning_rate": 0.000929177508028661, + "loss": 0.1216, + "step": 497 + }, + { + "epoch": 0.1, + "learning_rate": 0.0009288488851087635, + "loss": 0.1171, + "step": 498 + }, + { + "epoch": 0.1, + "learning_rate": 0.0009285195599239402, + "loss": 0.1191, + "step": 499 + }, + { + "epoch": 0.1, + "learning_rate": 0.0009281895330134795, + "loss": 0.1179, + "step": 500 + }, + { + "epoch": 0.1, + "learning_rate": 0.0009278588049178203, + "loss": 0.1173, + "step": 501 + }, + { + "epoch": 0.1, + "learning_rate": 0.0009275273761785485, + "loss": 0.1138, + "step": 502 + }, + { + "epoch": 0.1, + "learning_rate": 0.0009271952473383984, + "loss": 0.1168, + "step": 503 + }, + { + "epoch": 0.1, + "learning_rate": 0.0009268624189412498, + "loss": 0.1167, + "step": 504 + }, + { + "epoch": 0.1, + "learning_rate": 0.0009265288915321286, + "loss": 0.1131, + "step": 505 + }, + { + "epoch": 0.1, + "learning_rate": 0.0009261946656572054, + "loss": 0.1157, + "step": 506 + }, + { + "epoch": 0.1, + "learning_rate": 0.0009258597418637945, + "loss": 0.1099, + "step": 507 + }, + { + "epoch": 0.1, + "learning_rate": 0.0009255241207003529, + "loss": 0.1101, + "step": 508 + }, + { + "epoch": 0.1, + "learning_rate": 0.0009251878027164797, + "loss": 0.1136, + "step": 509 + }, + { + "epoch": 0.1, + "learning_rate": 0.0009248507884629152, + "loss": 0.1098, + "step": 510 + }, + { + "epoch": 0.1, + "learning_rate": 0.0009245130784915398, + "loss": 0.1063, + "step": 511 + }, + { + "epoch": 0.1, + "learning_rate": 0.0009241746733553734, + "loss": 0.11, + "step": 512 + }, + { + "epoch": 0.1, + "learning_rate": 0.0009238355736085734, + "loss": 0.1122, + "step": 513 + }, + { + "epoch": 0.1, + "learning_rate": 0.0009234957798064359, + "loss": 0.1109, + "step": 514 + }, + { + "epoch": 0.1, + "learning_rate": 0.0009231552925053926, + "loss": 0.1069, + "step": 515 + }, + { + "epoch": 0.1, + "learning_rate": 0.0009228141122630114, + "loss": 0.1089, + "step": 516 + }, + { + "epoch": 0.1, + "learning_rate": 0.0009224722396379948, + "loss": 0.1112, + "step": 517 + }, + { + "epoch": 0.1, + "learning_rate": 0.0009221296751901788, + "loss": 0.1079, + "step": 518 + }, + { + "epoch": 0.1, + "learning_rate": 0.0009217864194805327, + "loss": 0.1105, + "step": 519 + }, + { + "epoch": 0.1, + "learning_rate": 0.0009214424730711577, + "loss": 0.1079, + "step": 520 + }, + { + "epoch": 0.1, + "learning_rate": 0.000921097836525286, + "loss": 0.1085, + "step": 521 + }, + { + "epoch": 0.1, + "learning_rate": 0.0009207525104072799, + "loss": 0.1098, + "step": 522 + }, + { + "epoch": 0.1, + "learning_rate": 0.0009204064952826307, + "loss": 0.1104, + "step": 523 + }, + { + "epoch": 0.1, + "learning_rate": 0.0009200597917179585, + "loss": 0.1065, + "step": 524 + }, + { + "epoch": 0.1, + "learning_rate": 0.0009197124002810106, + "loss": 0.1066, + "step": 525 + }, + { + "epoch": 0.1, + "learning_rate": 0.0009193643215406604, + "loss": 0.1074, + "step": 526 + }, + { + "epoch": 0.1, + "learning_rate": 0.0009190155560669072, + "loss": 0.1094, + "step": 527 + }, + { + "epoch": 0.1, + "learning_rate": 0.0009186661044308745, + "loss": 0.1049, + "step": 528 + }, + { + "epoch": 0.1, + "learning_rate": 0.0009183159672048098, + "loss": 0.1077, + "step": 529 + }, + { + "epoch": 0.1, + "learning_rate": 0.0009179651449620831, + "loss": 0.1076, + "step": 530 + }, + { + "epoch": 0.1, + "learning_rate": 0.000917613638277186, + "loss": 0.1069, + "step": 531 + }, + { + "epoch": 0.11, + "learning_rate": 0.0009172614477257313, + "loss": 0.105, + "step": 532 + }, + { + "epoch": 0.11, + "learning_rate": 0.0009169085738844514, + "loss": 0.1073, + "step": 533 + }, + { + "epoch": 0.11, + "learning_rate": 0.0009165550173311976, + "loss": 0.106, + "step": 534 + }, + { + "epoch": 0.11, + "learning_rate": 0.0009162007786449394, + "loss": 0.1082, + "step": 535 + }, + { + "epoch": 0.11, + "learning_rate": 0.0009158458584057629, + "loss": 0.105, + "step": 536 + }, + { + "epoch": 0.11, + "learning_rate": 0.000915490257194871, + "loss": 0.1041, + "step": 537 + }, + { + "epoch": 0.11, + "learning_rate": 0.0009151339755945811, + "loss": 0.1065, + "step": 538 + }, + { + "epoch": 0.11, + "learning_rate": 0.000914777014188325, + "loss": 0.1067, + "step": 539 + }, + { + "epoch": 0.11, + "learning_rate": 0.0009144193735606477, + "loss": 0.1042, + "step": 540 + }, + { + "epoch": 0.11, + "learning_rate": 0.0009140610542972064, + "loss": 0.1044, + "step": 541 + }, + { + "epoch": 0.11, + "learning_rate": 0.0009137020569847698, + "loss": 0.1063, + "step": 542 + }, + { + "epoch": 0.11, + "learning_rate": 0.0009133423822112168, + "loss": 0.1079, + "step": 543 + }, + { + "epoch": 0.11, + "learning_rate": 0.0009129820305655357, + "loss": 0.1067, + "step": 544 + }, + { + "epoch": 0.11, + "learning_rate": 0.0009126210026378232, + "loss": 0.1064, + "step": 545 + }, + { + "epoch": 0.11, + "learning_rate": 0.0009122592990192835, + "loss": 0.104, + "step": 546 + }, + { + "epoch": 0.11, + "learning_rate": 0.0009118969203022272, + "loss": 0.1058, + "step": 547 + }, + { + "epoch": 0.11, + "learning_rate": 0.0009115338670800706, + "loss": 0.1042, + "step": 548 + }, + { + "epoch": 0.11, + "learning_rate": 0.0009111701399473342, + "loss": 0.1059, + "step": 549 + }, + { + "epoch": 0.11, + "learning_rate": 0.0009108057394996425, + "loss": 0.1049, + "step": 550 + }, + { + "epoch": 0.11, + "learning_rate": 0.0009104406663337221, + "loss": 0.1047, + "step": 551 + }, + { + "epoch": 0.11, + "learning_rate": 0.000910074921047402, + "loss": 0.1041, + "step": 552 + }, + { + "epoch": 0.11, + "learning_rate": 0.0009097085042396107, + "loss": 0.1032, + "step": 553 + }, + { + "epoch": 0.11, + "learning_rate": 0.0009093414165103774, + "loss": 0.1046, + "step": 554 + }, + { + "epoch": 0.11, + "learning_rate": 0.0009089736584608294, + "loss": 0.1052, + "step": 555 + }, + { + "epoch": 0.11, + "learning_rate": 0.0009086052306931918, + "loss": 0.1065, + "step": 556 + }, + { + "epoch": 0.11, + "learning_rate": 0.0009082361338107865, + "loss": 0.1049, + "step": 557 + }, + { + "epoch": 0.11, + "learning_rate": 0.000907866368418031, + "loss": 0.105, + "step": 558 + }, + { + "epoch": 0.11, + "learning_rate": 0.0009074959351204377, + "loss": 0.1042, + "step": 559 + }, + { + "epoch": 0.11, + "learning_rate": 0.0009071248345246125, + "loss": 0.1037, + "step": 560 + }, + { + "epoch": 0.11, + "learning_rate": 0.0009067530672382543, + "loss": 0.103, + "step": 561 + }, + { + "epoch": 0.11, + "learning_rate": 0.0009063806338701534, + "loss": 0.104, + "step": 562 + }, + { + "epoch": 0.11, + "learning_rate": 0.0009060075350301913, + "loss": 0.1045, + "step": 563 + }, + { + "epoch": 0.11, + "learning_rate": 0.0009056337713293387, + "loss": 0.1033, + "step": 564 + }, + { + "epoch": 0.11, + "learning_rate": 0.0009052593433796554, + "loss": 0.1064, + "step": 565 + }, + { + "epoch": 0.11, + "learning_rate": 0.000904884251794289, + "loss": 0.1064, + "step": 566 + }, + { + "epoch": 0.11, + "learning_rate": 0.0009045084971874737, + "loss": 0.1032, + "step": 567 + }, + { + "epoch": 0.11, + "learning_rate": 0.0009041320801745295, + "loss": 0.1094, + "step": 568 + }, + { + "epoch": 0.11, + "learning_rate": 0.000903755001371861, + "loss": 0.1043, + "step": 569 + }, + { + "epoch": 0.11, + "learning_rate": 0.0009033772613969566, + "loss": 0.1057, + "step": 570 + }, + { + "epoch": 0.11, + "learning_rate": 0.0009029988608683877, + "loss": 0.1029, + "step": 571 + }, + { + "epoch": 0.11, + "learning_rate": 0.0009026198004058068, + "loss": 0.1056, + "step": 572 + }, + { + "epoch": 0.11, + "learning_rate": 0.0009022400806299474, + "loss": 0.1073, + "step": 573 + }, + { + "epoch": 0.11, + "learning_rate": 0.0009018597021626227, + "loss": 0.105, + "step": 574 + }, + { + "epoch": 0.11, + "learning_rate": 0.0009014786656267247, + "loss": 0.104, + "step": 575 + }, + { + "epoch": 0.11, + "learning_rate": 0.0009010969716462228, + "loss": 0.106, + "step": 576 + }, + { + "epoch": 0.11, + "learning_rate": 0.0009007146208461626, + "loss": 0.104, + "step": 577 + }, + { + "epoch": 0.11, + "learning_rate": 0.0009003316138526663, + "loss": 0.1054, + "step": 578 + }, + { + "epoch": 0.11, + "learning_rate": 0.0008999479512929296, + "loss": 0.1043, + "step": 579 + }, + { + "epoch": 0.11, + "learning_rate": 0.0008995636337952226, + "loss": 0.1032, + "step": 580 + }, + { + "epoch": 0.11, + "learning_rate": 0.0008991786619888874, + "loss": 0.1037, + "step": 581 + }, + { + "epoch": 0.11, + "learning_rate": 0.0008987930365043373, + "loss": 0.105, + "step": 582 + }, + { + "epoch": 0.12, + "learning_rate": 0.0008984067579730567, + "loss": 0.1043, + "step": 583 + }, + { + "epoch": 0.12, + "learning_rate": 0.0008980198270275991, + "loss": 0.105, + "step": 584 + }, + { + "epoch": 0.12, + "learning_rate": 0.0008976322443015864, + "loss": 0.1042, + "step": 585 + }, + { + "epoch": 0.12, + "learning_rate": 0.0008972440104297077, + "loss": 0.1025, + "step": 586 + }, + { + "epoch": 0.12, + "learning_rate": 0.0008968551260477185, + "loss": 0.1059, + "step": 587 + }, + { + "epoch": 0.12, + "learning_rate": 0.0008964655917924395, + "loss": 0.1038, + "step": 588 + }, + { + "epoch": 0.12, + "learning_rate": 0.0008960754083017558, + "loss": 0.1038, + "step": 589 + }, + { + "epoch": 0.12, + "learning_rate": 0.0008956845762146153, + "loss": 0.1051, + "step": 590 + }, + { + "epoch": 0.12, + "learning_rate": 0.0008952930961710284, + "loss": 0.1062, + "step": 591 + }, + { + "epoch": 0.12, + "learning_rate": 0.0008949009688120662, + "loss": 0.1049, + "step": 592 + }, + { + "epoch": 0.12, + "learning_rate": 0.0008945081947798601, + "loss": 0.1047, + "step": 593 + }, + { + "epoch": 0.12, + "learning_rate": 0.0008941147747176005, + "loss": 0.1027, + "step": 594 + }, + { + "epoch": 0.12, + "learning_rate": 0.0008937207092695352, + "loss": 0.1052, + "step": 595 + }, + { + "epoch": 0.12, + "learning_rate": 0.0008933259990809697, + "loss": 0.1039, + "step": 596 + }, + { + "epoch": 0.12, + "learning_rate": 0.0008929306447982644, + "loss": 0.1052, + "step": 597 + }, + { + "epoch": 0.12, + "learning_rate": 0.000892534647068835, + "loss": 0.1058, + "step": 598 + }, + { + "epoch": 0.12, + "learning_rate": 0.0008921380065411509, + "loss": 0.1035, + "step": 599 + }, + { + "epoch": 0.12, + "learning_rate": 0.0008917407238647339, + "loss": 0.1043, + "step": 600 + }, + { + "epoch": 0.12, + "learning_rate": 0.0008913427996901573, + "loss": 0.1021, + "step": 601 + }, + { + "epoch": 0.12, + "learning_rate": 0.0008909442346690453, + "loss": 0.1015, + "step": 602 + }, + { + "epoch": 0.12, + "learning_rate": 0.0008905450294540709, + "loss": 0.1063, + "step": 603 + }, + { + "epoch": 0.12, + "learning_rate": 0.0008901451846989558, + "loss": 0.103, + "step": 604 + }, + { + "epoch": 0.12, + "learning_rate": 0.0008897447010584695, + "loss": 0.1077, + "step": 605 + }, + { + "epoch": 0.12, + "learning_rate": 0.0008893435791884267, + "loss": 0.1039, + "step": 606 + }, + { + "epoch": 0.12, + "learning_rate": 0.0008889418197456879, + "loss": 0.1029, + "step": 607 + }, + { + "epoch": 0.12, + "learning_rate": 0.0008885394233881574, + "loss": 0.1068, + "step": 608 + }, + { + "epoch": 0.12, + "learning_rate": 0.0008881363907747826, + "loss": 0.1083, + "step": 609 + }, + { + "epoch": 0.12, + "learning_rate": 0.000887732722565553, + "loss": 0.1043, + "step": 610 + }, + { + "epoch": 0.12, + "learning_rate": 0.0008873284194214983, + "loss": 0.1047, + "step": 611 + }, + { + "epoch": 0.12, + "learning_rate": 0.0008869234820046887, + "loss": 0.1018, + "step": 612 + }, + { + "epoch": 0.12, + "learning_rate": 0.0008865179109782326, + "loss": 0.1035, + "step": 613 + }, + { + "epoch": 0.12, + "learning_rate": 0.0008861117070062761, + "loss": 0.1043, + "step": 614 + }, + { + "epoch": 0.12, + "learning_rate": 0.0008857048707540016, + "loss": 0.1043, + "step": 615 + }, + { + "epoch": 0.12, + "learning_rate": 0.0008852974028876273, + "loss": 0.1076, + "step": 616 + }, + { + "epoch": 0.12, + "learning_rate": 0.0008848893040744053, + "loss": 0.1047, + "step": 617 + }, + { + "epoch": 0.12, + "learning_rate": 0.0008844805749826213, + "loss": 0.104, + "step": 618 + }, + { + "epoch": 0.12, + "learning_rate": 0.0008840712162815927, + "loss": 0.1035, + "step": 619 + }, + { + "epoch": 0.12, + "learning_rate": 0.0008836612286416681, + "loss": 0.1031, + "step": 620 + }, + { + "epoch": 0.12, + "learning_rate": 0.0008832506127342261, + "loss": 0.1042, + "step": 621 + }, + { + "epoch": 0.12, + "learning_rate": 0.000882839369231674, + "loss": 0.1035, + "step": 622 + }, + { + "epoch": 0.12, + "learning_rate": 0.0008824274988074473, + "loss": 0.1019, + "step": 623 + }, + { + "epoch": 0.12, + "learning_rate": 0.0008820150021360071, + "loss": 0.1049, + "step": 624 + }, + { + "epoch": 0.12, + "learning_rate": 0.0008816018798928409, + "loss": 0.1043, + "step": 625 + }, + { + "epoch": 0.12, + "learning_rate": 0.0008811881327544604, + "loss": 0.1047, + "step": 626 + }, + { + "epoch": 0.12, + "learning_rate": 0.0008807737613984006, + "loss": 0.1018, + "step": 627 + }, + { + "epoch": 0.12, + "learning_rate": 0.0008803587665032183, + "loss": 0.1027, + "step": 628 + }, + { + "epoch": 0.12, + "learning_rate": 0.0008799431487484921, + "loss": 0.1043, + "step": 629 + }, + { + "epoch": 0.12, + "learning_rate": 0.0008795269088148199, + "loss": 0.1039, + "step": 630 + }, + { + "epoch": 0.12, + "learning_rate": 0.000879110047383819, + "loss": 0.1054, + "step": 631 + }, + { + "epoch": 0.12, + "learning_rate": 0.0008786925651381239, + "loss": 0.104, + "step": 632 + }, + { + "epoch": 0.13, + "learning_rate": 0.0008782744627613861, + "loss": 0.1029, + "step": 633 + }, + { + "epoch": 0.13, + "learning_rate": 0.0008778557409382726, + "loss": 0.1051, + "step": 634 + }, + { + "epoch": 0.13, + "learning_rate": 0.0008774364003544646, + "loss": 0.102, + "step": 635 + }, + { + "epoch": 0.13, + "learning_rate": 0.0008770164416966565, + "loss": 0.1016, + "step": 636 + }, + { + "epoch": 0.13, + "learning_rate": 0.0008765958656525553, + "loss": 0.1055, + "step": 637 + }, + { + "epoch": 0.13, + "learning_rate": 0.0008761746729108781, + "loss": 0.1038, + "step": 638 + }, + { + "epoch": 0.13, + "learning_rate": 0.0008757528641613531, + "loss": 0.1031, + "step": 639 + }, + { + "epoch": 0.13, + "learning_rate": 0.0008753304400947162, + "loss": 0.1041, + "step": 640 + }, + { + "epoch": 0.13, + "learning_rate": 0.0008749074014027115, + "loss": 0.1027, + "step": 641 + }, + { + "epoch": 0.13, + "learning_rate": 0.0008744837487780892, + "loss": 0.1059, + "step": 642 + }, + { + "epoch": 0.13, + "learning_rate": 0.0008740594829146052, + "loss": 0.1036, + "step": 643 + }, + { + "epoch": 0.13, + "learning_rate": 0.0008736346045070194, + "loss": 0.1047, + "step": 644 + }, + { + "epoch": 0.13, + "learning_rate": 0.0008732091142510949, + "loss": 0.104, + "step": 645 + }, + { + "epoch": 0.13, + "learning_rate": 0.0008727830128435965, + "loss": 0.1019, + "step": 646 + }, + { + "epoch": 0.13, + "learning_rate": 0.0008723563009822902, + "loss": 0.1064, + "step": 647 + }, + { + "epoch": 0.13, + "learning_rate": 0.0008719289793659414, + "loss": 0.1069, + "step": 648 + }, + { + "epoch": 0.13, + "learning_rate": 0.0008715010486943138, + "loss": 0.1046, + "step": 649 + }, + { + "epoch": 0.13, + "learning_rate": 0.0008710725096681691, + "loss": 0.1045, + "step": 650 + }, + { + "epoch": 0.13, + "learning_rate": 0.0008706433629892642, + "loss": 0.1034, + "step": 651 + }, + { + "epoch": 0.13, + "learning_rate": 0.0008702136093603524, + "loss": 0.1083, + "step": 652 + }, + { + "epoch": 0.13, + "learning_rate": 0.0008697832494851798, + "loss": 0.1037, + "step": 653 + }, + { + "epoch": 0.13, + "learning_rate": 0.0008693522840684856, + "loss": 0.1038, + "step": 654 + }, + { + "epoch": 0.13, + "learning_rate": 0.0008689207138160009, + "loss": 0.1041, + "step": 655 + }, + { + "epoch": 0.13, + "learning_rate": 0.0008684885394344468, + "loss": 0.103, + "step": 656 + }, + { + "epoch": 0.13, + "learning_rate": 0.0008680557616315341, + "loss": 0.1059, + "step": 657 + }, + { + "epoch": 0.13, + "learning_rate": 0.0008676223811159615, + "loss": 0.1054, + "step": 658 + }, + { + "epoch": 0.13, + "learning_rate": 0.0008671883985974147, + "loss": 0.1038, + "step": 659 + }, + { + "epoch": 0.13, + "learning_rate": 0.0008667538147865652, + "loss": 0.1047, + "step": 660 + }, + { + "epoch": 0.13, + "learning_rate": 0.0008663186303950693, + "loss": 0.1063, + "step": 661 + }, + { + "epoch": 0.13, + "learning_rate": 0.0008658828461355667, + "loss": 0.1041, + "step": 662 + }, + { + "epoch": 0.13, + "learning_rate": 0.0008654464627216793, + "loss": 0.1013, + "step": 663 + }, + { + "epoch": 0.13, + "learning_rate": 0.0008650094808680103, + "loss": 0.1007, + "step": 664 + }, + { + "epoch": 0.13, + "learning_rate": 0.0008645719012901428, + "loss": 0.1053, + "step": 665 + }, + { + "epoch": 0.13, + "learning_rate": 0.000864133724704639, + "loss": 0.1047, + "step": 666 + }, + { + "epoch": 0.13, + "learning_rate": 0.000863694951829038, + "loss": 0.1042, + "step": 667 + }, + { + "epoch": 0.13, + "learning_rate": 0.0008632555833818563, + "loss": 0.1044, + "step": 668 + }, + { + "epoch": 0.13, + "learning_rate": 0.0008628156200825848, + "loss": 0.1041, + "step": 669 + }, + { + "epoch": 0.13, + "learning_rate": 0.0008623750626516893, + "loss": 0.1052, + "step": 670 + }, + { + "epoch": 0.13, + "learning_rate": 0.000861933911810608, + "loss": 0.1026, + "step": 671 + }, + { + "epoch": 0.13, + "learning_rate": 0.0008614921682817509, + "loss": 0.1027, + "step": 672 + }, + { + "epoch": 0.13, + "learning_rate": 0.0008610498327884988, + "loss": 0.1035, + "step": 673 + }, + { + "epoch": 0.13, + "learning_rate": 0.0008606069060552017, + "loss": 0.1021, + "step": 674 + }, + { + "epoch": 0.13, + "learning_rate": 0.0008601633888071776, + "loss": 0.1036, + "step": 675 + }, + { + "epoch": 0.13, + "learning_rate": 0.0008597192817707121, + "loss": 0.1045, + "step": 676 + }, + { + "epoch": 0.13, + "learning_rate": 0.000859274585673056, + "loss": 0.1009, + "step": 677 + }, + { + "epoch": 0.13, + "learning_rate": 0.0008588293012424249, + "loss": 0.1057, + "step": 678 + }, + { + "epoch": 0.13, + "learning_rate": 0.000858383429207998, + "loss": 0.1027, + "step": 679 + }, + { + "epoch": 0.13, + "learning_rate": 0.0008579369702999167, + "loss": 0.1036, + "step": 680 + }, + { + "epoch": 0.13, + "learning_rate": 0.0008574899252492832, + "loss": 0.1052, + "step": 681 + }, + { + "epoch": 0.13, + "learning_rate": 0.0008570422947881597, + "loss": 0.1057, + "step": 682 + }, + { + "epoch": 0.13, + "learning_rate": 0.0008565940796495672, + "loss": 0.1048, + "step": 683 + }, + { + "epoch": 0.14, + "learning_rate": 0.0008561452805674841, + "loss": 0.1031, + "step": 684 + }, + { + "epoch": 0.14, + "learning_rate": 0.0008556958982768444, + "loss": 0.105, + "step": 685 + }, + { + "epoch": 0.14, + "learning_rate": 0.0008552459335135381, + "loss": 0.1064, + "step": 686 + }, + { + "epoch": 0.14, + "learning_rate": 0.0008547953870144085, + "loss": 0.1034, + "step": 687 + }, + { + "epoch": 0.14, + "learning_rate": 0.0008543442595172517, + "loss": 0.1026, + "step": 688 + }, + { + "epoch": 0.14, + "learning_rate": 0.000853892551760815, + "loss": 0.1009, + "step": 689 + }, + { + "epoch": 0.14, + "learning_rate": 0.0008534402644847962, + "loss": 0.1041, + "step": 690 + }, + { + "epoch": 0.14, + "learning_rate": 0.0008529873984298418, + "loss": 0.1025, + "step": 691 + }, + { + "epoch": 0.14, + "learning_rate": 0.0008525339543375463, + "loss": 0.1022, + "step": 692 + }, + { + "epoch": 0.14, + "learning_rate": 0.0008520799329504507, + "loss": 0.1052, + "step": 693 + }, + { + "epoch": 0.14, + "learning_rate": 0.0008516253350120415, + "loss": 0.1042, + "step": 694 + }, + { + "epoch": 0.14, + "learning_rate": 0.000851170161266749, + "loss": 0.104, + "step": 695 + }, + { + "epoch": 0.14, + "learning_rate": 0.0008507144124599468, + "loss": 0.1038, + "step": 696 + }, + { + "epoch": 0.14, + "learning_rate": 0.0008502580893379497, + "loss": 0.1037, + "step": 697 + }, + { + "epoch": 0.14, + "learning_rate": 0.0008498011926480136, + "loss": 0.1049, + "step": 698 + }, + { + "epoch": 0.14, + "learning_rate": 0.0008493437231383332, + "loss": 0.1025, + "step": 699 + }, + { + "epoch": 0.14, + "learning_rate": 0.0008488856815580413, + "loss": 0.1011, + "step": 700 + }, + { + "epoch": 0.14, + "learning_rate": 0.0008484270686572078, + "loss": 0.1034, + "step": 701 + }, + { + "epoch": 0.14, + "learning_rate": 0.0008479678851868375, + "loss": 0.0996, + "step": 702 + }, + { + "epoch": 0.14, + "learning_rate": 0.0008475081318988704, + "loss": 0.1034, + "step": 703 + }, + { + "epoch": 0.14, + "learning_rate": 0.0008470478095461789, + "loss": 0.1024, + "step": 704 + }, + { + "epoch": 0.14, + "learning_rate": 0.0008465869188825677, + "loss": 0.1036, + "step": 705 + }, + { + "epoch": 0.14, + "learning_rate": 0.000846125460662772, + "loss": 0.1028, + "step": 706 + }, + { + "epoch": 0.14, + "learning_rate": 0.0008456634356424562, + "loss": 0.1058, + "step": 707 + }, + { + "epoch": 0.14, + "learning_rate": 0.0008452008445782133, + "loss": 0.1043, + "step": 708 + }, + { + "epoch": 0.14, + "learning_rate": 0.0008447376882275631, + "loss": 0.1047, + "step": 709 + }, + { + "epoch": 0.14, + "learning_rate": 0.0008442739673489506, + "loss": 0.1031, + "step": 710 + }, + { + "epoch": 0.14, + "learning_rate": 0.000843809682701746, + "loss": 0.1033, + "step": 711 + }, + { + "epoch": 0.14, + "learning_rate": 0.000843344835046242, + "loss": 0.1032, + "step": 712 + }, + { + "epoch": 0.14, + "learning_rate": 0.000842879425143654, + "loss": 0.1046, + "step": 713 + }, + { + "epoch": 0.14, + "learning_rate": 0.0008424134537561175, + "loss": 0.1031, + "step": 714 + }, + { + "epoch": 0.14, + "learning_rate": 0.0008419469216466878, + "loss": 0.1044, + "step": 715 + }, + { + "epoch": 0.14, + "learning_rate": 0.000841479829579338, + "loss": 0.1032, + "step": 716 + }, + { + "epoch": 0.14, + "learning_rate": 0.0008410121783189587, + "loss": 0.1013, + "step": 717 + }, + { + "epoch": 0.14, + "learning_rate": 0.0008405439686313558, + "loss": 0.1027, + "step": 718 + }, + { + "epoch": 0.14, + "learning_rate": 0.0008400752012832501, + "loss": 0.1043, + "step": 719 + }, + { + "epoch": 0.14, + "learning_rate": 0.0008396058770422751, + "loss": 0.1032, + "step": 720 + }, + { + "epoch": 0.14, + "learning_rate": 0.0008391359966769765, + "loss": 0.1032, + "step": 721 + }, + { + "epoch": 0.14, + "learning_rate": 0.0008386655609568106, + "loss": 0.1063, + "step": 722 + }, + { + "epoch": 0.14, + "learning_rate": 0.0008381945706521435, + "loss": 0.1046, + "step": 723 + }, + { + "epoch": 0.14, + "learning_rate": 0.0008377230265342486, + "loss": 0.1034, + "step": 724 + }, + { + "epoch": 0.14, + "learning_rate": 0.0008372509293753072, + "loss": 0.1021, + "step": 725 + }, + { + "epoch": 0.14, + "learning_rate": 0.0008367782799484058, + "loss": 0.1025, + "step": 726 + }, + { + "epoch": 0.14, + "learning_rate": 0.0008363050790275348, + "loss": 0.1037, + "step": 727 + }, + { + "epoch": 0.14, + "learning_rate": 0.0008358313273875886, + "loss": 0.1023, + "step": 728 + }, + { + "epoch": 0.14, + "learning_rate": 0.0008353570258043628, + "loss": 0.1032, + "step": 729 + }, + { + "epoch": 0.14, + "learning_rate": 0.0008348821750545539, + "loss": 0.1026, + "step": 730 + }, + { + "epoch": 0.14, + "learning_rate": 0.0008344067759157572, + "loss": 0.1019, + "step": 731 + }, + { + "epoch": 0.14, + "learning_rate": 0.0008339308291664668, + "loss": 0.1025, + "step": 732 + }, + { + "epoch": 0.14, + "learning_rate": 0.0008334543355860729, + "loss": 0.1053, + "step": 733 + }, + { + "epoch": 0.14, + "learning_rate": 0.0008329772959548614, + "loss": 0.1043, + "step": 734 + }, + { + "epoch": 0.15, + "learning_rate": 0.0008324997110540123, + "loss": 0.1021, + "step": 735 + }, + { + "epoch": 0.15, + "learning_rate": 0.0008320215816655987, + "loss": 0.1047, + "step": 736 + }, + { + "epoch": 0.15, + "learning_rate": 0.0008315429085725852, + "loss": 0.1044, + "step": 737 + }, + { + "epoch": 0.15, + "learning_rate": 0.0008310636925588266, + "loss": 0.1032, + "step": 738 + }, + { + "epoch": 0.15, + "learning_rate": 0.0008305839344090671, + "loss": 0.1048, + "step": 739 + }, + { + "epoch": 0.15, + "learning_rate": 0.0008301036349089384, + "loss": 0.1039, + "step": 740 + }, + { + "epoch": 0.15, + "learning_rate": 0.0008296227948449589, + "loss": 0.1051, + "step": 741 + }, + { + "epoch": 0.15, + "learning_rate": 0.000829141415004532, + "loss": 0.1036, + "step": 742 + }, + { + "epoch": 0.15, + "learning_rate": 0.0008286594961759451, + "loss": 0.1047, + "step": 743 + }, + { + "epoch": 0.15, + "learning_rate": 0.0008281770391483683, + "loss": 0.1015, + "step": 744 + }, + { + "epoch": 0.15, + "learning_rate": 0.0008276940447118528, + "loss": 0.1044, + "step": 745 + }, + { + "epoch": 0.15, + "learning_rate": 0.0008272105136573303, + "loss": 0.1029, + "step": 746 + }, + { + "epoch": 0.15, + "learning_rate": 0.0008267264467766108, + "loss": 0.1024, + "step": 747 + }, + { + "epoch": 0.15, + "learning_rate": 0.0008262418448623819, + "loss": 0.105, + "step": 748 + }, + { + "epoch": 0.15, + "learning_rate": 0.0008257567087082072, + "loss": 0.1043, + "step": 749 + }, + { + "epoch": 0.15, + "learning_rate": 0.0008252710391085256, + "loss": 0.1018, + "step": 750 + }, + { + "epoch": 0.15, + "learning_rate": 0.0008247848368586491, + "loss": 0.1024, + "step": 751 + }, + { + "epoch": 0.15, + "learning_rate": 0.000824298102754762, + "loss": 0.1043, + "step": 752 + }, + { + "epoch": 0.15, + "learning_rate": 0.0008238108375939196, + "loss": 0.1027, + "step": 753 + }, + { + "epoch": 0.15, + "learning_rate": 0.0008233230421740471, + "loss": 0.1047, + "step": 754 + }, + { + "epoch": 0.15, + "learning_rate": 0.0008228347172939375, + "loss": 0.1045, + "step": 755 + }, + { + "epoch": 0.15, + "learning_rate": 0.0008223458637532515, + "loss": 0.1011, + "step": 756 + }, + { + "epoch": 0.15, + "learning_rate": 0.0008218564823525147, + "loss": 0.1019, + "step": 757 + }, + { + "epoch": 0.15, + "learning_rate": 0.0008213665738931178, + "loss": 0.1029, + "step": 758 + }, + { + "epoch": 0.15, + "learning_rate": 0.0008208761391773144, + "loss": 0.1, + "step": 759 + }, + { + "epoch": 0.15, + "learning_rate": 0.0008203851790082196, + "loss": 0.1047, + "step": 760 + }, + { + "epoch": 0.15, + "learning_rate": 0.0008198936941898091, + "loss": 0.1043, + "step": 761 + }, + { + "epoch": 0.15, + "learning_rate": 0.000819401685526918, + "loss": 0.105, + "step": 762 + }, + { + "epoch": 0.15, + "learning_rate": 0.0008189091538252389, + "loss": 0.1011, + "step": 763 + }, + { + "epoch": 0.15, + "learning_rate": 0.000818416099891321, + "loss": 0.1035, + "step": 764 + }, + { + "epoch": 0.15, + "learning_rate": 0.000817922524532569, + "loss": 0.1027, + "step": 765 + }, + { + "epoch": 0.15, + "learning_rate": 0.0008174284285572407, + "loss": 0.1008, + "step": 766 + }, + { + "epoch": 0.15, + "learning_rate": 0.0008169338127744474, + "loss": 0.1025, + "step": 767 + }, + { + "epoch": 0.15, + "learning_rate": 0.0008164386779941508, + "loss": 0.1049, + "step": 768 + }, + { + "epoch": 0.15, + "learning_rate": 0.0008159430250271631, + "loss": 0.1025, + "step": 769 + }, + { + "epoch": 0.15, + "learning_rate": 0.0008154468546851445, + "loss": 0.1014, + "step": 770 + }, + { + "epoch": 0.15, + "learning_rate": 0.0008149501677806029, + "loss": 0.1032, + "step": 771 + }, + { + "epoch": 0.15, + "learning_rate": 0.0008144529651268919, + "loss": 0.1018, + "step": 772 + }, + { + "epoch": 0.15, + "learning_rate": 0.0008139552475382098, + "loss": 0.1046, + "step": 773 + }, + { + "epoch": 0.15, + "learning_rate": 0.0008134570158295976, + "loss": 0.1038, + "step": 774 + }, + { + "epoch": 0.15, + "learning_rate": 0.000812958270816939, + "loss": 0.1046, + "step": 775 + }, + { + "epoch": 0.15, + "learning_rate": 0.000812459013316958, + "loss": 0.1042, + "step": 776 + }, + { + "epoch": 0.15, + "learning_rate": 0.0008119592441472172, + "loss": 0.1029, + "step": 777 + }, + { + "epoch": 0.15, + "learning_rate": 0.0008114589641261181, + "loss": 0.1044, + "step": 778 + }, + { + "epoch": 0.15, + "learning_rate": 0.0008109581740728981, + "loss": 0.1016, + "step": 779 + }, + { + "epoch": 0.15, + "learning_rate": 0.0008104568748076297, + "loss": 0.1043, + "step": 780 + }, + { + "epoch": 0.15, + "learning_rate": 0.0008099550671512201, + "loss": 0.1024, + "step": 781 + }, + { + "epoch": 0.15, + "learning_rate": 0.0008094527519254079, + "loss": 0.1025, + "step": 782 + }, + { + "epoch": 0.15, + "learning_rate": 0.0008089499299527637, + "loss": 0.1038, + "step": 783 + }, + { + "epoch": 0.15, + "learning_rate": 0.0008084466020566876, + "loss": 0.1028, + "step": 784 + }, + { + "epoch": 0.16, + "learning_rate": 0.0008079427690614083, + "loss": 0.1025, + "step": 785 + }, + { + "epoch": 0.16, + "learning_rate": 0.0008074384317919811, + "loss": 0.1015, + "step": 786 + }, + { + "epoch": 0.16, + "learning_rate": 0.0008069335910742883, + "loss": 0.102, + "step": 787 + }, + { + "epoch": 0.16, + "learning_rate": 0.0008064282477350353, + "loss": 0.1033, + "step": 788 + }, + { + "epoch": 0.16, + "learning_rate": 0.0008059224026017512, + "loss": 0.1015, + "step": 789 + }, + { + "epoch": 0.16, + "learning_rate": 0.0008054160565027869, + "loss": 0.1047, + "step": 790 + }, + { + "epoch": 0.16, + "learning_rate": 0.0008049092102673135, + "loss": 0.1026, + "step": 791 + }, + { + "epoch": 0.16, + "learning_rate": 0.000804401864725321, + "loss": 0.107, + "step": 792 + }, + { + "epoch": 0.16, + "learning_rate": 0.0008038940207076174, + "loss": 0.1019, + "step": 793 + }, + { + "epoch": 0.16, + "learning_rate": 0.0008033856790458263, + "loss": 0.1014, + "step": 794 + }, + { + "epoch": 0.16, + "learning_rate": 0.000802876840572387, + "loss": 0.1001, + "step": 795 + }, + { + "epoch": 0.16, + "learning_rate": 0.0008023675061205518, + "loss": 0.1006, + "step": 796 + }, + { + "epoch": 0.16, + "learning_rate": 0.0008018576765243857, + "loss": 0.1031, + "step": 797 + }, + { + "epoch": 0.16, + "learning_rate": 0.000801347352618764, + "loss": 0.1045, + "step": 798 + }, + { + "epoch": 0.16, + "learning_rate": 0.0008008365352393718, + "loss": 0.1027, + "step": 799 + }, + { + "epoch": 0.16, + "learning_rate": 0.0008003252252227022, + "loss": 0.1051, + "step": 800 + }, + { + "epoch": 0.16, + "learning_rate": 0.000799813423406055, + "loss": 0.1026, + "step": 801 + }, + { + "epoch": 0.16, + "learning_rate": 0.0007993011306275354, + "loss": 0.1013, + "step": 802 + }, + { + "epoch": 0.16, + "learning_rate": 0.0007987883477260523, + "loss": 0.1006, + "step": 803 + }, + { + "epoch": 0.16, + "learning_rate": 0.0007982750755413178, + "loss": 0.1021, + "step": 804 + }, + { + "epoch": 0.16, + "learning_rate": 0.0007977613149138445, + "loss": 0.1037, + "step": 805 + }, + { + "epoch": 0.16, + "learning_rate": 0.0007972470666849456, + "loss": 0.102, + "step": 806 + }, + { + "epoch": 0.16, + "learning_rate": 0.0007967323316967323, + "loss": 0.0997, + "step": 807 + }, + { + "epoch": 0.16, + "learning_rate": 0.0007962171107921128, + "loss": 0.1037, + "step": 808 + }, + { + "epoch": 0.16, + "learning_rate": 0.0007957014048147914, + "loss": 0.1019, + "step": 809 + }, + { + "epoch": 0.16, + "learning_rate": 0.0007951852146092667, + "loss": 0.1025, + "step": 810 + }, + { + "epoch": 0.16, + "learning_rate": 0.0007946685410208296, + "loss": 0.102, + "step": 811 + }, + { + "epoch": 0.16, + "learning_rate": 0.0007941513848955634, + "loss": 0.1015, + "step": 812 + }, + { + "epoch": 0.16, + "learning_rate": 0.0007936337470803415, + "loss": 0.1023, + "step": 813 + }, + { + "epoch": 0.16, + "learning_rate": 0.0007931156284228254, + "loss": 0.1044, + "step": 814 + }, + { + "epoch": 0.16, + "learning_rate": 0.0007925970297714648, + "loss": 0.1031, + "step": 815 + }, + { + "epoch": 0.16, + "learning_rate": 0.0007920779519754948, + "loss": 0.1006, + "step": 816 + }, + { + "epoch": 0.16, + "learning_rate": 0.0007915583958849357, + "loss": 0.1024, + "step": 817 + }, + { + "epoch": 0.16, + "learning_rate": 0.0007910383623505904, + "loss": 0.1017, + "step": 818 + }, + { + "epoch": 0.16, + "learning_rate": 0.0007905178522240443, + "loss": 0.1015, + "step": 819 + }, + { + "epoch": 0.16, + "learning_rate": 0.0007899968663576626, + "loss": 0.1027, + "step": 820 + }, + { + "epoch": 0.16, + "learning_rate": 0.00078947540560459, + "loss": 0.1039, + "step": 821 + }, + { + "epoch": 0.16, + "learning_rate": 0.0007889534708187491, + "loss": 0.1039, + "step": 822 + }, + { + "epoch": 0.16, + "learning_rate": 0.0007884310628548379, + "loss": 0.1016, + "step": 823 + }, + { + "epoch": 0.16, + "learning_rate": 0.0007879081825683298, + "loss": 0.1035, + "step": 824 + }, + { + "epoch": 0.16, + "learning_rate": 0.0007873848308154719, + "loss": 0.1014, + "step": 825 + }, + { + "epoch": 0.16, + "learning_rate": 0.0007868610084532827, + "loss": 0.1042, + "step": 826 + }, + { + "epoch": 0.16, + "learning_rate": 0.0007863367163395518, + "loss": 0.103, + "step": 827 + }, + { + "epoch": 0.16, + "learning_rate": 0.0007858119553328382, + "loss": 0.1001, + "step": 828 + }, + { + "epoch": 0.16, + "learning_rate": 0.0007852867262924683, + "loss": 0.1028, + "step": 829 + }, + { + "epoch": 0.16, + "learning_rate": 0.0007847610300785352, + "loss": 0.1024, + "step": 830 + }, + { + "epoch": 0.16, + "learning_rate": 0.0007842348675518967, + "loss": 0.1027, + "step": 831 + }, + { + "epoch": 0.16, + "learning_rate": 0.0007837082395741748, + "loss": 0.1044, + "step": 832 + }, + { + "epoch": 0.16, + "learning_rate": 0.0007831811470077531, + "loss": 0.1014, + "step": 833 + }, + { + "epoch": 0.16, + "learning_rate": 0.0007826535907157763, + "loss": 0.103, + "step": 834 + }, + { + "epoch": 0.16, + "learning_rate": 0.0007821255715621486, + "loss": 0.1021, + "step": 835 + }, + { + "epoch": 0.17, + "learning_rate": 0.000781597090411532, + "loss": 0.1008, + "step": 836 + }, + { + "epoch": 0.17, + "learning_rate": 0.0007810681481293447, + "loss": 0.1073, + "step": 837 + }, + { + "epoch": 0.17, + "learning_rate": 0.0007805387455817605, + "loss": 0.1, + "step": 838 + }, + { + "epoch": 0.17, + "learning_rate": 0.0007800088836357071, + "loss": 0.1037, + "step": 839 + }, + { + "epoch": 0.17, + "learning_rate": 0.000779478563158864, + "loss": 0.1009, + "step": 840 + }, + { + "epoch": 0.17, + "learning_rate": 0.0007789477850196614, + "loss": 0.104, + "step": 841 + }, + { + "epoch": 0.17, + "learning_rate": 0.0007784165500872796, + "loss": 0.1022, + "step": 842 + }, + { + "epoch": 0.17, + "learning_rate": 0.0007778848592316467, + "loss": 0.103, + "step": 843 + }, + { + "epoch": 0.17, + "learning_rate": 0.0007773527133234372, + "loss": 0.1027, + "step": 844 + }, + { + "epoch": 0.17, + "learning_rate": 0.0007768201132340711, + "loss": 0.1047, + "step": 845 + }, + { + "epoch": 0.17, + "learning_rate": 0.0007762870598357114, + "loss": 0.1025, + "step": 846 + }, + { + "epoch": 0.17, + "learning_rate": 0.0007757535540012646, + "loss": 0.1036, + "step": 847 + }, + { + "epoch": 0.17, + "learning_rate": 0.0007752195966043771, + "loss": 0.1048, + "step": 848 + }, + { + "epoch": 0.17, + "learning_rate": 0.0007746851885194351, + "loss": 0.1033, + "step": 849 + }, + { + "epoch": 0.17, + "learning_rate": 0.0007741503306215628, + "loss": 0.1014, + "step": 850 + }, + { + "epoch": 0.17, + "learning_rate": 0.0007736150237866213, + "loss": 0.1039, + "step": 851 + }, + { + "epoch": 0.17, + "learning_rate": 0.0007730792688912064, + "loss": 0.0999, + "step": 852 + }, + { + "epoch": 0.17, + "learning_rate": 0.0007725430668126479, + "loss": 0.105, + "step": 853 + }, + { + "epoch": 0.17, + "learning_rate": 0.0007720064184290077, + "loss": 0.102, + "step": 854 + }, + { + "epoch": 0.17, + "learning_rate": 0.0007714693246190787, + "loss": 0.1034, + "step": 855 + }, + { + "epoch": 0.17, + "learning_rate": 0.0007709317862623832, + "loss": 0.1052, + "step": 856 + }, + { + "epoch": 0.17, + "learning_rate": 0.0007703938042391716, + "loss": 0.1042, + "step": 857 + }, + { + "epoch": 0.17, + "learning_rate": 0.0007698553794304204, + "loss": 0.1047, + "step": 858 + }, + { + "epoch": 0.17, + "learning_rate": 0.0007693165127178317, + "loss": 0.1022, + "step": 859 + }, + { + "epoch": 0.17, + "learning_rate": 0.0007687772049838306, + "loss": 0.1032, + "step": 860 + }, + { + "epoch": 0.17, + "learning_rate": 0.0007682374571115651, + "loss": 0.1046, + "step": 861 + }, + { + "epoch": 0.17, + "learning_rate": 0.0007676972699849038, + "loss": 0.1044, + "step": 862 + }, + { + "epoch": 0.17, + "learning_rate": 0.0007671566444884341, + "loss": 0.1019, + "step": 863 + }, + { + "epoch": 0.17, + "learning_rate": 0.0007666155815074618, + "loss": 0.1034, + "step": 864 + }, + { + "epoch": 0.17, + "learning_rate": 0.000766074081928009, + "loss": 0.1048, + "step": 865 + }, + { + "epoch": 0.17, + "learning_rate": 0.0007655321466368126, + "loss": 0.1021, + "step": 866 + }, + { + "epoch": 0.17, + "learning_rate": 0.0007649897765213228, + "loss": 0.1035, + "step": 867 + }, + { + "epoch": 0.17, + "learning_rate": 0.0007644469724697025, + "loss": 0.1037, + "step": 868 + }, + { + "epoch": 0.17, + "learning_rate": 0.0007639037353708248, + "loss": 0.1016, + "step": 869 + }, + { + "epoch": 0.17, + "learning_rate": 0.0007633600661142718, + "loss": 0.1016, + "step": 870 + }, + { + "epoch": 0.17, + "learning_rate": 0.0007628159655903335, + "loss": 0.1028, + "step": 871 + }, + { + "epoch": 0.17, + "learning_rate": 0.0007622714346900061, + "loss": 0.101, + "step": 872 + }, + { + "epoch": 0.17, + "learning_rate": 0.0007617264743049905, + "loss": 0.1016, + "step": 873 + }, + { + "epoch": 0.17, + "learning_rate": 0.0007611810853276909, + "loss": 0.1006, + "step": 874 + }, + { + "epoch": 0.17, + "learning_rate": 0.0007606352686512133, + "loss": 0.1016, + "step": 875 + }, + { + "epoch": 0.17, + "learning_rate": 0.0007600890251693646, + "loss": 0.1019, + "step": 876 + }, + { + "epoch": 0.17, + "learning_rate": 0.0007595423557766497, + "loss": 0.1029, + "step": 877 + }, + { + "epoch": 0.17, + "learning_rate": 0.0007589952613682716, + "loss": 0.1012, + "step": 878 + }, + { + "epoch": 0.17, + "learning_rate": 0.0007584477428401293, + "loss": 0.1026, + "step": 879 + }, + { + "epoch": 0.17, + "learning_rate": 0.000757899801088816, + "loss": 0.1015, + "step": 880 + }, + { + "epoch": 0.17, + "learning_rate": 0.000757351437011618, + "loss": 0.1001, + "step": 881 + }, + { + "epoch": 0.17, + "learning_rate": 0.0007568026515065136, + "loss": 0.1029, + "step": 882 + }, + { + "epoch": 0.17, + "learning_rate": 0.0007562534454721706, + "loss": 0.1033, + "step": 883 + }, + { + "epoch": 0.17, + "learning_rate": 0.0007557038198079457, + "loss": 0.1052, + "step": 884 + }, + { + "epoch": 0.17, + "learning_rate": 0.0007551537754138831, + "loss": 0.1021, + "step": 885 + }, + { + "epoch": 0.18, + "learning_rate": 0.0007546033131907121, + "loss": 0.1025, + "step": 886 + }, + { + "epoch": 0.18, + "learning_rate": 0.0007540524340398469, + "loss": 0.1031, + "step": 887 + }, + { + "epoch": 0.18, + "learning_rate": 0.0007535011388633839, + "loss": 0.1049, + "step": 888 + }, + { + "epoch": 0.18, + "learning_rate": 0.0007529494285641006, + "loss": 0.1021, + "step": 889 + }, + { + "epoch": 0.18, + "learning_rate": 0.0007523973040454551, + "loss": 0.1024, + "step": 890 + }, + { + "epoch": 0.18, + "learning_rate": 0.000751844766211583, + "loss": 0.1045, + "step": 891 + }, + { + "epoch": 0.18, + "learning_rate": 0.0007512918159672973, + "loss": 0.1011, + "step": 892 + }, + { + "epoch": 0.18, + "learning_rate": 0.0007507384542180857, + "loss": 0.1026, + "step": 893 + }, + { + "epoch": 0.18, + "learning_rate": 0.0007501846818701106, + "loss": 0.1013, + "step": 894 + }, + { + "epoch": 0.18, + "learning_rate": 0.0007496304998302062, + "loss": 0.1012, + "step": 895 + }, + { + "epoch": 0.18, + "learning_rate": 0.0007490759090058778, + "loss": 0.1, + "step": 896 + }, + { + "epoch": 0.18, + "learning_rate": 0.0007485209103052999, + "loss": 0.1021, + "step": 897 + }, + { + "epoch": 0.18, + "learning_rate": 0.0007479655046373151, + "loss": 0.1033, + "step": 898 + }, + { + "epoch": 0.18, + "learning_rate": 0.0007474096929114323, + "loss": 0.1018, + "step": 899 + }, + { + "epoch": 0.18, + "learning_rate": 0.0007468534760378258, + "loss": 0.103, + "step": 900 + }, + { + "epoch": 0.18, + "learning_rate": 0.0007462968549273326, + "loss": 0.0987, + "step": 901 + }, + { + "epoch": 0.18, + "learning_rate": 0.0007457398304914523, + "loss": 0.1025, + "step": 902 + }, + { + "epoch": 0.18, + "learning_rate": 0.0007451824036423446, + "loss": 0.1017, + "step": 903 + }, + { + "epoch": 0.18, + "learning_rate": 0.0007446245752928285, + "loss": 0.104, + "step": 904 + }, + { + "epoch": 0.18, + "learning_rate": 0.0007440663463563799, + "loss": 0.1015, + "step": 905 + }, + { + "epoch": 0.18, + "learning_rate": 0.0007435077177471314, + "loss": 0.0978, + "step": 906 + }, + { + "epoch": 0.18, + "learning_rate": 0.0007429486903798697, + "loss": 0.1031, + "step": 907 + }, + { + "epoch": 0.18, + "learning_rate": 0.0007423892651700345, + "loss": 0.1034, + "step": 908 + }, + { + "epoch": 0.18, + "learning_rate": 0.0007418294430337169, + "loss": 0.1041, + "step": 909 + }, + { + "epoch": 0.18, + "learning_rate": 0.0007412692248876583, + "loss": 0.0996, + "step": 910 + }, + { + "epoch": 0.18, + "learning_rate": 0.0007407086116492484, + "loss": 0.1011, + "step": 911 + }, + { + "epoch": 0.18, + "learning_rate": 0.0007401476042365238, + "loss": 0.101, + "step": 912 + }, + { + "epoch": 0.18, + "learning_rate": 0.000739586203568167, + "loss": 0.1001, + "step": 913 + }, + { + "epoch": 0.18, + "learning_rate": 0.0007390244105635036, + "loss": 0.1021, + "step": 914 + }, + { + "epoch": 0.18, + "learning_rate": 0.0007384622261425026, + "loss": 0.1008, + "step": 915 + }, + { + "epoch": 0.18, + "learning_rate": 0.0007378996512257735, + "loss": 0.1039, + "step": 916 + }, + { + "epoch": 0.18, + "learning_rate": 0.0007373366867345655, + "loss": 0.1003, + "step": 917 + }, + { + "epoch": 0.18, + "learning_rate": 0.0007367733335907654, + "loss": 0.1029, + "step": 918 + }, + { + "epoch": 0.18, + "learning_rate": 0.0007362095927168968, + "loss": 0.1034, + "step": 919 + }, + { + "epoch": 0.18, + "learning_rate": 0.000735645465036118, + "loss": 0.1026, + "step": 920 + }, + { + "epoch": 0.18, + "learning_rate": 0.0007350809514722208, + "loss": 0.1007, + "step": 921 + }, + { + "epoch": 0.18, + "learning_rate": 0.0007345160529496292, + "loss": 0.1023, + "step": 922 + }, + { + "epoch": 0.18, + "learning_rate": 0.0007339507703933969, + "loss": 0.1033, + "step": 923 + }, + { + "epoch": 0.18, + "learning_rate": 0.0007333851047292068, + "loss": 0.102, + "step": 924 + }, + { + "epoch": 0.18, + "learning_rate": 0.0007328190568833697, + "loss": 0.0992, + "step": 925 + }, + { + "epoch": 0.18, + "learning_rate": 0.0007322526277828216, + "loss": 0.1032, + "step": 926 + }, + { + "epoch": 0.18, + "learning_rate": 0.0007316858183551227, + "loss": 0.1001, + "step": 927 + }, + { + "epoch": 0.18, + "learning_rate": 0.0007311186295284567, + "loss": 0.1006, + "step": 928 + }, + { + "epoch": 0.18, + "learning_rate": 0.0007305510622316281, + "loss": 0.1009, + "step": 929 + }, + { + "epoch": 0.18, + "learning_rate": 0.0007299831173940612, + "loss": 0.1024, + "step": 930 + }, + { + "epoch": 0.18, + "learning_rate": 0.0007294147959457988, + "loss": 0.1036, + "step": 931 + }, + { + "epoch": 0.18, + "learning_rate": 0.0007288460988175001, + "loss": 0.1009, + "step": 932 + }, + { + "epoch": 0.18, + "learning_rate": 0.0007282770269404395, + "loss": 0.1049, + "step": 933 + }, + { + "epoch": 0.18, + "learning_rate": 0.0007277075812465054, + "loss": 0.1011, + "step": 934 + }, + { + "epoch": 0.18, + "learning_rate": 0.0007271377626681981, + "loss": 0.1013, + "step": 935 + }, + { + "epoch": 0.18, + "learning_rate": 0.0007265675721386285, + "loss": 0.1005, + "step": 936 + }, + { + "epoch": 0.19, + "learning_rate": 0.0007259970105915167, + "loss": 0.1018, + "step": 937 + }, + { + "epoch": 0.19, + "learning_rate": 0.0007254260789611906, + "loss": 0.1009, + "step": 938 + }, + { + "epoch": 0.19, + "learning_rate": 0.0007248547781825836, + "loss": 0.1037, + "step": 939 + }, + { + "epoch": 0.19, + "learning_rate": 0.0007242831091912339, + "loss": 0.1007, + "step": 940 + }, + { + "epoch": 0.19, + "learning_rate": 0.0007237110729232826, + "loss": 0.1018, + "step": 941 + }, + { + "epoch": 0.19, + "learning_rate": 0.0007231386703154723, + "loss": 0.0998, + "step": 942 + }, + { + "epoch": 0.19, + "learning_rate": 0.0007225659023051455, + "loss": 0.1022, + "step": 943 + }, + { + "epoch": 0.19, + "learning_rate": 0.0007219927698302431, + "loss": 0.1033, + "step": 944 + }, + { + "epoch": 0.19, + "learning_rate": 0.0007214192738293026, + "loss": 0.1016, + "step": 945 + }, + { + "epoch": 0.19, + "learning_rate": 0.0007208454152414571, + "loss": 0.1011, + "step": 946 + }, + { + "epoch": 0.19, + "learning_rate": 0.0007202711950064334, + "loss": 0.101, + "step": 947 + }, + { + "epoch": 0.19, + "learning_rate": 0.0007196966140645503, + "loss": 0.1014, + "step": 948 + }, + { + "epoch": 0.19, + "learning_rate": 0.0007191216733567174, + "loss": 0.1001, + "step": 949 + }, + { + "epoch": 0.19, + "learning_rate": 0.0007185463738244337, + "loss": 0.1027, + "step": 950 + }, + { + "epoch": 0.19, + "learning_rate": 0.0007179707164097852, + "loss": 0.1003, + "step": 951 + }, + { + "epoch": 0.19, + "learning_rate": 0.0007173947020554446, + "loss": 0.1008, + "step": 952 + }, + { + "epoch": 0.19, + "learning_rate": 0.0007168183317046685, + "loss": 0.1004, + "step": 953 + }, + { + "epoch": 0.19, + "learning_rate": 0.0007162416063012973, + "loss": 0.1021, + "step": 954 + }, + { + "epoch": 0.19, + "learning_rate": 0.0007156645267897518, + "loss": 0.1003, + "step": 955 + }, + { + "epoch": 0.19, + "learning_rate": 0.0007150870941150336, + "loss": 0.0977, + "step": 956 + }, + { + "epoch": 0.19, + "learning_rate": 0.0007145093092227218, + "loss": 0.1004, + "step": 957 + }, + { + "epoch": 0.19, + "learning_rate": 0.0007139311730589729, + "loss": 0.1034, + "step": 958 + }, + { + "epoch": 0.19, + "learning_rate": 0.0007133526865705182, + "loss": 0.1032, + "step": 959 + }, + { + "epoch": 0.19, + "learning_rate": 0.0007127738507046632, + "loss": 0.1015, + "step": 960 + }, + { + "epoch": 0.19, + "learning_rate": 0.0007121946664092849, + "loss": 0.0995, + "step": 961 + }, + { + "epoch": 0.19, + "learning_rate": 0.0007116151346328315, + "loss": 0.1046, + "step": 962 + }, + { + "epoch": 0.19, + "learning_rate": 0.0007110352563243197, + "loss": 0.1059, + "step": 963 + }, + { + "epoch": 0.19, + "learning_rate": 0.0007104550324333338, + "loss": 0.1008, + "step": 964 + }, + { + "epoch": 0.19, + "learning_rate": 0.0007098744639100244, + "loss": 0.1013, + "step": 965 + }, + { + "epoch": 0.19, + "learning_rate": 0.0007092935517051058, + "loss": 0.0993, + "step": 966 + }, + { + "epoch": 0.19, + "learning_rate": 0.0007087122967698554, + "loss": 0.1012, + "step": 967 + }, + { + "epoch": 0.19, + "learning_rate": 0.0007081307000561121, + "loss": 0.1006, + "step": 968 + }, + { + "epoch": 0.19, + "learning_rate": 0.0007075487625162742, + "loss": 0.1017, + "step": 969 + }, + { + "epoch": 0.19, + "learning_rate": 0.0007069664851032982, + "loss": 0.1035, + "step": 970 + }, + { + "epoch": 0.19, + "learning_rate": 0.0007063838687706971, + "loss": 0.1057, + "step": 971 + }, + { + "epoch": 0.19, + "learning_rate": 0.0007058009144725388, + "loss": 0.099, + "step": 972 + }, + { + "epoch": 0.19, + "learning_rate": 0.0007052176231634451, + "loss": 0.1043, + "step": 973 + }, + { + "epoch": 0.19, + "learning_rate": 0.0007046339957985891, + "loss": 0.1041, + "step": 974 + }, + { + "epoch": 0.19, + "learning_rate": 0.0007040500333336944, + "loss": 0.1034, + "step": 975 + }, + { + "epoch": 0.19, + "learning_rate": 0.0007034657367250336, + "loss": 0.1012, + "step": 976 + }, + { + "epoch": 0.19, + "learning_rate": 0.0007028811069294263, + "loss": 0.1056, + "step": 977 + }, + { + "epoch": 0.19, + "learning_rate": 0.0007022961449042376, + "loss": 0.1045, + "step": 978 + }, + { + "epoch": 0.19, + "learning_rate": 0.0007017108516073769, + "loss": 0.105, + "step": 979 + }, + { + "epoch": 0.19, + "learning_rate": 0.0007011252279972958, + "loss": 0.1032, + "step": 980 + }, + { + "epoch": 0.19, + "learning_rate": 0.0007005392750329868, + "loss": 0.1025, + "step": 981 + }, + { + "epoch": 0.19, + "learning_rate": 0.0006999529936739821, + "loss": 0.1005, + "step": 982 + }, + { + "epoch": 0.19, + "learning_rate": 0.0006993663848803513, + "loss": 0.1026, + "step": 983 + }, + { + "epoch": 0.19, + "learning_rate": 0.0006987794496127003, + "loss": 0.1014, + "step": 984 + }, + { + "epoch": 0.19, + "learning_rate": 0.0006981921888321699, + "loss": 0.1031, + "step": 985 + }, + { + "epoch": 0.19, + "learning_rate": 0.0006976046035004334, + "loss": 0.1, + "step": 986 + }, + { + "epoch": 0.19, + "learning_rate": 0.0006970166945796961, + "loss": 0.1034, + "step": 987 + }, + { + "epoch": 0.2, + "learning_rate": 0.0006964284630326927, + "loss": 0.1026, + "step": 988 + }, + { + "epoch": 0.2, + "learning_rate": 0.0006958399098226868, + "loss": 0.1, + "step": 989 + }, + { + "epoch": 0.2, + "learning_rate": 0.0006952510359134681, + "loss": 0.1011, + "step": 990 + }, + { + "epoch": 0.2, + "learning_rate": 0.000694661842269352, + "loss": 0.1001, + "step": 991 + }, + { + "epoch": 0.2, + "learning_rate": 0.0006940723298551772, + "loss": 0.1006, + "step": 992 + }, + { + "epoch": 0.2, + "learning_rate": 0.0006934824996363045, + "loss": 0.101, + "step": 993 + }, + { + "epoch": 0.2, + "learning_rate": 0.000692892352578615, + "loss": 0.1031, + "step": 994 + }, + { + "epoch": 0.2, + "learning_rate": 0.0006923018896485089, + "loss": 0.1027, + "step": 995 + }, + { + "epoch": 0.2, + "learning_rate": 0.0006917111118129035, + "loss": 0.0999, + "step": 996 + }, + { + "epoch": 0.2, + "learning_rate": 0.0006911200200392315, + "loss": 0.1012, + "step": 997 + }, + { + "epoch": 0.2, + "learning_rate": 0.0006905286152954402, + "loss": 0.1019, + "step": 998 + }, + { + "epoch": 0.2, + "learning_rate": 0.0006899368985499893, + "loss": 0.1035, + "step": 999 + }, + { + "epoch": 0.2, + "learning_rate": 0.0006893448707718491, + "loss": 0.1041, + "step": 1000 + }, + { + "epoch": 0.2, + "learning_rate": 0.0006887525329304994, + "loss": 0.1031, + "step": 1001 + }, + { + "epoch": 0.2, + "learning_rate": 0.0006881598859959277, + "loss": 0.1022, + "step": 1002 + }, + { + "epoch": 0.2, + "learning_rate": 0.000687566930938628, + "loss": 0.1011, + "step": 1003 + }, + { + "epoch": 0.2, + "learning_rate": 0.0006869736687295984, + "loss": 0.1027, + "step": 1004 + }, + { + "epoch": 0.2, + "learning_rate": 0.0006863801003403403, + "loss": 0.1006, + "step": 1005 + }, + { + "epoch": 0.2, + "learning_rate": 0.0006857862267428563, + "loss": 0.1001, + "step": 1006 + }, + { + "epoch": 0.2, + "learning_rate": 0.000685192048909649, + "loss": 0.1014, + "step": 1007 + }, + { + "epoch": 0.2, + "learning_rate": 0.0006845975678137189, + "loss": 0.1032, + "step": 1008 + }, + { + "epoch": 0.2, + "learning_rate": 0.0006840027844285632, + "loss": 0.1022, + "step": 1009 + }, + { + "epoch": 0.2, + "learning_rate": 0.0006834076997281745, + "loss": 0.1016, + "step": 1010 + }, + { + "epoch": 0.2, + "learning_rate": 0.0006828123146870383, + "loss": 0.1048, + "step": 1011 + }, + { + "epoch": 0.2, + "learning_rate": 0.0006822166302801322, + "loss": 0.1019, + "step": 1012 + }, + { + "epoch": 0.2, + "learning_rate": 0.0006816206474829238, + "loss": 0.1033, + "step": 1013 + }, + { + "epoch": 0.2, + "learning_rate": 0.0006810243672713698, + "loss": 0.0988, + "step": 1014 + }, + { + "epoch": 0.2, + "learning_rate": 0.0006804277906219135, + "loss": 0.0996, + "step": 1015 + }, + { + "epoch": 0.2, + "learning_rate": 0.000679830918511484, + "loss": 0.1, + "step": 1016 + }, + { + "epoch": 0.2, + "learning_rate": 0.0006792337519174933, + "loss": 0.1003, + "step": 1017 + }, + { + "epoch": 0.2, + "learning_rate": 0.0006786362918178372, + "loss": 0.1003, + "step": 1018 + }, + { + "epoch": 0.2, + "learning_rate": 0.0006780385391908908, + "loss": 0.1016, + "step": 1019 + }, + { + "epoch": 0.2, + "learning_rate": 0.0006774404950155087, + "loss": 0.1005, + "step": 1020 + }, + { + "epoch": 0.2, + "learning_rate": 0.000676842160271023, + "loss": 0.1037, + "step": 1021 + }, + { + "epoch": 0.2, + "learning_rate": 0.0006762435359372415, + "loss": 0.1021, + "step": 1022 + }, + { + "epoch": 0.2, + "learning_rate": 0.0006756446229944464, + "loss": 0.1034, + "step": 1023 + }, + { + "epoch": 0.2, + "learning_rate": 0.0006750454224233924, + "loss": 0.1004, + "step": 1024 + }, + { + "epoch": 0.2, + "learning_rate": 0.0006744459352053051, + "loss": 0.0983, + "step": 1025 + }, + { + "epoch": 0.2, + "learning_rate": 0.0006738461623218794, + "loss": 0.1009, + "step": 1026 + }, + { + "epoch": 0.2, + "learning_rate": 0.0006732461047552787, + "loss": 0.1027, + "step": 1027 + }, + { + "epoch": 0.2, + "learning_rate": 0.0006726457634881316, + "loss": 0.1018, + "step": 1028 + }, + { + "epoch": 0.2, + "learning_rate": 0.000672045139503532, + "loss": 0.1004, + "step": 1029 + }, + { + "epoch": 0.2, + "learning_rate": 0.0006714442337850364, + "loss": 0.1032, + "step": 1030 + }, + { + "epoch": 0.2, + "learning_rate": 0.0006708430473166628, + "loss": 0.1018, + "step": 1031 + }, + { + "epoch": 0.2, + "learning_rate": 0.0006702415810828889, + "loss": 0.1031, + "step": 1032 + }, + { + "epoch": 0.2, + "learning_rate": 0.0006696398360686506, + "loss": 0.1038, + "step": 1033 + }, + { + "epoch": 0.2, + "learning_rate": 0.0006690378132593403, + "loss": 0.0996, + "step": 1034 + }, + { + "epoch": 0.2, + "learning_rate": 0.0006684355136408052, + "loss": 0.1032, + "step": 1035 + }, + { + "epoch": 0.2, + "learning_rate": 0.0006678329381993458, + "loss": 0.1012, + "step": 1036 + }, + { + "epoch": 0.2, + "learning_rate": 0.0006672300879217145, + "loss": 0.1021, + "step": 1037 + }, + { + "epoch": 0.21, + "learning_rate": 0.0006666269637951134, + "loss": 0.1007, + "step": 1038 + }, + { + "epoch": 0.21, + "learning_rate": 0.0006660235668071935, + "loss": 0.1017, + "step": 1039 + }, + { + "epoch": 0.21, + "learning_rate": 0.0006654198979460521, + "loss": 0.1005, + "step": 1040 + }, + { + "epoch": 0.21, + "learning_rate": 0.0006648159582002322, + "loss": 0.0992, + "step": 1041 + }, + { + "epoch": 0.21, + "learning_rate": 0.0006642117485587202, + "loss": 0.1048, + "step": 1042 + }, + { + "epoch": 0.21, + "learning_rate": 0.000663607270010944, + "loss": 0.1029, + "step": 1043 + }, + { + "epoch": 0.21, + "learning_rate": 0.0006630025235467727, + "loss": 0.1014, + "step": 1044 + }, + { + "epoch": 0.21, + "learning_rate": 0.0006623975101565137, + "loss": 0.1015, + "step": 1045 + }, + { + "epoch": 0.21, + "learning_rate": 0.0006617922308309115, + "loss": 0.1006, + "step": 1046 + }, + { + "epoch": 0.21, + "learning_rate": 0.0006611866865611457, + "loss": 0.1029, + "step": 1047 + }, + { + "epoch": 0.21, + "learning_rate": 0.0006605808783388308, + "loss": 0.1022, + "step": 1048 + }, + { + "epoch": 0.21, + "learning_rate": 0.0006599748071560125, + "loss": 0.0992, + "step": 1049 + }, + { + "epoch": 0.21, + "learning_rate": 0.0006593684740051677, + "loss": 0.1003, + "step": 1050 + }, + { + "epoch": 0.21, + "learning_rate": 0.0006587618798792023, + "loss": 0.1, + "step": 1051 + }, + { + "epoch": 0.21, + "learning_rate": 0.0006581550257714488, + "loss": 0.1004, + "step": 1052 + }, + { + "epoch": 0.21, + "learning_rate": 0.0006575479126756662, + "loss": 0.0996, + "step": 1053 + }, + { + "epoch": 0.21, + "learning_rate": 0.0006569405415860378, + "loss": 0.0989, + "step": 1054 + }, + { + "epoch": 0.21, + "learning_rate": 0.0006563329134971685, + "loss": 0.1029, + "step": 1055 + }, + { + "epoch": 0.21, + "learning_rate": 0.0006557250294040849, + "loss": 0.0976, + "step": 1056 + }, + { + "epoch": 0.21, + "learning_rate": 0.0006551168903022323, + "loss": 0.1014, + "step": 1057 + }, + { + "epoch": 0.21, + "learning_rate": 0.0006545084971874737, + "loss": 0.1017, + "step": 1058 + }, + { + "epoch": 0.21, + "learning_rate": 0.0006538998510560883, + "loss": 0.0998, + "step": 1059 + }, + { + "epoch": 0.21, + "learning_rate": 0.0006532909529047693, + "loss": 0.1024, + "step": 1060 + }, + { + "epoch": 0.21, + "learning_rate": 0.0006526818037306228, + "loss": 0.1036, + "step": 1061 + }, + { + "epoch": 0.21, + "learning_rate": 0.0006520724045311659, + "loss": 0.0994, + "step": 1062 + }, + { + "epoch": 0.21, + "learning_rate": 0.0006514627563043252, + "loss": 0.1024, + "step": 1063 + }, + { + "epoch": 0.21, + "learning_rate": 0.0006508528600484348, + "loss": 0.1007, + "step": 1064 + }, + { + "epoch": 0.21, + "learning_rate": 0.0006502427167622355, + "loss": 0.0985, + "step": 1065 + }, + { + "epoch": 0.21, + "learning_rate": 0.0006496323274448721, + "loss": 0.1027, + "step": 1066 + }, + { + "epoch": 0.21, + "learning_rate": 0.0006490216930958928, + "loss": 0.1018, + "step": 1067 + }, + { + "epoch": 0.21, + "learning_rate": 0.0006484108147152465, + "loss": 0.1006, + "step": 1068 + }, + { + "epoch": 0.21, + "learning_rate": 0.000647799693303282, + "loss": 0.0985, + "step": 1069 + }, + { + "epoch": 0.21, + "learning_rate": 0.0006471883298607462, + "loss": 0.1021, + "step": 1070 + }, + { + "epoch": 0.21, + "learning_rate": 0.000646576725388782, + "loss": 0.1003, + "step": 1071 + }, + { + "epoch": 0.21, + "learning_rate": 0.0006459648808889274, + "loss": 0.0996, + "step": 1072 + }, + { + "epoch": 0.21, + "learning_rate": 0.0006453527973631132, + "loss": 0.1029, + "step": 1073 + }, + { + "epoch": 0.21, + "learning_rate": 0.0006447404758136617, + "loss": 0.0982, + "step": 1074 + }, + { + "epoch": 0.21, + "learning_rate": 0.0006441279172432848, + "loss": 0.0998, + "step": 1075 + }, + { + "epoch": 0.21, + "learning_rate": 0.0006435151226550828, + "loss": 0.0998, + "step": 1076 + }, + { + "epoch": 0.21, + "learning_rate": 0.0006429020930525427, + "loss": 0.104, + "step": 1077 + }, + { + "epoch": 0.21, + "learning_rate": 0.0006422888294395355, + "loss": 0.1041, + "step": 1078 + }, + { + "epoch": 0.21, + "learning_rate": 0.0006416753328203162, + "loss": 0.1038, + "step": 1079 + }, + { + "epoch": 0.21, + "learning_rate": 0.0006410616041995211, + "loss": 0.1003, + "step": 1080 + }, + { + "epoch": 0.21, + "learning_rate": 0.0006404476445821663, + "loss": 0.1044, + "step": 1081 + }, + { + "epoch": 0.21, + "learning_rate": 0.0006398334549736466, + "loss": 0.1041, + "step": 1082 + }, + { + "epoch": 0.21, + "learning_rate": 0.0006392190363797327, + "loss": 0.1003, + "step": 1083 + }, + { + "epoch": 0.21, + "learning_rate": 0.000638604389806571, + "loss": 0.0985, + "step": 1084 + }, + { + "epoch": 0.21, + "learning_rate": 0.0006379895162606808, + "loss": 0.0996, + "step": 1085 + }, + { + "epoch": 0.21, + "learning_rate": 0.0006373744167489532, + "loss": 0.1011, + "step": 1086 + }, + { + "epoch": 0.21, + "learning_rate": 0.0006367590922786492, + "loss": 0.1014, + "step": 1087 + }, + { + "epoch": 0.21, + "learning_rate": 0.0006361435438573986, + "loss": 0.1017, + "step": 1088 + }, + { + "epoch": 0.22, + "learning_rate": 0.0006355277724931973, + "loss": 0.1009, + "step": 1089 + }, + { + "epoch": 0.22, + "learning_rate": 0.000634911779194407, + "loss": 0.0974, + "step": 1090 + }, + { + "epoch": 0.22, + "learning_rate": 0.0006342955649697523, + "loss": 0.102, + "step": 1091 + }, + { + "epoch": 0.22, + "learning_rate": 0.0006336791308283196, + "loss": 0.1067, + "step": 1092 + }, + { + "epoch": 0.22, + "learning_rate": 0.0006330624777795557, + "loss": 0.0999, + "step": 1093 + }, + { + "epoch": 0.22, + "learning_rate": 0.0006324456068332659, + "loss": 0.1004, + "step": 1094 + }, + { + "epoch": 0.22, + "learning_rate": 0.0006318285189996118, + "loss": 0.1019, + "step": 1095 + }, + { + "epoch": 0.22, + "learning_rate": 0.0006312112152891108, + "loss": 0.1003, + "step": 1096 + }, + { + "epoch": 0.22, + "learning_rate": 0.0006305936967126334, + "loss": 0.1018, + "step": 1097 + }, + { + "epoch": 0.22, + "learning_rate": 0.000629975964281402, + "loss": 0.1027, + "step": 1098 + }, + { + "epoch": 0.22, + "learning_rate": 0.0006293580190069897, + "loss": 0.1037, + "step": 1099 + }, + { + "epoch": 0.22, + "learning_rate": 0.0006287398619013171, + "loss": 0.0975, + "step": 1100 + }, + { + "epoch": 0.22, + "learning_rate": 0.0006281214939766529, + "loss": 0.0974, + "step": 1101 + }, + { + "epoch": 0.22, + "learning_rate": 0.0006275029162456103, + "loss": 0.0993, + "step": 1102 + }, + { + "epoch": 0.22, + "learning_rate": 0.0006268841297211459, + "loss": 0.1019, + "step": 1103 + }, + { + "epoch": 0.22, + "learning_rate": 0.0006262651354165589, + "loss": 0.1022, + "step": 1104 + }, + { + "epoch": 0.22, + "learning_rate": 0.0006256459343454883, + "loss": 0.0998, + "step": 1105 + }, + { + "epoch": 0.22, + "learning_rate": 0.0006250265275219116, + "loss": 0.0991, + "step": 1106 + }, + { + "epoch": 0.22, + "learning_rate": 0.0006244069159601435, + "loss": 0.0988, + "step": 1107 + }, + { + "epoch": 0.22, + "learning_rate": 0.000623787100674834, + "loss": 0.1009, + "step": 1108 + }, + { + "epoch": 0.22, + "learning_rate": 0.0006231670826809664, + "loss": 0.0999, + "step": 1109 + }, + { + "epoch": 0.22, + "learning_rate": 0.0006225468629938564, + "loss": 0.099, + "step": 1110 + }, + { + "epoch": 0.22, + "learning_rate": 0.0006219264426291494, + "loss": 0.1014, + "step": 1111 + }, + { + "epoch": 0.22, + "learning_rate": 0.0006213058226028199, + "loss": 0.0997, + "step": 1112 + }, + { + "epoch": 0.22, + "learning_rate": 0.0006206850039311691, + "loss": 0.1015, + "step": 1113 + }, + { + "epoch": 0.22, + "learning_rate": 0.0006200639876308236, + "loss": 0.0996, + "step": 1114 + }, + { + "epoch": 0.22, + "learning_rate": 0.0006194427747187337, + "loss": 0.1018, + "step": 1115 + }, + { + "epoch": 0.22, + "learning_rate": 0.0006188213662121716, + "loss": 0.101, + "step": 1116 + }, + { + "epoch": 0.22, + "learning_rate": 0.0006181997631287296, + "loss": 0.1024, + "step": 1117 + }, + { + "epoch": 0.22, + "learning_rate": 0.000617577966486319, + "loss": 0.0998, + "step": 1118 + }, + { + "epoch": 0.22, + "learning_rate": 0.0006169559773031678, + "loss": 0.0975, + "step": 1119 + }, + { + "epoch": 0.22, + "learning_rate": 0.0006163337965978194, + "loss": 0.1004, + "step": 1120 + }, + { + "epoch": 0.22, + "learning_rate": 0.0006157114253891307, + "loss": 0.0995, + "step": 1121 + }, + { + "epoch": 0.22, + "learning_rate": 0.0006150888646962708, + "loss": 0.0983, + "step": 1122 + }, + { + "epoch": 0.22, + "learning_rate": 0.0006144661155387188, + "loss": 0.1008, + "step": 1123 + }, + { + "epoch": 0.22, + "learning_rate": 0.0006138431789362626, + "loss": 0.1015, + "step": 1124 + }, + { + "epoch": 0.22, + "learning_rate": 0.0006132200559089971, + "loss": 0.1001, + "step": 1125 + }, + { + "epoch": 0.22, + "learning_rate": 0.0006125967474773223, + "loss": 0.0989, + "step": 1126 + }, + { + "epoch": 0.22, + "learning_rate": 0.000611973254661942, + "loss": 0.0985, + "step": 1127 + }, + { + "epoch": 0.22, + "learning_rate": 0.000611349578483862, + "loss": 0.0981, + "step": 1128 + }, + { + "epoch": 0.22, + "learning_rate": 0.0006107257199643878, + "loss": 0.1011, + "step": 1129 + }, + { + "epoch": 0.22, + "learning_rate": 0.0006101016801251242, + "loss": 0.1006, + "step": 1130 + }, + { + "epoch": 0.22, + "learning_rate": 0.0006094774599879727, + "loss": 0.1009, + "step": 1131 + }, + { + "epoch": 0.22, + "learning_rate": 0.0006088530605751298, + "loss": 0.1013, + "step": 1132 + }, + { + "epoch": 0.22, + "learning_rate": 0.0006082284829090858, + "loss": 0.1009, + "step": 1133 + }, + { + "epoch": 0.22, + "learning_rate": 0.000607603728012623, + "loss": 0.1, + "step": 1134 + }, + { + "epoch": 0.22, + "learning_rate": 0.0006069787969088137, + "loss": 0.1017, + "step": 1135 + }, + { + "epoch": 0.22, + "learning_rate": 0.0006063536906210187, + "loss": 0.1037, + "step": 1136 + }, + { + "epoch": 0.22, + "learning_rate": 0.0006057284101728861, + "loss": 0.1002, + "step": 1137 + }, + { + "epoch": 0.22, + "learning_rate": 0.0006051029565883486, + "loss": 0.0986, + "step": 1138 + }, + { + "epoch": 0.22, + "learning_rate": 0.000604477330891623, + "loss": 0.1017, + "step": 1139 + }, + { + "epoch": 0.23, + "learning_rate": 0.0006038515341072073, + "loss": 0.0992, + "step": 1140 + }, + { + "epoch": 0.23, + "learning_rate": 0.0006032255672598803, + "loss": 0.1015, + "step": 1141 + }, + { + "epoch": 0.23, + "learning_rate": 0.0006025994313746991, + "loss": 0.0982, + "step": 1142 + }, + { + "epoch": 0.23, + "learning_rate": 0.0006019731274769973, + "loss": 0.1031, + "step": 1143 + }, + { + "epoch": 0.23, + "learning_rate": 0.0006013466565923841, + "loss": 0.1009, + "step": 1144 + }, + { + "epoch": 0.23, + "learning_rate": 0.0006007200197467417, + "loss": 0.102, + "step": 1145 + }, + { + "epoch": 0.23, + "learning_rate": 0.0006000932179662244, + "loss": 0.1005, + "step": 1146 + }, + { + "epoch": 0.23, + "learning_rate": 0.0005994662522772565, + "loss": 0.0945, + "step": 1147 + }, + { + "epoch": 0.23, + "learning_rate": 0.0005988391237065306, + "loss": 0.1018, + "step": 1148 + }, + { + "epoch": 0.23, + "learning_rate": 0.0005982118332810061, + "loss": 0.1026, + "step": 1149 + }, + { + "epoch": 0.23, + "learning_rate": 0.0005975843820279076, + "loss": 0.0997, + "step": 1150 + }, + { + "epoch": 0.23, + "learning_rate": 0.0005969567709747228, + "loss": 0.1007, + "step": 1151 + }, + { + "epoch": 0.23, + "learning_rate": 0.0005963290011492013, + "loss": 0.0986, + "step": 1152 + }, + { + "epoch": 0.23, + "learning_rate": 0.0005957010735793525, + "loss": 0.0982, + "step": 1153 + }, + { + "epoch": 0.23, + "learning_rate": 0.0005950729892934443, + "loss": 0.1019, + "step": 1154 + }, + { + "epoch": 0.23, + "learning_rate": 0.0005944447493200012, + "loss": 0.0985, + "step": 1155 + }, + { + "epoch": 0.23, + "learning_rate": 0.0005938163546878024, + "loss": 0.1021, + "step": 1156 + }, + { + "epoch": 0.23, + "learning_rate": 0.0005931878064258806, + "loss": 0.1011, + "step": 1157 + }, + { + "epoch": 0.23, + "learning_rate": 0.0005925591055635203, + "loss": 0.1013, + "step": 1158 + }, + { + "epoch": 0.23, + "learning_rate": 0.0005919302531302553, + "loss": 0.1021, + "step": 1159 + }, + { + "epoch": 0.23, + "learning_rate": 0.0005913012501558683, + "loss": 0.1016, + "step": 1160 + }, + { + "epoch": 0.23, + "learning_rate": 0.0005906720976703876, + "loss": 0.1013, + "step": 1161 + }, + { + "epoch": 0.23, + "learning_rate": 0.0005900427967040876, + "loss": 0.0984, + "step": 1162 + }, + { + "epoch": 0.23, + "learning_rate": 0.0005894133482874847, + "loss": 0.1019, + "step": 1163 + }, + { + "epoch": 0.23, + "learning_rate": 0.0005887837534513372, + "loss": 0.1001, + "step": 1164 + }, + { + "epoch": 0.23, + "learning_rate": 0.0005881540132266432, + "loss": 0.0984, + "step": 1165 + }, + { + "epoch": 0.23, + "learning_rate": 0.000587524128644639, + "loss": 0.102, + "step": 1166 + }, + { + "epoch": 0.23, + "learning_rate": 0.000586894100736797, + "loss": 0.0991, + "step": 1167 + }, + { + "epoch": 0.23, + "learning_rate": 0.0005862639305348244, + "loss": 0.0972, + "step": 1168 + }, + { + "epoch": 0.23, + "learning_rate": 0.0005856336190706615, + "loss": 0.1, + "step": 1169 + }, + { + "epoch": 0.23, + "learning_rate": 0.00058500316737648, + "loss": 0.0988, + "step": 1170 + }, + { + "epoch": 0.23, + "learning_rate": 0.0005843725764846813, + "loss": 0.0996, + "step": 1171 + }, + { + "epoch": 0.23, + "learning_rate": 0.000583741847427894, + "loss": 0.1012, + "step": 1172 + }, + { + "epoch": 0.23, + "learning_rate": 0.0005831109812389737, + "loss": 0.1043, + "step": 1173 + }, + { + "epoch": 0.23, + "learning_rate": 0.0005824799789510007, + "loss": 0.0988, + "step": 1174 + }, + { + "epoch": 0.23, + "learning_rate": 0.0005818488415972777, + "loss": 0.1015, + "step": 1175 + }, + { + "epoch": 0.23, + "learning_rate": 0.0005812175702113285, + "loss": 0.0995, + "step": 1176 + }, + { + "epoch": 0.23, + "learning_rate": 0.0005805861658268969, + "loss": 0.1013, + "step": 1177 + }, + { + "epoch": 0.23, + "learning_rate": 0.0005799546294779442, + "loss": 0.0992, + "step": 1178 + }, + { + "epoch": 0.23, + "learning_rate": 0.0005793229621986475, + "loss": 0.0976, + "step": 1179 + }, + { + "epoch": 0.23, + "learning_rate": 0.000578691165023399, + "loss": 0.0993, + "step": 1180 + }, + { + "epoch": 0.23, + "learning_rate": 0.000578059238986803, + "loss": 0.0979, + "step": 1181 + }, + { + "epoch": 0.23, + "learning_rate": 0.0005774271851236751, + "loss": 0.1034, + "step": 1182 + }, + { + "epoch": 0.23, + "learning_rate": 0.0005767950044690401, + "loss": 0.1002, + "step": 1183 + }, + { + "epoch": 0.23, + "learning_rate": 0.0005761626980581305, + "loss": 0.1006, + "step": 1184 + }, + { + "epoch": 0.23, + "learning_rate": 0.0005755302669263848, + "loss": 0.1005, + "step": 1185 + }, + { + "epoch": 0.23, + "learning_rate": 0.0005748977121094456, + "loss": 0.1, + "step": 1186 + }, + { + "epoch": 0.23, + "learning_rate": 0.0005742650346431583, + "loss": 0.0985, + "step": 1187 + }, + { + "epoch": 0.23, + "learning_rate": 0.0005736322355635688, + "loss": 0.1006, + "step": 1188 + }, + { + "epoch": 0.23, + "learning_rate": 0.0005729993159069222, + "loss": 0.098, + "step": 1189 + }, + { + "epoch": 0.24, + "learning_rate": 0.0005723662767096612, + "loss": 0.0991, + "step": 1190 + }, + { + "epoch": 0.24, + "learning_rate": 0.0005717331190084243, + "loss": 0.1007, + "step": 1191 + }, + { + "epoch": 0.24, + "learning_rate": 0.0005710998438400439, + "loss": 0.1002, + "step": 1192 + }, + { + "epoch": 0.24, + "learning_rate": 0.0005704664522415448, + "loss": 0.0993, + "step": 1193 + }, + { + "epoch": 0.24, + "learning_rate": 0.0005698329452501425, + "loss": 0.0986, + "step": 1194 + }, + { + "epoch": 0.24, + "learning_rate": 0.0005691993239032416, + "loss": 0.0996, + "step": 1195 + }, + { + "epoch": 0.24, + "learning_rate": 0.0005685655892384336, + "loss": 0.0996, + "step": 1196 + }, + { + "epoch": 0.24, + "learning_rate": 0.000567931742293496, + "loss": 0.0994, + "step": 1197 + }, + { + "epoch": 0.24, + "learning_rate": 0.0005672977841063897, + "loss": 0.1005, + "step": 1198 + }, + { + "epoch": 0.24, + "learning_rate": 0.000566663715715258, + "loss": 0.0983, + "step": 1199 + }, + { + "epoch": 0.24, + "learning_rate": 0.0005660295381584248, + "loss": 0.1019, + "step": 1200 + }, + { + "epoch": 0.24, + "learning_rate": 0.0005653952524743927, + "loss": 0.0979, + "step": 1201 + }, + { + "epoch": 0.24, + "learning_rate": 0.0005647608597018412, + "loss": 0.1008, + "step": 1202 + }, + { + "epoch": 0.24, + "learning_rate": 0.0005641263608796252, + "loss": 0.1018, + "step": 1203 + }, + { + "epoch": 0.24, + "learning_rate": 0.0005634917570467734, + "loss": 0.102, + "step": 1204 + }, + { + "epoch": 0.24, + "learning_rate": 0.0005628570492424867, + "loss": 0.1005, + "step": 1205 + }, + { + "epoch": 0.24, + "learning_rate": 0.0005622222385061353, + "loss": 0.0995, + "step": 1206 + }, + { + "epoch": 0.24, + "learning_rate": 0.000561587325877259, + "loss": 0.1005, + "step": 1207 + }, + { + "epoch": 0.24, + "learning_rate": 0.0005609523123955641, + "loss": 0.1025, + "step": 1208 + }, + { + "epoch": 0.24, + "learning_rate": 0.0005603171991009219, + "loss": 0.1013, + "step": 1209 + }, + { + "epoch": 0.24, + "learning_rate": 0.0005596819870333673, + "loss": 0.1006, + "step": 1210 + }, + { + "epoch": 0.24, + "learning_rate": 0.0005590466772330968, + "loss": 0.0998, + "step": 1211 + }, + { + "epoch": 0.24, + "learning_rate": 0.0005584112707404671, + "loss": 0.1008, + "step": 1212 + }, + { + "epoch": 0.24, + "learning_rate": 0.0005577757685959933, + "loss": 0.1008, + "step": 1213 + }, + { + "epoch": 0.24, + "learning_rate": 0.0005571401718403472, + "loss": 0.101, + "step": 1214 + }, + { + "epoch": 0.24, + "learning_rate": 0.0005565044815143548, + "loss": 0.0969, + "step": 1215 + }, + { + "epoch": 0.24, + "learning_rate": 0.0005558686986589963, + "loss": 0.0991, + "step": 1216 + }, + { + "epoch": 0.24, + "learning_rate": 0.0005552328243154028, + "loss": 0.0984, + "step": 1217 + }, + { + "epoch": 0.24, + "learning_rate": 0.0005545968595248558, + "loss": 0.0984, + "step": 1218 + }, + { + "epoch": 0.24, + "learning_rate": 0.0005539608053287841, + "loss": 0.0975, + "step": 1219 + }, + { + "epoch": 0.24, + "learning_rate": 0.0005533246627687634, + "loss": 0.1026, + "step": 1220 + }, + { + "epoch": 0.24, + "learning_rate": 0.0005526884328865141, + "loss": 0.0981, + "step": 1221 + }, + { + "epoch": 0.24, + "learning_rate": 0.0005520521167238998, + "loss": 0.0982, + "step": 1222 + }, + { + "epoch": 0.24, + "learning_rate": 0.0005514157153229248, + "loss": 0.0997, + "step": 1223 + }, + { + "epoch": 0.24, + "learning_rate": 0.0005507792297257335, + "loss": 0.0984, + "step": 1224 + }, + { + "epoch": 0.24, + "learning_rate": 0.0005501426609746078, + "loss": 0.1011, + "step": 1225 + }, + { + "epoch": 0.24, + "learning_rate": 0.0005495060101119662, + "loss": 0.1009, + "step": 1226 + }, + { + "epoch": 0.24, + "learning_rate": 0.0005488692781803612, + "loss": 0.0979, + "step": 1227 + }, + { + "epoch": 0.24, + "learning_rate": 0.0005482324662224784, + "loss": 0.1006, + "step": 1228 + }, + { + "epoch": 0.24, + "learning_rate": 0.0005475955752811344, + "loss": 0.1018, + "step": 1229 + }, + { + "epoch": 0.24, + "learning_rate": 0.0005469586063992747, + "loss": 0.0986, + "step": 1230 + }, + { + "epoch": 0.24, + "learning_rate": 0.0005463215606199733, + "loss": 0.0981, + "step": 1231 + }, + { + "epoch": 0.24, + "learning_rate": 0.0005456844389864292, + "loss": 0.0962, + "step": 1232 + }, + { + "epoch": 0.24, + "learning_rate": 0.0005450472425419662, + "loss": 0.1039, + "step": 1233 + }, + { + "epoch": 0.24, + "learning_rate": 0.0005444099723300304, + "loss": 0.1001, + "step": 1234 + }, + { + "epoch": 0.24, + "learning_rate": 0.0005437726293941888, + "loss": 0.0961, + "step": 1235 + }, + { + "epoch": 0.24, + "learning_rate": 0.0005431352147781274, + "loss": 0.0989, + "step": 1236 + }, + { + "epoch": 0.24, + "learning_rate": 0.0005424977295256496, + "loss": 0.0998, + "step": 1237 + }, + { + "epoch": 0.24, + "learning_rate": 0.0005418601746806745, + "loss": 0.0986, + "step": 1238 + }, + { + "epoch": 0.24, + "learning_rate": 0.0005412225512872351, + "loss": 0.1048, + "step": 1239 + }, + { + "epoch": 0.24, + "learning_rate": 0.0005405848603894769, + "loss": 0.0987, + "step": 1240 + }, + { + "epoch": 0.25, + "learning_rate": 0.0005399471030316554, + "loss": 0.0991, + "step": 1241 + }, + { + "epoch": 0.25, + "learning_rate": 0.0005393092802581355, + "loss": 0.1001, + "step": 1242 + }, + { + "epoch": 0.25, + "learning_rate": 0.0005386713931133887, + "loss": 0.1032, + "step": 1243 + }, + { + "epoch": 0.25, + "learning_rate": 0.0005380334426419927, + "loss": 0.0988, + "step": 1244 + }, + { + "epoch": 0.25, + "learning_rate": 0.0005373954298886279, + "loss": 0.0995, + "step": 1245 + }, + { + "epoch": 0.25, + "learning_rate": 0.0005367573558980775, + "loss": 0.1, + "step": 1246 + }, + { + "epoch": 0.25, + "learning_rate": 0.0005361192217152246, + "loss": 0.1018, + "step": 1247 + }, + { + "epoch": 0.25, + "learning_rate": 0.000535481028385051, + "loss": 0.0987, + "step": 1248 + }, + { + "epoch": 0.25, + "learning_rate": 0.0005348427769526351, + "loss": 0.1011, + "step": 1249 + }, + { + "epoch": 0.25, + "learning_rate": 0.0005342044684631509, + "loss": 0.0992, + "step": 1250 + }, + { + "epoch": 0.25, + "learning_rate": 0.0005335661039618653, + "loss": 0.102, + "step": 1251 + }, + { + "epoch": 0.25, + "learning_rate": 0.0005329276844941375, + "loss": 0.0994, + "step": 1252 + }, + { + "epoch": 0.25, + "learning_rate": 0.0005322892111054162, + "loss": 0.099, + "step": 1253 + }, + { + "epoch": 0.25, + "learning_rate": 0.0005316506848412386, + "loss": 0.099, + "step": 1254 + }, + { + "epoch": 0.25, + "learning_rate": 0.0005310121067472287, + "loss": 0.1008, + "step": 1255 + }, + { + "epoch": 0.25, + "learning_rate": 0.000530373477869095, + "loss": 0.1004, + "step": 1256 + }, + { + "epoch": 0.25, + "learning_rate": 0.0005297347992526295, + "loss": 0.1004, + "step": 1257 + }, + { + "epoch": 0.25, + "learning_rate": 0.0005290960719437052, + "loss": 0.0995, + "step": 1258 + }, + { + "epoch": 0.25, + "learning_rate": 0.0005284572969882753, + "loss": 0.0988, + "step": 1259 + }, + { + "epoch": 0.25, + "learning_rate": 0.0005278184754323709, + "loss": 0.1012, + "step": 1260 + }, + { + "epoch": 0.25, + "learning_rate": 0.0005271796083220991, + "loss": 0.1001, + "step": 1261 + }, + { + "epoch": 0.25, + "learning_rate": 0.0005265406967036422, + "loss": 0.1019, + "step": 1262 + }, + { + "epoch": 0.25, + "learning_rate": 0.0005259017416232547, + "loss": 0.0963, + "step": 1263 + }, + { + "epoch": 0.25, + "learning_rate": 0.000525262744127263, + "loss": 0.1001, + "step": 1264 + }, + { + "epoch": 0.25, + "learning_rate": 0.0005246237052620623, + "loss": 0.0985, + "step": 1265 + }, + { + "epoch": 0.25, + "learning_rate": 0.0005239846260741157, + "loss": 0.1023, + "step": 1266 + }, + { + "epoch": 0.25, + "learning_rate": 0.0005233455076099528, + "loss": 0.0988, + "step": 1267 + }, + { + "epoch": 0.25, + "learning_rate": 0.0005227063509161668, + "loss": 0.0989, + "step": 1268 + }, + { + "epoch": 0.25, + "learning_rate": 0.0005220671570394141, + "loss": 0.1026, + "step": 1269 + }, + { + "epoch": 0.25, + "learning_rate": 0.0005214279270264118, + "loss": 0.1004, + "step": 1270 + }, + { + "epoch": 0.25, + "learning_rate": 0.0005207886619239357, + "loss": 0.0991, + "step": 1271 + }, + { + "epoch": 0.25, + "learning_rate": 0.0005201493627788199, + "loss": 0.0998, + "step": 1272 + }, + { + "epoch": 0.25, + "learning_rate": 0.0005195100306379539, + "loss": 0.1013, + "step": 1273 + }, + { + "epoch": 0.25, + "learning_rate": 0.0005188706665482808, + "loss": 0.0988, + "step": 1274 + }, + { + "epoch": 0.25, + "learning_rate": 0.0005182312715567968, + "loss": 0.0964, + "step": 1275 + }, + { + "epoch": 0.25, + "learning_rate": 0.0005175918467105478, + "loss": 0.1042, + "step": 1276 + }, + { + "epoch": 0.25, + "learning_rate": 0.0005169523930566294, + "loss": 0.1026, + "step": 1277 + }, + { + "epoch": 0.25, + "learning_rate": 0.000516312911642184, + "loss": 0.1001, + "step": 1278 + }, + { + "epoch": 0.25, + "learning_rate": 0.0005156734035143996, + "loss": 0.0957, + "step": 1279 + }, + { + "epoch": 0.25, + "learning_rate": 0.0005150338697205077, + "loss": 0.1002, + "step": 1280 + }, + { + "epoch": 0.25, + "learning_rate": 0.000514394311307782, + "loss": 0.1004, + "step": 1281 + }, + { + "epoch": 0.25, + "learning_rate": 0.0005137547293235366, + "loss": 0.0996, + "step": 1282 + }, + { + "epoch": 0.25, + "learning_rate": 0.0005131151248151241, + "loss": 0.1001, + "step": 1283 + }, + { + "epoch": 0.25, + "learning_rate": 0.0005124754988299338, + "loss": 0.1007, + "step": 1284 + }, + { + "epoch": 0.25, + "learning_rate": 0.0005118358524153906, + "loss": 0.1023, + "step": 1285 + }, + { + "epoch": 0.25, + "learning_rate": 0.0005111961866189524, + "loss": 0.0986, + "step": 1286 + }, + { + "epoch": 0.25, + "learning_rate": 0.0005105565024881093, + "loss": 0.0995, + "step": 1287 + }, + { + "epoch": 0.25, + "learning_rate": 0.0005099168010703808, + "loss": 0.0999, + "step": 1288 + }, + { + "epoch": 0.25, + "learning_rate": 0.0005092770834133154, + "loss": 0.0999, + "step": 1289 + }, + { + "epoch": 0.25, + "learning_rate": 0.0005086373505644876, + "loss": 0.1004, + "step": 1290 + }, + { + "epoch": 0.26, + "learning_rate": 0.0005079976035714976, + "loss": 0.0983, + "step": 1291 + }, + { + "epoch": 0.26, + "learning_rate": 0.0005073578434819676, + "loss": 0.1003, + "step": 1292 + }, + { + "epoch": 0.26, + "learning_rate": 0.0005067180713435419, + "loss": 0.1003, + "step": 1293 + }, + { + "epoch": 0.26, + "learning_rate": 0.000506078288203885, + "loss": 0.0977, + "step": 1294 + }, + { + "epoch": 0.26, + "learning_rate": 0.0005054384951106785, + "loss": 0.0997, + "step": 1295 + }, + { + "epoch": 0.26, + "learning_rate": 0.0005047986931116205, + "loss": 0.101, + "step": 1296 + }, + { + "epoch": 0.26, + "learning_rate": 0.0005041588832544243, + "loss": 0.1014, + "step": 1297 + }, + { + "epoch": 0.26, + "learning_rate": 0.0005035190665868157, + "loss": 0.0975, + "step": 1298 + }, + { + "epoch": 0.26, + "learning_rate": 0.0005028792441565313, + "loss": 0.1014, + "step": 1299 + }, + { + "epoch": 0.26, + "learning_rate": 0.0005022394170113175, + "loss": 0.0991, + "step": 1300 + }, + { + "epoch": 0.26, + "learning_rate": 0.0005015995861989286, + "loss": 0.0973, + "step": 1301 + }, + { + "epoch": 0.26, + "learning_rate": 0.0005009597527671245, + "loss": 0.0974, + "step": 1302 + }, + { + "epoch": 0.26, + "learning_rate": 0.0005003199177636695, + "loss": 0.0973, + "step": 1303 + }, + { + "epoch": 0.26, + "learning_rate": 0.0004996800822363307, + "loss": 0.1012, + "step": 1304 + }, + { + "epoch": 0.26, + "learning_rate": 0.0004990402472328756, + "loss": 0.0988, + "step": 1305 + }, + { + "epoch": 0.26, + "learning_rate": 0.0004984004138010715, + "loss": 0.0986, + "step": 1306 + }, + { + "epoch": 0.26, + "learning_rate": 0.0004977605829886825, + "loss": 0.103, + "step": 1307 + }, + { + "epoch": 0.26, + "learning_rate": 0.0004971207558434687, + "loss": 0.0977, + "step": 1308 + }, + { + "epoch": 0.26, + "learning_rate": 0.0004964809334131844, + "loss": 0.1007, + "step": 1309 + }, + { + "epoch": 0.26, + "learning_rate": 0.0004958411167455757, + "loss": 0.0988, + "step": 1310 + }, + { + "epoch": 0.26, + "learning_rate": 0.0004952013068883795, + "loss": 0.0981, + "step": 1311 + }, + { + "epoch": 0.26, + "learning_rate": 0.0004945615048893217, + "loss": 0.097, + "step": 1312 + }, + { + "epoch": 0.26, + "learning_rate": 0.0004939217117961151, + "loss": 0.0983, + "step": 1313 + }, + { + "epoch": 0.26, + "learning_rate": 0.0004932819286564581, + "loss": 0.0995, + "step": 1314 + }, + { + "epoch": 0.26, + "learning_rate": 0.0004926421565180325, + "loss": 0.0994, + "step": 1315 + }, + { + "epoch": 0.26, + "learning_rate": 0.0004920023964285025, + "loss": 0.097, + "step": 1316 + }, + { + "epoch": 0.26, + "learning_rate": 0.0004913626494355123, + "loss": 0.099, + "step": 1317 + }, + { + "epoch": 0.26, + "learning_rate": 0.0004907229165866846, + "loss": 0.1005, + "step": 1318 + }, + { + "epoch": 0.26, + "learning_rate": 0.0004900831989296192, + "loss": 0.1006, + "step": 1319 + }, + { + "epoch": 0.26, + "learning_rate": 0.0004894434975118907, + "loss": 0.099, + "step": 1320 + }, + { + "epoch": 0.26, + "learning_rate": 0.0004888038133810477, + "loss": 0.099, + "step": 1321 + }, + { + "epoch": 0.26, + "learning_rate": 0.0004881641475846096, + "loss": 0.0994, + "step": 1322 + }, + { + "epoch": 0.26, + "learning_rate": 0.0004875245011700663, + "loss": 0.1006, + "step": 1323 + }, + { + "epoch": 0.26, + "learning_rate": 0.00048688487518487605, + "loss": 0.0981, + "step": 1324 + }, + { + "epoch": 0.26, + "learning_rate": 0.0004862452706764635, + "loss": 0.1007, + "step": 1325 + }, + { + "epoch": 0.26, + "learning_rate": 0.00048560568869221806, + "loss": 0.0992, + "step": 1326 + }, + { + "epoch": 0.26, + "learning_rate": 0.00048496613027949236, + "loss": 0.1013, + "step": 1327 + }, + { + "epoch": 0.26, + "learning_rate": 0.00048432659648560053, + "loss": 0.099, + "step": 1328 + }, + { + "epoch": 0.26, + "learning_rate": 0.00048368708835781597, + "loss": 0.1, + "step": 1329 + }, + { + "epoch": 0.26, + "learning_rate": 0.00048304760694337063, + "loss": 0.0974, + "step": 1330 + }, + { + "epoch": 0.26, + "learning_rate": 0.00048240815328945224, + "loss": 0.1, + "step": 1331 + }, + { + "epoch": 0.26, + "learning_rate": 0.00048176872844320337, + "loss": 0.0986, + "step": 1332 + }, + { + "epoch": 0.26, + "learning_rate": 0.00048112933345171915, + "loss": 0.1013, + "step": 1333 + }, + { + "epoch": 0.26, + "learning_rate": 0.00048048996936204616, + "loss": 0.1029, + "step": 1334 + }, + { + "epoch": 0.26, + "learning_rate": 0.00047985063722118, + "loss": 0.0988, + "step": 1335 + }, + { + "epoch": 0.26, + "learning_rate": 0.0004792113380760642, + "loss": 0.0976, + "step": 1336 + }, + { + "epoch": 0.26, + "learning_rate": 0.0004785720729735883, + "loss": 0.099, + "step": 1337 + }, + { + "epoch": 0.26, + "learning_rate": 0.00047793284296058597, + "loss": 0.1003, + "step": 1338 + }, + { + "epoch": 0.26, + "learning_rate": 0.00047729364908383323, + "loss": 0.0983, + "step": 1339 + }, + { + "epoch": 0.26, + "learning_rate": 0.0004766544923900473, + "loss": 0.099, + "step": 1340 + }, + { + "epoch": 0.26, + "learning_rate": 0.0004760153739258843, + "loss": 0.0995, + "step": 1341 + }, + { + "epoch": 0.27, + "learning_rate": 0.0004753762947379378, + "loss": 0.0965, + "step": 1342 + }, + { + "epoch": 0.27, + "learning_rate": 0.0004747372558727371, + "loss": 0.1003, + "step": 1343 + }, + { + "epoch": 0.27, + "learning_rate": 0.00047409825837674524, + "loss": 0.098, + "step": 1344 + }, + { + "epoch": 0.27, + "learning_rate": 0.0004734593032963579, + "loss": 0.1015, + "step": 1345 + }, + { + "epoch": 0.27, + "learning_rate": 0.00047282039167790093, + "loss": 0.097, + "step": 1346 + }, + { + "epoch": 0.27, + "learning_rate": 0.00047218152456762925, + "loss": 0.1003, + "step": 1347 + }, + { + "epoch": 0.27, + "learning_rate": 0.0004715427030117248, + "loss": 0.0997, + "step": 1348 + }, + { + "epoch": 0.27, + "learning_rate": 0.0004709039280562949, + "loss": 0.0998, + "step": 1349 + }, + { + "epoch": 0.27, + "learning_rate": 0.0004702652007473707, + "loss": 0.0956, + "step": 1350 + }, + { + "epoch": 0.27, + "learning_rate": 0.00046962652213090503, + "loss": 0.1012, + "step": 1351 + }, + { + "epoch": 0.27, + "learning_rate": 0.0004689878932527713, + "loss": 0.0973, + "step": 1352 + }, + { + "epoch": 0.27, + "learning_rate": 0.00046834931515876135, + "loss": 0.1016, + "step": 1353 + }, + { + "epoch": 0.27, + "learning_rate": 0.00046771078889458386, + "loss": 0.0977, + "step": 1354 + }, + { + "epoch": 0.27, + "learning_rate": 0.0004670723155058625, + "loss": 0.0971, + "step": 1355 + }, + { + "epoch": 0.27, + "learning_rate": 0.00046643389603813484, + "loss": 0.0973, + "step": 1356 + }, + { + "epoch": 0.27, + "learning_rate": 0.00046579553153684933, + "loss": 0.0932, + "step": 1357 + }, + { + "epoch": 0.27, + "learning_rate": 0.0004651572230473651, + "loss": 0.0979, + "step": 1358 + }, + { + "epoch": 0.27, + "learning_rate": 0.0004645189716149492, + "loss": 0.1004, + "step": 1359 + }, + { + "epoch": 0.27, + "learning_rate": 0.00046388077828477556, + "loss": 0.1008, + "step": 1360 + }, + { + "epoch": 0.27, + "learning_rate": 0.0004632426441019226, + "loss": 0.1005, + "step": 1361 + }, + { + "epoch": 0.27, + "learning_rate": 0.0004626045701113722, + "loss": 0.1006, + "step": 1362 + }, + { + "epoch": 0.27, + "learning_rate": 0.0004619665573580075, + "loss": 0.1002, + "step": 1363 + }, + { + "epoch": 0.27, + "learning_rate": 0.0004613286068866114, + "loss": 0.1005, + "step": 1364 + }, + { + "epoch": 0.27, + "learning_rate": 0.0004606907197418647, + "loss": 0.0995, + "step": 1365 + }, + { + "epoch": 0.27, + "learning_rate": 0.0004600528969683447, + "loss": 0.1019, + "step": 1366 + }, + { + "epoch": 0.27, + "learning_rate": 0.00045941513961052325, + "loss": 0.1003, + "step": 1367 + }, + { + "epoch": 0.27, + "learning_rate": 0.0004587774487127648, + "loss": 0.0999, + "step": 1368 + }, + { + "epoch": 0.27, + "learning_rate": 0.00045813982531932545, + "loss": 0.0974, + "step": 1369 + }, + { + "epoch": 0.27, + "learning_rate": 0.0004575022704743503, + "loss": 0.0974, + "step": 1370 + }, + { + "epoch": 0.27, + "learning_rate": 0.0004568647852218725, + "loss": 0.0993, + "step": 1371 + }, + { + "epoch": 0.27, + "learning_rate": 0.00045622737060581114, + "loss": 0.0988, + "step": 1372 + }, + { + "epoch": 0.27, + "learning_rate": 0.00045559002766996974, + "loss": 0.1012, + "step": 1373 + }, + { + "epoch": 0.27, + "learning_rate": 0.000454952757458034, + "loss": 0.0952, + "step": 1374 + }, + { + "epoch": 0.27, + "learning_rate": 0.00045431556101357094, + "loss": 0.0984, + "step": 1375 + }, + { + "epoch": 0.27, + "learning_rate": 0.0004536784393800269, + "loss": 0.1003, + "step": 1376 + }, + { + "epoch": 0.27, + "learning_rate": 0.00045304139360072536, + "loss": 0.0951, + "step": 1377 + }, + { + "epoch": 0.27, + "learning_rate": 0.00045240442471886576, + "loss": 0.0991, + "step": 1378 + }, + { + "epoch": 0.27, + "learning_rate": 0.00045176753377752164, + "loss": 0.098, + "step": 1379 + }, + { + "epoch": 0.27, + "learning_rate": 0.0004511307218196389, + "loss": 0.0971, + "step": 1380 + }, + { + "epoch": 0.27, + "learning_rate": 0.0004504939898880339, + "loss": 0.1008, + "step": 1381 + }, + { + "epoch": 0.27, + "learning_rate": 0.00044985733902539225, + "loss": 0.0971, + "step": 1382 + }, + { + "epoch": 0.27, + "learning_rate": 0.00044922077027426664, + "loss": 0.0961, + "step": 1383 + }, + { + "epoch": 0.27, + "learning_rate": 0.00044858428467707523, + "loss": 0.0998, + "step": 1384 + }, + { + "epoch": 0.27, + "learning_rate": 0.0004479478832761003, + "loss": 0.0974, + "step": 1385 + }, + { + "epoch": 0.27, + "learning_rate": 0.00044731156711348593, + "loss": 0.0972, + "step": 1386 + }, + { + "epoch": 0.27, + "learning_rate": 0.00044667533723123675, + "loss": 0.098, + "step": 1387 + }, + { + "epoch": 0.27, + "learning_rate": 0.0004460391946712161, + "loss": 0.0954, + "step": 1388 + }, + { + "epoch": 0.27, + "learning_rate": 0.0004454031404751444, + "loss": 0.1012, + "step": 1389 + }, + { + "epoch": 0.27, + "learning_rate": 0.0004447671756845973, + "loss": 0.0961, + "step": 1390 + }, + { + "epoch": 0.27, + "learning_rate": 0.00044413130134100386, + "loss": 0.0978, + "step": 1391 + }, + { + "epoch": 0.27, + "learning_rate": 0.0004434955184856454, + "loss": 0.0993, + "step": 1392 + }, + { + "epoch": 0.28, + "learning_rate": 0.00044285982815965303, + "loss": 0.0989, + "step": 1393 + }, + { + "epoch": 0.28, + "learning_rate": 0.0004422242314040067, + "loss": 0.0986, + "step": 1394 + }, + { + "epoch": 0.28, + "learning_rate": 0.00044158872925953294, + "loss": 0.095, + "step": 1395 + }, + { + "epoch": 0.28, + "learning_rate": 0.0004409533227669033, + "loss": 0.0961, + "step": 1396 + }, + { + "epoch": 0.28, + "learning_rate": 0.0004403180129666328, + "loss": 0.0969, + "step": 1397 + }, + { + "epoch": 0.28, + "learning_rate": 0.0004396828008990782, + "loss": 0.1005, + "step": 1398 + }, + { + "epoch": 0.28, + "learning_rate": 0.000439047687604436, + "loss": 0.0961, + "step": 1399 + }, + { + "epoch": 0.28, + "learning_rate": 0.000438412674122741, + "loss": 0.1001, + "step": 1400 + }, + { + "epoch": 0.28, + "learning_rate": 0.00043777776149386474, + "loss": 0.0979, + "step": 1401 + }, + { + "epoch": 0.28, + "learning_rate": 0.0004371429507575134, + "loss": 0.0958, + "step": 1402 + }, + { + "epoch": 0.28, + "learning_rate": 0.0004365082429532265, + "loss": 0.0976, + "step": 1403 + }, + { + "epoch": 0.28, + "learning_rate": 0.00043587363912037477, + "loss": 0.0947, + "step": 1404 + }, + { + "epoch": 0.28, + "learning_rate": 0.0004352391402981588, + "loss": 0.0985, + "step": 1405 + }, + { + "epoch": 0.28, + "learning_rate": 0.0004346047475256072, + "loss": 0.0955, + "step": 1406 + }, + { + "epoch": 0.28, + "learning_rate": 0.00043397046184157534, + "loss": 0.0983, + "step": 1407 + }, + { + "epoch": 0.28, + "learning_rate": 0.00043333628428474216, + "loss": 0.1, + "step": 1408 + }, + { + "epoch": 0.28, + "learning_rate": 0.00043270221589361053, + "loss": 0.0958, + "step": 1409 + }, + { + "epoch": 0.28, + "learning_rate": 0.0004320682577065042, + "loss": 0.0976, + "step": 1410 + }, + { + "epoch": 0.28, + "learning_rate": 0.0004314344107615665, + "loss": 0.0991, + "step": 1411 + }, + { + "epoch": 0.28, + "learning_rate": 0.0004308006760967585, + "loss": 0.0996, + "step": 1412 + }, + { + "epoch": 0.28, + "learning_rate": 0.0004301670547498575, + "loss": 0.0993, + "step": 1413 + }, + { + "epoch": 0.28, + "learning_rate": 0.00042953354775845525, + "loss": 0.0988, + "step": 1414 + }, + { + "epoch": 0.28, + "learning_rate": 0.0004289001561599562, + "loss": 0.0987, + "step": 1415 + }, + { + "epoch": 0.28, + "learning_rate": 0.0004282668809915758, + "loss": 0.1005, + "step": 1416 + }, + { + "epoch": 0.28, + "learning_rate": 0.0004276337232903389, + "loss": 0.0992, + "step": 1417 + }, + { + "epoch": 0.28, + "learning_rate": 0.0004270006840930779, + "loss": 0.1009, + "step": 1418 + }, + { + "epoch": 0.28, + "learning_rate": 0.0004263677644364313, + "loss": 0.0988, + "step": 1419 + }, + { + "epoch": 0.28, + "learning_rate": 0.0004257349653568417, + "loss": 0.0999, + "step": 1420 + }, + { + "epoch": 0.28, + "learning_rate": 0.0004251022878905543, + "loss": 0.098, + "step": 1421 + }, + { + "epoch": 0.28, + "learning_rate": 0.0004244697330736151, + "loss": 0.0992, + "step": 1422 + }, + { + "epoch": 0.28, + "learning_rate": 0.00042383730194186944, + "loss": 0.0979, + "step": 1423 + }, + { + "epoch": 0.28, + "learning_rate": 0.00042320499553096, + "loss": 0.0992, + "step": 1424 + }, + { + "epoch": 0.28, + "learning_rate": 0.000422572814876325, + "loss": 0.0967, + "step": 1425 + }, + { + "epoch": 0.28, + "learning_rate": 0.00042194076101319706, + "loss": 0.097, + "step": 1426 + }, + { + "epoch": 0.28, + "learning_rate": 0.00042130883497660106, + "loss": 0.1008, + "step": 1427 + }, + { + "epoch": 0.28, + "learning_rate": 0.0004206770378013525, + "loss": 0.0972, + "step": 1428 + }, + { + "epoch": 0.28, + "learning_rate": 0.0004200453705220559, + "loss": 0.099, + "step": 1429 + }, + { + "epoch": 0.28, + "learning_rate": 0.0004194138341731031, + "loss": 0.101, + "step": 1430 + }, + { + "epoch": 0.28, + "learning_rate": 0.0004187824297886715, + "loss": 0.0974, + "step": 1431 + }, + { + "epoch": 0.28, + "learning_rate": 0.00041815115840272243, + "loss": 0.0998, + "step": 1432 + }, + { + "epoch": 0.28, + "learning_rate": 0.00041752002104899935, + "loss": 0.0997, + "step": 1433 + }, + { + "epoch": 0.28, + "learning_rate": 0.0004168890187610263, + "loss": 0.0989, + "step": 1434 + }, + { + "epoch": 0.28, + "learning_rate": 0.0004162581525721062, + "loss": 0.096, + "step": 1435 + }, + { + "epoch": 0.28, + "learning_rate": 0.0004156274235153189, + "loss": 0.0988, + "step": 1436 + }, + { + "epoch": 0.28, + "learning_rate": 0.00041499683262351993, + "loss": 0.0997, + "step": 1437 + }, + { + "epoch": 0.28, + "learning_rate": 0.0004143663809293384, + "loss": 0.1024, + "step": 1438 + }, + { + "epoch": 0.28, + "learning_rate": 0.00041373606946517563, + "loss": 0.0969, + "step": 1439 + }, + { + "epoch": 0.28, + "learning_rate": 0.00041310589926320306, + "loss": 0.1007, + "step": 1440 + }, + { + "epoch": 0.28, + "learning_rate": 0.0004124758713553612, + "loss": 0.098, + "step": 1441 + }, + { + "epoch": 0.28, + "learning_rate": 0.00041184598677335697, + "loss": 0.0983, + "step": 1442 + }, + { + "epoch": 0.29, + "learning_rate": 0.000411216246548663, + "loss": 0.098, + "step": 1443 + }, + { + "epoch": 0.29, + "learning_rate": 0.0004105866517125155, + "loss": 0.0995, + "step": 1444 + }, + { + "epoch": 0.29, + "learning_rate": 0.0004099572032959125, + "loss": 0.0955, + "step": 1445 + }, + { + "epoch": 0.29, + "learning_rate": 0.00040932790232961236, + "loss": 0.098, + "step": 1446 + }, + { + "epoch": 0.29, + "learning_rate": 0.0004086987498441319, + "loss": 0.0975, + "step": 1447 + }, + { + "epoch": 0.29, + "learning_rate": 0.00040806974686974476, + "loss": 0.0984, + "step": 1448 + }, + { + "epoch": 0.29, + "learning_rate": 0.0004074408944364798, + "loss": 0.1002, + "step": 1449 + }, + { + "epoch": 0.29, + "learning_rate": 0.00040681219357411946, + "loss": 0.0955, + "step": 1450 + }, + { + "epoch": 0.29, + "learning_rate": 0.00040618364531219773, + "loss": 0.0948, + "step": 1451 + }, + { + "epoch": 0.29, + "learning_rate": 0.00040555525067999894, + "loss": 0.0951, + "step": 1452 + }, + { + "epoch": 0.29, + "learning_rate": 0.0004049270107065557, + "loss": 0.098, + "step": 1453 + }, + { + "epoch": 0.29, + "learning_rate": 0.0004042989264206475, + "loss": 0.0998, + "step": 1454 + }, + { + "epoch": 0.29, + "learning_rate": 0.00040367099885079875, + "loss": 0.0964, + "step": 1455 + }, + { + "epoch": 0.29, + "learning_rate": 0.0004030432290252771, + "loss": 0.0975, + "step": 1456 + }, + { + "epoch": 0.29, + "learning_rate": 0.0004024156179720924, + "loss": 0.0992, + "step": 1457 + }, + { + "epoch": 0.29, + "learning_rate": 0.00040178816671899384, + "loss": 0.0971, + "step": 1458 + }, + { + "epoch": 0.29, + "learning_rate": 0.0004011608762934695, + "loss": 0.0952, + "step": 1459 + }, + { + "epoch": 0.29, + "learning_rate": 0.0004005337477227436, + "loss": 0.101, + "step": 1460 + }, + { + "epoch": 0.29, + "learning_rate": 0.0003999067820337757, + "loss": 0.0985, + "step": 1461 + }, + { + "epoch": 0.29, + "learning_rate": 0.0003992799802532584, + "loss": 0.0944, + "step": 1462 + }, + { + "epoch": 0.29, + "learning_rate": 0.000398653343407616, + "loss": 0.0984, + "step": 1463 + }, + { + "epoch": 0.29, + "learning_rate": 0.00039802687252300274, + "loss": 0.0981, + "step": 1464 + }, + { + "epoch": 0.29, + "learning_rate": 0.000397400568625301, + "loss": 0.098, + "step": 1465 + }, + { + "epoch": 0.29, + "learning_rate": 0.0003967744327401197, + "loss": 0.0962, + "step": 1466 + }, + { + "epoch": 0.29, + "learning_rate": 0.0003961484658927928, + "loss": 0.1003, + "step": 1467 + }, + { + "epoch": 0.29, + "learning_rate": 0.0003955226691083772, + "loss": 0.098, + "step": 1468 + }, + { + "epoch": 0.29, + "learning_rate": 0.00039489704341165145, + "loss": 0.0998, + "step": 1469 + }, + { + "epoch": 0.29, + "learning_rate": 0.000394271589827114, + "loss": 0.0956, + "step": 1470 + }, + { + "epoch": 0.29, + "learning_rate": 0.00039364630937898125, + "loss": 0.0995, + "step": 1471 + }, + { + "epoch": 0.29, + "learning_rate": 0.0003930212030911863, + "loss": 0.0986, + "step": 1472 + }, + { + "epoch": 0.29, + "learning_rate": 0.00039239627198737695, + "loss": 0.0988, + "step": 1473 + }, + { + "epoch": 0.29, + "learning_rate": 0.0003917715170909141, + "loss": 0.0997, + "step": 1474 + }, + { + "epoch": 0.29, + "learning_rate": 0.0003911469394248702, + "loss": 0.0966, + "step": 1475 + }, + { + "epoch": 0.29, + "learning_rate": 0.00039052254001202747, + "loss": 0.0952, + "step": 1476 + }, + { + "epoch": 0.29, + "learning_rate": 0.00038989831987487595, + "loss": 0.0972, + "step": 1477 + }, + { + "epoch": 0.29, + "learning_rate": 0.0003892742800356124, + "loss": 0.0974, + "step": 1478 + }, + { + "epoch": 0.29, + "learning_rate": 0.0003886504215161383, + "loss": 0.0981, + "step": 1479 + }, + { + "epoch": 0.29, + "learning_rate": 0.0003880267453380581, + "loss": 0.0997, + "step": 1480 + }, + { + "epoch": 0.29, + "learning_rate": 0.0003874032525226778, + "loss": 0.0997, + "step": 1481 + }, + { + "epoch": 0.29, + "learning_rate": 0.00038677994409100304, + "loss": 0.0988, + "step": 1482 + }, + { + "epoch": 0.29, + "learning_rate": 0.00038615682106373753, + "loss": 0.0977, + "step": 1483 + }, + { + "epoch": 0.29, + "learning_rate": 0.00038553388446128136, + "loss": 0.0971, + "step": 1484 + }, + { + "epoch": 0.29, + "learning_rate": 0.0003849111353037293, + "loss": 0.0994, + "step": 1485 + }, + { + "epoch": 0.29, + "learning_rate": 0.0003842885746108693, + "loss": 0.0982, + "step": 1486 + }, + { + "epoch": 0.29, + "learning_rate": 0.00038366620340218063, + "loss": 0.0987, + "step": 1487 + }, + { + "epoch": 0.29, + "learning_rate": 0.0003830440226968322, + "loss": 0.0981, + "step": 1488 + }, + { + "epoch": 0.29, + "learning_rate": 0.00038242203351368097, + "loss": 0.0985, + "step": 1489 + }, + { + "epoch": 0.29, + "learning_rate": 0.00038180023687127033, + "loss": 0.0987, + "step": 1490 + }, + { + "epoch": 0.29, + "learning_rate": 0.0003811786337878284, + "loss": 0.0987, + "step": 1491 + }, + { + "epoch": 0.29, + "learning_rate": 0.00038055722528126625, + "loss": 0.0963, + "step": 1492 + }, + { + "epoch": 0.29, + "learning_rate": 0.0003799360123691766, + "loss": 0.1017, + "step": 1493 + }, + { + "epoch": 0.3, + "learning_rate": 0.00037931499606883116, + "loss": 0.0993, + "step": 1494 + }, + { + "epoch": 0.3, + "learning_rate": 0.00037869417739718034, + "loss": 0.096, + "step": 1495 + }, + { + "epoch": 0.3, + "learning_rate": 0.00037807355737085074, + "loss": 0.0959, + "step": 1496 + }, + { + "epoch": 0.3, + "learning_rate": 0.00037745313700614377, + "loss": 0.0979, + "step": 1497 + }, + { + "epoch": 0.3, + "learning_rate": 0.00037683291731903357, + "loss": 0.0979, + "step": 1498 + }, + { + "epoch": 0.3, + "learning_rate": 0.00037621289932516605, + "loss": 0.1015, + "step": 1499 + }, + { + "epoch": 0.3, + "learning_rate": 0.0003755930840398565, + "loss": 0.0978, + "step": 1500 + }, + { + "epoch": 0.3, + "learning_rate": 0.00037497347247808846, + "loss": 0.0995, + "step": 1501 + }, + { + "epoch": 0.3, + "learning_rate": 0.0003743540656545118, + "loss": 0.1006, + "step": 1502 + }, + { + "epoch": 0.3, + "learning_rate": 0.00037373486458344116, + "loss": 0.095, + "step": 1503 + }, + { + "epoch": 0.3, + "learning_rate": 0.00037311587027885406, + "loss": 0.0974, + "step": 1504 + }, + { + "epoch": 0.3, + "learning_rate": 0.0003724970837543898, + "loss": 0.099, + "step": 1505 + }, + { + "epoch": 0.3, + "learning_rate": 0.0003718785060233471, + "loss": 0.0965, + "step": 1506 + }, + { + "epoch": 0.3, + "learning_rate": 0.00037126013809868287, + "loss": 0.0967, + "step": 1507 + }, + { + "epoch": 0.3, + "learning_rate": 0.00037064198099301046, + "loss": 0.0965, + "step": 1508 + }, + { + "epoch": 0.3, + "learning_rate": 0.000370024035718598, + "loss": 0.1019, + "step": 1509 + }, + { + "epoch": 0.3, + "learning_rate": 0.0003694063032873668, + "loss": 0.0988, + "step": 1510 + }, + { + "epoch": 0.3, + "learning_rate": 0.0003687887847108894, + "loss": 0.0946, + "step": 1511 + }, + { + "epoch": 0.3, + "learning_rate": 0.0003681714810003883, + "loss": 0.0954, + "step": 1512 + }, + { + "epoch": 0.3, + "learning_rate": 0.0003675543931667343, + "loss": 0.0989, + "step": 1513 + }, + { + "epoch": 0.3, + "learning_rate": 0.00036693752222044436, + "loss": 0.0987, + "step": 1514 + }, + { + "epoch": 0.3, + "learning_rate": 0.0003663208691716805, + "loss": 0.0979, + "step": 1515 + }, + { + "epoch": 0.3, + "learning_rate": 0.00036570443503024784, + "loss": 0.0994, + "step": 1516 + }, + { + "epoch": 0.3, + "learning_rate": 0.00036508822080559306, + "loss": 0.0998, + "step": 1517 + }, + { + "epoch": 0.3, + "learning_rate": 0.0003644722275068027, + "loss": 0.0986, + "step": 1518 + }, + { + "epoch": 0.3, + "learning_rate": 0.0003638564561426015, + "loss": 0.0983, + "step": 1519 + }, + { + "epoch": 0.3, + "learning_rate": 0.00036324090772135086, + "loss": 0.0981, + "step": 1520 + }, + { + "epoch": 0.3, + "learning_rate": 0.00036262558325104695, + "loss": 0.0996, + "step": 1521 + }, + { + "epoch": 0.3, + "learning_rate": 0.00036201048373931934, + "loss": 0.0989, + "step": 1522 + }, + { + "epoch": 0.3, + "learning_rate": 0.000361395610193429, + "loss": 0.0957, + "step": 1523 + }, + { + "epoch": 0.3, + "learning_rate": 0.00036078096362026724, + "loss": 0.0993, + "step": 1524 + }, + { + "epoch": 0.3, + "learning_rate": 0.00036016654502635346, + "loss": 0.0982, + "step": 1525 + }, + { + "epoch": 0.3, + "learning_rate": 0.0003595523554178336, + "loss": 0.0968, + "step": 1526 + }, + { + "epoch": 0.3, + "learning_rate": 0.00035893839580047903, + "loss": 0.0953, + "step": 1527 + }, + { + "epoch": 0.3, + "learning_rate": 0.00035832466717968393, + "loss": 0.0996, + "step": 1528 + }, + { + "epoch": 0.3, + "learning_rate": 0.00035771117056046465, + "loss": 0.0978, + "step": 1529 + }, + { + "epoch": 0.3, + "learning_rate": 0.00035709790694745747, + "loss": 0.0963, + "step": 1530 + }, + { + "epoch": 0.3, + "learning_rate": 0.0003564848773449172, + "loss": 0.0995, + "step": 1531 + }, + { + "epoch": 0.3, + "learning_rate": 0.00035587208275671524, + "loss": 0.0943, + "step": 1532 + }, + { + "epoch": 0.3, + "learning_rate": 0.00035525952418633845, + "loss": 0.0951, + "step": 1533 + }, + { + "epoch": 0.3, + "learning_rate": 0.00035464720263688685, + "loss": 0.098, + "step": 1534 + }, + { + "epoch": 0.3, + "learning_rate": 0.00035403511911107267, + "loss": 0.0983, + "step": 1535 + }, + { + "epoch": 0.3, + "learning_rate": 0.00035342327461121805, + "loss": 0.0942, + "step": 1536 + }, + { + "epoch": 0.3, + "learning_rate": 0.0003528116701392539, + "loss": 0.0948, + "step": 1537 + }, + { + "epoch": 0.3, + "learning_rate": 0.0003522003066967181, + "loss": 0.1011, + "step": 1538 + }, + { + "epoch": 0.3, + "learning_rate": 0.0003515891852847536, + "loss": 0.0969, + "step": 1539 + }, + { + "epoch": 0.3, + "learning_rate": 0.00035097830690410727, + "loss": 0.0971, + "step": 1540 + }, + { + "epoch": 0.3, + "learning_rate": 0.00035036767255512783, + "loss": 0.0999, + "step": 1541 + }, + { + "epoch": 0.3, + "learning_rate": 0.0003497572832377645, + "loss": 0.0957, + "step": 1542 + }, + { + "epoch": 0.3, + "learning_rate": 0.00034914713995156516, + "loss": 0.0985, + "step": 1543 + }, + { + "epoch": 0.3, + "learning_rate": 0.00034853724369567497, + "loss": 0.0994, + "step": 1544 + }, + { + "epoch": 0.31, + "learning_rate": 0.00034792759546883417, + "loss": 0.0976, + "step": 1545 + }, + { + "epoch": 0.31, + "learning_rate": 0.00034731819626937727, + "loss": 0.0966, + "step": 1546 + }, + { + "epoch": 0.31, + "learning_rate": 0.00034670904709523077, + "loss": 0.0953, + "step": 1547 + }, + { + "epoch": 0.31, + "learning_rate": 0.0003461001489439118, + "loss": 0.0943, + "step": 1548 + }, + { + "epoch": 0.31, + "learning_rate": 0.00034549150281252633, + "loss": 0.0978, + "step": 1549 + }, + { + "epoch": 0.31, + "learning_rate": 0.00034488310969776784, + "loss": 0.0975, + "step": 1550 + }, + { + "epoch": 0.31, + "learning_rate": 0.00034427497059591515, + "loss": 0.0974, + "step": 1551 + }, + { + "epoch": 0.31, + "learning_rate": 0.0003436670865028315, + "loss": 0.0953, + "step": 1552 + }, + { + "epoch": 0.31, + "learning_rate": 0.0003430594584139623, + "loss": 0.0963, + "step": 1553 + }, + { + "epoch": 0.31, + "learning_rate": 0.0003424520873243337, + "loss": 0.0989, + "step": 1554 + }, + { + "epoch": 0.31, + "learning_rate": 0.0003418449742285513, + "loss": 0.0968, + "step": 1555 + }, + { + "epoch": 0.31, + "learning_rate": 0.00034123812012079786, + "loss": 0.097, + "step": 1556 + }, + { + "epoch": 0.31, + "learning_rate": 0.00034063152599483215, + "loss": 0.1, + "step": 1557 + }, + { + "epoch": 0.31, + "learning_rate": 0.00034002519284398735, + "loss": 0.0982, + "step": 1558 + }, + { + "epoch": 0.31, + "learning_rate": 0.00033941912166116913, + "loss": 0.0968, + "step": 1559 + }, + { + "epoch": 0.31, + "learning_rate": 0.0003388133134388541, + "loss": 0.0985, + "step": 1560 + }, + { + "epoch": 0.31, + "learning_rate": 0.0003382077691690886, + "loss": 0.0993, + "step": 1561 + }, + { + "epoch": 0.31, + "learning_rate": 0.00033760248984348646, + "loss": 0.0976, + "step": 1562 + }, + { + "epoch": 0.31, + "learning_rate": 0.0003369974764532274, + "loss": 0.0999, + "step": 1563 + }, + { + "epoch": 0.31, + "learning_rate": 0.0003363927299890561, + "loss": 0.0986, + "step": 1564 + }, + { + "epoch": 0.31, + "learning_rate": 0.00033578825144128013, + "loss": 0.0976, + "step": 1565 + }, + { + "epoch": 0.31, + "learning_rate": 0.0003351840417997679, + "loss": 0.0979, + "step": 1566 + }, + { + "epoch": 0.31, + "learning_rate": 0.00033458010205394793, + "loss": 0.0997, + "step": 1567 + }, + { + "epoch": 0.31, + "learning_rate": 0.00033397643319280665, + "loss": 0.0996, + "step": 1568 + }, + { + "epoch": 0.31, + "learning_rate": 0.0003333730362048866, + "loss": 0.0944, + "step": 1569 + }, + { + "epoch": 0.31, + "learning_rate": 0.00033276991207828563, + "loss": 0.0996, + "step": 1570 + }, + { + "epoch": 0.31, + "learning_rate": 0.00033216706180065424, + "loss": 0.0943, + "step": 1571 + }, + { + "epoch": 0.31, + "learning_rate": 0.0003315644863591949, + "loss": 0.0975, + "step": 1572 + }, + { + "epoch": 0.31, + "learning_rate": 0.0003309621867406597, + "loss": 0.0971, + "step": 1573 + }, + { + "epoch": 0.31, + "learning_rate": 0.00033036016393134937, + "loss": 0.0982, + "step": 1574 + }, + { + "epoch": 0.31, + "learning_rate": 0.00032975841891711105, + "loss": 0.0993, + "step": 1575 + }, + { + "epoch": 0.31, + "learning_rate": 0.0003291569526833372, + "loss": 0.0937, + "step": 1576 + }, + { + "epoch": 0.31, + "learning_rate": 0.0003285557662149636, + "loss": 0.0949, + "step": 1577 + }, + { + "epoch": 0.31, + "learning_rate": 0.000327954860496468, + "loss": 0.0987, + "step": 1578 + }, + { + "epoch": 0.31, + "learning_rate": 0.0003273542365118685, + "loss": 0.099, + "step": 1579 + }, + { + "epoch": 0.31, + "learning_rate": 0.00032675389524472145, + "loss": 0.0929, + "step": 1580 + }, + { + "epoch": 0.31, + "learning_rate": 0.0003261538376781206, + "loss": 0.098, + "step": 1581 + }, + { + "epoch": 0.31, + "learning_rate": 0.0003255540647946951, + "loss": 0.0954, + "step": 1582 + }, + { + "epoch": 0.31, + "learning_rate": 0.0003249545775766077, + "loss": 0.0967, + "step": 1583 + }, + { + "epoch": 0.31, + "learning_rate": 0.00032435537700555364, + "loss": 0.0977, + "step": 1584 + }, + { + "epoch": 0.31, + "learning_rate": 0.00032375646406275857, + "loss": 0.0965, + "step": 1585 + }, + { + "epoch": 0.31, + "learning_rate": 0.0003231578397289772, + "loss": 0.0948, + "step": 1586 + }, + { + "epoch": 0.31, + "learning_rate": 0.0003225595049844915, + "loss": 0.0953, + "step": 1587 + }, + { + "epoch": 0.31, + "learning_rate": 0.00032196146080910935, + "loss": 0.0955, + "step": 1588 + }, + { + "epoch": 0.31, + "learning_rate": 0.0003213637081821629, + "loss": 0.0939, + "step": 1589 + }, + { + "epoch": 0.31, + "learning_rate": 0.00032076624808250663, + "loss": 0.0961, + "step": 1590 + }, + { + "epoch": 0.31, + "learning_rate": 0.0003201690814885162, + "loss": 0.0965, + "step": 1591 + }, + { + "epoch": 0.31, + "learning_rate": 0.0003195722093780864, + "loss": 0.0961, + "step": 1592 + }, + { + "epoch": 0.31, + "learning_rate": 0.0003189756327286301, + "loss": 0.0963, + "step": 1593 + }, + { + "epoch": 0.31, + "learning_rate": 0.0003183793525170761, + "loss": 0.0937, + "step": 1594 + }, + { + "epoch": 0.32, + "learning_rate": 0.00031778336971986787, + "loss": 0.0995, + "step": 1595 + }, + { + "epoch": 0.32, + "learning_rate": 0.00031718768531296195, + "loss": 0.0961, + "step": 1596 + }, + { + "epoch": 0.32, + "learning_rate": 0.00031659230027182567, + "loss": 0.0992, + "step": 1597 + }, + { + "epoch": 0.32, + "learning_rate": 0.0003159972155714369, + "loss": 0.0992, + "step": 1598 + }, + { + "epoch": 0.32, + "learning_rate": 0.0003154024321862813, + "loss": 0.0983, + "step": 1599 + }, + { + "epoch": 0.32, + "learning_rate": 0.00031480795109035123, + "loss": 0.0979, + "step": 1600 + }, + { + "epoch": 0.32, + "learning_rate": 0.00031421377325714374, + "loss": 0.0967, + "step": 1601 + }, + { + "epoch": 0.32, + "learning_rate": 0.00031361989965965977, + "loss": 0.0964, + "step": 1602 + }, + { + "epoch": 0.32, + "learning_rate": 0.0003130263312704017, + "loss": 0.1, + "step": 1603 + }, + { + "epoch": 0.32, + "learning_rate": 0.00031243306906137216, + "loss": 0.0972, + "step": 1604 + }, + { + "epoch": 0.32, + "learning_rate": 0.00031184011400407243, + "loss": 0.099, + "step": 1605 + }, + { + "epoch": 0.32, + "learning_rate": 0.0003112474670695008, + "loss": 0.0957, + "step": 1606 + }, + { + "epoch": 0.32, + "learning_rate": 0.0003106551292281511, + "loss": 0.0953, + "step": 1607 + }, + { + "epoch": 0.32, + "learning_rate": 0.0003100631014500108, + "loss": 0.1009, + "step": 1608 + }, + { + "epoch": 0.32, + "learning_rate": 0.00030947138470455973, + "loss": 0.0966, + "step": 1609 + }, + { + "epoch": 0.32, + "learning_rate": 0.0003088799799607684, + "loss": 0.0983, + "step": 1610 + }, + { + "epoch": 0.32, + "learning_rate": 0.00030828888818709656, + "loss": 0.0975, + "step": 1611 + }, + { + "epoch": 0.32, + "learning_rate": 0.00030769811035149104, + "loss": 0.0954, + "step": 1612 + }, + { + "epoch": 0.32, + "learning_rate": 0.0003071076474213851, + "loss": 0.0953, + "step": 1613 + }, + { + "epoch": 0.32, + "learning_rate": 0.00030651750036369565, + "loss": 0.1027, + "step": 1614 + }, + { + "epoch": 0.32, + "learning_rate": 0.00030592767014482293, + "loss": 0.0975, + "step": 1615 + }, + { + "epoch": 0.32, + "learning_rate": 0.0003053381577306481, + "loss": 0.0995, + "step": 1616 + }, + { + "epoch": 0.32, + "learning_rate": 0.000304748964086532, + "loss": 0.0962, + "step": 1617 + }, + { + "epoch": 0.32, + "learning_rate": 0.0003041600901773133, + "loss": 0.0964, + "step": 1618 + }, + { + "epoch": 0.32, + "learning_rate": 0.00030357153696730735, + "loss": 0.0945, + "step": 1619 + }, + { + "epoch": 0.32, + "learning_rate": 0.00030298330542030406, + "loss": 0.0997, + "step": 1620 + }, + { + "epoch": 0.32, + "learning_rate": 0.00030239539649956664, + "loss": 0.097, + "step": 1621 + }, + { + "epoch": 0.32, + "learning_rate": 0.0003018078111678302, + "loss": 0.0928, + "step": 1622 + }, + { + "epoch": 0.32, + "learning_rate": 0.00030122055038729975, + "loss": 0.096, + "step": 1623 + }, + { + "epoch": 0.32, + "learning_rate": 0.0003006336151196488, + "loss": 0.0957, + "step": 1624 + }, + { + "epoch": 0.32, + "learning_rate": 0.00030004700632601806, + "loss": 0.0994, + "step": 1625 + }, + { + "epoch": 0.32, + "learning_rate": 0.0002994607249670133, + "loss": 0.097, + "step": 1626 + }, + { + "epoch": 0.32, + "learning_rate": 0.0002988747720027044, + "loss": 0.1009, + "step": 1627 + }, + { + "epoch": 0.32, + "learning_rate": 0.0002982891483926232, + "loss": 0.0946, + "step": 1628 + }, + { + "epoch": 0.32, + "learning_rate": 0.0002977038550957624, + "loss": 0.096, + "step": 1629 + }, + { + "epoch": 0.32, + "learning_rate": 0.00029711889307057384, + "loss": 0.0967, + "step": 1630 + }, + { + "epoch": 0.32, + "learning_rate": 0.0002965342632749665, + "loss": 0.0973, + "step": 1631 + }, + { + "epoch": 0.32, + "learning_rate": 0.0002959499666663057, + "loss": 0.0995, + "step": 1632 + }, + { + "epoch": 0.32, + "learning_rate": 0.0002953660042014111, + "loss": 0.0913, + "step": 1633 + }, + { + "epoch": 0.32, + "learning_rate": 0.00029478237683655507, + "loss": 0.0983, + "step": 1634 + }, + { + "epoch": 0.32, + "learning_rate": 0.00029419908552746123, + "loss": 0.0947, + "step": 1635 + }, + { + "epoch": 0.32, + "learning_rate": 0.00029361613122930305, + "loss": 0.1003, + "step": 1636 + }, + { + "epoch": 0.32, + "learning_rate": 0.0002930335148967018, + "loss": 0.0943, + "step": 1637 + }, + { + "epoch": 0.32, + "learning_rate": 0.0002924512374837258, + "loss": 0.0964, + "step": 1638 + }, + { + "epoch": 0.32, + "learning_rate": 0.00029186929994388786, + "loss": 0.0977, + "step": 1639 + }, + { + "epoch": 0.32, + "learning_rate": 0.00029128770323014473, + "loss": 0.0959, + "step": 1640 + }, + { + "epoch": 0.32, + "learning_rate": 0.0002907064482948943, + "loss": 0.0958, + "step": 1641 + }, + { + "epoch": 0.32, + "learning_rate": 0.00029012553608997576, + "loss": 0.0974, + "step": 1642 + }, + { + "epoch": 0.32, + "learning_rate": 0.0002895449675666661, + "loss": 0.0946, + "step": 1643 + }, + { + "epoch": 0.32, + "learning_rate": 0.0002889647436756804, + "loss": 0.0957, + "step": 1644 + }, + { + "epoch": 0.32, + "learning_rate": 0.0002883848653671685, + "loss": 0.0967, + "step": 1645 + }, + { + "epoch": 0.33, + "learning_rate": 0.00028780533359071503, + "loss": 0.0967, + "step": 1646 + }, + { + "epoch": 0.33, + "learning_rate": 0.00028722614929533696, + "loss": 0.0969, + "step": 1647 + }, + { + "epoch": 0.33, + "learning_rate": 0.0002866473134294818, + "loss": 0.0985, + "step": 1648 + }, + { + "epoch": 0.33, + "learning_rate": 0.00028606882694102737, + "loss": 0.0939, + "step": 1649 + }, + { + "epoch": 0.33, + "learning_rate": 0.0002854906907772783, + "loss": 0.0952, + "step": 1650 + }, + { + "epoch": 0.33, + "learning_rate": 0.00028491290588496666, + "loss": 0.0986, + "step": 1651 + }, + { + "epoch": 0.33, + "learning_rate": 0.00028433547321024815, + "loss": 0.0957, + "step": 1652 + }, + { + "epoch": 0.33, + "learning_rate": 0.0002837583936987028, + "loss": 0.0962, + "step": 1653 + }, + { + "epoch": 0.33, + "learning_rate": 0.00028318166829533137, + "loss": 0.0995, + "step": 1654 + }, + { + "epoch": 0.33, + "learning_rate": 0.0002826052979445556, + "loss": 0.0953, + "step": 1655 + }, + { + "epoch": 0.33, + "learning_rate": 0.0002820292835902148, + "loss": 0.0946, + "step": 1656 + }, + { + "epoch": 0.33, + "learning_rate": 0.00028145362617556645, + "loss": 0.0986, + "step": 1657 + }, + { + "epoch": 0.33, + "learning_rate": 0.0002808783266432825, + "loss": 0.0981, + "step": 1658 + }, + { + "epoch": 0.33, + "learning_rate": 0.0002803033859354498, + "loss": 0.0958, + "step": 1659 + }, + { + "epoch": 0.33, + "learning_rate": 0.00027972880499356657, + "loss": 0.094, + "step": 1660 + }, + { + "epoch": 0.33, + "learning_rate": 0.00027915458475854285, + "loss": 0.0942, + "step": 1661 + }, + { + "epoch": 0.33, + "learning_rate": 0.0002785807261706973, + "loss": 0.0994, + "step": 1662 + }, + { + "epoch": 0.33, + "learning_rate": 0.00027800723016975693, + "loss": 0.0912, + "step": 1663 + }, + { + "epoch": 0.33, + "learning_rate": 0.0002774340976948544, + "loss": 0.0931, + "step": 1664 + }, + { + "epoch": 0.33, + "learning_rate": 0.0002768613296845279, + "loss": 0.099, + "step": 1665 + }, + { + "epoch": 0.33, + "learning_rate": 0.0002762889270767175, + "loss": 0.0956, + "step": 1666 + }, + { + "epoch": 0.33, + "learning_rate": 0.0002757168908087663, + "loss": 0.0939, + "step": 1667 + }, + { + "epoch": 0.33, + "learning_rate": 0.00027514522181741645, + "loss": 0.0977, + "step": 1668 + }, + { + "epoch": 0.33, + "learning_rate": 0.0002745739210388095, + "loss": 0.0955, + "step": 1669 + }, + { + "epoch": 0.33, + "learning_rate": 0.0002740029894084832, + "loss": 0.0932, + "step": 1670 + }, + { + "epoch": 0.33, + "learning_rate": 0.0002734324278613717, + "loss": 0.0957, + "step": 1671 + }, + { + "epoch": 0.33, + "learning_rate": 0.00027286223733180207, + "loss": 0.0979, + "step": 1672 + }, + { + "epoch": 0.33, + "learning_rate": 0.0002722924187534948, + "loss": 0.097, + "step": 1673 + }, + { + "epoch": 0.33, + "learning_rate": 0.0002717229730595606, + "loss": 0.0959, + "step": 1674 + }, + { + "epoch": 0.33, + "learning_rate": 0.00027115390118250015, + "loss": 0.0943, + "step": 1675 + }, + { + "epoch": 0.33, + "learning_rate": 0.0002705852040542012, + "loss": 0.0956, + "step": 1676 + }, + { + "epoch": 0.33, + "learning_rate": 0.00027001688260593884, + "loss": 0.0958, + "step": 1677 + }, + { + "epoch": 0.33, + "learning_rate": 0.0002694489377683719, + "loss": 0.099, + "step": 1678 + }, + { + "epoch": 0.33, + "learning_rate": 0.00026888137047154337, + "loss": 0.0979, + "step": 1679 + }, + { + "epoch": 0.33, + "learning_rate": 0.0002683141816448772, + "loss": 0.0972, + "step": 1680 + }, + { + "epoch": 0.33, + "learning_rate": 0.0002677473722171786, + "loss": 0.0924, + "step": 1681 + }, + { + "epoch": 0.33, + "learning_rate": 0.0002671809431166304, + "loss": 0.0975, + "step": 1682 + }, + { + "epoch": 0.33, + "learning_rate": 0.0002666148952707932, + "loss": 0.0973, + "step": 1683 + }, + { + "epoch": 0.33, + "learning_rate": 0.0002660492296066034, + "loss": 0.092, + "step": 1684 + }, + { + "epoch": 0.33, + "learning_rate": 0.0002654839470503709, + "loss": 0.096, + "step": 1685 + }, + { + "epoch": 0.33, + "learning_rate": 0.0002649190485277792, + "loss": 0.0958, + "step": 1686 + }, + { + "epoch": 0.33, + "learning_rate": 0.00026435453496388196, + "loss": 0.0963, + "step": 1687 + }, + { + "epoch": 0.33, + "learning_rate": 0.00026379040728310326, + "loss": 0.0951, + "step": 1688 + }, + { + "epoch": 0.33, + "learning_rate": 0.0002632266664092345, + "loss": 0.0955, + "step": 1689 + }, + { + "epoch": 0.33, + "learning_rate": 0.0002626633132654346, + "loss": 0.099, + "step": 1690 + }, + { + "epoch": 0.33, + "learning_rate": 0.0002621003487742264, + "loss": 0.0973, + "step": 1691 + }, + { + "epoch": 0.33, + "learning_rate": 0.00026153777385749745, + "loss": 0.0935, + "step": 1692 + }, + { + "epoch": 0.33, + "learning_rate": 0.00026097558943649634, + "loss": 0.0981, + "step": 1693 + }, + { + "epoch": 0.33, + "learning_rate": 0.00026041379643183316, + "loss": 0.0986, + "step": 1694 + }, + { + "epoch": 0.33, + "learning_rate": 0.00025985239576347595, + "loss": 0.0949, + "step": 1695 + }, + { + "epoch": 0.34, + "learning_rate": 0.0002592913883507515, + "loss": 0.0965, + "step": 1696 + }, + { + "epoch": 0.34, + "learning_rate": 0.00025873077511234154, + "loss": 0.1001, + "step": 1697 + }, + { + "epoch": 0.34, + "learning_rate": 0.000258170556966283, + "loss": 0.0956, + "step": 1698 + }, + { + "epoch": 0.34, + "learning_rate": 0.0002576107348299656, + "loss": 0.0946, + "step": 1699 + }, + { + "epoch": 0.34, + "learning_rate": 0.0002570513096201305, + "loss": 0.0983, + "step": 1700 + }, + { + "epoch": 0.34, + "learning_rate": 0.0002564922822528686, + "loss": 0.0951, + "step": 1701 + }, + { + "epoch": 0.34, + "learning_rate": 0.0002559336536436202, + "loss": 0.0954, + "step": 1702 + }, + { + "epoch": 0.34, + "learning_rate": 0.0002553754247071717, + "loss": 0.0947, + "step": 1703 + }, + { + "epoch": 0.34, + "learning_rate": 0.00025481759635765554, + "loss": 0.0978, + "step": 1704 + }, + { + "epoch": 0.34, + "learning_rate": 0.00025426016950854774, + "loss": 0.0989, + "step": 1705 + }, + { + "epoch": 0.34, + "learning_rate": 0.00025370314507266756, + "loss": 0.097, + "step": 1706 + }, + { + "epoch": 0.34, + "learning_rate": 0.0002531465239621743, + "loss": 0.0989, + "step": 1707 + }, + { + "epoch": 0.34, + "learning_rate": 0.0002525903070885678, + "loss": 0.0946, + "step": 1708 + }, + { + "epoch": 0.34, + "learning_rate": 0.00025203449536268495, + "loss": 0.095, + "step": 1709 + }, + { + "epoch": 0.34, + "learning_rate": 0.00025147908969470027, + "loss": 0.0978, + "step": 1710 + }, + { + "epoch": 0.34, + "learning_rate": 0.00025092409099412226, + "loss": 0.0959, + "step": 1711 + }, + { + "epoch": 0.34, + "learning_rate": 0.0002503695001697939, + "loss": 0.0969, + "step": 1712 + }, + { + "epoch": 0.34, + "learning_rate": 0.0002498153181298893, + "loss": 0.0953, + "step": 1713 + }, + { + "epoch": 0.34, + "learning_rate": 0.00024926154578191437, + "loss": 0.0972, + "step": 1714 + }, + { + "epoch": 0.34, + "learning_rate": 0.0002487081840327028, + "loss": 0.0946, + "step": 1715 + }, + { + "epoch": 0.34, + "learning_rate": 0.00024815523378841724, + "loss": 0.0994, + "step": 1716 + }, + { + "epoch": 0.34, + "learning_rate": 0.0002476026959545451, + "loss": 0.0965, + "step": 1717 + }, + { + "epoch": 0.34, + "learning_rate": 0.0002470505714358996, + "loss": 0.0973, + "step": 1718 + }, + { + "epoch": 0.34, + "learning_rate": 0.00024649886113661633, + "loss": 0.0951, + "step": 1719 + }, + { + "epoch": 0.34, + "learning_rate": 0.00024594756596015325, + "loss": 0.0963, + "step": 1720 + }, + { + "epoch": 0.34, + "learning_rate": 0.0002453966868092878, + "loss": 0.0972, + "step": 1721 + }, + { + "epoch": 0.34, + "learning_rate": 0.0002448462245861171, + "loss": 0.0942, + "step": 1722 + }, + { + "epoch": 0.34, + "learning_rate": 0.00024429618019205433, + "loss": 0.0969, + "step": 1723 + }, + { + "epoch": 0.34, + "learning_rate": 0.00024374655452782967, + "loss": 0.0936, + "step": 1724 + }, + { + "epoch": 0.34, + "learning_rate": 0.00024319734849348657, + "loss": 0.0949, + "step": 1725 + }, + { + "epoch": 0.34, + "learning_rate": 0.0002426485629883821, + "loss": 0.101, + "step": 1726 + }, + { + "epoch": 0.34, + "learning_rate": 0.00024210019891118413, + "loss": 0.097, + "step": 1727 + }, + { + "epoch": 0.34, + "learning_rate": 0.00024155225715987084, + "loss": 0.0936, + "step": 1728 + }, + { + "epoch": 0.34, + "learning_rate": 0.00024100473863172838, + "loss": 0.0995, + "step": 1729 + }, + { + "epoch": 0.34, + "learning_rate": 0.0002404576442233504, + "loss": 0.0952, + "step": 1730 + }, + { + "epoch": 0.34, + "learning_rate": 0.0002399109748306355, + "loss": 0.0999, + "step": 1731 + }, + { + "epoch": 0.34, + "learning_rate": 0.00023936473134878673, + "loss": 0.0938, + "step": 1732 + }, + { + "epoch": 0.34, + "learning_rate": 0.00023881891467230932, + "loss": 0.0979, + "step": 1733 + }, + { + "epoch": 0.34, + "learning_rate": 0.00023827352569500966, + "loss": 0.0945, + "step": 1734 + }, + { + "epoch": 0.34, + "learning_rate": 0.00023772856530999409, + "loss": 0.0959, + "step": 1735 + }, + { + "epoch": 0.34, + "learning_rate": 0.0002371840344096665, + "loss": 0.0935, + "step": 1736 + }, + { + "epoch": 0.34, + "learning_rate": 0.0002366399338857283, + "loss": 0.0964, + "step": 1737 + }, + { + "epoch": 0.34, + "learning_rate": 0.00023609626462917516, + "loss": 0.0948, + "step": 1738 + }, + { + "epoch": 0.34, + "learning_rate": 0.0002355530275302975, + "loss": 0.0951, + "step": 1739 + }, + { + "epoch": 0.34, + "learning_rate": 0.00023501022347867712, + "loss": 0.0986, + "step": 1740 + }, + { + "epoch": 0.34, + "learning_rate": 0.00023446785336318754, + "loss": 0.0989, + "step": 1741 + }, + { + "epoch": 0.34, + "learning_rate": 0.000233925918071991, + "loss": 0.0947, + "step": 1742 + }, + { + "epoch": 0.34, + "learning_rate": 0.00023338441849253823, + "loss": 0.0949, + "step": 1743 + }, + { + "epoch": 0.34, + "learning_rate": 0.00023284335551156582, + "loss": 0.0932, + "step": 1744 + }, + { + "epoch": 0.34, + "learning_rate": 0.00023230273001509626, + "loss": 0.0962, + "step": 1745 + }, + { + "epoch": 0.34, + "learning_rate": 0.0002317625428884348, + "loss": 0.0947, + "step": 1746 + }, + { + "epoch": 0.35, + "learning_rate": 0.00023122279501616944, + "loss": 0.0928, + "step": 1747 + }, + { + "epoch": 0.35, + "learning_rate": 0.00023068348728216836, + "loss": 0.0926, + "step": 1748 + }, + { + "epoch": 0.35, + "learning_rate": 0.00023014462056957963, + "loss": 0.0921, + "step": 1749 + }, + { + "epoch": 0.35, + "learning_rate": 0.00022960619576082854, + "loss": 0.0951, + "step": 1750 + }, + { + "epoch": 0.35, + "learning_rate": 0.00022906821373761688, + "loss": 0.0958, + "step": 1751 + }, + { + "epoch": 0.35, + "learning_rate": 0.0002285306753809213, + "loss": 0.0961, + "step": 1752 + }, + { + "epoch": 0.35, + "learning_rate": 0.0002279935815709925, + "loss": 0.0943, + "step": 1753 + }, + { + "epoch": 0.35, + "learning_rate": 0.00022745693318735222, + "loss": 0.0944, + "step": 1754 + }, + { + "epoch": 0.35, + "learning_rate": 0.00022692073110879373, + "loss": 0.0967, + "step": 1755 + }, + { + "epoch": 0.35, + "learning_rate": 0.0002263849762133788, + "loss": 0.0956, + "step": 1756 + }, + { + "epoch": 0.35, + "learning_rate": 0.0002258496693784373, + "loss": 0.0962, + "step": 1757 + }, + { + "epoch": 0.35, + "learning_rate": 0.00022531481148056504, + "loss": 0.0959, + "step": 1758 + }, + { + "epoch": 0.35, + "learning_rate": 0.00022478040339562317, + "loss": 0.0906, + "step": 1759 + }, + { + "epoch": 0.35, + "learning_rate": 0.0002242464459987355, + "loss": 0.0919, + "step": 1760 + }, + { + "epoch": 0.35, + "learning_rate": 0.00022371294016428867, + "loss": 0.096, + "step": 1761 + }, + { + "epoch": 0.35, + "learning_rate": 0.00022317988676592905, + "loss": 0.0963, + "step": 1762 + }, + { + "epoch": 0.35, + "learning_rate": 0.0002226472866765628, + "loss": 0.0963, + "step": 1763 + }, + { + "epoch": 0.35, + "learning_rate": 0.00022211514076835327, + "loss": 0.0957, + "step": 1764 + }, + { + "epoch": 0.35, + "learning_rate": 0.00022158344991272044, + "loss": 0.0982, + "step": 1765 + }, + { + "epoch": 0.35, + "learning_rate": 0.0002210522149803386, + "loss": 0.0941, + "step": 1766 + }, + { + "epoch": 0.35, + "learning_rate": 0.00022052143684113623, + "loss": 0.0943, + "step": 1767 + }, + { + "epoch": 0.35, + "learning_rate": 0.0002199911163642931, + "loss": 0.0967, + "step": 1768 + }, + { + "epoch": 0.35, + "learning_rate": 0.0002194612544182395, + "loss": 0.097, + "step": 1769 + }, + { + "epoch": 0.35, + "learning_rate": 0.0002189318518706555, + "loss": 0.095, + "step": 1770 + }, + { + "epoch": 0.35, + "learning_rate": 0.00021840290958846816, + "loss": 0.0964, + "step": 1771 + }, + { + "epoch": 0.35, + "learning_rate": 0.0002178744284378515, + "loss": 0.0962, + "step": 1772 + }, + { + "epoch": 0.35, + "learning_rate": 0.0002173464092842236, + "loss": 0.0927, + "step": 1773 + }, + { + "epoch": 0.35, + "learning_rate": 0.00021681885299224696, + "loss": 0.0969, + "step": 1774 + }, + { + "epoch": 0.35, + "learning_rate": 0.00021629176042582522, + "loss": 0.0932, + "step": 1775 + }, + { + "epoch": 0.35, + "learning_rate": 0.0002157651324481033, + "loss": 0.0924, + "step": 1776 + }, + { + "epoch": 0.35, + "learning_rate": 0.0002152389699214648, + "loss": 0.0949, + "step": 1777 + }, + { + "epoch": 0.35, + "learning_rate": 0.00021471327370753169, + "loss": 0.096, + "step": 1778 + }, + { + "epoch": 0.35, + "learning_rate": 0.00021418804466716168, + "loss": 0.0927, + "step": 1779 + }, + { + "epoch": 0.35, + "learning_rate": 0.00021366328366044813, + "loss": 0.0977, + "step": 1780 + }, + { + "epoch": 0.35, + "learning_rate": 0.0002131389915467173, + "loss": 0.0937, + "step": 1781 + }, + { + "epoch": 0.35, + "learning_rate": 0.0002126151691845282, + "loss": 0.0993, + "step": 1782 + }, + { + "epoch": 0.35, + "learning_rate": 0.00021209181743167012, + "loss": 0.0931, + "step": 1783 + }, + { + "epoch": 0.35, + "learning_rate": 0.00021156893714516218, + "loss": 0.0933, + "step": 1784 + }, + { + "epoch": 0.35, + "learning_rate": 0.00021104652918125106, + "loss": 0.0931, + "step": 1785 + }, + { + "epoch": 0.35, + "learning_rate": 0.00021052459439541005, + "loss": 0.093, + "step": 1786 + }, + { + "epoch": 0.35, + "learning_rate": 0.0002100031336423375, + "loss": 0.0944, + "step": 1787 + }, + { + "epoch": 0.35, + "learning_rate": 0.00020948214777595593, + "loss": 0.0955, + "step": 1788 + }, + { + "epoch": 0.35, + "learning_rate": 0.0002089616376494096, + "loss": 0.1013, + "step": 1789 + }, + { + "epoch": 0.35, + "learning_rate": 0.00020844160411506447, + "loss": 0.0992, + "step": 1790 + }, + { + "epoch": 0.35, + "learning_rate": 0.00020792204802450514, + "loss": 0.0948, + "step": 1791 + }, + { + "epoch": 0.35, + "learning_rate": 0.00020740297022853532, + "loss": 0.0932, + "step": 1792 + }, + { + "epoch": 0.35, + "learning_rate": 0.00020688437157717455, + "loss": 0.0939, + "step": 1793 + }, + { + "epoch": 0.35, + "learning_rate": 0.00020636625291965861, + "loss": 0.0961, + "step": 1794 + }, + { + "epoch": 0.35, + "learning_rate": 0.00020584861510443653, + "loss": 0.0998, + "step": 1795 + }, + { + "epoch": 0.35, + "learning_rate": 0.00020533145897917054, + "loss": 0.0929, + "step": 1796 + }, + { + "epoch": 0.35, + "learning_rate": 0.0002048147853907335, + "loss": 0.0946, + "step": 1797 + }, + { + "epoch": 0.36, + "learning_rate": 0.0002042985951852087, + "loss": 0.0975, + "step": 1798 + }, + { + "epoch": 0.36, + "learning_rate": 0.00020378288920788718, + "loss": 0.0961, + "step": 1799 + }, + { + "epoch": 0.36, + "learning_rate": 0.00020326766830326782, + "loss": 0.0967, + "step": 1800 + }, + { + "epoch": 0.36, + "learning_rate": 0.00020275293331505434, + "loss": 0.0928, + "step": 1801 + }, + { + "epoch": 0.36, + "learning_rate": 0.00020223868508615551, + "loss": 0.0956, + "step": 1802 + }, + { + "epoch": 0.36, + "learning_rate": 0.0002017249244586824, + "loss": 0.0984, + "step": 1803 + }, + { + "epoch": 0.36, + "learning_rate": 0.0002012116522739477, + "loss": 0.094, + "step": 1804 + }, + { + "epoch": 0.36, + "learning_rate": 0.0002006988693724648, + "loss": 0.0954, + "step": 1805 + }, + { + "epoch": 0.36, + "learning_rate": 0.00020018657659394496, + "loss": 0.0951, + "step": 1806 + }, + { + "epoch": 0.36, + "learning_rate": 0.00019967477477729785, + "loss": 0.0948, + "step": 1807 + }, + { + "epoch": 0.36, + "learning_rate": 0.00019916346476062813, + "loss": 0.0939, + "step": 1808 + }, + { + "epoch": 0.36, + "learning_rate": 0.000198652647381236, + "loss": 0.0955, + "step": 1809 + }, + { + "epoch": 0.36, + "learning_rate": 0.00019814232347561427, + "loss": 0.0968, + "step": 1810 + }, + { + "epoch": 0.36, + "learning_rate": 0.0001976324938794482, + "loss": 0.096, + "step": 1811 + }, + { + "epoch": 0.36, + "learning_rate": 0.00019712315942761304, + "loss": 0.0954, + "step": 1812 + }, + { + "epoch": 0.36, + "learning_rate": 0.0001966143209541738, + "loss": 0.0954, + "step": 1813 + }, + { + "epoch": 0.36, + "learning_rate": 0.00019610597929238272, + "loss": 0.0965, + "step": 1814 + }, + { + "epoch": 0.36, + "learning_rate": 0.00019559813527467902, + "loss": 0.0961, + "step": 1815 + }, + { + "epoch": 0.36, + "learning_rate": 0.00019509078973268645, + "loss": 0.092, + "step": 1816 + }, + { + "epoch": 0.36, + "learning_rate": 0.0001945839434972131, + "loss": 0.0917, + "step": 1817 + }, + { + "epoch": 0.36, + "learning_rate": 0.0001940775973982487, + "loss": 0.095, + "step": 1818 + }, + { + "epoch": 0.36, + "learning_rate": 0.00019357175226496494, + "loss": 0.0924, + "step": 1819 + }, + { + "epoch": 0.36, + "learning_rate": 0.00019306640892571188, + "loss": 0.0957, + "step": 1820 + }, + { + "epoch": 0.36, + "learning_rate": 0.00019256156820801897, + "loss": 0.0916, + "step": 1821 + }, + { + "epoch": 0.36, + "learning_rate": 0.0001920572309385919, + "loss": 0.0957, + "step": 1822 + }, + { + "epoch": 0.36, + "learning_rate": 0.00019155339794331257, + "loss": 0.0988, + "step": 1823 + }, + { + "epoch": 0.36, + "learning_rate": 0.00019105007004723636, + "loss": 0.0949, + "step": 1824 + }, + { + "epoch": 0.36, + "learning_rate": 0.00019054724807459218, + "loss": 0.0956, + "step": 1825 + }, + { + "epoch": 0.36, + "learning_rate": 0.00019004493284877994, + "loss": 0.0955, + "step": 1826 + }, + { + "epoch": 0.36, + "learning_rate": 0.00018954312519237028, + "loss": 0.0981, + "step": 1827 + }, + { + "epoch": 0.36, + "learning_rate": 0.00018904182592710195, + "loss": 0.0968, + "step": 1828 + }, + { + "epoch": 0.36, + "learning_rate": 0.00018854103587388199, + "loss": 0.0966, + "step": 1829 + }, + { + "epoch": 0.36, + "learning_rate": 0.00018804075585278278, + "loss": 0.095, + "step": 1830 + }, + { + "epoch": 0.36, + "learning_rate": 0.0001875409866830422, + "loss": 0.0954, + "step": 1831 + }, + { + "epoch": 0.36, + "learning_rate": 0.00018704172918306095, + "loss": 0.0971, + "step": 1832 + }, + { + "epoch": 0.36, + "learning_rate": 0.00018654298417040244, + "loss": 0.0902, + "step": 1833 + }, + { + "epoch": 0.36, + "learning_rate": 0.00018604475246179031, + "loss": 0.0922, + "step": 1834 + }, + { + "epoch": 0.36, + "learning_rate": 0.00018554703487310808, + "loss": 0.0945, + "step": 1835 + }, + { + "epoch": 0.36, + "learning_rate": 0.0001850498322193972, + "loss": 0.0985, + "step": 1836 + }, + { + "epoch": 0.36, + "learning_rate": 0.00018455314531485567, + "loss": 0.0936, + "step": 1837 + }, + { + "epoch": 0.36, + "learning_rate": 0.00018405697497283702, + "loss": 0.0982, + "step": 1838 + }, + { + "epoch": 0.36, + "learning_rate": 0.00018356132200584928, + "loss": 0.0988, + "step": 1839 + }, + { + "epoch": 0.36, + "learning_rate": 0.00018306618722555267, + "loss": 0.0966, + "step": 1840 + }, + { + "epoch": 0.36, + "learning_rate": 0.00018257157144275937, + "loss": 0.0967, + "step": 1841 + }, + { + "epoch": 0.36, + "learning_rate": 0.00018207747546743113, + "loss": 0.094, + "step": 1842 + }, + { + "epoch": 0.36, + "learning_rate": 0.00018158390010867908, + "loss": 0.0901, + "step": 1843 + }, + { + "epoch": 0.36, + "learning_rate": 0.0001810908461747612, + "loss": 0.0914, + "step": 1844 + }, + { + "epoch": 0.36, + "learning_rate": 0.00018059831447308217, + "loss": 0.0949, + "step": 1845 + }, + { + "epoch": 0.36, + "learning_rate": 0.00018010630581019095, + "loss": 0.0978, + "step": 1846 + }, + { + "epoch": 0.36, + "learning_rate": 0.0001796148209917806, + "loss": 0.0917, + "step": 1847 + }, + { + "epoch": 0.37, + "learning_rate": 0.00017912386082268567, + "loss": 0.0966, + "step": 1848 + }, + { + "epoch": 0.37, + "learning_rate": 0.0001786334261068822, + "loss": 0.0985, + "step": 1849 + }, + { + "epoch": 0.37, + "learning_rate": 0.00017814351764748525, + "loss": 0.0966, + "step": 1850 + }, + { + "epoch": 0.37, + "learning_rate": 0.00017765413624674866, + "loss": 0.0964, + "step": 1851 + }, + { + "epoch": 0.37, + "learning_rate": 0.0001771652827060624, + "loss": 0.0968, + "step": 1852 + }, + { + "epoch": 0.37, + "learning_rate": 0.000176676957825953, + "loss": 0.0912, + "step": 1853 + }, + { + "epoch": 0.37, + "learning_rate": 0.00017618916240608052, + "loss": 0.0946, + "step": 1854 + }, + { + "epoch": 0.37, + "learning_rate": 0.0001757018972452381, + "loss": 0.0945, + "step": 1855 + }, + { + "epoch": 0.37, + "learning_rate": 0.00017521516314135112, + "loss": 0.0979, + "step": 1856 + }, + { + "epoch": 0.37, + "learning_rate": 0.00017472896089147443, + "loss": 0.0965, + "step": 1857 + }, + { + "epoch": 0.37, + "learning_rate": 0.00017424329129179283, + "loss": 0.0952, + "step": 1858 + }, + { + "epoch": 0.37, + "learning_rate": 0.00017375815513761818, + "loss": 0.0968, + "step": 1859 + }, + { + "epoch": 0.37, + "learning_rate": 0.00017327355322338935, + "loss": 0.0971, + "step": 1860 + }, + { + "epoch": 0.37, + "learning_rate": 0.00017278948634266966, + "loss": 0.0912, + "step": 1861 + }, + { + "epoch": 0.37, + "learning_rate": 0.00017230595528814724, + "loss": 0.0893, + "step": 1862 + }, + { + "epoch": 0.37, + "learning_rate": 0.0001718229608516318, + "loss": 0.0948, + "step": 1863 + }, + { + "epoch": 0.37, + "learning_rate": 0.00017134050382405504, + "loss": 0.0993, + "step": 1864 + }, + { + "epoch": 0.37, + "learning_rate": 0.00017085858499546802, + "loss": 0.0925, + "step": 1865 + }, + { + "epoch": 0.37, + "learning_rate": 0.0001703772051550412, + "loss": 0.093, + "step": 1866 + }, + { + "epoch": 0.37, + "learning_rate": 0.00016989636509106155, + "loss": 0.0974, + "step": 1867 + }, + { + "epoch": 0.37, + "learning_rate": 0.00016941606559093292, + "loss": 0.0955, + "step": 1868 + }, + { + "epoch": 0.37, + "learning_rate": 0.00016893630744117333, + "loss": 0.0944, + "step": 1869 + }, + { + "epoch": 0.37, + "learning_rate": 0.00016845709142741488, + "loss": 0.0942, + "step": 1870 + }, + { + "epoch": 0.37, + "learning_rate": 0.0001679784183344014, + "loss": 0.0954, + "step": 1871 + }, + { + "epoch": 0.37, + "learning_rate": 0.00016750028894598786, + "loss": 0.0922, + "step": 1872 + }, + { + "epoch": 0.37, + "learning_rate": 0.0001670227040451387, + "loss": 0.0964, + "step": 1873 + }, + { + "epoch": 0.37, + "learning_rate": 0.00016654566441392726, + "loss": 0.0962, + "step": 1874 + }, + { + "epoch": 0.37, + "learning_rate": 0.00016606917083353324, + "loss": 0.0933, + "step": 1875 + }, + { + "epoch": 0.37, + "learning_rate": 0.00016559322408424287, + "loss": 0.0938, + "step": 1876 + }, + { + "epoch": 0.37, + "learning_rate": 0.00016511782494544626, + "loss": 0.0948, + "step": 1877 + }, + { + "epoch": 0.37, + "learning_rate": 0.00016464297419563733, + "loss": 0.0993, + "step": 1878 + }, + { + "epoch": 0.37, + "learning_rate": 0.00016416867261241148, + "loss": 0.0966, + "step": 1879 + }, + { + "epoch": 0.37, + "learning_rate": 0.0001636949209724653, + "loss": 0.0937, + "step": 1880 + }, + { + "epoch": 0.37, + "learning_rate": 0.00016322172005159435, + "loss": 0.091, + "step": 1881 + }, + { + "epoch": 0.37, + "learning_rate": 0.00016274907062469284, + "loss": 0.0923, + "step": 1882 + }, + { + "epoch": 0.37, + "learning_rate": 0.00016227697346575138, + "loss": 0.0935, + "step": 1883 + }, + { + "epoch": 0.37, + "learning_rate": 0.0001618054293478567, + "loss": 0.0929, + "step": 1884 + }, + { + "epoch": 0.37, + "learning_rate": 0.00016133443904318935, + "loss": 0.0935, + "step": 1885 + }, + { + "epoch": 0.37, + "learning_rate": 0.0001608640033230236, + "loss": 0.0932, + "step": 1886 + }, + { + "epoch": 0.37, + "learning_rate": 0.00016039412295772493, + "loss": 0.0938, + "step": 1887 + }, + { + "epoch": 0.37, + "learning_rate": 0.00015992479871674997, + "loss": 0.0951, + "step": 1888 + }, + { + "epoch": 0.37, + "learning_rate": 0.0001594560313686443, + "loss": 0.0964, + "step": 1889 + }, + { + "epoch": 0.37, + "learning_rate": 0.00015898782168104138, + "loss": 0.0965, + "step": 1890 + }, + { + "epoch": 0.37, + "learning_rate": 0.00015852017042066214, + "loss": 0.0988, + "step": 1891 + }, + { + "epoch": 0.37, + "learning_rate": 0.0001580530783533123, + "loss": 0.095, + "step": 1892 + }, + { + "epoch": 0.37, + "learning_rate": 0.00015758654624388252, + "loss": 0.0938, + "step": 1893 + }, + { + "epoch": 0.37, + "learning_rate": 0.0001571205748563459, + "loss": 0.093, + "step": 1894 + }, + { + "epoch": 0.37, + "learning_rate": 0.0001566551649537579, + "loss": 0.093, + "step": 1895 + }, + { + "epoch": 0.37, + "learning_rate": 0.000156190317298254, + "loss": 0.0979, + "step": 1896 + }, + { + "epoch": 0.37, + "learning_rate": 0.00015572603265104945, + "loss": 0.095, + "step": 1897 + }, + { + "epoch": 0.37, + "learning_rate": 0.00015526231177243695, + "loss": 0.0974, + "step": 1898 + }, + { + "epoch": 0.38, + "learning_rate": 0.0001547991554217867, + "loss": 0.0955, + "step": 1899 + }, + { + "epoch": 0.38, + "learning_rate": 0.00015433656435754372, + "loss": 0.0932, + "step": 1900 + }, + { + "epoch": 0.38, + "learning_rate": 0.00015387453933722811, + "loss": 0.0953, + "step": 1901 + }, + { + "epoch": 0.38, + "learning_rate": 0.0001534130811174323, + "loss": 0.0975, + "step": 1902 + }, + { + "epoch": 0.38, + "learning_rate": 0.00015295219045382113, + "loss": 0.0966, + "step": 1903 + }, + { + "epoch": 0.38, + "learning_rate": 0.00015249186810112957, + "loss": 0.0914, + "step": 1904 + }, + { + "epoch": 0.38, + "learning_rate": 0.0001520321148131627, + "loss": 0.0915, + "step": 1905 + }, + { + "epoch": 0.38, + "learning_rate": 0.00015157293134279243, + "loss": 0.0942, + "step": 1906 + }, + { + "epoch": 0.38, + "learning_rate": 0.00015111431844195883, + "loss": 0.0956, + "step": 1907 + }, + { + "epoch": 0.38, + "learning_rate": 0.00015065627686166688, + "loss": 0.0977, + "step": 1908 + }, + { + "epoch": 0.38, + "learning_rate": 0.00015019880735198655, + "loss": 0.096, + "step": 1909 + }, + { + "epoch": 0.38, + "learning_rate": 0.00014974191066205033, + "loss": 0.0929, + "step": 1910 + }, + { + "epoch": 0.38, + "learning_rate": 0.0001492855875400534, + "loss": 0.0957, + "step": 1911 + }, + { + "epoch": 0.38, + "learning_rate": 0.00014882983873325102, + "loss": 0.0936, + "step": 1912 + }, + { + "epoch": 0.38, + "learning_rate": 0.0001483746649879586, + "loss": 0.0942, + "step": 1913 + }, + { + "epoch": 0.38, + "learning_rate": 0.00014792006704954924, + "loss": 0.0917, + "step": 1914 + }, + { + "epoch": 0.38, + "learning_rate": 0.00014746604566245376, + "loss": 0.0973, + "step": 1915 + }, + { + "epoch": 0.38, + "learning_rate": 0.0001470126015701582, + "loss": 0.0925, + "step": 1916 + }, + { + "epoch": 0.38, + "learning_rate": 0.0001465597355152039, + "loss": 0.0938, + "step": 1917 + }, + { + "epoch": 0.38, + "learning_rate": 0.00014610744823918498, + "loss": 0.0961, + "step": 1918 + }, + { + "epoch": 0.38, + "learning_rate": 0.00014565574048274837, + "loss": 0.0933, + "step": 1919 + }, + { + "epoch": 0.38, + "learning_rate": 0.00014520461298559145, + "loss": 0.0967, + "step": 1920 + }, + { + "epoch": 0.38, + "learning_rate": 0.00014475406648646196, + "loss": 0.0959, + "step": 1921 + }, + { + "epoch": 0.38, + "learning_rate": 0.00014430410172315572, + "loss": 0.0932, + "step": 1922 + }, + { + "epoch": 0.38, + "learning_rate": 0.00014385471943251604, + "loss": 0.0954, + "step": 1923 + }, + { + "epoch": 0.38, + "learning_rate": 0.00014340592035043281, + "loss": 0.0924, + "step": 1924 + }, + { + "epoch": 0.38, + "learning_rate": 0.0001429577052118402, + "loss": 0.0914, + "step": 1925 + }, + { + "epoch": 0.38, + "learning_rate": 0.00014251007475071686, + "loss": 0.0955, + "step": 1926 + }, + { + "epoch": 0.38, + "learning_rate": 0.0001420630297000833, + "loss": 0.0947, + "step": 1927 + }, + { + "epoch": 0.38, + "learning_rate": 0.00014161657079200202, + "loss": 0.0971, + "step": 1928 + }, + { + "epoch": 0.38, + "learning_rate": 0.00014117069875757505, + "loss": 0.0942, + "step": 1929 + }, + { + "epoch": 0.38, + "learning_rate": 0.00014072541432694408, + "loss": 0.096, + "step": 1930 + }, + { + "epoch": 0.38, + "learning_rate": 0.0001402807182292879, + "loss": 0.0928, + "step": 1931 + }, + { + "epoch": 0.38, + "learning_rate": 0.00013983661119282238, + "loss": 0.0923, + "step": 1932 + }, + { + "epoch": 0.38, + "learning_rate": 0.0001393930939447983, + "loss": 0.0973, + "step": 1933 + }, + { + "epoch": 0.38, + "learning_rate": 0.00013895016721150123, + "loss": 0.0969, + "step": 1934 + }, + { + "epoch": 0.38, + "learning_rate": 0.00013850783171824905, + "loss": 0.0921, + "step": 1935 + }, + { + "epoch": 0.38, + "learning_rate": 0.00013806608818939204, + "loss": 0.0926, + "step": 1936 + }, + { + "epoch": 0.38, + "learning_rate": 0.0001376249373483106, + "loss": 0.0921, + "step": 1937 + }, + { + "epoch": 0.38, + "learning_rate": 0.00013718437991741517, + "loss": 0.0922, + "step": 1938 + }, + { + "epoch": 0.38, + "learning_rate": 0.00013674441661814385, + "loss": 0.0947, + "step": 1939 + }, + { + "epoch": 0.38, + "learning_rate": 0.00013630504817096212, + "loss": 0.0961, + "step": 1940 + }, + { + "epoch": 0.38, + "learning_rate": 0.00013586627529536116, + "loss": 0.0931, + "step": 1941 + }, + { + "epoch": 0.38, + "learning_rate": 0.00013542809870985728, + "loss": 0.0971, + "step": 1942 + }, + { + "epoch": 0.38, + "learning_rate": 0.0001349905191319898, + "loss": 0.0975, + "step": 1943 + }, + { + "epoch": 0.38, + "learning_rate": 0.00013455353727832086, + "loss": 0.094, + "step": 1944 + }, + { + "epoch": 0.38, + "learning_rate": 0.0001341171538644334, + "loss": 0.094, + "step": 1945 + }, + { + "epoch": 0.38, + "learning_rate": 0.00013368136960493083, + "loss": 0.0952, + "step": 1946 + }, + { + "epoch": 0.38, + "learning_rate": 0.00013324618521343484, + "loss": 0.0918, + "step": 1947 + }, + { + "epoch": 0.38, + "learning_rate": 0.00013281160140258546, + "loss": 0.0961, + "step": 1948 + }, + { + "epoch": 0.38, + "learning_rate": 0.00013237761888403854, + "loss": 0.0952, + "step": 1949 + }, + { + "epoch": 0.39, + "learning_rate": 0.00013194423836846597, + "loss": 0.0935, + "step": 1950 + }, + { + "epoch": 0.39, + "learning_rate": 0.00013151146056555318, + "loss": 0.0925, + "step": 1951 + }, + { + "epoch": 0.39, + "learning_rate": 0.00013107928618399917, + "loss": 0.0956, + "step": 1952 + }, + { + "epoch": 0.39, + "learning_rate": 0.00013064771593151436, + "loss": 0.0913, + "step": 1953 + }, + { + "epoch": 0.39, + "learning_rate": 0.0001302167505148203, + "loss": 0.0911, + "step": 1954 + }, + { + "epoch": 0.39, + "learning_rate": 0.00012978639063964754, + "loss": 0.0954, + "step": 1955 + }, + { + "epoch": 0.39, + "learning_rate": 0.00012935663701073587, + "loss": 0.0947, + "step": 1956 + }, + { + "epoch": 0.39, + "learning_rate": 0.0001289274903318311, + "loss": 0.0912, + "step": 1957 + }, + { + "epoch": 0.39, + "learning_rate": 0.00012849895130568633, + "loss": 0.0926, + "step": 1958 + }, + { + "epoch": 0.39, + "learning_rate": 0.00012807102063405873, + "loss": 0.0963, + "step": 1959 + }, + { + "epoch": 0.39, + "learning_rate": 0.00012764369901770988, + "loss": 0.0944, + "step": 1960 + }, + { + "epoch": 0.39, + "learning_rate": 0.0001272169871564035, + "loss": 0.0939, + "step": 1961 + }, + { + "epoch": 0.39, + "learning_rate": 0.0001267908857489053, + "loss": 0.0928, + "step": 1962 + }, + { + "epoch": 0.39, + "learning_rate": 0.00012636539549298065, + "loss": 0.0965, + "step": 1963 + }, + { + "epoch": 0.39, + "learning_rate": 0.00012594051708539493, + "loss": 0.0968, + "step": 1964 + }, + { + "epoch": 0.39, + "learning_rate": 0.00012551625122191084, + "loss": 0.0925, + "step": 1965 + }, + { + "epoch": 0.39, + "learning_rate": 0.0001250925985972886, + "loss": 0.0956, + "step": 1966 + }, + { + "epoch": 0.39, + "learning_rate": 0.00012466955990528378, + "loss": 0.0984, + "step": 1967 + }, + { + "epoch": 0.39, + "learning_rate": 0.00012424713583864694, + "loss": 0.0958, + "step": 1968 + }, + { + "epoch": 0.39, + "learning_rate": 0.0001238253270891218, + "loss": 0.0979, + "step": 1969 + }, + { + "epoch": 0.39, + "learning_rate": 0.00012340413434744484, + "loss": 0.0944, + "step": 1970 + }, + { + "epoch": 0.39, + "learning_rate": 0.00012298355830334346, + "loss": 0.0917, + "step": 1971 + }, + { + "epoch": 0.39, + "learning_rate": 0.0001225635996455355, + "loss": 0.0959, + "step": 1972 + }, + { + "epoch": 0.39, + "learning_rate": 0.0001221442590617274, + "loss": 0.0977, + "step": 1973 + }, + { + "epoch": 0.39, + "learning_rate": 0.0001217255372386139, + "loss": 0.0974, + "step": 1974 + }, + { + "epoch": 0.39, + "learning_rate": 0.00012130743486187623, + "loss": 0.0939, + "step": 1975 + }, + { + "epoch": 0.39, + "learning_rate": 0.00012088995261618107, + "loss": 0.0959, + "step": 1976 + }, + { + "epoch": 0.39, + "learning_rate": 0.00012047309118518019, + "loss": 0.0941, + "step": 1977 + }, + { + "epoch": 0.39, + "learning_rate": 0.00012005685125150795, + "loss": 0.0956, + "step": 1978 + }, + { + "epoch": 0.39, + "learning_rate": 0.00011964123349678174, + "loss": 0.0956, + "step": 1979 + }, + { + "epoch": 0.39, + "learning_rate": 0.00011922623860159948, + "loss": 0.0927, + "step": 1980 + }, + { + "epoch": 0.39, + "learning_rate": 0.00011881186724553966, + "loss": 0.0924, + "step": 1981 + }, + { + "epoch": 0.39, + "learning_rate": 0.00011839812010715911, + "loss": 0.0958, + "step": 1982 + }, + { + "epoch": 0.39, + "learning_rate": 0.00011798499786399303, + "loss": 0.0968, + "step": 1983 + }, + { + "epoch": 0.39, + "learning_rate": 0.00011757250119255281, + "loss": 0.0913, + "step": 1984 + }, + { + "epoch": 0.39, + "learning_rate": 0.00011716063076832595, + "loss": 0.0962, + "step": 1985 + }, + { + "epoch": 0.39, + "learning_rate": 0.00011674938726577388, + "loss": 0.0958, + "step": 1986 + }, + { + "epoch": 0.39, + "learning_rate": 0.00011633877135833198, + "loss": 0.0943, + "step": 1987 + }, + { + "epoch": 0.39, + "learning_rate": 0.00011592878371840732, + "loss": 0.0921, + "step": 1988 + }, + { + "epoch": 0.39, + "learning_rate": 0.00011551942501737877, + "loss": 0.0919, + "step": 1989 + }, + { + "epoch": 0.39, + "learning_rate": 0.00011511069592559459, + "loss": 0.0902, + "step": 1990 + }, + { + "epoch": 0.39, + "learning_rate": 0.00011470259711237285, + "loss": 0.0932, + "step": 1991 + }, + { + "epoch": 0.39, + "learning_rate": 0.0001142951292459985, + "loss": 0.0944, + "step": 1992 + }, + { + "epoch": 0.39, + "learning_rate": 0.00011388829299372411, + "loss": 0.0932, + "step": 1993 + }, + { + "epoch": 0.39, + "learning_rate": 0.00011348208902176749, + "loss": 0.0956, + "step": 1994 + }, + { + "epoch": 0.39, + "learning_rate": 0.00011307651799531144, + "loss": 0.0913, + "step": 1995 + }, + { + "epoch": 0.39, + "learning_rate": 0.00011267158057850174, + "loss": 0.0923, + "step": 1996 + }, + { + "epoch": 0.39, + "learning_rate": 0.0001122672774344472, + "loss": 0.0942, + "step": 1997 + }, + { + "epoch": 0.39, + "learning_rate": 0.00011186360922521743, + "loss": 0.0889, + "step": 1998 + }, + { + "epoch": 0.39, + "learning_rate": 0.00011146057661184273, + "loss": 0.0973, + "step": 1999 + }, + { + "epoch": 0.4, + "learning_rate": 0.00011105818025431219, + "loss": 0.0934, + "step": 2000 + }, + { + "epoch": 0.4, + "learning_rate": 0.0001106564208115734, + "loss": 0.0917, + "step": 2001 + }, + { + "epoch": 0.4, + "learning_rate": 0.00011025529894153053, + "loss": 0.0945, + "step": 2002 + }, + { + "epoch": 0.4, + "learning_rate": 0.00010985481530104413, + "loss": 0.0909, + "step": 2003 + }, + { + "epoch": 0.4, + "learning_rate": 0.00010945497054592917, + "loss": 0.0961, + "step": 2004 + }, + { + "epoch": 0.4, + "learning_rate": 0.0001090557653309549, + "loss": 0.0962, + "step": 2005 + }, + { + "epoch": 0.4, + "learning_rate": 0.00010865720030984266, + "loss": 0.0944, + "step": 2006 + }, + { + "epoch": 0.4, + "learning_rate": 0.0001082592761352662, + "loss": 0.0951, + "step": 2007 + }, + { + "epoch": 0.4, + "learning_rate": 0.00010786199345884923, + "loss": 0.0951, + "step": 2008 + }, + { + "epoch": 0.4, + "learning_rate": 0.00010746535293116505, + "loss": 0.095, + "step": 2009 + }, + { + "epoch": 0.4, + "learning_rate": 0.00010706935520173577, + "loss": 0.0922, + "step": 2010 + }, + { + "epoch": 0.4, + "learning_rate": 0.0001066740009190304, + "loss": 0.0924, + "step": 2011 + }, + { + "epoch": 0.4, + "learning_rate": 0.00010627929073046483, + "loss": 0.0977, + "step": 2012 + }, + { + "epoch": 0.4, + "learning_rate": 0.00010588522528239953, + "loss": 0.1008, + "step": 2013 + }, + { + "epoch": 0.4, + "learning_rate": 0.0001054918052201399, + "loss": 0.0913, + "step": 2014 + }, + { + "epoch": 0.4, + "learning_rate": 0.00010509903118793374, + "loss": 0.0953, + "step": 2015 + }, + { + "epoch": 0.4, + "learning_rate": 0.00010470690382897164, + "loss": 0.0917, + "step": 2016 + }, + { + "epoch": 0.4, + "learning_rate": 0.00010431542378538461, + "loss": 0.0956, + "step": 2017 + }, + { + "epoch": 0.4, + "learning_rate": 0.00010392459169824425, + "loss": 0.0923, + "step": 2018 + }, + { + "epoch": 0.4, + "learning_rate": 0.00010353440820756043, + "loss": 0.0959, + "step": 2019 + }, + { + "epoch": 0.4, + "learning_rate": 0.00010314487395228156, + "loss": 0.0939, + "step": 2020 + }, + { + "epoch": 0.4, + "learning_rate": 0.0001027559895702923, + "loss": 0.0965, + "step": 2021 + }, + { + "epoch": 0.4, + "learning_rate": 0.00010236775569841367, + "loss": 0.0904, + "step": 2022 + }, + { + "epoch": 0.4, + "learning_rate": 0.00010198017297240087, + "loss": 0.0909, + "step": 2023 + }, + { + "epoch": 0.4, + "learning_rate": 0.00010159324202694337, + "loss": 0.0994, + "step": 2024 + }, + { + "epoch": 0.4, + "learning_rate": 0.00010120696349566289, + "loss": 0.095, + "step": 2025 + }, + { + "epoch": 0.4, + "learning_rate": 0.00010082133801111293, + "loss": 0.095, + "step": 2026 + }, + { + "epoch": 0.4, + "learning_rate": 0.00010043636620477748, + "loss": 0.094, + "step": 2027 + }, + { + "epoch": 0.4, + "learning_rate": 0.00010005204870707046, + "loss": 0.0931, + "step": 2028 + }, + { + "epoch": 0.4, + "learning_rate": 9.966838614733382e-05, + "loss": 0.0968, + "step": 2029 + }, + { + "epoch": 0.4, + "learning_rate": 9.928537915383745e-05, + "loss": 0.0921, + "step": 2030 + }, + { + "epoch": 0.4, + "learning_rate": 9.890302835377735e-05, + "loss": 0.093, + "step": 2031 + }, + { + "epoch": 0.4, + "learning_rate": 9.852133437327538e-05, + "loss": 0.0956, + "step": 2032 + }, + { + "epoch": 0.4, + "learning_rate": 9.814029783737727e-05, + "loss": 0.0942, + "step": 2033 + }, + { + "epoch": 0.4, + "learning_rate": 9.775991937005274e-05, + "loss": 0.092, + "step": 2034 + }, + { + "epoch": 0.4, + "learning_rate": 9.738019959419331e-05, + "loss": 0.0926, + "step": 2035 + }, + { + "epoch": 0.4, + "learning_rate": 9.70011391316124e-05, + "loss": 0.095, + "step": 2036 + }, + { + "epoch": 0.4, + "learning_rate": 9.662273860304332e-05, + "loss": 0.0933, + "step": 2037 + }, + { + "epoch": 0.4, + "learning_rate": 9.624499862813907e-05, + "loss": 0.0916, + "step": 2038 + }, + { + "epoch": 0.4, + "learning_rate": 9.586791982547049e-05, + "loss": 0.0942, + "step": 2039 + }, + { + "epoch": 0.4, + "learning_rate": 9.549150281252633e-05, + "loss": 0.0911, + "step": 2040 + }, + { + "epoch": 0.4, + "learning_rate": 9.511574820571096e-05, + "loss": 0.0943, + "step": 2041 + }, + { + "epoch": 0.4, + "learning_rate": 9.474065662034465e-05, + "loss": 0.0916, + "step": 2042 + }, + { + "epoch": 0.4, + "learning_rate": 9.436622867066146e-05, + "loss": 0.0948, + "step": 2043 + }, + { + "epoch": 0.4, + "learning_rate": 9.39924649698088e-05, + "loss": 0.0916, + "step": 2044 + }, + { + "epoch": 0.4, + "learning_rate": 9.361936612984661e-05, + "loss": 0.0926, + "step": 2045 + }, + { + "epoch": 0.4, + "learning_rate": 9.324693276174567e-05, + "loss": 0.0981, + "step": 2046 + }, + { + "epoch": 0.4, + "learning_rate": 9.28751654753875e-05, + "loss": 0.0955, + "step": 2047 + }, + { + "epoch": 0.4, + "learning_rate": 9.250406487956226e-05, + "loss": 0.0964, + "step": 2048 + }, + { + "epoch": 0.4, + "learning_rate": 9.213363158196902e-05, + "loss": 0.0944, + "step": 2049 + }, + { + "epoch": 0.4, + "learning_rate": 9.17638661892135e-05, + "loss": 0.0948, + "step": 2050 + }, + { + "epoch": 0.41, + "learning_rate": 9.139476930680829e-05, + "loss": 0.0909, + "step": 2051 + }, + { + "epoch": 0.41, + "learning_rate": 9.102634153917061e-05, + "loss": 0.0941, + "step": 2052 + }, + { + "epoch": 0.41, + "learning_rate": 9.065858348962269e-05, + "loss": 0.0871, + "step": 2053 + }, + { + "epoch": 0.41, + "learning_rate": 9.029149576038925e-05, + "loss": 0.0952, + "step": 2054 + }, + { + "epoch": 0.41, + "learning_rate": 8.992507895259811e-05, + "loss": 0.0977, + "step": 2055 + }, + { + "epoch": 0.41, + "learning_rate": 8.955933366627778e-05, + "loss": 0.093, + "step": 2056 + }, + { + "epoch": 0.41, + "learning_rate": 8.919426050035756e-05, + "loss": 0.0951, + "step": 2057 + }, + { + "epoch": 0.41, + "learning_rate": 8.882986005266575e-05, + "loss": 0.0916, + "step": 2058 + }, + { + "epoch": 0.41, + "learning_rate": 8.846613291992961e-05, + "loss": 0.0915, + "step": 2059 + }, + { + "epoch": 0.41, + "learning_rate": 8.810307969777287e-05, + "loss": 0.0929, + "step": 2060 + }, + { + "epoch": 0.41, + "learning_rate": 8.774070098071668e-05, + "loss": 0.0931, + "step": 2061 + }, + { + "epoch": 0.41, + "learning_rate": 8.737899736217686e-05, + "loss": 0.0953, + "step": 2062 + }, + { + "epoch": 0.41, + "learning_rate": 8.701796943446444e-05, + "loss": 0.0962, + "step": 2063 + }, + { + "epoch": 0.41, + "learning_rate": 8.665761778878323e-05, + "loss": 0.0933, + "step": 2064 + }, + { + "epoch": 0.41, + "learning_rate": 8.62979430152303e-05, + "loss": 0.0923, + "step": 2065 + }, + { + "epoch": 0.41, + "learning_rate": 8.593894570279365e-05, + "loss": 0.0873, + "step": 2066 + }, + { + "epoch": 0.41, + "learning_rate": 8.558062643935244e-05, + "loss": 0.0951, + "step": 2067 + }, + { + "epoch": 0.41, + "learning_rate": 8.522298581167504e-05, + "loss": 0.0959, + "step": 2068 + }, + { + "epoch": 0.41, + "learning_rate": 8.486602440541897e-05, + "loss": 0.0928, + "step": 2069 + }, + { + "epoch": 0.41, + "learning_rate": 8.450974280512897e-05, + "loss": 0.0943, + "step": 2070 + }, + { + "epoch": 0.41, + "learning_rate": 8.415414159423706e-05, + "loss": 0.0926, + "step": 2071 + }, + { + "epoch": 0.41, + "learning_rate": 8.379922135506068e-05, + "loss": 0.0946, + "step": 2072 + }, + { + "epoch": 0.41, + "learning_rate": 8.344498266880246e-05, + "loss": 0.0925, + "step": 2073 + }, + { + "epoch": 0.41, + "learning_rate": 8.30914261155486e-05, + "loss": 0.0911, + "step": 2074 + }, + { + "epoch": 0.41, + "learning_rate": 8.273855227426874e-05, + "loss": 0.0905, + "step": 2075 + }, + { + "epoch": 0.41, + "learning_rate": 8.238636172281394e-05, + "loss": 0.0915, + "step": 2076 + }, + { + "epoch": 0.41, + "learning_rate": 8.203485503791708e-05, + "loss": 0.0934, + "step": 2077 + }, + { + "epoch": 0.41, + "learning_rate": 8.168403279519027e-05, + "loss": 0.0941, + "step": 2078 + }, + { + "epoch": 0.41, + "learning_rate": 8.133389556912563e-05, + "loss": 0.0926, + "step": 2079 + }, + { + "epoch": 0.41, + "learning_rate": 8.09844439330929e-05, + "loss": 0.0948, + "step": 2080 + }, + { + "epoch": 0.41, + "learning_rate": 8.063567845933972e-05, + "loss": 0.0922, + "step": 2081 + }, + { + "epoch": 0.41, + "learning_rate": 8.028759971898947e-05, + "loss": 0.0925, + "step": 2082 + }, + { + "epoch": 0.41, + "learning_rate": 7.994020828204157e-05, + "loss": 0.091, + "step": 2083 + }, + { + "epoch": 0.41, + "learning_rate": 7.959350471736937e-05, + "loss": 0.0964, + "step": 2084 + }, + { + "epoch": 0.41, + "learning_rate": 7.924748959272038e-05, + "loss": 0.0968, + "step": 2085 + }, + { + "epoch": 0.41, + "learning_rate": 7.890216347471407e-05, + "loss": 0.0887, + "step": 2086 + }, + { + "epoch": 0.41, + "learning_rate": 7.855752692884238e-05, + "loss": 0.0936, + "step": 2087 + }, + { + "epoch": 0.41, + "learning_rate": 7.821358051946731e-05, + "loss": 0.0928, + "step": 2088 + }, + { + "epoch": 0.41, + "learning_rate": 7.787032480982132e-05, + "loss": 0.0931, + "step": 2089 + }, + { + "epoch": 0.41, + "learning_rate": 7.752776036200531e-05, + "loss": 0.0943, + "step": 2090 + }, + { + "epoch": 0.41, + "learning_rate": 7.71858877369887e-05, + "loss": 0.0911, + "step": 2091 + }, + { + "epoch": 0.41, + "learning_rate": 7.684470749460743e-05, + "loss": 0.0931, + "step": 2092 + }, + { + "epoch": 0.41, + "learning_rate": 7.65042201935643e-05, + "loss": 0.0951, + "step": 2093 + }, + { + "epoch": 0.41, + "learning_rate": 7.616442639142674e-05, + "loss": 0.0947, + "step": 2094 + }, + { + "epoch": 0.41, + "learning_rate": 7.582532664462682e-05, + "loss": 0.0956, + "step": 2095 + }, + { + "epoch": 0.41, + "learning_rate": 7.54869215084602e-05, + "loss": 0.092, + "step": 2096 + }, + { + "epoch": 0.41, + "learning_rate": 7.514921153708476e-05, + "loss": 0.0933, + "step": 2097 + }, + { + "epoch": 0.41, + "learning_rate": 7.481219728352035e-05, + "loss": 0.0949, + "step": 2098 + }, + { + "epoch": 0.41, + "learning_rate": 7.447587929964717e-05, + "loss": 0.0939, + "step": 2099 + }, + { + "epoch": 0.41, + "learning_rate": 7.414025813620561e-05, + "loss": 0.0935, + "step": 2100 + }, + { + "epoch": 0.42, + "learning_rate": 7.380533434279457e-05, + "loss": 0.0912, + "step": 2101 + }, + { + "epoch": 0.42, + "learning_rate": 7.347110846787147e-05, + "loss": 0.0929, + "step": 2102 + }, + { + "epoch": 0.42, + "learning_rate": 7.31375810587503e-05, + "loss": 0.0925, + "step": 2103 + }, + { + "epoch": 0.42, + "learning_rate": 7.280475266160175e-05, + "loss": 0.0927, + "step": 2104 + }, + { + "epoch": 0.42, + "learning_rate": 7.247262382145142e-05, + "loss": 0.0921, + "step": 2105 + }, + { + "epoch": 0.42, + "learning_rate": 7.214119508217975e-05, + "loss": 0.0914, + "step": 2106 + }, + { + "epoch": 0.42, + "learning_rate": 7.181046698652038e-05, + "loss": 0.0916, + "step": 2107 + }, + { + "epoch": 0.42, + "learning_rate": 7.148044007605992e-05, + "loss": 0.0924, + "step": 2108 + }, + { + "epoch": 0.42, + "learning_rate": 7.115111489123637e-05, + "loss": 0.0972, + "step": 2109 + }, + { + "epoch": 0.42, + "learning_rate": 7.082249197133905e-05, + "loss": 0.0939, + "step": 2110 + }, + { + "epoch": 0.42, + "learning_rate": 7.049457185450692e-05, + "loss": 0.0944, + "step": 2111 + }, + { + "epoch": 0.42, + "learning_rate": 7.01673550777282e-05, + "loss": 0.0925, + "step": 2112 + }, + { + "epoch": 0.42, + "learning_rate": 6.984084217683922e-05, + "loss": 0.0899, + "step": 2113 + }, + { + "epoch": 0.42, + "learning_rate": 6.951503368652407e-05, + "loss": 0.0925, + "step": 2114 + }, + { + "epoch": 0.42, + "learning_rate": 6.918993014031277e-05, + "loss": 0.0932, + "step": 2115 + }, + { + "epoch": 0.42, + "learning_rate": 6.88655320705815e-05, + "loss": 0.089, + "step": 2116 + }, + { + "epoch": 0.42, + "learning_rate": 6.854184000855068e-05, + "loss": 0.094, + "step": 2117 + }, + { + "epoch": 0.42, + "learning_rate": 6.821885448428505e-05, + "loss": 0.0948, + "step": 2118 + }, + { + "epoch": 0.42, + "learning_rate": 6.789657602669196e-05, + "loss": 0.0939, + "step": 2119 + }, + { + "epoch": 0.42, + "learning_rate": 6.757500516352122e-05, + "loss": 0.096, + "step": 2120 + }, + { + "epoch": 0.42, + "learning_rate": 6.725414242136363e-05, + "loss": 0.0957, + "step": 2121 + }, + { + "epoch": 0.42, + "learning_rate": 6.693398832565073e-05, + "loss": 0.0957, + "step": 2122 + }, + { + "epoch": 0.42, + "learning_rate": 6.66145434006532e-05, + "loss": 0.0962, + "step": 2123 + }, + { + "epoch": 0.42, + "learning_rate": 6.629580816948088e-05, + "loss": 0.0953, + "step": 2124 + }, + { + "epoch": 0.42, + "learning_rate": 6.597778315408098e-05, + "loss": 0.0957, + "step": 2125 + }, + { + "epoch": 0.42, + "learning_rate": 6.566046887523808e-05, + "loss": 0.0962, + "step": 2126 + }, + { + "epoch": 0.42, + "learning_rate": 6.534386585257257e-05, + "loss": 0.0916, + "step": 2127 + }, + { + "epoch": 0.42, + "learning_rate": 6.502797460454041e-05, + "loss": 0.0927, + "step": 2128 + }, + { + "epoch": 0.42, + "learning_rate": 6.47127956484318e-05, + "loss": 0.0961, + "step": 2129 + }, + { + "epoch": 0.42, + "learning_rate": 6.439832950037039e-05, + "loss": 0.0924, + "step": 2130 + }, + { + "epoch": 0.42, + "learning_rate": 6.408457667531298e-05, + "loss": 0.0957, + "step": 2131 + }, + { + "epoch": 0.42, + "learning_rate": 6.377153768704785e-05, + "loss": 0.0947, + "step": 2132 + }, + { + "epoch": 0.42, + "learning_rate": 6.345921304819469e-05, + "loss": 0.0923, + "step": 2133 + }, + { + "epoch": 0.42, + "learning_rate": 6.314760327020297e-05, + "loss": 0.0949, + "step": 2134 + }, + { + "epoch": 0.42, + "learning_rate": 6.283670886335208e-05, + "loss": 0.0936, + "step": 2135 + }, + { + "epoch": 0.42, + "learning_rate": 6.252653033674927e-05, + "loss": 0.0904, + "step": 2136 + }, + { + "epoch": 0.42, + "learning_rate": 6.221706819833023e-05, + "loss": 0.0933, + "step": 2137 + }, + { + "epoch": 0.42, + "learning_rate": 6.190832295485687e-05, + "loss": 0.0912, + "step": 2138 + }, + { + "epoch": 0.42, + "learning_rate": 6.160029511191772e-05, + "loss": 0.0922, + "step": 2139 + }, + { + "epoch": 0.42, + "learning_rate": 6.129298517392601e-05, + "loss": 0.0948, + "step": 2140 + }, + { + "epoch": 0.42, + "learning_rate": 6.098639364411973e-05, + "loss": 0.0926, + "step": 2141 + }, + { + "epoch": 0.42, + "learning_rate": 6.068052102456012e-05, + "loss": 0.0968, + "step": 2142 + }, + { + "epoch": 0.42, + "learning_rate": 6.037536781613157e-05, + "loss": 0.0914, + "step": 2143 + }, + { + "epoch": 0.42, + "learning_rate": 6.007093451853996e-05, + "loss": 0.0927, + "step": 2144 + }, + { + "epoch": 0.42, + "learning_rate": 5.976722163031278e-05, + "loss": 0.0925, + "step": 2145 + }, + { + "epoch": 0.42, + "learning_rate": 5.9464229648797054e-05, + "loss": 0.0917, + "step": 2146 + }, + { + "epoch": 0.42, + "learning_rate": 5.916195907016003e-05, + "loss": 0.0972, + "step": 2147 + }, + { + "epoch": 0.42, + "learning_rate": 5.886041038938722e-05, + "loss": 0.095, + "step": 2148 + }, + { + "epoch": 0.42, + "learning_rate": 5.855958410028212e-05, + "loss": 0.0946, + "step": 2149 + }, + { + "epoch": 0.42, + "learning_rate": 5.825948069546516e-05, + "loss": 0.0935, + "step": 2150 + }, + { + "epoch": 0.42, + "learning_rate": 5.7960100666373194e-05, + "loss": 0.0907, + "step": 2151 + }, + { + "epoch": 0.43, + "learning_rate": 5.766144450325827e-05, + "loss": 0.0959, + "step": 2152 + }, + { + "epoch": 0.43, + "learning_rate": 5.736351269518725e-05, + "loss": 0.0916, + "step": 2153 + }, + { + "epoch": 0.43, + "learning_rate": 5.706630573004068e-05, + "loss": 0.0934, + "step": 2154 + }, + { + "epoch": 0.43, + "learning_rate": 5.676982409451237e-05, + "loss": 0.0954, + "step": 2155 + }, + { + "epoch": 0.43, + "learning_rate": 5.647406827410795e-05, + "loss": 0.0922, + "step": 2156 + }, + { + "epoch": 0.43, + "learning_rate": 5.617903875314495e-05, + "loss": 0.0916, + "step": 2157 + }, + { + "epoch": 0.43, + "learning_rate": 5.5884736014751135e-05, + "loss": 0.0953, + "step": 2158 + }, + { + "epoch": 0.43, + "learning_rate": 5.559116054086455e-05, + "loss": 0.0912, + "step": 2159 + }, + { + "epoch": 0.43, + "learning_rate": 5.52983128122318e-05, + "loss": 0.0956, + "step": 2160 + }, + { + "epoch": 0.43, + "learning_rate": 5.5006193308408284e-05, + "loss": 0.0956, + "step": 2161 + }, + { + "epoch": 0.43, + "learning_rate": 5.4714802507756515e-05, + "loss": 0.0909, + "step": 2162 + }, + { + "epoch": 0.43, + "learning_rate": 5.4424140887445684e-05, + "loss": 0.0943, + "step": 2163 + }, + { + "epoch": 0.43, + "learning_rate": 5.413420892345128e-05, + "loss": 0.0947, + "step": 2164 + }, + { + "epoch": 0.43, + "learning_rate": 5.3845007090553564e-05, + "loss": 0.0927, + "step": 2165 + }, + { + "epoch": 0.43, + "learning_rate": 5.3556535862337495e-05, + "loss": 0.0924, + "step": 2166 + }, + { + "epoch": 0.43, + "learning_rate": 5.32687957111912e-05, + "loss": 0.0946, + "step": 2167 + }, + { + "epoch": 0.43, + "learning_rate": 5.298178710830609e-05, + "loss": 0.0884, + "step": 2168 + }, + { + "epoch": 0.43, + "learning_rate": 5.269551052367516e-05, + "loss": 0.0914, + "step": 2169 + }, + { + "epoch": 0.43, + "learning_rate": 5.2409966426093244e-05, + "loss": 0.0907, + "step": 2170 + }, + { + "epoch": 0.43, + "learning_rate": 5.2125155283155034e-05, + "loss": 0.0929, + "step": 2171 + }, + { + "epoch": 0.43, + "learning_rate": 5.184107756125561e-05, + "loss": 0.096, + "step": 2172 + }, + { + "epoch": 0.43, + "learning_rate": 5.155773372558842e-05, + "loss": 0.0933, + "step": 2173 + }, + { + "epoch": 0.43, + "learning_rate": 5.1275124240145684e-05, + "loss": 0.0934, + "step": 2174 + }, + { + "epoch": 0.43, + "learning_rate": 5.0993249567716615e-05, + "loss": 0.0921, + "step": 2175 + }, + { + "epoch": 0.43, + "learning_rate": 5.071211016988753e-05, + "loss": 0.0934, + "step": 2176 + }, + { + "epoch": 0.43, + "learning_rate": 5.043170650704032e-05, + "loss": 0.0956, + "step": 2177 + }, + { + "epoch": 0.43, + "learning_rate": 5.015203903835247e-05, + "loss": 0.0972, + "step": 2178 + }, + { + "epoch": 0.43, + "learning_rate": 4.987310822179542e-05, + "loss": 0.088, + "step": 2179 + }, + { + "epoch": 0.43, + "learning_rate": 4.959491451413489e-05, + "loss": 0.0924, + "step": 2180 + }, + { + "epoch": 0.43, + "learning_rate": 4.931745837092888e-05, + "loss": 0.0903, + "step": 2181 + }, + { + "epoch": 0.43, + "learning_rate": 4.90407402465281e-05, + "loss": 0.093, + "step": 2182 + }, + { + "epoch": 0.43, + "learning_rate": 4.876476059407442e-05, + "loss": 0.095, + "step": 2183 + }, + { + "epoch": 0.43, + "learning_rate": 4.848951986550071e-05, + "loss": 0.0924, + "step": 2184 + }, + { + "epoch": 0.43, + "learning_rate": 4.821501851152943e-05, + "loss": 0.0927, + "step": 2185 + }, + { + "epoch": 0.43, + "learning_rate": 4.794125698167262e-05, + "loss": 0.095, + "step": 2186 + }, + { + "epoch": 0.43, + "learning_rate": 4.7668235724230566e-05, + "loss": 0.0906, + "step": 2187 + }, + { + "epoch": 0.43, + "learning_rate": 4.739595518629153e-05, + "loss": 0.0894, + "step": 2188 + }, + { + "epoch": 0.43, + "learning_rate": 4.7124415813730505e-05, + "loss": 0.0945, + "step": 2189 + }, + { + "epoch": 0.43, + "learning_rate": 4.6853618051209136e-05, + "loss": 0.0917, + "step": 2190 + }, + { + "epoch": 0.43, + "learning_rate": 4.658356234217437e-05, + "loss": 0.0936, + "step": 2191 + }, + { + "epoch": 0.43, + "learning_rate": 4.631424912885823e-05, + "loss": 0.0939, + "step": 2192 + }, + { + "epoch": 0.43, + "learning_rate": 4.6045678852276507e-05, + "loss": 0.0906, + "step": 2193 + }, + { + "epoch": 0.43, + "learning_rate": 4.5777851952228775e-05, + "loss": 0.0909, + "step": 2194 + }, + { + "epoch": 0.43, + "learning_rate": 4.551076886729705e-05, + "loss": 0.0905, + "step": 2195 + }, + { + "epoch": 0.43, + "learning_rate": 4.5244430034845464e-05, + "loss": 0.0885, + "step": 2196 + }, + { + "epoch": 0.43, + "learning_rate": 4.497883589101925e-05, + "loss": 0.0962, + "step": 2197 + }, + { + "epoch": 0.43, + "learning_rate": 4.4713986870744185e-05, + "loss": 0.0888, + "step": 2198 + }, + { + "epoch": 0.43, + "learning_rate": 4.444988340772588e-05, + "loss": 0.0936, + "step": 2199 + }, + { + "epoch": 0.43, + "learning_rate": 4.418652593444916e-05, + "loss": 0.09, + "step": 2200 + }, + { + "epoch": 0.43, + "learning_rate": 4.3923914882177116e-05, + "loss": 0.0944, + "step": 2201 + }, + { + "epoch": 0.43, + "learning_rate": 4.366205068095064e-05, + "loss": 0.09, + "step": 2202 + }, + { + "epoch": 0.44, + "learning_rate": 4.3400933759587424e-05, + "loss": 0.0896, + "step": 2203 + }, + { + "epoch": 0.44, + "learning_rate": 4.314056454568177e-05, + "loss": 0.0925, + "step": 2204 + }, + { + "epoch": 0.44, + "learning_rate": 4.288094346560312e-05, + "loss": 0.0927, + "step": 2205 + }, + { + "epoch": 0.44, + "learning_rate": 4.262207094449633e-05, + "loss": 0.0927, + "step": 2206 + }, + { + "epoch": 0.44, + "learning_rate": 4.2363947406279914e-05, + "loss": 0.0896, + "step": 2207 + }, + { + "epoch": 0.44, + "learning_rate": 4.2106573273646307e-05, + "loss": 0.0949, + "step": 2208 + }, + { + "epoch": 0.44, + "learning_rate": 4.184994896806049e-05, + "loss": 0.0955, + "step": 2209 + }, + { + "epoch": 0.44, + "learning_rate": 4.159407490975981e-05, + "loss": 0.0892, + "step": 2210 + }, + { + "epoch": 0.44, + "learning_rate": 4.1338951517752634e-05, + "loss": 0.0952, + "step": 2211 + }, + { + "epoch": 0.44, + "learning_rate": 4.108457920981851e-05, + "loss": 0.0938, + "step": 2212 + }, + { + "epoch": 0.44, + "learning_rate": 4.083095840250667e-05, + "loss": 0.095, + "step": 2213 + }, + { + "epoch": 0.44, + "learning_rate": 4.057808951113617e-05, + "loss": 0.0908, + "step": 2214 + }, + { + "epoch": 0.44, + "learning_rate": 4.032597294979423e-05, + "loss": 0.0952, + "step": 2215 + }, + { + "epoch": 0.44, + "learning_rate": 4.0074609131336425e-05, + "loss": 0.0904, + "step": 2216 + }, + { + "epoch": 0.44, + "learning_rate": 3.9823998467385656e-05, + "loss": 0.0909, + "step": 2217 + }, + { + "epoch": 0.44, + "learning_rate": 3.957414136833132e-05, + "loss": 0.0907, + "step": 2218 + }, + { + "epoch": 0.44, + "learning_rate": 3.9325038243329e-05, + "loss": 0.0951, + "step": 2219 + }, + { + "epoch": 0.44, + "learning_rate": 3.907668950029941e-05, + "loss": 0.0946, + "step": 2220 + }, + { + "epoch": 0.44, + "learning_rate": 3.8829095545928175e-05, + "loss": 0.0896, + "step": 2221 + }, + { + "epoch": 0.44, + "learning_rate": 3.8582256785664575e-05, + "loss": 0.0924, + "step": 2222 + }, + { + "epoch": 0.44, + "learning_rate": 3.83361736237216e-05, + "loss": 0.0892, + "step": 2223 + }, + { + "epoch": 0.44, + "learning_rate": 3.809084646307448e-05, + "loss": 0.0916, + "step": 2224 + }, + { + "epoch": 0.44, + "learning_rate": 3.7846275705460845e-05, + "loss": 0.0884, + "step": 2225 + }, + { + "epoch": 0.44, + "learning_rate": 3.760246175137938e-05, + "loss": 0.0906, + "step": 2226 + }, + { + "epoch": 0.44, + "learning_rate": 3.735940500008977e-05, + "loss": 0.0897, + "step": 2227 + }, + { + "epoch": 0.44, + "learning_rate": 3.711710584961125e-05, + "loss": 0.0916, + "step": 2228 + }, + { + "epoch": 0.44, + "learning_rate": 3.687556469672304e-05, + "loss": 0.0942, + "step": 2229 + }, + { + "epoch": 0.44, + "learning_rate": 3.6634781936962515e-05, + "loss": 0.0942, + "step": 2230 + }, + { + "epoch": 0.44, + "learning_rate": 3.639475796462577e-05, + "loss": 0.0931, + "step": 2231 + }, + { + "epoch": 0.44, + "learning_rate": 3.6155493172765506e-05, + "loss": 0.0939, + "step": 2232 + }, + { + "epoch": 0.44, + "learning_rate": 3.5916987953192094e-05, + "loss": 0.0902, + "step": 2233 + }, + { + "epoch": 0.44, + "learning_rate": 3.5679242696471435e-05, + "loss": 0.0955, + "step": 2234 + }, + { + "epoch": 0.44, + "learning_rate": 3.544225779192528e-05, + "loss": 0.0923, + "step": 2235 + }, + { + "epoch": 0.44, + "learning_rate": 3.520603362763014e-05, + "loss": 0.0936, + "step": 2236 + }, + { + "epoch": 0.44, + "learning_rate": 3.4970570590416806e-05, + "loss": 0.0901, + "step": 2237 + }, + { + "epoch": 0.44, + "learning_rate": 3.473586906586962e-05, + "loss": 0.0912, + "step": 2238 + }, + { + "epoch": 0.44, + "learning_rate": 3.450192943832597e-05, + "loss": 0.0923, + "step": 2239 + }, + { + "epoch": 0.44, + "learning_rate": 3.4268752090875544e-05, + "loss": 0.0923, + "step": 2240 + }, + { + "epoch": 0.44, + "learning_rate": 3.403633740535983e-05, + "loss": 0.0938, + "step": 2241 + }, + { + "epoch": 0.44, + "learning_rate": 3.3804685762371276e-05, + "loss": 0.0938, + "step": 2242 + }, + { + "epoch": 0.44, + "learning_rate": 3.3573797541253e-05, + "loss": 0.0925, + "step": 2243 + }, + { + "epoch": 0.44, + "learning_rate": 3.3343673120097674e-05, + "loss": 0.0894, + "step": 2244 + }, + { + "epoch": 0.44, + "learning_rate": 3.3114312875747624e-05, + "loss": 0.0945, + "step": 2245 + }, + { + "epoch": 0.44, + "learning_rate": 3.28857171837933e-05, + "loss": 0.0926, + "step": 2246 + }, + { + "epoch": 0.44, + "learning_rate": 3.265788641857364e-05, + "loss": 0.0946, + "step": 2247 + }, + { + "epoch": 0.44, + "learning_rate": 3.243082095317462e-05, + "loss": 0.0919, + "step": 2248 + }, + { + "epoch": 0.44, + "learning_rate": 3.220452115942907e-05, + "loss": 0.092, + "step": 2249 + }, + { + "epoch": 0.44, + "learning_rate": 3.197898740791616e-05, + "loss": 0.0892, + "step": 2250 + }, + { + "epoch": 0.44, + "learning_rate": 3.17542200679603e-05, + "loss": 0.0917, + "step": 2251 + }, + { + "epoch": 0.44, + "learning_rate": 3.1530219507631294e-05, + "loss": 0.0914, + "step": 2252 + }, + { + "epoch": 0.45, + "learning_rate": 3.130698609374283e-05, + "loss": 0.0928, + "step": 2253 + }, + { + "epoch": 0.45, + "learning_rate": 3.108452019185276e-05, + "loss": 0.0915, + "step": 2254 + }, + { + "epoch": 0.45, + "learning_rate": 3.0862822166261684e-05, + "loss": 0.0928, + "step": 2255 + }, + { + "epoch": 0.45, + "learning_rate": 3.064189238001325e-05, + "loss": 0.0909, + "step": 2256 + }, + { + "epoch": 0.45, + "learning_rate": 3.0421731194892498e-05, + "loss": 0.0912, + "step": 2257 + }, + { + "epoch": 0.45, + "learning_rate": 3.0202338971426435e-05, + "loss": 0.0896, + "step": 2258 + }, + { + "epoch": 0.45, + "learning_rate": 2.9983716068882338e-05, + "loss": 0.0934, + "step": 2259 + }, + { + "epoch": 0.45, + "learning_rate": 2.9765862845268e-05, + "loss": 0.0897, + "step": 2260 + }, + { + "epoch": 0.45, + "learning_rate": 2.9548779657330605e-05, + "loss": 0.0954, + "step": 2261 + }, + { + "epoch": 0.45, + "learning_rate": 2.9332466860556683e-05, + "loss": 0.0899, + "step": 2262 + }, + { + "epoch": 0.45, + "learning_rate": 2.9116924809170718e-05, + "loss": 0.0933, + "step": 2263 + }, + { + "epoch": 0.45, + "learning_rate": 2.8902153856135482e-05, + "loss": 0.0956, + "step": 2264 + }, + { + "epoch": 0.45, + "learning_rate": 2.868815435315092e-05, + "loss": 0.0963, + "step": 2265 + }, + { + "epoch": 0.45, + "learning_rate": 2.8474926650653487e-05, + "loss": 0.0899, + "step": 2266 + }, + { + "epoch": 0.45, + "learning_rate": 2.8262471097815934e-05, + "loss": 0.092, + "step": 2267 + }, + { + "epoch": 0.45, + "learning_rate": 2.8050788042546627e-05, + "loss": 0.0945, + "step": 2268 + }, + { + "epoch": 0.45, + "learning_rate": 2.783987783148878e-05, + "loss": 0.0897, + "step": 2269 + }, + { + "epoch": 0.45, + "learning_rate": 2.7629740810020176e-05, + "loss": 0.0941, + "step": 2270 + }, + { + "epoch": 0.45, + "learning_rate": 2.742037732225228e-05, + "loss": 0.0899, + "step": 2271 + }, + { + "epoch": 0.45, + "learning_rate": 2.7211787711030112e-05, + "loss": 0.0911, + "step": 2272 + }, + { + "epoch": 0.45, + "learning_rate": 2.7003972317931002e-05, + "loss": 0.0932, + "step": 2273 + }, + { + "epoch": 0.45, + "learning_rate": 2.6796931483265008e-05, + "loss": 0.0906, + "step": 2274 + }, + { + "epoch": 0.45, + "learning_rate": 2.6590665546073258e-05, + "loss": 0.0912, + "step": 2275 + }, + { + "epoch": 0.45, + "learning_rate": 2.6385174844128334e-05, + "loss": 0.093, + "step": 2276 + }, + { + "epoch": 0.45, + "learning_rate": 2.618045971393307e-05, + "loss": 0.0953, + "step": 2277 + }, + { + "epoch": 0.45, + "learning_rate": 2.5976520490720524e-05, + "loss": 0.0914, + "step": 2278 + }, + { + "epoch": 0.45, + "learning_rate": 2.5773357508452887e-05, + "loss": 0.0938, + "step": 2279 + }, + { + "epoch": 0.45, + "learning_rate": 2.5570971099821373e-05, + "loss": 0.095, + "step": 2280 + }, + { + "epoch": 0.45, + "learning_rate": 2.5369361596245365e-05, + "loss": 0.094, + "step": 2281 + }, + { + "epoch": 0.45, + "learning_rate": 2.5168529327872282e-05, + "loss": 0.0887, + "step": 2282 + }, + { + "epoch": 0.45, + "learning_rate": 2.4968474623576544e-05, + "loss": 0.0941, + "step": 2283 + }, + { + "epoch": 0.45, + "learning_rate": 2.4769197810959266e-05, + "loss": 0.0927, + "step": 2284 + }, + { + "epoch": 0.45, + "learning_rate": 2.4570699216347914e-05, + "loss": 0.092, + "step": 2285 + }, + { + "epoch": 0.45, + "learning_rate": 2.4372979164795306e-05, + "loss": 0.093, + "step": 2286 + }, + { + "epoch": 0.45, + "learning_rate": 2.4176037980079612e-05, + "loss": 0.0922, + "step": 2287 + }, + { + "epoch": 0.45, + "learning_rate": 2.397987598470336e-05, + "loss": 0.0915, + "step": 2288 + }, + { + "epoch": 0.45, + "learning_rate": 2.3784493499893367e-05, + "loss": 0.0964, + "step": 2289 + }, + { + "epoch": 0.45, + "learning_rate": 2.358989084559954e-05, + "loss": 0.0922, + "step": 2290 + }, + { + "epoch": 0.45, + "learning_rate": 2.339606834049518e-05, + "loss": 0.0901, + "step": 2291 + }, + { + "epoch": 0.45, + "learning_rate": 2.320302630197585e-05, + "loss": 0.088, + "step": 2292 + }, + { + "epoch": 0.45, + "learning_rate": 2.3010765046159065e-05, + "loss": 0.0905, + "step": 2293 + }, + { + "epoch": 0.45, + "learning_rate": 2.2819284887883764e-05, + "loss": 0.096, + "step": 2294 + }, + { + "epoch": 0.45, + "learning_rate": 2.2628586140709896e-05, + "loss": 0.0932, + "step": 2295 + }, + { + "epoch": 0.45, + "learning_rate": 2.243866911691761e-05, + "loss": 0.0913, + "step": 2296 + }, + { + "epoch": 0.45, + "learning_rate": 2.2249534127507187e-05, + "loss": 0.0922, + "step": 2297 + }, + { + "epoch": 0.45, + "learning_rate": 2.206118148219799e-05, + "loss": 0.0897, + "step": 2298 + }, + { + "epoch": 0.45, + "learning_rate": 2.187361148942857e-05, + "loss": 0.0908, + "step": 2299 + }, + { + "epoch": 0.45, + "learning_rate": 2.1686824456355558e-05, + "loss": 0.0896, + "step": 2300 + }, + { + "epoch": 0.45, + "learning_rate": 2.1500820688853563e-05, + "loss": 0.0918, + "step": 2301 + }, + { + "epoch": 0.45, + "learning_rate": 2.1315600491514486e-05, + "loss": 0.0889, + "step": 2302 + }, + { + "epoch": 0.45, + "learning_rate": 2.1131164167647265e-05, + "loss": 0.0883, + "step": 2303 + }, + { + "epoch": 0.46, + "learning_rate": 2.0947512019277025e-05, + "loss": 0.0923, + "step": 2304 + }, + { + "epoch": 0.46, + "learning_rate": 2.0764644347144813e-05, + "loss": 0.091, + "step": 2305 + }, + { + "epoch": 0.46, + "learning_rate": 2.0582561450707026e-05, + "loss": 0.0896, + "step": 2306 + }, + { + "epoch": 0.46, + "learning_rate": 2.040126362813505e-05, + "loss": 0.0944, + "step": 2307 + }, + { + "epoch": 0.46, + "learning_rate": 2.02207511763145e-05, + "loss": 0.0884, + "step": 2308 + }, + { + "epoch": 0.46, + "learning_rate": 2.0041024390845043e-05, + "loss": 0.0937, + "step": 2309 + }, + { + "epoch": 0.46, + "learning_rate": 1.9862083566039634e-05, + "loss": 0.0945, + "step": 2310 + }, + { + "epoch": 0.46, + "learning_rate": 1.968392899492438e-05, + "loss": 0.0933, + "step": 2311 + }, + { + "epoch": 0.46, + "learning_rate": 1.950656096923764e-05, + "loss": 0.089, + "step": 2312 + }, + { + "epoch": 0.46, + "learning_rate": 1.932997977942985e-05, + "loss": 0.0892, + "step": 2313 + }, + { + "epoch": 0.46, + "learning_rate": 1.9154185714662985e-05, + "loss": 0.0943, + "step": 2314 + }, + { + "epoch": 0.46, + "learning_rate": 1.8979179062809992e-05, + "loss": 0.0882, + "step": 2315 + }, + { + "epoch": 0.46, + "learning_rate": 1.8804960110454405e-05, + "loss": 0.0876, + "step": 2316 + }, + { + "epoch": 0.46, + "learning_rate": 1.8631529142890015e-05, + "loss": 0.091, + "step": 2317 + }, + { + "epoch": 0.46, + "learning_rate": 1.8458886444119803e-05, + "loss": 0.089, + "step": 2318 + }, + { + "epoch": 0.46, + "learning_rate": 1.828703229685641e-05, + "loss": 0.0902, + "step": 2319 + }, + { + "epoch": 0.46, + "learning_rate": 1.8115966982520937e-05, + "loss": 0.0936, + "step": 2320 + }, + { + "epoch": 0.46, + "learning_rate": 1.7945690781242752e-05, + "loss": 0.0928, + "step": 2321 + }, + { + "epoch": 0.46, + "learning_rate": 1.7776203971858972e-05, + "loss": 0.0893, + "step": 2322 + }, + { + "epoch": 0.46, + "learning_rate": 1.7607506831914145e-05, + "loss": 0.0924, + "step": 2323 + }, + { + "epoch": 0.46, + "learning_rate": 1.743959963765951e-05, + "loss": 0.0886, + "step": 2324 + }, + { + "epoch": 0.46, + "learning_rate": 1.7272482664053012e-05, + "loss": 0.0925, + "step": 2325 + }, + { + "epoch": 0.46, + "learning_rate": 1.7106156184758247e-05, + "loss": 0.0951, + "step": 2326 + }, + { + "epoch": 0.46, + "learning_rate": 1.6940620472144564e-05, + "loss": 0.0925, + "step": 2327 + }, + { + "epoch": 0.46, + "learning_rate": 1.6775875797286233e-05, + "loss": 0.0932, + "step": 2328 + }, + { + "epoch": 0.46, + "learning_rate": 1.6611922429962235e-05, + "loss": 0.093, + "step": 2329 + }, + { + "epoch": 0.46, + "learning_rate": 1.644876063865569e-05, + "loss": 0.0913, + "step": 2330 + }, + { + "epoch": 0.46, + "learning_rate": 1.6286390690553598e-05, + "loss": 0.0952, + "step": 2331 + }, + { + "epoch": 0.46, + "learning_rate": 1.6124812851546045e-05, + "loss": 0.0934, + "step": 2332 + }, + { + "epoch": 0.46, + "learning_rate": 1.596402738622621e-05, + "loss": 0.0937, + "step": 2333 + }, + { + "epoch": 0.46, + "learning_rate": 1.5804034557889536e-05, + "loss": 0.0938, + "step": 2334 + }, + { + "epoch": 0.46, + "learning_rate": 1.564483462853361e-05, + "loss": 0.0893, + "step": 2335 + }, + { + "epoch": 0.46, + "learning_rate": 1.5486427858857566e-05, + "loss": 0.0927, + "step": 2336 + }, + { + "epoch": 0.46, + "learning_rate": 1.5328814508261567e-05, + "loss": 0.0931, + "step": 2337 + }, + { + "epoch": 0.46, + "learning_rate": 1.5171994834846825e-05, + "loss": 0.0929, + "step": 2338 + }, + { + "epoch": 0.46, + "learning_rate": 1.5015969095414416e-05, + "loss": 0.0917, + "step": 2339 + }, + { + "epoch": 0.46, + "learning_rate": 1.4860737545465741e-05, + "loss": 0.092, + "step": 2340 + }, + { + "epoch": 0.46, + "learning_rate": 1.4706300439201347e-05, + "loss": 0.0907, + "step": 2341 + }, + { + "epoch": 0.46, + "learning_rate": 1.4552658029520993e-05, + "loss": 0.0921, + "step": 2342 + }, + { + "epoch": 0.46, + "learning_rate": 1.439981056802303e-05, + "loss": 0.0929, + "step": 2343 + }, + { + "epoch": 0.46, + "learning_rate": 1.4247758305004077e-05, + "loss": 0.091, + "step": 2344 + }, + { + "epoch": 0.46, + "learning_rate": 1.4096501489458403e-05, + "loss": 0.093, + "step": 2345 + }, + { + "epoch": 0.46, + "learning_rate": 1.394604036907804e-05, + "loss": 0.0936, + "step": 2346 + }, + { + "epoch": 0.46, + "learning_rate": 1.3796375190251564e-05, + "loss": 0.0951, + "step": 2347 + }, + { + "epoch": 0.46, + "learning_rate": 1.3647506198064596e-05, + "loss": 0.0901, + "step": 2348 + }, + { + "epoch": 0.46, + "learning_rate": 1.3499433636298631e-05, + "loss": 0.0898, + "step": 2349 + }, + { + "epoch": 0.46, + "learning_rate": 1.3352157747431093e-05, + "loss": 0.0928, + "step": 2350 + }, + { + "epoch": 0.46, + "learning_rate": 1.3205678772634789e-05, + "loss": 0.0932, + "step": 2351 + }, + { + "epoch": 0.46, + "learning_rate": 1.305999695177762e-05, + "loss": 0.0924, + "step": 2352 + }, + { + "epoch": 0.46, + "learning_rate": 1.2915112523421813e-05, + "loss": 0.0891, + "step": 2353 + }, + { + "epoch": 0.46, + "learning_rate": 1.2771025724824249e-05, + "loss": 0.0922, + "step": 2354 + }, + { + "epoch": 0.47, + "learning_rate": 1.2627736791935297e-05, + "loss": 0.09, + "step": 2355 + }, + { + "epoch": 0.47, + "learning_rate": 1.2485245959398927e-05, + "loss": 0.0922, + "step": 2356 + }, + { + "epoch": 0.47, + "learning_rate": 1.2343553460552105e-05, + "loss": 0.091, + "step": 2357 + }, + { + "epoch": 0.47, + "learning_rate": 1.220265952742461e-05, + "loss": 0.0905, + "step": 2358 + }, + { + "epoch": 0.47, + "learning_rate": 1.2062564390738328e-05, + "loss": 0.0937, + "step": 2359 + }, + { + "epoch": 0.47, + "learning_rate": 1.1923268279907307e-05, + "loss": 0.0903, + "step": 2360 + }, + { + "epoch": 0.47, + "learning_rate": 1.1784771423036799e-05, + "loss": 0.0905, + "step": 2361 + }, + { + "epoch": 0.47, + "learning_rate": 1.1647074046923666e-05, + "loss": 0.0919, + "step": 2362 + }, + { + "epoch": 0.47, + "learning_rate": 1.1510176377055203e-05, + "loss": 0.0943, + "step": 2363 + }, + { + "epoch": 0.47, + "learning_rate": 1.137407863760931e-05, + "loss": 0.0919, + "step": 2364 + }, + { + "epoch": 0.47, + "learning_rate": 1.1238781051453983e-05, + "loss": 0.0948, + "step": 2365 + }, + { + "epoch": 0.47, + "learning_rate": 1.1104283840146834e-05, + "loss": 0.0931, + "step": 2366 + }, + { + "epoch": 0.47, + "learning_rate": 1.0970587223934792e-05, + "loss": 0.0929, + "step": 2367 + }, + { + "epoch": 0.47, + "learning_rate": 1.0837691421753947e-05, + "loss": 0.0918, + "step": 2368 + }, + { + "epoch": 0.47, + "learning_rate": 1.0705596651228832e-05, + "loss": 0.0936, + "step": 2369 + }, + { + "epoch": 0.47, + "learning_rate": 1.0574303128672192e-05, + "loss": 0.0873, + "step": 2370 + }, + { + "epoch": 0.47, + "learning_rate": 1.044381106908493e-05, + "loss": 0.0916, + "step": 2371 + }, + { + "epoch": 0.47, + "learning_rate": 1.0314120686155281e-05, + "loss": 0.0905, + "step": 2372 + }, + { + "epoch": 0.47, + "learning_rate": 1.018523219225881e-05, + "loss": 0.0935, + "step": 2373 + }, + { + "epoch": 0.47, + "learning_rate": 1.0057145798457844e-05, + "loss": 0.0903, + "step": 2374 + }, + { + "epoch": 0.47, + "learning_rate": 9.929861714501386e-06, + "loss": 0.0932, + "step": 2375 + }, + { + "epoch": 0.47, + "learning_rate": 9.80338014882437e-06, + "loss": 0.09, + "step": 2376 + }, + { + "epoch": 0.47, + "learning_rate": 9.677701308547892e-06, + "loss": 0.0927, + "step": 2377 + }, + { + "epoch": 0.47, + "learning_rate": 9.552825399478105e-06, + "loss": 0.0904, + "step": 2378 + }, + { + "epoch": 0.47, + "learning_rate": 9.428752626106762e-06, + "loss": 0.0911, + "step": 2379 + }, + { + "epoch": 0.47, + "learning_rate": 9.305483191610065e-06, + "loss": 0.088, + "step": 2380 + }, + { + "epoch": 0.47, + "learning_rate": 9.183017297849039e-06, + "loss": 0.094, + "step": 2381 + }, + { + "epoch": 0.47, + "learning_rate": 9.061355145368489e-06, + "loss": 0.0954, + "step": 2382 + }, + { + "epoch": 0.47, + "learning_rate": 8.94049693339738e-06, + "loss": 0.0942, + "step": 2383 + }, + { + "epoch": 0.47, + "learning_rate": 8.82044285984801e-06, + "loss": 0.0939, + "step": 2384 + }, + { + "epoch": 0.47, + "learning_rate": 8.701193121315897e-06, + "loss": 0.0918, + "step": 2385 + }, + { + "epoch": 0.47, + "learning_rate": 8.582747913079447e-06, + "loss": 0.0908, + "step": 2386 + }, + { + "epoch": 0.47, + "learning_rate": 8.46510742909945e-06, + "loss": 0.0917, + "step": 2387 + }, + { + "epoch": 0.47, + "learning_rate": 8.348271862019086e-06, + "loss": 0.091, + "step": 2388 + }, + { + "epoch": 0.47, + "learning_rate": 8.232241403163366e-06, + "loss": 0.0892, + "step": 2389 + }, + { + "epoch": 0.47, + "learning_rate": 8.11701624253891e-06, + "loss": 0.0941, + "step": 2390 + }, + { + "epoch": 0.47, + "learning_rate": 8.00259656883362e-06, + "loss": 0.0913, + "step": 2391 + }, + { + "epoch": 0.47, + "learning_rate": 7.88898256941628e-06, + "loss": 0.0965, + "step": 2392 + }, + { + "epoch": 0.47, + "learning_rate": 7.776174430336458e-06, + "loss": 0.0921, + "step": 2393 + }, + { + "epoch": 0.47, + "learning_rate": 7.664172336323993e-06, + "loss": 0.0942, + "step": 2394 + }, + { + "epoch": 0.47, + "learning_rate": 7.552976470788897e-06, + "loss": 0.0939, + "step": 2395 + }, + { + "epoch": 0.47, + "learning_rate": 7.442587015820734e-06, + "loss": 0.0951, + "step": 2396 + }, + { + "epoch": 0.47, + "learning_rate": 7.333004152188738e-06, + "loss": 0.0917, + "step": 2397 + }, + { + "epoch": 0.47, + "learning_rate": 7.224228059341087e-06, + "loss": 0.0905, + "step": 2398 + }, + { + "epoch": 0.47, + "learning_rate": 7.116258915405072e-06, + "loss": 0.0903, + "step": 2399 + }, + { + "epoch": 0.47, + "learning_rate": 7.009096897186318e-06, + "loss": 0.0872, + "step": 2400 + }, + { + "epoch": 0.47, + "learning_rate": 6.902742180168953e-06, + "loss": 0.0882, + "step": 2401 + }, + { + "epoch": 0.47, + "learning_rate": 6.797194938514939e-06, + "loss": 0.0922, + "step": 2402 + }, + { + "epoch": 0.47, + "learning_rate": 6.692455345064019e-06, + "loss": 0.0931, + "step": 2403 + }, + { + "epoch": 0.47, + "learning_rate": 6.588523571333327e-06, + "loss": 0.093, + "step": 2404 + }, + { + "epoch": 0.48, + "learning_rate": 6.485399787517165e-06, + "loss": 0.0922, + "step": 2405 + }, + { + "epoch": 0.48, + "learning_rate": 6.3830841624867296e-06, + "loss": 0.0931, + "step": 2406 + }, + { + "epoch": 0.48, + "learning_rate": 6.281576863789828e-06, + "loss": 0.0895, + "step": 2407 + }, + { + "epoch": 0.48, + "learning_rate": 6.180878057650552e-06, + "loss": 0.0909, + "step": 2408 + }, + { + "epoch": 0.48, + "learning_rate": 6.0809879089689376e-06, + "loss": 0.093, + "step": 2409 + }, + { + "epoch": 0.48, + "learning_rate": 5.9819065813209724e-06, + "loss": 0.0904, + "step": 2410 + }, + { + "epoch": 0.48, + "learning_rate": 5.883634236958091e-06, + "loss": 0.0919, + "step": 2411 + }, + { + "epoch": 0.48, + "learning_rate": 5.786171036806953e-06, + "loss": 0.0945, + "step": 2412 + }, + { + "epoch": 0.48, + "learning_rate": 5.689517140469169e-06, + "loss": 0.0924, + "step": 2413 + }, + { + "epoch": 0.48, + "learning_rate": 5.593672706221131e-06, + "loss": 0.0914, + "step": 2414 + }, + { + "epoch": 0.48, + "learning_rate": 5.498637891013625e-06, + "loss": 0.0918, + "step": 2415 + }, + { + "epoch": 0.48, + "learning_rate": 5.404412850471719e-06, + "loss": 0.0937, + "step": 2416 + }, + { + "epoch": 0.48, + "learning_rate": 5.310997738894319e-06, + "loss": 0.0916, + "step": 2417 + }, + { + "epoch": 0.48, + "learning_rate": 5.218392709254171e-06, + "loss": 0.0878, + "step": 2418 + }, + { + "epoch": 0.48, + "learning_rate": 5.126597913197362e-06, + "loss": 0.0889, + "step": 2419 + }, + { + "epoch": 0.48, + "learning_rate": 5.035613501043146e-06, + "loss": 0.0897, + "step": 2420 + }, + { + "epoch": 0.48, + "learning_rate": 4.945439621783842e-06, + "loss": 0.0944, + "step": 2421 + }, + { + "epoch": 0.48, + "learning_rate": 4.856076423084332e-06, + "loss": 0.0947, + "step": 2422 + }, + { + "epoch": 0.48, + "learning_rate": 4.7675240512820575e-06, + "loss": 0.0936, + "step": 2423 + }, + { + "epoch": 0.48, + "learning_rate": 4.679782651386744e-06, + "loss": 0.0924, + "step": 2424 + }, + { + "epoch": 0.48, + "learning_rate": 4.5928523670799025e-06, + "loss": 0.0967, + "step": 2425 + }, + { + "epoch": 0.48, + "learning_rate": 4.506733340714997e-06, + "loss": 0.093, + "step": 2426 + }, + { + "epoch": 0.48, + "learning_rate": 4.4214257133168845e-06, + "loss": 0.0883, + "step": 2427 + }, + { + "epoch": 0.48, + "learning_rate": 4.33692962458182e-06, + "loss": 0.0934, + "step": 2428 + }, + { + "epoch": 0.48, + "learning_rate": 4.253245212877011e-06, + "loss": 0.0907, + "step": 2429 + }, + { + "epoch": 0.48, + "learning_rate": 4.170372615240503e-06, + "loss": 0.0938, + "step": 2430 + }, + { + "epoch": 0.48, + "learning_rate": 4.08831196738102e-06, + "loss": 0.0884, + "step": 2431 + }, + { + "epoch": 0.48, + "learning_rate": 4.007063403677624e-06, + "loss": 0.0898, + "step": 2432 + }, + { + "epoch": 0.48, + "learning_rate": 3.926627057179555e-06, + "loss": 0.089, + "step": 2433 + }, + { + "epoch": 0.48, + "learning_rate": 3.847003059606002e-06, + "loss": 0.0938, + "step": 2434 + }, + { + "epoch": 0.48, + "learning_rate": 3.7681915413458888e-06, + "loss": 0.0913, + "step": 2435 + }, + { + "epoch": 0.48, + "learning_rate": 3.6901926314575895e-06, + "loss": 0.0937, + "step": 2436 + }, + { + "epoch": 0.48, + "learning_rate": 3.6130064576689324e-06, + "loss": 0.0926, + "step": 2437 + }, + { + "epoch": 0.48, + "learning_rate": 3.5366331463767e-06, + "loss": 0.0922, + "step": 2438 + }, + { + "epoch": 0.48, + "learning_rate": 3.4610728226465717e-06, + "loss": 0.0877, + "step": 2439 + }, + { + "epoch": 0.48, + "learning_rate": 3.3863256102130703e-06, + "loss": 0.0916, + "step": 2440 + }, + { + "epoch": 0.48, + "learning_rate": 3.312391631479006e-06, + "loss": 0.0915, + "step": 2441 + }, + { + "epoch": 0.48, + "learning_rate": 3.2392710075155873e-06, + "loss": 0.0911, + "step": 2442 + }, + { + "epoch": 0.48, + "learning_rate": 3.1669638580620887e-06, + "loss": 0.0911, + "step": 2443 + }, + { + "epoch": 0.48, + "learning_rate": 3.0954703015256826e-06, + "loss": 0.0909, + "step": 2444 + }, + { + "epoch": 0.48, + "learning_rate": 3.0247904549811633e-06, + "loss": 0.0928, + "step": 2445 + }, + { + "epoch": 0.48, + "learning_rate": 2.954924434170891e-06, + "loss": 0.0897, + "step": 2446 + }, + { + "epoch": 0.48, + "learning_rate": 2.885872353504515e-06, + "loss": 0.09, + "step": 2447 + }, + { + "epoch": 0.48, + "learning_rate": 2.8176343260589155e-06, + "loss": 0.0939, + "step": 2448 + }, + { + "epoch": 0.48, + "learning_rate": 2.7502104635776514e-06, + "loss": 0.0898, + "step": 2449 + }, + { + "epoch": 0.48, + "learning_rate": 2.6836008764714037e-06, + "loss": 0.0907, + "step": 2450 + }, + { + "epoch": 0.48, + "learning_rate": 2.6178056738170864e-06, + "loss": 0.0928, + "step": 2451 + }, + { + "epoch": 0.48, + "learning_rate": 2.5528249633582356e-06, + "loss": 0.0917, + "step": 2452 + }, + { + "epoch": 0.48, + "learning_rate": 2.4886588515045105e-06, + "loss": 0.0885, + "step": 2453 + }, + { + "epoch": 0.48, + "learning_rate": 2.425307443331637e-06, + "loss": 0.088, + "step": 2454 + }, + { + "epoch": 0.48, + "learning_rate": 2.362770842581241e-06, + "loss": 0.0879, + "step": 2455 + }, + { + "epoch": 0.49, + "learning_rate": 2.301049151660628e-06, + "loss": 0.0942, + "step": 2456 + }, + { + "epoch": 0.49, + "learning_rate": 2.2401424716426146e-06, + "loss": 0.0945, + "step": 2457 + }, + { + "epoch": 0.49, + "learning_rate": 2.1800509022654733e-06, + "loss": 0.0928, + "step": 2458 + }, + { + "epoch": 0.49, + "learning_rate": 2.120774541932602e-06, + "loss": 0.0923, + "step": 2459 + }, + { + "epoch": 0.49, + "learning_rate": 2.062313487712464e-06, + "loss": 0.0955, + "step": 2460 + }, + { + "epoch": 0.49, + "learning_rate": 2.004667835338425e-06, + "loss": 0.0909, + "step": 2461 + }, + { + "epoch": 0.49, + "learning_rate": 1.947837679208642e-06, + "loss": 0.0935, + "step": 2462 + }, + { + "epoch": 0.49, + "learning_rate": 1.891823112385782e-06, + "loss": 0.0877, + "step": 2463 + }, + { + "epoch": 0.49, + "learning_rate": 1.836624226596917e-06, + "loss": 0.0918, + "step": 2464 + }, + { + "epoch": 0.49, + "learning_rate": 1.782241112233407e-06, + "loss": 0.0873, + "step": 2465 + }, + { + "epoch": 0.49, + "learning_rate": 1.7286738583507933e-06, + "loss": 0.0941, + "step": 2466 + }, + { + "epoch": 0.49, + "learning_rate": 1.6759225526685184e-06, + "loss": 0.0916, + "step": 2467 + }, + { + "epoch": 0.49, + "learning_rate": 1.623987281569983e-06, + "loss": 0.092, + "step": 2468 + }, + { + "epoch": 0.49, + "learning_rate": 1.5728681301021564e-06, + "loss": 0.0901, + "step": 2469 + }, + { + "epoch": 0.49, + "learning_rate": 1.522565181975577e-06, + "loss": 0.0921, + "step": 2470 + }, + { + "epoch": 0.49, + "learning_rate": 1.4730785195643527e-06, + "loss": 0.0886, + "step": 2471 + }, + { + "epoch": 0.49, + "learning_rate": 1.4244082239056044e-06, + "loss": 0.0914, + "step": 2472 + }, + { + "epoch": 0.49, + "learning_rate": 1.376554374699912e-06, + "loss": 0.0903, + "step": 2473 + }, + { + "epoch": 0.49, + "learning_rate": 1.3295170503106467e-06, + "loss": 0.0914, + "step": 2474 + }, + { + "epoch": 0.49, + "learning_rate": 1.283296327764194e-06, + "loss": 0.0909, + "step": 2475 + }, + { + "epoch": 0.49, + "learning_rate": 1.2378922827496197e-06, + "loss": 0.0892, + "step": 2476 + }, + { + "epoch": 0.49, + "learning_rate": 1.193304989618782e-06, + "loss": 0.0921, + "step": 2477 + }, + { + "epoch": 0.49, + "learning_rate": 1.149534521385831e-06, + "loss": 0.095, + "step": 2478 + }, + { + "epoch": 0.49, + "learning_rate": 1.1065809497275426e-06, + "loss": 0.0876, + "step": 2479 + }, + { + "epoch": 0.49, + "learning_rate": 1.0644443449828179e-06, + "loss": 0.0873, + "step": 2480 + }, + { + "epoch": 0.49, + "learning_rate": 1.0231247761528506e-06, + "loss": 0.094, + "step": 2481 + }, + { + "epoch": 0.49, + "learning_rate": 9.826223109007937e-07, + "loss": 0.0936, + "step": 2482 + }, + { + "epoch": 0.49, + "learning_rate": 9.429370155517592e-07, + "loss": 0.0922, + "step": 2483 + }, + { + "epoch": 0.49, + "learning_rate": 9.040689550927628e-07, + "loss": 0.0946, + "step": 2484 + }, + { + "epoch": 0.49, + "learning_rate": 8.660181931725575e-07, + "loss": 0.0915, + "step": 2485 + }, + { + "epoch": 0.49, + "learning_rate": 8.287847921013559e-07, + "loss": 0.0899, + "step": 2486 + }, + { + "epoch": 0.49, + "learning_rate": 7.923688128511075e-07, + "loss": 0.0929, + "step": 2487 + }, + { + "epoch": 0.49, + "learning_rate": 7.567703150550553e-07, + "loss": 0.0892, + "step": 2488 + }, + { + "epoch": 0.49, + "learning_rate": 7.219893570077907e-07, + "loss": 0.0919, + "step": 2489 + }, + { + "epoch": 0.49, + "learning_rate": 6.880259956651424e-07, + "loss": 0.0932, + "step": 2490 + }, + { + "epoch": 0.49, + "learning_rate": 6.548802866441217e-07, + "loss": 0.0946, + "step": 2491 + }, + { + "epoch": 0.49, + "learning_rate": 6.225522842226994e-07, + "loss": 0.0942, + "step": 2492 + }, + { + "epoch": 0.49, + "learning_rate": 5.910420413399176e-07, + "loss": 0.0889, + "step": 2493 + }, + { + "epoch": 0.49, + "learning_rate": 5.603496095956118e-07, + "loss": 0.0896, + "step": 2494 + }, + { + "epoch": 0.49, + "learning_rate": 5.304750392504109e-07, + "loss": 0.094, + "step": 2495 + }, + { + "epoch": 0.49, + "learning_rate": 5.014183792256266e-07, + "loss": 0.0916, + "step": 2496 + }, + { + "epoch": 0.49, + "learning_rate": 4.7317967710325263e-07, + "loss": 0.0953, + "step": 2497 + }, + { + "epoch": 0.49, + "learning_rate": 4.457589791257988e-07, + "loss": 0.0942, + "step": 2498 + }, + { + "epoch": 0.49, + "learning_rate": 4.1915633019629086e-07, + "loss": 0.0901, + "step": 2499 + }, + { + "epoch": 0.49, + "learning_rate": 3.9337177387804844e-07, + "loss": 0.0971, + "step": 2500 + }, + { + "epoch": 0.49, + "learning_rate": 3.684053523947406e-07, + "loss": 0.0923, + "step": 2501 + }, + { + "epoch": 0.49, + "learning_rate": 3.442571066304412e-07, + "loss": 0.0937, + "step": 2502 + }, + { + "epoch": 0.49, + "learning_rate": 3.2092707612924043e-07, + "loss": 0.0903, + "step": 2503 + }, + { + "epoch": 0.49, + "learning_rate": 2.984152990954114e-07, + "loss": 0.0913, + "step": 2504 + }, + { + "epoch": 0.49, + "learning_rate": 2.767218123933546e-07, + "loss": 0.0923, + "step": 2505 + }, + { + "epoch": 0.5, + "learning_rate": 2.558466515473201e-07, + "loss": 0.0907, + "step": 2506 + }, + { + "epoch": 0.5, + "learning_rate": 2.3578985074163005e-07, + "loss": 0.0925, + "step": 2507 + }, + { + "epoch": 0.5, + "learning_rate": 2.1655144282051177e-07, + "loss": 0.0942, + "step": 2508 + }, + { + "epoch": 0.5, + "learning_rate": 1.9813145928793131e-07, + "loss": 0.0897, + "step": 2509 + }, + { + "epoch": 0.5, + "learning_rate": 1.805299303077046e-07, + "loss": 0.0913, + "step": 2510 + }, + { + "epoch": 0.5, + "learning_rate": 1.6374688470327525e-07, + "loss": 0.0934, + "step": 2511 + }, + { + "epoch": 0.5, + "learning_rate": 1.477823499579367e-07, + "loss": 0.0926, + "step": 2512 + }, + { + "epoch": 0.5, + "learning_rate": 1.3263635221455461e-07, + "loss": 0.0949, + "step": 2513 + }, + { + "epoch": 0.5, + "learning_rate": 1.1830891627551133e-07, + "loss": 0.09, + "step": 2514 + }, + { + "epoch": 0.5, + "learning_rate": 1.0480006560281696e-07, + "loss": 0.0919, + "step": 2515 + }, + { + "epoch": 0.5, + "learning_rate": 9.210982231805387e-08, + "loss": 0.0937, + "step": 2516 + }, + { + "epoch": 0.5, + "learning_rate": 8.023820720221009e-08, + "loss": 0.0914, + "step": 2517 + }, + { + "epoch": 0.5, + "learning_rate": 6.918523969573486e-08, + "loss": 0.0922, + "step": 2518 + }, + { + "epoch": 0.5, + "learning_rate": 5.895093789848316e-08, + "loss": 0.0971, + "step": 2519 + }, + { + "epoch": 0.5, + "learning_rate": 4.9535318569771113e-08, + "loss": 0.0928, + "step": 2520 + }, + { + "epoch": 0.5, + "learning_rate": 4.0938397128154057e-08, + "loss": 0.0913, + "step": 2521 + }, + { + "epoch": 0.5, + "learning_rate": 3.316018765170403e-08, + "loss": 0.0922, + "step": 2522 + }, + { + "epoch": 0.5, + "learning_rate": 2.6200702877510197e-08, + "loss": 0.0905, + "step": 2523 + }, + { + "epoch": 0.5, + "learning_rate": 2.0059954202289455e-08, + "loss": 0.0912, + "step": 2524 + }, + { + "epoch": 0.5, + "learning_rate": 1.473795168183134e-08, + "loss": 0.0958, + "step": 2525 + }, + { + "epoch": 0.5, + "learning_rate": 1.0234704031220066e-08, + "loss": 0.0857, + "step": 2526 + }, + { + "epoch": 0.5, + "learning_rate": 6.5502186247234914e-09, + "loss": 0.0935, + "step": 2527 + }, + { + "epoch": 0.5, + "learning_rate": 3.68450149601518e-09, + "loss": 0.0893, + "step": 2528 + }, + { + "epoch": 0.5, + "learning_rate": 1.637557337785811e-09, + "loss": 0.0922, + "step": 2529 + }, + { + "epoch": 0.5, + "learning_rate": 4.093895020207405e-10, + "loss": 0.0912, + "step": 2530 + }, + { + "epoch": 0.5, + "learning_rate": 0.0, + "loss": 0.0933, + "step": 2531 + }, + { + "epoch": 0.5, + "step": 2531, + "total_flos": 503332674961408.0, + "train_loss": 0.13915327479838382, + "train_runtime": 34071.0421, + "train_samples_per_second": 9.51, + "train_steps_per_second": 0.074 + } + ], + "max_steps": 2531, + "num_train_epochs": 1, + "total_flos": 503332674961408.0, + "trial_name": null, + "trial_params": null +}