diff --git "a/crimeandpunishment_llama3/training_graph.json" "b/crimeandpunishment_llama3/training_graph.json" new file mode 100644--- /dev/null +++ "b/crimeandpunishment_llama3/training_graph.json" @@ -0,0 +1,19778 @@ +[ + { + "current_steps": 0, + "loss": 2.9411, + "learning_rate": 1e-08, + "epoch": 0.0015174506828528073 + }, + { + "current_steps": 1, + "loss": 2.8545, + "learning_rate": 2e-08, + "epoch": 0.0030349013657056147 + }, + { + "current_steps": 2, + "loss": 2.8173, + "learning_rate": 3e-08, + "epoch": 0.004552352048558422 + }, + { + "current_steps": 3, + "loss": 2.9607, + "learning_rate": 4e-08, + "epoch": 0.006069802731411229 + }, + { + "current_steps": 4, + "loss": 2.9681, + "learning_rate": 5e-08, + "epoch": 0.007587253414264037 + }, + { + "current_steps": 5, + "loss": 2.8543, + "learning_rate": 6e-08, + "epoch": 0.009104704097116844 + }, + { + "current_steps": 6, + "loss": 2.4343, + "learning_rate": 7e-08, + "epoch": 0.010622154779969651 + }, + { + "current_steps": 7, + "loss": 3.1157, + "learning_rate": 8e-08, + "epoch": 0.012139605462822459 + }, + { + "current_steps": 8, + "loss": 2.7941, + "learning_rate": 9e-08, + "epoch": 0.013657056145675266 + }, + { + "current_steps": 9, + "loss": 3.2049, + "learning_rate": 1e-07, + "epoch": 0.015174506828528073 + }, + { + "current_steps": 10, + "loss": 2.9544, + "learning_rate": 1.0999999999999999e-07, + "epoch": 0.01669195751138088 + }, + { + "current_steps": 11, + "loss": 3.0743, + "learning_rate": 1.2e-07, + "epoch": 0.018209408194233688 + }, + { + "current_steps": 12, + "loss": 3.143, + "learning_rate": 1.3e-07, + "epoch": 0.019726858877086494 + }, + { + "current_steps": 13, + "loss": 3.1292, + "learning_rate": 1.4e-07, + "epoch": 0.021244309559939303 + }, + { + "current_steps": 14, + "loss": 2.9548, + "learning_rate": 1.5e-07, + "epoch": 0.02276176024279211 + }, + { + "current_steps": 15, + "loss": 3.085, + "learning_rate": 1.6e-07, + "epoch": 0.024279210925644917 + }, + { + "current_steps": 16, + "loss": 2.9782, + "learning_rate": 1.7000000000000001e-07, + "epoch": 0.025796661608497723 + }, + { + "current_steps": 17, + "loss": 3.1923, + "learning_rate": 1.8e-07, + "epoch": 0.027314112291350532 + }, + { + "current_steps": 18, + "loss": 2.9306, + "learning_rate": 1.8999999999999998e-07, + "epoch": 0.028831562974203338 + }, + { + "current_steps": 19, + "loss": 2.6943, + "learning_rate": 2e-07, + "epoch": 0.030349013657056147 + }, + { + "current_steps": 20, + "loss": 3.1413, + "learning_rate": 2.0999999999999997e-07, + "epoch": 0.03186646433990895 + }, + { + "current_steps": 21, + "loss": 2.9483, + "learning_rate": 2.1999999999999998e-07, + "epoch": 0.03338391502276176 + }, + { + "current_steps": 22, + "loss": 2.9394, + "learning_rate": 2.3e-07, + "epoch": 0.03490136570561457 + }, + { + "current_steps": 23, + "loss": 3.0488, + "learning_rate": 2.4e-07, + "epoch": 0.036418816388467376 + }, + { + "current_steps": 24, + "loss": 2.889, + "learning_rate": 2.5e-07, + "epoch": 0.03793626707132018 + }, + { + "current_steps": 25, + "loss": 3.0922, + "learning_rate": 2.6e-07, + "epoch": 0.03945371775417299 + }, + { + "current_steps": 26, + "loss": 3.0159, + "learning_rate": 2.7e-07, + "epoch": 0.0409711684370258 + }, + { + "current_steps": 27, + "loss": 2.8798, + "learning_rate": 2.8e-07, + "epoch": 0.042488619119878605 + }, + { + "current_steps": 28, + "loss": 2.9432, + "learning_rate": 2.9e-07, + "epoch": 0.04400606980273141 + }, + { + "current_steps": 29, + "loss": 2.9249, + "learning_rate": 3e-07, + "epoch": 0.04552352048558422 + }, + { + "current_steps": 30, + "loss": 3.1007, + "learning_rate": 3.1e-07, + "epoch": 0.04704097116843703 + }, + { + "current_steps": 31, + "loss": 3.1706, + "learning_rate": 3.2e-07, + "epoch": 0.048558421851289835 + }, + { + "current_steps": 32, + "loss": 3.3955, + "learning_rate": 3.3e-07, + "epoch": 0.05007587253414264 + }, + { + "current_steps": 33, + "loss": 3.1176, + "learning_rate": 3.4000000000000003e-07, + "epoch": 0.051593323216995446 + }, + { + "current_steps": 34, + "loss": 3.0433, + "learning_rate": 3.5e-07, + "epoch": 0.05311077389984825 + }, + { + "current_steps": 35, + "loss": 3.0587, + "learning_rate": 3.6e-07, + "epoch": 0.054628224582701064 + }, + { + "current_steps": 36, + "loss": 3.0846, + "learning_rate": 3.7e-07, + "epoch": 0.05614567526555387 + }, + { + "current_steps": 37, + "loss": 2.9319, + "learning_rate": 3.7999999999999996e-07, + "epoch": 0.057663125948406675 + }, + { + "current_steps": 38, + "loss": 3.3501, + "learning_rate": 3.8999999999999997e-07, + "epoch": 0.05918057663125948 + }, + { + "current_steps": 39, + "loss": 3.0554, + "learning_rate": 4e-07, + "epoch": 0.06069802731411229 + }, + { + "current_steps": 40, + "loss": 3.0643, + "learning_rate": 4.0999999999999994e-07, + "epoch": 0.0622154779969651 + }, + { + "current_steps": 41, + "loss": 2.938, + "learning_rate": 4.1999999999999995e-07, + "epoch": 0.0637329286798179 + }, + { + "current_steps": 42, + "loss": 3.0767, + "learning_rate": 4.2999999999999996e-07, + "epoch": 0.06525037936267071 + }, + { + "current_steps": 43, + "loss": 3.2688, + "learning_rate": 4.3999999999999997e-07, + "epoch": 0.06676783004552352 + }, + { + "current_steps": 44, + "loss": 2.9776, + "learning_rate": 4.5e-07, + "epoch": 0.06828528072837632 + }, + { + "current_steps": 45, + "loss": 2.9547, + "learning_rate": 4.6e-07, + "epoch": 0.06980273141122914 + }, + { + "current_steps": 46, + "loss": 3.1347, + "learning_rate": 4.6999999999999995e-07, + "epoch": 0.07132018209408195 + }, + { + "current_steps": 47, + "loss": 2.8561, + "learning_rate": 4.8e-07, + "epoch": 0.07283763277693475 + }, + { + "current_steps": 48, + "loss": 2.9389, + "learning_rate": 4.9e-07, + "epoch": 0.07435508345978756 + }, + { + "current_steps": 49, + "loss": 3.0377, + "learning_rate": 5e-07, + "epoch": 0.07587253414264036 + }, + { + "current_steps": 50, + "loss": 3.0788, + "learning_rate": 5.1e-07, + "epoch": 0.07738998482549317 + }, + { + "current_steps": 51, + "loss": 3.0232, + "learning_rate": 5.2e-07, + "epoch": 0.07890743550834597 + }, + { + "current_steps": 52, + "loss": 3.1228, + "learning_rate": 5.3e-07, + "epoch": 0.08042488619119878 + }, + { + "current_steps": 53, + "loss": 3.017, + "learning_rate": 5.4e-07, + "epoch": 0.0819423368740516 + }, + { + "current_steps": 54, + "loss": 2.6945, + "learning_rate": 5.5e-07, + "epoch": 0.0834597875569044 + }, + { + "current_steps": 55, + "loss": 2.3648, + "learning_rate": 5.6e-07, + "epoch": 0.08497723823975721 + }, + { + "current_steps": 56, + "loss": 2.9953, + "learning_rate": 5.699999999999999e-07, + "epoch": 0.08649468892261002 + }, + { + "current_steps": 57, + "loss": 2.5556, + "learning_rate": 5.8e-07, + "epoch": 0.08801213960546282 + }, + { + "current_steps": 58, + "loss": 2.8318, + "learning_rate": 5.9e-07, + "epoch": 0.08952959028831563 + }, + { + "current_steps": 59, + "loss": 3.0898, + "learning_rate": 6e-07, + "epoch": 0.09104704097116843 + }, + { + "current_steps": 60, + "loss": 3.1807, + "learning_rate": 6.1e-07, + "epoch": 0.09256449165402124 + }, + { + "current_steps": 61, + "loss": 2.9374, + "learning_rate": 6.2e-07, + "epoch": 0.09408194233687406 + }, + { + "current_steps": 62, + "loss": 3.0356, + "learning_rate": 6.3e-07, + "epoch": 0.09559939301972686 + }, + { + "current_steps": 63, + "loss": 2.9339, + "learning_rate": 6.4e-07, + "epoch": 0.09711684370257967 + }, + { + "current_steps": 64, + "loss": 3.0431, + "learning_rate": 6.5e-07, + "epoch": 0.09863429438543247 + }, + { + "current_steps": 65, + "loss": 3.1936, + "learning_rate": 6.6e-07, + "epoch": 0.10015174506828528 + }, + { + "current_steps": 66, + "loss": 3.0084, + "learning_rate": 6.7e-07, + "epoch": 0.10166919575113809 + }, + { + "current_steps": 67, + "loss": 3.0426, + "learning_rate": 6.800000000000001e-07, + "epoch": 0.10318664643399089 + }, + { + "current_steps": 68, + "loss": 2.907, + "learning_rate": 6.9e-07, + "epoch": 0.1047040971168437 + }, + { + "current_steps": 69, + "loss": 2.9178, + "learning_rate": 7e-07, + "epoch": 0.1062215477996965 + }, + { + "current_steps": 70, + "loss": 3.0038, + "learning_rate": 7.1e-07, + "epoch": 0.10773899848254932 + }, + { + "current_steps": 71, + "loss": 2.8516, + "learning_rate": 7.2e-07, + "epoch": 0.10925644916540213 + }, + { + "current_steps": 72, + "loss": 2.9062, + "learning_rate": 7.3e-07, + "epoch": 0.11077389984825493 + }, + { + "current_steps": 73, + "loss": 3.0572, + "learning_rate": 7.4e-07, + "epoch": 0.11229135053110774 + }, + { + "current_steps": 74, + "loss": 2.819, + "learning_rate": 7.5e-07, + "epoch": 0.11380880121396054 + }, + { + "current_steps": 75, + "loss": 2.8277, + "learning_rate": 7.599999999999999e-07, + "epoch": 0.11532625189681335 + }, + { + "current_steps": 76, + "loss": 3.0996, + "learning_rate": 7.699999999999999e-07, + "epoch": 0.11684370257966616 + }, + { + "current_steps": 77, + "loss": 3.0922, + "learning_rate": 7.799999999999999e-07, + "epoch": 0.11836115326251896 + }, + { + "current_steps": 78, + "loss": 3.136, + "learning_rate": 7.9e-07, + "epoch": 0.11987860394537178 + }, + { + "current_steps": 79, + "loss": 3.0052, + "learning_rate": 8e-07, + "epoch": 0.12139605462822459 + }, + { + "current_steps": 80, + "loss": 3.1779, + "learning_rate": 8.1e-07, + "epoch": 0.12291350531107739 + }, + { + "current_steps": 81, + "loss": 3.0857, + "learning_rate": 8.199999999999999e-07, + "epoch": 0.1244309559939302 + }, + { + "current_steps": 82, + "loss": 3.036, + "learning_rate": 8.299999999999999e-07, + "epoch": 0.125948406676783 + }, + { + "current_steps": 83, + "loss": 3.1165, + "learning_rate": 8.399999999999999e-07, + "epoch": 0.1274658573596358 + }, + { + "current_steps": 84, + "loss": 2.4379, + "learning_rate": 8.499999999999999e-07, + "epoch": 0.12898330804248861 + }, + { + "current_steps": 85, + "loss": 2.9721, + "learning_rate": 8.599999999999999e-07, + "epoch": 0.13050075872534142 + }, + { + "current_steps": 86, + "loss": 3.0331, + "learning_rate": 8.699999999999999e-07, + "epoch": 0.13201820940819423 + }, + { + "current_steps": 87, + "loss": 3.0471, + "learning_rate": 8.799999999999999e-07, + "epoch": 0.13353566009104703 + }, + { + "current_steps": 88, + "loss": 2.9383, + "learning_rate": 8.9e-07, + "epoch": 0.13505311077389984 + }, + { + "current_steps": 89, + "loss": 2.9521, + "learning_rate": 9e-07, + "epoch": 0.13657056145675264 + }, + { + "current_steps": 90, + "loss": 3.2215, + "learning_rate": 9.1e-07, + "epoch": 0.13808801213960548 + }, + { + "current_steps": 91, + "loss": 2.3835, + "learning_rate": 9.2e-07, + "epoch": 0.13960546282245828 + }, + { + "current_steps": 92, + "loss": 3.0394, + "learning_rate": 9.3e-07, + "epoch": 0.1411229135053111 + }, + { + "current_steps": 93, + "loss": 2.946, + "learning_rate": 9.399999999999999e-07, + "epoch": 0.1426403641881639 + }, + { + "current_steps": 94, + "loss": 2.8589, + "learning_rate": 9.499999999999999e-07, + "epoch": 0.1441578148710167 + }, + { + "current_steps": 95, + "loss": 2.995, + "learning_rate": 9.6e-07, + "epoch": 0.1456752655538695 + }, + { + "current_steps": 96, + "loss": 3.2708, + "learning_rate": 9.7e-07, + "epoch": 0.1471927162367223 + }, + { + "current_steps": 97, + "loss": 3.0794, + "learning_rate": 9.8e-07, + "epoch": 0.14871016691957512 + }, + { + "current_steps": 98, + "loss": 2.7359, + "learning_rate": 9.9e-07, + "epoch": 0.15022761760242792 + }, + { + "current_steps": 99, + "loss": 2.3657, + "learning_rate": 1e-06, + "epoch": 0.15174506828528073 + }, + { + "current_steps": 100, + "loss": 3.0243, + "learning_rate": 9.996870109546165e-07, + "epoch": 0.15326251896813353 + }, + { + "current_steps": 101, + "loss": 2.7001, + "learning_rate": 9.993740219092331e-07, + "epoch": 0.15477996965098634 + }, + { + "current_steps": 102, + "loss": 2.8392, + "learning_rate": 9.990610328638497e-07, + "epoch": 0.15629742033383914 + }, + { + "current_steps": 103, + "loss": 2.6513, + "learning_rate": 9.987480438184663e-07, + "epoch": 0.15781487101669195 + }, + { + "current_steps": 104, + "loss": 2.9609, + "learning_rate": 9.984350547730829e-07, + "epoch": 0.15933232169954475 + }, + { + "current_steps": 105, + "loss": 2.9308, + "learning_rate": 9.981220657276995e-07, + "epoch": 0.16084977238239756 + }, + { + "current_steps": 106, + "loss": 3.202, + "learning_rate": 9.981220657276995e-07, + "epoch": 0.16236722306525037 + }, + { + "current_steps": 107, + "loss": 2.9117, + "learning_rate": 9.97809076682316e-07, + "epoch": 0.1638846737481032 + }, + { + "current_steps": 108, + "loss": 2.7512, + "learning_rate": 9.974960876369326e-07, + "epoch": 0.165402124430956 + }, + { + "current_steps": 109, + "loss": 2.9761, + "learning_rate": 9.971830985915492e-07, + "epoch": 0.1669195751138088 + }, + { + "current_steps": 110, + "loss": 3.0493, + "learning_rate": 9.968701095461658e-07, + "epoch": 0.16843702579666162 + }, + { + "current_steps": 111, + "loss": 3.0741, + "learning_rate": 9.965571205007824e-07, + "epoch": 0.16995447647951442 + }, + { + "current_steps": 112, + "loss": 2.9888, + "learning_rate": 9.96244131455399e-07, + "epoch": 0.17147192716236723 + }, + { + "current_steps": 113, + "loss": 2.9072, + "learning_rate": 9.959311424100156e-07, + "epoch": 0.17298937784522003 + }, + { + "current_steps": 114, + "loss": 3.1044, + "learning_rate": 9.956181533646322e-07, + "epoch": 0.17450682852807284 + }, + { + "current_steps": 115, + "loss": 2.9109, + "learning_rate": 9.953051643192487e-07, + "epoch": 0.17602427921092564 + }, + { + "current_steps": 116, + "loss": 3.0933, + "learning_rate": 9.949921752738653e-07, + "epoch": 0.17754172989377845 + }, + { + "current_steps": 117, + "loss": 2.9359, + "learning_rate": 9.94679186228482e-07, + "epoch": 0.17905918057663125 + }, + { + "current_steps": 118, + "loss": 2.7232, + "learning_rate": 9.943661971830985e-07, + "epoch": 0.18057663125948406 + }, + { + "current_steps": 119, + "loss": 3.1489, + "learning_rate": 9.94053208137715e-07, + "epoch": 0.18209408194233687 + }, + { + "current_steps": 120, + "loss": 2.8817, + "learning_rate": 9.937402190923317e-07, + "epoch": 0.18361153262518967 + }, + { + "current_steps": 121, + "loss": 2.5922, + "learning_rate": 9.934272300469483e-07, + "epoch": 0.18512898330804248 + }, + { + "current_steps": 122, + "loss": 3.2339, + "learning_rate": 9.931142410015648e-07, + "epoch": 0.18664643399089528 + }, + { + "current_steps": 123, + "loss": 3.049, + "learning_rate": 9.928012519561814e-07, + "epoch": 0.18816388467374812 + }, + { + "current_steps": 124, + "loss": 2.9691, + "learning_rate": 9.92488262910798e-07, + "epoch": 0.18968133535660092 + }, + { + "current_steps": 125, + "loss": 2.9531, + "learning_rate": 9.921752738654146e-07, + "epoch": 0.19119878603945373 + }, + { + "current_steps": 126, + "loss": 2.8471, + "learning_rate": 9.918622848200312e-07, + "epoch": 0.19271623672230653 + }, + { + "current_steps": 127, + "loss": 3.1392, + "learning_rate": 9.915492957746478e-07, + "epoch": 0.19423368740515934 + }, + { + "current_steps": 128, + "loss": 2.9357, + "learning_rate": 9.912363067292644e-07, + "epoch": 0.19575113808801214 + }, + { + "current_steps": 129, + "loss": 3.0804, + "learning_rate": 9.90923317683881e-07, + "epoch": 0.19726858877086495 + }, + { + "current_steps": 130, + "loss": 2.8314, + "learning_rate": 9.906103286384975e-07, + "epoch": 0.19878603945371776 + }, + { + "current_steps": 131, + "loss": 2.9615, + "learning_rate": 9.902973395931143e-07, + "epoch": 0.20030349013657056 + }, + { + "current_steps": 132, + "loss": 3.0766, + "learning_rate": 9.899843505477307e-07, + "epoch": 0.20182094081942337 + }, + { + "current_steps": 133, + "loss": 2.9684, + "learning_rate": 9.896713615023475e-07, + "epoch": 0.20333839150227617 + }, + { + "current_steps": 134, + "loss": 3.0053, + "learning_rate": 9.893583724569639e-07, + "epoch": 0.20485584218512898 + }, + { + "current_steps": 135, + "loss": 2.8741, + "learning_rate": 9.890453834115805e-07, + "epoch": 0.20637329286798178 + }, + { + "current_steps": 136, + "loss": 2.9743, + "learning_rate": 9.88732394366197e-07, + "epoch": 0.2078907435508346 + }, + { + "current_steps": 137, + "loss": 2.3444, + "learning_rate": 9.884194053208136e-07, + "epoch": 0.2094081942336874 + }, + { + "current_steps": 138, + "loss": 3.0163, + "learning_rate": 9.881064162754304e-07, + "epoch": 0.2109256449165402 + }, + { + "current_steps": 139, + "loss": 2.9994, + "learning_rate": 9.881064162754304e-07, + "epoch": 0.212443095599393 + }, + { + "current_steps": 140, + "loss": 2.9812, + "learning_rate": 9.877934272300468e-07, + "epoch": 0.21396054628224584 + }, + { + "current_steps": 141, + "loss": 2.971, + "learning_rate": 9.874804381846636e-07, + "epoch": 0.21547799696509864 + }, + { + "current_steps": 142, + "loss": 2.962, + "learning_rate": 9.8716744913928e-07, + "epoch": 0.21699544764795145 + }, + { + "current_steps": 143, + "loss": 2.7153, + "learning_rate": 9.868544600938968e-07, + "epoch": 0.21851289833080426 + }, + { + "current_steps": 144, + "loss": 2.9814, + "learning_rate": 9.865414710485132e-07, + "epoch": 0.22003034901365706 + }, + { + "current_steps": 145, + "loss": 2.9448, + "learning_rate": 9.862284820031297e-07, + "epoch": 0.22154779969650987 + }, + { + "current_steps": 146, + "loss": 2.5367, + "learning_rate": 9.859154929577465e-07, + "epoch": 0.22306525037936267 + }, + { + "current_steps": 147, + "loss": 3.0402, + "learning_rate": 9.85602503912363e-07, + "epoch": 0.22458270106221548 + }, + { + "current_steps": 148, + "loss": 2.9785, + "learning_rate": 9.852895148669797e-07, + "epoch": 0.22610015174506828 + }, + { + "current_steps": 149, + "loss": 2.9923, + "learning_rate": 9.84976525821596e-07, + "epoch": 0.2276176024279211 + }, + { + "current_steps": 150, + "loss": 2.8504, + "learning_rate": 9.846635367762129e-07, + "epoch": 0.2291350531107739 + }, + { + "current_steps": 151, + "loss": 2.8149, + "learning_rate": 9.843505477308295e-07, + "epoch": 0.2306525037936267 + }, + { + "current_steps": 152, + "loss": 2.7853, + "learning_rate": 9.840375586854458e-07, + "epoch": 0.2321699544764795 + }, + { + "current_steps": 153, + "loss": 3.0267, + "learning_rate": 9.837245696400626e-07, + "epoch": 0.2336874051593323 + }, + { + "current_steps": 154, + "loss": 2.7998, + "learning_rate": 9.83411580594679e-07, + "epoch": 0.23520485584218512 + }, + { + "current_steps": 155, + "loss": 3.0651, + "learning_rate": 9.830985915492958e-07, + "epoch": 0.23672230652503792 + }, + { + "current_steps": 156, + "loss": 3.2173, + "learning_rate": 9.827856025039122e-07, + "epoch": 0.23823975720789076 + }, + { + "current_steps": 157, + "loss": 2.7616, + "learning_rate": 9.82472613458529e-07, + "epoch": 0.23975720789074356 + }, + { + "current_steps": 158, + "loss": 3.1525, + "learning_rate": 9.821596244131456e-07, + "epoch": 0.24127465857359637 + }, + { + "current_steps": 159, + "loss": 3.0622, + "learning_rate": 9.818466353677622e-07, + "epoch": 0.24279210925644917 + }, + { + "current_steps": 160, + "loss": 2.9675, + "learning_rate": 9.815336463223787e-07, + "epoch": 0.24430955993930198 + }, + { + "current_steps": 161, + "loss": 3.0039, + "learning_rate": 9.812206572769951e-07, + "epoch": 0.24582701062215478 + }, + { + "current_steps": 162, + "loss": 2.7817, + "learning_rate": 9.80907668231612e-07, + "epoch": 0.2473444613050076 + }, + { + "current_steps": 163, + "loss": 3.2313, + "learning_rate": 9.805946791862285e-07, + "epoch": 0.2488619119878604 + }, + { + "current_steps": 164, + "loss": 2.8018, + "learning_rate": 9.80281690140845e-07, + "epoch": 0.2503793626707132 + }, + { + "current_steps": 165, + "loss": 3.029, + "learning_rate": 9.799687010954617e-07, + "epoch": 0.251896813353566 + }, + { + "current_steps": 166, + "loss": 2.7847, + "learning_rate": 9.796557120500783e-07, + "epoch": 0.2534142640364188 + }, + { + "current_steps": 167, + "loss": 3.2531, + "learning_rate": 9.793427230046949e-07, + "epoch": 0.2549317147192716 + }, + { + "current_steps": 168, + "loss": 2.781, + "learning_rate": 9.790297339593114e-07, + "epoch": 0.2564491654021244 + }, + { + "current_steps": 169, + "loss": 2.9585, + "learning_rate": 9.78716744913928e-07, + "epoch": 0.25796661608497723 + }, + { + "current_steps": 170, + "loss": 2.7364, + "learning_rate": 9.784037558685446e-07, + "epoch": 0.25948406676783003 + }, + { + "current_steps": 171, + "loss": 3.0717, + "learning_rate": 9.780907668231612e-07, + "epoch": 0.26100151745068284 + }, + { + "current_steps": 172, + "loss": 3.0081, + "learning_rate": 9.777777777777778e-07, + "epoch": 0.26251896813353565 + }, + { + "current_steps": 173, + "loss": 3.1585, + "learning_rate": 9.774647887323944e-07, + "epoch": 0.26403641881638845 + }, + { + "current_steps": 174, + "loss": 2.8551, + "learning_rate": 9.77151799687011e-07, + "epoch": 0.26555386949924126 + }, + { + "current_steps": 175, + "loss": 2.7573, + "learning_rate": 9.768388106416275e-07, + "epoch": 0.26707132018209406 + }, + { + "current_steps": 176, + "loss": 2.9672, + "learning_rate": 9.765258215962441e-07, + "epoch": 0.26858877086494687 + }, + { + "current_steps": 177, + "loss": 2.9237, + "learning_rate": 9.762128325508607e-07, + "epoch": 0.2701062215477997 + }, + { + "current_steps": 178, + "loss": 2.9823, + "learning_rate": 9.758998435054773e-07, + "epoch": 0.2716236722306525 + }, + { + "current_steps": 179, + "loss": 2.9492, + "learning_rate": 9.755868544600939e-07, + "epoch": 0.2731411229135053 + }, + { + "current_steps": 180, + "loss": 2.916, + "learning_rate": 9.752738654147105e-07, + "epoch": 0.2746585735963581 + }, + { + "current_steps": 181, + "loss": 2.8225, + "learning_rate": 9.74960876369327e-07, + "epoch": 0.27617602427921095 + }, + { + "current_steps": 182, + "loss": 2.4404, + "learning_rate": 9.746478873239436e-07, + "epoch": 0.27769347496206376 + }, + { + "current_steps": 183, + "loss": 2.8828, + "learning_rate": 9.743348982785602e-07, + "epoch": 0.27921092564491656 + }, + { + "current_steps": 184, + "loss": 2.7597, + "learning_rate": 9.740219092331768e-07, + "epoch": 0.28072837632776937 + }, + { + "current_steps": 185, + "loss": 3.1516, + "learning_rate": 9.737089201877934e-07, + "epoch": 0.2822458270106222 + }, + { + "current_steps": 186, + "loss": 2.9901, + "learning_rate": 9.7339593114241e-07, + "epoch": 0.283763277693475 + }, + { + "current_steps": 187, + "loss": 2.9251, + "learning_rate": 9.730829420970266e-07, + "epoch": 0.2852807283763278 + }, + { + "current_steps": 188, + "loss": 2.9616, + "learning_rate": 9.727699530516432e-07, + "epoch": 0.2867981790591806 + }, + { + "current_steps": 189, + "loss": 2.4373, + "learning_rate": 9.724569640062597e-07, + "epoch": 0.2883156297420334 + }, + { + "current_steps": 190, + "loss": 2.9682, + "learning_rate": 9.721439749608763e-07, + "epoch": 0.2898330804248862 + }, + { + "current_steps": 191, + "loss": 2.8157, + "learning_rate": 9.71830985915493e-07, + "epoch": 0.291350531107739 + }, + { + "current_steps": 192, + "loss": 2.9342, + "learning_rate": 9.715179968701095e-07, + "epoch": 0.2928679817905918 + }, + { + "current_steps": 193, + "loss": 2.8531, + "learning_rate": 9.71205007824726e-07, + "epoch": 0.2943854324734446 + }, + { + "current_steps": 194, + "loss": 2.8648, + "learning_rate": 9.708920187793427e-07, + "epoch": 0.2959028831562974 + }, + { + "current_steps": 195, + "loss": 2.8248, + "learning_rate": 9.705790297339593e-07, + "epoch": 0.29742033383915023 + }, + { + "current_steps": 196, + "loss": 2.9196, + "learning_rate": 9.702660406885758e-07, + "epoch": 0.29893778452200304 + }, + { + "current_steps": 197, + "loss": 2.9291, + "learning_rate": 9.699530516431924e-07, + "epoch": 0.30045523520485584 + }, + { + "current_steps": 198, + "loss": 3.1644, + "learning_rate": 9.69640062597809e-07, + "epoch": 0.30197268588770865 + }, + { + "current_steps": 199, + "loss": 2.9307, + "learning_rate": 9.693270735524256e-07, + "epoch": 0.30349013657056145 + }, + { + "current_steps": 200, + "loss": 2.746, + "learning_rate": 9.690140845070422e-07, + "epoch": 0.30500758725341426 + }, + { + "current_steps": 201, + "loss": 2.7845, + "learning_rate": 9.687010954616588e-07, + "epoch": 0.30652503793626706 + }, + { + "current_steps": 202, + "loss": 2.8281, + "learning_rate": 9.683881064162754e-07, + "epoch": 0.30804248861911987 + }, + { + "current_steps": 203, + "loss": 2.9504, + "learning_rate": 9.68075117370892e-07, + "epoch": 0.3095599393019727 + }, + { + "current_steps": 204, + "loss": 2.8501, + "learning_rate": 9.677621283255085e-07, + "epoch": 0.3110773899848255 + }, + { + "current_steps": 205, + "loss": 3.2895, + "learning_rate": 9.674491392801251e-07, + "epoch": 0.3125948406676783 + }, + { + "current_steps": 206, + "loss": 2.8217, + "learning_rate": 9.671361502347417e-07, + "epoch": 0.3141122913505311 + }, + { + "current_steps": 207, + "loss": 2.793, + "learning_rate": 9.668231611893583e-07, + "epoch": 0.3156297420333839 + }, + { + "current_steps": 208, + "loss": 2.8939, + "learning_rate": 9.665101721439749e-07, + "epoch": 0.3171471927162367 + }, + { + "current_steps": 209, + "loss": 2.7005, + "learning_rate": 9.661971830985915e-07, + "epoch": 0.3186646433990895 + }, + { + "current_steps": 210, + "loss": 2.9099, + "learning_rate": 9.65884194053208e-07, + "epoch": 0.3201820940819423 + }, + { + "current_steps": 211, + "loss": 3.1734, + "learning_rate": 9.655712050078246e-07, + "epoch": 0.3216995447647951 + }, + { + "current_steps": 212, + "loss": 2.8999, + "learning_rate": 9.652582159624412e-07, + "epoch": 0.3232169954476479 + }, + { + "current_steps": 213, + "loss": 2.9966, + "learning_rate": 9.649452269170578e-07, + "epoch": 0.32473444613050073 + }, + { + "current_steps": 214, + "loss": 3.1118, + "learning_rate": 9.646322378716744e-07, + "epoch": 0.3262518968133536 + }, + { + "current_steps": 215, + "loss": 2.908, + "learning_rate": 9.64319248826291e-07, + "epoch": 0.3277693474962064 + }, + { + "current_steps": 216, + "loss": 2.8644, + "learning_rate": 9.640062597809076e-07, + "epoch": 0.3292867981790592 + }, + { + "current_steps": 217, + "loss": 2.8121, + "learning_rate": 9.636932707355242e-07, + "epoch": 0.330804248861912 + }, + { + "current_steps": 218, + "loss": 2.771, + "learning_rate": 9.63380281690141e-07, + "epoch": 0.3323216995447648 + }, + { + "current_steps": 219, + "loss": 3.1117, + "learning_rate": 9.630672926447573e-07, + "epoch": 0.3338391502276176 + }, + { + "current_steps": 220, + "loss": 3.1757, + "learning_rate": 9.62754303599374e-07, + "epoch": 0.3353566009104704 + }, + { + "current_steps": 221, + "loss": 2.9569, + "learning_rate": 9.624413145539905e-07, + "epoch": 0.33687405159332323 + }, + { + "current_steps": 222, + "loss": 2.7911, + "learning_rate": 9.62128325508607e-07, + "epoch": 0.33839150227617604 + }, + { + "current_steps": 223, + "loss": 3.2308, + "learning_rate": 9.618153364632237e-07, + "epoch": 0.33990895295902884 + }, + { + "current_steps": 224, + "loss": 2.7308, + "learning_rate": 9.615023474178403e-07, + "epoch": 0.34142640364188165 + }, + { + "current_steps": 225, + "loss": 3.0307, + "learning_rate": 9.61189358372457e-07, + "epoch": 0.34294385432473445 + }, + { + "current_steps": 226, + "loss": 2.9794, + "learning_rate": 9.608763693270734e-07, + "epoch": 0.34446130500758726 + }, + { + "current_steps": 227, + "loss": 2.9641, + "learning_rate": 9.605633802816902e-07, + "epoch": 0.34597875569044007 + }, + { + "current_steps": 228, + "loss": 2.8622, + "learning_rate": 9.602503912363066e-07, + "epoch": 0.34749620637329287 + }, + { + "current_steps": 229, + "loss": 2.8021, + "learning_rate": 9.599374021909232e-07, + "epoch": 0.3490136570561457 + }, + { + "current_steps": 230, + "loss": 3.0891, + "learning_rate": 9.596244131455398e-07, + "epoch": 0.3505311077389985 + }, + { + "current_steps": 231, + "loss": 2.9736, + "learning_rate": 9.593114241001564e-07, + "epoch": 0.3520485584218513 + }, + { + "current_steps": 232, + "loss": 2.8482, + "learning_rate": 9.589984350547732e-07, + "epoch": 0.3535660091047041 + }, + { + "current_steps": 233, + "loss": 2.9314, + "learning_rate": 9.586854460093895e-07, + "epoch": 0.3550834597875569 + }, + { + "current_steps": 234, + "loss": 3.0489, + "learning_rate": 9.583724569640063e-07, + "epoch": 0.3566009104704097 + }, + { + "current_steps": 235, + "loss": 2.8818, + "learning_rate": 9.580594679186227e-07, + "epoch": 0.3581183611532625 + }, + { + "current_steps": 236, + "loss": 2.8575, + "learning_rate": 9.577464788732393e-07, + "epoch": 0.3596358118361153 + }, + { + "current_steps": 237, + "loss": 2.5001, + "learning_rate": 9.57433489827856e-07, + "epoch": 0.3611532625189681 + }, + { + "current_steps": 238, + "loss": 2.792, + "learning_rate": 9.571205007824725e-07, + "epoch": 0.3626707132018209 + }, + { + "current_steps": 239, + "loss": 2.9418, + "learning_rate": 9.568075117370893e-07, + "epoch": 0.36418816388467373 + }, + { + "current_steps": 240, + "loss": 3.0265, + "learning_rate": 9.564945226917056e-07, + "epoch": 0.36570561456752654 + }, + { + "current_steps": 241, + "loss": 2.748, + "learning_rate": 9.561815336463224e-07, + "epoch": 0.36722306525037934 + }, + { + "current_steps": 242, + "loss": 2.9705, + "learning_rate": 9.558685446009388e-07, + "epoch": 0.36874051593323215 + }, + { + "current_steps": 243, + "loss": 2.8055, + "learning_rate": 9.555555555555556e-07, + "epoch": 0.37025796661608495 + }, + { + "current_steps": 244, + "loss": 3.039, + "learning_rate": 9.552425665101722e-07, + "epoch": 0.37177541729893776 + }, + { + "current_steps": 245, + "loss": 2.975, + "learning_rate": 9.549295774647886e-07, + "epoch": 0.37329286798179057 + }, + { + "current_steps": 246, + "loss": 2.9279, + "learning_rate": 9.546165884194054e-07, + "epoch": 0.37481031866464337 + }, + { + "current_steps": 247, + "loss": 3.0687, + "learning_rate": 9.543035993740217e-07, + "epoch": 0.37632776934749623 + }, + { + "current_steps": 248, + "loss": 2.5354, + "learning_rate": 9.539906103286385e-07, + "epoch": 0.37784522003034904 + }, + { + "current_steps": 249, + "loss": 2.7224, + "learning_rate": 9.536776212832551e-07, + "epoch": 0.37936267071320184 + }, + { + "current_steps": 250, + "loss": 2.8899, + "learning_rate": 9.533646322378717e-07, + "epoch": 0.38088012139605465 + }, + { + "current_steps": 251, + "loss": 2.9458, + "learning_rate": 9.530516431924882e-07, + "epoch": 0.38239757207890746 + }, + { + "current_steps": 252, + "loss": 2.9613, + "learning_rate": 9.527386541471049e-07, + "epoch": 0.38391502276176026 + }, + { + "current_steps": 253, + "loss": 2.6724, + "learning_rate": 9.524256651017214e-07, + "epoch": 0.38543247344461307 + }, + { + "current_steps": 254, + "loss": 2.7529, + "learning_rate": 9.52112676056338e-07, + "epoch": 0.38694992412746587 + }, + { + "current_steps": 255, + "loss": 2.9075, + "learning_rate": 9.517996870109546e-07, + "epoch": 0.3884673748103187 + }, + { + "current_steps": 256, + "loss": 2.7731, + "learning_rate": 9.514866979655711e-07, + "epoch": 0.3899848254931715 + }, + { + "current_steps": 257, + "loss": 2.809, + "learning_rate": 9.511737089201878e-07, + "epoch": 0.3915022761760243 + }, + { + "current_steps": 258, + "loss": 3.0258, + "learning_rate": 9.508607198748043e-07, + "epoch": 0.3930197268588771 + }, + { + "current_steps": 259, + "loss": 2.5215, + "learning_rate": 9.50547730829421e-07, + "epoch": 0.3945371775417299 + }, + { + "current_steps": 260, + "loss": 2.7954, + "learning_rate": 9.502347417840375e-07, + "epoch": 0.3960546282245827 + }, + { + "current_steps": 261, + "loss": 2.8948, + "learning_rate": 9.499217527386542e-07, + "epoch": 0.3975720789074355 + }, + { + "current_steps": 262, + "loss": 2.7883, + "learning_rate": 9.496087636932707e-07, + "epoch": 0.3990895295902883 + }, + { + "current_steps": 263, + "loss": 2.8921, + "learning_rate": 9.492957746478872e-07, + "epoch": 0.4006069802731411 + }, + { + "current_steps": 264, + "loss": 2.4995, + "learning_rate": 9.489827856025039e-07, + "epoch": 0.40212443095599393 + }, + { + "current_steps": 265, + "loss": 2.9574, + "learning_rate": 9.486697965571204e-07, + "epoch": 0.40364188163884673 + }, + { + "current_steps": 266, + "loss": 2.5981, + "learning_rate": 9.483568075117371e-07, + "epoch": 0.40515933232169954 + }, + { + "current_steps": 267, + "loss": 2.8717, + "learning_rate": 9.480438184663536e-07, + "epoch": 0.40667678300455234 + }, + { + "current_steps": 268, + "loss": 2.8266, + "learning_rate": 9.477308294209703e-07, + "epoch": 0.40819423368740515 + }, + { + "current_steps": 269, + "loss": 2.9851, + "learning_rate": 9.474178403755868e-07, + "epoch": 0.40971168437025796 + }, + { + "current_steps": 270, + "loss": 3.1026, + "learning_rate": 9.471048513302033e-07, + "epoch": 0.41122913505311076 + }, + { + "current_steps": 271, + "loss": 3.0123, + "learning_rate": 9.4679186228482e-07, + "epoch": 0.41274658573596357 + }, + { + "current_steps": 272, + "loss": 2.8961, + "learning_rate": 9.464788732394365e-07, + "epoch": 0.4142640364188164 + }, + { + "current_steps": 273, + "loss": 2.7328, + "learning_rate": 9.461658841940532e-07, + "epoch": 0.4157814871016692 + }, + { + "current_steps": 274, + "loss": 2.8203, + "learning_rate": 9.458528951486698e-07, + "epoch": 0.417298937784522 + }, + { + "current_steps": 275, + "loss": 2.115, + "learning_rate": 9.455399061032864e-07, + "epoch": 0.4188163884673748 + }, + { + "current_steps": 276, + "loss": 3.1932, + "learning_rate": 9.45226917057903e-07, + "epoch": 0.4203338391502276 + }, + { + "current_steps": 277, + "loss": 2.817, + "learning_rate": 9.449139280125195e-07, + "epoch": 0.4218512898330804 + }, + { + "current_steps": 278, + "loss": 2.9826, + "learning_rate": 9.446009389671361e-07, + "epoch": 0.4233687405159332 + }, + { + "current_steps": 279, + "loss": 2.9338, + "learning_rate": 9.442879499217526e-07, + "epoch": 0.424886191198786 + }, + { + "current_steps": 280, + "loss": 3.0123, + "learning_rate": 9.439749608763693e-07, + "epoch": 0.4264036418816389 + }, + { + "current_steps": 281, + "loss": 2.987, + "learning_rate": 9.436619718309859e-07, + "epoch": 0.4279210925644917 + }, + { + "current_steps": 282, + "loss": 2.8779, + "learning_rate": 9.433489827856025e-07, + "epoch": 0.4294385432473445 + }, + { + "current_steps": 283, + "loss": 3.0333, + "learning_rate": 9.43035993740219e-07, + "epoch": 0.4309559939301973 + }, + { + "current_steps": 284, + "loss": 2.5038, + "learning_rate": 9.427230046948356e-07, + "epoch": 0.4324734446130501 + }, + { + "current_steps": 285, + "loss": 2.7507, + "learning_rate": 9.424100156494522e-07, + "epoch": 0.4339908952959029 + }, + { + "current_steps": 286, + "loss": 2.8421, + "learning_rate": 9.420970266040689e-07, + "epoch": 0.4355083459787557 + }, + { + "current_steps": 287, + "loss": 3.0909, + "learning_rate": 9.417840375586854e-07, + "epoch": 0.4370257966616085 + }, + { + "current_steps": 288, + "loss": 2.8093, + "learning_rate": 9.41471048513302e-07, + "epoch": 0.4385432473444613 + }, + { + "current_steps": 289, + "loss": 2.7904, + "learning_rate": 9.411580594679186e-07, + "epoch": 0.4400606980273141 + }, + { + "current_steps": 290, + "loss": 3.1672, + "learning_rate": 9.408450704225352e-07, + "epoch": 0.44157814871016693 + }, + { + "current_steps": 291, + "loss": 2.9345, + "learning_rate": 9.405320813771517e-07, + "epoch": 0.44309559939301973 + }, + { + "current_steps": 292, + "loss": 2.7829, + "learning_rate": 9.402190923317683e-07, + "epoch": 0.44461305007587254 + }, + { + "current_steps": 293, + "loss": 3.2218, + "learning_rate": 9.39906103286385e-07, + "epoch": 0.44613050075872535 + }, + { + "current_steps": 294, + "loss": 2.8115, + "learning_rate": 9.395931142410015e-07, + "epoch": 0.44764795144157815 + }, + { + "current_steps": 295, + "loss": 2.1784, + "learning_rate": 9.392801251956181e-07, + "epoch": 0.44916540212443096 + }, + { + "current_steps": 296, + "loss": 2.9249, + "learning_rate": 9.389671361502347e-07, + "epoch": 0.45068285280728376 + }, + { + "current_steps": 297, + "loss": 3.0792, + "learning_rate": 9.386541471048513e-07, + "epoch": 0.45220030349013657 + }, + { + "current_steps": 298, + "loss": 2.9528, + "learning_rate": 9.38341158059468e-07, + "epoch": 0.4537177541729894 + }, + { + "current_steps": 299, + "loss": 3.0145, + "learning_rate": 9.380281690140844e-07, + "epoch": 0.4552352048558422 + }, + { + "current_steps": 300, + "loss": 3.0044, + "learning_rate": 9.377151799687011e-07, + "epoch": 0.456752655538695 + }, + { + "current_steps": 301, + "loss": 2.7036, + "learning_rate": 9.374021909233176e-07, + "epoch": 0.4582701062215478 + }, + { + "current_steps": 302, + "loss": 3.1776, + "learning_rate": 9.370892018779343e-07, + "epoch": 0.4597875569044006 + }, + { + "current_steps": 303, + "loss": 3.0121, + "learning_rate": 9.367762128325508e-07, + "epoch": 0.4613050075872534 + }, + { + "current_steps": 304, + "loss": 2.87, + "learning_rate": 9.364632237871674e-07, + "epoch": 0.4628224582701062 + }, + { + "current_steps": 305, + "loss": 2.9064, + "learning_rate": 9.36150234741784e-07, + "epoch": 0.464339908952959 + }, + { + "current_steps": 306, + "loss": 2.9643, + "learning_rate": 9.358372456964005e-07, + "epoch": 0.4658573596358118 + }, + { + "current_steps": 307, + "loss": 2.8595, + "learning_rate": 9.355242566510172e-07, + "epoch": 0.4673748103186646 + }, + { + "current_steps": 308, + "loss": 2.871, + "learning_rate": 9.352112676056337e-07, + "epoch": 0.46889226100151743 + }, + { + "current_steps": 309, + "loss": 2.8314, + "learning_rate": 9.348982785602504e-07, + "epoch": 0.47040971168437024 + }, + { + "current_steps": 310, + "loss": 2.9647, + "learning_rate": 9.345852895148669e-07, + "epoch": 0.47192716236722304 + }, + { + "current_steps": 311, + "loss": 2.8688, + "learning_rate": 9.342723004694836e-07, + "epoch": 0.47344461305007585 + }, + { + "current_steps": 312, + "loss": 2.8102, + "learning_rate": 9.339593114241002e-07, + "epoch": 0.47496206373292865 + }, + { + "current_steps": 313, + "loss": 2.8202, + "learning_rate": 9.336463223787166e-07, + "epoch": 0.4764795144157815 + }, + { + "current_steps": 314, + "loss": 2.8969, + "learning_rate": 9.333333333333333e-07, + "epoch": 0.4779969650986343 + }, + { + "current_steps": 315, + "loss": 2.8789, + "learning_rate": 9.330203442879498e-07, + "epoch": 0.4795144157814871 + }, + { + "current_steps": 316, + "loss": 2.9373, + "learning_rate": 9.327073552425665e-07, + "epoch": 0.48103186646433993 + }, + { + "current_steps": 317, + "loss": 2.9073, + "learning_rate": 9.323943661971831e-07, + "epoch": 0.48254931714719274 + }, + { + "current_steps": 318, + "loss": 2.9506, + "learning_rate": 9.320813771517997e-07, + "epoch": 0.48406676783004554 + }, + { + "current_steps": 319, + "loss": 3.0583, + "learning_rate": 9.317683881064163e-07, + "epoch": 0.48558421851289835 + }, + { + "current_steps": 320, + "loss": 2.8713, + "learning_rate": 9.314553990610328e-07, + "epoch": 0.48710166919575115 + }, + { + "current_steps": 321, + "loss": 2.6779, + "learning_rate": 9.311424100156494e-07, + "epoch": 0.48861911987860396 + }, + { + "current_steps": 322, + "loss": 2.9962, + "learning_rate": 9.308294209702659e-07, + "epoch": 0.49013657056145676 + }, + { + "current_steps": 323, + "loss": 2.953, + "learning_rate": 9.305164319248826e-07, + "epoch": 0.49165402124430957 + }, + { + "current_steps": 324, + "loss": 2.7805, + "learning_rate": 9.302034428794992e-07, + "epoch": 0.4931714719271624 + }, + { + "current_steps": 325, + "loss": 2.9387, + "learning_rate": 9.298904538341158e-07, + "epoch": 0.4946889226100152 + }, + { + "current_steps": 326, + "loss": 3.0342, + "learning_rate": 9.295774647887324e-07, + "epoch": 0.496206373292868 + }, + { + "current_steps": 327, + "loss": 2.8274, + "learning_rate": 9.292644757433489e-07, + "epoch": 0.4977238239757208 + }, + { + "current_steps": 328, + "loss": 2.7162, + "learning_rate": 9.289514866979655e-07, + "epoch": 0.4992412746585736 + }, + { + "current_steps": 329, + "loss": 2.9019, + "learning_rate": 9.28638497652582e-07, + "epoch": 0.5007587253414264 + }, + { + "current_steps": 330, + "loss": 2.8622, + "learning_rate": 9.283255086071987e-07, + "epoch": 0.5022761760242792 + }, + { + "current_steps": 331, + "loss": 2.8689, + "learning_rate": 9.280125195618153e-07, + "epoch": 0.503793626707132 + }, + { + "current_steps": 332, + "loss": 2.8581, + "learning_rate": 9.276995305164319e-07, + "epoch": 0.5053110773899848 + }, + { + "current_steps": 333, + "loss": 2.8811, + "learning_rate": 9.273865414710485e-07, + "epoch": 0.5068285280728376 + }, + { + "current_steps": 334, + "loss": 3.0835, + "learning_rate": 9.27073552425665e-07, + "epoch": 0.5083459787556904 + }, + { + "current_steps": 335, + "loss": 2.9084, + "learning_rate": 9.267605633802816e-07, + "epoch": 0.5098634294385432 + }, + { + "current_steps": 336, + "loss": 2.9811, + "learning_rate": 9.264475743348983e-07, + "epoch": 0.511380880121396 + }, + { + "current_steps": 337, + "loss": 2.894, + "learning_rate": 9.261345852895148e-07, + "epoch": 0.5128983308042488 + }, + { + "current_steps": 338, + "loss": 2.9457, + "learning_rate": 9.258215962441314e-07, + "epoch": 0.5144157814871017 + }, + { + "current_steps": 339, + "loss": 2.8513, + "learning_rate": 9.25508607198748e-07, + "epoch": 0.5159332321699545 + }, + { + "current_steps": 340, + "loss": 2.9324, + "learning_rate": 9.251956181533646e-07, + "epoch": 0.5174506828528073 + }, + { + "current_steps": 341, + "loss": 2.74, + "learning_rate": 9.248826291079813e-07, + "epoch": 0.5189681335356601 + }, + { + "current_steps": 342, + "loss": 2.933, + "learning_rate": 9.245696400625977e-07, + "epoch": 0.5204855842185129 + }, + { + "current_steps": 343, + "loss": 3.049, + "learning_rate": 9.242566510172144e-07, + "epoch": 0.5220030349013657 + }, + { + "current_steps": 344, + "loss": 2.9297, + "learning_rate": 9.239436619718309e-07, + "epoch": 0.5235204855842185 + }, + { + "current_steps": 345, + "loss": 2.791, + "learning_rate": 9.236306729264476e-07, + "epoch": 0.5250379362670713 + }, + { + "current_steps": 346, + "loss": 2.7501, + "learning_rate": 9.233176838810641e-07, + "epoch": 0.5265553869499241 + }, + { + "current_steps": 347, + "loss": 2.8148, + "learning_rate": 9.230046948356807e-07, + "epoch": 0.5280728376327769 + }, + { + "current_steps": 348, + "loss": 2.4203, + "learning_rate": 9.226917057902974e-07, + "epoch": 0.5295902883156297 + }, + { + "current_steps": 349, + "loss": 2.8668, + "learning_rate": 9.223787167449138e-07, + "epoch": 0.5311077389984825 + }, + { + "current_steps": 350, + "loss": 2.8372, + "learning_rate": 9.220657276995305e-07, + "epoch": 0.5326251896813353 + }, + { + "current_steps": 351, + "loss": 3.0186, + "learning_rate": 9.21752738654147e-07, + "epoch": 0.5341426403641881 + }, + { + "current_steps": 352, + "loss": 2.8572, + "learning_rate": 9.214397496087637e-07, + "epoch": 0.5356600910470409 + }, + { + "current_steps": 353, + "loss": 2.8614, + "learning_rate": 9.211267605633802e-07, + "epoch": 0.5371775417298937 + }, + { + "current_steps": 354, + "loss": 2.7753, + "learning_rate": 9.208137715179968e-07, + "epoch": 0.5386949924127465 + }, + { + "current_steps": 355, + "loss": 2.917, + "learning_rate": 9.205007824726135e-07, + "epoch": 0.5402124430955993 + }, + { + "current_steps": 356, + "loss": 2.8441, + "learning_rate": 9.201877934272299e-07, + "epoch": 0.5417298937784522 + }, + { + "current_steps": 357, + "loss": 2.6123, + "learning_rate": 9.198748043818466e-07, + "epoch": 0.543247344461305 + }, + { + "current_steps": 358, + "loss": 2.8969, + "learning_rate": 9.195618153364631e-07, + "epoch": 0.5447647951441578 + }, + { + "current_steps": 359, + "loss": 2.8851, + "learning_rate": 9.192488262910798e-07, + "epoch": 0.5462822458270106 + }, + { + "current_steps": 360, + "loss": 2.8514, + "learning_rate": 9.189358372456964e-07, + "epoch": 0.5477996965098634 + }, + { + "current_steps": 361, + "loss": 2.9326, + "learning_rate": 9.18622848200313e-07, + "epoch": 0.5493171471927162 + }, + { + "current_steps": 362, + "loss": 2.8429, + "learning_rate": 9.183098591549296e-07, + "epoch": 0.5508345978755691 + }, + { + "current_steps": 363, + "loss": 3.0218, + "learning_rate": 9.17996870109546e-07, + "epoch": 0.5523520485584219 + }, + { + "current_steps": 364, + "loss": 2.8842, + "learning_rate": 9.176838810641627e-07, + "epoch": 0.5538694992412747 + }, + { + "current_steps": 365, + "loss": 2.9477, + "learning_rate": 9.173708920187792e-07, + "epoch": 0.5553869499241275 + }, + { + "current_steps": 366, + "loss": 2.8515, + "learning_rate": 9.170579029733959e-07, + "epoch": 0.5569044006069803 + }, + { + "current_steps": 367, + "loss": 2.9399, + "learning_rate": 9.167449139280125e-07, + "epoch": 0.5584218512898331 + }, + { + "current_steps": 368, + "loss": 2.9214, + "learning_rate": 9.164319248826291e-07, + "epoch": 0.5599393019726859 + }, + { + "current_steps": 369, + "loss": 2.9305, + "learning_rate": 9.161189358372457e-07, + "epoch": 0.5614567526555387 + }, + { + "current_steps": 370, + "loss": 2.759, + "learning_rate": 9.158059467918623e-07, + "epoch": 0.5629742033383915 + }, + { + "current_steps": 371, + "loss": 2.9273, + "learning_rate": 9.154929577464788e-07, + "epoch": 0.5644916540212443 + }, + { + "current_steps": 372, + "loss": 2.7117, + "learning_rate": 9.151799687010953e-07, + "epoch": 0.5660091047040972 + }, + { + "current_steps": 373, + "loss": 2.9005, + "learning_rate": 9.14866979655712e-07, + "epoch": 0.56752655538695 + }, + { + "current_steps": 374, + "loss": 2.8185, + "learning_rate": 9.145539906103286e-07, + "epoch": 0.5690440060698028 + }, + { + "current_steps": 375, + "loss": 2.9261, + "learning_rate": 9.142410015649452e-07, + "epoch": 0.5705614567526556 + }, + { + "current_steps": 376, + "loss": 2.736, + "learning_rate": 9.139280125195618e-07, + "epoch": 0.5720789074355084 + }, + { + "current_steps": 377, + "loss": 2.7778, + "learning_rate": 9.136150234741784e-07, + "epoch": 0.5735963581183612 + }, + { + "current_steps": 378, + "loss": 2.691, + "learning_rate": 9.133020344287949e-07, + "epoch": 0.575113808801214 + }, + { + "current_steps": 379, + "loss": 2.9932, + "learning_rate": 9.129890453834116e-07, + "epoch": 0.5766312594840668 + }, + { + "current_steps": 380, + "loss": 2.8017, + "learning_rate": 9.126760563380281e-07, + "epoch": 0.5781487101669196 + }, + { + "current_steps": 381, + "loss": 2.6763, + "learning_rate": 9.123630672926447e-07, + "epoch": 0.5796661608497724 + }, + { + "current_steps": 382, + "loss": 2.8724, + "learning_rate": 9.120500782472613e-07, + "epoch": 0.5811836115326252 + }, + { + "current_steps": 383, + "loss": 2.8178, + "learning_rate": 9.117370892018779e-07, + "epoch": 0.582701062215478 + }, + { + "current_steps": 384, + "loss": 2.7833, + "learning_rate": 9.114241001564945e-07, + "epoch": 0.5842185128983308 + }, + { + "current_steps": 385, + "loss": 2.9048, + "learning_rate": 9.11111111111111e-07, + "epoch": 0.5857359635811836 + }, + { + "current_steps": 386, + "loss": 2.974, + "learning_rate": 9.107981220657277e-07, + "epoch": 0.5872534142640364 + }, + { + "current_steps": 387, + "loss": 3.0191, + "learning_rate": 9.104851330203442e-07, + "epoch": 0.5887708649468892 + }, + { + "current_steps": 388, + "loss": 2.9018, + "learning_rate": 9.101721439749608e-07, + "epoch": 0.590288315629742 + }, + { + "current_steps": 389, + "loss": 2.7449, + "learning_rate": 9.098591549295774e-07, + "epoch": 0.5918057663125948 + }, + { + "current_steps": 390, + "loss": 2.7923, + "learning_rate": 9.09546165884194e-07, + "epoch": 0.5933232169954477 + }, + { + "current_steps": 391, + "loss": 2.9581, + "learning_rate": 9.092331768388107e-07, + "epoch": 0.5948406676783005 + }, + { + "current_steps": 392, + "loss": 3.0036, + "learning_rate": 9.089201877934271e-07, + "epoch": 0.5963581183611533 + }, + { + "current_steps": 393, + "loss": 2.7718, + "learning_rate": 9.086071987480438e-07, + "epoch": 0.5978755690440061 + }, + { + "current_steps": 394, + "loss": 2.1854, + "learning_rate": 9.082942097026603e-07, + "epoch": 0.5993930197268589 + }, + { + "current_steps": 395, + "loss": 2.7402, + "learning_rate": 9.07981220657277e-07, + "epoch": 0.6009104704097117 + }, + { + "current_steps": 396, + "loss": 2.9586, + "learning_rate": 9.076682316118935e-07, + "epoch": 0.6024279210925645 + }, + { + "current_steps": 397, + "loss": 2.9023, + "learning_rate": 9.073552425665101e-07, + "epoch": 0.6039453717754173 + }, + { + "current_steps": 398, + "loss": 2.8239, + "learning_rate": 9.070422535211268e-07, + "epoch": 0.6054628224582701 + }, + { + "current_steps": 399, + "loss": 2.8282, + "learning_rate": 9.067292644757433e-07, + "epoch": 0.6069802731411229 + }, + { + "current_steps": 400, + "loss": 2.8625, + "learning_rate": 9.064162754303599e-07, + "epoch": 0.6084977238239757 + }, + { + "current_steps": 401, + "loss": 3.3468, + "learning_rate": 9.061032863849764e-07, + "epoch": 0.6100151745068285 + }, + { + "current_steps": 402, + "loss": 2.8919, + "learning_rate": 9.057902973395931e-07, + "epoch": 0.6115326251896813 + }, + { + "current_steps": 403, + "loss": 2.9283, + "learning_rate": 9.054773082942097e-07, + "epoch": 0.6130500758725341 + }, + { + "current_steps": 404, + "loss": 2.8615, + "learning_rate": 9.051643192488263e-07, + "epoch": 0.6145675265553869 + }, + { + "current_steps": 405, + "loss": 2.9101, + "learning_rate": 9.048513302034429e-07, + "epoch": 0.6160849772382397 + }, + { + "current_steps": 406, + "loss": 2.6953, + "learning_rate": 9.045383411580594e-07, + "epoch": 0.6176024279210925 + }, + { + "current_steps": 407, + "loss": 2.2014, + "learning_rate": 9.04225352112676e-07, + "epoch": 0.6191198786039454 + }, + { + "current_steps": 408, + "loss": 2.7359, + "learning_rate": 9.039123630672925e-07, + "epoch": 0.6206373292867982 + }, + { + "current_steps": 409, + "loss": 2.8156, + "learning_rate": 9.035993740219092e-07, + "epoch": 0.622154779969651 + }, + { + "current_steps": 410, + "loss": 2.8534, + "learning_rate": 9.032863849765258e-07, + "epoch": 0.6236722306525038 + }, + { + "current_steps": 411, + "loss": 2.6601, + "learning_rate": 9.029733959311424e-07, + "epoch": 0.6251896813353566 + }, + { + "current_steps": 412, + "loss": 2.6415, + "learning_rate": 9.02660406885759e-07, + "epoch": 0.6267071320182094 + }, + { + "current_steps": 413, + "loss": 2.9632, + "learning_rate": 9.023474178403755e-07, + "epoch": 0.6282245827010622 + }, + { + "current_steps": 414, + "loss": 2.9106, + "learning_rate": 9.020344287949921e-07, + "epoch": 0.629742033383915 + }, + { + "current_steps": 415, + "loss": 3.0015, + "learning_rate": 9.017214397496086e-07, + "epoch": 0.6312594840667678 + }, + { + "current_steps": 416, + "loss": 2.6653, + "learning_rate": 9.014084507042253e-07, + "epoch": 0.6327769347496206 + }, + { + "current_steps": 417, + "loss": 2.8016, + "learning_rate": 9.010954616588419e-07, + "epoch": 0.6342943854324734 + }, + { + "current_steps": 418, + "loss": 2.9234, + "learning_rate": 9.007824726134585e-07, + "epoch": 0.6358118361153262 + }, + { + "current_steps": 419, + "loss": 2.8825, + "learning_rate": 9.004694835680751e-07, + "epoch": 0.637329286798179 + }, + { + "current_steps": 420, + "loss": 2.6642, + "learning_rate": 9.001564945226917e-07, + "epoch": 0.6388467374810318 + }, + { + "current_steps": 421, + "loss": 2.7824, + "learning_rate": 8.998435054773083e-07, + "epoch": 0.6403641881638846 + }, + { + "current_steps": 422, + "loss": 2.97, + "learning_rate": 8.995305164319248e-07, + "epoch": 0.6418816388467374 + }, + { + "current_steps": 423, + "loss": 2.8175, + "learning_rate": 8.992175273865414e-07, + "epoch": 0.6433990895295902 + }, + { + "current_steps": 424, + "loss": 2.7487, + "learning_rate": 8.98904538341158e-07, + "epoch": 0.644916540212443 + }, + { + "current_steps": 425, + "loss": 2.9221, + "learning_rate": 8.985915492957746e-07, + "epoch": 0.6464339908952959 + }, + { + "current_steps": 426, + "loss": 2.8391, + "learning_rate": 8.982785602503912e-07, + "epoch": 0.6479514415781487 + }, + { + "current_steps": 427, + "loss": 2.9355, + "learning_rate": 8.979655712050078e-07, + "epoch": 0.6494688922610015 + }, + { + "current_steps": 428, + "loss": 2.8924, + "learning_rate": 8.976525821596244e-07, + "epoch": 0.6509863429438544 + }, + { + "current_steps": 429, + "loss": 2.9381, + "learning_rate": 8.97339593114241e-07, + "epoch": 0.6525037936267072 + }, + { + "current_steps": 430, + "loss": 3.1598, + "learning_rate": 8.970266040688575e-07, + "epoch": 0.65402124430956 + }, + { + "current_steps": 431, + "loss": 3.0202, + "learning_rate": 8.967136150234741e-07, + "epoch": 0.6555386949924128 + }, + { + "current_steps": 432, + "loss": 2.8991, + "learning_rate": 8.964006259780907e-07, + "epoch": 0.6570561456752656 + }, + { + "current_steps": 433, + "loss": 2.6988, + "learning_rate": 8.960876369327073e-07, + "epoch": 0.6585735963581184 + }, + { + "current_steps": 434, + "loss": 2.8604, + "learning_rate": 8.95774647887324e-07, + "epoch": 0.6600910470409712 + }, + { + "current_steps": 435, + "loss": 2.8196, + "learning_rate": 8.954616588419405e-07, + "epoch": 0.661608497723824 + }, + { + "current_steps": 436, + "loss": 2.7689, + "learning_rate": 8.951486697965571e-07, + "epoch": 0.6631259484066768 + }, + { + "current_steps": 437, + "loss": 2.6639, + "learning_rate": 8.948356807511736e-07, + "epoch": 0.6646433990895296 + }, + { + "current_steps": 438, + "loss": 2.8738, + "learning_rate": 8.945226917057903e-07, + "epoch": 0.6661608497723824 + }, + { + "current_steps": 439, + "loss": 2.9266, + "learning_rate": 8.942097026604068e-07, + "epoch": 0.6676783004552352 + }, + { + "current_steps": 440, + "loss": 2.8831, + "learning_rate": 8.938967136150234e-07, + "epoch": 0.669195751138088 + }, + { + "current_steps": 441, + "loss": 2.6031, + "learning_rate": 8.935837245696401e-07, + "epoch": 0.6707132018209409 + }, + { + "current_steps": 442, + "loss": 2.8578, + "learning_rate": 8.932707355242566e-07, + "epoch": 0.6722306525037937 + }, + { + "current_steps": 443, + "loss": 2.9378, + "learning_rate": 8.929577464788733e-07, + "epoch": 0.6737481031866465 + }, + { + "current_steps": 444, + "loss": 2.836, + "learning_rate": 8.926447574334897e-07, + "epoch": 0.6752655538694993 + }, + { + "current_steps": 445, + "loss": 2.7052, + "learning_rate": 8.923317683881064e-07, + "epoch": 0.6767830045523521 + }, + { + "current_steps": 446, + "loss": 2.8476, + "learning_rate": 8.92018779342723e-07, + "epoch": 0.6783004552352049 + }, + { + "current_steps": 447, + "loss": 2.4444, + "learning_rate": 8.917057902973395e-07, + "epoch": 0.6798179059180577 + }, + { + "current_steps": 448, + "loss": 3.0076, + "learning_rate": 8.913928012519562e-07, + "epoch": 0.6813353566009105 + }, + { + "current_steps": 449, + "loss": 2.676, + "learning_rate": 8.910798122065727e-07, + "epoch": 0.6828528072837633 + }, + { + "current_steps": 450, + "loss": 2.635, + "learning_rate": 8.907668231611894e-07, + "epoch": 0.6843702579666161 + }, + { + "current_steps": 451, + "loss": 2.6396, + "learning_rate": 8.904538341158058e-07, + "epoch": 0.6858877086494689 + }, + { + "current_steps": 452, + "loss": 2.7057, + "learning_rate": 8.901408450704225e-07, + "epoch": 0.6874051593323217 + }, + { + "current_steps": 453, + "loss": 2.6703, + "learning_rate": 8.898278560250391e-07, + "epoch": 0.6889226100151745 + }, + { + "current_steps": 454, + "loss": 3.0736, + "learning_rate": 8.895148669796557e-07, + "epoch": 0.6904400606980273 + }, + { + "current_steps": 455, + "loss": 2.7926, + "learning_rate": 8.892018779342723e-07, + "epoch": 0.6919575113808801 + }, + { + "current_steps": 456, + "loss": 2.6833, + "learning_rate": 8.888888888888888e-07, + "epoch": 0.6934749620637329 + }, + { + "current_steps": 457, + "loss": 2.7843, + "learning_rate": 8.885758998435055e-07, + "epoch": 0.6949924127465857 + }, + { + "current_steps": 458, + "loss": 2.6202, + "learning_rate": 8.882629107981219e-07, + "epoch": 0.6965098634294385 + }, + { + "current_steps": 459, + "loss": 2.7497, + "learning_rate": 8.879499217527386e-07, + "epoch": 0.6980273141122914 + }, + { + "current_steps": 460, + "loss": 2.5877, + "learning_rate": 8.876369327073552e-07, + "epoch": 0.6995447647951442 + }, + { + "current_steps": 461, + "loss": 2.5484, + "learning_rate": 8.873239436619718e-07, + "epoch": 0.701062215477997 + }, + { + "current_steps": 462, + "loss": 2.9525, + "learning_rate": 8.870109546165884e-07, + "epoch": 0.7025796661608498 + }, + { + "current_steps": 463, + "loss": 2.74, + "learning_rate": 8.86697965571205e-07, + "epoch": 0.7040971168437026 + }, + { + "current_steps": 464, + "loss": 2.9092, + "learning_rate": 8.863849765258216e-07, + "epoch": 0.7056145675265554 + }, + { + "current_steps": 465, + "loss": 2.8179, + "learning_rate": 8.860719874804381e-07, + "epoch": 0.7071320182094082 + }, + { + "current_steps": 466, + "loss": 2.9483, + "learning_rate": 8.857589984350547e-07, + "epoch": 0.708649468892261 + }, + { + "current_steps": 467, + "loss": 2.9366, + "learning_rate": 8.854460093896713e-07, + "epoch": 0.7101669195751138 + }, + { + "current_steps": 468, + "loss": 2.8618, + "learning_rate": 8.851330203442879e-07, + "epoch": 0.7116843702579666 + }, + { + "current_steps": 469, + "loss": 2.7355, + "learning_rate": 8.848200312989045e-07, + "epoch": 0.7132018209408194 + }, + { + "current_steps": 470, + "loss": 2.9608, + "learning_rate": 8.845070422535211e-07, + "epoch": 0.7147192716236722 + }, + { + "current_steps": 471, + "loss": 2.9544, + "learning_rate": 8.841940532081377e-07, + "epoch": 0.716236722306525 + }, + { + "current_steps": 472, + "loss": 2.8978, + "learning_rate": 8.838810641627543e-07, + "epoch": 0.7177541729893778 + }, + { + "current_steps": 473, + "loss": 2.6595, + "learning_rate": 8.835680751173708e-07, + "epoch": 0.7192716236722306 + }, + { + "current_steps": 474, + "loss": 3.0273, + "learning_rate": 8.832550860719874e-07, + "epoch": 0.7207890743550834 + }, + { + "current_steps": 475, + "loss": 2.7609, + "learning_rate": 8.82942097026604e-07, + "epoch": 0.7223065250379362 + }, + { + "current_steps": 476, + "loss": 2.7386, + "learning_rate": 8.826291079812206e-07, + "epoch": 0.723823975720789 + }, + { + "current_steps": 477, + "loss": 2.5596, + "learning_rate": 8.823161189358373e-07, + "epoch": 0.7253414264036419 + }, + { + "current_steps": 478, + "loss": 2.7939, + "learning_rate": 8.820031298904538e-07, + "epoch": 0.7268588770864947 + }, + { + "current_steps": 479, + "loss": 2.7121, + "learning_rate": 8.816901408450705e-07, + "epoch": 0.7283763277693475 + }, + { + "current_steps": 480, + "loss": 2.8556, + "learning_rate": 8.813771517996869e-07, + "epoch": 0.7298937784522003 + }, + { + "current_steps": 481, + "loss": 2.8219, + "learning_rate": 8.810641627543035e-07, + "epoch": 0.7314112291350531 + }, + { + "current_steps": 482, + "loss": 2.725, + "learning_rate": 8.807511737089201e-07, + "epoch": 0.7329286798179059 + }, + { + "current_steps": 483, + "loss": 2.8828, + "learning_rate": 8.804381846635367e-07, + "epoch": 0.7344461305007587 + }, + { + "current_steps": 484, + "loss": 2.7639, + "learning_rate": 8.801251956181534e-07, + "epoch": 0.7359635811836115 + }, + { + "current_steps": 485, + "loss": 2.858, + "learning_rate": 8.798122065727699e-07, + "epoch": 0.7374810318664643 + }, + { + "current_steps": 486, + "loss": 2.9176, + "learning_rate": 8.794992175273866e-07, + "epoch": 0.7389984825493171 + }, + { + "current_steps": 487, + "loss": 2.6871, + "learning_rate": 8.79186228482003e-07, + "epoch": 0.7405159332321699 + }, + { + "current_steps": 488, + "loss": 3.1114, + "learning_rate": 8.788732394366197e-07, + "epoch": 0.7420333839150227 + }, + { + "current_steps": 489, + "loss": 2.8466, + "learning_rate": 8.785602503912363e-07, + "epoch": 0.7435508345978755 + }, + { + "current_steps": 490, + "loss": 2.7808, + "learning_rate": 8.782472613458528e-07, + "epoch": 0.7450682852807283 + }, + { + "current_steps": 491, + "loss": 2.9078, + "learning_rate": 8.779342723004695e-07, + "epoch": 0.7465857359635811 + }, + { + "current_steps": 492, + "loss": 2.9521, + "learning_rate": 8.77621283255086e-07, + "epoch": 0.7481031866464339 + }, + { + "current_steps": 493, + "loss": 2.8252, + "learning_rate": 8.773082942097027e-07, + "epoch": 0.7496206373292867 + }, + { + "current_steps": 494, + "loss": 2.815, + "learning_rate": 8.769953051643191e-07, + "epoch": 0.7511380880121397 + }, + { + "current_steps": 495, + "loss": 2.9195, + "learning_rate": 8.766823161189358e-07, + "epoch": 0.7526555386949925 + }, + { + "current_steps": 496, + "loss": 2.708, + "learning_rate": 8.763693270735524e-07, + "epoch": 0.7541729893778453 + }, + { + "current_steps": 497, + "loss": 3.0399, + "learning_rate": 8.76056338028169e-07, + "epoch": 0.7556904400606981 + }, + { + "current_steps": 498, + "loss": 2.7705, + "learning_rate": 8.757433489827856e-07, + "epoch": 0.7572078907435509 + }, + { + "current_steps": 499, + "loss": 2.6687, + "learning_rate": 8.754303599374021e-07, + "epoch": 0.7587253414264037 + }, + { + "current_steps": 500, + "loss": 2.7734, + "learning_rate": 8.751173708920188e-07, + "epoch": 0.7602427921092565 + }, + { + "current_steps": 501, + "loss": 2.9005, + "learning_rate": 8.748043818466352e-07, + "epoch": 0.7617602427921093 + }, + { + "current_steps": 502, + "loss": 2.6717, + "learning_rate": 8.744913928012519e-07, + "epoch": 0.7632776934749621 + }, + { + "current_steps": 503, + "loss": 2.665, + "learning_rate": 8.741784037558685e-07, + "epoch": 0.7647951441578149 + }, + { + "current_steps": 504, + "loss": 2.8577, + "learning_rate": 8.738654147104851e-07, + "epoch": 0.7663125948406677 + }, + { + "current_steps": 505, + "loss": 2.8069, + "learning_rate": 8.735524256651017e-07, + "epoch": 0.7678300455235205 + }, + { + "current_steps": 506, + "loss": 3.0527, + "learning_rate": 8.732394366197182e-07, + "epoch": 0.7693474962063733 + }, + { + "current_steps": 507, + "loss": 2.7761, + "learning_rate": 8.729264475743349e-07, + "epoch": 0.7708649468892261 + }, + { + "current_steps": 508, + "loss": 2.5835, + "learning_rate": 8.726134585289515e-07, + "epoch": 0.7723823975720789 + }, + { + "current_steps": 509, + "loss": 2.7866, + "learning_rate": 8.72300469483568e-07, + "epoch": 0.7738998482549317 + }, + { + "current_steps": 510, + "loss": 2.7771, + "learning_rate": 8.719874804381846e-07, + "epoch": 0.7754172989377845 + }, + { + "current_steps": 511, + "loss": 2.6448, + "learning_rate": 8.716744913928012e-07, + "epoch": 0.7769347496206374 + }, + { + "current_steps": 512, + "loss": 2.8837, + "learning_rate": 8.713615023474178e-07, + "epoch": 0.7784522003034902 + }, + { + "current_steps": 513, + "loss": 2.7056, + "learning_rate": 8.710485133020344e-07, + "epoch": 0.779969650986343 + }, + { + "current_steps": 514, + "loss": 2.9083, + "learning_rate": 8.70735524256651e-07, + "epoch": 0.7814871016691958 + }, + { + "current_steps": 515, + "loss": 2.6626, + "learning_rate": 8.704225352112676e-07, + "epoch": 0.7830045523520486 + }, + { + "current_steps": 516, + "loss": 2.8557, + "learning_rate": 8.701095461658841e-07, + "epoch": 0.7845220030349014 + }, + { + "current_steps": 517, + "loss": 3.226, + "learning_rate": 8.697965571205007e-07, + "epoch": 0.7860394537177542 + }, + { + "current_steps": 518, + "loss": 2.4786, + "learning_rate": 8.694835680751173e-07, + "epoch": 0.787556904400607 + }, + { + "current_steps": 519, + "loss": 2.636, + "learning_rate": 8.691705790297339e-07, + "epoch": 0.7890743550834598 + }, + { + "current_steps": 520, + "loss": 2.5938, + "learning_rate": 8.688575899843506e-07, + "epoch": 0.7905918057663126 + }, + { + "current_steps": 521, + "loss": 2.6832, + "learning_rate": 8.685446009389671e-07, + "epoch": 0.7921092564491654 + }, + { + "current_steps": 522, + "loss": 2.7169, + "learning_rate": 8.682316118935838e-07, + "epoch": 0.7936267071320182 + }, + { + "current_steps": 523, + "loss": 2.5597, + "learning_rate": 8.679186228482002e-07, + "epoch": 0.795144157814871 + }, + { + "current_steps": 524, + "loss": 2.9073, + "learning_rate": 8.676056338028168e-07, + "epoch": 0.7966616084977238 + }, + { + "current_steps": 525, + "loss": 2.7273, + "learning_rate": 8.672926447574334e-07, + "epoch": 0.7981790591805766 + }, + { + "current_steps": 526, + "loss": 2.7542, + "learning_rate": 8.6697965571205e-07, + "epoch": 0.7996965098634294 + }, + { + "current_steps": 527, + "loss": 3.0509, + "learning_rate": 8.666666666666667e-07, + "epoch": 0.8012139605462822 + }, + { + "current_steps": 528, + "loss": 2.7621, + "learning_rate": 8.663536776212832e-07, + "epoch": 0.802731411229135 + }, + { + "current_steps": 529, + "loss": 2.8424, + "learning_rate": 8.660406885758999e-07, + "epoch": 0.8042488619119879 + }, + { + "current_steps": 530, + "loss": 2.7223, + "learning_rate": 8.657276995305164e-07, + "epoch": 0.8057663125948407 + }, + { + "current_steps": 531, + "loss": 2.3873, + "learning_rate": 8.654147104851329e-07, + "epoch": 0.8072837632776935 + }, + { + "current_steps": 532, + "loss": 2.8396, + "learning_rate": 8.651017214397496e-07, + "epoch": 0.8088012139605463 + }, + { + "current_steps": 533, + "loss": 2.9001, + "learning_rate": 8.647887323943661e-07, + "epoch": 0.8103186646433991 + }, + { + "current_steps": 534, + "loss": 3.0069, + "learning_rate": 8.644757433489828e-07, + "epoch": 0.8118361153262519 + }, + { + "current_steps": 535, + "loss": 2.8878, + "learning_rate": 8.641627543035993e-07, + "epoch": 0.8133535660091047 + }, + { + "current_steps": 536, + "loss": 2.6356, + "learning_rate": 8.63849765258216e-07, + "epoch": 0.8148710166919575 + }, + { + "current_steps": 537, + "loss": 2.8178, + "learning_rate": 8.635367762128325e-07, + "epoch": 0.8163884673748103 + }, + { + "current_steps": 538, + "loss": 2.6943, + "learning_rate": 8.632237871674491e-07, + "epoch": 0.8179059180576631 + }, + { + "current_steps": 539, + "loss": 2.5974, + "learning_rate": 8.629107981220657e-07, + "epoch": 0.8194233687405159 + }, + { + "current_steps": 540, + "loss": 2.7098, + "learning_rate": 8.625978090766822e-07, + "epoch": 0.8209408194233687 + }, + { + "current_steps": 541, + "loss": 2.7607, + "learning_rate": 8.622848200312989e-07, + "epoch": 0.8224582701062215 + }, + { + "current_steps": 542, + "loss": 2.0336, + "learning_rate": 8.619718309859154e-07, + "epoch": 0.8239757207890743 + }, + { + "current_steps": 543, + "loss": 2.4511, + "learning_rate": 8.616588419405321e-07, + "epoch": 0.8254931714719271 + }, + { + "current_steps": 544, + "loss": 2.9017, + "learning_rate": 8.613458528951486e-07, + "epoch": 0.8270106221547799 + }, + { + "current_steps": 545, + "loss": 2.7415, + "learning_rate": 8.610328638497652e-07, + "epoch": 0.8285280728376327 + }, + { + "current_steps": 546, + "loss": 2.8296, + "learning_rate": 8.607198748043818e-07, + "epoch": 0.8300455235204856 + }, + { + "current_steps": 547, + "loss": 2.7855, + "learning_rate": 8.604068857589984e-07, + "epoch": 0.8315629742033384 + }, + { + "current_steps": 548, + "loss": 2.7826, + "learning_rate": 8.60093896713615e-07, + "epoch": 0.8330804248861912 + }, + { + "current_steps": 549, + "loss": 2.8187, + "learning_rate": 8.597809076682315e-07, + "epoch": 0.834597875569044 + }, + { + "current_steps": 550, + "loss": 3.0226, + "learning_rate": 8.594679186228482e-07, + "epoch": 0.8361153262518968 + }, + { + "current_steps": 551, + "loss": 2.6852, + "learning_rate": 8.591549295774648e-07, + "epoch": 0.8376327769347496 + }, + { + "current_steps": 552, + "loss": 2.8641, + "learning_rate": 8.588419405320814e-07, + "epoch": 0.8391502276176024 + }, + { + "current_steps": 553, + "loss": 2.8248, + "learning_rate": 8.585289514866979e-07, + "epoch": 0.8406676783004552 + }, + { + "current_steps": 554, + "loss": 3.0064, + "learning_rate": 8.582159624413145e-07, + "epoch": 0.842185128983308 + }, + { + "current_steps": 555, + "loss": 2.7089, + "learning_rate": 8.579029733959311e-07, + "epoch": 0.8437025796661608 + }, + { + "current_steps": 556, + "loss": 2.6675, + "learning_rate": 8.575899843505477e-07, + "epoch": 0.8452200303490136 + }, + { + "current_steps": 557, + "loss": 2.8839, + "learning_rate": 8.572769953051643e-07, + "epoch": 0.8467374810318664 + }, + { + "current_steps": 558, + "loss": 2.9424, + "learning_rate": 8.569640062597809e-07, + "epoch": 0.8482549317147192 + }, + { + "current_steps": 559, + "loss": 2.8422, + "learning_rate": 8.566510172143975e-07, + "epoch": 0.849772382397572 + }, + { + "current_steps": 560, + "loss": 2.7289, + "learning_rate": 8.56338028169014e-07, + "epoch": 0.8512898330804249 + }, + { + "current_steps": 561, + "loss": 2.7405, + "learning_rate": 8.560250391236306e-07, + "epoch": 0.8528072837632777 + }, + { + "current_steps": 562, + "loss": 2.6102, + "learning_rate": 8.557120500782472e-07, + "epoch": 0.8543247344461306 + }, + { + "current_steps": 563, + "loss": 2.859, + "learning_rate": 8.553990610328639e-07, + "epoch": 0.8558421851289834 + }, + { + "current_steps": 564, + "loss": 2.7302, + "learning_rate": 8.550860719874804e-07, + "epoch": 0.8573596358118362 + }, + { + "current_steps": 565, + "loss": 2.7054, + "learning_rate": 8.54773082942097e-07, + "epoch": 0.858877086494689 + }, + { + "current_steps": 566, + "loss": 2.6915, + "learning_rate": 8.544600938967136e-07, + "epoch": 0.8603945371775418 + }, + { + "current_steps": 567, + "loss": 2.7599, + "learning_rate": 8.541471048513301e-07, + "epoch": 0.8619119878603946 + }, + { + "current_steps": 568, + "loss": 2.8532, + "learning_rate": 8.538341158059467e-07, + "epoch": 0.8634294385432474 + }, + { + "current_steps": 569, + "loss": 2.6993, + "learning_rate": 8.535211267605633e-07, + "epoch": 0.8649468892261002 + }, + { + "current_steps": 570, + "loss": 2.8206, + "learning_rate": 8.5320813771518e-07, + "epoch": 0.866464339908953 + }, + { + "current_steps": 571, + "loss": 2.6908, + "learning_rate": 8.528951486697965e-07, + "epoch": 0.8679817905918058 + }, + { + "current_steps": 572, + "loss": 2.7514, + "learning_rate": 8.525821596244132e-07, + "epoch": 0.8694992412746586 + }, + { + "current_steps": 573, + "loss": 2.8886, + "learning_rate": 8.522691705790297e-07, + "epoch": 0.8710166919575114 + }, + { + "current_steps": 574, + "loss": 2.8766, + "learning_rate": 8.519561815336462e-07, + "epoch": 0.8725341426403642 + }, + { + "current_steps": 575, + "loss": 2.7874, + "learning_rate": 8.516431924882629e-07, + "epoch": 0.874051593323217 + }, + { + "current_steps": 576, + "loss": 2.4636, + "learning_rate": 8.513302034428794e-07, + "epoch": 0.8755690440060698 + }, + { + "current_steps": 577, + "loss": 3.0048, + "learning_rate": 8.510172143974961e-07, + "epoch": 0.8770864946889226 + }, + { + "current_steps": 578, + "loss": 2.5183, + "learning_rate": 8.507042253521126e-07, + "epoch": 0.8786039453717754 + }, + { + "current_steps": 579, + "loss": 2.3303, + "learning_rate": 8.503912363067293e-07, + "epoch": 0.8801213960546282 + }, + { + "current_steps": 580, + "loss": 2.7417, + "learning_rate": 8.500782472613458e-07, + "epoch": 0.881638846737481 + }, + { + "current_steps": 581, + "loss": 2.9567, + "learning_rate": 8.497652582159625e-07, + "epoch": 0.8831562974203339 + }, + { + "current_steps": 582, + "loss": 2.7442, + "learning_rate": 8.49452269170579e-07, + "epoch": 0.8846737481031867 + }, + { + "current_steps": 583, + "loss": 2.2966, + "learning_rate": 8.491392801251955e-07, + "epoch": 0.8861911987860395 + }, + { + "current_steps": 584, + "loss": 2.5882, + "learning_rate": 8.488262910798122e-07, + "epoch": 0.8877086494688923 + }, + { + "current_steps": 585, + "loss": 2.7152, + "learning_rate": 8.485133020344287e-07, + "epoch": 0.8892261001517451 + }, + { + "current_steps": 586, + "loss": 2.9563, + "learning_rate": 8.482003129890454e-07, + "epoch": 0.8907435508345979 + }, + { + "current_steps": 587, + "loss": 2.84, + "learning_rate": 8.478873239436619e-07, + "epoch": 0.8922610015174507 + }, + { + "current_steps": 588, + "loss": 2.8859, + "learning_rate": 8.475743348982786e-07, + "epoch": 0.8937784522003035 + }, + { + "current_steps": 589, + "loss": 2.6066, + "learning_rate": 8.472613458528951e-07, + "epoch": 0.8952959028831563 + }, + { + "current_steps": 590, + "loss": 2.7734, + "learning_rate": 8.469483568075116e-07, + "epoch": 0.8968133535660091 + }, + { + "current_steps": 591, + "loss": 2.6567, + "learning_rate": 8.466353677621283e-07, + "epoch": 0.8983308042488619 + }, + { + "current_steps": 592, + "loss": 2.9967, + "learning_rate": 8.463223787167448e-07, + "epoch": 0.8998482549317147 + }, + { + "current_steps": 593, + "loss": 2.8681, + "learning_rate": 8.460093896713615e-07, + "epoch": 0.9013657056145675 + }, + { + "current_steps": 594, + "loss": 2.6945, + "learning_rate": 8.456964006259781e-07, + "epoch": 0.9028831562974203 + }, + { + "current_steps": 595, + "loss": 2.8062, + "learning_rate": 8.453834115805947e-07, + "epoch": 0.9044006069802731 + }, + { + "current_steps": 596, + "loss": 2.7389, + "learning_rate": 8.450704225352112e-07, + "epoch": 0.9059180576631259 + }, + { + "current_steps": 597, + "loss": 2.7413, + "learning_rate": 8.447574334898278e-07, + "epoch": 0.9074355083459787 + }, + { + "current_steps": 598, + "loss": 2.6592, + "learning_rate": 8.444444444444444e-07, + "epoch": 0.9089529590288316 + }, + { + "current_steps": 599, + "loss": 2.5343, + "learning_rate": 8.441314553990609e-07, + "epoch": 0.9104704097116844 + }, + { + "current_steps": 600, + "loss": 2.4053, + "learning_rate": 8.438184663536776e-07, + "epoch": 0.9119878603945372 + }, + { + "current_steps": 601, + "loss": 2.6896, + "learning_rate": 8.435054773082942e-07, + "epoch": 0.91350531107739 + }, + { + "current_steps": 602, + "loss": 2.7394, + "learning_rate": 8.431924882629108e-07, + "epoch": 0.9150227617602428 + }, + { + "current_steps": 603, + "loss": 2.6742, + "learning_rate": 8.428794992175273e-07, + "epoch": 0.9165402124430956 + }, + { + "current_steps": 604, + "loss": 2.7276, + "learning_rate": 8.425665101721439e-07, + "epoch": 0.9180576631259484 + }, + { + "current_steps": 605, + "loss": 2.5785, + "learning_rate": 8.422535211267605e-07, + "epoch": 0.9195751138088012 + }, + { + "current_steps": 606, + "loss": 2.7324, + "learning_rate": 8.419405320813772e-07, + "epoch": 0.921092564491654 + }, + { + "current_steps": 607, + "loss": 2.6245, + "learning_rate": 8.416275430359937e-07, + "epoch": 0.9226100151745068 + }, + { + "current_steps": 608, + "loss": 2.6536, + "learning_rate": 8.413145539906103e-07, + "epoch": 0.9241274658573596 + }, + { + "current_steps": 609, + "loss": 2.6916, + "learning_rate": 8.410015649452269e-07, + "epoch": 0.9256449165402124 + }, + { + "current_steps": 610, + "loss": 2.9629, + "learning_rate": 8.406885758998435e-07, + "epoch": 0.9271623672230652 + }, + { + "current_steps": 611, + "loss": 2.8472, + "learning_rate": 8.4037558685446e-07, + "epoch": 0.928679817905918 + }, + { + "current_steps": 612, + "loss": 2.468, + "learning_rate": 8.400625978090766e-07, + "epoch": 0.9301972685887708 + }, + { + "current_steps": 613, + "loss": 2.7389, + "learning_rate": 8.397496087636933e-07, + "epoch": 0.9317147192716236 + }, + { + "current_steps": 614, + "loss": 2.846, + "learning_rate": 8.394366197183098e-07, + "epoch": 0.9332321699544764 + }, + { + "current_steps": 615, + "loss": 2.7779, + "learning_rate": 8.391236306729265e-07, + "epoch": 0.9347496206373292 + }, + { + "current_steps": 616, + "loss": 2.5376, + "learning_rate": 8.38810641627543e-07, + "epoch": 0.936267071320182 + }, + { + "current_steps": 617, + "loss": 2.9947, + "learning_rate": 8.384976525821596e-07, + "epoch": 0.9377845220030349 + }, + { + "current_steps": 618, + "loss": 2.6561, + "learning_rate": 8.381846635367761e-07, + "epoch": 0.9393019726858877 + }, + { + "current_steps": 619, + "loss": 2.8268, + "learning_rate": 8.378716744913927e-07, + "epoch": 0.9408194233687405 + }, + { + "current_steps": 620, + "loss": 2.8756, + "learning_rate": 8.375586854460094e-07, + "epoch": 0.9423368740515933 + }, + { + "current_steps": 621, + "loss": 2.9151, + "learning_rate": 8.372456964006259e-07, + "epoch": 0.9438543247344461 + }, + { + "current_steps": 622, + "loss": 2.7237, + "learning_rate": 8.369327073552426e-07, + "epoch": 0.9453717754172989 + }, + { + "current_steps": 623, + "loss": 2.272, + "learning_rate": 8.366197183098591e-07, + "epoch": 0.9468892261001517 + }, + { + "current_steps": 624, + "loss": 2.9197, + "learning_rate": 8.363067292644757e-07, + "epoch": 0.9484066767830045 + }, + { + "current_steps": 625, + "loss": 2.5405, + "learning_rate": 8.359937402190923e-07, + "epoch": 0.9499241274658573 + }, + { + "current_steps": 626, + "loss": 2.7868, + "learning_rate": 8.356807511737088e-07, + "epoch": 0.9514415781487102 + }, + { + "current_steps": 627, + "loss": 2.6399, + "learning_rate": 8.353677621283255e-07, + "epoch": 0.952959028831563 + }, + { + "current_steps": 628, + "loss": 2.5033, + "learning_rate": 8.35054773082942e-07, + "epoch": 0.9544764795144158 + }, + { + "current_steps": 629, + "loss": 2.6476, + "learning_rate": 8.347417840375587e-07, + "epoch": 0.9559939301972686 + }, + { + "current_steps": 630, + "loss": 2.6161, + "learning_rate": 8.344287949921752e-07, + "epoch": 0.9575113808801214 + }, + { + "current_steps": 631, + "loss": 2.9137, + "learning_rate": 8.341158059467919e-07, + "epoch": 0.9590288315629742 + }, + { + "current_steps": 632, + "loss": 3.0193, + "learning_rate": 8.338028169014085e-07, + "epoch": 0.960546282245827 + }, + { + "current_steps": 633, + "loss": 2.7694, + "learning_rate": 8.334898278560249e-07, + "epoch": 0.9620637329286799 + }, + { + "current_steps": 634, + "loss": 2.9557, + "learning_rate": 8.331768388106416e-07, + "epoch": 0.9635811836115327 + }, + { + "current_steps": 635, + "loss": 2.9484, + "learning_rate": 8.328638497652581e-07, + "epoch": 0.9650986342943855 + }, + { + "current_steps": 636, + "loss": 3.0272, + "learning_rate": 8.325508607198748e-07, + "epoch": 0.9666160849772383 + }, + { + "current_steps": 637, + "loss": 2.838, + "learning_rate": 8.322378716744914e-07, + "epoch": 0.9681335356600911 + }, + { + "current_steps": 638, + "loss": 2.7086, + "learning_rate": 8.31924882629108e-07, + "epoch": 0.9696509863429439 + }, + { + "current_steps": 639, + "loss": 2.5959, + "learning_rate": 8.316118935837246e-07, + "epoch": 0.9711684370257967 + }, + { + "current_steps": 640, + "loss": 2.6347, + "learning_rate": 8.312989045383411e-07, + "epoch": 0.9726858877086495 + }, + { + "current_steps": 641, + "loss": 2.874, + "learning_rate": 8.309859154929577e-07, + "epoch": 0.9742033383915023 + }, + { + "current_steps": 642, + "loss": 2.7139, + "learning_rate": 8.306729264475742e-07, + "epoch": 0.9757207890743551 + }, + { + "current_steps": 643, + "loss": 2.3057, + "learning_rate": 8.303599374021909e-07, + "epoch": 0.9772382397572079 + }, + { + "current_steps": 644, + "loss": 2.7353, + "learning_rate": 8.300469483568075e-07, + "epoch": 0.9787556904400607 + }, + { + "current_steps": 645, + "loss": 2.5498, + "learning_rate": 8.297339593114241e-07, + "epoch": 0.9802731411229135 + }, + { + "current_steps": 646, + "loss": 2.8912, + "learning_rate": 8.294209702660407e-07, + "epoch": 0.9817905918057663 + }, + { + "current_steps": 647, + "loss": 2.8417, + "learning_rate": 8.291079812206572e-07, + "epoch": 0.9833080424886191 + }, + { + "current_steps": 648, + "loss": 2.804, + "learning_rate": 8.287949921752738e-07, + "epoch": 0.9848254931714719 + }, + { + "current_steps": 649, + "loss": 2.4255, + "learning_rate": 8.284820031298903e-07, + "epoch": 0.9863429438543247 + }, + { + "current_steps": 650, + "loss": 2.4969, + "learning_rate": 8.28169014084507e-07, + "epoch": 0.9878603945371776 + }, + { + "current_steps": 651, + "loss": 2.701, + "learning_rate": 8.278560250391236e-07, + "epoch": 0.9893778452200304 + }, + { + "current_steps": 652, + "loss": 2.6623, + "learning_rate": 8.275430359937402e-07, + "epoch": 0.9908952959028832 + }, + { + "current_steps": 653, + "loss": 2.6653, + "learning_rate": 8.272300469483568e-07, + "epoch": 0.992412746585736 + }, + { + "current_steps": 654, + "loss": 2.7632, + "learning_rate": 8.269170579029733e-07, + "epoch": 0.9939301972685888 + }, + { + "current_steps": 655, + "loss": 2.8107, + "learning_rate": 8.266040688575899e-07, + "epoch": 0.9954476479514416 + }, + { + "current_steps": 656, + "loss": 2.7726, + "learning_rate": 8.262910798122066e-07, + "epoch": 0.9969650986342944 + }, + { + "current_steps": 657, + "loss": 2.7334, + "learning_rate": 8.259780907668231e-07, + "epoch": 0.9984825493171472 + }, + { + "current_steps": 658, + "loss": 3.1185, + "learning_rate": 8.256651017214397e-07, + "epoch": 1.0 + }, + { + "current_steps": 659, + "loss": 2.7057, + "learning_rate": 8.253521126760563e-07, + "epoch": 1.0015174506828528 + }, + { + "current_steps": 660, + "loss": 2.7552, + "learning_rate": 8.250391236306729e-07, + "epoch": 1.0030349013657056 + }, + { + "current_steps": 661, + "loss": 2.798, + "learning_rate": 8.247261345852894e-07, + "epoch": 1.0045523520485584 + }, + { + "current_steps": 662, + "loss": 2.7356, + "learning_rate": 8.24413145539906e-07, + "epoch": 1.0060698027314112 + }, + { + "current_steps": 663, + "loss": 2.7291, + "learning_rate": 8.241001564945227e-07, + "epoch": 1.007587253414264 + }, + { + "current_steps": 664, + "loss": 2.737, + "learning_rate": 8.237871674491392e-07, + "epoch": 1.0091047040971168 + }, + { + "current_steps": 665, + "loss": 2.6458, + "learning_rate": 8.234741784037559e-07, + "epoch": 1.0106221547799696 + }, + { + "current_steps": 666, + "loss": 2.7598, + "learning_rate": 8.231611893583724e-07, + "epoch": 1.0121396054628224 + }, + { + "current_steps": 667, + "loss": 2.5427, + "learning_rate": 8.22848200312989e-07, + "epoch": 1.0136570561456753 + }, + { + "current_steps": 668, + "loss": 2.4963, + "learning_rate": 8.225352112676057e-07, + "epoch": 1.015174506828528 + }, + { + "current_steps": 669, + "loss": 2.8477, + "learning_rate": 8.222222222222221e-07, + "epoch": 1.0166919575113809 + }, + { + "current_steps": 670, + "loss": 2.6976, + "learning_rate": 8.219092331768388e-07, + "epoch": 1.0182094081942337 + }, + { + "current_steps": 671, + "loss": 2.7528, + "learning_rate": 8.215962441314553e-07, + "epoch": 1.0197268588770865 + }, + { + "current_steps": 672, + "loss": 2.8939, + "learning_rate": 8.21283255086072e-07, + "epoch": 1.0212443095599393 + }, + { + "current_steps": 673, + "loss": 2.8181, + "learning_rate": 8.209702660406885e-07, + "epoch": 1.022761760242792 + }, + { + "current_steps": 674, + "loss": 2.2642, + "learning_rate": 8.206572769953052e-07, + "epoch": 1.024279210925645 + }, + { + "current_steps": 675, + "loss": 2.6724, + "learning_rate": 8.203442879499218e-07, + "epoch": 1.0257966616084977 + }, + { + "current_steps": 676, + "loss": 2.704, + "learning_rate": 8.200312989045382e-07, + "epoch": 1.0273141122913505 + }, + { + "current_steps": 677, + "loss": 2.6456, + "learning_rate": 8.197183098591549e-07, + "epoch": 1.0288315629742033 + }, + { + "current_steps": 678, + "loss": 2.5683, + "learning_rate": 8.194053208137714e-07, + "epoch": 1.0303490136570561 + }, + { + "current_steps": 679, + "loss": 2.6557, + "learning_rate": 8.190923317683881e-07, + "epoch": 1.031866464339909 + }, + { + "current_steps": 680, + "loss": 2.6801, + "learning_rate": 8.187793427230047e-07, + "epoch": 1.0333839150227617 + }, + { + "current_steps": 681, + "loss": 2.7235, + "learning_rate": 8.184663536776213e-07, + "epoch": 1.0349013657056145 + }, + { + "current_steps": 682, + "loss": 2.8182, + "learning_rate": 8.181533646322379e-07, + "epoch": 1.0364188163884673 + }, + { + "current_steps": 683, + "loss": 2.7622, + "learning_rate": 8.178403755868543e-07, + "epoch": 1.0379362670713201 + }, + { + "current_steps": 684, + "loss": 2.8101, + "learning_rate": 8.17527386541471e-07, + "epoch": 1.039453717754173 + }, + { + "current_steps": 685, + "loss": 2.7924, + "learning_rate": 8.172143974960875e-07, + "epoch": 1.0409711684370258 + }, + { + "current_steps": 686, + "loss": 2.8767, + "learning_rate": 8.169014084507042e-07, + "epoch": 1.0424886191198786 + }, + { + "current_steps": 687, + "loss": 2.6496, + "learning_rate": 8.165884194053208e-07, + "epoch": 1.0440060698027314 + }, + { + "current_steps": 688, + "loss": 2.8342, + "learning_rate": 8.162754303599374e-07, + "epoch": 1.0455235204855842 + }, + { + "current_steps": 689, + "loss": 2.7823, + "learning_rate": 8.15962441314554e-07, + "epoch": 1.047040971168437 + }, + { + "current_steps": 690, + "loss": 2.8568, + "learning_rate": 8.156494522691706e-07, + "epoch": 1.0485584218512898 + }, + { + "current_steps": 691, + "loss": 2.646, + "learning_rate": 8.153364632237871e-07, + "epoch": 1.0500758725341426 + }, + { + "current_steps": 692, + "loss": 3.0355, + "learning_rate": 8.150234741784036e-07, + "epoch": 1.0515933232169954 + }, + { + "current_steps": 693, + "loss": 2.8073, + "learning_rate": 8.147104851330203e-07, + "epoch": 1.0531107738998482 + }, + { + "current_steps": 694, + "loss": 2.764, + "learning_rate": 8.143974960876369e-07, + "epoch": 1.054628224582701 + }, + { + "current_steps": 695, + "loss": 2.8828, + "learning_rate": 8.140845070422535e-07, + "epoch": 1.0561456752655538 + }, + { + "current_steps": 696, + "loss": 2.5166, + "learning_rate": 8.137715179968701e-07, + "epoch": 1.0576631259484066 + }, + { + "current_steps": 697, + "loss": 2.5047, + "learning_rate": 8.134585289514867e-07, + "epoch": 1.0591805766312594 + }, + { + "current_steps": 698, + "loss": 2.9513, + "learning_rate": 8.131455399061032e-07, + "epoch": 1.0606980273141122 + }, + { + "current_steps": 699, + "loss": 2.7962, + "learning_rate": 8.128325508607199e-07, + "epoch": 1.062215477996965 + }, + { + "current_steps": 700, + "loss": 2.9232, + "learning_rate": 8.125195618153364e-07, + "epoch": 1.0637329286798178 + }, + { + "current_steps": 701, + "loss": 2.6966, + "learning_rate": 8.12206572769953e-07, + "epoch": 1.0652503793626706 + }, + { + "current_steps": 702, + "loss": 2.7763, + "learning_rate": 8.118935837245696e-07, + "epoch": 1.0667678300455234 + }, + { + "current_steps": 703, + "loss": 2.5419, + "learning_rate": 8.115805946791862e-07, + "epoch": 1.0682852807283763 + }, + { + "current_steps": 704, + "loss": 2.3603, + "learning_rate": 8.112676056338028e-07, + "epoch": 1.069802731411229 + }, + { + "current_steps": 705, + "loss": 2.7678, + "learning_rate": 8.109546165884193e-07, + "epoch": 1.0713201820940819 + }, + { + "current_steps": 706, + "loss": 2.9878, + "learning_rate": 8.10641627543036e-07, + "epoch": 1.0728376327769347 + }, + { + "current_steps": 707, + "loss": 2.7143, + "learning_rate": 8.103286384976525e-07, + "epoch": 1.0743550834597875 + }, + { + "current_steps": 708, + "loss": 2.6862, + "learning_rate": 8.100156494522691e-07, + "epoch": 1.0758725341426403 + }, + { + "current_steps": 709, + "loss": 2.8759, + "learning_rate": 8.097026604068857e-07, + "epoch": 1.077389984825493 + }, + { + "current_steps": 710, + "loss": 2.8472, + "learning_rate": 8.093896713615023e-07, + "epoch": 1.078907435508346 + }, + { + "current_steps": 711, + "loss": 3.1544, + "learning_rate": 8.09076682316119e-07, + "epoch": 1.0804248861911987 + }, + { + "current_steps": 712, + "loss": 2.6725, + "learning_rate": 8.087636932707354e-07, + "epoch": 1.0819423368740515 + }, + { + "current_steps": 713, + "loss": 2.7206, + "learning_rate": 8.084507042253521e-07, + "epoch": 1.0834597875569043 + }, + { + "current_steps": 714, + "loss": 2.1061, + "learning_rate": 8.081377151799686e-07, + "epoch": 1.0849772382397571 + }, + { + "current_steps": 715, + "loss": 2.5851, + "learning_rate": 8.078247261345853e-07, + "epoch": 1.08649468892261 + }, + { + "current_steps": 716, + "loss": 2.6752, + "learning_rate": 8.075117370892018e-07, + "epoch": 1.0880121396054627 + }, + { + "current_steps": 717, + "loss": 2.6798, + "learning_rate": 8.071987480438184e-07, + "epoch": 1.0895295902883155 + }, + { + "current_steps": 718, + "loss": 2.601, + "learning_rate": 8.068857589984351e-07, + "epoch": 1.0910470409711683 + }, + { + "current_steps": 719, + "loss": 2.9763, + "learning_rate": 8.065727699530515e-07, + "epoch": 1.0925644916540211 + }, + { + "current_steps": 720, + "loss": 2.6629, + "learning_rate": 8.062597809076682e-07, + "epoch": 1.094081942336874 + }, + { + "current_steps": 721, + "loss": 2.8952, + "learning_rate": 8.059467918622847e-07, + "epoch": 1.095599393019727 + }, + { + "current_steps": 722, + "loss": 2.6739, + "learning_rate": 8.056338028169014e-07, + "epoch": 1.0971168437025796 + }, + { + "current_steps": 723, + "loss": 2.7147, + "learning_rate": 8.05320813771518e-07, + "epoch": 1.0986342943854326 + }, + { + "current_steps": 724, + "loss": 2.7167, + "learning_rate": 8.050078247261346e-07, + "epoch": 1.1001517450682852 + }, + { + "current_steps": 725, + "loss": 2.8604, + "learning_rate": 8.046948356807512e-07, + "epoch": 1.1016691957511382 + }, + { + "current_steps": 726, + "loss": 2.915, + "learning_rate": 8.043818466353677e-07, + "epoch": 1.1031866464339908 + }, + { + "current_steps": 727, + "loss": 2.0438, + "learning_rate": 8.040688575899843e-07, + "epoch": 1.1047040971168438 + }, + { + "current_steps": 728, + "loss": 2.6652, + "learning_rate": 8.037558685446008e-07, + "epoch": 1.1062215477996964 + }, + { + "current_steps": 729, + "loss": 2.7911, + "learning_rate": 8.034428794992175e-07, + "epoch": 1.1077389984825494 + }, + { + "current_steps": 730, + "loss": 2.7155, + "learning_rate": 8.031298904538341e-07, + "epoch": 1.1092564491654022 + }, + { + "current_steps": 731, + "loss": 2.5602, + "learning_rate": 8.028169014084507e-07, + "epoch": 1.110773899848255 + }, + { + "current_steps": 732, + "loss": 2.8246, + "learning_rate": 8.025039123630673e-07, + "epoch": 1.1122913505311078 + }, + { + "current_steps": 733, + "loss": 2.8333, + "learning_rate": 8.021909233176839e-07, + "epoch": 1.1138088012139606 + }, + { + "current_steps": 734, + "loss": 2.598, + "learning_rate": 8.018779342723004e-07, + "epoch": 1.1153262518968134 + }, + { + "current_steps": 735, + "loss": 3.045, + "learning_rate": 8.015649452269169e-07, + "epoch": 1.1168437025796663 + }, + { + "current_steps": 736, + "loss": 2.6799, + "learning_rate": 8.012519561815336e-07, + "epoch": 1.118361153262519 + }, + { + "current_steps": 737, + "loss": 2.6636, + "learning_rate": 8.009389671361502e-07, + "epoch": 1.1198786039453719 + }, + { + "current_steps": 738, + "loss": 2.639, + "learning_rate": 8.006259780907668e-07, + "epoch": 1.1213960546282247 + }, + { + "current_steps": 739, + "loss": 2.6914, + "learning_rate": 8.003129890453834e-07, + "epoch": 1.1229135053110775 + }, + { + "current_steps": 740, + "loss": 2.7469, + "learning_rate": 8e-07, + "epoch": 1.1244309559939303 + }, + { + "current_steps": 741, + "loss": 2.8245, + "learning_rate": 7.996870109546165e-07, + "epoch": 1.125948406676783 + }, + { + "current_steps": 742, + "loss": 2.6604, + "learning_rate": 7.993740219092331e-07, + "epoch": 1.127465857359636 + }, + { + "current_steps": 743, + "loss": 2.8339, + "learning_rate": 7.990610328638497e-07, + "epoch": 1.1289833080424887 + }, + { + "current_steps": 744, + "loss": 2.9505, + "learning_rate": 7.987480438184663e-07, + "epoch": 1.1305007587253415 + }, + { + "current_steps": 745, + "loss": 2.8184, + "learning_rate": 7.984350547730829e-07, + "epoch": 1.1320182094081943 + }, + { + "current_steps": 746, + "loss": 2.5736, + "learning_rate": 7.981220657276995e-07, + "epoch": 1.1335356600910471 + }, + { + "current_steps": 747, + "loss": 2.9925, + "learning_rate": 7.978090766823161e-07, + "epoch": 1.1350531107739 + }, + { + "current_steps": 748, + "loss": 2.7954, + "learning_rate": 7.974960876369327e-07, + "epoch": 1.1365705614567527 + }, + { + "current_steps": 749, + "loss": 2.9514, + "learning_rate": 7.971830985915493e-07, + "epoch": 1.1380880121396055 + }, + { + "current_steps": 750, + "loss": 2.7304, + "learning_rate": 7.968701095461658e-07, + "epoch": 1.1396054628224583 + }, + { + "current_steps": 751, + "loss": 2.071, + "learning_rate": 7.965571205007824e-07, + "epoch": 1.1411229135053111 + }, + { + "current_steps": 752, + "loss": 2.7606, + "learning_rate": 7.96244131455399e-07, + "epoch": 1.142640364188164 + }, + { + "current_steps": 753, + "loss": 2.7711, + "learning_rate": 7.959311424100156e-07, + "epoch": 1.1441578148710168 + }, + { + "current_steps": 754, + "loss": 2.4568, + "learning_rate": 7.956181533646323e-07, + "epoch": 1.1456752655538696 + }, + { + "current_steps": 755, + "loss": 2.57, + "learning_rate": 7.953051643192488e-07, + "epoch": 1.1471927162367224 + }, + { + "current_steps": 756, + "loss": 2.8447, + "learning_rate": 7.949921752738654e-07, + "epoch": 1.1487101669195752 + }, + { + "current_steps": 757, + "loss": 2.9067, + "learning_rate": 7.946791862284819e-07, + "epoch": 1.150227617602428 + }, + { + "current_steps": 758, + "loss": 2.7521, + "learning_rate": 7.943661971830986e-07, + "epoch": 1.1517450682852808 + }, + { + "current_steps": 759, + "loss": 2.8471, + "learning_rate": 7.940532081377151e-07, + "epoch": 1.1532625189681336 + }, + { + "current_steps": 760, + "loss": 2.8127, + "learning_rate": 7.937402190923317e-07, + "epoch": 1.1547799696509864 + }, + { + "current_steps": 761, + "loss": 2.6924, + "learning_rate": 7.934272300469484e-07, + "epoch": 1.1562974203338392 + }, + { + "current_steps": 762, + "loss": 2.6936, + "learning_rate": 7.931142410015649e-07, + "epoch": 1.157814871016692 + }, + { + "current_steps": 763, + "loss": 2.741, + "learning_rate": 7.928012519561816e-07, + "epoch": 1.1593323216995448 + }, + { + "current_steps": 764, + "loss": 2.9293, + "learning_rate": 7.92488262910798e-07, + "epoch": 1.1608497723823976 + }, + { + "current_steps": 765, + "loss": 2.8469, + "learning_rate": 7.921752738654147e-07, + "epoch": 1.1623672230652504 + }, + { + "current_steps": 766, + "loss": 2.6381, + "learning_rate": 7.918622848200313e-07, + "epoch": 1.1638846737481032 + }, + { + "current_steps": 767, + "loss": 2.8847, + "learning_rate": 7.915492957746478e-07, + "epoch": 1.165402124430956 + }, + { + "current_steps": 768, + "loss": 2.7676, + "learning_rate": 7.912363067292645e-07, + "epoch": 1.1669195751138088 + }, + { + "current_steps": 769, + "loss": 2.6735, + "learning_rate": 7.90923317683881e-07, + "epoch": 1.1684370257966616 + }, + { + "current_steps": 770, + "loss": 2.7414, + "learning_rate": 7.906103286384977e-07, + "epoch": 1.1699544764795144 + }, + { + "current_steps": 771, + "loss": 2.6967, + "learning_rate": 7.902973395931141e-07, + "epoch": 1.1714719271623673 + }, + { + "current_steps": 772, + "loss": 2.774, + "learning_rate": 7.899843505477308e-07, + "epoch": 1.17298937784522 + }, + { + "current_steps": 773, + "loss": 2.7336, + "learning_rate": 7.896713615023474e-07, + "epoch": 1.1745068285280729 + }, + { + "current_steps": 774, + "loss": 2.6652, + "learning_rate": 7.89358372456964e-07, + "epoch": 1.1760242792109257 + }, + { + "current_steps": 775, + "loss": 3.0065, + "learning_rate": 7.890453834115806e-07, + "epoch": 1.1775417298937785 + }, + { + "current_steps": 776, + "loss": 2.9583, + "learning_rate": 7.887323943661971e-07, + "epoch": 1.1790591805766313 + }, + { + "current_steps": 777, + "loss": 2.7213, + "learning_rate": 7.884194053208138e-07, + "epoch": 1.180576631259484 + }, + { + "current_steps": 778, + "loss": 2.5227, + "learning_rate": 7.881064162754302e-07, + "epoch": 1.182094081942337 + }, + { + "current_steps": 779, + "loss": 2.5755, + "learning_rate": 7.877934272300469e-07, + "epoch": 1.1836115326251897 + }, + { + "current_steps": 780, + "loss": 2.663, + "learning_rate": 7.874804381846635e-07, + "epoch": 1.1851289833080425 + }, + { + "current_steps": 781, + "loss": 2.6369, + "learning_rate": 7.871674491392801e-07, + "epoch": 1.1866464339908953 + }, + { + "current_steps": 782, + "loss": 2.5819, + "learning_rate": 7.868544600938967e-07, + "epoch": 1.1881638846737481 + }, + { + "current_steps": 783, + "loss": 2.8346, + "learning_rate": 7.865414710485133e-07, + "epoch": 1.189681335356601 + }, + { + "current_steps": 784, + "loss": 2.6973, + "learning_rate": 7.862284820031299e-07, + "epoch": 1.1911987860394537 + }, + { + "current_steps": 785, + "loss": 2.7975, + "learning_rate": 7.859154929577464e-07, + "epoch": 1.1927162367223065 + }, + { + "current_steps": 786, + "loss": 2.8321, + "learning_rate": 7.85602503912363e-07, + "epoch": 1.1942336874051593 + }, + { + "current_steps": 787, + "loss": 2.604, + "learning_rate": 7.852895148669796e-07, + "epoch": 1.1957511380880121 + }, + { + "current_steps": 788, + "loss": 2.7276, + "learning_rate": 7.849765258215962e-07, + "epoch": 1.197268588770865 + }, + { + "current_steps": 789, + "loss": 2.681, + "learning_rate": 7.846635367762128e-07, + "epoch": 1.1987860394537178 + }, + { + "current_steps": 790, + "loss": 2.885, + "learning_rate": 7.843505477308294e-07, + "epoch": 1.2003034901365706 + }, + { + "current_steps": 791, + "loss": 2.5433, + "learning_rate": 7.84037558685446e-07, + "epoch": 1.2018209408194234 + }, + { + "current_steps": 792, + "loss": 2.7894, + "learning_rate": 7.837245696400627e-07, + "epoch": 1.2033383915022762 + }, + { + "current_steps": 793, + "loss": 2.6237, + "learning_rate": 7.834115805946791e-07, + "epoch": 1.204855842185129 + }, + { + "current_steps": 794, + "loss": 2.2351, + "learning_rate": 7.830985915492957e-07, + "epoch": 1.2063732928679818 + }, + { + "current_steps": 795, + "loss": 2.8594, + "learning_rate": 7.827856025039123e-07, + "epoch": 1.2078907435508346 + }, + { + "current_steps": 796, + "loss": 2.6416, + "learning_rate": 7.824726134585289e-07, + "epoch": 1.2094081942336874 + }, + { + "current_steps": 797, + "loss": 2.6586, + "learning_rate": 7.821596244131456e-07, + "epoch": 1.2109256449165402 + }, + { + "current_steps": 798, + "loss": 2.9739, + "learning_rate": 7.818466353677621e-07, + "epoch": 1.212443095599393 + }, + { + "current_steps": 799, + "loss": 2.4439, + "learning_rate": 7.815336463223788e-07, + "epoch": 1.2139605462822458 + }, + { + "current_steps": 800, + "loss": 2.7472, + "learning_rate": 7.812206572769952e-07, + "epoch": 1.2154779969650986 + }, + { + "current_steps": 801, + "loss": 2.4462, + "learning_rate": 7.809076682316118e-07, + "epoch": 1.2169954476479514 + }, + { + "current_steps": 802, + "loss": 2.7813, + "learning_rate": 7.805946791862284e-07, + "epoch": 1.2185128983308042 + }, + { + "current_steps": 803, + "loss": 2.9486, + "learning_rate": 7.80281690140845e-07, + "epoch": 1.220030349013657 + }, + { + "current_steps": 804, + "loss": 2.5001, + "learning_rate": 7.799687010954617e-07, + "epoch": 1.2215477996965098 + }, + { + "current_steps": 805, + "loss": 2.6083, + "learning_rate": 7.796557120500782e-07, + "epoch": 1.2230652503793626 + }, + { + "current_steps": 806, + "loss": 2.1391, + "learning_rate": 7.793427230046949e-07, + "epoch": 1.2245827010622155 + }, + { + "current_steps": 807, + "loss": 2.5552, + "learning_rate": 7.790297339593113e-07, + "epoch": 1.2261001517450683 + }, + { + "current_steps": 808, + "loss": 2.7472, + "learning_rate": 7.78716744913928e-07, + "epoch": 1.227617602427921 + }, + { + "current_steps": 809, + "loss": 2.8669, + "learning_rate": 7.784037558685446e-07, + "epoch": 1.2291350531107739 + }, + { + "current_steps": 810, + "loss": 2.7228, + "learning_rate": 7.780907668231611e-07, + "epoch": 1.2306525037936267 + }, + { + "current_steps": 811, + "loss": 2.5973, + "learning_rate": 7.777777777777778e-07, + "epoch": 1.2321699544764795 + }, + { + "current_steps": 812, + "loss": 2.6296, + "learning_rate": 7.774647887323943e-07, + "epoch": 1.2336874051593323 + }, + { + "current_steps": 813, + "loss": 2.5037, + "learning_rate": 7.77151799687011e-07, + "epoch": 1.235204855842185 + }, + { + "current_steps": 814, + "loss": 2.8852, + "learning_rate": 7.768388106416274e-07, + "epoch": 1.236722306525038 + }, + { + "current_steps": 815, + "loss": 2.5322, + "learning_rate": 7.765258215962441e-07, + "epoch": 1.2382397572078907 + }, + { + "current_steps": 816, + "loss": 2.5904, + "learning_rate": 7.762128325508607e-07, + "epoch": 1.2397572078907435 + }, + { + "current_steps": 817, + "loss": 2.993, + "learning_rate": 7.758998435054773e-07, + "epoch": 1.2412746585735963 + }, + { + "current_steps": 818, + "loss": 2.9536, + "learning_rate": 7.755868544600939e-07, + "epoch": 1.2427921092564491 + }, + { + "current_steps": 819, + "loss": 2.7338, + "learning_rate": 7.752738654147104e-07, + "epoch": 1.244309559939302 + }, + { + "current_steps": 820, + "loss": 2.5743, + "learning_rate": 7.749608763693271e-07, + "epoch": 1.2458270106221547 + }, + { + "current_steps": 821, + "loss": 2.4991, + "learning_rate": 7.746478873239435e-07, + "epoch": 1.2473444613050075 + }, + { + "current_steps": 822, + "loss": 2.7027, + "learning_rate": 7.743348982785602e-07, + "epoch": 1.2488619119878603 + }, + { + "current_steps": 823, + "loss": 2.8969, + "learning_rate": 7.740219092331768e-07, + "epoch": 1.2503793626707131 + }, + { + "current_steps": 824, + "loss": 2.5454, + "learning_rate": 7.737089201877934e-07, + "epoch": 1.251896813353566 + }, + { + "current_steps": 825, + "loss": 2.5529, + "learning_rate": 7.7339593114241e-07, + "epoch": 1.2534142640364188 + }, + { + "current_steps": 826, + "loss": 2.5815, + "learning_rate": 7.730829420970265e-07, + "epoch": 1.2549317147192716 + }, + { + "current_steps": 827, + "loss": 2.7021, + "learning_rate": 7.727699530516432e-07, + "epoch": 1.2564491654021244 + }, + { + "current_steps": 828, + "loss": 2.9294, + "learning_rate": 7.724569640062598e-07, + "epoch": 1.2579666160849772 + }, + { + "current_steps": 829, + "loss": 2.6426, + "learning_rate": 7.721439749608763e-07, + "epoch": 1.25948406676783 + }, + { + "current_steps": 830, + "loss": 2.6154, + "learning_rate": 7.718309859154929e-07, + "epoch": 1.2610015174506828 + }, + { + "current_steps": 831, + "loss": 2.6634, + "learning_rate": 7.715179968701095e-07, + "epoch": 1.2625189681335356 + }, + { + "current_steps": 832, + "loss": 2.6702, + "learning_rate": 7.712050078247261e-07, + "epoch": 1.2640364188163884 + }, + { + "current_steps": 833, + "loss": 2.7721, + "learning_rate": 7.708920187793427e-07, + "epoch": 1.2655538694992412 + }, + { + "current_steps": 834, + "loss": 2.6019, + "learning_rate": 7.705790297339593e-07, + "epoch": 1.267071320182094 + }, + { + "current_steps": 835, + "loss": 2.7685, + "learning_rate": 7.702660406885759e-07, + "epoch": 1.2685887708649468 + }, + { + "current_steps": 836, + "loss": 2.8552, + "learning_rate": 7.699530516431924e-07, + "epoch": 1.2701062215477996 + }, + { + "current_steps": 837, + "loss": 2.7018, + "learning_rate": 7.69640062597809e-07, + "epoch": 1.2716236722306524 + }, + { + "current_steps": 838, + "loss": 2.9055, + "learning_rate": 7.693270735524256e-07, + "epoch": 1.2731411229135052 + }, + { + "current_steps": 839, + "loss": 2.8331, + "learning_rate": 7.690140845070422e-07, + "epoch": 1.274658573596358 + }, + { + "current_steps": 840, + "loss": 2.6895, + "learning_rate": 7.687010954616589e-07, + "epoch": 1.276176024279211 + }, + { + "current_steps": 841, + "loss": 2.9731, + "learning_rate": 7.683881064162754e-07, + "epoch": 1.2776934749620636 + }, + { + "current_steps": 842, + "loss": 2.6102, + "learning_rate": 7.680751173708921e-07, + "epoch": 1.2792109256449167 + }, + { + "current_steps": 843, + "loss": 2.7169, + "learning_rate": 7.677621283255085e-07, + "epoch": 1.2807283763277693 + }, + { + "current_steps": 844, + "loss": 2.7231, + "learning_rate": 7.674491392801251e-07, + "epoch": 1.2822458270106223 + }, + { + "current_steps": 845, + "loss": 2.7346, + "learning_rate": 7.671361502347417e-07, + "epoch": 1.2837632776934749 + }, + { + "current_steps": 846, + "loss": 2.7808, + "learning_rate": 7.668231611893583e-07, + "epoch": 1.285280728376328 + }, + { + "current_steps": 847, + "loss": 2.8719, + "learning_rate": 7.66510172143975e-07, + "epoch": 1.2867981790591805 + }, + { + "current_steps": 848, + "loss": 2.7533, + "learning_rate": 7.661971830985915e-07, + "epoch": 1.2883156297420335 + }, + { + "current_steps": 849, + "loss": 2.7282, + "learning_rate": 7.658841940532082e-07, + "epoch": 1.289833080424886 + }, + { + "current_steps": 850, + "loss": 2.9163, + "learning_rate": 7.655712050078246e-07, + "epoch": 1.2913505311077391 + }, + { + "current_steps": 851, + "loss": 2.7587, + "learning_rate": 7.652582159624413e-07, + "epoch": 1.2928679817905917 + }, + { + "current_steps": 852, + "loss": 2.7221, + "learning_rate": 7.649452269170578e-07, + "epoch": 1.2943854324734447 + }, + { + "current_steps": 853, + "loss": 2.8139, + "learning_rate": 7.646322378716744e-07, + "epoch": 1.2959028831562973 + }, + { + "current_steps": 854, + "loss": 2.6771, + "learning_rate": 7.643192488262911e-07, + "epoch": 1.2974203338391503 + }, + { + "current_steps": 855, + "loss": 2.527, + "learning_rate": 7.640062597809076e-07, + "epoch": 1.298937784522003 + }, + { + "current_steps": 856, + "loss": 2.7963, + "learning_rate": 7.636932707355243e-07, + "epoch": 1.300455235204856 + }, + { + "current_steps": 857, + "loss": 2.5161, + "learning_rate": 7.633802816901408e-07, + "epoch": 1.3019726858877085 + }, + { + "current_steps": 858, + "loss": 2.5378, + "learning_rate": 7.630672926447574e-07, + "epoch": 1.3034901365705616 + }, + { + "current_steps": 859, + "loss": 2.6306, + "learning_rate": 7.62754303599374e-07, + "epoch": 1.3050075872534141 + }, + { + "current_steps": 860, + "loss": 2.5669, + "learning_rate": 7.624413145539905e-07, + "epoch": 1.3065250379362672 + }, + { + "current_steps": 861, + "loss": 2.6092, + "learning_rate": 7.621283255086072e-07, + "epoch": 1.3080424886191198 + }, + { + "current_steps": 862, + "loss": 2.7438, + "learning_rate": 7.618153364632237e-07, + "epoch": 1.3095599393019728 + }, + { + "current_steps": 863, + "loss": 2.6369, + "learning_rate": 7.615023474178404e-07, + "epoch": 1.3110773899848254 + }, + { + "current_steps": 864, + "loss": 3.0088, + "learning_rate": 7.611893583724569e-07, + "epoch": 1.3125948406676784 + }, + { + "current_steps": 865, + "loss": 2.1511, + "learning_rate": 7.608763693270735e-07, + "epoch": 1.314112291350531 + }, + { + "current_steps": 866, + "loss": 2.652, + "learning_rate": 7.605633802816901e-07, + "epoch": 1.315629742033384 + }, + { + "current_steps": 867, + "loss": 2.6005, + "learning_rate": 7.602503912363067e-07, + "epoch": 1.3171471927162366 + }, + { + "current_steps": 868, + "loss": 2.8148, + "learning_rate": 7.599374021909233e-07, + "epoch": 1.3186646433990896 + }, + { + "current_steps": 869, + "loss": 2.5553, + "learning_rate": 7.596244131455398e-07, + "epoch": 1.3201820940819422 + }, + { + "current_steps": 870, + "loss": 2.7712, + "learning_rate": 7.593114241001565e-07, + "epoch": 1.3216995447647952 + }, + { + "current_steps": 871, + "loss": 2.6649, + "learning_rate": 7.589984350547731e-07, + "epoch": 1.3232169954476478 + }, + { + "current_steps": 872, + "loss": 2.7309, + "learning_rate": 7.586854460093896e-07, + "epoch": 1.3247344461305008 + }, + { + "current_steps": 873, + "loss": 2.5561, + "learning_rate": 7.583724569640062e-07, + "epoch": 1.3262518968133536 + }, + { + "current_steps": 874, + "loss": 2.7506, + "learning_rate": 7.580594679186228e-07, + "epoch": 1.3277693474962065 + }, + { + "current_steps": 875, + "loss": 2.609, + "learning_rate": 7.577464788732394e-07, + "epoch": 1.3292867981790593 + }, + { + "current_steps": 876, + "loss": 2.6948, + "learning_rate": 7.57433489827856e-07, + "epoch": 1.330804248861912 + }, + { + "current_steps": 877, + "loss": 1.9532, + "learning_rate": 7.571205007824726e-07, + "epoch": 1.3323216995447649 + }, + { + "current_steps": 878, + "loss": 2.7331, + "learning_rate": 7.568075117370892e-07, + "epoch": 1.3338391502276177 + }, + { + "current_steps": 879, + "loss": 2.7003, + "learning_rate": 7.564945226917058e-07, + "epoch": 1.3353566009104705 + }, + { + "current_steps": 880, + "loss": 2.678, + "learning_rate": 7.561815336463223e-07, + "epoch": 1.3368740515933233 + }, + { + "current_steps": 881, + "loss": 2.7248, + "learning_rate": 7.558685446009389e-07, + "epoch": 1.338391502276176 + }, + { + "current_steps": 882, + "loss": 2.8826, + "learning_rate": 7.555555555555555e-07, + "epoch": 1.339908952959029 + }, + { + "current_steps": 883, + "loss": 2.6218, + "learning_rate": 7.552425665101722e-07, + "epoch": 1.3414264036418817 + }, + { + "current_steps": 884, + "loss": 2.7633, + "learning_rate": 7.549295774647887e-07, + "epoch": 1.3429438543247345 + }, + { + "current_steps": 885, + "loss": 2.7806, + "learning_rate": 7.546165884194053e-07, + "epoch": 1.3444613050075873 + }, + { + "current_steps": 886, + "loss": 2.6857, + "learning_rate": 7.543035993740219e-07, + "epoch": 1.3459787556904401 + }, + { + "current_steps": 887, + "loss": 2.4855, + "learning_rate": 7.539906103286384e-07, + "epoch": 1.347496206373293 + }, + { + "current_steps": 888, + "loss": 2.9157, + "learning_rate": 7.53677621283255e-07, + "epoch": 1.3490136570561457 + }, + { + "current_steps": 889, + "loss": 2.4755, + "learning_rate": 7.533646322378716e-07, + "epoch": 1.3505311077389985 + }, + { + "current_steps": 890, + "loss": 2.9141, + "learning_rate": 7.530516431924883e-07, + "epoch": 1.3520485584218513 + }, + { + "current_steps": 891, + "loss": 2.7298, + "learning_rate": 7.527386541471048e-07, + "epoch": 1.3535660091047041 + }, + { + "current_steps": 892, + "loss": 2.53, + "learning_rate": 7.524256651017215e-07, + "epoch": 1.355083459787557 + }, + { + "current_steps": 893, + "loss": 2.7494, + "learning_rate": 7.52112676056338e-07, + "epoch": 1.3566009104704098 + }, + { + "current_steps": 894, + "loss": 2.727, + "learning_rate": 7.517996870109545e-07, + "epoch": 1.3581183611532626 + }, + { + "current_steps": 895, + "loss": 2.7195, + "learning_rate": 7.514866979655711e-07, + "epoch": 1.3596358118361154 + }, + { + "current_steps": 896, + "loss": 2.6381, + "learning_rate": 7.511737089201877e-07, + "epoch": 1.3611532625189682 + }, + { + "current_steps": 897, + "loss": 2.7653, + "learning_rate": 7.508607198748044e-07, + "epoch": 1.362670713201821 + }, + { + "current_steps": 898, + "loss": 2.7519, + "learning_rate": 7.505477308294209e-07, + "epoch": 1.3641881638846738 + }, + { + "current_steps": 899, + "loss": 2.6321, + "learning_rate": 7.502347417840376e-07, + "epoch": 1.3657056145675266 + }, + { + "current_steps": 900, + "loss": 2.6347, + "learning_rate": 7.499217527386541e-07, + "epoch": 1.3672230652503794 + }, + { + "current_steps": 901, + "loss": 2.8999, + "learning_rate": 7.496087636932708e-07, + "epoch": 1.3687405159332322 + }, + { + "current_steps": 902, + "loss": 2.8223, + "learning_rate": 7.492957746478873e-07, + "epoch": 1.370257966616085 + }, + { + "current_steps": 903, + "loss": 2.8066, + "learning_rate": 7.489827856025038e-07, + "epoch": 1.3717754172989378 + }, + { + "current_steps": 904, + "loss": 2.5432, + "learning_rate": 7.486697965571205e-07, + "epoch": 1.3732928679817906 + }, + { + "current_steps": 905, + "loss": 2.6699, + "learning_rate": 7.48356807511737e-07, + "epoch": 1.3748103186646434 + }, + { + "current_steps": 906, + "loss": 2.3712, + "learning_rate": 7.480438184663537e-07, + "epoch": 1.3763277693474962 + }, + { + "current_steps": 907, + "loss": 2.8259, + "learning_rate": 7.477308294209702e-07, + "epoch": 1.377845220030349 + }, + { + "current_steps": 908, + "loss": 2.8271, + "learning_rate": 7.474178403755869e-07, + "epoch": 1.3793626707132018 + }, + { + "current_steps": 909, + "loss": 2.7287, + "learning_rate": 7.471048513302034e-07, + "epoch": 1.3808801213960546 + }, + { + "current_steps": 910, + "loss": 2.5147, + "learning_rate": 7.4679186228482e-07, + "epoch": 1.3823975720789075 + }, + { + "current_steps": 911, + "loss": 2.8739, + "learning_rate": 7.464788732394366e-07, + "epoch": 1.3839150227617603 + }, + { + "current_steps": 912, + "loss": 2.478, + "learning_rate": 7.461658841940531e-07, + "epoch": 1.385432473444613 + }, + { + "current_steps": 913, + "loss": 2.7046, + "learning_rate": 7.458528951486698e-07, + "epoch": 1.3869499241274659 + }, + { + "current_steps": 914, + "loss": 2.716, + "learning_rate": 7.455399061032864e-07, + "epoch": 1.3884673748103187 + }, + { + "current_steps": 915, + "loss": 2.5921, + "learning_rate": 7.45226917057903e-07, + "epoch": 1.3899848254931715 + }, + { + "current_steps": 916, + "loss": 2.6932, + "learning_rate": 7.449139280125195e-07, + "epoch": 1.3915022761760243 + }, + { + "current_steps": 917, + "loss": 2.6604, + "learning_rate": 7.446009389671361e-07, + "epoch": 1.393019726858877 + }, + { + "current_steps": 918, + "loss": 2.6854, + "learning_rate": 7.442879499217527e-07, + "epoch": 1.39453717754173 + }, + { + "current_steps": 919, + "loss": 2.5896, + "learning_rate": 7.439749608763692e-07, + "epoch": 1.3960546282245827 + }, + { + "current_steps": 920, + "loss": 2.6665, + "learning_rate": 7.436619718309859e-07, + "epoch": 1.3975720789074355 + }, + { + "current_steps": 921, + "loss": 2.7608, + "learning_rate": 7.433489827856025e-07, + "epoch": 1.3990895295902883 + }, + { + "current_steps": 922, + "loss": 2.6149, + "learning_rate": 7.430359937402191e-07, + "epoch": 1.4006069802731411 + }, + { + "current_steps": 923, + "loss": 2.7345, + "learning_rate": 7.427230046948356e-07, + "epoch": 1.402124430955994 + }, + { + "current_steps": 924, + "loss": 2.8129, + "learning_rate": 7.424100156494522e-07, + "epoch": 1.4036418816388467 + }, + { + "current_steps": 925, + "loss": 2.6727, + "learning_rate": 7.420970266040688e-07, + "epoch": 1.4051593323216995 + }, + { + "current_steps": 926, + "loss": 2.9032, + "learning_rate": 7.417840375586855e-07, + "epoch": 1.4066767830045523 + }, + { + "current_steps": 927, + "loss": 2.6112, + "learning_rate": 7.41471048513302e-07, + "epoch": 1.4081942336874052 + }, + { + "current_steps": 928, + "loss": 2.8483, + "learning_rate": 7.411580594679186e-07, + "epoch": 1.409711684370258 + }, + { + "current_steps": 929, + "loss": 2.66, + "learning_rate": 7.408450704225352e-07, + "epoch": 1.4112291350531108 + }, + { + "current_steps": 930, + "loss": 2.9426, + "learning_rate": 7.405320813771517e-07, + "epoch": 1.4127465857359636 + }, + { + "current_steps": 931, + "loss": 2.8566, + "learning_rate": 7.402190923317683e-07, + "epoch": 1.4142640364188164 + }, + { + "current_steps": 932, + "loss": 2.2733, + "learning_rate": 7.399061032863849e-07, + "epoch": 1.4157814871016692 + }, + { + "current_steps": 933, + "loss": 2.8355, + "learning_rate": 7.395931142410016e-07, + "epoch": 1.417298937784522 + }, + { + "current_steps": 934, + "loss": 2.769, + "learning_rate": 7.392801251956181e-07, + "epoch": 1.4188163884673748 + }, + { + "current_steps": 935, + "loss": 2.3641, + "learning_rate": 7.389671361502348e-07, + "epoch": 1.4203338391502276 + }, + { + "current_steps": 936, + "loss": 2.7396, + "learning_rate": 7.386541471048513e-07, + "epoch": 1.4218512898330804 + }, + { + "current_steps": 937, + "loss": 2.5938, + "learning_rate": 7.383411580594679e-07, + "epoch": 1.4233687405159332 + }, + { + "current_steps": 938, + "loss": 2.8148, + "learning_rate": 7.380281690140844e-07, + "epoch": 1.424886191198786 + }, + { + "current_steps": 939, + "loss": 2.5963, + "learning_rate": 7.37715179968701e-07, + "epoch": 1.4264036418816388 + }, + { + "current_steps": 940, + "loss": 2.1212, + "learning_rate": 7.374021909233177e-07, + "epoch": 1.4279210925644916 + }, + { + "current_steps": 941, + "loss": 2.9409, + "learning_rate": 7.370892018779342e-07, + "epoch": 1.4294385432473444 + }, + { + "current_steps": 942, + "loss": 2.6343, + "learning_rate": 7.367762128325509e-07, + "epoch": 1.4309559939301972 + }, + { + "current_steps": 943, + "loss": 2.6366, + "learning_rate": 7.364632237871674e-07, + "epoch": 1.43247344461305 + }, + { + "current_steps": 944, + "loss": 2.6837, + "learning_rate": 7.361502347417841e-07, + "epoch": 1.4339908952959028 + }, + { + "current_steps": 945, + "loss": 2.5518, + "learning_rate": 7.358372456964006e-07, + "epoch": 1.4355083459787557 + }, + { + "current_steps": 946, + "loss": 2.5757, + "learning_rate": 7.355242566510171e-07, + "epoch": 1.4370257966616085 + }, + { + "current_steps": 947, + "loss": 2.7608, + "learning_rate": 7.352112676056338e-07, + "epoch": 1.4385432473444613 + }, + { + "current_steps": 948, + "loss": 2.6995, + "learning_rate": 7.348982785602503e-07, + "epoch": 1.440060698027314 + }, + { + "current_steps": 949, + "loss": 2.6631, + "learning_rate": 7.34585289514867e-07, + "epoch": 1.4415781487101669 + }, + { + "current_steps": 950, + "loss": 2.7499, + "learning_rate": 7.342723004694835e-07, + "epoch": 1.4430955993930197 + }, + { + "current_steps": 951, + "loss": 2.6441, + "learning_rate": 7.339593114241002e-07, + "epoch": 1.4446130500758725 + }, + { + "current_steps": 952, + "loss": 2.5668, + "learning_rate": 7.336463223787167e-07, + "epoch": 1.4461305007587253 + }, + { + "current_steps": 953, + "loss": 2.4801, + "learning_rate": 7.333333333333332e-07, + "epoch": 1.447647951441578 + }, + { + "current_steps": 954, + "loss": 2.6358, + "learning_rate": 7.330203442879499e-07, + "epoch": 1.449165402124431 + }, + { + "current_steps": 955, + "loss": 2.7393, + "learning_rate": 7.327073552425664e-07, + "epoch": 1.4506828528072837 + }, + { + "current_steps": 956, + "loss": 2.6734, + "learning_rate": 7.323943661971831e-07, + "epoch": 1.4522003034901365 + }, + { + "current_steps": 957, + "loss": 2.8628, + "learning_rate": 7.320813771517997e-07, + "epoch": 1.4537177541729893 + }, + { + "current_steps": 958, + "loss": 2.7713, + "learning_rate": 7.317683881064163e-07, + "epoch": 1.4552352048558421 + }, + { + "current_steps": 959, + "loss": 2.9002, + "learning_rate": 7.314553990610329e-07, + "epoch": 1.456752655538695 + }, + { + "current_steps": 960, + "loss": 2.9065, + "learning_rate": 7.311424100156494e-07, + "epoch": 1.4582701062215477 + }, + { + "current_steps": 961, + "loss": 2.7094, + "learning_rate": 7.30829420970266e-07, + "epoch": 1.4597875569044005 + }, + { + "current_steps": 962, + "loss": 2.494, + "learning_rate": 7.305164319248825e-07, + "epoch": 1.4613050075872533 + }, + { + "current_steps": 963, + "loss": 2.6684, + "learning_rate": 7.302034428794992e-07, + "epoch": 1.4628224582701062 + }, + { + "current_steps": 964, + "loss": 2.3032, + "learning_rate": 7.298904538341158e-07, + "epoch": 1.464339908952959 + }, + { + "current_steps": 965, + "loss": 2.7739, + "learning_rate": 7.295774647887324e-07, + "epoch": 1.4658573596358118 + }, + { + "current_steps": 966, + "loss": 2.7013, + "learning_rate": 7.29264475743349e-07, + "epoch": 1.4673748103186646 + }, + { + "current_steps": 967, + "loss": 2.8356, + "learning_rate": 7.289514866979655e-07, + "epoch": 1.4688922610015174 + }, + { + "current_steps": 968, + "loss": 2.6803, + "learning_rate": 7.286384976525821e-07, + "epoch": 1.4704097116843702 + }, + { + "current_steps": 969, + "loss": 2.6546, + "learning_rate": 7.283255086071988e-07, + "epoch": 1.471927162367223 + }, + { + "current_steps": 970, + "loss": 2.7258, + "learning_rate": 7.280125195618153e-07, + "epoch": 1.4734446130500758 + }, + { + "current_steps": 971, + "loss": 2.4845, + "learning_rate": 7.276995305164319e-07, + "epoch": 1.4749620637329286 + }, + { + "current_steps": 972, + "loss": 2.7182, + "learning_rate": 7.273865414710485e-07, + "epoch": 1.4764795144157814 + }, + { + "current_steps": 973, + "loss": 2.8969, + "learning_rate": 7.270735524256651e-07, + "epoch": 1.4779969650986344 + }, + { + "current_steps": 974, + "loss": 2.7522, + "learning_rate": 7.270735524256651e-07, + "epoch": 1.479514415781487 + }, + { + "current_steps": 975, + "loss": 2.5234, + "learning_rate": 7.267605633802816e-07, + "epoch": 1.48103186646434 + }, + { + "current_steps": 976, + "loss": 2.8098, + "learning_rate": 7.264475743348982e-07, + "epoch": 1.4825493171471926 + }, + { + "current_steps": 977, + "loss": 2.6767, + "learning_rate": 7.261345852895149e-07, + "epoch": 1.4840667678300457 + }, + { + "current_steps": 978, + "loss": 2.7842, + "learning_rate": 7.258215962441314e-07, + "epoch": 1.4855842185128982 + }, + { + "current_steps": 979, + "loss": 2.617, + "learning_rate": 7.25508607198748e-07, + "epoch": 1.4871016691957513 + }, + { + "current_steps": 980, + "loss": 2.7097, + "learning_rate": 7.251956181533646e-07, + "epoch": 1.4886191198786038 + }, + { + "current_steps": 981, + "loss": 2.8353, + "learning_rate": 7.248826291079812e-07, + "epoch": 1.4901365705614569 + }, + { + "current_steps": 982, + "loss": 1.9958, + "learning_rate": 7.245696400625977e-07, + "epoch": 1.4916540212443095 + }, + { + "current_steps": 983, + "loss": 2.9299, + "learning_rate": 7.242566510172143e-07, + "epoch": 1.4931714719271625 + }, + { + "current_steps": 984, + "loss": 2.3206, + "learning_rate": 7.23943661971831e-07, + "epoch": 1.494688922610015 + }, + { + "current_steps": 985, + "loss": 2.5987, + "learning_rate": 7.236306729264475e-07, + "epoch": 1.496206373292868 + }, + { + "current_steps": 986, + "loss": 2.7211, + "learning_rate": 7.233176838810642e-07, + "epoch": 1.4977238239757207 + }, + { + "current_steps": 987, + "loss": 2.7347, + "learning_rate": 7.230046948356807e-07, + "epoch": 1.4992412746585737 + }, + { + "current_steps": 988, + "loss": 2.7535, + "learning_rate": 7.226917057902973e-07, + "epoch": 1.5007587253414263 + }, + { + "current_steps": 989, + "loss": 2.9188, + "learning_rate": 7.22378716744914e-07, + "epoch": 1.5022761760242793 + }, + { + "current_steps": 990, + "loss": 2.5641, + "learning_rate": 7.220657276995304e-07, + "epoch": 1.503793626707132 + }, + { + "current_steps": 991, + "loss": 2.5115, + "learning_rate": 7.217527386541471e-07, + "epoch": 1.505311077389985 + }, + { + "current_steps": 992, + "loss": 2.6486, + "learning_rate": 7.214397496087636e-07, + "epoch": 1.5068285280728375 + }, + { + "current_steps": 993, + "loss": 2.6257, + "learning_rate": 7.211267605633803e-07, + "epoch": 1.5083459787556905 + }, + { + "current_steps": 994, + "loss": 2.6885, + "learning_rate": 7.208137715179968e-07, + "epoch": 1.5098634294385431 + }, + { + "current_steps": 995, + "loss": 2.9251, + "learning_rate": 7.205007824726135e-07, + "epoch": 1.5113808801213962 + }, + { + "current_steps": 996, + "loss": 2.5704, + "learning_rate": 7.201877934272301e-07, + "epoch": 1.5128983308042487 + }, + { + "current_steps": 997, + "loss": 2.8099, + "learning_rate": 7.198748043818465e-07, + "epoch": 1.5144157814871018 + }, + { + "current_steps": 998, + "loss": 2.5017, + "learning_rate": 7.195618153364632e-07, + "epoch": 1.5159332321699543 + }, + { + "current_steps": 999, + "loss": 2.6836, + "learning_rate": 7.192488262910797e-07, + "epoch": 1.5174506828528074 + }, + { + "current_steps": 1000, + "loss": 2.5946, + "learning_rate": 7.189358372456964e-07, + "epoch": 1.51896813353566 + }, + { + "current_steps": 1001, + "loss": 2.8715, + "learning_rate": 7.18622848200313e-07, + "epoch": 1.520485584218513 + }, + { + "current_steps": 1002, + "loss": 2.6067, + "learning_rate": 7.183098591549296e-07, + "epoch": 1.5220030349013656 + }, + { + "current_steps": 1003, + "loss": 2.8158, + "learning_rate": 7.179968701095462e-07, + "epoch": 1.5235204855842186 + }, + { + "current_steps": 1004, + "loss": 2.4538, + "learning_rate": 7.176838810641627e-07, + "epoch": 1.5250379362670712 + }, + { + "current_steps": 1005, + "loss": 2.4622, + "learning_rate": 7.173708920187793e-07, + "epoch": 1.5265553869499242 + }, + { + "current_steps": 1006, + "loss": 2.7296, + "learning_rate": 7.170579029733958e-07, + "epoch": 1.5280728376327768 + }, + { + "current_steps": 1007, + "loss": 2.4219, + "learning_rate": 7.167449139280125e-07, + "epoch": 1.5295902883156298 + }, + { + "current_steps": 1008, + "loss": 2.5217, + "learning_rate": 7.164319248826291e-07, + "epoch": 1.5311077389984824 + }, + { + "current_steps": 1009, + "loss": 2.6156, + "learning_rate": 7.161189358372457e-07, + "epoch": 1.5326251896813354 + }, + { + "current_steps": 1010, + "loss": 2.776, + "learning_rate": 7.158059467918623e-07, + "epoch": 1.534142640364188 + }, + { + "current_steps": 1011, + "loss": 2.7688, + "learning_rate": 7.154929577464788e-07, + "epoch": 1.535660091047041 + }, + { + "current_steps": 1012, + "loss": 2.8672, + "learning_rate": 7.151799687010954e-07, + "epoch": 1.5371775417298936 + }, + { + "current_steps": 1013, + "loss": 2.8609, + "learning_rate": 7.148669796557119e-07, + "epoch": 1.5386949924127467 + }, + { + "current_steps": 1014, + "loss": 2.6494, + "learning_rate": 7.145539906103286e-07, + "epoch": 1.5402124430955992 + }, + { + "current_steps": 1015, + "loss": 2.698, + "learning_rate": 7.142410015649452e-07, + "epoch": 1.5417298937784523 + }, + { + "current_steps": 1016, + "loss": 2.7061, + "learning_rate": 7.139280125195618e-07, + "epoch": 1.5432473444613048 + }, + { + "current_steps": 1017, + "loss": 2.6843, + "learning_rate": 7.136150234741784e-07, + "epoch": 1.5447647951441579 + }, + { + "current_steps": 1018, + "loss": 2.7602, + "learning_rate": 7.13302034428795e-07, + "epoch": 1.5462822458270105 + }, + { + "current_steps": 1019, + "loss": 2.6079, + "learning_rate": 7.129890453834115e-07, + "epoch": 1.5477996965098635 + }, + { + "current_steps": 1020, + "loss": 2.7211, + "learning_rate": 7.126760563380282e-07, + "epoch": 1.549317147192716 + }, + { + "current_steps": 1021, + "loss": 2.8559, + "learning_rate": 7.123630672926447e-07, + "epoch": 1.550834597875569 + }, + { + "current_steps": 1022, + "loss": 2.8248, + "learning_rate": 7.120500782472613e-07, + "epoch": 1.552352048558422 + }, + { + "current_steps": 1023, + "loss": 2.8104, + "learning_rate": 7.117370892018779e-07, + "epoch": 1.5538694992412747 + }, + { + "current_steps": 1024, + "loss": 2.6465, + "learning_rate": 7.114241001564945e-07, + "epoch": 1.5553869499241275 + }, + { + "current_steps": 1025, + "loss": 2.9654, + "learning_rate": 7.111111111111111e-07, + "epoch": 1.5569044006069803 + }, + { + "current_steps": 1026, + "loss": 2.1261, + "learning_rate": 7.107981220657276e-07, + "epoch": 1.5584218512898331 + }, + { + "current_steps": 1027, + "loss": 2.5719, + "learning_rate": 7.104851330203443e-07, + "epoch": 1.559939301972686 + }, + { + "current_steps": 1028, + "loss": 2.6063, + "learning_rate": 7.101721439749608e-07, + "epoch": 1.5614567526555387 + }, + { + "current_steps": 1029, + "loss": 2.5984, + "learning_rate": 7.098591549295775e-07, + "epoch": 1.5629742033383915 + }, + { + "current_steps": 1030, + "loss": 2.7813, + "learning_rate": 7.09546165884194e-07, + "epoch": 1.5644916540212443 + }, + { + "current_steps": 1031, + "loss": 2.6231, + "learning_rate": 7.092331768388106e-07, + "epoch": 1.5660091047040972 + }, + { + "current_steps": 1032, + "loss": 2.6253, + "learning_rate": 7.089201877934273e-07, + "epoch": 1.56752655538695 + }, + { + "current_steps": 1033, + "loss": 2.5131, + "learning_rate": 7.086071987480437e-07, + "epoch": 1.5690440060698028 + }, + { + "current_steps": 1034, + "loss": 2.5393, + "learning_rate": 7.082942097026604e-07, + "epoch": 1.5705614567526556 + }, + { + "current_steps": 1035, + "loss": 2.5708, + "learning_rate": 7.079812206572769e-07, + "epoch": 1.5720789074355084 + }, + { + "current_steps": 1036, + "loss": 2.6677, + "learning_rate": 7.076682316118936e-07, + "epoch": 1.5735963581183612 + }, + { + "current_steps": 1037, + "loss": 2.5183, + "learning_rate": 7.073552425665101e-07, + "epoch": 1.575113808801214 + }, + { + "current_steps": 1038, + "loss": 2.5671, + "learning_rate": 7.070422535211267e-07, + "epoch": 1.5766312594840668 + }, + { + "current_steps": 1039, + "loss": 2.7826, + "learning_rate": 7.067292644757434e-07, + "epoch": 1.5781487101669196 + }, + { + "current_steps": 1040, + "loss": 2.5686, + "learning_rate": 7.064162754303598e-07, + "epoch": 1.5796661608497724 + }, + { + "current_steps": 1041, + "loss": 2.7554, + "learning_rate": 7.061032863849765e-07, + "epoch": 1.5811836115326252 + }, + { + "current_steps": 1042, + "loss": 2.6948, + "learning_rate": 7.05790297339593e-07, + "epoch": 1.582701062215478 + }, + { + "current_steps": 1043, + "loss": 2.6002, + "learning_rate": 7.054773082942097e-07, + "epoch": 1.5842185128983308 + }, + { + "current_steps": 1044, + "loss": 2.5512, + "learning_rate": 7.051643192488263e-07, + "epoch": 1.5857359635811836 + }, + { + "current_steps": 1045, + "loss": 2.4634, + "learning_rate": 7.048513302034429e-07, + "epoch": 1.5872534142640364 + }, + { + "current_steps": 1046, + "loss": 2.5413, + "learning_rate": 7.045383411580595e-07, + "epoch": 1.5887708649468892 + }, + { + "current_steps": 1047, + "loss": 2.6958, + "learning_rate": 7.04225352112676e-07, + "epoch": 1.590288315629742 + }, + { + "current_steps": 1048, + "loss": 2.6714, + "learning_rate": 7.039123630672926e-07, + "epoch": 1.5918057663125948 + }, + { + "current_steps": 1049, + "loss": 2.9981, + "learning_rate": 7.035993740219091e-07, + "epoch": 1.5933232169954477 + }, + { + "current_steps": 1050, + "loss": 2.786, + "learning_rate": 7.032863849765258e-07, + "epoch": 1.5948406676783005 + }, + { + "current_steps": 1051, + "loss": 2.2378, + "learning_rate": 7.029733959311424e-07, + "epoch": 1.5963581183611533 + }, + { + "current_steps": 1052, + "loss": 2.5998, + "learning_rate": 7.02660406885759e-07, + "epoch": 1.597875569044006 + }, + { + "current_steps": 1053, + "loss": 2.7531, + "learning_rate": 7.023474178403756e-07, + "epoch": 1.5993930197268589 + }, + { + "current_steps": 1054, + "loss": 2.5211, + "learning_rate": 7.020344287949922e-07, + "epoch": 1.6009104704097117 + }, + { + "current_steps": 1055, + "loss": 2.7422, + "learning_rate": 7.017214397496087e-07, + "epoch": 1.6024279210925645 + }, + { + "current_steps": 1056, + "loss": 2.6342, + "learning_rate": 7.014084507042252e-07, + "epoch": 1.6039453717754173 + }, + { + "current_steps": 1057, + "loss": 2.9074, + "learning_rate": 7.010954616588419e-07, + "epoch": 1.60546282245827 + }, + { + "current_steps": 1058, + "loss": 2.6133, + "learning_rate": 7.007824726134585e-07, + "epoch": 1.606980273141123 + }, + { + "current_steps": 1059, + "loss": 2.6418, + "learning_rate": 7.004694835680751e-07, + "epoch": 1.6084977238239757 + }, + { + "current_steps": 1060, + "loss": 2.6543, + "learning_rate": 7.001564945226917e-07, + "epoch": 1.6100151745068285 + }, + { + "current_steps": 1061, + "loss": 2.746, + "learning_rate": 6.998435054773083e-07, + "epoch": 1.6115326251896813 + }, + { + "current_steps": 1062, + "loss": 2.716, + "learning_rate": 6.995305164319248e-07, + "epoch": 1.6130500758725341 + }, + { + "current_steps": 1063, + "loss": 2.738, + "learning_rate": 6.992175273865415e-07, + "epoch": 1.614567526555387 + }, + { + "current_steps": 1064, + "loss": 2.6846, + "learning_rate": 6.98904538341158e-07, + "epoch": 1.6160849772382397 + }, + { + "current_steps": 1065, + "loss": 2.7593, + "learning_rate": 6.985915492957746e-07, + "epoch": 1.6176024279210925 + }, + { + "current_steps": 1066, + "loss": 2.7258, + "learning_rate": 6.982785602503912e-07, + "epoch": 1.6191198786039454 + }, + { + "current_steps": 1067, + "loss": 3.0366, + "learning_rate": 6.979655712050078e-07, + "epoch": 1.6206373292867982 + }, + { + "current_steps": 1068, + "loss": 2.7345, + "learning_rate": 6.976525821596244e-07, + "epoch": 1.622154779969651 + }, + { + "current_steps": 1069, + "loss": 2.7627, + "learning_rate": 6.97339593114241e-07, + "epoch": 1.6236722306525038 + }, + { + "current_steps": 1070, + "loss": 2.5909, + "learning_rate": 6.970266040688576e-07, + "epoch": 1.6251896813353566 + }, + { + "current_steps": 1071, + "loss": 2.588, + "learning_rate": 6.967136150234741e-07, + "epoch": 1.6267071320182094 + }, + { + "current_steps": 1072, + "loss": 2.5667, + "learning_rate": 6.964006259780907e-07, + "epoch": 1.6282245827010622 + }, + { + "current_steps": 1073, + "loss": 2.514, + "learning_rate": 6.960876369327073e-07, + "epoch": 1.629742033383915 + }, + { + "current_steps": 1074, + "loss": 2.5923, + "learning_rate": 6.957746478873239e-07, + "epoch": 1.6312594840667678 + }, + { + "current_steps": 1075, + "loss": 2.6753, + "learning_rate": 6.954616588419406e-07, + "epoch": 1.6327769347496206 + }, + { + "current_steps": 1076, + "loss": 2.7319, + "learning_rate": 6.951486697965571e-07, + "epoch": 1.6342943854324734 + }, + { + "current_steps": 1077, + "loss": 2.6377, + "learning_rate": 6.948356807511737e-07, + "epoch": 1.6358118361153262 + }, + { + "current_steps": 1078, + "loss": 2.8635, + "learning_rate": 6.945226917057902e-07, + "epoch": 1.637329286798179 + }, + { + "current_steps": 1079, + "loss": 2.5672, + "learning_rate": 6.942097026604069e-07, + "epoch": 1.6388467374810318 + }, + { + "current_steps": 1080, + "loss": 2.4701, + "learning_rate": 6.938967136150234e-07, + "epoch": 1.6403641881638846 + }, + { + "current_steps": 1081, + "loss": 2.9289, + "learning_rate": 6.9358372456964e-07, + "epoch": 1.6418816388467374 + }, + { + "current_steps": 1082, + "loss": 2.7146, + "learning_rate": 6.932707355242567e-07, + "epoch": 1.6433990895295902 + }, + { + "current_steps": 1083, + "loss": 2.6154, + "learning_rate": 6.929577464788732e-07, + "epoch": 1.644916540212443 + }, + { + "current_steps": 1084, + "loss": 2.8372, + "learning_rate": 6.926447574334898e-07, + "epoch": 1.6464339908952959 + }, + { + "current_steps": 1085, + "loss": 2.5718, + "learning_rate": 6.923317683881063e-07, + "epoch": 1.6479514415781487 + }, + { + "current_steps": 1086, + "loss": 2.452, + "learning_rate": 6.92018779342723e-07, + "epoch": 1.6494688922610015 + }, + { + "current_steps": 1087, + "loss": 2.5461, + "learning_rate": 6.917057902973395e-07, + "epoch": 1.6509863429438543 + }, + { + "current_steps": 1088, + "loss": 2.6617, + "learning_rate": 6.913928012519562e-07, + "epoch": 1.6525037936267073 + }, + { + "current_steps": 1089, + "loss": 2.5092, + "learning_rate": 6.910798122065728e-07, + "epoch": 1.6540212443095599 + }, + { + "current_steps": 1090, + "loss": 2.7448, + "learning_rate": 6.907668231611893e-07, + "epoch": 1.655538694992413 + }, + { + "current_steps": 1091, + "loss": 2.6032, + "learning_rate": 6.90453834115806e-07, + "epoch": 1.6570561456752655 + }, + { + "current_steps": 1092, + "loss": 2.6667, + "learning_rate": 6.901408450704224e-07, + "epoch": 1.6585735963581185 + }, + { + "current_steps": 1093, + "loss": 2.5146, + "learning_rate": 6.898278560250391e-07, + "epoch": 1.660091047040971 + }, + { + "current_steps": 1094, + "loss": 2.3787, + "learning_rate": 6.895148669796557e-07, + "epoch": 1.6616084977238241 + }, + { + "current_steps": 1095, + "loss": 2.7217, + "learning_rate": 6.892018779342723e-07, + "epoch": 1.6631259484066767 + }, + { + "current_steps": 1096, + "loss": 2.7328, + "learning_rate": 6.888888888888889e-07, + "epoch": 1.6646433990895297 + }, + { + "current_steps": 1097, + "loss": 2.7909, + "learning_rate": 6.885758998435054e-07, + "epoch": 1.6661608497723823 + }, + { + "current_steps": 1098, + "loss": 2.4946, + "learning_rate": 6.882629107981221e-07, + "epoch": 1.6676783004552354 + }, + { + "current_steps": 1099, + "loss": 2.4522, + "learning_rate": 6.879499217527385e-07, + "epoch": 1.669195751138088 + }, + { + "current_steps": 1100, + "loss": 2.0456, + "learning_rate": 6.876369327073552e-07, + "epoch": 1.670713201820941 + }, + { + "current_steps": 1101, + "loss": 2.6554, + "learning_rate": 6.873239436619718e-07, + "epoch": 1.6722306525037935 + }, + { + "current_steps": 1102, + "loss": 2.7718, + "learning_rate": 6.870109546165884e-07, + "epoch": 1.6737481031866466 + }, + { + "current_steps": 1103, + "loss": 2.6934, + "learning_rate": 6.86697965571205e-07, + "epoch": 1.6752655538694992 + }, + { + "current_steps": 1104, + "loss": 2.6551, + "learning_rate": 6.863849765258216e-07, + "epoch": 1.6767830045523522 + }, + { + "current_steps": 1105, + "loss": 2.7982, + "learning_rate": 6.860719874804382e-07, + "epoch": 1.6783004552352048 + }, + { + "current_steps": 1106, + "loss": 2.5465, + "learning_rate": 6.857589984350547e-07, + "epoch": 1.6798179059180578 + }, + { + "current_steps": 1107, + "loss": 2.5973, + "learning_rate": 6.854460093896713e-07, + "epoch": 1.6813353566009104 + }, + { + "current_steps": 1108, + "loss": 2.6538, + "learning_rate": 6.851330203442879e-07, + "epoch": 1.6828528072837634 + }, + { + "current_steps": 1109, + "loss": 2.4883, + "learning_rate": 6.848200312989045e-07, + "epoch": 1.684370257966616 + }, + { + "current_steps": 1110, + "loss": 2.3091, + "learning_rate": 6.845070422535211e-07, + "epoch": 1.685887708649469 + }, + { + "current_steps": 1111, + "loss": 2.5734, + "learning_rate": 6.841940532081377e-07, + "epoch": 1.6874051593323216 + }, + { + "current_steps": 1112, + "loss": 2.6373, + "learning_rate": 6.838810641627543e-07, + "epoch": 1.6889226100151746 + }, + { + "current_steps": 1113, + "loss": 2.61, + "learning_rate": 6.83568075117371e-07, + "epoch": 1.6904400606980272 + }, + { + "current_steps": 1114, + "loss": 2.661, + "learning_rate": 6.832550860719874e-07, + "epoch": 1.6919575113808802 + }, + { + "current_steps": 1115, + "loss": 2.7875, + "learning_rate": 6.82942097026604e-07, + "epoch": 1.6934749620637328 + }, + { + "current_steps": 1116, + "loss": 2.3102, + "learning_rate": 6.826291079812206e-07, + "epoch": 1.6949924127465859 + }, + { + "current_steps": 1117, + "loss": 2.6256, + "learning_rate": 6.823161189358372e-07, + "epoch": 1.6965098634294384 + }, + { + "current_steps": 1118, + "loss": 2.4978, + "learning_rate": 6.820031298904539e-07, + "epoch": 1.6980273141122915 + }, + { + "current_steps": 1119, + "loss": 2.7383, + "learning_rate": 6.816901408450704e-07, + "epoch": 1.699544764795144 + }, + { + "current_steps": 1120, + "loss": 2.6371, + "learning_rate": 6.813771517996871e-07, + "epoch": 1.701062215477997 + }, + { + "current_steps": 1121, + "loss": 2.377, + "learning_rate": 6.810641627543035e-07, + "epoch": 1.7025796661608497 + }, + { + "current_steps": 1122, + "loss": 2.6857, + "learning_rate": 6.807511737089202e-07, + "epoch": 1.7040971168437027 + }, + { + "current_steps": 1123, + "loss": 2.7306, + "learning_rate": 6.804381846635367e-07, + "epoch": 1.7056145675265553 + }, + { + "current_steps": 1124, + "loss": 2.4957, + "learning_rate": 6.801251956181533e-07, + "epoch": 1.7071320182094083 + }, + { + "current_steps": 1125, + "loss": 2.7825, + "learning_rate": 6.7981220657277e-07, + "epoch": 1.7086494688922609 + }, + { + "current_steps": 1126, + "loss": 2.4713, + "learning_rate": 6.794992175273865e-07, + "epoch": 1.710166919575114 + }, + { + "current_steps": 1127, + "loss": 2.6389, + "learning_rate": 6.791862284820032e-07, + "epoch": 1.7116843702579665 + }, + { + "current_steps": 1128, + "loss": 2.6506, + "learning_rate": 6.788732394366196e-07, + "epoch": 1.7132018209408195 + }, + { + "current_steps": 1129, + "loss": 2.5002, + "learning_rate": 6.785602503912363e-07, + "epoch": 1.714719271623672 + }, + { + "current_steps": 1130, + "loss": 2.9281, + "learning_rate": 6.782472613458528e-07, + "epoch": 1.7162367223065251 + }, + { + "current_steps": 1131, + "loss": 2.6052, + "learning_rate": 6.779342723004694e-07, + "epoch": 1.7177541729893777 + }, + { + "current_steps": 1132, + "loss": 2.5308, + "learning_rate": 6.776212832550861e-07, + "epoch": 1.7192716236722307 + }, + { + "current_steps": 1133, + "loss": 2.8017, + "learning_rate": 6.773082942097026e-07, + "epoch": 1.7207890743550833 + }, + { + "current_steps": 1134, + "loss": 2.7197, + "learning_rate": 6.769953051643193e-07, + "epoch": 1.7223065250379364 + }, + { + "current_steps": 1135, + "loss": 2.6563, + "learning_rate": 6.766823161189357e-07, + "epoch": 1.723823975720789 + }, + { + "current_steps": 1136, + "loss": 2.8231, + "learning_rate": 6.763693270735524e-07, + "epoch": 1.725341426403642 + }, + { + "current_steps": 1137, + "loss": 2.7922, + "learning_rate": 6.76056338028169e-07, + "epoch": 1.7268588770864945 + }, + { + "current_steps": 1138, + "loss": 2.5446, + "learning_rate": 6.757433489827856e-07, + "epoch": 1.7283763277693476 + }, + { + "current_steps": 1139, + "loss": 2.8635, + "learning_rate": 6.754303599374022e-07, + "epoch": 1.7298937784522002 + }, + { + "current_steps": 1140, + "loss": 2.5415, + "learning_rate": 6.751173708920187e-07, + "epoch": 1.7314112291350532 + }, + { + "current_steps": 1141, + "loss": 2.5187, + "learning_rate": 6.748043818466354e-07, + "epoch": 1.7329286798179058 + }, + { + "current_steps": 1142, + "loss": 2.6561, + "learning_rate": 6.744913928012518e-07, + "epoch": 1.7344461305007588 + }, + { + "current_steps": 1143, + "loss": 2.7025, + "learning_rate": 6.741784037558685e-07, + "epoch": 1.7359635811836114 + }, + { + "current_steps": 1144, + "loss": 2.7125, + "learning_rate": 6.738654147104851e-07, + "epoch": 1.7374810318664644 + }, + { + "current_steps": 1145, + "loss": 2.738, + "learning_rate": 6.735524256651017e-07, + "epoch": 1.738998482549317 + }, + { + "current_steps": 1146, + "loss": 2.8048, + "learning_rate": 6.732394366197183e-07, + "epoch": 1.74051593323217 + }, + { + "current_steps": 1147, + "loss": 2.6323, + "learning_rate": 6.729264475743349e-07, + "epoch": 1.7420333839150226 + }, + { + "current_steps": 1148, + "loss": 2.5536, + "learning_rate": 6.726134585289515e-07, + "epoch": 1.7435508345978756 + }, + { + "current_steps": 1149, + "loss": 2.7348, + "learning_rate": 6.72300469483568e-07, + "epoch": 1.7450682852807282 + }, + { + "current_steps": 1150, + "loss": 2.6283, + "learning_rate": 6.719874804381846e-07, + "epoch": 1.7465857359635812 + }, + { + "current_steps": 1151, + "loss": 2.6868, + "learning_rate": 6.716744913928012e-07, + "epoch": 1.7481031866464338 + }, + { + "current_steps": 1152, + "loss": 2.6993, + "learning_rate": 6.713615023474178e-07, + "epoch": 1.7496206373292869 + }, + { + "current_steps": 1153, + "loss": 2.553, + "learning_rate": 6.710485133020344e-07, + "epoch": 1.7511380880121397 + }, + { + "current_steps": 1154, + "loss": 2.6098, + "learning_rate": 6.70735524256651e-07, + "epoch": 1.7526555386949925 + }, + { + "current_steps": 1155, + "loss": 2.7078, + "learning_rate": 6.704225352112676e-07, + "epoch": 1.7541729893778453 + }, + { + "current_steps": 1156, + "loss": 2.6103, + "learning_rate": 6.701095461658842e-07, + "epoch": 1.755690440060698 + }, + { + "current_steps": 1157, + "loss": 2.7712, + "learning_rate": 6.697965571205007e-07, + "epoch": 1.7572078907435509 + }, + { + "current_steps": 1158, + "loss": 2.7045, + "learning_rate": 6.694835680751173e-07, + "epoch": 1.7587253414264037 + }, + { + "current_steps": 1159, + "loss": 2.493, + "learning_rate": 6.691705790297339e-07, + "epoch": 1.7602427921092565 + }, + { + "current_steps": 1160, + "loss": 2.7866, + "learning_rate": 6.688575899843505e-07, + "epoch": 1.7617602427921093 + }, + { + "current_steps": 1161, + "loss": 2.7935, + "learning_rate": 6.685446009389672e-07, + "epoch": 1.763277693474962 + }, + { + "current_steps": 1162, + "loss": 2.9813, + "learning_rate": 6.682316118935837e-07, + "epoch": 1.764795144157815 + }, + { + "current_steps": 1163, + "loss": 2.9022, + "learning_rate": 6.679186228482004e-07, + "epoch": 1.7663125948406677 + }, + { + "current_steps": 1164, + "loss": 2.2721, + "learning_rate": 6.676056338028168e-07, + "epoch": 1.7678300455235205 + }, + { + "current_steps": 1165, + "loss": 2.596, + "learning_rate": 6.672926447574334e-07, + "epoch": 1.7693474962063733 + }, + { + "current_steps": 1166, + "loss": 2.6422, + "learning_rate": 6.6697965571205e-07, + "epoch": 1.7708649468892261 + }, + { + "current_steps": 1167, + "loss": 2.5952, + "learning_rate": 6.666666666666666e-07, + "epoch": 1.772382397572079 + }, + { + "current_steps": 1168, + "loss": 2.8122, + "learning_rate": 6.663536776212833e-07, + "epoch": 1.7738998482549317 + }, + { + "current_steps": 1169, + "loss": 2.6116, + "learning_rate": 6.660406885758998e-07, + "epoch": 1.7754172989377845 + }, + { + "current_steps": 1170, + "loss": 2.7243, + "learning_rate": 6.657276995305165e-07, + "epoch": 1.7769347496206374 + }, + { + "current_steps": 1171, + "loss": 2.6319, + "learning_rate": 6.654147104851329e-07, + "epoch": 1.7784522003034902 + }, + { + "current_steps": 1172, + "loss": 2.5246, + "learning_rate": 6.651017214397496e-07, + "epoch": 1.779969650986343 + }, + { + "current_steps": 1173, + "loss": 2.6652, + "learning_rate": 6.647887323943661e-07, + "epoch": 1.7814871016691958 + }, + { + "current_steps": 1174, + "loss": 2.153, + "learning_rate": 6.644757433489827e-07, + "epoch": 1.7830045523520486 + }, + { + "current_steps": 1175, + "loss": 2.484, + "learning_rate": 6.641627543035994e-07, + "epoch": 1.7845220030349014 + }, + { + "current_steps": 1176, + "loss": 2.5651, + "learning_rate": 6.638497652582159e-07, + "epoch": 1.7860394537177542 + }, + { + "current_steps": 1177, + "loss": 2.7817, + "learning_rate": 6.635367762128326e-07, + "epoch": 1.787556904400607 + }, + { + "current_steps": 1178, + "loss": 2.568, + "learning_rate": 6.63223787167449e-07, + "epoch": 1.7890743550834598 + }, + { + "current_steps": 1179, + "loss": 2.4006, + "learning_rate": 6.629107981220657e-07, + "epoch": 1.7905918057663126 + }, + { + "current_steps": 1180, + "loss": 2.5821, + "learning_rate": 6.625978090766823e-07, + "epoch": 1.7921092564491654 + }, + { + "current_steps": 1181, + "loss": 2.6107, + "learning_rate": 6.622848200312989e-07, + "epoch": 1.7936267071320182 + }, + { + "current_steps": 1182, + "loss": 2.645, + "learning_rate": 6.619718309859155e-07, + "epoch": 1.795144157814871 + }, + { + "current_steps": 1183, + "loss": 2.771, + "learning_rate": 6.61658841940532e-07, + "epoch": 1.7966616084977238 + }, + { + "current_steps": 1184, + "loss": 2.827, + "learning_rate": 6.613458528951487e-07, + "epoch": 1.7981790591805766 + }, + { + "current_steps": 1185, + "loss": 2.6915, + "learning_rate": 6.610328638497652e-07, + "epoch": 1.7996965098634294 + }, + { + "current_steps": 1186, + "loss": 2.7067, + "learning_rate": 6.607198748043818e-07, + "epoch": 1.8012139605462822 + }, + { + "current_steps": 1187, + "loss": 2.5689, + "learning_rate": 6.604068857589984e-07, + "epoch": 1.802731411229135 + }, + { + "current_steps": 1188, + "loss": 2.6635, + "learning_rate": 6.60093896713615e-07, + "epoch": 1.8042488619119879 + }, + { + "current_steps": 1189, + "loss": 2.0873, + "learning_rate": 6.597809076682316e-07, + "epoch": 1.8057663125948407 + }, + { + "current_steps": 1190, + "loss": 2.9775, + "learning_rate": 6.594679186228481e-07, + "epoch": 1.8072837632776935 + }, + { + "current_steps": 1191, + "loss": 2.5873, + "learning_rate": 6.591549295774648e-07, + "epoch": 1.8088012139605463 + }, + { + "current_steps": 1192, + "loss": 2.4976, + "learning_rate": 6.588419405320814e-07, + "epoch": 1.810318664643399 + }, + { + "current_steps": 1193, + "loss": 2.7282, + "learning_rate": 6.585289514866979e-07, + "epoch": 1.8118361153262519 + }, + { + "current_steps": 1194, + "loss": 2.6834, + "learning_rate": 6.582159624413145e-07, + "epoch": 1.8133535660091047 + }, + { + "current_steps": 1195, + "loss": 2.6946, + "learning_rate": 6.579029733959311e-07, + "epoch": 1.8148710166919575 + }, + { + "current_steps": 1196, + "loss": 2.2968, + "learning_rate": 6.575899843505477e-07, + "epoch": 1.8163884673748103 + }, + { + "current_steps": 1197, + "loss": 2.6128, + "learning_rate": 6.572769953051643e-07, + "epoch": 1.817905918057663 + }, + { + "current_steps": 1198, + "loss": 2.7578, + "learning_rate": 6.569640062597809e-07, + "epoch": 1.819423368740516 + }, + { + "current_steps": 1199, + "loss": 2.6156, + "learning_rate": 6.566510172143975e-07, + "epoch": 1.8209408194233687 + }, + { + "current_steps": 1200, + "loss": 2.5516, + "learning_rate": 6.56338028169014e-07, + "epoch": 1.8224582701062215 + }, + { + "current_steps": 1201, + "loss": 2.6514, + "learning_rate": 6.560250391236306e-07, + "epoch": 1.8239757207890743 + }, + { + "current_steps": 1202, + "loss": 2.4579, + "learning_rate": 6.557120500782472e-07, + "epoch": 1.8254931714719271 + }, + { + "current_steps": 1203, + "loss": 2.4497, + "learning_rate": 6.553990610328638e-07, + "epoch": 1.82701062215478 + }, + { + "current_steps": 1204, + "loss": 2.6125, + "learning_rate": 6.550860719874805e-07, + "epoch": 1.8285280728376327 + }, + { + "current_steps": 1205, + "loss": 2.6871, + "learning_rate": 6.54773082942097e-07, + "epoch": 1.8300455235204856 + }, + { + "current_steps": 1206, + "loss": 2.6652, + "learning_rate": 6.544600938967137e-07, + "epoch": 1.8315629742033384 + }, + { + "current_steps": 1207, + "loss": 2.5172, + "learning_rate": 6.541471048513302e-07, + "epoch": 1.8330804248861912 + }, + { + "current_steps": 1208, + "loss": 2.7241, + "learning_rate": 6.538341158059467e-07, + "epoch": 1.834597875569044 + }, + { + "current_steps": 1209, + "loss": 2.094, + "learning_rate": 6.535211267605633e-07, + "epoch": 1.8361153262518968 + }, + { + "current_steps": 1210, + "loss": 2.7619, + "learning_rate": 6.532081377151799e-07, + "epoch": 1.8376327769347496 + }, + { + "current_steps": 1211, + "loss": 2.8079, + "learning_rate": 6.528951486697966e-07, + "epoch": 1.8391502276176024 + }, + { + "current_steps": 1212, + "loss": 2.7218, + "learning_rate": 6.525821596244131e-07, + "epoch": 1.8406676783004552 + }, + { + "current_steps": 1213, + "loss": 2.8291, + "learning_rate": 6.522691705790298e-07, + "epoch": 1.842185128983308 + }, + { + "current_steps": 1214, + "loss": 2.7693, + "learning_rate": 6.519561815336463e-07, + "epoch": 1.8437025796661608 + }, + { + "current_steps": 1215, + "loss": 2.6731, + "learning_rate": 6.516431924882628e-07, + "epoch": 1.8452200303490136 + }, + { + "current_steps": 1216, + "loss": 2.3596, + "learning_rate": 6.513302034428794e-07, + "epoch": 1.8467374810318664 + }, + { + "current_steps": 1217, + "loss": 2.6519, + "learning_rate": 6.51017214397496e-07, + "epoch": 1.8482549317147192 + }, + { + "current_steps": 1218, + "loss": 2.4988, + "learning_rate": 6.507042253521127e-07, + "epoch": 1.849772382397572 + }, + { + "current_steps": 1219, + "loss": 2.8423, + "learning_rate": 6.503912363067292e-07, + "epoch": 1.851289833080425 + }, + { + "current_steps": 1220, + "loss": 2.8369, + "learning_rate": 6.500782472613459e-07, + "epoch": 1.8528072837632776 + }, + { + "current_steps": 1221, + "loss": 2.649, + "learning_rate": 6.497652582159624e-07, + "epoch": 1.8543247344461307 + }, + { + "current_steps": 1222, + "loss": 2.9262, + "learning_rate": 6.49452269170579e-07, + "epoch": 1.8558421851289832 + }, + { + "current_steps": 1223, + "loss": 2.8866, + "learning_rate": 6.491392801251956e-07, + "epoch": 1.8573596358118363 + }, + { + "current_steps": 1224, + "loss": 2.5051, + "learning_rate": 6.488262910798121e-07, + "epoch": 1.8588770864946889 + }, + { + "current_steps": 1225, + "loss": 2.9152, + "learning_rate": 6.485133020344288e-07, + "epoch": 1.8603945371775419 + }, + { + "current_steps": 1226, + "loss": 2.5223, + "learning_rate": 6.482003129890453e-07, + "epoch": 1.8619119878603945 + }, + { + "current_steps": 1227, + "loss": 2.7096, + "learning_rate": 6.47887323943662e-07, + "epoch": 1.8634294385432475 + }, + { + "current_steps": 1228, + "loss": 2.5291, + "learning_rate": 6.475743348982785e-07, + "epoch": 1.8649468892261 + }, + { + "current_steps": 1229, + "loss": 2.668, + "learning_rate": 6.472613458528952e-07, + "epoch": 1.866464339908953 + }, + { + "current_steps": 1230, + "loss": 2.1827, + "learning_rate": 6.469483568075117e-07, + "epoch": 1.8679817905918057 + }, + { + "current_steps": 1231, + "loss": 2.6694, + "learning_rate": 6.466353677621283e-07, + "epoch": 1.8694992412746587 + }, + { + "current_steps": 1232, + "loss": 2.5806, + "learning_rate": 6.463223787167449e-07, + "epoch": 1.8710166919575113 + }, + { + "current_steps": 1233, + "loss": 2.6575, + "learning_rate": 6.460093896713614e-07, + "epoch": 1.8725341426403643 + }, + { + "current_steps": 1234, + "loss": 2.3412, + "learning_rate": 6.456964006259781e-07, + "epoch": 1.874051593323217 + }, + { + "current_steps": 1235, + "loss": 2.5623, + "learning_rate": 6.453834115805947e-07, + "epoch": 1.87556904400607 + }, + { + "current_steps": 1236, + "loss": 2.535, + "learning_rate": 6.450704225352113e-07, + "epoch": 1.8770864946889225 + }, + { + "current_steps": 1237, + "loss": 2.6913, + "learning_rate": 6.447574334898278e-07, + "epoch": 1.8786039453717756 + }, + { + "current_steps": 1238, + "loss": 2.8122, + "learning_rate": 6.444444444444444e-07, + "epoch": 1.8801213960546281 + }, + { + "current_steps": 1239, + "loss": 2.5576, + "learning_rate": 6.44131455399061e-07, + "epoch": 1.8816388467374812 + }, + { + "current_steps": 1240, + "loss": 2.8451, + "learning_rate": 6.438184663536776e-07, + "epoch": 1.8831562974203337 + }, + { + "current_steps": 1241, + "loss": 2.5796, + "learning_rate": 6.435054773082942e-07, + "epoch": 1.8846737481031868 + }, + { + "current_steps": 1242, + "loss": 2.5971, + "learning_rate": 6.431924882629108e-07, + "epoch": 1.8861911987860394 + }, + { + "current_steps": 1243, + "loss": 2.5675, + "learning_rate": 6.428794992175274e-07, + "epoch": 1.8877086494688924 + }, + { + "current_steps": 1244, + "loss": 2.6895, + "learning_rate": 6.425665101721439e-07, + "epoch": 1.889226100151745 + }, + { + "current_steps": 1245, + "loss": 2.5878, + "learning_rate": 6.422535211267605e-07, + "epoch": 1.890743550834598 + }, + { + "current_steps": 1246, + "loss": 2.5891, + "learning_rate": 6.419405320813771e-07, + "epoch": 1.8922610015174506 + }, + { + "current_steps": 1247, + "loss": 2.6193, + "learning_rate": 6.416275430359938e-07, + "epoch": 1.8937784522003036 + }, + { + "current_steps": 1248, + "loss": 2.4002, + "learning_rate": 6.413145539906103e-07, + "epoch": 1.8952959028831562 + }, + { + "current_steps": 1249, + "loss": 2.6001, + "learning_rate": 6.410015649452269e-07, + "epoch": 1.8968133535660092 + }, + { + "current_steps": 1250, + "loss": 2.4886, + "learning_rate": 6.406885758998435e-07, + "epoch": 1.8983308042488618 + }, + { + "current_steps": 1251, + "loss": 2.5925, + "learning_rate": 6.4037558685446e-07, + "epoch": 1.8998482549317148 + }, + { + "current_steps": 1252, + "loss": 2.5875, + "learning_rate": 6.400625978090766e-07, + "epoch": 1.9013657056145674 + }, + { + "current_steps": 1253, + "loss": 2.6753, + "learning_rate": 6.397496087636932e-07, + "epoch": 1.9028831562974204 + }, + { + "current_steps": 1254, + "loss": 2.5452, + "learning_rate": 6.394366197183099e-07, + "epoch": 1.904400606980273 + }, + { + "current_steps": 1255, + "loss": 2.6514, + "learning_rate": 6.391236306729264e-07, + "epoch": 1.905918057663126 + }, + { + "current_steps": 1256, + "loss": 2.5867, + "learning_rate": 6.388106416275431e-07, + "epoch": 1.9074355083459786 + }, + { + "current_steps": 1257, + "loss": 2.1161, + "learning_rate": 6.384976525821596e-07, + "epoch": 1.9089529590288317 + }, + { + "current_steps": 1258, + "loss": 2.7434, + "learning_rate": 6.381846635367761e-07, + "epoch": 1.9104704097116842 + }, + { + "current_steps": 1259, + "loss": 2.6993, + "learning_rate": 6.378716744913927e-07, + "epoch": 1.9119878603945373 + }, + { + "current_steps": 1260, + "loss": 2.5003, + "learning_rate": 6.375586854460093e-07, + "epoch": 1.9135053110773899 + }, + { + "current_steps": 1261, + "loss": 2.6957, + "learning_rate": 6.37245696400626e-07, + "epoch": 1.9150227617602429 + }, + { + "current_steps": 1262, + "loss": 2.2843, + "learning_rate": 6.369327073552425e-07, + "epoch": 1.9165402124430955 + }, + { + "current_steps": 1263, + "loss": 2.6018, + "learning_rate": 6.366197183098592e-07, + "epoch": 1.9180576631259485 + }, + { + "current_steps": 1264, + "loss": 2.6013, + "learning_rate": 6.363067292644757e-07, + "epoch": 1.919575113808801 + }, + { + "current_steps": 1265, + "loss": 2.7921, + "learning_rate": 6.359937402190924e-07, + "epoch": 1.921092564491654 + }, + { + "current_steps": 1266, + "loss": 2.3878, + "learning_rate": 6.356807511737089e-07, + "epoch": 1.9226100151745067 + }, + { + "current_steps": 1267, + "loss": 2.506, + "learning_rate": 6.353677621283254e-07, + "epoch": 1.9241274658573597 + }, + { + "current_steps": 1268, + "loss": 2.3843, + "learning_rate": 6.350547730829421e-07, + "epoch": 1.9256449165402123 + }, + { + "current_steps": 1269, + "loss": 2.5985, + "learning_rate": 6.347417840375586e-07, + "epoch": 1.9271623672230653 + }, + { + "current_steps": 1270, + "loss": 2.7112, + "learning_rate": 6.344287949921753e-07, + "epoch": 1.928679817905918 + }, + { + "current_steps": 1271, + "loss": 2.9039, + "learning_rate": 6.341158059467918e-07, + "epoch": 1.930197268588771 + }, + { + "current_steps": 1272, + "loss": 2.8512, + "learning_rate": 6.338028169014085e-07, + "epoch": 1.9317147192716235 + }, + { + "current_steps": 1273, + "loss": 2.6138, + "learning_rate": 6.33489827856025e-07, + "epoch": 1.9332321699544766 + }, + { + "current_steps": 1274, + "loss": 2.3345, + "learning_rate": 6.331768388106415e-07, + "epoch": 1.9347496206373291 + }, + { + "current_steps": 1275, + "loss": 2.4821, + "learning_rate": 6.328638497652582e-07, + "epoch": 1.9362670713201822 + }, + { + "current_steps": 1276, + "loss": 2.5166, + "learning_rate": 6.325508607198747e-07, + "epoch": 1.9377845220030347 + }, + { + "current_steps": 1277, + "loss": 2.7326, + "learning_rate": 6.322378716744914e-07, + "epoch": 1.9393019726858878 + }, + { + "current_steps": 1278, + "loss": 2.6079, + "learning_rate": 6.31924882629108e-07, + "epoch": 1.9408194233687404 + }, + { + "current_steps": 1279, + "loss": 2.5511, + "learning_rate": 6.316118935837246e-07, + "epoch": 1.9423368740515934 + }, + { + "current_steps": 1280, + "loss": 2.0749, + "learning_rate": 6.312989045383411e-07, + "epoch": 1.943854324734446 + }, + { + "current_steps": 1281, + "loss": 2.5127, + "learning_rate": 6.309859154929577e-07, + "epoch": 1.945371775417299 + }, + { + "current_steps": 1282, + "loss": 2.6498, + "learning_rate": 6.306729264475743e-07, + "epoch": 1.9468892261001516 + }, + { + "current_steps": 1283, + "loss": 2.5588, + "learning_rate": 6.303599374021908e-07, + "epoch": 1.9484066767830046 + }, + { + "current_steps": 1284, + "loss": 2.6811, + "learning_rate": 6.300469483568075e-07, + "epoch": 1.9499241274658572 + }, + { + "current_steps": 1285, + "loss": 3.0106, + "learning_rate": 6.297339593114241e-07, + "epoch": 1.9514415781487102 + }, + { + "current_steps": 1286, + "loss": 2.7788, + "learning_rate": 6.294209702660407e-07, + "epoch": 1.952959028831563 + }, + { + "current_steps": 1287, + "loss": 2.5157, + "learning_rate": 6.291079812206573e-07, + "epoch": 1.9544764795144158 + }, + { + "current_steps": 1288, + "loss": 2.5008, + "learning_rate": 6.287949921752738e-07, + "epoch": 1.9559939301972686 + }, + { + "current_steps": 1289, + "loss": 2.6932, + "learning_rate": 6.284820031298904e-07, + "epoch": 1.9575113808801214 + }, + { + "current_steps": 1290, + "loss": 2.4222, + "learning_rate": 6.281690140845071e-07, + "epoch": 1.9590288315629742 + }, + { + "current_steps": 1291, + "loss": 2.7521, + "learning_rate": 6.278560250391236e-07, + "epoch": 1.960546282245827 + }, + { + "current_steps": 1292, + "loss": 2.6577, + "learning_rate": 6.275430359937402e-07, + "epoch": 1.9620637329286799 + }, + { + "current_steps": 1293, + "loss": 2.3307, + "learning_rate": 6.272300469483568e-07, + "epoch": 1.9635811836115327 + }, + { + "current_steps": 1294, + "loss": 2.6643, + "learning_rate": 6.269170579029734e-07, + "epoch": 1.9650986342943855 + }, + { + "current_steps": 1295, + "loss": 2.3262, + "learning_rate": 6.266040688575899e-07, + "epoch": 1.9666160849772383 + }, + { + "current_steps": 1296, + "loss": 2.6379, + "learning_rate": 6.262910798122065e-07, + "epoch": 1.968133535660091 + }, + { + "current_steps": 1297, + "loss": 2.7996, + "learning_rate": 6.259780907668232e-07, + "epoch": 1.9696509863429439 + }, + { + "current_steps": 1298, + "loss": 2.6277, + "learning_rate": 6.256651017214397e-07, + "epoch": 1.9711684370257967 + }, + { + "current_steps": 1299, + "loss": 2.3185, + "learning_rate": 6.253521126760564e-07, + "epoch": 1.9726858877086495 + }, + { + "current_steps": 1300, + "loss": 2.638, + "learning_rate": 6.250391236306729e-07, + "epoch": 1.9742033383915023 + }, + { + "current_steps": 1301, + "loss": 2.7046, + "learning_rate": 6.247261345852895e-07, + "epoch": 1.975720789074355 + }, + { + "current_steps": 1302, + "loss": 2.6651, + "learning_rate": 6.24413145539906e-07, + "epoch": 1.977238239757208 + }, + { + "current_steps": 1303, + "loss": 2.5558, + "learning_rate": 6.241001564945226e-07, + "epoch": 1.9787556904400607 + }, + { + "current_steps": 1304, + "loss": 2.4924, + "learning_rate": 6.237871674491393e-07, + "epoch": 1.9802731411229135 + }, + { + "current_steps": 1305, + "loss": 2.6882, + "learning_rate": 6.234741784037558e-07, + "epoch": 1.9817905918057663 + }, + { + "current_steps": 1306, + "loss": 2.4799, + "learning_rate": 6.231611893583725e-07, + "epoch": 1.9833080424886191 + }, + { + "current_steps": 1307, + "loss": 2.8285, + "learning_rate": 6.22848200312989e-07, + "epoch": 1.984825493171472 + }, + { + "current_steps": 1308, + "loss": 2.7834, + "learning_rate": 6.225352112676056e-07, + "epoch": 1.9863429438543247 + }, + { + "current_steps": 1309, + "loss": 2.6028, + "learning_rate": 6.222222222222223e-07, + "epoch": 1.9878603945371776 + }, + { + "current_steps": 1310, + "loss": 2.419, + "learning_rate": 6.219092331768387e-07, + "epoch": 1.9893778452200304 + }, + { + "current_steps": 1311, + "loss": 2.7332, + "learning_rate": 6.215962441314554e-07, + "epoch": 1.9908952959028832 + }, + { + "current_steps": 1312, + "loss": 2.3534, + "learning_rate": 6.212832550860719e-07, + "epoch": 1.992412746585736 + }, + { + "current_steps": 1313, + "loss": 2.7812, + "learning_rate": 6.209702660406886e-07, + "epoch": 1.9939301972685888 + }, + { + "current_steps": 1314, + "loss": 2.5806, + "learning_rate": 6.206572769953051e-07, + "epoch": 1.9954476479514416 + }, + { + "current_steps": 1315, + "loss": 2.5473, + "learning_rate": 6.203442879499218e-07, + "epoch": 1.9969650986342944 + }, + { + "current_steps": 1316, + "loss": 2.5898, + "learning_rate": 6.200312989045384e-07, + "epoch": 1.9984825493171472 + }, + { + "current_steps": 1317, + "loss": 2.5964, + "learning_rate": 6.197183098591548e-07, + "epoch": 2.0 + }, + { + "current_steps": 1318, + "loss": 2.5558, + "learning_rate": 6.194053208137715e-07, + "epoch": 2.001517450682853 + }, + { + "current_steps": 1319, + "loss": 2.4679, + "learning_rate": 6.19092331768388e-07, + "epoch": 2.0030349013657056 + }, + { + "current_steps": 1320, + "loss": 2.7638, + "learning_rate": 6.187793427230047e-07, + "epoch": 2.0045523520485586 + }, + { + "current_steps": 1321, + "loss": 2.7115, + "learning_rate": 6.184663536776212e-07, + "epoch": 2.0060698027314112 + }, + { + "current_steps": 1322, + "loss": 2.2378, + "learning_rate": 6.181533646322379e-07, + "epoch": 2.0075872534142643 + }, + { + "current_steps": 1323, + "loss": 2.0814, + "learning_rate": 6.178403755868545e-07, + "epoch": 2.009104704097117 + }, + { + "current_steps": 1324, + "loss": 2.4871, + "learning_rate": 6.17527386541471e-07, + "epoch": 2.01062215477997 + }, + { + "current_steps": 1325, + "loss": 2.5282, + "learning_rate": 6.172143974960876e-07, + "epoch": 2.0121396054628224 + }, + { + "current_steps": 1326, + "loss": 2.671, + "learning_rate": 6.169014084507041e-07, + "epoch": 2.0136570561456755 + }, + { + "current_steps": 1327, + "loss": 2.5312, + "learning_rate": 6.165884194053208e-07, + "epoch": 2.015174506828528 + }, + { + "current_steps": 1328, + "loss": 2.6998, + "learning_rate": 6.162754303599374e-07, + "epoch": 2.016691957511381 + }, + { + "current_steps": 1329, + "loss": 2.9641, + "learning_rate": 6.15962441314554e-07, + "epoch": 2.0182094081942337 + }, + { + "current_steps": 1330, + "loss": 2.5766, + "learning_rate": 6.156494522691706e-07, + "epoch": 2.0197268588770867 + }, + { + "current_steps": 1331, + "loss": 2.6833, + "learning_rate": 6.153364632237871e-07, + "epoch": 2.0212443095599393 + }, + { + "current_steps": 1332, + "loss": 2.5255, + "learning_rate": 6.150234741784037e-07, + "epoch": 2.0227617602427923 + }, + { + "current_steps": 1333, + "loss": 2.4472, + "learning_rate": 6.147104851330202e-07, + "epoch": 2.024279210925645 + }, + { + "current_steps": 1334, + "loss": 2.7304, + "learning_rate": 6.143974960876369e-07, + "epoch": 2.025796661608498 + }, + { + "current_steps": 1335, + "loss": 2.6867, + "learning_rate": 6.140845070422535e-07, + "epoch": 2.0273141122913505 + }, + { + "current_steps": 1336, + "loss": 2.5554, + "learning_rate": 6.137715179968701e-07, + "epoch": 2.0288315629742035 + }, + { + "current_steps": 1337, + "loss": 2.7311, + "learning_rate": 6.134585289514867e-07, + "epoch": 2.030349013657056 + }, + { + "current_steps": 1338, + "loss": 2.5189, + "learning_rate": 6.131455399061033e-07, + "epoch": 2.031866464339909 + }, + { + "current_steps": 1339, + "loss": 2.6173, + "learning_rate": 6.128325508607198e-07, + "epoch": 2.0333839150227617 + }, + { + "current_steps": 1340, + "loss": 2.1303, + "learning_rate": 6.125195618153365e-07, + "epoch": 2.0349013657056148 + }, + { + "current_steps": 1341, + "loss": 2.5003, + "learning_rate": 6.12206572769953e-07, + "epoch": 2.0364188163884673 + }, + { + "current_steps": 1342, + "loss": 2.6757, + "learning_rate": 6.118935837245696e-07, + "epoch": 2.0379362670713204 + }, + { + "current_steps": 1343, + "loss": 2.6249, + "learning_rate": 6.115805946791862e-07, + "epoch": 2.039453717754173 + }, + { + "current_steps": 1344, + "loss": 2.3039, + "learning_rate": 6.112676056338028e-07, + "epoch": 2.040971168437026 + }, + { + "current_steps": 1345, + "loss": 2.5457, + "learning_rate": 6.109546165884194e-07, + "epoch": 2.0424886191198786 + }, + { + "current_steps": 1346, + "loss": 2.2121, + "learning_rate": 6.106416275430359e-07, + "epoch": 2.0440060698027316 + }, + { + "current_steps": 1347, + "loss": 2.5407, + "learning_rate": 6.103286384976526e-07, + "epoch": 2.045523520485584 + }, + { + "current_steps": 1348, + "loss": 2.673, + "learning_rate": 6.100156494522691e-07, + "epoch": 2.047040971168437 + }, + { + "current_steps": 1349, + "loss": 2.4765, + "learning_rate": 6.097026604068858e-07, + "epoch": 2.04855842185129 + }, + { + "current_steps": 1350, + "loss": 2.8278, + "learning_rate": 6.093896713615023e-07, + "epoch": 2.050075872534143 + }, + { + "current_steps": 1351, + "loss": 2.4782, + "learning_rate": 6.090766823161189e-07, + "epoch": 2.0515933232169954 + }, + { + "current_steps": 1352, + "loss": 2.5558, + "learning_rate": 6.087636932707356e-07, + "epoch": 2.0531107738998484 + }, + { + "current_steps": 1353, + "loss": 2.2509, + "learning_rate": 6.08450704225352e-07, + "epoch": 2.054628224582701 + }, + { + "current_steps": 1354, + "loss": 2.5071, + "learning_rate": 6.081377151799687e-07, + "epoch": 2.056145675265554 + }, + { + "current_steps": 1355, + "loss": 2.5092, + "learning_rate": 6.078247261345852e-07, + "epoch": 2.0576631259484066 + }, + { + "current_steps": 1356, + "loss": 2.6401, + "learning_rate": 6.075117370892019e-07, + "epoch": 2.0591805766312596 + }, + { + "current_steps": 1357, + "loss": 2.7332, + "learning_rate": 6.071987480438184e-07, + "epoch": 2.0606980273141122 + }, + { + "current_steps": 1358, + "loss": 2.6328, + "learning_rate": 6.068857589984351e-07, + "epoch": 2.0622154779969653 + }, + { + "current_steps": 1359, + "loss": 2.669, + "learning_rate": 6.065727699530517e-07, + "epoch": 2.063732928679818 + }, + { + "current_steps": 1360, + "loss": 2.6856, + "learning_rate": 6.062597809076681e-07, + "epoch": 2.065250379362671 + }, + { + "current_steps": 1361, + "loss": 2.836, + "learning_rate": 6.059467918622848e-07, + "epoch": 2.0667678300455234 + }, + { + "current_steps": 1362, + "loss": 2.4376, + "learning_rate": 6.056338028169013e-07, + "epoch": 2.0682852807283765 + }, + { + "current_steps": 1363, + "loss": 2.5733, + "learning_rate": 6.05320813771518e-07, + "epoch": 2.069802731411229 + }, + { + "current_steps": 1364, + "loss": 2.6894, + "learning_rate": 6.050078247261345e-07, + "epoch": 2.071320182094082 + }, + { + "current_steps": 1365, + "loss": 2.602, + "learning_rate": 6.046948356807512e-07, + "epoch": 2.0728376327769347 + }, + { + "current_steps": 1366, + "loss": 2.708, + "learning_rate": 6.043818466353678e-07, + "epoch": 2.0743550834597877 + }, + { + "current_steps": 1367, + "loss": 2.5989, + "learning_rate": 6.040688575899842e-07, + "epoch": 2.0758725341426403 + }, + { + "current_steps": 1368, + "loss": 2.7784, + "learning_rate": 6.037558685446009e-07, + "epoch": 2.0773899848254933 + }, + { + "current_steps": 1369, + "loss": 2.5414, + "learning_rate": 6.034428794992174e-07, + "epoch": 2.078907435508346 + }, + { + "current_steps": 1370, + "loss": 2.4192, + "learning_rate": 6.031298904538341e-07, + "epoch": 2.080424886191199 + }, + { + "current_steps": 1371, + "loss": 2.5567, + "learning_rate": 6.028169014084507e-07, + "epoch": 2.0819423368740515 + }, + { + "current_steps": 1372, + "loss": 2.7881, + "learning_rate": 6.025039123630673e-07, + "epoch": 2.0834597875569045 + }, + { + "current_steps": 1373, + "loss": 2.591, + "learning_rate": 6.021909233176839e-07, + "epoch": 2.084977238239757 + }, + { + "current_steps": 1374, + "loss": 2.7796, + "learning_rate": 6.018779342723005e-07, + "epoch": 2.08649468892261 + }, + { + "current_steps": 1375, + "loss": 2.6391, + "learning_rate": 6.01564945226917e-07, + "epoch": 2.0880121396054627 + }, + { + "current_steps": 1376, + "loss": 2.3996, + "learning_rate": 6.012519561815335e-07, + "epoch": 2.0895295902883158 + }, + { + "current_steps": 1377, + "loss": 2.5673, + "learning_rate": 6.009389671361502e-07, + "epoch": 2.0910470409711683 + }, + { + "current_steps": 1378, + "loss": 2.562, + "learning_rate": 6.006259780907668e-07, + "epoch": 2.0925644916540214 + }, + { + "current_steps": 1379, + "loss": 2.5885, + "learning_rate": 6.003129890453834e-07, + "epoch": 2.094081942336874 + }, + { + "current_steps": 1380, + "loss": 2.7276, + "learning_rate": 6e-07, + "epoch": 2.095599393019727 + }, + { + "current_steps": 1381, + "loss": 2.5377, + "learning_rate": 5.996870109546166e-07, + "epoch": 2.0971168437025796 + }, + { + "current_steps": 1382, + "loss": 2.633, + "learning_rate": 5.993740219092331e-07, + "epoch": 2.0986342943854326 + }, + { + "current_steps": 1383, + "loss": 2.6867, + "learning_rate": 5.990610328638498e-07, + "epoch": 2.100151745068285 + }, + { + "current_steps": 1384, + "loss": 2.7953, + "learning_rate": 5.987480438184663e-07, + "epoch": 2.101669195751138 + }, + { + "current_steps": 1385, + "loss": 2.5168, + "learning_rate": 5.984350547730829e-07, + "epoch": 2.103186646433991 + }, + { + "current_steps": 1386, + "loss": 2.499, + "learning_rate": 5.981220657276995e-07, + "epoch": 2.104704097116844 + }, + { + "current_steps": 1387, + "loss": 2.7314, + "learning_rate": 5.978090766823161e-07, + "epoch": 2.1062215477996964 + }, + { + "current_steps": 1388, + "loss": 2.6643, + "learning_rate": 5.974960876369327e-07, + "epoch": 2.1077389984825494 + }, + { + "current_steps": 1389, + "loss": 2.4853, + "learning_rate": 5.971830985915492e-07, + "epoch": 2.109256449165402 + }, + { + "current_steps": 1390, + "loss": 2.4967, + "learning_rate": 5.968701095461659e-07, + "epoch": 2.110773899848255 + }, + { + "current_steps": 1391, + "loss": 2.0279, + "learning_rate": 5.965571205007824e-07, + "epoch": 2.1122913505311076 + }, + { + "current_steps": 1392, + "loss": 2.7255, + "learning_rate": 5.96244131455399e-07, + "epoch": 2.1138088012139606 + }, + { + "current_steps": 1393, + "loss": 2.5191, + "learning_rate": 5.959311424100156e-07, + "epoch": 2.1153262518968132 + }, + { + "current_steps": 1394, + "loss": 2.6303, + "learning_rate": 5.956181533646322e-07, + "epoch": 2.1168437025796663 + }, + { + "current_steps": 1395, + "loss": 2.6014, + "learning_rate": 5.953051643192489e-07, + "epoch": 2.118361153262519 + }, + { + "current_steps": 1396, + "loss": 2.6301, + "learning_rate": 5.949921752738654e-07, + "epoch": 2.119878603945372 + }, + { + "current_steps": 1397, + "loss": 2.5133, + "learning_rate": 5.94679186228482e-07, + "epoch": 2.1213960546282244 + }, + { + "current_steps": 1398, + "loss": 2.5753, + "learning_rate": 5.943661971830985e-07, + "epoch": 2.1229135053110775 + }, + { + "current_steps": 1399, + "loss": 2.4372, + "learning_rate": 5.940532081377152e-07, + "epoch": 2.12443095599393 + }, + { + "current_steps": 1400, + "loss": 2.7082, + "learning_rate": 5.937402190923317e-07, + "epoch": 2.125948406676783 + }, + { + "current_steps": 1401, + "loss": 2.6832, + "learning_rate": 5.934272300469483e-07, + "epoch": 2.1274658573596357 + }, + { + "current_steps": 1402, + "loss": 2.7925, + "learning_rate": 5.93114241001565e-07, + "epoch": 2.1289833080424887 + }, + { + "current_steps": 1403, + "loss": 2.5164, + "learning_rate": 5.928012519561815e-07, + "epoch": 2.1305007587253413 + }, + { + "current_steps": 1404, + "loss": 2.6148, + "learning_rate": 5.924882629107981e-07, + "epoch": 2.1320182094081943 + }, + { + "current_steps": 1405, + "loss": 2.6336, + "learning_rate": 5.921752738654146e-07, + "epoch": 2.133535660091047 + }, + { + "current_steps": 1406, + "loss": 2.8894, + "learning_rate": 5.918622848200313e-07, + "epoch": 2.1350531107739 + }, + { + "current_steps": 1407, + "loss": 2.1882, + "learning_rate": 5.915492957746478e-07, + "epoch": 2.1365705614567525 + }, + { + "current_steps": 1408, + "loss": 2.5814, + "learning_rate": 5.912363067292645e-07, + "epoch": 2.1380880121396055 + }, + { + "current_steps": 1409, + "loss": 2.5057, + "learning_rate": 5.909233176838811e-07, + "epoch": 2.139605462822458 + }, + { + "current_steps": 1410, + "loss": 2.4919, + "learning_rate": 5.906103286384976e-07, + "epoch": 2.141122913505311 + }, + { + "current_steps": 1411, + "loss": 2.6927, + "learning_rate": 5.902973395931142e-07, + "epoch": 2.1426403641881637 + }, + { + "current_steps": 1412, + "loss": 2.5574, + "learning_rate": 5.899843505477307e-07, + "epoch": 2.1441578148710168 + }, + { + "current_steps": 1413, + "loss": 2.4501, + "learning_rate": 5.896713615023474e-07, + "epoch": 2.1456752655538693 + }, + { + "current_steps": 1414, + "loss": 2.6277, + "learning_rate": 5.89358372456964e-07, + "epoch": 2.1471927162367224 + }, + { + "current_steps": 1415, + "loss": 2.7256, + "learning_rate": 5.890453834115806e-07, + "epoch": 2.148710166919575 + }, + { + "current_steps": 1416, + "loss": 2.6706, + "learning_rate": 5.887323943661972e-07, + "epoch": 2.150227617602428 + }, + { + "current_steps": 1417, + "loss": 2.285, + "learning_rate": 5.884194053208138e-07, + "epoch": 2.1517450682852806 + }, + { + "current_steps": 1418, + "loss": 2.581, + "learning_rate": 5.881064162754304e-07, + "epoch": 2.1532625189681336 + }, + { + "current_steps": 1419, + "loss": 2.7162, + "learning_rate": 5.877934272300468e-07, + "epoch": 2.154779969650986 + }, + { + "current_steps": 1420, + "loss": 2.5513, + "learning_rate": 5.874804381846635e-07, + "epoch": 2.156297420333839 + }, + { + "current_steps": 1421, + "loss": 2.4325, + "learning_rate": 5.871674491392801e-07, + "epoch": 2.157814871016692 + }, + { + "current_steps": 1422, + "loss": 2.5977, + "learning_rate": 5.868544600938967e-07, + "epoch": 2.159332321699545 + }, + { + "current_steps": 1423, + "loss": 2.239, + "learning_rate": 5.865414710485133e-07, + "epoch": 2.1608497723823974 + }, + { + "current_steps": 1424, + "loss": 2.6608, + "learning_rate": 5.862284820031299e-07, + "epoch": 2.1623672230652504 + }, + { + "current_steps": 1425, + "loss": 2.6664, + "learning_rate": 5.859154929577465e-07, + "epoch": 2.163884673748103 + }, + { + "current_steps": 1426, + "loss": 2.4875, + "learning_rate": 5.85602503912363e-07, + "epoch": 2.165402124430956 + }, + { + "current_steps": 1427, + "loss": 2.5724, + "learning_rate": 5.852895148669796e-07, + "epoch": 2.1669195751138086 + }, + { + "current_steps": 1428, + "loss": 2.3397, + "learning_rate": 5.849765258215962e-07, + "epoch": 2.1684370257966616 + }, + { + "current_steps": 1429, + "loss": 2.6394, + "learning_rate": 5.846635367762128e-07, + "epoch": 2.1699544764795142 + }, + { + "current_steps": 1430, + "loss": 2.7428, + "learning_rate": 5.843505477308294e-07, + "epoch": 2.1714719271623673 + }, + { + "current_steps": 1431, + "loss": 2.7245, + "learning_rate": 5.84037558685446e-07, + "epoch": 2.17298937784522 + }, + { + "current_steps": 1432, + "loss": 2.5268, + "learning_rate": 5.837245696400626e-07, + "epoch": 2.174506828528073 + }, + { + "current_steps": 1433, + "loss": 2.719, + "learning_rate": 5.834115805946792e-07, + "epoch": 2.1760242792109254 + }, + { + "current_steps": 1434, + "loss": 2.6182, + "learning_rate": 5.830985915492957e-07, + "epoch": 2.1775417298937785 + }, + { + "current_steps": 1435, + "loss": 2.3724, + "learning_rate": 5.827856025039123e-07, + "epoch": 2.179059180576631 + }, + { + "current_steps": 1436, + "loss": 2.6857, + "learning_rate": 5.824726134585289e-07, + "epoch": 2.180576631259484 + }, + { + "current_steps": 1437, + "loss": 2.5512, + "learning_rate": 5.821596244131455e-07, + "epoch": 2.1820940819423367 + }, + { + "current_steps": 1438, + "loss": 2.3613, + "learning_rate": 5.818466353677622e-07, + "epoch": 2.1836115326251897 + }, + { + "current_steps": 1439, + "loss": 2.5811, + "learning_rate": 5.815336463223787e-07, + "epoch": 2.1851289833080423 + }, + { + "current_steps": 1440, + "loss": 2.6232, + "learning_rate": 5.812206572769954e-07, + "epoch": 2.1866464339908953 + }, + { + "current_steps": 1441, + "loss": 2.5085, + "learning_rate": 5.809076682316118e-07, + "epoch": 2.188163884673748 + }, + { + "current_steps": 1442, + "loss": 2.6375, + "learning_rate": 5.805946791862285e-07, + "epoch": 2.189681335356601 + }, + { + "current_steps": 1443, + "loss": 2.9656, + "learning_rate": 5.80281690140845e-07, + "epoch": 2.191198786039454 + }, + { + "current_steps": 1444, + "loss": 2.7663, + "learning_rate": 5.799687010954616e-07, + "epoch": 2.1927162367223065 + }, + { + "current_steps": 1445, + "loss": 2.3824, + "learning_rate": 5.796557120500783e-07, + "epoch": 2.194233687405159 + }, + { + "current_steps": 1446, + "loss": 2.2048, + "learning_rate": 5.793427230046948e-07, + "epoch": 2.195751138088012 + }, + { + "current_steps": 1447, + "loss": 2.4429, + "learning_rate": 5.790297339593115e-07, + "epoch": 2.197268588770865 + }, + { + "current_steps": 1448, + "loss": 2.7717, + "learning_rate": 5.787167449139279e-07, + "epoch": 2.1987860394537178 + }, + { + "current_steps": 1449, + "loss": 2.5658, + "learning_rate": 5.784037558685446e-07, + "epoch": 2.2003034901365703 + }, + { + "current_steps": 1450, + "loss": 2.4431, + "learning_rate": 5.780907668231611e-07, + "epoch": 2.2018209408194234 + }, + { + "current_steps": 1451, + "loss": 2.8375, + "learning_rate": 5.777777777777777e-07, + "epoch": 2.2033383915022764 + }, + { + "current_steps": 1452, + "loss": 2.6723, + "learning_rate": 5.774647887323944e-07, + "epoch": 2.204855842185129 + }, + { + "current_steps": 1453, + "loss": 2.2829, + "learning_rate": 5.771517996870109e-07, + "epoch": 2.2063732928679816 + }, + { + "current_steps": 1454, + "loss": 2.6572, + "learning_rate": 5.768388106416276e-07, + "epoch": 2.2078907435508346 + }, + { + "current_steps": 1455, + "loss": 2.6608, + "learning_rate": 5.76525821596244e-07, + "epoch": 2.2094081942336876 + }, + { + "current_steps": 1456, + "loss": 2.7334, + "learning_rate": 5.762128325508607e-07, + "epoch": 2.21092564491654 + }, + { + "current_steps": 1457, + "loss": 2.67, + "learning_rate": 5.758998435054773e-07, + "epoch": 2.212443095599393 + }, + { + "current_steps": 1458, + "loss": 2.5568, + "learning_rate": 5.755868544600939e-07, + "epoch": 2.213960546282246 + }, + { + "current_steps": 1459, + "loss": 2.5783, + "learning_rate": 5.752738654147105e-07, + "epoch": 2.215477996965099 + }, + { + "current_steps": 1460, + "loss": 2.6967, + "learning_rate": 5.74960876369327e-07, + "epoch": 2.2169954476479514 + }, + { + "current_steps": 1461, + "loss": 2.1546, + "learning_rate": 5.746478873239437e-07, + "epoch": 2.2185128983308045 + }, + { + "current_steps": 1462, + "loss": 2.5936, + "learning_rate": 5.743348982785601e-07, + "epoch": 2.220030349013657 + }, + { + "current_steps": 1463, + "loss": 2.7278, + "learning_rate": 5.740219092331768e-07, + "epoch": 2.22154779969651 + }, + { + "current_steps": 1464, + "loss": 2.4835, + "learning_rate": 5.737089201877934e-07, + "epoch": 2.2230652503793626 + }, + { + "current_steps": 1465, + "loss": 2.5749, + "learning_rate": 5.7339593114241e-07, + "epoch": 2.2245827010622157 + }, + { + "current_steps": 1466, + "loss": 2.581, + "learning_rate": 5.730829420970266e-07, + "epoch": 2.2261001517450683 + }, + { + "current_steps": 1467, + "loss": 2.4602, + "learning_rate": 5.727699530516432e-07, + "epoch": 2.2276176024279213 + }, + { + "current_steps": 1468, + "loss": 2.558, + "learning_rate": 5.724569640062598e-07, + "epoch": 2.229135053110774 + }, + { + "current_steps": 1469, + "loss": 2.5131, + "learning_rate": 5.721439749608763e-07, + "epoch": 2.230652503793627 + }, + { + "current_steps": 1470, + "loss": 2.709, + "learning_rate": 5.718309859154929e-07, + "epoch": 2.2321699544764795 + }, + { + "current_steps": 1471, + "loss": 2.7032, + "learning_rate": 5.715179968701095e-07, + "epoch": 2.2336874051593325 + }, + { + "current_steps": 1472, + "loss": 2.5537, + "learning_rate": 5.712050078247261e-07, + "epoch": 2.235204855842185 + }, + { + "current_steps": 1473, + "loss": 2.6682, + "learning_rate": 5.708920187793427e-07, + "epoch": 2.236722306525038 + }, + { + "current_steps": 1474, + "loss": 2.4767, + "learning_rate": 5.705790297339593e-07, + "epoch": 2.2382397572078907 + }, + { + "current_steps": 1475, + "loss": 2.7505, + "learning_rate": 5.702660406885759e-07, + "epoch": 2.2397572078907437 + }, + { + "current_steps": 1476, + "loss": 2.4823, + "learning_rate": 5.699530516431926e-07, + "epoch": 2.2412746585735963 + }, + { + "current_steps": 1477, + "loss": 2.8422, + "learning_rate": 5.69640062597809e-07, + "epoch": 2.2427921092564493 + }, + { + "current_steps": 1478, + "loss": 2.5519, + "learning_rate": 5.693270735524256e-07, + "epoch": 2.244309559939302 + }, + { + "current_steps": 1479, + "loss": 2.743, + "learning_rate": 5.690140845070422e-07, + "epoch": 2.245827010622155 + }, + { + "current_steps": 1480, + "loss": 2.4704, + "learning_rate": 5.687010954616588e-07, + "epoch": 2.2473444613050075 + }, + { + "current_steps": 1481, + "loss": 2.587, + "learning_rate": 5.683881064162755e-07, + "epoch": 2.2488619119878606 + }, + { + "current_steps": 1482, + "loss": 2.5503, + "learning_rate": 5.68075117370892e-07, + "epoch": 2.250379362670713 + }, + { + "current_steps": 1483, + "loss": 2.5498, + "learning_rate": 5.677621283255087e-07, + "epoch": 2.251896813353566 + }, + { + "current_steps": 1484, + "loss": 2.3865, + "learning_rate": 5.674491392801251e-07, + "epoch": 2.2534142640364188 + }, + { + "current_steps": 1485, + "loss": 2.762, + "learning_rate": 5.671361502347417e-07, + "epoch": 2.254931714719272 + }, + { + "current_steps": 1486, + "loss": 2.671, + "learning_rate": 5.668231611893583e-07, + "epoch": 2.2564491654021244 + }, + { + "current_steps": 1487, + "loss": 2.7156, + "learning_rate": 5.665101721439749e-07, + "epoch": 2.2579666160849774 + }, + { + "current_steps": 1488, + "loss": 2.7018, + "learning_rate": 5.661971830985916e-07, + "epoch": 2.25948406676783 + }, + { + "current_steps": 1489, + "loss": 2.4556, + "learning_rate": 5.658841940532081e-07, + "epoch": 2.261001517450683 + }, + { + "current_steps": 1490, + "loss": 2.6177, + "learning_rate": 5.655712050078248e-07, + "epoch": 2.2625189681335356 + }, + { + "current_steps": 1491, + "loss": 2.4934, + "learning_rate": 5.652582159624412e-07, + "epoch": 2.2640364188163886 + }, + { + "current_steps": 1492, + "loss": 2.5629, + "learning_rate": 5.649452269170579e-07, + "epoch": 2.265553869499241 + }, + { + "current_steps": 1493, + "loss": 2.5203, + "learning_rate": 5.646322378716744e-07, + "epoch": 2.2670713201820942 + }, + { + "current_steps": 1494, + "loss": 2.5837, + "learning_rate": 5.64319248826291e-07, + "epoch": 2.268588770864947 + }, + { + "current_steps": 1495, + "loss": 2.6761, + "learning_rate": 5.640062597809077e-07, + "epoch": 2.2701062215478 + }, + { + "current_steps": 1496, + "loss": 2.6451, + "learning_rate": 5.636932707355242e-07, + "epoch": 2.2716236722306524 + }, + { + "current_steps": 1497, + "loss": 2.5329, + "learning_rate": 5.633802816901409e-07, + "epoch": 2.2731411229135055 + }, + { + "current_steps": 1498, + "loss": 2.5377, + "learning_rate": 5.630672926447573e-07, + "epoch": 2.274658573596358 + }, + { + "current_steps": 1499, + "loss": 2.3915, + "learning_rate": 5.62754303599374e-07, + "epoch": 2.276176024279211 + }, + { + "current_steps": 1500, + "loss": 2.6888, + "learning_rate": 5.624413145539906e-07, + "epoch": 2.2776934749620636 + }, + { + "current_steps": 1501, + "loss": 2.536, + "learning_rate": 5.621283255086072e-07, + "epoch": 2.2792109256449167 + }, + { + "current_steps": 1502, + "loss": 2.6012, + "learning_rate": 5.618153364632238e-07, + "epoch": 2.2807283763277693 + }, + { + "current_steps": 1503, + "loss": 2.4499, + "learning_rate": 5.615023474178403e-07, + "epoch": 2.2822458270106223 + }, + { + "current_steps": 1504, + "loss": 2.6459, + "learning_rate": 5.61189358372457e-07, + "epoch": 2.283763277693475 + }, + { + "current_steps": 1505, + "loss": 2.7645, + "learning_rate": 5.608763693270734e-07, + "epoch": 2.285280728376328 + }, + { + "current_steps": 1506, + "loss": 2.4969, + "learning_rate": 5.605633802816901e-07, + "epoch": 2.2867981790591805 + }, + { + "current_steps": 1507, + "loss": 2.5639, + "learning_rate": 5.602503912363067e-07, + "epoch": 2.2883156297420335 + }, + { + "current_steps": 1508, + "loss": 2.9699, + "learning_rate": 5.599374021909233e-07, + "epoch": 2.289833080424886 + }, + { + "current_steps": 1509, + "loss": 2.5037, + "learning_rate": 5.596244131455399e-07, + "epoch": 2.291350531107739 + }, + { + "current_steps": 1510, + "loss": 2.7138, + "learning_rate": 5.593114241001564e-07, + "epoch": 2.2928679817905917 + }, + { + "current_steps": 1511, + "loss": 2.8392, + "learning_rate": 5.589984350547731e-07, + "epoch": 2.2943854324734447 + }, + { + "current_steps": 1512, + "loss": 2.6229, + "learning_rate": 5.586854460093897e-07, + "epoch": 2.2959028831562973 + }, + { + "current_steps": 1513, + "loss": 2.6719, + "learning_rate": 5.583724569640062e-07, + "epoch": 2.2974203338391503 + }, + { + "current_steps": 1514, + "loss": 2.7165, + "learning_rate": 5.580594679186228e-07, + "epoch": 2.298937784522003 + }, + { + "current_steps": 1515, + "loss": 2.8382, + "learning_rate": 5.577464788732394e-07, + "epoch": 2.300455235204856 + }, + { + "current_steps": 1516, + "loss": 2.6035, + "learning_rate": 5.57433489827856e-07, + "epoch": 2.3019726858877085 + }, + { + "current_steps": 1517, + "loss": 2.6164, + "learning_rate": 5.571205007824726e-07, + "epoch": 2.3034901365705616 + }, + { + "current_steps": 1518, + "loss": 2.5765, + "learning_rate": 5.568075117370892e-07, + "epoch": 2.305007587253414 + }, + { + "current_steps": 1519, + "loss": 2.5311, + "learning_rate": 5.564945226917058e-07, + "epoch": 2.306525037936267 + }, + { + "current_steps": 1520, + "loss": 2.8214, + "learning_rate": 5.561815336463223e-07, + "epoch": 2.3080424886191198 + }, + { + "current_steps": 1521, + "loss": 2.545, + "learning_rate": 5.558685446009389e-07, + "epoch": 2.309559939301973 + }, + { + "current_steps": 1522, + "loss": 2.556, + "learning_rate": 5.555555555555555e-07, + "epoch": 2.3110773899848254 + }, + { + "current_steps": 1523, + "loss": 2.6808, + "learning_rate": 5.552425665101721e-07, + "epoch": 2.3125948406676784 + }, + { + "current_steps": 1524, + "loss": 2.6542, + "learning_rate": 5.549295774647888e-07, + "epoch": 2.314112291350531 + }, + { + "current_steps": 1525, + "loss": 2.6761, + "learning_rate": 5.546165884194053e-07, + "epoch": 2.315629742033384 + }, + { + "current_steps": 1526, + "loss": 2.7262, + "learning_rate": 5.54303599374022e-07, + "epoch": 2.3171471927162366 + }, + { + "current_steps": 1527, + "loss": 2.3008, + "learning_rate": 5.539906103286384e-07, + "epoch": 2.3186646433990896 + }, + { + "current_steps": 1528, + "loss": 2.4754, + "learning_rate": 5.53677621283255e-07, + "epoch": 2.320182094081942 + }, + { + "current_steps": 1529, + "loss": 2.3158, + "learning_rate": 5.533646322378716e-07, + "epoch": 2.3216995447647952 + }, + { + "current_steps": 1530, + "loss": 2.502, + "learning_rate": 5.530516431924882e-07, + "epoch": 2.323216995447648 + }, + { + "current_steps": 1531, + "loss": 2.7423, + "learning_rate": 5.527386541471049e-07, + "epoch": 2.324734446130501 + }, + { + "current_steps": 1532, + "loss": 2.7317, + "learning_rate": 5.524256651017214e-07, + "epoch": 2.3262518968133534 + }, + { + "current_steps": 1533, + "loss": 2.6384, + "learning_rate": 5.521126760563381e-07, + "epoch": 2.3277693474962065 + }, + { + "current_steps": 1534, + "loss": 2.4915, + "learning_rate": 5.517996870109546e-07, + "epoch": 2.329286798179059 + }, + { + "current_steps": 1535, + "loss": 2.66, + "learning_rate": 5.514866979655712e-07, + "epoch": 2.330804248861912 + }, + { + "current_steps": 1536, + "loss": 2.9893, + "learning_rate": 5.511737089201877e-07, + "epoch": 2.3323216995447646 + }, + { + "current_steps": 1537, + "loss": 2.1353, + "learning_rate": 5.508607198748043e-07, + "epoch": 2.3338391502276177 + }, + { + "current_steps": 1538, + "loss": 2.6129, + "learning_rate": 5.50547730829421e-07, + "epoch": 2.3353566009104703 + }, + { + "current_steps": 1539, + "loss": 2.6382, + "learning_rate": 5.502347417840375e-07, + "epoch": 2.3368740515933233 + }, + { + "current_steps": 1540, + "loss": 2.706, + "learning_rate": 5.499217527386542e-07, + "epoch": 2.338391502276176 + }, + { + "current_steps": 1541, + "loss": 2.615, + "learning_rate": 5.496087636932707e-07, + "epoch": 2.339908952959029 + }, + { + "current_steps": 1542, + "loss": 2.4563, + "learning_rate": 5.492957746478873e-07, + "epoch": 2.3414264036418815 + }, + { + "current_steps": 1543, + "loss": 2.7434, + "learning_rate": 5.489827856025039e-07, + "epoch": 2.3429438543247345 + }, + { + "current_steps": 1544, + "loss": 2.7087, + "learning_rate": 5.486697965571204e-07, + "epoch": 2.344461305007587 + }, + { + "current_steps": 1545, + "loss": 2.4953, + "learning_rate": 5.483568075117371e-07, + "epoch": 2.34597875569044 + }, + { + "current_steps": 1546, + "loss": 2.5007, + "learning_rate": 5.480438184663536e-07, + "epoch": 2.3474962063732927 + }, + { + "current_steps": 1547, + "loss": 2.6176, + "learning_rate": 5.477308294209703e-07, + "epoch": 2.3490136570561457 + }, + { + "current_steps": 1548, + "loss": 2.5873, + "learning_rate": 5.474178403755868e-07, + "epoch": 2.3505311077389983 + }, + { + "current_steps": 1549, + "loss": 2.8637, + "learning_rate": 5.471048513302034e-07, + "epoch": 2.3520485584218513 + }, + { + "current_steps": 1550, + "loss": 2.6718, + "learning_rate": 5.4679186228482e-07, + "epoch": 2.353566009104704 + }, + { + "current_steps": 1551, + "loss": 2.5844, + "learning_rate": 5.464788732394366e-07, + "epoch": 2.355083459787557 + }, + { + "current_steps": 1552, + "loss": 2.684, + "learning_rate": 5.461658841940532e-07, + "epoch": 2.3566009104704095 + }, + { + "current_steps": 1553, + "loss": 2.6584, + "learning_rate": 5.458528951486697e-07, + "epoch": 2.3581183611532626 + }, + { + "current_steps": 1554, + "loss": 2.6848, + "learning_rate": 5.455399061032864e-07, + "epoch": 2.359635811836115 + }, + { + "current_steps": 1555, + "loss": 2.6988, + "learning_rate": 5.452269170579029e-07, + "epoch": 2.361153262518968 + }, + { + "current_steps": 1556, + "loss": 2.5181, + "learning_rate": 5.449139280125196e-07, + "epoch": 2.3626707132018208 + }, + { + "current_steps": 1557, + "loss": 2.2624, + "learning_rate": 5.446009389671361e-07, + "epoch": 2.364188163884674 + }, + { + "current_steps": 1558, + "loss": 2.3037, + "learning_rate": 5.442879499217527e-07, + "epoch": 2.3657056145675264 + }, + { + "current_steps": 1559, + "loss": 2.8184, + "learning_rate": 5.439749608763693e-07, + "epoch": 2.3672230652503794 + }, + { + "current_steps": 1560, + "loss": 2.5617, + "learning_rate": 5.436619718309859e-07, + "epoch": 2.368740515933232 + }, + { + "current_steps": 1561, + "loss": 2.724, + "learning_rate": 5.433489827856025e-07, + "epoch": 2.370257966616085 + }, + { + "current_steps": 1562, + "loss": 2.5149, + "learning_rate": 5.430359937402191e-07, + "epoch": 2.3717754172989376 + }, + { + "current_steps": 1563, + "loss": 2.6886, + "learning_rate": 5.427230046948357e-07, + "epoch": 2.3732928679817906 + }, + { + "current_steps": 1564, + "loss": 2.6376, + "learning_rate": 5.424100156494522e-07, + "epoch": 2.374810318664643 + }, + { + "current_steps": 1565, + "loss": 2.8739, + "learning_rate": 5.420970266040688e-07, + "epoch": 2.3763277693474962 + }, + { + "current_steps": 1566, + "loss": 2.7766, + "learning_rate": 5.417840375586854e-07, + "epoch": 2.3778452200303493 + }, + { + "current_steps": 1567, + "loss": 2.6251, + "learning_rate": 5.414710485133021e-07, + "epoch": 2.379362670713202 + }, + { + "current_steps": 1568, + "loss": 2.7869, + "learning_rate": 5.411580594679186e-07, + "epoch": 2.3808801213960544 + }, + { + "current_steps": 1569, + "loss": 2.6281, + "learning_rate": 5.408450704225352e-07, + "epoch": 2.3823975720789075 + }, + { + "current_steps": 1570, + "loss": 2.6086, + "learning_rate": 5.405320813771518e-07, + "epoch": 2.3839150227617605 + }, + { + "current_steps": 1571, + "loss": 2.6949, + "learning_rate": 5.402190923317683e-07, + "epoch": 2.385432473444613 + }, + { + "current_steps": 1572, + "loss": 2.7593, + "learning_rate": 5.399061032863849e-07, + "epoch": 2.3869499241274656 + }, + { + "current_steps": 1573, + "loss": 2.4489, + "learning_rate": 5.395931142410015e-07, + "epoch": 2.3884673748103187 + }, + { + "current_steps": 1574, + "loss": 2.6939, + "learning_rate": 5.392801251956182e-07, + "epoch": 2.3899848254931717 + }, + { + "current_steps": 1575, + "loss": 2.6694, + "learning_rate": 5.389671361502347e-07, + "epoch": 2.3915022761760243 + }, + { + "current_steps": 1576, + "loss": 2.5852, + "learning_rate": 5.386541471048514e-07, + "epoch": 2.393019726858877 + }, + { + "current_steps": 1577, + "loss": 2.5841, + "learning_rate": 5.383411580594679e-07, + "epoch": 2.39453717754173 + }, + { + "current_steps": 1578, + "loss": 2.5556, + "learning_rate": 5.380281690140844e-07, + "epoch": 2.396054628224583 + }, + { + "current_steps": 1579, + "loss": 2.6525, + "learning_rate": 5.37715179968701e-07, + "epoch": 2.3975720789074355 + }, + { + "current_steps": 1580, + "loss": 2.0741, + "learning_rate": 5.374021909233176e-07, + "epoch": 2.399089529590288 + }, + { + "current_steps": 1581, + "loss": 2.5847, + "learning_rate": 5.370892018779343e-07, + "epoch": 2.400606980273141 + }, + { + "current_steps": 1582, + "loss": 2.385, + "learning_rate": 5.367762128325508e-07, + "epoch": 2.402124430955994 + }, + { + "current_steps": 1583, + "loss": 2.5872, + "learning_rate": 5.364632237871675e-07, + "epoch": 2.4036418816388467 + }, + { + "current_steps": 1584, + "loss": 2.6751, + "learning_rate": 5.36150234741784e-07, + "epoch": 2.4051593323216993 + }, + { + "current_steps": 1585, + "loss": 2.8342, + "learning_rate": 5.358372456964007e-07, + "epoch": 2.4066767830045523 + }, + { + "current_steps": 1586, + "loss": 2.5573, + "learning_rate": 5.355242566510172e-07, + "epoch": 2.4081942336874054 + }, + { + "current_steps": 1587, + "loss": 2.9128, + "learning_rate": 5.352112676056337e-07, + "epoch": 2.409711684370258 + }, + { + "current_steps": 1588, + "loss": 2.6131, + "learning_rate": 5.348982785602504e-07, + "epoch": 2.4112291350531105 + }, + { + "current_steps": 1589, + "loss": 2.7343, + "learning_rate": 5.345852895148669e-07, + "epoch": 2.4127465857359636 + }, + { + "current_steps": 1590, + "loss": 2.6511, + "learning_rate": 5.342723004694836e-07, + "epoch": 2.4142640364188166 + }, + { + "current_steps": 1591, + "loss": 2.5854, + "learning_rate": 5.339593114241001e-07, + "epoch": 2.415781487101669 + }, + { + "current_steps": 1592, + "loss": 2.61, + "learning_rate": 5.336463223787168e-07, + "epoch": 2.4172989377845218 + }, + { + "current_steps": 1593, + "loss": 2.5463, + "learning_rate": 5.333333333333333e-07, + "epoch": 2.418816388467375 + }, + { + "current_steps": 1594, + "loss": 2.6026, + "learning_rate": 5.330203442879499e-07, + "epoch": 2.420333839150228 + }, + { + "current_steps": 1595, + "loss": 2.4274, + "learning_rate": 5.327073552425665e-07, + "epoch": 2.4218512898330804 + }, + { + "current_steps": 1596, + "loss": 2.5328, + "learning_rate": 5.32394366197183e-07, + "epoch": 2.423368740515933 + }, + { + "current_steps": 1597, + "loss": 2.7245, + "learning_rate": 5.320813771517997e-07, + "epoch": 2.424886191198786 + }, + { + "current_steps": 1598, + "loss": 2.7635, + "learning_rate": 5.317683881064162e-07, + "epoch": 2.426403641881639 + }, + { + "current_steps": 1599, + "loss": 2.6509, + "learning_rate": 5.314553990610329e-07, + "epoch": 2.4279210925644916 + }, + { + "current_steps": 1600, + "loss": 2.6039, + "learning_rate": 5.311424100156494e-07, + "epoch": 2.4294385432473447 + }, + { + "current_steps": 1601, + "loss": 2.4946, + "learning_rate": 5.30829420970266e-07, + "epoch": 2.4309559939301972 + }, + { + "current_steps": 1602, + "loss": 2.7799, + "learning_rate": 5.305164319248826e-07, + "epoch": 2.4324734446130503 + }, + { + "current_steps": 1603, + "loss": 2.5104, + "learning_rate": 5.302034428794991e-07, + "epoch": 2.433990895295903 + }, + { + "current_steps": 1604, + "loss": 2.5367, + "learning_rate": 5.298904538341158e-07, + "epoch": 2.435508345978756 + }, + { + "current_steps": 1605, + "loss": 2.4246, + "learning_rate": 5.295774647887324e-07, + "epoch": 2.4370257966616085 + }, + { + "current_steps": 1606, + "loss": 2.6591, + "learning_rate": 5.29264475743349e-07, + "epoch": 2.4385432473444615 + }, + { + "current_steps": 1607, + "loss": 2.5864, + "learning_rate": 5.289514866979656e-07, + "epoch": 2.440060698027314 + }, + { + "current_steps": 1608, + "loss": 2.6838, + "learning_rate": 5.286384976525821e-07, + "epoch": 2.441578148710167 + }, + { + "current_steps": 1609, + "loss": 2.4829, + "learning_rate": 5.283255086071987e-07, + "epoch": 2.4430955993930197 + }, + { + "current_steps": 1610, + "loss": 2.5942, + "learning_rate": 5.280125195618154e-07, + "epoch": 2.4446130500758727 + }, + { + "current_steps": 1611, + "loss": 2.758, + "learning_rate": 5.276995305164319e-07, + "epoch": 2.4461305007587253 + }, + { + "current_steps": 1612, + "loss": 2.6533, + "learning_rate": 5.273865414710485e-07, + "epoch": 2.4476479514415783 + }, + { + "current_steps": 1613, + "loss": 2.4483, + "learning_rate": 5.270735524256651e-07, + "epoch": 2.449165402124431 + }, + { + "current_steps": 1614, + "loss": 2.3925, + "learning_rate": 5.267605633802817e-07, + "epoch": 2.450682852807284 + }, + { + "current_steps": 1615, + "loss": 2.8401, + "learning_rate": 5.264475743348982e-07, + "epoch": 2.4522003034901365 + }, + { + "current_steps": 1616, + "loss": 2.5747, + "learning_rate": 5.261345852895148e-07, + "epoch": 2.4537177541729895 + }, + { + "current_steps": 1617, + "loss": 2.7434, + "learning_rate": 5.258215962441315e-07, + "epoch": 2.455235204855842 + }, + { + "current_steps": 1618, + "loss": 2.4021, + "learning_rate": 5.25508607198748e-07, + "epoch": 2.456752655538695 + }, + { + "current_steps": 1619, + "loss": 2.7495, + "learning_rate": 5.251956181533647e-07, + "epoch": 2.4582701062215477 + }, + { + "current_steps": 1620, + "loss": 2.4359, + "learning_rate": 5.248826291079812e-07, + "epoch": 2.4597875569044008 + }, + { + "current_steps": 1621, + "loss": 2.6389, + "learning_rate": 5.245696400625978e-07, + "epoch": 2.4613050075872533 + }, + { + "current_steps": 1622, + "loss": 2.7096, + "learning_rate": 5.242566510172143e-07, + "epoch": 2.4628224582701064 + }, + { + "current_steps": 1623, + "loss": 2.7798, + "learning_rate": 5.239436619718309e-07, + "epoch": 2.464339908952959 + }, + { + "current_steps": 1624, + "loss": 2.8212, + "learning_rate": 5.236306729264476e-07, + "epoch": 2.465857359635812 + }, + { + "current_steps": 1625, + "loss": 2.4728, + "learning_rate": 5.233176838810641e-07, + "epoch": 2.4673748103186646 + }, + { + "current_steps": 1626, + "loss": 2.6226, + "learning_rate": 5.230046948356808e-07, + "epoch": 2.4688922610015176 + }, + { + "current_steps": 1627, + "loss": 2.5472, + "learning_rate": 5.226917057902973e-07, + "epoch": 2.47040971168437 + }, + { + "current_steps": 1628, + "loss": 2.5537, + "learning_rate": 5.223787167449139e-07, + "epoch": 2.471927162367223 + }, + { + "current_steps": 1629, + "loss": 2.3473, + "learning_rate": 5.220657276995306e-07, + "epoch": 2.473444613050076 + }, + { + "current_steps": 1630, + "loss": 2.6625, + "learning_rate": 5.21752738654147e-07, + "epoch": 2.474962063732929 + }, + { + "current_steps": 1631, + "loss": 2.5809, + "learning_rate": 5.214397496087637e-07, + "epoch": 2.4764795144157814 + }, + { + "current_steps": 1632, + "loss": 2.8554, + "learning_rate": 5.211267605633802e-07, + "epoch": 2.4779969650986344 + }, + { + "current_steps": 1633, + "loss": 2.6699, + "learning_rate": 5.208137715179969e-07, + "epoch": 2.479514415781487 + }, + { + "current_steps": 1634, + "loss": 2.4967, + "learning_rate": 5.205007824726134e-07, + "epoch": 2.48103186646434 + }, + { + "current_steps": 1635, + "loss": 2.6655, + "learning_rate": 5.201877934272301e-07, + "epoch": 2.4825493171471926 + }, + { + "current_steps": 1636, + "loss": 2.8127, + "learning_rate": 5.198748043818467e-07, + "epoch": 2.4840667678300457 + }, + { + "current_steps": 1637, + "loss": 2.5072, + "learning_rate": 5.195618153364631e-07, + "epoch": 2.4855842185128982 + }, + { + "current_steps": 1638, + "loss": 2.6391, + "learning_rate": 5.192488262910798e-07, + "epoch": 2.4871016691957513 + }, + { + "current_steps": 1639, + "loss": 2.5459, + "learning_rate": 5.189358372456963e-07, + "epoch": 2.488619119878604 + }, + { + "current_steps": 1640, + "loss": 2.672, + "learning_rate": 5.18622848200313e-07, + "epoch": 2.490136570561457 + }, + { + "current_steps": 1641, + "loss": 2.6946, + "learning_rate": 5.183098591549295e-07, + "epoch": 2.4916540212443095 + }, + { + "current_steps": 1642, + "loss": 2.5693, + "learning_rate": 5.179968701095462e-07, + "epoch": 2.4931714719271625 + }, + { + "current_steps": 1643, + "loss": 2.4589, + "learning_rate": 5.176838810641628e-07, + "epoch": 2.494688922610015 + }, + { + "current_steps": 1644, + "loss": 2.5856, + "learning_rate": 5.173708920187793e-07, + "epoch": 2.496206373292868 + }, + { + "current_steps": 1645, + "loss": 2.8665, + "learning_rate": 5.170579029733959e-07, + "epoch": 2.4977238239757207 + }, + { + "current_steps": 1646, + "loss": 2.6751, + "learning_rate": 5.167449139280124e-07, + "epoch": 2.4992412746585737 + }, + { + "current_steps": 1647, + "loss": 2.5174, + "learning_rate": 5.164319248826291e-07, + "epoch": 2.5007587253414263 + }, + { + "current_steps": 1648, + "loss": 2.1053, + "learning_rate": 5.161189358372457e-07, + "epoch": 2.5022761760242793 + }, + { + "current_steps": 1649, + "loss": 2.7104, + "learning_rate": 5.158059467918623e-07, + "epoch": 2.503793626707132 + }, + { + "current_steps": 1650, + "loss": 1.9607, + "learning_rate": 5.154929577464789e-07, + "epoch": 2.505311077389985 + }, + { + "current_steps": 1651, + "loss": 2.8276, + "learning_rate": 5.151799687010954e-07, + "epoch": 2.5068285280728375 + }, + { + "current_steps": 1652, + "loss": 2.5554, + "learning_rate": 5.14866979655712e-07, + "epoch": 2.5083459787556905 + }, + { + "current_steps": 1653, + "loss": 2.6291, + "learning_rate": 5.145539906103286e-07, + "epoch": 2.509863429438543 + }, + { + "current_steps": 1654, + "loss": 2.5317, + "learning_rate": 5.142410015649452e-07, + "epoch": 2.511380880121396 + }, + { + "current_steps": 1655, + "loss": 2.5942, + "learning_rate": 5.139280125195618e-07, + "epoch": 2.5128983308042487 + }, + { + "current_steps": 1656, + "loss": 2.6019, + "learning_rate": 5.136150234741784e-07, + "epoch": 2.5144157814871018 + }, + { + "current_steps": 1657, + "loss": 2.6681, + "learning_rate": 5.13302034428795e-07, + "epoch": 2.5159332321699543 + }, + { + "current_steps": 1658, + "loss": 2.5585, + "learning_rate": 5.129890453834115e-07, + "epoch": 2.5174506828528074 + }, + { + "current_steps": 1659, + "loss": 2.5702, + "learning_rate": 5.126760563380281e-07, + "epoch": 2.51896813353566 + }, + { + "current_steps": 1660, + "loss": 2.6203, + "learning_rate": 5.123630672926448e-07, + "epoch": 2.520485584218513 + }, + { + "current_steps": 1661, + "loss": 2.1566, + "learning_rate": 5.120500782472613e-07, + "epoch": 2.5220030349013656 + }, + { + "current_steps": 1662, + "loss": 2.5463, + "learning_rate": 5.117370892018779e-07, + "epoch": 2.5235204855842186 + }, + { + "current_steps": 1663, + "loss": 2.5508, + "learning_rate": 5.114241001564945e-07, + "epoch": 2.525037936267071 + }, + { + "current_steps": 1664, + "loss": 2.5597, + "learning_rate": 5.111111111111111e-07, + "epoch": 2.526555386949924 + }, + { + "current_steps": 1665, + "loss": 2.6467, + "learning_rate": 5.107981220657277e-07, + "epoch": 2.528072837632777 + }, + { + "current_steps": 1666, + "loss": 2.591, + "learning_rate": 5.104851330203442e-07, + "epoch": 2.52959028831563 + }, + { + "current_steps": 1667, + "loss": 3.052, + "learning_rate": 5.101721439749609e-07, + "epoch": 2.5311077389984824 + }, + { + "current_steps": 1668, + "loss": 2.6734, + "learning_rate": 5.098591549295774e-07, + "epoch": 2.5326251896813354 + }, + { + "current_steps": 1669, + "loss": 2.7081, + "learning_rate": 5.095461658841941e-07, + "epoch": 2.534142640364188 + }, + { + "current_steps": 1670, + "loss": 2.5379, + "learning_rate": 5.092331768388106e-07, + "epoch": 2.535660091047041 + }, + { + "current_steps": 1671, + "loss": 2.8155, + "learning_rate": 5.089201877934272e-07, + "epoch": 2.5371775417298936 + }, + { + "current_steps": 1672, + "loss": 2.4689, + "learning_rate": 5.086071987480439e-07, + "epoch": 2.5386949924127467 + }, + { + "current_steps": 1673, + "loss": 2.7178, + "learning_rate": 5.082942097026603e-07, + "epoch": 2.5402124430955992 + }, + { + "current_steps": 1674, + "loss": 2.665, + "learning_rate": 5.07981220657277e-07, + "epoch": 2.5417298937784523 + }, + { + "current_steps": 1675, + "loss": 2.585, + "learning_rate": 5.076682316118935e-07, + "epoch": 2.543247344461305 + }, + { + "current_steps": 1676, + "loss": 2.6375, + "learning_rate": 5.073552425665102e-07, + "epoch": 2.544764795144158 + }, + { + "current_steps": 1677, + "loss": 2.4821, + "learning_rate": 5.070422535211267e-07, + "epoch": 2.5462822458270105 + }, + { + "current_steps": 1678, + "loss": 2.4828, + "learning_rate": 5.067292644757434e-07, + "epoch": 2.5477996965098635 + }, + { + "current_steps": 1679, + "loss": 2.4881, + "learning_rate": 5.0641627543036e-07, + "epoch": 2.549317147192716 + }, + { + "current_steps": 1680, + "loss": 2.5826, + "learning_rate": 5.061032863849764e-07, + "epoch": 2.550834597875569 + }, + { + "current_steps": 1681, + "loss": 2.6624, + "learning_rate": 5.057902973395931e-07, + "epoch": 2.552352048558422 + }, + { + "current_steps": 1682, + "loss": 2.6803, + "learning_rate": 5.054773082942096e-07, + "epoch": 2.5538694992412747 + }, + { + "current_steps": 1683, + "loss": 2.5849, + "learning_rate": 5.051643192488263e-07, + "epoch": 2.5553869499241273 + }, + { + "current_steps": 1684, + "loss": 2.8364, + "learning_rate": 5.048513302034428e-07, + "epoch": 2.5569044006069803 + }, + { + "current_steps": 1685, + "loss": 2.65, + "learning_rate": 5.045383411580595e-07, + "epoch": 2.5584218512898333 + }, + { + "current_steps": 1686, + "loss": 2.5379, + "learning_rate": 5.042253521126761e-07, + "epoch": 2.559939301972686 + }, + { + "current_steps": 1687, + "loss": 2.6532, + "learning_rate": 5.039123630672925e-07, + "epoch": 2.5614567526555385 + }, + { + "current_steps": 1688, + "loss": 2.7475, + "learning_rate": 5.035993740219092e-07, + "epoch": 2.5629742033383915 + }, + { + "current_steps": 1689, + "loss": 2.885, + "learning_rate": 5.032863849765257e-07, + "epoch": 2.5644916540212446 + }, + { + "current_steps": 1690, + "loss": 2.2614, + "learning_rate": 5.029733959311424e-07, + "epoch": 2.566009104704097 + }, + { + "current_steps": 1691, + "loss": 2.4554, + "learning_rate": 5.02660406885759e-07, + "epoch": 2.5675265553869497 + }, + { + "current_steps": 1692, + "loss": 2.5807, + "learning_rate": 5.023474178403756e-07, + "epoch": 2.5690440060698028 + }, + { + "current_steps": 1693, + "loss": 2.6579, + "learning_rate": 5.020344287949922e-07, + "epoch": 2.570561456752656 + }, + { + "current_steps": 1694, + "loss": 2.4734, + "learning_rate": 5.017214397496088e-07, + "epoch": 2.5720789074355084 + }, + { + "current_steps": 1695, + "loss": 2.8139, + "learning_rate": 5.014084507042253e-07, + "epoch": 2.573596358118361 + }, + { + "current_steps": 1696, + "loss": 2.4491, + "learning_rate": 5.010954616588418e-07, + "epoch": 2.575113808801214 + }, + { + "current_steps": 1697, + "loss": 2.6297, + "learning_rate": 5.007824726134585e-07, + "epoch": 2.576631259484067 + }, + { + "current_steps": 1698, + "loss": 2.452, + "learning_rate": 5.004694835680751e-07, + "epoch": 2.5781487101669196 + }, + { + "current_steps": 1699, + "loss": 2.4067, + "learning_rate": 5.001564945226917e-07, + "epoch": 2.579666160849772 + }, + { + "current_steps": 1700, + "loss": 2.6476, + "learning_rate": 4.998435054773083e-07, + "epoch": 2.581183611532625 + }, + { + "current_steps": 1701, + "loss": 2.5637, + "learning_rate": 4.995305164319249e-07, + "epoch": 2.5827010622154782 + }, + { + "current_steps": 1702, + "loss": 2.7736, + "learning_rate": 4.992175273865414e-07, + "epoch": 2.584218512898331 + }, + { + "current_steps": 1703, + "loss": 2.7577, + "learning_rate": 4.98904538341158e-07, + "epoch": 2.5857359635811834 + }, + { + "current_steps": 1704, + "loss": 2.6234, + "learning_rate": 4.985915492957746e-07, + "epoch": 2.5872534142640364 + }, + { + "current_steps": 1705, + "loss": 2.7232, + "learning_rate": 4.982785602503912e-07, + "epoch": 2.5887708649468895 + }, + { + "current_steps": 1706, + "loss": 2.6702, + "learning_rate": 4.979655712050078e-07, + "epoch": 2.590288315629742 + }, + { + "current_steps": 1707, + "loss": 2.5585, + "learning_rate": 4.976525821596244e-07, + "epoch": 2.5918057663125946 + }, + { + "current_steps": 1708, + "loss": 2.4798, + "learning_rate": 4.97339593114241e-07, + "epoch": 2.5933232169954477 + }, + { + "current_steps": 1709, + "loss": 2.4137, + "learning_rate": 4.970266040688575e-07, + "epoch": 2.5948406676783007 + }, + { + "current_steps": 1710, + "loss": 2.6254, + "learning_rate": 4.967136150234741e-07, + "epoch": 2.5963581183611533 + }, + { + "current_steps": 1711, + "loss": 2.502, + "learning_rate": 4.964006259780907e-07, + "epoch": 2.597875569044006 + }, + { + "current_steps": 1712, + "loss": 2.4613, + "learning_rate": 4.960876369327073e-07, + "epoch": 2.599393019726859 + }, + { + "current_steps": 1713, + "loss": 2.4696, + "learning_rate": 4.957746478873239e-07, + "epoch": 2.600910470409712 + }, + { + "current_steps": 1714, + "loss": 2.3254, + "learning_rate": 4.954616588419405e-07, + "epoch": 2.6024279210925645 + }, + { + "current_steps": 1715, + "loss": 2.6184, + "learning_rate": 4.951486697965572e-07, + "epoch": 2.603945371775417 + }, + { + "current_steps": 1716, + "loss": 2.6511, + "learning_rate": 4.948356807511738e-07, + "epoch": 2.60546282245827 + }, + { + "current_steps": 1717, + "loss": 2.7622, + "learning_rate": 4.945226917057902e-07, + "epoch": 2.606980273141123 + }, + { + "current_steps": 1718, + "loss": 2.5387, + "learning_rate": 4.942097026604068e-07, + "epoch": 2.6084977238239757 + }, + { + "current_steps": 1719, + "loss": 2.4886, + "learning_rate": 4.938967136150234e-07, + "epoch": 2.6100151745068283 + }, + { + "current_steps": 1720, + "loss": 2.5839, + "learning_rate": 4.9358372456964e-07, + "epoch": 2.6115326251896813 + }, + { + "current_steps": 1721, + "loss": 2.4639, + "learning_rate": 4.932707355242566e-07, + "epoch": 2.6130500758725344 + }, + { + "current_steps": 1722, + "loss": 2.6205, + "learning_rate": 4.929577464788733e-07, + "epoch": 2.614567526555387 + }, + { + "current_steps": 1723, + "loss": 2.5926, + "learning_rate": 4.926447574334899e-07, + "epoch": 2.6160849772382395 + }, + { + "current_steps": 1724, + "loss": 2.6481, + "learning_rate": 4.923317683881064e-07, + "epoch": 2.6176024279210925 + }, + { + "current_steps": 1725, + "loss": 2.4512, + "learning_rate": 4.920187793427229e-07, + "epoch": 2.6191198786039456 + }, + { + "current_steps": 1726, + "loss": 2.7615, + "learning_rate": 4.917057902973395e-07, + "epoch": 2.620637329286798 + }, + { + "current_steps": 1727, + "loss": 2.4716, + "learning_rate": 4.913928012519561e-07, + "epoch": 2.6221547799696507 + }, + { + "current_steps": 1728, + "loss": 2.591, + "learning_rate": 4.910798122065728e-07, + "epoch": 2.6236722306525038 + }, + { + "current_steps": 1729, + "loss": 1.9837, + "learning_rate": 4.907668231611894e-07, + "epoch": 2.625189681335357 + }, + { + "current_steps": 1730, + "loss": 2.5867, + "learning_rate": 4.90453834115806e-07, + "epoch": 2.6267071320182094 + }, + { + "current_steps": 1731, + "loss": 2.7437, + "learning_rate": 4.901408450704225e-07, + "epoch": 2.628224582701062 + }, + { + "current_steps": 1732, + "loss": 2.6971, + "learning_rate": 4.898278560250391e-07, + "epoch": 2.629742033383915 + }, + { + "current_steps": 1733, + "loss": 2.7214, + "learning_rate": 4.895148669796557e-07, + "epoch": 2.631259484066768 + }, + { + "current_steps": 1734, + "loss": 2.5992, + "learning_rate": 4.892018779342723e-07, + "epoch": 2.6327769347496206 + }, + { + "current_steps": 1735, + "loss": 2.6317, + "learning_rate": 4.888888888888889e-07, + "epoch": 2.634294385432473 + }, + { + "current_steps": 1736, + "loss": 2.7083, + "learning_rate": 4.885758998435055e-07, + "epoch": 2.635811836115326 + }, + { + "current_steps": 1737, + "loss": 2.7257, + "learning_rate": 4.882629107981221e-07, + "epoch": 2.6373292867981792 + }, + { + "current_steps": 1738, + "loss": 2.612, + "learning_rate": 4.879499217527386e-07, + "epoch": 2.638846737481032 + }, + { + "current_steps": 1739, + "loss": 2.5617, + "learning_rate": 4.876369327073552e-07, + "epoch": 2.6403641881638844 + }, + { + "current_steps": 1740, + "loss": 2.4451, + "learning_rate": 4.873239436619718e-07, + "epoch": 2.6418816388467374 + }, + { + "current_steps": 1741, + "loss": 2.743, + "learning_rate": 4.870109546165884e-07, + "epoch": 2.6433990895295905 + }, + { + "current_steps": 1742, + "loss": 2.7043, + "learning_rate": 4.86697965571205e-07, + "epoch": 2.644916540212443 + }, + { + "current_steps": 1743, + "loss": 2.4918, + "learning_rate": 4.863849765258216e-07, + "epoch": 2.6464339908952956 + }, + { + "current_steps": 1744, + "loss": 2.6083, + "learning_rate": 4.860719874804382e-07, + "epoch": 2.6479514415781487 + }, + { + "current_steps": 1745, + "loss": 2.5208, + "learning_rate": 4.857589984350548e-07, + "epoch": 2.6494688922610017 + }, + { + "current_steps": 1746, + "loss": 2.5325, + "learning_rate": 4.854460093896713e-07, + "epoch": 2.6509863429438543 + }, + { + "current_steps": 1747, + "loss": 2.4207, + "learning_rate": 4.851330203442879e-07, + "epoch": 2.6525037936267073 + }, + { + "current_steps": 1748, + "loss": 2.6623, + "learning_rate": 4.848200312989045e-07, + "epoch": 2.65402124430956 + }, + { + "current_steps": 1749, + "loss": 2.6152, + "learning_rate": 4.845070422535211e-07, + "epoch": 2.655538694992413 + }, + { + "current_steps": 1750, + "loss": 2.6322, + "learning_rate": 4.841940532081377e-07, + "epoch": 2.6570561456752655 + }, + { + "current_steps": 1751, + "loss": 2.3908, + "learning_rate": 4.838810641627543e-07, + "epoch": 2.6585735963581185 + }, + { + "current_steps": 1752, + "loss": 2.7247, + "learning_rate": 4.835680751173709e-07, + "epoch": 2.660091047040971 + }, + { + "current_steps": 1753, + "loss": 2.4559, + "learning_rate": 4.832550860719874e-07, + "epoch": 2.661608497723824 + }, + { + "current_steps": 1754, + "loss": 2.5748, + "learning_rate": 4.82942097026604e-07, + "epoch": 2.6631259484066767 + }, + { + "current_steps": 1755, + "loss": 2.7931, + "learning_rate": 4.826291079812206e-07, + "epoch": 2.6646433990895297 + }, + { + "current_steps": 1756, + "loss": 2.5422, + "learning_rate": 4.823161189358372e-07, + "epoch": 2.6661608497723823 + }, + { + "current_steps": 1757, + "loss": 2.7688, + "learning_rate": 4.820031298904538e-07, + "epoch": 2.6676783004552354 + }, + { + "current_steps": 1758, + "loss": 2.7049, + "learning_rate": 4.816901408450705e-07, + "epoch": 2.669195751138088 + }, + { + "current_steps": 1759, + "loss": 2.6797, + "learning_rate": 4.81377151799687e-07, + "epoch": 2.670713201820941 + }, + { + "current_steps": 1760, + "loss": 2.7628, + "learning_rate": 4.810641627543035e-07, + "epoch": 2.6722306525037935 + }, + { + "current_steps": 1761, + "loss": 2.6489, + "learning_rate": 4.807511737089201e-07, + "epoch": 2.6737481031866466 + }, + { + "current_steps": 1762, + "loss": 2.6832, + "learning_rate": 4.804381846635367e-07, + "epoch": 2.675265553869499 + }, + { + "current_steps": 1763, + "loss": 1.5856, + "learning_rate": 4.801251956181533e-07, + "epoch": 2.676783004552352 + }, + { + "current_steps": 1764, + "loss": 2.5099, + "learning_rate": 4.798122065727699e-07, + "epoch": 2.6783004552352048 + }, + { + "current_steps": 1765, + "loss": 2.3253, + "learning_rate": 4.794992175273866e-07, + "epoch": 2.679817905918058 + }, + { + "current_steps": 1766, + "loss": 2.618, + "learning_rate": 4.791862284820032e-07, + "epoch": 2.6813353566009104 + }, + { + "current_steps": 1767, + "loss": 2.5446, + "learning_rate": 4.788732394366196e-07, + "epoch": 2.6828528072837634 + }, + { + "current_steps": 1768, + "loss": 2.7164, + "learning_rate": 4.785602503912362e-07, + "epoch": 2.684370257966616 + }, + { + "current_steps": 1769, + "loss": 2.4652, + "learning_rate": 4.782472613458528e-07, + "epoch": 2.685887708649469 + }, + { + "current_steps": 1770, + "loss": 2.4918, + "learning_rate": 4.779342723004694e-07, + "epoch": 2.6874051593323216 + }, + { + "current_steps": 1771, + "loss": 2.7807, + "learning_rate": 4.776212832550861e-07, + "epoch": 2.6889226100151746 + }, + { + "current_steps": 1772, + "loss": 2.5292, + "learning_rate": 4.773082942097027e-07, + "epoch": 2.690440060698027 + }, + { + "current_steps": 1773, + "loss": 2.6627, + "learning_rate": 4.769953051643193e-07, + "epoch": 2.6919575113808802 + }, + { + "current_steps": 1774, + "loss": 2.4335, + "learning_rate": 4.7668231611893585e-07, + "epoch": 2.693474962063733 + }, + { + "current_steps": 1775, + "loss": 2.6763, + "learning_rate": 4.7636932707355244e-07, + "epoch": 2.694992412746586 + }, + { + "current_steps": 1776, + "loss": 2.7397, + "learning_rate": 4.76056338028169e-07, + "epoch": 2.6965098634294384 + }, + { + "current_steps": 1777, + "loss": 2.7594, + "learning_rate": 4.7574334898278556e-07, + "epoch": 2.6980273141122915 + }, + { + "current_steps": 1778, + "loss": 2.8738, + "learning_rate": 4.7543035993740215e-07, + "epoch": 2.699544764795144 + }, + { + "current_steps": 1779, + "loss": 2.3882, + "learning_rate": 4.7511737089201873e-07, + "epoch": 2.701062215477997 + }, + { + "current_steps": 1780, + "loss": 1.9448, + "learning_rate": 4.7480438184663537e-07, + "epoch": 2.7025796661608497 + }, + { + "current_steps": 1781, + "loss": 2.5913, + "learning_rate": 4.7449139280125196e-07, + "epoch": 2.7040971168437027 + }, + { + "current_steps": 1782, + "loss": 2.6829, + "learning_rate": 4.7417840375586854e-07, + "epoch": 2.7056145675265553 + }, + { + "current_steps": 1783, + "loss": 2.5225, + "learning_rate": 4.7386541471048513e-07, + "epoch": 2.7071320182094083 + }, + { + "current_steps": 1784, + "loss": 2.3237, + "learning_rate": 4.7355242566510166e-07, + "epoch": 2.708649468892261 + }, + { + "current_steps": 1785, + "loss": 2.5504, + "learning_rate": 4.7323943661971825e-07, + "epoch": 2.710166919575114 + }, + { + "current_steps": 1786, + "loss": 2.715, + "learning_rate": 4.729264475743349e-07, + "epoch": 2.7116843702579665 + }, + { + "current_steps": 1787, + "loss": 2.4769, + "learning_rate": 4.726134585289515e-07, + "epoch": 2.7132018209408195 + }, + { + "current_steps": 1788, + "loss": 2.5446, + "learning_rate": 4.7230046948356806e-07, + "epoch": 2.714719271623672 + }, + { + "current_steps": 1789, + "loss": 2.4567, + "learning_rate": 4.7198748043818465e-07, + "epoch": 2.716236722306525 + }, + { + "current_steps": 1790, + "loss": 2.4794, + "learning_rate": 4.7167449139280123e-07, + "epoch": 2.7177541729893777 + }, + { + "current_steps": 1791, + "loss": 2.7878, + "learning_rate": 4.713615023474178e-07, + "epoch": 2.7192716236722307 + }, + { + "current_steps": 1792, + "loss": 2.5873, + "learning_rate": 4.7104851330203446e-07, + "epoch": 2.7207890743550833 + }, + { + "current_steps": 1793, + "loss": 2.5285, + "learning_rate": 4.70735524256651e-07, + "epoch": 2.7223065250379364 + }, + { + "current_steps": 1794, + "loss": 2.8651, + "learning_rate": 4.704225352112676e-07, + "epoch": 2.723823975720789 + }, + { + "current_steps": 1795, + "loss": 2.3081, + "learning_rate": 4.7010954616588416e-07, + "epoch": 2.725341426403642 + }, + { + "current_steps": 1796, + "loss": 2.7076, + "learning_rate": 4.6979655712050075e-07, + "epoch": 2.7268588770864945 + }, + { + "current_steps": 1797, + "loss": 2.7117, + "learning_rate": 4.6948356807511734e-07, + "epoch": 2.7283763277693476 + }, + { + "current_steps": 1798, + "loss": 2.776, + "learning_rate": 4.69170579029734e-07, + "epoch": 2.7298937784522 + }, + { + "current_steps": 1799, + "loss": 2.576, + "learning_rate": 4.6885758998435056e-07, + "epoch": 2.731411229135053 + }, + { + "current_steps": 1800, + "loss": 2.5836, + "learning_rate": 4.6854460093896715e-07, + "epoch": 2.7329286798179058 + }, + { + "current_steps": 1801, + "loss": 2.5516, + "learning_rate": 4.682316118935837e-07, + "epoch": 2.734446130500759 + }, + { + "current_steps": 1802, + "loss": 2.5146, + "learning_rate": 4.6791862284820027e-07, + "epoch": 2.7359635811836114 + }, + { + "current_steps": 1803, + "loss": 2.4724, + "learning_rate": 4.6760563380281685e-07, + "epoch": 2.7374810318664644 + }, + { + "current_steps": 1804, + "loss": 2.6385, + "learning_rate": 4.6729264475743344e-07, + "epoch": 2.738998482549317 + }, + { + "current_steps": 1805, + "loss": 2.4831, + "learning_rate": 4.669796557120501e-07, + "epoch": 2.74051593323217 + }, + { + "current_steps": 1806, + "loss": 2.6123, + "learning_rate": 4.6666666666666666e-07, + "epoch": 2.7420333839150226 + }, + { + "current_steps": 1807, + "loss": 2.801, + "learning_rate": 4.6635367762128325e-07, + "epoch": 2.7435508345978756 + }, + { + "current_steps": 1808, + "loss": 2.6447, + "learning_rate": 4.6604068857589984e-07, + "epoch": 2.745068285280728 + }, + { + "current_steps": 1809, + "loss": 2.4999, + "learning_rate": 4.657276995305164e-07, + "epoch": 2.7465857359635812 + }, + { + "current_steps": 1810, + "loss": 2.5139, + "learning_rate": 4.6541471048513295e-07, + "epoch": 2.748103186646434 + }, + { + "current_steps": 1811, + "loss": 2.5076, + "learning_rate": 4.651017214397496e-07, + "epoch": 2.749620637329287 + }, + { + "current_steps": 1812, + "loss": 2.8815, + "learning_rate": 4.647887323943662e-07, + "epoch": 2.75113808801214 + }, + { + "current_steps": 1813, + "loss": 2.7012, + "learning_rate": 4.6447574334898277e-07, + "epoch": 2.7526555386949925 + }, + { + "current_steps": 1814, + "loss": 2.5817, + "learning_rate": 4.6416275430359935e-07, + "epoch": 2.754172989377845 + }, + { + "current_steps": 1815, + "loss": 2.4421, + "learning_rate": 4.6384976525821594e-07, + "epoch": 2.755690440060698 + }, + { + "current_steps": 1816, + "loss": 2.4929, + "learning_rate": 4.635367762128325e-07, + "epoch": 2.757207890743551 + }, + { + "current_steps": 1817, + "loss": 2.6541, + "learning_rate": 4.6322378716744916e-07, + "epoch": 2.7587253414264037 + }, + { + "current_steps": 1818, + "loss": 2.6767, + "learning_rate": 4.629107981220657e-07, + "epoch": 2.7602427921092563 + }, + { + "current_steps": 1819, + "loss": 2.7325, + "learning_rate": 4.625978090766823e-07, + "epoch": 2.7617602427921093 + }, + { + "current_steps": 1820, + "loss": 2.3363, + "learning_rate": 4.6228482003129887e-07, + "epoch": 2.7632776934749623 + }, + { + "current_steps": 1821, + "loss": 2.5634, + "learning_rate": 4.6197183098591545e-07, + "epoch": 2.764795144157815 + }, + { + "current_steps": 1822, + "loss": 2.7635, + "learning_rate": 4.6165884194053204e-07, + "epoch": 2.7663125948406675 + }, + { + "current_steps": 1823, + "loss": 2.7643, + "learning_rate": 4.613458528951487e-07, + "epoch": 2.7678300455235205 + }, + { + "current_steps": 1824, + "loss": 2.4938, + "learning_rate": 4.6103286384976527e-07, + "epoch": 2.7693474962063735 + }, + { + "current_steps": 1825, + "loss": 2.4878, + "learning_rate": 4.6071987480438185e-07, + "epoch": 2.770864946889226 + }, + { + "current_steps": 1826, + "loss": 2.5921, + "learning_rate": 4.604068857589984e-07, + "epoch": 2.7723823975720787 + }, + { + "current_steps": 1827, + "loss": 2.3363, + "learning_rate": 4.6009389671361497e-07, + "epoch": 2.7738998482549317 + }, + { + "current_steps": 1828, + "loss": 2.6131, + "learning_rate": 4.5978090766823156e-07, + "epoch": 2.7754172989377848 + }, + { + "current_steps": 1829, + "loss": 2.5707, + "learning_rate": 4.594679186228482e-07, + "epoch": 2.7769347496206374 + }, + { + "current_steps": 1830, + "loss": 2.4249, + "learning_rate": 4.591549295774648e-07, + "epoch": 2.77845220030349 + }, + { + "current_steps": 1831, + "loss": 2.3847, + "learning_rate": 4.5884194053208137e-07, + "epoch": 2.779969650986343 + }, + { + "current_steps": 1832, + "loss": 2.5745, + "learning_rate": 4.5852895148669796e-07, + "epoch": 2.781487101669196 + }, + { + "current_steps": 1833, + "loss": 2.5529, + "learning_rate": 4.5821596244131454e-07, + "epoch": 2.7830045523520486 + }, + { + "current_steps": 1834, + "loss": 2.7217, + "learning_rate": 4.5790297339593113e-07, + "epoch": 2.784522003034901 + }, + { + "current_steps": 1835, + "loss": 2.5959, + "learning_rate": 4.5758998435054766e-07, + "epoch": 2.786039453717754 + }, + { + "current_steps": 1836, + "loss": 2.6305, + "learning_rate": 4.572769953051643e-07, + "epoch": 2.787556904400607 + }, + { + "current_steps": 1837, + "loss": 2.3558, + "learning_rate": 4.569640062597809e-07, + "epoch": 2.78907435508346 + }, + { + "current_steps": 1838, + "loss": 2.7185, + "learning_rate": 4.5665101721439747e-07, + "epoch": 2.7905918057663124 + }, + { + "current_steps": 1839, + "loss": 2.1164, + "learning_rate": 4.5633802816901406e-07, + "epoch": 2.7921092564491654 + }, + { + "current_steps": 1840, + "loss": 2.6496, + "learning_rate": 4.5602503912363064e-07, + "epoch": 2.7936267071320184 + }, + { + "current_steps": 1841, + "loss": 2.6204, + "learning_rate": 4.5571205007824723e-07, + "epoch": 2.795144157814871 + }, + { + "current_steps": 1842, + "loss": 2.5559, + "learning_rate": 4.5539906103286387e-07, + "epoch": 2.7966616084977236 + }, + { + "current_steps": 1843, + "loss": 2.614, + "learning_rate": 4.550860719874804e-07, + "epoch": 2.7981790591805766 + }, + { + "current_steps": 1844, + "loss": 2.5745, + "learning_rate": 4.54773082942097e-07, + "epoch": 2.7996965098634297 + }, + { + "current_steps": 1845, + "loss": 2.0933, + "learning_rate": 4.544600938967136e-07, + "epoch": 2.8012139605462822 + }, + { + "current_steps": 1846, + "loss": 2.495, + "learning_rate": 4.5414710485133016e-07, + "epoch": 2.802731411229135 + }, + { + "current_steps": 1847, + "loss": 2.5465, + "learning_rate": 4.5383411580594675e-07, + "epoch": 2.804248861911988 + }, + { + "current_steps": 1848, + "loss": 2.4241, + "learning_rate": 4.535211267605634e-07, + "epoch": 2.805766312594841 + }, + { + "current_steps": 1849, + "loss": 1.9578, + "learning_rate": 4.5320813771517997e-07, + "epoch": 2.8072837632776935 + }, + { + "current_steps": 1850, + "loss": 2.2929, + "learning_rate": 4.5289514866979656e-07, + "epoch": 2.808801213960546 + }, + { + "current_steps": 1851, + "loss": 2.612, + "learning_rate": 4.5258215962441314e-07, + "epoch": 2.810318664643399 + }, + { + "current_steps": 1852, + "loss": 2.5252, + "learning_rate": 4.522691705790297e-07, + "epoch": 2.811836115326252 + }, + { + "current_steps": 1853, + "loss": 2.8107, + "learning_rate": 4.5195618153364626e-07, + "epoch": 2.8133535660091047 + }, + { + "current_steps": 1854, + "loss": 2.7408, + "learning_rate": 4.516431924882629e-07, + "epoch": 2.8148710166919573 + }, + { + "current_steps": 1855, + "loss": 2.5536, + "learning_rate": 4.513302034428795e-07, + "epoch": 2.8163884673748103 + }, + { + "current_steps": 1856, + "loss": 2.5805, + "learning_rate": 4.510172143974961e-07, + "epoch": 2.8179059180576633 + }, + { + "current_steps": 1857, + "loss": 2.4591, + "learning_rate": 4.5070422535211266e-07, + "epoch": 2.819423368740516 + }, + { + "current_steps": 1858, + "loss": 2.4199, + "learning_rate": 4.5039123630672925e-07, + "epoch": 2.8209408194233685 + }, + { + "current_steps": 1859, + "loss": 2.7325, + "learning_rate": 4.5007824726134583e-07, + "epoch": 2.8224582701062215 + }, + { + "current_steps": 1860, + "loss": 2.4758, + "learning_rate": 4.497652582159624e-07, + "epoch": 2.8239757207890746 + }, + { + "current_steps": 1861, + "loss": 2.5386, + "learning_rate": 4.49452269170579e-07, + "epoch": 2.825493171471927 + }, + { + "current_steps": 1862, + "loss": 2.3939, + "learning_rate": 4.491392801251956e-07, + "epoch": 2.8270106221547797 + }, + { + "current_steps": 1863, + "loss": 2.5822, + "learning_rate": 4.488262910798122e-07, + "epoch": 2.8285280728376327 + }, + { + "current_steps": 1864, + "loss": 2.4097, + "learning_rate": 4.4851330203442876e-07, + "epoch": 2.8300455235204858 + }, + { + "current_steps": 1865, + "loss": 2.5733, + "learning_rate": 4.4820031298904535e-07, + "epoch": 2.8315629742033384 + }, + { + "current_steps": 1866, + "loss": 2.7941, + "learning_rate": 4.47887323943662e-07, + "epoch": 2.833080424886191 + }, + { + "current_steps": 1867, + "loss": 2.5354, + "learning_rate": 4.475743348982786e-07, + "epoch": 2.834597875569044 + }, + { + "current_steps": 1868, + "loss": 2.4745, + "learning_rate": 4.4726134585289516e-07, + "epoch": 2.836115326251897 + }, + { + "current_steps": 1869, + "loss": 2.3939, + "learning_rate": 4.469483568075117e-07, + "epoch": 2.8376327769347496 + }, + { + "current_steps": 1870, + "loss": 2.7521, + "learning_rate": 4.466353677621283e-07, + "epoch": 2.839150227617602 + }, + { + "current_steps": 1871, + "loss": 2.6014, + "learning_rate": 4.4632237871674487e-07, + "epoch": 2.840667678300455 + }, + { + "current_steps": 1872, + "loss": 2.3476, + "learning_rate": 4.460093896713615e-07, + "epoch": 2.842185128983308 + }, + { + "current_steps": 1873, + "loss": 2.7242, + "learning_rate": 4.456964006259781e-07, + "epoch": 2.843702579666161 + }, + { + "current_steps": 1874, + "loss": 2.7551, + "learning_rate": 4.453834115805947e-07, + "epoch": 2.8452200303490134 + }, + { + "current_steps": 1875, + "loss": 2.4155, + "learning_rate": 4.4507042253521126e-07, + "epoch": 2.8467374810318664 + }, + { + "current_steps": 1876, + "loss": 2.4808, + "learning_rate": 4.4475743348982785e-07, + "epoch": 2.8482549317147194 + }, + { + "current_steps": 1877, + "loss": 2.3921, + "learning_rate": 4.444444444444444e-07, + "epoch": 2.849772382397572 + }, + { + "current_steps": 1878, + "loss": 2.5514, + "learning_rate": 4.4413145539906097e-07, + "epoch": 2.851289833080425 + }, + { + "current_steps": 1879, + "loss": 2.4037, + "learning_rate": 4.438184663536776e-07, + "epoch": 2.8528072837632776 + }, + { + "current_steps": 1880, + "loss": 2.5061, + "learning_rate": 4.435054773082942e-07, + "epoch": 2.8543247344461307 + }, + { + "current_steps": 1881, + "loss": 2.5366, + "learning_rate": 4.431924882629108e-07, + "epoch": 2.8558421851289832 + }, + { + "current_steps": 1882, + "loss": 1.9563, + "learning_rate": 4.4287949921752737e-07, + "epoch": 2.8573596358118363 + }, + { + "current_steps": 1883, + "loss": 2.5772, + "learning_rate": 4.4256651017214395e-07, + "epoch": 2.858877086494689 + }, + { + "current_steps": 1884, + "loss": 2.516, + "learning_rate": 4.4225352112676054e-07, + "epoch": 2.860394537177542 + }, + { + "current_steps": 1885, + "loss": 2.8695, + "learning_rate": 4.419405320813771e-07, + "epoch": 2.8619119878603945 + }, + { + "current_steps": 1886, + "loss": 2.3186, + "learning_rate": 4.416275430359937e-07, + "epoch": 2.8634294385432475 + }, + { + "current_steps": 1887, + "loss": 2.4676, + "learning_rate": 4.413145539906103e-07, + "epoch": 2.8649468892261 + }, + { + "current_steps": 1888, + "loss": 2.0917, + "learning_rate": 4.410015649452269e-07, + "epoch": 2.866464339908953 + }, + { + "current_steps": 1889, + "loss": 2.6292, + "learning_rate": 4.4068857589984347e-07, + "epoch": 2.8679817905918057 + }, + { + "current_steps": 1890, + "loss": 2.0066, + "learning_rate": 4.4037558685446006e-07, + "epoch": 2.8694992412746587 + }, + { + "current_steps": 1891, + "loss": 2.6763, + "learning_rate": 4.400625978090767e-07, + "epoch": 2.8710166919575113 + }, + { + "current_steps": 1892, + "loss": 2.693, + "learning_rate": 4.397496087636933e-07, + "epoch": 2.8725341426403643 + }, + { + "current_steps": 1893, + "loss": 2.6833, + "learning_rate": 4.3943661971830987e-07, + "epoch": 2.874051593323217 + }, + { + "current_steps": 1894, + "loss": 2.5455, + "learning_rate": 4.391236306729264e-07, + "epoch": 2.87556904400607 + }, + { + "current_steps": 1895, + "loss": 2.6727, + "learning_rate": 4.38810641627543e-07, + "epoch": 2.8770864946889225 + }, + { + "current_steps": 1896, + "loss": 2.5301, + "learning_rate": 4.3849765258215957e-07, + "epoch": 2.8786039453717756 + }, + { + "current_steps": 1897, + "loss": 2.4825, + "learning_rate": 4.381846635367762e-07, + "epoch": 2.880121396054628 + }, + { + "current_steps": 1898, + "loss": 2.8633, + "learning_rate": 4.378716744913928e-07, + "epoch": 2.881638846737481 + }, + { + "current_steps": 1899, + "loss": 2.5781, + "learning_rate": 4.375586854460094e-07, + "epoch": 2.8831562974203337 + }, + { + "current_steps": 1900, + "loss": 2.5892, + "learning_rate": 4.3724569640062597e-07, + "epoch": 2.8846737481031868 + }, + { + "current_steps": 1901, + "loss": 2.5759, + "learning_rate": 4.3693270735524256e-07, + "epoch": 2.8861911987860394 + }, + { + "current_steps": 1902, + "loss": 2.4917, + "learning_rate": 4.366197183098591e-07, + "epoch": 2.8877086494688924 + }, + { + "current_steps": 1903, + "loss": 2.7001, + "learning_rate": 4.3630672926447573e-07, + "epoch": 2.889226100151745 + }, + { + "current_steps": 1904, + "loss": 2.5609, + "learning_rate": 4.359937402190923e-07, + "epoch": 2.890743550834598 + }, + { + "current_steps": 1905, + "loss": 2.5559, + "learning_rate": 4.356807511737089e-07, + "epoch": 2.8922610015174506 + }, + { + "current_steps": 1906, + "loss": 2.4363, + "learning_rate": 4.353677621283255e-07, + "epoch": 2.8937784522003036 + }, + { + "current_steps": 1907, + "loss": 2.4432, + "learning_rate": 4.3505477308294207e-07, + "epoch": 2.895295902883156 + }, + { + "current_steps": 1908, + "loss": 2.5271, + "learning_rate": 4.3474178403755866e-07, + "epoch": 2.896813353566009 + }, + { + "current_steps": 1909, + "loss": 2.499, + "learning_rate": 4.344287949921753e-07, + "epoch": 2.898330804248862 + }, + { + "current_steps": 1910, + "loss": 2.5848, + "learning_rate": 4.341158059467919e-07, + "epoch": 2.899848254931715 + }, + { + "current_steps": 1911, + "loss": 2.4764, + "learning_rate": 4.338028169014084e-07, + "epoch": 2.9013657056145674 + }, + { + "current_steps": 1912, + "loss": 2.5018, + "learning_rate": 4.33489827856025e-07, + "epoch": 2.9028831562974204 + }, + { + "current_steps": 1913, + "loss": 2.5485, + "learning_rate": 4.331768388106416e-07, + "epoch": 2.904400606980273 + }, + { + "current_steps": 1914, + "loss": 2.3634, + "learning_rate": 4.328638497652582e-07, + "epoch": 2.905918057663126 + }, + { + "current_steps": 1915, + "loss": 2.5663, + "learning_rate": 4.325508607198748e-07, + "epoch": 2.9074355083459786 + }, + { + "current_steps": 1916, + "loss": 2.547, + "learning_rate": 4.322378716744914e-07, + "epoch": 2.9089529590288317 + }, + { + "current_steps": 1917, + "loss": 2.6141, + "learning_rate": 4.31924882629108e-07, + "epoch": 2.9104704097116842 + }, + { + "current_steps": 1918, + "loss": 2.6488, + "learning_rate": 4.3161189358372457e-07, + "epoch": 2.9119878603945373 + }, + { + "current_steps": 1919, + "loss": 2.0717, + "learning_rate": 4.312989045383411e-07, + "epoch": 2.91350531107739 + }, + { + "current_steps": 1920, + "loss": 2.6115, + "learning_rate": 4.309859154929577e-07, + "epoch": 2.915022761760243 + }, + { + "current_steps": 1921, + "loss": 2.5568, + "learning_rate": 4.306729264475743e-07, + "epoch": 2.9165402124430955 + }, + { + "current_steps": 1922, + "loss": 2.5972, + "learning_rate": 4.303599374021909e-07, + "epoch": 2.9180576631259485 + }, + { + "current_steps": 1923, + "loss": 2.5466, + "learning_rate": 4.300469483568075e-07, + "epoch": 2.919575113808801 + }, + { + "current_steps": 1924, + "loss": 2.5433, + "learning_rate": 4.297339593114241e-07, + "epoch": 2.921092564491654 + }, + { + "current_steps": 1925, + "loss": 2.7394, + "learning_rate": 4.294209702660407e-07, + "epoch": 2.9226100151745067 + }, + { + "current_steps": 1926, + "loss": 2.5807, + "learning_rate": 4.2910798122065726e-07, + "epoch": 2.9241274658573597 + }, + { + "current_steps": 1927, + "loss": 2.6734, + "learning_rate": 4.2879499217527385e-07, + "epoch": 2.9256449165402123 + }, + { + "current_steps": 1928, + "loss": 2.3501, + "learning_rate": 4.2848200312989043e-07, + "epoch": 2.9271623672230653 + }, + { + "current_steps": 1929, + "loss": 2.511, + "learning_rate": 4.28169014084507e-07, + "epoch": 2.928679817905918 + }, + { + "current_steps": 1930, + "loss": 2.4365, + "learning_rate": 4.278560250391236e-07, + "epoch": 2.930197268588771 + }, + { + "current_steps": 1931, + "loss": 2.5524, + "learning_rate": 4.275430359937402e-07, + "epoch": 2.9317147192716235 + }, + { + "current_steps": 1932, + "loss": 2.5767, + "learning_rate": 4.272300469483568e-07, + "epoch": 2.9332321699544766 + }, + { + "current_steps": 1933, + "loss": 2.7359, + "learning_rate": 4.2691705790297336e-07, + "epoch": 2.934749620637329 + }, + { + "current_steps": 1934, + "loss": 2.7514, + "learning_rate": 4.2660406885759e-07, + "epoch": 2.936267071320182 + }, + { + "current_steps": 1935, + "loss": 2.516, + "learning_rate": 4.262910798122066e-07, + "epoch": 2.9377845220030347 + }, + { + "current_steps": 1936, + "loss": 2.3566, + "learning_rate": 4.259780907668231e-07, + "epoch": 2.9393019726858878 + }, + { + "current_steps": 1937, + "loss": 2.727, + "learning_rate": 4.256651017214397e-07, + "epoch": 2.9408194233687404 + }, + { + "current_steps": 1938, + "loss": 2.5228, + "learning_rate": 4.253521126760563e-07, + "epoch": 2.9423368740515934 + }, + { + "current_steps": 1939, + "loss": 2.5228, + "learning_rate": 4.250391236306729e-07, + "epoch": 2.943854324734446 + }, + { + "current_steps": 1940, + "loss": 2.6765, + "learning_rate": 4.247261345852895e-07, + "epoch": 2.945371775417299 + }, + { + "current_steps": 1941, + "loss": 2.7168, + "learning_rate": 4.244131455399061e-07, + "epoch": 2.9468892261001516 + }, + { + "current_steps": 1942, + "loss": 2.4037, + "learning_rate": 4.241001564945227e-07, + "epoch": 2.9484066767830046 + }, + { + "current_steps": 1943, + "loss": 2.5607, + "learning_rate": 4.237871674491393e-07, + "epoch": 2.949924127465857 + }, + { + "current_steps": 1944, + "loss": 2.7669, + "learning_rate": 4.234741784037558e-07, + "epoch": 2.95144157814871 + }, + { + "current_steps": 1945, + "loss": 2.7141, + "learning_rate": 4.231611893583724e-07, + "epoch": 2.952959028831563 + }, + { + "current_steps": 1946, + "loss": 2.6049, + "learning_rate": 4.2284820031298904e-07, + "epoch": 2.954476479514416 + }, + { + "current_steps": 1947, + "loss": 2.48, + "learning_rate": 4.225352112676056e-07, + "epoch": 2.955993930197269 + }, + { + "current_steps": 1948, + "loss": 2.8061, + "learning_rate": 4.222222222222222e-07, + "epoch": 2.9575113808801214 + }, + { + "current_steps": 1949, + "loss": 2.482, + "learning_rate": 4.219092331768388e-07, + "epoch": 2.959028831562974 + }, + { + "current_steps": 1950, + "loss": 2.5065, + "learning_rate": 4.215962441314554e-07, + "epoch": 2.960546282245827 + }, + { + "current_steps": 1951, + "loss": 2.63, + "learning_rate": 4.2128325508607197e-07, + "epoch": 2.96206373292868 + }, + { + "current_steps": 1952, + "loss": 2.4683, + "learning_rate": 4.209702660406886e-07, + "epoch": 2.9635811836115327 + }, + { + "current_steps": 1953, + "loss": 2.4913, + "learning_rate": 4.2065727699530514e-07, + "epoch": 2.9650986342943852 + }, + { + "current_steps": 1954, + "loss": 2.5076, + "learning_rate": 4.203442879499217e-07, + "epoch": 2.9666160849772383 + }, + { + "current_steps": 1955, + "loss": 2.6537, + "learning_rate": 4.200312989045383e-07, + "epoch": 2.9681335356600913 + }, + { + "current_steps": 1956, + "loss": 2.201, + "learning_rate": 4.197183098591549e-07, + "epoch": 2.969650986342944 + }, + { + "current_steps": 1957, + "loss": 2.5927, + "learning_rate": 4.194053208137715e-07, + "epoch": 2.9711684370257965 + }, + { + "current_steps": 1958, + "loss": 2.608, + "learning_rate": 4.1909233176838807e-07, + "epoch": 2.9726858877086495 + }, + { + "current_steps": 1959, + "loss": 2.3317, + "learning_rate": 4.187793427230047e-07, + "epoch": 2.9742033383915025 + }, + { + "current_steps": 1960, + "loss": 2.4645, + "learning_rate": 4.184663536776213e-07, + "epoch": 2.975720789074355 + }, + { + "current_steps": 1961, + "loss": 2.5413, + "learning_rate": 4.1815336463223783e-07, + "epoch": 2.9772382397572077 + }, + { + "current_steps": 1962, + "loss": 2.5523, + "learning_rate": 4.178403755868544e-07, + "epoch": 2.9787556904400607 + }, + { + "current_steps": 1963, + "loss": 2.7826, + "learning_rate": 4.17527386541471e-07, + "epoch": 2.9802731411229137 + }, + { + "current_steps": 1964, + "loss": 2.5948, + "learning_rate": 4.172143974960876e-07, + "epoch": 2.9817905918057663 + }, + { + "current_steps": 1965, + "loss": 2.4657, + "learning_rate": 4.169014084507042e-07, + "epoch": 2.983308042488619 + }, + { + "current_steps": 1966, + "loss": 2.4106, + "learning_rate": 4.165884194053208e-07, + "epoch": 2.984825493171472 + }, + { + "current_steps": 1967, + "loss": 2.6359, + "learning_rate": 4.162754303599374e-07, + "epoch": 2.986342943854325 + }, + { + "current_steps": 1968, + "loss": 2.6606, + "learning_rate": 4.15962441314554e-07, + "epoch": 2.9878603945371776 + }, + { + "current_steps": 1969, + "loss": 2.6442, + "learning_rate": 4.1564945226917057e-07, + "epoch": 2.98937784522003 + }, + { + "current_steps": 1970, + "loss": 2.3763, + "learning_rate": 4.153364632237871e-07, + "epoch": 2.990895295902883 + }, + { + "current_steps": 1971, + "loss": 2.7271, + "learning_rate": 4.1502347417840374e-07, + "epoch": 2.992412746585736 + }, + { + "current_steps": 1972, + "loss": 2.6586, + "learning_rate": 4.1471048513302033e-07, + "epoch": 2.9939301972685888 + }, + { + "current_steps": 1973, + "loss": 2.5377, + "learning_rate": 4.143974960876369e-07, + "epoch": 2.9954476479514414 + }, + { + "current_steps": 1974, + "loss": 2.3221, + "learning_rate": 4.140845070422535e-07, + "epoch": 2.9969650986342944 + }, + { + "current_steps": 1975, + "loss": 2.5713, + "learning_rate": 4.137715179968701e-07, + "epoch": 2.9984825493171474 + }, + { + "current_steps": 1976, + "loss": 2.5726, + "learning_rate": 4.1345852895148667e-07, + "epoch": 3.0 + }, + { + "current_steps": 1977, + "loss": 2.7201, + "learning_rate": 4.131455399061033e-07, + "epoch": 3.001517450682853 + }, + { + "current_steps": 1978, + "loss": 2.5513, + "learning_rate": 4.1283255086071985e-07, + "epoch": 3.0030349013657056 + }, + { + "current_steps": 1979, + "loss": 2.5151, + "learning_rate": 4.1251956181533643e-07, + "epoch": 3.0045523520485586 + }, + { + "current_steps": 1980, + "loss": 2.5058, + "learning_rate": 4.12206572769953e-07, + "epoch": 3.0060698027314112 + }, + { + "current_steps": 1981, + "loss": 2.4421, + "learning_rate": 4.118935837245696e-07, + "epoch": 3.0075872534142643 + }, + { + "current_steps": 1982, + "loss": 2.6666, + "learning_rate": 4.115805946791862e-07, + "epoch": 3.009104704097117 + }, + { + "current_steps": 1983, + "loss": 2.7656, + "learning_rate": 4.1126760563380283e-07, + "epoch": 3.01062215477997 + }, + { + "current_steps": 1984, + "loss": 2.5536, + "learning_rate": 4.109546165884194e-07, + "epoch": 3.0121396054628224 + }, + { + "current_steps": 1985, + "loss": 2.5194, + "learning_rate": 4.10641627543036e-07, + "epoch": 3.0136570561456755 + }, + { + "current_steps": 1986, + "loss": 2.572, + "learning_rate": 4.103286384976526e-07, + "epoch": 3.015174506828528 + }, + { + "current_steps": 1987, + "loss": 2.3919, + "learning_rate": 4.100156494522691e-07, + "epoch": 3.016691957511381 + }, + { + "current_steps": 1988, + "loss": 2.5216, + "learning_rate": 4.097026604068857e-07, + "epoch": 3.0182094081942337 + }, + { + "current_steps": 1989, + "loss": 2.7029, + "learning_rate": 4.0938967136150235e-07, + "epoch": 3.0197268588770867 + }, + { + "current_steps": 1990, + "loss": 2.6796, + "learning_rate": 4.0907668231611893e-07, + "epoch": 3.0212443095599393 + }, + { + "current_steps": 1991, + "loss": 2.4967, + "learning_rate": 4.087636932707355e-07, + "epoch": 3.0227617602427923 + }, + { + "current_steps": 1992, + "loss": 2.5264, + "learning_rate": 4.084507042253521e-07, + "epoch": 3.024279210925645 + }, + { + "current_steps": 1993, + "loss": 2.8724, + "learning_rate": 4.081377151799687e-07, + "epoch": 3.025796661608498 + }, + { + "current_steps": 1994, + "loss": 2.771, + "learning_rate": 4.078247261345853e-07, + "epoch": 3.0273141122913505 + }, + { + "current_steps": 1995, + "loss": 2.6059, + "learning_rate": 4.075117370892018e-07, + "epoch": 3.0288315629742035 + }, + { + "current_steps": 1996, + "loss": 2.539, + "learning_rate": 4.0719874804381845e-07, + "epoch": 3.030349013657056 + }, + { + "current_steps": 1997, + "loss": 2.5571, + "learning_rate": 4.0688575899843503e-07, + "epoch": 3.031866464339909 + }, + { + "current_steps": 1998, + "loss": 2.5701, + "learning_rate": 4.065727699530516e-07, + "epoch": 3.0333839150227617 + }, + { + "current_steps": 1999, + "loss": 2.5959, + "learning_rate": 4.062597809076682e-07, + "epoch": 3.0349013657056148 + }, + { + "current_steps": 2000, + "loss": 2.5855, + "learning_rate": 4.059467918622848e-07, + "epoch": 3.0364188163884673 + }, + { + "current_steps": 2001, + "loss": 2.4349, + "learning_rate": 4.056338028169014e-07, + "epoch": 3.0379362670713204 + }, + { + "current_steps": 2002, + "loss": 2.4763, + "learning_rate": 4.05320813771518e-07, + "epoch": 3.039453717754173 + }, + { + "current_steps": 2003, + "loss": 2.4725, + "learning_rate": 4.0500782472613455e-07, + "epoch": 3.040971168437026 + }, + { + "current_steps": 2004, + "loss": 2.6275, + "learning_rate": 4.0469483568075114e-07, + "epoch": 3.0424886191198786 + }, + { + "current_steps": 2005, + "loss": 2.5267, + "learning_rate": 4.043818466353677e-07, + "epoch": 3.0440060698027316 + }, + { + "current_steps": 2006, + "loss": 2.6145, + "learning_rate": 4.040688575899843e-07, + "epoch": 3.045523520485584 + }, + { + "current_steps": 2007, + "loss": 2.5599, + "learning_rate": 4.037558685446009e-07, + "epoch": 3.047040971168437 + }, + { + "current_steps": 2008, + "loss": 2.602, + "learning_rate": 4.0344287949921753e-07, + "epoch": 3.04855842185129 + }, + { + "current_steps": 2009, + "loss": 2.6955, + "learning_rate": 4.031298904538341e-07, + "epoch": 3.050075872534143 + }, + { + "current_steps": 2010, + "loss": 2.5392, + "learning_rate": 4.028169014084507e-07, + "epoch": 3.0515933232169954 + }, + { + "current_steps": 2011, + "loss": 2.1895, + "learning_rate": 4.025039123630673e-07, + "epoch": 3.0531107738998484 + }, + { + "current_steps": 2012, + "loss": 2.5574, + "learning_rate": 4.021909233176838e-07, + "epoch": 3.054628224582701 + }, + { + "current_steps": 2013, + "loss": 2.6149, + "learning_rate": 4.018779342723004e-07, + "epoch": 3.056145675265554 + }, + { + "current_steps": 2014, + "loss": 2.4327, + "learning_rate": 4.0156494522691705e-07, + "epoch": 3.0576631259484066 + }, + { + "current_steps": 2015, + "loss": 2.6664, + "learning_rate": 4.0125195618153364e-07, + "epoch": 3.0591805766312596 + }, + { + "current_steps": 2016, + "loss": 2.5793, + "learning_rate": 4.009389671361502e-07, + "epoch": 3.0606980273141122 + }, + { + "current_steps": 2017, + "loss": 2.3111, + "learning_rate": 4.006259780907668e-07, + "epoch": 3.0622154779969653 + }, + { + "current_steps": 2018, + "loss": 2.6379, + "learning_rate": 4.003129890453834e-07, + "epoch": 3.063732928679818 + }, + { + "current_steps": 2019, + "loss": 2.6166, + "learning_rate": 4e-07, + "epoch": 3.065250379362671 + }, + { + "current_steps": 2020, + "loss": 2.6402, + "learning_rate": 3.9968701095461657e-07, + "epoch": 3.0667678300455234 + }, + { + "current_steps": 2021, + "loss": 2.7829, + "learning_rate": 3.9937402190923315e-07, + "epoch": 3.0682852807283765 + }, + { + "current_steps": 2022, + "loss": 2.5444, + "learning_rate": 3.9906103286384974e-07, + "epoch": 3.069802731411229 + }, + { + "current_steps": 2023, + "loss": 2.4947, + "learning_rate": 3.987480438184663e-07, + "epoch": 3.071320182094082 + }, + { + "current_steps": 2024, + "loss": 2.5756, + "learning_rate": 3.984350547730829e-07, + "epoch": 3.0728376327769347 + }, + { + "current_steps": 2025, + "loss": 2.1944, + "learning_rate": 3.981220657276995e-07, + "epoch": 3.0743550834597877 + }, + { + "current_steps": 2026, + "loss": 2.4609, + "learning_rate": 3.9780907668231614e-07, + "epoch": 3.0758725341426403 + }, + { + "current_steps": 2027, + "loss": 2.2877, + "learning_rate": 3.974960876369327e-07, + "epoch": 3.0773899848254933 + }, + { + "current_steps": 2028, + "loss": 2.627, + "learning_rate": 3.971830985915493e-07, + "epoch": 3.078907435508346 + }, + { + "current_steps": 2029, + "loss": 2.6812, + "learning_rate": 3.9687010954616584e-07, + "epoch": 3.080424886191199 + }, + { + "current_steps": 2030, + "loss": 2.5184, + "learning_rate": 3.9655712050078243e-07, + "epoch": 3.0819423368740515 + }, + { + "current_steps": 2031, + "loss": 2.5884, + "learning_rate": 3.96244131455399e-07, + "epoch": 3.0834597875569045 + }, + { + "current_steps": 2032, + "loss": 2.5971, + "learning_rate": 3.9593114241001565e-07, + "epoch": 3.084977238239757 + }, + { + "current_steps": 2033, + "loss": 2.3663, + "learning_rate": 3.9561815336463224e-07, + "epoch": 3.08649468892261 + }, + { + "current_steps": 2034, + "loss": 2.6211, + "learning_rate": 3.9530516431924883e-07, + "epoch": 3.0880121396054627 + }, + { + "current_steps": 2035, + "loss": 2.5257, + "learning_rate": 3.949921752738654e-07, + "epoch": 3.0895295902883158 + }, + { + "current_steps": 2036, + "loss": 2.8633, + "learning_rate": 3.94679186228482e-07, + "epoch": 3.0910470409711683 + }, + { + "current_steps": 2037, + "loss": 2.6309, + "learning_rate": 3.9436619718309853e-07, + "epoch": 3.0925644916540214 + }, + { + "current_steps": 2038, + "loss": 2.7032, + "learning_rate": 3.940532081377151e-07, + "epoch": 3.094081942336874 + }, + { + "current_steps": 2039, + "loss": 2.7366, + "learning_rate": 3.9374021909233176e-07, + "epoch": 3.095599393019727 + }, + { + "current_steps": 2040, + "loss": 2.3686, + "learning_rate": 3.9342723004694834e-07, + "epoch": 3.0971168437025796 + }, + { + "current_steps": 2041, + "loss": 2.4249, + "learning_rate": 3.9311424100156493e-07, + "epoch": 3.0986342943854326 + }, + { + "current_steps": 2042, + "loss": 2.5339, + "learning_rate": 3.928012519561815e-07, + "epoch": 3.100151745068285 + }, + { + "current_steps": 2043, + "loss": 2.5132, + "learning_rate": 3.924882629107981e-07, + "epoch": 3.101669195751138 + }, + { + "current_steps": 2044, + "loss": 2.6059, + "learning_rate": 3.921752738654147e-07, + "epoch": 3.103186646433991 + }, + { + "current_steps": 2045, + "loss": 2.5199, + "learning_rate": 3.9186228482003133e-07, + "epoch": 3.104704097116844 + }, + { + "current_steps": 2046, + "loss": 2.6968, + "learning_rate": 3.9154929577464786e-07, + "epoch": 3.1062215477996964 + }, + { + "current_steps": 2047, + "loss": 2.8117, + "learning_rate": 3.9123630672926445e-07, + "epoch": 3.1077389984825494 + }, + { + "current_steps": 2048, + "loss": 2.8682, + "learning_rate": 3.9092331768388103e-07, + "epoch": 3.109256449165402 + }, + { + "current_steps": 2049, + "loss": 2.5484, + "learning_rate": 3.906103286384976e-07, + "epoch": 3.110773899848255 + }, + { + "current_steps": 2050, + "loss": 2.3885, + "learning_rate": 3.902973395931142e-07, + "epoch": 3.1122913505311076 + }, + { + "current_steps": 2051, + "loss": 2.2015, + "learning_rate": 3.8998435054773084e-07, + "epoch": 3.1138088012139606 + }, + { + "current_steps": 2052, + "loss": 2.6627, + "learning_rate": 3.8967136150234743e-07, + "epoch": 3.1153262518968132 + }, + { + "current_steps": 2053, + "loss": 2.5904, + "learning_rate": 3.89358372456964e-07, + "epoch": 3.1168437025796663 + }, + { + "current_steps": 2054, + "loss": 2.522, + "learning_rate": 3.8904538341158055e-07, + "epoch": 3.118361153262519 + }, + { + "current_steps": 2055, + "loss": 2.62, + "learning_rate": 3.8873239436619713e-07, + "epoch": 3.119878603945372 + }, + { + "current_steps": 2056, + "loss": 2.7186, + "learning_rate": 3.884194053208137e-07, + "epoch": 3.1213960546282244 + }, + { + "current_steps": 2057, + "loss": 2.7047, + "learning_rate": 3.8810641627543036e-07, + "epoch": 3.1229135053110775 + }, + { + "current_steps": 2058, + "loss": 2.4508, + "learning_rate": 3.8779342723004695e-07, + "epoch": 3.12443095599393 + }, + { + "current_steps": 2059, + "loss": 1.9242, + "learning_rate": 3.8748043818466353e-07, + "epoch": 3.125948406676783 + }, + { + "current_steps": 2060, + "loss": 2.6166, + "learning_rate": 3.871674491392801e-07, + "epoch": 3.1274658573596357 + }, + { + "current_steps": 2061, + "loss": 2.6318, + "learning_rate": 3.868544600938967e-07, + "epoch": 3.1289833080424887 + }, + { + "current_steps": 2062, + "loss": 2.4529, + "learning_rate": 3.8654147104851324e-07, + "epoch": 3.1305007587253413 + }, + { + "current_steps": 2063, + "loss": 2.5139, + "learning_rate": 3.862284820031299e-07, + "epoch": 3.1320182094081943 + }, + { + "current_steps": 2064, + "loss": 2.479, + "learning_rate": 3.8591549295774646e-07, + "epoch": 3.133535660091047 + }, + { + "current_steps": 2065, + "loss": 2.4178, + "learning_rate": 3.8560250391236305e-07, + "epoch": 3.1350531107739 + }, + { + "current_steps": 2066, + "loss": 2.5484, + "learning_rate": 3.8528951486697964e-07, + "epoch": 3.1365705614567525 + }, + { + "current_steps": 2067, + "loss": 2.3839, + "learning_rate": 3.849765258215962e-07, + "epoch": 3.1380880121396055 + }, + { + "current_steps": 2068, + "loss": 2.5635, + "learning_rate": 3.846635367762128e-07, + "epoch": 3.139605462822458 + }, + { + "current_steps": 2069, + "loss": 2.6849, + "learning_rate": 3.8435054773082945e-07, + "epoch": 3.141122913505311 + }, + { + "current_steps": 2070, + "loss": 2.4883, + "learning_rate": 3.8403755868544603e-07, + "epoch": 3.1426403641881637 + }, + { + "current_steps": 2071, + "loss": 2.6456, + "learning_rate": 3.8372456964006257e-07, + "epoch": 3.1441578148710168 + }, + { + "current_steps": 2072, + "loss": 2.5642, + "learning_rate": 3.8341158059467915e-07, + "epoch": 3.1456752655538693 + }, + { + "current_steps": 2073, + "loss": 2.5942, + "learning_rate": 3.8309859154929574e-07, + "epoch": 3.1471927162367224 + }, + { + "current_steps": 2074, + "loss": 2.1412, + "learning_rate": 3.827856025039123e-07, + "epoch": 3.148710166919575 + }, + { + "current_steps": 2075, + "loss": 2.5187, + "learning_rate": 3.824726134585289e-07, + "epoch": 3.150227617602428 + }, + { + "current_steps": 2076, + "loss": 2.7158, + "learning_rate": 3.8215962441314555e-07, + "epoch": 3.1517450682852806 + }, + { + "current_steps": 2077, + "loss": 2.6727, + "learning_rate": 3.8184663536776214e-07, + "epoch": 3.1532625189681336 + }, + { + "current_steps": 2078, + "loss": 2.4341, + "learning_rate": 3.815336463223787e-07, + "epoch": 3.154779969650986 + }, + { + "current_steps": 2079, + "loss": 2.3565, + "learning_rate": 3.8122065727699525e-07, + "epoch": 3.156297420333839 + }, + { + "current_steps": 2080, + "loss": 2.572, + "learning_rate": 3.8090766823161184e-07, + "epoch": 3.157814871016692 + }, + { + "current_steps": 2081, + "loss": 2.6033, + "learning_rate": 3.8059467918622843e-07, + "epoch": 3.159332321699545 + }, + { + "current_steps": 2082, + "loss": 2.691, + "learning_rate": 3.8028169014084507e-07, + "epoch": 3.1608497723823974 + }, + { + "current_steps": 2083, + "loss": 2.65, + "learning_rate": 3.7996870109546165e-07, + "epoch": 3.1623672230652504 + }, + { + "current_steps": 2084, + "loss": 2.5768, + "learning_rate": 3.7965571205007824e-07, + "epoch": 3.163884673748103 + }, + { + "current_steps": 2085, + "loss": 2.4379, + "learning_rate": 3.793427230046948e-07, + "epoch": 3.165402124430956 + }, + { + "current_steps": 2086, + "loss": 2.6184, + "learning_rate": 3.790297339593114e-07, + "epoch": 3.1669195751138086 + }, + { + "current_steps": 2087, + "loss": 2.272, + "learning_rate": 3.78716744913928e-07, + "epoch": 3.1684370257966616 + }, + { + "current_steps": 2088, + "loss": 2.2812, + "learning_rate": 3.784037558685446e-07, + "epoch": 3.1699544764795142 + }, + { + "current_steps": 2089, + "loss": 2.4576, + "learning_rate": 3.7809076682316117e-07, + "epoch": 3.1714719271623673 + }, + { + "current_steps": 2090, + "loss": 2.465, + "learning_rate": 3.7777777777777775e-07, + "epoch": 3.17298937784522 + }, + { + "current_steps": 2091, + "loss": 2.4921, + "learning_rate": 3.7746478873239434e-07, + "epoch": 3.174506828528073 + }, + { + "current_steps": 2092, + "loss": 2.5767, + "learning_rate": 3.7715179968701093e-07, + "epoch": 3.1760242792109254 + }, + { + "current_steps": 2093, + "loss": 2.3482, + "learning_rate": 3.768388106416275e-07, + "epoch": 3.1775417298937785 + }, + { + "current_steps": 2094, + "loss": 2.585, + "learning_rate": 3.7652582159624415e-07, + "epoch": 3.179059180576631 + }, + { + "current_steps": 2095, + "loss": 2.5916, + "learning_rate": 3.7621283255086074e-07, + "epoch": 3.180576631259484 + }, + { + "current_steps": 2096, + "loss": 2.5669, + "learning_rate": 3.7589984350547727e-07, + "epoch": 3.1820940819423367 + }, + { + "current_steps": 2097, + "loss": 2.6775, + "learning_rate": 3.7558685446009386e-07, + "epoch": 3.1836115326251897 + }, + { + "current_steps": 2098, + "loss": 2.6782, + "learning_rate": 3.7527386541471044e-07, + "epoch": 3.1851289833080423 + }, + { + "current_steps": 2099, + "loss": 2.5707, + "learning_rate": 3.7496087636932703e-07, + "epoch": 3.1866464339908953 + }, + { + "current_steps": 2100, + "loss": 2.133, + "learning_rate": 3.7464788732394367e-07, + "epoch": 3.188163884673748 + }, + { + "current_steps": 2101, + "loss": 2.4146, + "learning_rate": 3.7433489827856025e-07, + "epoch": 3.189681335356601 + }, + { + "current_steps": 2102, + "loss": 2.4863, + "learning_rate": 3.7402190923317684e-07, + "epoch": 3.191198786039454 + }, + { + "current_steps": 2103, + "loss": 2.6085, + "learning_rate": 3.7370892018779343e-07, + "epoch": 3.1927162367223065 + }, + { + "current_steps": 2104, + "loss": 2.5056, + "learning_rate": 3.7339593114241e-07, + "epoch": 3.194233687405159 + }, + { + "current_steps": 2105, + "loss": 2.448, + "learning_rate": 3.7308294209702655e-07, + "epoch": 3.195751138088012 + }, + { + "current_steps": 2106, + "loss": 2.7068, + "learning_rate": 3.727699530516432e-07, + "epoch": 3.197268588770865 + }, + { + "current_steps": 2107, + "loss": 2.3754, + "learning_rate": 3.7245696400625977e-07, + "epoch": 3.1987860394537178 + }, + { + "current_steps": 2108, + "loss": 2.1788, + "learning_rate": 3.7214397496087636e-07, + "epoch": 3.2003034901365703 + }, + { + "current_steps": 2109, + "loss": 2.5223, + "learning_rate": 3.7183098591549294e-07, + "epoch": 3.2018209408194234 + }, + { + "current_steps": 2110, + "loss": 2.5015, + "learning_rate": 3.7151799687010953e-07, + "epoch": 3.2033383915022764 + }, + { + "current_steps": 2111, + "loss": 2.6268, + "learning_rate": 3.712050078247261e-07, + "epoch": 3.204855842185129 + }, + { + "current_steps": 2112, + "loss": 2.7475, + "learning_rate": 3.7089201877934276e-07, + "epoch": 3.2063732928679816 + }, + { + "current_steps": 2113, + "loss": 2.5451, + "learning_rate": 3.705790297339593e-07, + "epoch": 3.2078907435508346 + }, + { + "current_steps": 2114, + "loss": 2.7588, + "learning_rate": 3.702660406885759e-07, + "epoch": 3.2094081942336876 + }, + { + "current_steps": 2115, + "loss": 2.6293, + "learning_rate": 3.6995305164319246e-07, + "epoch": 3.21092564491654 + }, + { + "current_steps": 2116, + "loss": 2.5299, + "learning_rate": 3.6964006259780905e-07, + "epoch": 3.212443095599393 + }, + { + "current_steps": 2117, + "loss": 2.5819, + "learning_rate": 3.6932707355242563e-07, + "epoch": 3.213960546282246 + }, + { + "current_steps": 2118, + "loss": 2.7456, + "learning_rate": 3.690140845070422e-07, + "epoch": 3.215477996965099 + }, + { + "current_steps": 2119, + "loss": 2.3703, + "learning_rate": 3.6870109546165886e-07, + "epoch": 3.2169954476479514 + }, + { + "current_steps": 2120, + "loss": 2.6856, + "learning_rate": 3.6838810641627544e-07, + "epoch": 3.2185128983308045 + }, + { + "current_steps": 2121, + "loss": 2.3307, + "learning_rate": 3.6807511737089203e-07, + "epoch": 3.220030349013657 + }, + { + "current_steps": 2122, + "loss": 2.3936, + "learning_rate": 3.6776212832550856e-07, + "epoch": 3.22154779969651 + }, + { + "current_steps": 2123, + "loss": 2.5291, + "learning_rate": 3.6744913928012515e-07, + "epoch": 3.2230652503793626 + }, + { + "current_steps": 2124, + "loss": 2.8036, + "learning_rate": 3.6713615023474174e-07, + "epoch": 3.2245827010622157 + }, + { + "current_steps": 2125, + "loss": 2.6181, + "learning_rate": 3.668231611893584e-07, + "epoch": 3.2261001517450683 + }, + { + "current_steps": 2126, + "loss": 2.6376, + "learning_rate": 3.6651017214397496e-07, + "epoch": 3.2276176024279213 + }, + { + "current_steps": 2127, + "loss": 2.6056, + "learning_rate": 3.6619718309859155e-07, + "epoch": 3.229135053110774 + }, + { + "current_steps": 2128, + "loss": 2.649, + "learning_rate": 3.6588419405320813e-07, + "epoch": 3.230652503793627 + }, + { + "current_steps": 2129, + "loss": 2.2512, + "learning_rate": 3.655712050078247e-07, + "epoch": 3.2321699544764795 + }, + { + "current_steps": 2130, + "loss": 2.4283, + "learning_rate": 3.6525821596244125e-07, + "epoch": 3.2336874051593325 + }, + { + "current_steps": 2131, + "loss": 2.4408, + "learning_rate": 3.649452269170579e-07, + "epoch": 3.235204855842185 + }, + { + "current_steps": 2132, + "loss": 2.4886, + "learning_rate": 3.646322378716745e-07, + "epoch": 3.236722306525038 + }, + { + "current_steps": 2133, + "loss": 2.5785, + "learning_rate": 3.6431924882629106e-07, + "epoch": 3.2382397572078907 + }, + { + "current_steps": 2134, + "loss": 2.7307, + "learning_rate": 3.6400625978090765e-07, + "epoch": 3.2397572078907437 + }, + { + "current_steps": 2135, + "loss": 2.5484, + "learning_rate": 3.6369327073552424e-07, + "epoch": 3.2412746585735963 + }, + { + "current_steps": 2136, + "loss": 2.677, + "learning_rate": 3.633802816901408e-07, + "epoch": 3.2427921092564493 + }, + { + "current_steps": 2137, + "loss": 2.6487, + "learning_rate": 3.6306729264475746e-07, + "epoch": 3.244309559939302 + }, + { + "current_steps": 2138, + "loss": 2.6693, + "learning_rate": 3.62754303599374e-07, + "epoch": 3.245827010622155 + }, + { + "current_steps": 2139, + "loss": 2.5964, + "learning_rate": 3.624413145539906e-07, + "epoch": 3.2473444613050075 + }, + { + "current_steps": 2140, + "loss": 1.4441, + "learning_rate": 3.6212832550860717e-07, + "epoch": 3.2488619119878606 + }, + { + "current_steps": 2141, + "loss": 2.415, + "learning_rate": 3.6181533646322375e-07, + "epoch": 3.250379362670713 + }, + { + "current_steps": 2142, + "loss": 2.6906, + "learning_rate": 3.6150234741784034e-07, + "epoch": 3.251896813353566 + }, + { + "current_steps": 2143, + "loss": 2.4679, + "learning_rate": 3.61189358372457e-07, + "epoch": 3.2534142640364188 + }, + { + "current_steps": 2144, + "loss": 2.4526, + "learning_rate": 3.6087636932707356e-07, + "epoch": 3.254931714719272 + }, + { + "current_steps": 2145, + "loss": 2.6252, + "learning_rate": 3.6056338028169015e-07, + "epoch": 3.2564491654021244 + }, + { + "current_steps": 2146, + "loss": 2.5464, + "learning_rate": 3.6025039123630674e-07, + "epoch": 3.2579666160849774 + }, + { + "current_steps": 2147, + "loss": 2.6464, + "learning_rate": 3.5993740219092327e-07, + "epoch": 3.25948406676783 + }, + { + "current_steps": 2148, + "loss": 2.4985, + "learning_rate": 3.5962441314553986e-07, + "epoch": 3.261001517450683 + }, + { + "current_steps": 2149, + "loss": 2.6822, + "learning_rate": 3.593114241001565e-07, + "epoch": 3.2625189681335356 + }, + { + "current_steps": 2150, + "loss": 2.4604, + "learning_rate": 3.589984350547731e-07, + "epoch": 3.2640364188163886 + }, + { + "current_steps": 2151, + "loss": 2.1528, + "learning_rate": 3.5868544600938967e-07, + "epoch": 3.265553869499241 + }, + { + "current_steps": 2152, + "loss": 2.4946, + "learning_rate": 3.5837245696400625e-07, + "epoch": 3.2670713201820942 + }, + { + "current_steps": 2153, + "loss": 2.6311, + "learning_rate": 3.5805946791862284e-07, + "epoch": 3.268588770864947 + }, + { + "current_steps": 2154, + "loss": 2.4423, + "learning_rate": 3.577464788732394e-07, + "epoch": 3.2701062215478 + }, + { + "current_steps": 2155, + "loss": 2.5462, + "learning_rate": 3.5743348982785596e-07, + "epoch": 3.2716236722306524 + }, + { + "current_steps": 2156, + "loss": 2.3789, + "learning_rate": 3.571205007824726e-07, + "epoch": 3.2731411229135055 + }, + { + "current_steps": 2157, + "loss": 2.5868, + "learning_rate": 3.568075117370892e-07, + "epoch": 3.274658573596358 + }, + { + "current_steps": 2158, + "loss": 2.7072, + "learning_rate": 3.5649452269170577e-07, + "epoch": 3.276176024279211 + }, + { + "current_steps": 2159, + "loss": 2.4698, + "learning_rate": 3.5618153364632236e-07, + "epoch": 3.2776934749620636 + }, + { + "current_steps": 2160, + "loss": 2.4413, + "learning_rate": 3.5586854460093894e-07, + "epoch": 3.2792109256449167 + }, + { + "current_steps": 2161, + "loss": 2.392, + "learning_rate": 3.5555555555555553e-07, + "epoch": 3.2807283763277693 + }, + { + "current_steps": 2162, + "loss": 2.6904, + "learning_rate": 3.5524256651017217e-07, + "epoch": 3.2822458270106223 + }, + { + "current_steps": 2163, + "loss": 2.1863, + "learning_rate": 3.5492957746478875e-07, + "epoch": 3.283763277693475 + }, + { + "current_steps": 2164, + "loss": 2.4539, + "learning_rate": 3.546165884194053e-07, + "epoch": 3.285280728376328 + }, + { + "current_steps": 2165, + "loss": 2.5729, + "learning_rate": 3.5430359937402187e-07, + "epoch": 3.2867981790591805 + }, + { + "current_steps": 2166, + "loss": 2.6139, + "learning_rate": 3.5399061032863846e-07, + "epoch": 3.2883156297420335 + }, + { + "current_steps": 2167, + "loss": 2.5752, + "learning_rate": 3.5367762128325504e-07, + "epoch": 3.289833080424886 + }, + { + "current_steps": 2168, + "loss": 2.5797, + "learning_rate": 3.533646322378717e-07, + "epoch": 3.291350531107739 + }, + { + "current_steps": 2169, + "loss": 2.5583, + "learning_rate": 3.5305164319248827e-07, + "epoch": 3.2928679817905917 + }, + { + "current_steps": 2170, + "loss": 2.3037, + "learning_rate": 3.5273865414710486e-07, + "epoch": 3.2943854324734447 + }, + { + "current_steps": 2171, + "loss": 2.6273, + "learning_rate": 3.5242566510172144e-07, + "epoch": 3.2959028831562973 + }, + { + "current_steps": 2172, + "loss": 2.5028, + "learning_rate": 3.52112676056338e-07, + "epoch": 3.2974203338391503 + }, + { + "current_steps": 2173, + "loss": 2.4307, + "learning_rate": 3.5179968701095456e-07, + "epoch": 3.298937784522003 + }, + { + "current_steps": 2174, + "loss": 2.9837, + "learning_rate": 3.514866979655712e-07, + "epoch": 3.300455235204856 + }, + { + "current_steps": 2175, + "loss": 2.5111, + "learning_rate": 3.511737089201878e-07, + "epoch": 3.3019726858877085 + }, + { + "current_steps": 2176, + "loss": 2.5181, + "learning_rate": 3.5086071987480437e-07, + "epoch": 3.3034901365705616 + }, + { + "current_steps": 2177, + "loss": 2.6511, + "learning_rate": 3.5054773082942096e-07, + "epoch": 3.305007587253414 + }, + { + "current_steps": 2178, + "loss": 2.5369, + "learning_rate": 3.5023474178403754e-07, + "epoch": 3.306525037936267 + }, + { + "current_steps": 2179, + "loss": 2.5192, + "learning_rate": 3.4992175273865413e-07, + "epoch": 3.3080424886191198 + }, + { + "current_steps": 2180, + "loss": 2.1411, + "learning_rate": 3.4960876369327077e-07, + "epoch": 3.309559939301973 + }, + { + "current_steps": 2181, + "loss": 2.5082, + "learning_rate": 3.492957746478873e-07, + "epoch": 3.3110773899848254 + }, + { + "current_steps": 2182, + "loss": 2.504, + "learning_rate": 3.489827856025039e-07, + "epoch": 3.3125948406676784 + }, + { + "current_steps": 2183, + "loss": 2.6953, + "learning_rate": 3.486697965571205e-07, + "epoch": 3.314112291350531 + }, + { + "current_steps": 2184, + "loss": 2.6233, + "learning_rate": 3.4835680751173706e-07, + "epoch": 3.315629742033384 + }, + { + "current_steps": 2185, + "loss": 2.5579, + "learning_rate": 3.4804381846635365e-07, + "epoch": 3.3171471927162366 + }, + { + "current_steps": 2186, + "loss": 2.6612, + "learning_rate": 3.477308294209703e-07, + "epoch": 3.3186646433990896 + }, + { + "current_steps": 2187, + "loss": 2.428, + "learning_rate": 3.4741784037558687e-07, + "epoch": 3.320182094081942 + }, + { + "current_steps": 2188, + "loss": 2.5541, + "learning_rate": 3.4710485133020346e-07, + "epoch": 3.3216995447647952 + }, + { + "current_steps": 2189, + "loss": 2.6862, + "learning_rate": 3.4679186228482e-07, + "epoch": 3.323216995447648 + }, + { + "current_steps": 2190, + "loss": 2.1261, + "learning_rate": 3.464788732394366e-07, + "epoch": 3.324734446130501 + }, + { + "current_steps": 2191, + "loss": 2.8253, + "learning_rate": 3.4616588419405316e-07, + "epoch": 3.3262518968133534 + }, + { + "current_steps": 2192, + "loss": 2.6423, + "learning_rate": 3.4585289514866975e-07, + "epoch": 3.3277693474962065 + }, + { + "current_steps": 2193, + "loss": 2.1499, + "learning_rate": 3.455399061032864e-07, + "epoch": 3.329286798179059 + }, + { + "current_steps": 2194, + "loss": 2.401, + "learning_rate": 3.45226917057903e-07, + "epoch": 3.330804248861912 + }, + { + "current_steps": 2195, + "loss": 2.6613, + "learning_rate": 3.4491392801251956e-07, + "epoch": 3.3323216995447646 + }, + { + "current_steps": 2196, + "loss": 2.525, + "learning_rate": 3.4460093896713615e-07, + "epoch": 3.3338391502276177 + }, + { + "current_steps": 2197, + "loss": 2.4563, + "learning_rate": 3.442879499217527e-07, + "epoch": 3.3353566009104703 + }, + { + "current_steps": 2198, + "loss": 2.4475, + "learning_rate": 3.4397496087636927e-07, + "epoch": 3.3368740515933233 + }, + { + "current_steps": 2199, + "loss": 2.6278, + "learning_rate": 3.436619718309859e-07, + "epoch": 3.338391502276176 + }, + { + "current_steps": 2200, + "loss": 2.4415, + "learning_rate": 3.433489827856025e-07, + "epoch": 3.339908952959029 + }, + { + "current_steps": 2201, + "loss": 2.5862, + "learning_rate": 3.430359937402191e-07, + "epoch": 3.3414264036418815 + }, + { + "current_steps": 2202, + "loss": 2.5646, + "learning_rate": 3.4272300469483566e-07, + "epoch": 3.3429438543247345 + }, + { + "current_steps": 2203, + "loss": 2.1161, + "learning_rate": 3.4241001564945225e-07, + "epoch": 3.344461305007587 + }, + { + "current_steps": 2204, + "loss": 2.0405, + "learning_rate": 3.4209702660406884e-07, + "epoch": 3.34597875569044 + }, + { + "current_steps": 2205, + "loss": 2.4808, + "learning_rate": 3.417840375586855e-07, + "epoch": 3.3474962063732927 + }, + { + "current_steps": 2206, + "loss": 2.2941, + "learning_rate": 3.41471048513302e-07, + "epoch": 3.3490136570561457 + }, + { + "current_steps": 2207, + "loss": 2.5969, + "learning_rate": 3.411580594679186e-07, + "epoch": 3.3505311077389983 + }, + { + "current_steps": 2208, + "loss": 2.1257, + "learning_rate": 3.408450704225352e-07, + "epoch": 3.3520485584218513 + }, + { + "current_steps": 2209, + "loss": 2.4588, + "learning_rate": 3.4053208137715177e-07, + "epoch": 3.353566009104704 + }, + { + "current_steps": 2210, + "loss": 2.4406, + "learning_rate": 3.4021909233176835e-07, + "epoch": 3.355083459787557 + }, + { + "current_steps": 2211, + "loss": 2.4517, + "learning_rate": 3.39906103286385e-07, + "epoch": 3.3566009104704095 + }, + { + "current_steps": 2212, + "loss": 2.6333, + "learning_rate": 3.395931142410016e-07, + "epoch": 3.3581183611532626 + }, + { + "current_steps": 2213, + "loss": 2.3363, + "learning_rate": 3.3928012519561816e-07, + "epoch": 3.359635811836115 + }, + { + "current_steps": 2214, + "loss": 2.5184, + "learning_rate": 3.389671361502347e-07, + "epoch": 3.361153262518968 + }, + { + "current_steps": 2215, + "loss": 2.718, + "learning_rate": 3.386541471048513e-07, + "epoch": 3.3626707132018208 + }, + { + "current_steps": 2216, + "loss": 2.4905, + "learning_rate": 3.3834115805946787e-07, + "epoch": 3.364188163884674 + }, + { + "current_steps": 2217, + "loss": 2.546, + "learning_rate": 3.380281690140845e-07, + "epoch": 3.3657056145675264 + }, + { + "current_steps": 2218, + "loss": 2.4432, + "learning_rate": 3.377151799687011e-07, + "epoch": 3.3672230652503794 + }, + { + "current_steps": 2219, + "loss": 2.7167, + "learning_rate": 3.374021909233177e-07, + "epoch": 3.368740515933232 + }, + { + "current_steps": 2220, + "loss": 2.5244, + "learning_rate": 3.3708920187793427e-07, + "epoch": 3.370257966616085 + }, + { + "current_steps": 2221, + "loss": 2.3824, + "learning_rate": 3.3677621283255085e-07, + "epoch": 3.3717754172989376 + }, + { + "current_steps": 2222, + "loss": 2.5481, + "learning_rate": 3.3646322378716744e-07, + "epoch": 3.3732928679817906 + }, + { + "current_steps": 2223, + "loss": 2.5502, + "learning_rate": 3.36150234741784e-07, + "epoch": 3.374810318664643 + }, + { + "current_steps": 2224, + "loss": 2.611, + "learning_rate": 3.358372456964006e-07, + "epoch": 3.3763277693474962 + }, + { + "current_steps": 2225, + "loss": 2.5596, + "learning_rate": 3.355242566510172e-07, + "epoch": 3.3778452200303493 + }, + { + "current_steps": 2226, + "loss": 2.6766, + "learning_rate": 3.352112676056338e-07, + "epoch": 3.379362670713202 + }, + { + "current_steps": 2227, + "loss": 2.5723, + "learning_rate": 3.3489827856025037e-07, + "epoch": 3.3808801213960544 + }, + { + "current_steps": 2228, + "loss": 2.5428, + "learning_rate": 3.3458528951486696e-07, + "epoch": 3.3823975720789075 + }, + { + "current_steps": 2229, + "loss": 2.5826, + "learning_rate": 3.342723004694836e-07, + "epoch": 3.3839150227617605 + }, + { + "current_steps": 2230, + "loss": 2.5273, + "learning_rate": 3.339593114241002e-07, + "epoch": 3.385432473444613 + }, + { + "current_steps": 2231, + "loss": 2.6294, + "learning_rate": 3.336463223787167e-07, + "epoch": 3.3869499241274656 + }, + { + "current_steps": 2232, + "loss": 2.7576, + "learning_rate": 3.333333333333333e-07, + "epoch": 3.3884673748103187 + }, + { + "current_steps": 2233, + "loss": 2.4553, + "learning_rate": 3.330203442879499e-07, + "epoch": 3.3899848254931717 + }, + { + "current_steps": 2234, + "loss": 2.4995, + "learning_rate": 3.3270735524256647e-07, + "epoch": 3.3915022761760243 + }, + { + "current_steps": 2235, + "loss": 2.4734, + "learning_rate": 3.3239436619718306e-07, + "epoch": 3.393019726858877 + }, + { + "current_steps": 2236, + "loss": 2.6085, + "learning_rate": 3.320813771517997e-07, + "epoch": 3.39453717754173 + }, + { + "current_steps": 2237, + "loss": 2.5442, + "learning_rate": 3.317683881064163e-07, + "epoch": 3.396054628224583 + }, + { + "current_steps": 2238, + "loss": 2.4642, + "learning_rate": 3.3145539906103287e-07, + "epoch": 3.3975720789074355 + }, + { + "current_steps": 2239, + "loss": 2.4013, + "learning_rate": 3.3114241001564946e-07, + "epoch": 3.399089529590288 + }, + { + "current_steps": 2240, + "loss": 2.5676, + "learning_rate": 3.30829420970266e-07, + "epoch": 3.400606980273141 + }, + { + "current_steps": 2241, + "loss": 2.6475, + "learning_rate": 3.305164319248826e-07, + "epoch": 3.402124430955994 + }, + { + "current_steps": 2242, + "loss": 2.6359, + "learning_rate": 3.302034428794992e-07, + "epoch": 3.4036418816388467 + }, + { + "current_steps": 2243, + "loss": 2.6086, + "learning_rate": 3.298904538341158e-07, + "epoch": 3.4051593323216993 + }, + { + "current_steps": 2244, + "loss": 2.5715, + "learning_rate": 3.295774647887324e-07, + "epoch": 3.4066767830045523 + }, + { + "current_steps": 2245, + "loss": 2.2782, + "learning_rate": 3.2926447574334897e-07, + "epoch": 3.4081942336874054 + }, + { + "current_steps": 2246, + "loss": 2.6835, + "learning_rate": 3.2895148669796556e-07, + "epoch": 3.409711684370258 + }, + { + "current_steps": 2247, + "loss": 2.5164, + "learning_rate": 3.2863849765258215e-07, + "epoch": 3.4112291350531105 + }, + { + "current_steps": 2248, + "loss": 2.4775, + "learning_rate": 3.2832550860719873e-07, + "epoch": 3.4127465857359636 + }, + { + "current_steps": 2249, + "loss": 2.6181, + "learning_rate": 3.280125195618153e-07, + "epoch": 3.4142640364188166 + }, + { + "current_steps": 2250, + "loss": 2.4406, + "learning_rate": 3.276995305164319e-07, + "epoch": 3.415781487101669 + }, + { + "current_steps": 2251, + "loss": 2.6988, + "learning_rate": 3.273865414710485e-07, + "epoch": 3.4172989377845218 + }, + { + "current_steps": 2252, + "loss": 2.8075, + "learning_rate": 3.270735524256651e-07, + "epoch": 3.418816388467375 + }, + { + "current_steps": 2253, + "loss": 2.5127, + "learning_rate": 3.2676056338028166e-07, + "epoch": 3.420333839150228 + }, + { + "current_steps": 2254, + "loss": 2.6479, + "learning_rate": 3.264475743348983e-07, + "epoch": 3.4218512898330804 + }, + { + "current_steps": 2255, + "loss": 2.3841, + "learning_rate": 3.261345852895149e-07, + "epoch": 3.423368740515933 + }, + { + "current_steps": 2256, + "loss": 2.686, + "learning_rate": 3.258215962441314e-07, + "epoch": 3.424886191198786 + }, + { + "current_steps": 2257, + "loss": 2.4982, + "learning_rate": 3.25508607198748e-07, + "epoch": 3.426403641881639 + }, + { + "current_steps": 2258, + "loss": 2.4802, + "learning_rate": 3.251956181533646e-07, + "epoch": 3.4279210925644916 + }, + { + "current_steps": 2259, + "loss": 2.4559, + "learning_rate": 3.248826291079812e-07, + "epoch": 3.4294385432473447 + }, + { + "current_steps": 2260, + "loss": 2.53, + "learning_rate": 3.245696400625978e-07, + "epoch": 3.4309559939301972 + }, + { + "current_steps": 2261, + "loss": 2.5836, + "learning_rate": 3.242566510172144e-07, + "epoch": 3.4324734446130503 + }, + { + "current_steps": 2262, + "loss": 2.4463, + "learning_rate": 3.23943661971831e-07, + "epoch": 3.433990895295903 + }, + { + "current_steps": 2263, + "loss": 2.5011, + "learning_rate": 3.236306729264476e-07, + "epoch": 3.435508345978756 + }, + { + "current_steps": 2264, + "loss": 2.5763, + "learning_rate": 3.2331768388106416e-07, + "epoch": 3.4370257966616085 + }, + { + "current_steps": 2265, + "loss": 2.6134, + "learning_rate": 3.230046948356807e-07, + "epoch": 3.4385432473444615 + }, + { + "current_steps": 2266, + "loss": 2.1822, + "learning_rate": 3.2269170579029733e-07, + "epoch": 3.440060698027314 + }, + { + "current_steps": 2267, + "loss": 2.5014, + "learning_rate": 3.223787167449139e-07, + "epoch": 3.441578148710167 + }, + { + "current_steps": 2268, + "loss": 2.4865, + "learning_rate": 3.220657276995305e-07, + "epoch": 3.4430955993930197 + }, + { + "current_steps": 2269, + "loss": 2.6384, + "learning_rate": 3.217527386541471e-07, + "epoch": 3.4446130500758727 + }, + { + "current_steps": 2270, + "loss": 2.6393, + "learning_rate": 3.214397496087637e-07, + "epoch": 3.4461305007587253 + }, + { + "current_steps": 2271, + "loss": 2.5009, + "learning_rate": 3.2112676056338026e-07, + "epoch": 3.4476479514415783 + }, + { + "current_steps": 2272, + "loss": 2.5666, + "learning_rate": 3.208137715179969e-07, + "epoch": 3.449165402124431 + }, + { + "current_steps": 2273, + "loss": 2.8644, + "learning_rate": 3.2050078247261344e-07, + "epoch": 3.450682852807284 + }, + { + "current_steps": 2274, + "loss": 2.5978, + "learning_rate": 3.2018779342723e-07, + "epoch": 3.4522003034901365 + }, + { + "current_steps": 2275, + "loss": 2.5394, + "learning_rate": 3.198748043818466e-07, + "epoch": 3.4537177541729895 + }, + { + "current_steps": 2276, + "loss": 2.4916, + "learning_rate": 3.195618153364632e-07, + "epoch": 3.455235204855842 + }, + { + "current_steps": 2277, + "loss": 2.4629, + "learning_rate": 3.192488262910798e-07, + "epoch": 3.456752655538695 + }, + { + "current_steps": 2278, + "loss": 2.4027, + "learning_rate": 3.1893583724569637e-07, + "epoch": 3.4582701062215477 + }, + { + "current_steps": 2279, + "loss": 2.7012, + "learning_rate": 3.18622848200313e-07, + "epoch": 3.4597875569044008 + }, + { + "current_steps": 2280, + "loss": 2.4975, + "learning_rate": 3.183098591549296e-07, + "epoch": 3.4613050075872533 + }, + { + "current_steps": 2281, + "loss": 2.6196, + "learning_rate": 3.179968701095462e-07, + "epoch": 3.4628224582701064 + }, + { + "current_steps": 2282, + "loss": 2.4136, + "learning_rate": 3.176838810641627e-07, + "epoch": 3.464339908952959 + }, + { + "current_steps": 2283, + "loss": 2.3535, + "learning_rate": 3.173708920187793e-07, + "epoch": 3.465857359635812 + }, + { + "current_steps": 2284, + "loss": 2.6169, + "learning_rate": 3.170579029733959e-07, + "epoch": 3.4673748103186646 + }, + { + "current_steps": 2285, + "loss": 2.4178, + "learning_rate": 3.167449139280125e-07, + "epoch": 3.4688922610015176 + }, + { + "current_steps": 2286, + "loss": 2.3677, + "learning_rate": 3.164319248826291e-07, + "epoch": 3.47040971168437 + }, + { + "current_steps": 2287, + "loss": 2.4056, + "learning_rate": 3.161189358372457e-07, + "epoch": 3.471927162367223 + }, + { + "current_steps": 2288, + "loss": 2.6427, + "learning_rate": 3.158059467918623e-07, + "epoch": 3.473444613050076 + }, + { + "current_steps": 2289, + "loss": 2.167, + "learning_rate": 3.1549295774647887e-07, + "epoch": 3.474962063732929 + }, + { + "current_steps": 2290, + "loss": 2.5872, + "learning_rate": 3.151799687010954e-07, + "epoch": 3.4764795144157814 + }, + { + "current_steps": 2291, + "loss": 2.6312, + "learning_rate": 3.1486697965571204e-07, + "epoch": 3.4779969650986344 + }, + { + "current_steps": 2292, + "loss": 2.7749, + "learning_rate": 3.145539906103286e-07, + "epoch": 3.479514415781487 + }, + { + "current_steps": 2293, + "loss": 2.5295, + "learning_rate": 3.142410015649452e-07, + "epoch": 3.48103186646434 + }, + { + "current_steps": 2294, + "loss": 2.6323, + "learning_rate": 3.139280125195618e-07, + "epoch": 3.4825493171471926 + }, + { + "current_steps": 2295, + "loss": 2.6252, + "learning_rate": 3.136150234741784e-07, + "epoch": 3.4840667678300457 + }, + { + "current_steps": 2296, + "loss": 2.4192, + "learning_rate": 3.1330203442879497e-07, + "epoch": 3.4855842185128982 + }, + { + "current_steps": 2297, + "loss": 2.5121, + "learning_rate": 3.129890453834116e-07, + "epoch": 3.4871016691957513 + }, + { + "current_steps": 2298, + "loss": 2.5226, + "learning_rate": 3.126760563380282e-07, + "epoch": 3.488619119878604 + }, + { + "current_steps": 2299, + "loss": 2.4121, + "learning_rate": 3.1236306729264473e-07, + "epoch": 3.490136570561457 + }, + { + "current_steps": 2300, + "loss": 2.4156, + "learning_rate": 3.120500782472613e-07, + "epoch": 3.4916540212443095 + }, + { + "current_steps": 2301, + "loss": 2.4386, + "learning_rate": 3.117370892018779e-07, + "epoch": 3.4931714719271625 + }, + { + "current_steps": 2302, + "loss": 2.6924, + "learning_rate": 3.114241001564945e-07, + "epoch": 3.494688922610015 + }, + { + "current_steps": 2303, + "loss": 2.5125, + "learning_rate": 3.111111111111111e-07, + "epoch": 3.496206373292868 + }, + { + "current_steps": 2304, + "loss": 2.4577, + "learning_rate": 3.107981220657277e-07, + "epoch": 3.4977238239757207 + }, + { + "current_steps": 2305, + "loss": 2.4394, + "learning_rate": 3.104851330203443e-07, + "epoch": 3.4992412746585737 + }, + { + "current_steps": 2306, + "loss": 2.5184, + "learning_rate": 3.101721439749609e-07, + "epoch": 3.5007587253414263 + }, + { + "current_steps": 2307, + "loss": 2.4024, + "learning_rate": 3.098591549295774e-07, + "epoch": 3.5022761760242793 + }, + { + "current_steps": 2308, + "loss": 2.6534, + "learning_rate": 3.09546165884194e-07, + "epoch": 3.503793626707132 + }, + { + "current_steps": 2309, + "loss": 2.6859, + "learning_rate": 3.092331768388106e-07, + "epoch": 3.505311077389985 + }, + { + "current_steps": 2310, + "loss": 2.5607, + "learning_rate": 3.0892018779342723e-07, + "epoch": 3.5068285280728375 + }, + { + "current_steps": 2311, + "loss": 2.5373, + "learning_rate": 3.086071987480438e-07, + "epoch": 3.5083459787556905 + }, + { + "current_steps": 2312, + "loss": 2.4978, + "learning_rate": 3.082942097026604e-07, + "epoch": 3.509863429438543 + }, + { + "current_steps": 2313, + "loss": 2.431, + "learning_rate": 3.07981220657277e-07, + "epoch": 3.511380880121396 + }, + { + "current_steps": 2314, + "loss": 2.3572, + "learning_rate": 3.076682316118936e-07, + "epoch": 3.5128983308042487 + }, + { + "current_steps": 2315, + "loss": 2.5874, + "learning_rate": 3.073552425665101e-07, + "epoch": 3.5144157814871018 + }, + { + "current_steps": 2316, + "loss": 2.6884, + "learning_rate": 3.0704225352112675e-07, + "epoch": 3.5159332321699543 + }, + { + "current_steps": 2317, + "loss": 2.4997, + "learning_rate": 3.0672926447574333e-07, + "epoch": 3.5174506828528074 + }, + { + "current_steps": 2318, + "loss": 2.6064, + "learning_rate": 3.064162754303599e-07, + "epoch": 3.51896813353566 + }, + { + "current_steps": 2319, + "loss": 2.4014, + "learning_rate": 3.061032863849765e-07, + "epoch": 3.520485584218513 + }, + { + "current_steps": 2320, + "loss": 2.4694, + "learning_rate": 3.057902973395931e-07, + "epoch": 3.5220030349013656 + }, + { + "current_steps": 2321, + "loss": 2.1927, + "learning_rate": 3.054773082942097e-07, + "epoch": 3.5235204855842186 + }, + { + "current_steps": 2322, + "loss": 2.7135, + "learning_rate": 3.051643192488263e-07, + "epoch": 3.525037936267071 + }, + { + "current_steps": 2323, + "loss": 2.5942, + "learning_rate": 3.048513302034429e-07, + "epoch": 3.526555386949924 + }, + { + "current_steps": 2324, + "loss": 2.5644, + "learning_rate": 3.0453834115805943e-07, + "epoch": 3.528072837632777 + }, + { + "current_steps": 2325, + "loss": 2.3523, + "learning_rate": 3.04225352112676e-07, + "epoch": 3.52959028831563 + }, + { + "current_steps": 2326, + "loss": 2.5608, + "learning_rate": 3.039123630672926e-07, + "epoch": 3.5311077389984824 + }, + { + "current_steps": 2327, + "loss": 2.6892, + "learning_rate": 3.035993740219092e-07, + "epoch": 3.5326251896813354 + }, + { + "current_steps": 2328, + "loss": 2.4247, + "learning_rate": 3.0328638497652583e-07, + "epoch": 3.534142640364188 + }, + { + "current_steps": 2329, + "loss": 2.3235, + "learning_rate": 3.029733959311424e-07, + "epoch": 3.535660091047041 + }, + { + "current_steps": 2330, + "loss": 2.4187, + "learning_rate": 3.02660406885759e-07, + "epoch": 3.5371775417298936 + }, + { + "current_steps": 2331, + "loss": 2.5454, + "learning_rate": 3.023474178403756e-07, + "epoch": 3.5386949924127467 + }, + { + "current_steps": 2332, + "loss": 2.5544, + "learning_rate": 3.020344287949921e-07, + "epoch": 3.5402124430955992 + }, + { + "current_steps": 2333, + "loss": 2.158, + "learning_rate": 3.017214397496087e-07, + "epoch": 3.5417298937784523 + }, + { + "current_steps": 2334, + "loss": 2.4422, + "learning_rate": 3.0140845070422535e-07, + "epoch": 3.543247344461305 + }, + { + "current_steps": 2335, + "loss": 2.5, + "learning_rate": 3.0109546165884194e-07, + "epoch": 3.544764795144158 + }, + { + "current_steps": 2336, + "loss": 2.5238, + "learning_rate": 3.007824726134585e-07, + "epoch": 3.5462822458270105 + }, + { + "current_steps": 2337, + "loss": 2.5042, + "learning_rate": 3.004694835680751e-07, + "epoch": 3.5477996965098635 + }, + { + "current_steps": 2338, + "loss": 2.6165, + "learning_rate": 3.001564945226917e-07, + "epoch": 3.549317147192716 + }, + { + "current_steps": 2339, + "loss": 2.5485, + "learning_rate": 2.998435054773083e-07, + "epoch": 3.550834597875569 + }, + { + "current_steps": 2340, + "loss": 2.5596, + "learning_rate": 2.995305164319249e-07, + "epoch": 3.552352048558422 + }, + { + "current_steps": 2341, + "loss": 2.6491, + "learning_rate": 2.9921752738654145e-07, + "epoch": 3.5538694992412747 + }, + { + "current_steps": 2342, + "loss": 2.4907, + "learning_rate": 2.9890453834115804e-07, + "epoch": 3.5553869499241273 + }, + { + "current_steps": 2343, + "loss": 2.5601, + "learning_rate": 2.985915492957746e-07, + "epoch": 3.5569044006069803 + }, + { + "current_steps": 2344, + "loss": 2.5464, + "learning_rate": 2.982785602503912e-07, + "epoch": 3.5584218512898333 + }, + { + "current_steps": 2345, + "loss": 2.5829, + "learning_rate": 2.979655712050078e-07, + "epoch": 3.559939301972686 + }, + { + "current_steps": 2346, + "loss": 2.5535, + "learning_rate": 2.9765258215962444e-07, + "epoch": 3.5614567526555385 + }, + { + "current_steps": 2347, + "loss": 2.376, + "learning_rate": 2.97339593114241e-07, + "epoch": 3.5629742033383915 + }, + { + "current_steps": 2348, + "loss": 2.5284, + "learning_rate": 2.970266040688576e-07, + "epoch": 3.5644916540212446 + }, + { + "current_steps": 2349, + "loss": 2.5681, + "learning_rate": 2.9671361502347414e-07, + "epoch": 3.566009104704097 + }, + { + "current_steps": 2350, + "loss": 2.4704, + "learning_rate": 2.9640062597809073e-07, + "epoch": 3.5675265553869497 + }, + { + "current_steps": 2351, + "loss": 2.7193, + "learning_rate": 2.960876369327073e-07, + "epoch": 3.5690440060698028 + }, + { + "current_steps": 2352, + "loss": 2.424, + "learning_rate": 2.957746478873239e-07, + "epoch": 3.570561456752656 + }, + { + "current_steps": 2353, + "loss": 2.3997, + "learning_rate": 2.9546165884194054e-07, + "epoch": 3.5720789074355084 + }, + { + "current_steps": 2354, + "loss": 2.5348, + "learning_rate": 2.951486697965571e-07, + "epoch": 3.573596358118361 + }, + { + "current_steps": 2355, + "loss": 2.5901, + "learning_rate": 2.948356807511737e-07, + "epoch": 3.575113808801214 + }, + { + "current_steps": 2356, + "loss": 2.5842, + "learning_rate": 2.945226917057903e-07, + "epoch": 3.576631259484067 + }, + { + "current_steps": 2357, + "loss": 2.4404, + "learning_rate": 2.942097026604069e-07, + "epoch": 3.5781487101669196 + }, + { + "current_steps": 2358, + "loss": 2.4803, + "learning_rate": 2.938967136150234e-07, + "epoch": 3.579666160849772 + }, + { + "current_steps": 2359, + "loss": 2.3797, + "learning_rate": 2.9358372456964005e-07, + "epoch": 3.581183611532625 + }, + { + "current_steps": 2360, + "loss": 2.5335, + "learning_rate": 2.9327073552425664e-07, + "epoch": 3.5827010622154782 + }, + { + "current_steps": 2361, + "loss": 2.3832, + "learning_rate": 2.9295774647887323e-07, + "epoch": 3.584218512898331 + }, + { + "current_steps": 2362, + "loss": 2.5866, + "learning_rate": 2.926447574334898e-07, + "epoch": 3.5857359635811834 + }, + { + "current_steps": 2363, + "loss": 2.4692, + "learning_rate": 2.923317683881064e-07, + "epoch": 3.5872534142640364 + }, + { + "current_steps": 2364, + "loss": 2.8246, + "learning_rate": 2.92018779342723e-07, + "epoch": 3.5887708649468895 + }, + { + "current_steps": 2365, + "loss": 2.2458, + "learning_rate": 2.917057902973396e-07, + "epoch": 3.590288315629742 + }, + { + "current_steps": 2366, + "loss": 2.4071, + "learning_rate": 2.9139280125195616e-07, + "epoch": 3.5918057663125946 + }, + { + "current_steps": 2367, + "loss": 2.5731, + "learning_rate": 2.9107981220657274e-07, + "epoch": 3.5933232169954477 + }, + { + "current_steps": 2368, + "loss": 2.5697, + "learning_rate": 2.9076682316118933e-07, + "epoch": 3.5948406676783007 + }, + { + "current_steps": 2369, + "loss": 2.6313, + "learning_rate": 2.904538341158059e-07, + "epoch": 3.5963581183611533 + }, + { + "current_steps": 2370, + "loss": 2.4661, + "learning_rate": 2.901408450704225e-07, + "epoch": 3.597875569044006 + }, + { + "current_steps": 2371, + "loss": 2.5027, + "learning_rate": 2.8982785602503914e-07, + "epoch": 3.599393019726859 + }, + { + "current_steps": 2372, + "loss": 2.5781, + "learning_rate": 2.8951486697965573e-07, + "epoch": 3.600910470409712 + }, + { + "current_steps": 2373, + "loss": 2.8134, + "learning_rate": 2.892018779342723e-07, + "epoch": 3.6024279210925645 + }, + { + "current_steps": 2374, + "loss": 2.6035, + "learning_rate": 2.8888888888888885e-07, + "epoch": 3.603945371775417 + }, + { + "current_steps": 2375, + "loss": 2.4906, + "learning_rate": 2.8857589984350543e-07, + "epoch": 3.60546282245827 + }, + { + "current_steps": 2376, + "loss": 2.358, + "learning_rate": 2.88262910798122e-07, + "epoch": 3.606980273141123 + }, + { + "current_steps": 2377, + "loss": 2.3552, + "learning_rate": 2.8794992175273866e-07, + "epoch": 3.6084977238239757 + }, + { + "current_steps": 2378, + "loss": 2.6623, + "learning_rate": 2.8763693270735524e-07, + "epoch": 3.6100151745068283 + }, + { + "current_steps": 2379, + "loss": 2.3377, + "learning_rate": 2.8732394366197183e-07, + "epoch": 3.6115326251896813 + }, + { + "current_steps": 2380, + "loss": 2.4912, + "learning_rate": 2.870109546165884e-07, + "epoch": 3.6130500758725344 + }, + { + "current_steps": 2381, + "loss": 2.2707, + "learning_rate": 2.86697965571205e-07, + "epoch": 3.614567526555387 + }, + { + "current_steps": 2382, + "loss": 2.5629, + "learning_rate": 2.863849765258216e-07, + "epoch": 3.6160849772382395 + }, + { + "current_steps": 2383, + "loss": 2.8552, + "learning_rate": 2.860719874804382e-07, + "epoch": 3.6176024279210925 + }, + { + "current_steps": 2384, + "loss": 2.5353, + "learning_rate": 2.8575899843505476e-07, + "epoch": 3.6191198786039456 + }, + { + "current_steps": 2385, + "loss": 2.6734, + "learning_rate": 2.8544600938967135e-07, + "epoch": 3.620637329286798 + }, + { + "current_steps": 2386, + "loss": 2.5539, + "learning_rate": 2.8513302034428793e-07, + "epoch": 3.6221547799696507 + }, + { + "current_steps": 2387, + "loss": 2.8593, + "learning_rate": 2.848200312989045e-07, + "epoch": 3.6236722306525038 + }, + { + "current_steps": 2388, + "loss": 2.5965, + "learning_rate": 2.845070422535211e-07, + "epoch": 3.625189681335357 + }, + { + "current_steps": 2389, + "loss": 2.6179, + "learning_rate": 2.8419405320813774e-07, + "epoch": 3.6267071320182094 + }, + { + "current_steps": 2390, + "loss": 2.6031, + "learning_rate": 2.8388106416275433e-07, + "epoch": 3.628224582701062 + }, + { + "current_steps": 2391, + "loss": 2.6505, + "learning_rate": 2.8356807511737086e-07, + "epoch": 3.629742033383915 + }, + { + "current_steps": 2392, + "loss": 2.4575, + "learning_rate": 2.8325508607198745e-07, + "epoch": 3.631259484066768 + }, + { + "current_steps": 2393, + "loss": 2.5411, + "learning_rate": 2.8294209702660404e-07, + "epoch": 3.6327769347496206 + }, + { + "current_steps": 2394, + "loss": 2.5734, + "learning_rate": 2.826291079812206e-07, + "epoch": 3.634294385432473 + }, + { + "current_steps": 2395, + "loss": 2.5612, + "learning_rate": 2.823161189358372e-07, + "epoch": 3.635811836115326 + }, + { + "current_steps": 2396, + "loss": 2.5464, + "learning_rate": 2.8200312989045385e-07, + "epoch": 3.6373292867981792 + }, + { + "current_steps": 2397, + "loss": 2.3116, + "learning_rate": 2.8169014084507043e-07, + "epoch": 3.638846737481032 + }, + { + "current_steps": 2398, + "loss": 1.9804, + "learning_rate": 2.81377151799687e-07, + "epoch": 3.6403641881638844 + }, + { + "current_steps": 2399, + "loss": 2.5735, + "learning_rate": 2.810641627543036e-07, + "epoch": 3.6418816388467374 + }, + { + "current_steps": 2400, + "loss": 2.6197, + "learning_rate": 2.8075117370892014e-07, + "epoch": 3.6433990895295905 + }, + { + "current_steps": 2401, + "loss": 2.8202, + "learning_rate": 2.804381846635367e-07, + "epoch": 3.644916540212443 + }, + { + "current_steps": 2402, + "loss": 2.5319, + "learning_rate": 2.8012519561815336e-07, + "epoch": 3.6464339908952956 + }, + { + "current_steps": 2403, + "loss": 2.7119, + "learning_rate": 2.7981220657276995e-07, + "epoch": 3.6479514415781487 + }, + { + "current_steps": 2404, + "loss": 2.512, + "learning_rate": 2.7949921752738654e-07, + "epoch": 3.6494688922610017 + }, + { + "current_steps": 2405, + "loss": 2.3792, + "learning_rate": 2.791862284820031e-07, + "epoch": 3.6509863429438543 + }, + { + "current_steps": 2406, + "loss": 2.5902, + "learning_rate": 2.788732394366197e-07, + "epoch": 3.6525037936267073 + }, + { + "current_steps": 2407, + "loss": 2.7776, + "learning_rate": 2.785602503912363e-07, + "epoch": 3.65402124430956 + }, + { + "current_steps": 2408, + "loss": 2.6519, + "learning_rate": 2.782472613458529e-07, + "epoch": 3.655538694992413 + }, + { + "current_steps": 2409, + "loss": 2.5788, + "learning_rate": 2.7793427230046947e-07, + "epoch": 3.6570561456752655 + }, + { + "current_steps": 2410, + "loss": 2.2214, + "learning_rate": 2.7762128325508605e-07, + "epoch": 3.6585735963581185 + }, + { + "current_steps": 2411, + "loss": 2.769, + "learning_rate": 2.7730829420970264e-07, + "epoch": 3.660091047040971 + }, + { + "current_steps": 2412, + "loss": 2.5484, + "learning_rate": 2.769953051643192e-07, + "epoch": 3.661608497723824 + }, + { + "current_steps": 2413, + "loss": 2.7065, + "learning_rate": 2.766823161189358e-07, + "epoch": 3.6631259484066767 + }, + { + "current_steps": 2414, + "loss": 2.3589, + "learning_rate": 2.7636932707355245e-07, + "epoch": 3.6646433990895297 + }, + { + "current_steps": 2415, + "loss": 2.6168, + "learning_rate": 2.7605633802816904e-07, + "epoch": 3.6661608497723823 + }, + { + "current_steps": 2416, + "loss": 2.4649, + "learning_rate": 2.757433489827856e-07, + "epoch": 3.6676783004552354 + }, + { + "current_steps": 2417, + "loss": 2.4457, + "learning_rate": 2.7543035993740216e-07, + "epoch": 3.669195751138088 + }, + { + "current_steps": 2418, + "loss": 2.5827, + "learning_rate": 2.7511737089201874e-07, + "epoch": 3.670713201820941 + }, + { + "current_steps": 2419, + "loss": 2.38, + "learning_rate": 2.7480438184663533e-07, + "epoch": 3.6722306525037935 + }, + { + "current_steps": 2420, + "loss": 2.5419, + "learning_rate": 2.7449139280125197e-07, + "epoch": 3.6737481031866466 + }, + { + "current_steps": 2421, + "loss": 2.3817, + "learning_rate": 2.7417840375586855e-07, + "epoch": 3.675265553869499 + }, + { + "current_steps": 2422, + "loss": 2.4779, + "learning_rate": 2.7386541471048514e-07, + "epoch": 3.676783004552352 + }, + { + "current_steps": 2423, + "loss": 2.3663, + "learning_rate": 2.735524256651017e-07, + "epoch": 3.6783004552352048 + }, + { + "current_steps": 2424, + "loss": 2.544, + "learning_rate": 2.732394366197183e-07, + "epoch": 3.679817905918058 + }, + { + "current_steps": 2425, + "loss": 2.5998, + "learning_rate": 2.7292644757433484e-07, + "epoch": 3.6813353566009104 + }, + { + "current_steps": 2426, + "loss": 2.6134, + "learning_rate": 2.7261345852895143e-07, + "epoch": 3.6828528072837634 + }, + { + "current_steps": 2427, + "loss": 2.8972, + "learning_rate": 2.7230046948356807e-07, + "epoch": 3.684370257966616 + }, + { + "current_steps": 2428, + "loss": 2.4784, + "learning_rate": 2.7198748043818466e-07, + "epoch": 3.685887708649469 + }, + { + "current_steps": 2429, + "loss": 2.6509, + "learning_rate": 2.7167449139280124e-07, + "epoch": 3.6874051593323216 + }, + { + "current_steps": 2430, + "loss": 2.7205, + "learning_rate": 2.7136150234741783e-07, + "epoch": 3.6889226100151746 + }, + { + "current_steps": 2431, + "loss": 2.4594, + "learning_rate": 2.710485133020344e-07, + "epoch": 3.690440060698027 + }, + { + "current_steps": 2432, + "loss": 2.6609, + "learning_rate": 2.7073552425665105e-07, + "epoch": 3.6919575113808802 + }, + { + "current_steps": 2433, + "loss": 2.7448, + "learning_rate": 2.704225352112676e-07, + "epoch": 3.693474962063733 + }, + { + "current_steps": 2434, + "loss": 2.1153, + "learning_rate": 2.7010954616588417e-07, + "epoch": 3.694992412746586 + }, + { + "current_steps": 2435, + "loss": 2.4642, + "learning_rate": 2.6979655712050076e-07, + "epoch": 3.6965098634294384 + }, + { + "current_steps": 2436, + "loss": 2.6774, + "learning_rate": 2.6948356807511734e-07, + "epoch": 3.6980273141122915 + }, + { + "current_steps": 2437, + "loss": 2.5016, + "learning_rate": 2.6917057902973393e-07, + "epoch": 3.699544764795144 + }, + { + "current_steps": 2438, + "loss": 2.3339, + "learning_rate": 2.688575899843505e-07, + "epoch": 3.701062215477997 + }, + { + "current_steps": 2439, + "loss": 2.6094, + "learning_rate": 2.6854460093896716e-07, + "epoch": 3.7025796661608497 + }, + { + "current_steps": 2440, + "loss": 2.3286, + "learning_rate": 2.6823161189358374e-07, + "epoch": 3.7040971168437027 + }, + { + "current_steps": 2441, + "loss": 2.5992, + "learning_rate": 2.6791862284820033e-07, + "epoch": 3.7056145675265553 + }, + { + "current_steps": 2442, + "loss": 2.6866, + "learning_rate": 2.6760563380281686e-07, + "epoch": 3.7071320182094083 + }, + { + "current_steps": 2443, + "loss": 2.4272, + "learning_rate": 2.6729264475743345e-07, + "epoch": 3.708649468892261 + }, + { + "current_steps": 2444, + "loss": 2.4857, + "learning_rate": 2.6697965571205003e-07, + "epoch": 3.710166919575114 + }, + { + "current_steps": 2445, + "loss": 2.4053, + "learning_rate": 2.6666666666666667e-07, + "epoch": 3.7116843702579665 + }, + { + "current_steps": 2446, + "loss": 2.3895, + "learning_rate": 2.6635367762128326e-07, + "epoch": 3.7132018209408195 + }, + { + "current_steps": 2447, + "loss": 2.5538, + "learning_rate": 2.6604068857589984e-07, + "epoch": 3.714719271623672 + }, + { + "current_steps": 2448, + "loss": 2.656, + "learning_rate": 2.6572769953051643e-07, + "epoch": 3.716236722306525 + }, + { + "current_steps": 2449, + "loss": 2.7155, + "learning_rate": 2.65414710485133e-07, + "epoch": 3.7177541729893777 + }, + { + "current_steps": 2450, + "loss": 2.6187, + "learning_rate": 2.6510172143974955e-07, + "epoch": 3.7192716236722307 + }, + { + "current_steps": 2451, + "loss": 2.5975, + "learning_rate": 2.647887323943662e-07, + "epoch": 3.7207890743550833 + }, + { + "current_steps": 2452, + "loss": 2.7849, + "learning_rate": 2.644757433489828e-07, + "epoch": 3.7223065250379364 + }, + { + "current_steps": 2453, + "loss": 2.5845, + "learning_rate": 2.6416275430359936e-07, + "epoch": 3.723823975720789 + }, + { + "current_steps": 2454, + "loss": 2.676, + "learning_rate": 2.6384976525821595e-07, + "epoch": 3.725341426403642 + }, + { + "current_steps": 2455, + "loss": 2.602, + "learning_rate": 2.6353677621283253e-07, + "epoch": 3.7268588770864945 + }, + { + "current_steps": 2456, + "loss": 2.3613, + "learning_rate": 2.632237871674491e-07, + "epoch": 3.7283763277693476 + }, + { + "current_steps": 2457, + "loss": 2.4326, + "learning_rate": 2.6291079812206576e-07, + "epoch": 3.7298937784522 + }, + { + "current_steps": 2458, + "loss": 2.6815, + "learning_rate": 2.6259780907668234e-07, + "epoch": 3.731411229135053 + }, + { + "current_steps": 2459, + "loss": 2.5125, + "learning_rate": 2.622848200312989e-07, + "epoch": 3.7329286798179058 + }, + { + "current_steps": 2460, + "loss": 2.724, + "learning_rate": 2.6197183098591546e-07, + "epoch": 3.734446130500759 + }, + { + "current_steps": 2461, + "loss": 2.3631, + "learning_rate": 2.6165884194053205e-07, + "epoch": 3.7359635811836114 + }, + { + "current_steps": 2462, + "loss": 2.8668, + "learning_rate": 2.6134585289514864e-07, + "epoch": 3.7374810318664644 + }, + { + "current_steps": 2463, + "loss": 2.6331, + "learning_rate": 2.610328638497653e-07, + "epoch": 3.738998482549317 + }, + { + "current_steps": 2464, + "loss": 2.4632, + "learning_rate": 2.6071987480438186e-07, + "epoch": 3.74051593323217 + }, + { + "current_steps": 2465, + "loss": 2.5879, + "learning_rate": 2.6040688575899845e-07, + "epoch": 3.7420333839150226 + }, + { + "current_steps": 2466, + "loss": 2.3877, + "learning_rate": 2.6009389671361503e-07, + "epoch": 3.7435508345978756 + }, + { + "current_steps": 2467, + "loss": 2.5071, + "learning_rate": 2.5978090766823157e-07, + "epoch": 3.745068285280728 + }, + { + "current_steps": 2468, + "loss": 2.7634, + "learning_rate": 2.5946791862284815e-07, + "epoch": 3.7465857359635812 + }, + { + "current_steps": 2469, + "loss": 2.5344, + "learning_rate": 2.5915492957746474e-07, + "epoch": 3.748103186646434 + }, + { + "current_steps": 2470, + "loss": 2.8301, + "learning_rate": 2.588419405320814e-07, + "epoch": 3.749620637329287 + }, + { + "current_steps": 2471, + "loss": 2.0656, + "learning_rate": 2.5852895148669796e-07, + "epoch": 3.75113808801214 + }, + { + "current_steps": 2472, + "loss": 1.8871, + "learning_rate": 2.5821596244131455e-07, + "epoch": 3.7526555386949925 + }, + { + "current_steps": 2473, + "loss": 2.6411, + "learning_rate": 2.5790297339593114e-07, + "epoch": 3.754172989377845 + }, + { + "current_steps": 2474, + "loss": 2.2802, + "learning_rate": 2.575899843505477e-07, + "epoch": 3.755690440060698 + }, + { + "current_steps": 2475, + "loss": 2.6379, + "learning_rate": 2.572769953051643e-07, + "epoch": 3.757207890743551 + }, + { + "current_steps": 2476, + "loss": 2.0686, + "learning_rate": 2.569640062597809e-07, + "epoch": 3.7587253414264037 + }, + { + "current_steps": 2477, + "loss": 2.5399, + "learning_rate": 2.566510172143975e-07, + "epoch": 3.7602427921092563 + }, + { + "current_steps": 2478, + "loss": 2.6711, + "learning_rate": 2.5633802816901407e-07, + "epoch": 3.7617602427921093 + }, + { + "current_steps": 2479, + "loss": 2.6185, + "learning_rate": 2.5602503912363065e-07, + "epoch": 3.7632776934749623 + }, + { + "current_steps": 2480, + "loss": 2.5684, + "learning_rate": 2.5571205007824724e-07, + "epoch": 3.764795144157815 + }, + { + "current_steps": 2481, + "loss": 2.5457, + "learning_rate": 2.553990610328638e-07, + "epoch": 3.7663125948406675 + }, + { + "current_steps": 2482, + "loss": 2.5574, + "learning_rate": 2.5508607198748046e-07, + "epoch": 3.7678300455235205 + }, + { + "current_steps": 2483, + "loss": 2.6162, + "learning_rate": 2.5477308294209705e-07, + "epoch": 3.7693474962063735 + }, + { + "current_steps": 2484, + "loss": 2.6698, + "learning_rate": 2.544600938967136e-07, + "epoch": 3.770864946889226 + }, + { + "current_steps": 2485, + "loss": 2.7672, + "learning_rate": 2.5414710485133017e-07, + "epoch": 3.7723823975720787 + }, + { + "current_steps": 2486, + "loss": 2.4441, + "learning_rate": 2.5383411580594676e-07, + "epoch": 3.7738998482549317 + }, + { + "current_steps": 2487, + "loss": 2.7116, + "learning_rate": 2.5352112676056334e-07, + "epoch": 3.7754172989377848 + }, + { + "current_steps": 2488, + "loss": 2.5354, + "learning_rate": 2.5320813771518e-07, + "epoch": 3.7769347496206374 + }, + { + "current_steps": 2489, + "loss": 2.2644, + "learning_rate": 2.5289514866979657e-07, + "epoch": 3.77845220030349 + }, + { + "current_steps": 2490, + "loss": 2.5542, + "learning_rate": 2.5258215962441315e-07, + "epoch": 3.779969650986343 + }, + { + "current_steps": 2491, + "loss": 2.4063, + "learning_rate": 2.5226917057902974e-07, + "epoch": 3.781487101669196 + }, + { + "current_steps": 2492, + "loss": 2.5262, + "learning_rate": 2.5195618153364627e-07, + "epoch": 3.7830045523520486 + }, + { + "current_steps": 2493, + "loss": 2.4061, + "learning_rate": 2.5164319248826286e-07, + "epoch": 3.784522003034901 + }, + { + "current_steps": 2494, + "loss": 2.5877, + "learning_rate": 2.513302034428795e-07, + "epoch": 3.786039453717754 + }, + { + "current_steps": 2495, + "loss": 2.6188, + "learning_rate": 2.510172143974961e-07, + "epoch": 3.787556904400607 + }, + { + "current_steps": 2496, + "loss": 2.4771, + "learning_rate": 2.5070422535211267e-07, + "epoch": 3.78907435508346 + }, + { + "current_steps": 2497, + "loss": 2.5375, + "learning_rate": 2.5039123630672926e-07, + "epoch": 3.7905918057663124 + }, + { + "current_steps": 2498, + "loss": 2.4187, + "learning_rate": 2.5007824726134584e-07, + "epoch": 3.7921092564491654 + }, + { + "current_steps": 2499, + "loss": 2.616, + "learning_rate": 2.4976525821596243e-07, + "epoch": 3.7936267071320184 + }, + { + "current_steps": 2500, + "loss": 2.7955, + "learning_rate": 2.49452269170579e-07, + "epoch": 3.795144157814871 + }, + { + "current_steps": 2501, + "loss": 2.5782, + "learning_rate": 2.491392801251956e-07, + "epoch": 3.7966616084977236 + }, + { + "current_steps": 2502, + "loss": 2.5143, + "learning_rate": 2.488262910798122e-07, + "epoch": 3.7981790591805766 + }, + { + "current_steps": 2503, + "loss": 2.5142, + "learning_rate": 2.4851330203442877e-07, + "epoch": 3.7996965098634297 + }, + { + "current_steps": 2504, + "loss": 2.5855, + "learning_rate": 2.4820031298904536e-07, + "epoch": 3.8012139605462822 + }, + { + "current_steps": 2505, + "loss": 2.4831, + "learning_rate": 2.4788732394366194e-07, + "epoch": 3.802731411229135 + }, + { + "current_steps": 2506, + "loss": 2.5165, + "learning_rate": 2.475743348982786e-07, + "epoch": 3.804248861911988 + }, + { + "current_steps": 2507, + "loss": 2.5582, + "learning_rate": 2.472613458528951e-07, + "epoch": 3.805766312594841 + }, + { + "current_steps": 2508, + "loss": 2.6604, + "learning_rate": 2.469483568075117e-07, + "epoch": 3.8072837632776935 + }, + { + "current_steps": 2509, + "loss": 2.6437, + "learning_rate": 2.466353677621283e-07, + "epoch": 3.808801213960546 + }, + { + "current_steps": 2510, + "loss": 2.7699, + "learning_rate": 2.4632237871674493e-07, + "epoch": 3.810318664643399 + }, + { + "current_steps": 2511, + "loss": 2.4122, + "learning_rate": 2.4600938967136146e-07, + "epoch": 3.811836115326252 + }, + { + "current_steps": 2512, + "loss": 2.5126, + "learning_rate": 2.4569640062597805e-07, + "epoch": 3.8133535660091047 + }, + { + "current_steps": 2513, + "loss": 2.4656, + "learning_rate": 2.453834115805947e-07, + "epoch": 3.8148710166919573 + }, + { + "current_steps": 2514, + "loss": 2.6191, + "learning_rate": 2.4507042253521127e-07, + "epoch": 3.8163884673748103 + }, + { + "current_steps": 2515, + "loss": 2.4861, + "learning_rate": 2.4475743348982786e-07, + "epoch": 3.8179059180576633 + }, + { + "current_steps": 2516, + "loss": 2.5461, + "learning_rate": 2.4444444444444445e-07, + "epoch": 3.819423368740516 + }, + { + "current_steps": 2517, + "loss": 2.5966, + "learning_rate": 2.4413145539906103e-07, + "epoch": 3.8209408194233685 + }, + { + "current_steps": 2518, + "loss": 2.4376, + "learning_rate": 2.438184663536776e-07, + "epoch": 3.8224582701062215 + }, + { + "current_steps": 2519, + "loss": 2.402, + "learning_rate": 2.435054773082942e-07, + "epoch": 3.8239757207890746 + }, + { + "current_steps": 2520, + "loss": 2.3213, + "learning_rate": 2.431924882629108e-07, + "epoch": 3.825493171471927 + }, + { + "current_steps": 2521, + "loss": 2.6835, + "learning_rate": 2.428794992175274e-07, + "epoch": 3.8270106221547797 + }, + { + "current_steps": 2522, + "loss": 2.5915, + "learning_rate": 2.4256651017214396e-07, + "epoch": 3.8285280728376327 + }, + { + "current_steps": 2523, + "loss": 2.6314, + "learning_rate": 2.4225352112676055e-07, + "epoch": 3.8300455235204858 + }, + { + "current_steps": 2524, + "loss": 2.7454, + "learning_rate": 2.4194053208137713e-07, + "epoch": 3.8315629742033384 + }, + { + "current_steps": 2525, + "loss": 2.6919, + "learning_rate": 2.416275430359937e-07, + "epoch": 3.833080424886191 + }, + { + "current_steps": 2526, + "loss": 2.1755, + "learning_rate": 2.413145539906103e-07, + "epoch": 3.834597875569044 + }, + { + "current_steps": 2527, + "loss": 2.6383, + "learning_rate": 2.410015649452269e-07, + "epoch": 3.836115326251897 + }, + { + "current_steps": 2528, + "loss": 2.5749, + "learning_rate": 2.406885758998435e-07, + "epoch": 3.8376327769347496 + }, + { + "current_steps": 2529, + "loss": 2.405, + "learning_rate": 2.4037558685446006e-07, + "epoch": 3.839150227617602 + }, + { + "current_steps": 2530, + "loss": 2.4686, + "learning_rate": 2.4006259780907665e-07, + "epoch": 3.840667678300455 + }, + { + "current_steps": 2531, + "loss": 2.3358, + "learning_rate": 2.397496087636933e-07, + "epoch": 3.842185128983308 + }, + { + "current_steps": 2532, + "loss": 2.6459, + "learning_rate": 2.394366197183098e-07, + "epoch": 3.843702579666161 + }, + { + "current_steps": 2533, + "loss": 2.525, + "learning_rate": 2.391236306729264e-07, + "epoch": 3.8452200303490134 + }, + { + "current_steps": 2534, + "loss": 2.4935, + "learning_rate": 2.3881064162754305e-07, + "epoch": 3.8467374810318664 + }, + { + "current_steps": 2535, + "loss": 2.669, + "learning_rate": 2.3849765258215963e-07, + "epoch": 3.8482549317147194 + }, + { + "current_steps": 2536, + "loss": 2.5296, + "learning_rate": 2.3818466353677622e-07, + "epoch": 3.849772382397572 + }, + { + "current_steps": 2537, + "loss": 2.5395, + "learning_rate": 2.3787167449139278e-07, + "epoch": 3.851289833080425 + }, + { + "current_steps": 2538, + "loss": 2.0518, + "learning_rate": 2.3755868544600937e-07, + "epoch": 3.8528072837632776 + }, + { + "current_steps": 2539, + "loss": 2.6513, + "learning_rate": 2.3724569640062598e-07, + "epoch": 3.8543247344461307 + }, + { + "current_steps": 2540, + "loss": 2.4723, + "learning_rate": 2.3693270735524256e-07, + "epoch": 3.8558421851289832 + }, + { + "current_steps": 2541, + "loss": 2.6909, + "learning_rate": 2.3661971830985912e-07, + "epoch": 3.8573596358118363 + }, + { + "current_steps": 2542, + "loss": 2.4051, + "learning_rate": 2.3630672926447574e-07, + "epoch": 3.858877086494689 + }, + { + "current_steps": 2543, + "loss": 2.6321, + "learning_rate": 2.3599374021909232e-07, + "epoch": 3.860394537177542 + }, + { + "current_steps": 2544, + "loss": 2.8618, + "learning_rate": 2.356807511737089e-07, + "epoch": 3.8619119878603945 + }, + { + "current_steps": 2545, + "loss": 2.6475, + "learning_rate": 2.353677621283255e-07, + "epoch": 3.8634294385432475 + }, + { + "current_steps": 2546, + "loss": 2.6111, + "learning_rate": 2.3505477308294208e-07, + "epoch": 3.8649468892261 + }, + { + "current_steps": 2547, + "loss": 2.3579, + "learning_rate": 2.3474178403755867e-07, + "epoch": 3.866464339908953 + }, + { + "current_steps": 2548, + "loss": 2.2596, + "learning_rate": 2.3442879499217528e-07, + "epoch": 3.8679817905918057 + }, + { + "current_steps": 2549, + "loss": 2.4871, + "learning_rate": 2.3411580594679184e-07, + "epoch": 3.8694992412746587 + }, + { + "current_steps": 2550, + "loss": 2.665, + "learning_rate": 2.3380281690140843e-07, + "epoch": 3.8710166919575113 + }, + { + "current_steps": 2551, + "loss": 2.6043, + "learning_rate": 2.3348982785602504e-07, + "epoch": 3.8725341426403643 + }, + { + "current_steps": 2552, + "loss": 2.5861, + "learning_rate": 2.3317683881064162e-07, + "epoch": 3.874051593323217 + }, + { + "current_steps": 2553, + "loss": 2.4674, + "learning_rate": 2.328638497652582e-07, + "epoch": 3.87556904400607 + }, + { + "current_steps": 2554, + "loss": 2.7033, + "learning_rate": 2.325508607198748e-07, + "epoch": 3.8770864946889225 + }, + { + "current_steps": 2555, + "loss": 2.2832, + "learning_rate": 2.3223787167449138e-07, + "epoch": 3.8786039453717756 + }, + { + "current_steps": 2556, + "loss": 2.5919, + "learning_rate": 2.3192488262910797e-07, + "epoch": 3.880121396054628 + }, + { + "current_steps": 2557, + "loss": 2.456, + "learning_rate": 2.3161189358372458e-07, + "epoch": 3.881638846737481 + }, + { + "current_steps": 2558, + "loss": 2.4966, + "learning_rate": 2.3129890453834114e-07, + "epoch": 3.8831562974203337 + }, + { + "current_steps": 2559, + "loss": 2.4098, + "learning_rate": 2.3098591549295773e-07, + "epoch": 3.8846737481031868 + }, + { + "current_steps": 2560, + "loss": 2.6691, + "learning_rate": 2.3067292644757434e-07, + "epoch": 3.8861911987860394 + }, + { + "current_steps": 2561, + "loss": 2.4332, + "learning_rate": 2.3035993740219093e-07, + "epoch": 3.8877086494688924 + }, + { + "current_steps": 2562, + "loss": 2.4793, + "learning_rate": 2.3004694835680749e-07, + "epoch": 3.889226100151745 + }, + { + "current_steps": 2563, + "loss": 2.4527, + "learning_rate": 2.297339593114241e-07, + "epoch": 3.890743550834598 + }, + { + "current_steps": 2564, + "loss": 2.4, + "learning_rate": 2.2942097026604068e-07, + "epoch": 3.8922610015174506 + }, + { + "current_steps": 2565, + "loss": 2.5852, + "learning_rate": 2.2910798122065727e-07, + "epoch": 3.8937784522003036 + }, + { + "current_steps": 2566, + "loss": 2.5429, + "learning_rate": 2.2879499217527383e-07, + "epoch": 3.895295902883156 + }, + { + "current_steps": 2567, + "loss": 2.5215, + "learning_rate": 2.2848200312989044e-07, + "epoch": 3.896813353566009 + }, + { + "current_steps": 2568, + "loss": 2.5775, + "learning_rate": 2.2816901408450703e-07, + "epoch": 3.898330804248862 + }, + { + "current_steps": 2569, + "loss": 2.5519, + "learning_rate": 2.2785602503912362e-07, + "epoch": 3.899848254931715 + }, + { + "current_steps": 2570, + "loss": 2.4159, + "learning_rate": 2.275430359937402e-07, + "epoch": 3.9013657056145674 + }, + { + "current_steps": 2571, + "loss": 2.4878, + "learning_rate": 2.272300469483568e-07, + "epoch": 3.9028831562974204 + }, + { + "current_steps": 2572, + "loss": 2.6295, + "learning_rate": 2.2691705790297337e-07, + "epoch": 3.904400606980273 + }, + { + "current_steps": 2573, + "loss": 2.5934, + "learning_rate": 2.2660406885758999e-07, + "epoch": 3.905918057663126 + }, + { + "current_steps": 2574, + "loss": 2.4794, + "learning_rate": 2.2629107981220657e-07, + "epoch": 3.9074355083459786 + }, + { + "current_steps": 2575, + "loss": 2.6804, + "learning_rate": 2.2597809076682313e-07, + "epoch": 3.9089529590288317 + }, + { + "current_steps": 2576, + "loss": 2.6575, + "learning_rate": 2.2566510172143974e-07, + "epoch": 3.9104704097116842 + }, + { + "current_steps": 2577, + "loss": 2.6857, + "learning_rate": 2.2535211267605633e-07, + "epoch": 3.9119878603945373 + }, + { + "current_steps": 2578, + "loss": 2.4386, + "learning_rate": 2.2503912363067292e-07, + "epoch": 3.91350531107739 + }, + { + "current_steps": 2579, + "loss": 2.4927, + "learning_rate": 2.247261345852895e-07, + "epoch": 3.915022761760243 + }, + { + "current_steps": 2580, + "loss": 2.5492, + "learning_rate": 2.244131455399061e-07, + "epoch": 3.9165402124430955 + }, + { + "current_steps": 2581, + "loss": 2.6366, + "learning_rate": 2.2410015649452267e-07, + "epoch": 3.9180576631259485 + }, + { + "current_steps": 2582, + "loss": 2.5442, + "learning_rate": 2.237871674491393e-07, + "epoch": 3.919575113808801 + }, + { + "current_steps": 2583, + "loss": 2.5192, + "learning_rate": 2.2347417840375585e-07, + "epoch": 3.921092564491654 + }, + { + "current_steps": 2584, + "loss": 2.6708, + "learning_rate": 2.2316118935837243e-07, + "epoch": 3.9226100151745067 + }, + { + "current_steps": 2585, + "loss": 2.6197, + "learning_rate": 2.2284820031298905e-07, + "epoch": 3.9241274658573597 + }, + { + "current_steps": 2586, + "loss": 2.5111, + "learning_rate": 2.2253521126760563e-07, + "epoch": 3.9256449165402123 + }, + { + "current_steps": 2587, + "loss": 2.4305, + "learning_rate": 2.222222222222222e-07, + "epoch": 3.9271623672230653 + }, + { + "current_steps": 2588, + "loss": 2.7398, + "learning_rate": 2.219092331768388e-07, + "epoch": 3.928679817905918 + }, + { + "current_steps": 2589, + "loss": 2.8469, + "learning_rate": 2.215962441314554e-07, + "epoch": 3.930197268588771 + }, + { + "current_steps": 2590, + "loss": 2.598, + "learning_rate": 2.2128325508607198e-07, + "epoch": 3.9317147192716235 + }, + { + "current_steps": 2591, + "loss": 2.6273, + "learning_rate": 2.2097026604068856e-07, + "epoch": 3.9332321699544766 + }, + { + "current_steps": 2592, + "loss": 2.6304, + "learning_rate": 2.2065727699530515e-07, + "epoch": 3.934749620637329 + }, + { + "current_steps": 2593, + "loss": 2.6067, + "learning_rate": 2.2034428794992173e-07, + "epoch": 3.936267071320182 + }, + { + "current_steps": 2594, + "loss": 2.5718, + "learning_rate": 2.2003129890453835e-07, + "epoch": 3.9377845220030347 + }, + { + "current_steps": 2595, + "loss": 2.1107, + "learning_rate": 2.1971830985915493e-07, + "epoch": 3.9393019726858878 + }, + { + "current_steps": 2596, + "loss": 2.5437, + "learning_rate": 2.194053208137715e-07, + "epoch": 3.9408194233687404 + }, + { + "current_steps": 2597, + "loss": 2.6827, + "learning_rate": 2.190923317683881e-07, + "epoch": 3.9423368740515934 + }, + { + "current_steps": 2598, + "loss": 2.5252, + "learning_rate": 2.187793427230047e-07, + "epoch": 3.943854324734446 + }, + { + "current_steps": 2599, + "loss": 2.483, + "learning_rate": 2.1846635367762128e-07, + "epoch": 3.945371775417299 + }, + { + "current_steps": 2600, + "loss": 2.4276, + "learning_rate": 2.1815336463223786e-07, + "epoch": 3.9468892261001516 + }, + { + "current_steps": 2601, + "loss": 2.4004, + "learning_rate": 2.1784037558685445e-07, + "epoch": 3.9484066767830046 + }, + { + "current_steps": 2602, + "loss": 2.0506, + "learning_rate": 2.1752738654147104e-07, + "epoch": 3.949924127465857 + }, + { + "current_steps": 2603, + "loss": 2.3809, + "learning_rate": 2.1721439749608765e-07, + "epoch": 3.95144157814871 + }, + { + "current_steps": 2604, + "loss": 2.7575, + "learning_rate": 2.169014084507042e-07, + "epoch": 3.952959028831563 + }, + { + "current_steps": 2605, + "loss": 2.6223, + "learning_rate": 2.165884194053208e-07, + "epoch": 3.954476479514416 + }, + { + "current_steps": 2606, + "loss": 2.9437, + "learning_rate": 2.162754303599374e-07, + "epoch": 3.955993930197269 + }, + { + "current_steps": 2607, + "loss": 2.4483, + "learning_rate": 2.15962441314554e-07, + "epoch": 3.9575113808801214 + }, + { + "current_steps": 2608, + "loss": 2.554, + "learning_rate": 2.1564945226917055e-07, + "epoch": 3.959028831562974 + }, + { + "current_steps": 2609, + "loss": 2.5112, + "learning_rate": 2.1533646322378714e-07, + "epoch": 3.960546282245827 + }, + { + "current_steps": 2610, + "loss": 2.5837, + "learning_rate": 2.1502347417840375e-07, + "epoch": 3.96206373292868 + }, + { + "current_steps": 2611, + "loss": 2.706, + "learning_rate": 2.1471048513302034e-07, + "epoch": 3.9635811836115327 + }, + { + "current_steps": 2612, + "loss": 2.4043, + "learning_rate": 2.1439749608763692e-07, + "epoch": 3.9650986342943852 + }, + { + "current_steps": 2613, + "loss": 2.0961, + "learning_rate": 2.140845070422535e-07, + "epoch": 3.9666160849772383 + }, + { + "current_steps": 2614, + "loss": 2.5522, + "learning_rate": 2.137715179968701e-07, + "epoch": 3.9681335356600913 + }, + { + "current_steps": 2615, + "loss": 2.6613, + "learning_rate": 2.1345852895148668e-07, + "epoch": 3.969650986342944 + }, + { + "current_steps": 2616, + "loss": 2.5316, + "learning_rate": 2.131455399061033e-07, + "epoch": 3.9711684370257965 + }, + { + "current_steps": 2617, + "loss": 2.5216, + "learning_rate": 2.1283255086071985e-07, + "epoch": 3.9726858877086495 + }, + { + "current_steps": 2618, + "loss": 2.2802, + "learning_rate": 2.1251956181533644e-07, + "epoch": 3.9742033383915025 + }, + { + "current_steps": 2619, + "loss": 2.514, + "learning_rate": 2.1220657276995305e-07, + "epoch": 3.975720789074355 + }, + { + "current_steps": 2620, + "loss": 2.7354, + "learning_rate": 2.1189358372456964e-07, + "epoch": 3.9772382397572077 + }, + { + "current_steps": 2621, + "loss": 2.6914, + "learning_rate": 2.115805946791862e-07, + "epoch": 3.9787556904400607 + }, + { + "current_steps": 2622, + "loss": 2.4145, + "learning_rate": 2.112676056338028e-07, + "epoch": 3.9802731411229137 + }, + { + "current_steps": 2623, + "loss": 2.5444, + "learning_rate": 2.109546165884194e-07, + "epoch": 3.9817905918057663 + }, + { + "current_steps": 2624, + "loss": 2.5293, + "learning_rate": 2.1064162754303598e-07, + "epoch": 3.983308042488619 + }, + { + "current_steps": 2625, + "loss": 2.5904, + "learning_rate": 2.1032863849765257e-07, + "epoch": 3.984825493171472 + }, + { + "current_steps": 2626, + "loss": 2.3156, + "learning_rate": 2.1001564945226916e-07, + "epoch": 3.986342943854325 + }, + { + "current_steps": 2627, + "loss": 2.391, + "learning_rate": 2.0970266040688574e-07, + "epoch": 3.9878603945371776 + }, + { + "current_steps": 2628, + "loss": 2.564, + "learning_rate": 2.0938967136150235e-07, + "epoch": 3.98937784522003 + }, + { + "current_steps": 2629, + "loss": 2.4928, + "learning_rate": 2.0907668231611891e-07, + "epoch": 3.990895295902883 + }, + { + "current_steps": 2630, + "loss": 2.4757, + "learning_rate": 2.087636932707355e-07, + "epoch": 3.992412746585736 + }, + { + "current_steps": 2631, + "loss": 2.6962, + "learning_rate": 2.084507042253521e-07, + "epoch": 3.9939301972685888 + }, + { + "current_steps": 2632, + "loss": 2.303, + "learning_rate": 2.081377151799687e-07, + "epoch": 3.9954476479514414 + }, + { + "current_steps": 2633, + "loss": 2.46, + "learning_rate": 2.0782472613458529e-07, + "epoch": 3.9969650986342944 + }, + { + "current_steps": 2634, + "loss": 2.7041, + "learning_rate": 2.0751173708920187e-07, + "epoch": 3.9984825493171474 + }, + { + "current_steps": 2635, + "loss": 2.3639, + "learning_rate": 2.0719874804381846e-07, + "epoch": 4.0 + }, + { + "current_steps": 2636, + "loss": 2.5526, + "learning_rate": 2.0688575899843504e-07, + "epoch": 4.001517450682853 + }, + { + "current_steps": 2637, + "loss": 2.6699, + "learning_rate": 2.0657276995305166e-07, + "epoch": 4.003034901365706 + }, + { + "current_steps": 2638, + "loss": 2.6216, + "learning_rate": 2.0625978090766822e-07, + "epoch": 4.004552352048559 + }, + { + "current_steps": 2639, + "loss": 2.3721, + "learning_rate": 2.059467918622848e-07, + "epoch": 4.006069802731411 + }, + { + "current_steps": 2640, + "loss": 2.5439, + "learning_rate": 2.0563380281690141e-07, + "epoch": 4.007587253414264 + }, + { + "current_steps": 2641, + "loss": 2.7, + "learning_rate": 2.05320813771518e-07, + "epoch": 4.009104704097117 + }, + { + "current_steps": 2642, + "loss": 2.4362, + "learning_rate": 2.0500782472613456e-07, + "epoch": 4.01062215477997 + }, + { + "current_steps": 2643, + "loss": 2.4331, + "learning_rate": 2.0469483568075117e-07, + "epoch": 4.0121396054628224 + }, + { + "current_steps": 2644, + "loss": 2.5038, + "learning_rate": 2.0438184663536776e-07, + "epoch": 4.013657056145675 + }, + { + "current_steps": 2645, + "loss": 2.3669, + "learning_rate": 2.0406885758998434e-07, + "epoch": 4.0151745068285285 + }, + { + "current_steps": 2646, + "loss": 2.4022, + "learning_rate": 2.037558685446009e-07, + "epoch": 4.016691957511381 + }, + { + "current_steps": 2647, + "loss": 2.4912, + "learning_rate": 2.0344287949921752e-07, + "epoch": 4.018209408194234 + }, + { + "current_steps": 2648, + "loss": 2.8918, + "learning_rate": 2.031298904538341e-07, + "epoch": 4.019726858877086 + }, + { + "current_steps": 2649, + "loss": 2.4316, + "learning_rate": 2.028169014084507e-07, + "epoch": 4.02124430955994 + }, + { + "current_steps": 2650, + "loss": 2.5665, + "learning_rate": 2.0250391236306728e-07, + "epoch": 4.022761760242792 + }, + { + "current_steps": 2651, + "loss": 2.3653, + "learning_rate": 2.0219092331768386e-07, + "epoch": 4.024279210925645 + }, + { + "current_steps": 2652, + "loss": 2.5183, + "learning_rate": 2.0187793427230045e-07, + "epoch": 4.0257966616084975 + }, + { + "current_steps": 2653, + "loss": 2.7189, + "learning_rate": 2.0156494522691706e-07, + "epoch": 4.027314112291351 + }, + { + "current_steps": 2654, + "loss": 2.0341, + "learning_rate": 2.0125195618153365e-07, + "epoch": 4.0288315629742035 + }, + { + "current_steps": 2655, + "loss": 2.6299, + "learning_rate": 2.009389671361502e-07, + "epoch": 4.030349013657056 + }, + { + "current_steps": 2656, + "loss": 2.4699, + "learning_rate": 2.0062597809076682e-07, + "epoch": 4.031866464339909 + }, + { + "current_steps": 2657, + "loss": 2.5054, + "learning_rate": 2.003129890453834e-07, + "epoch": 4.033383915022762 + }, + { + "current_steps": 2658, + "loss": 2.6054, + "learning_rate": 2e-07, + "epoch": 4.034901365705615 + }, + { + "current_steps": 2659, + "loss": 2.5621, + "learning_rate": 1.9968701095461658e-07, + "epoch": 4.036418816388467 + }, + { + "current_steps": 2660, + "loss": 2.0969, + "learning_rate": 1.9937402190923316e-07, + "epoch": 4.03793626707132 + }, + { + "current_steps": 2661, + "loss": 2.5758, + "learning_rate": 1.9906103286384975e-07, + "epoch": 4.039453717754173 + }, + { + "current_steps": 2662, + "loss": 2.4472, + "learning_rate": 1.9874804381846636e-07, + "epoch": 4.040971168437026 + }, + { + "current_steps": 2663, + "loss": 2.5102, + "learning_rate": 1.9843505477308292e-07, + "epoch": 4.042488619119879 + }, + { + "current_steps": 2664, + "loss": 2.4964, + "learning_rate": 1.981220657276995e-07, + "epoch": 4.044006069802731 + }, + { + "current_steps": 2665, + "loss": 2.4539, + "learning_rate": 1.9780907668231612e-07, + "epoch": 4.045523520485585 + }, + { + "current_steps": 2666, + "loss": 2.4877, + "learning_rate": 1.974960876369327e-07, + "epoch": 4.047040971168437 + }, + { + "current_steps": 2667, + "loss": 2.5811, + "learning_rate": 1.9718309859154927e-07, + "epoch": 4.04855842185129 + }, + { + "current_steps": 2668, + "loss": 2.5617, + "learning_rate": 1.9687010954616588e-07, + "epoch": 4.050075872534142 + }, + { + "current_steps": 2669, + "loss": 2.5036, + "learning_rate": 1.9655712050078246e-07, + "epoch": 4.051593323216996 + }, + { + "current_steps": 2670, + "loss": 2.527, + "learning_rate": 1.9624413145539905e-07, + "epoch": 4.053110773899848 + }, + { + "current_steps": 2671, + "loss": 2.4491, + "learning_rate": 1.9593114241001566e-07, + "epoch": 4.054628224582701 + }, + { + "current_steps": 2672, + "loss": 2.5864, + "learning_rate": 1.9561815336463222e-07, + "epoch": 4.056145675265554 + }, + { + "current_steps": 2673, + "loss": 2.6381, + "learning_rate": 1.953051643192488e-07, + "epoch": 4.057663125948407 + }, + { + "current_steps": 2674, + "loss": 2.5974, + "learning_rate": 1.9499217527386542e-07, + "epoch": 4.05918057663126 + }, + { + "current_steps": 2675, + "loss": 2.5535, + "learning_rate": 1.94679186228482e-07, + "epoch": 4.060698027314112 + }, + { + "current_steps": 2676, + "loss": 2.1037, + "learning_rate": 1.9436619718309857e-07, + "epoch": 4.062215477996965 + }, + { + "current_steps": 2677, + "loss": 2.3863, + "learning_rate": 1.9405320813771518e-07, + "epoch": 4.063732928679818 + }, + { + "current_steps": 2678, + "loss": 2.5807, + "learning_rate": 1.9374021909233177e-07, + "epoch": 4.065250379362671 + }, + { + "current_steps": 2679, + "loss": 2.5779, + "learning_rate": 1.9342723004694835e-07, + "epoch": 4.0667678300455234 + }, + { + "current_steps": 2680, + "loss": 2.5659, + "learning_rate": 1.9311424100156494e-07, + "epoch": 4.068285280728376 + }, + { + "current_steps": 2681, + "loss": 2.4681, + "learning_rate": 1.9280125195618152e-07, + "epoch": 4.0698027314112295 + }, + { + "current_steps": 2682, + "loss": 2.4212, + "learning_rate": 1.924882629107981e-07, + "epoch": 4.071320182094082 + }, + { + "current_steps": 2683, + "loss": 2.4809, + "learning_rate": 1.9217527386541472e-07, + "epoch": 4.072837632776935 + }, + { + "current_steps": 2684, + "loss": 2.6184, + "learning_rate": 1.9186228482003128e-07, + "epoch": 4.074355083459787 + }, + { + "current_steps": 2685, + "loss": 2.5157, + "learning_rate": 1.9154929577464787e-07, + "epoch": 4.075872534142641 + }, + { + "current_steps": 2686, + "loss": 2.7893, + "learning_rate": 1.9123630672926446e-07, + "epoch": 4.077389984825493 + }, + { + "current_steps": 2687, + "loss": 2.7509, + "learning_rate": 1.9092331768388107e-07, + "epoch": 4.078907435508346 + }, + { + "current_steps": 2688, + "loss": 2.4836, + "learning_rate": 1.9061032863849763e-07, + "epoch": 4.0804248861911985 + }, + { + "current_steps": 2689, + "loss": 2.3668, + "learning_rate": 1.9029733959311421e-07, + "epoch": 4.081942336874052 + }, + { + "current_steps": 2690, + "loss": 2.6041, + "learning_rate": 1.8998435054773083e-07, + "epoch": 4.0834597875569045 + }, + { + "current_steps": 2691, + "loss": 2.1119, + "learning_rate": 1.896713615023474e-07, + "epoch": 4.084977238239757 + }, + { + "current_steps": 2692, + "loss": 2.5061, + "learning_rate": 1.89358372456964e-07, + "epoch": 4.08649468892261 + }, + { + "current_steps": 2693, + "loss": 2.727, + "learning_rate": 1.8904538341158058e-07, + "epoch": 4.088012139605463 + }, + { + "current_steps": 2694, + "loss": 2.4711, + "learning_rate": 1.8873239436619717e-07, + "epoch": 4.089529590288316 + }, + { + "current_steps": 2695, + "loss": 2.4025, + "learning_rate": 1.8841940532081376e-07, + "epoch": 4.091047040971168 + }, + { + "current_steps": 2696, + "loss": 2.5543, + "learning_rate": 1.8810641627543037e-07, + "epoch": 4.092564491654021 + }, + { + "current_steps": 2697, + "loss": 2.819, + "learning_rate": 1.8779342723004693e-07, + "epoch": 4.094081942336874 + }, + { + "current_steps": 2698, + "loss": 2.3991, + "learning_rate": 1.8748043818466351e-07, + "epoch": 4.095599393019727 + }, + { + "current_steps": 2699, + "loss": 2.4762, + "learning_rate": 1.8716744913928013e-07, + "epoch": 4.09711684370258 + }, + { + "current_steps": 2700, + "loss": 2.4234, + "learning_rate": 1.8685446009389671e-07, + "epoch": 4.098634294385432 + }, + { + "current_steps": 2701, + "loss": 1.9719, + "learning_rate": 1.8654147104851327e-07, + "epoch": 4.100151745068286 + }, + { + "current_steps": 2702, + "loss": 2.3414, + "learning_rate": 1.8622848200312989e-07, + "epoch": 4.101669195751138 + }, + { + "current_steps": 2703, + "loss": 2.5245, + "learning_rate": 1.8591549295774647e-07, + "epoch": 4.103186646433991 + }, + { + "current_steps": 2704, + "loss": 2.5474, + "learning_rate": 1.8560250391236306e-07, + "epoch": 4.104704097116843 + }, + { + "current_steps": 2705, + "loss": 2.6604, + "learning_rate": 1.8528951486697964e-07, + "epoch": 4.106221547799697 + }, + { + "current_steps": 2706, + "loss": 2.3538, + "learning_rate": 1.8497652582159623e-07, + "epoch": 4.107738998482549 + }, + { + "current_steps": 2707, + "loss": 2.6253, + "learning_rate": 1.8466353677621282e-07, + "epoch": 4.109256449165402 + }, + { + "current_steps": 2708, + "loss": 2.7755, + "learning_rate": 1.8435054773082943e-07, + "epoch": 4.110773899848255 + }, + { + "current_steps": 2709, + "loss": 2.4265, + "learning_rate": 1.8403755868544602e-07, + "epoch": 4.112291350531108 + }, + { + "current_steps": 2710, + "loss": 2.4284, + "learning_rate": 1.8372456964006257e-07, + "epoch": 4.113808801213961 + }, + { + "current_steps": 2711, + "loss": 2.6268, + "learning_rate": 1.834115805946792e-07, + "epoch": 4.115326251896813 + }, + { + "current_steps": 2712, + "loss": 2.4694, + "learning_rate": 1.8309859154929577e-07, + "epoch": 4.116843702579666 + }, + { + "current_steps": 2713, + "loss": 2.4634, + "learning_rate": 1.8278560250391236e-07, + "epoch": 4.118361153262519 + }, + { + "current_steps": 2714, + "loss": 2.5561, + "learning_rate": 1.8247261345852895e-07, + "epoch": 4.119878603945372 + }, + { + "current_steps": 2715, + "loss": 2.5169, + "learning_rate": 1.8215962441314553e-07, + "epoch": 4.1213960546282244 + }, + { + "current_steps": 2716, + "loss": 2.5826, + "learning_rate": 1.8184663536776212e-07, + "epoch": 4.122913505311077 + }, + { + "current_steps": 2717, + "loss": 2.4084, + "learning_rate": 1.8153364632237873e-07, + "epoch": 4.1244309559939305 + }, + { + "current_steps": 2718, + "loss": 2.5331, + "learning_rate": 1.812206572769953e-07, + "epoch": 4.125948406676783 + }, + { + "current_steps": 2719, + "loss": 2.5407, + "learning_rate": 1.8090766823161188e-07, + "epoch": 4.127465857359636 + }, + { + "current_steps": 2720, + "loss": 2.4335, + "learning_rate": 1.805946791862285e-07, + "epoch": 4.128983308042488 + }, + { + "current_steps": 2721, + "loss": 2.3438, + "learning_rate": 1.8028169014084507e-07, + "epoch": 4.130500758725342 + }, + { + "current_steps": 2722, + "loss": 2.4962, + "learning_rate": 1.7996870109546163e-07, + "epoch": 4.132018209408194 + }, + { + "current_steps": 2723, + "loss": 2.0195, + "learning_rate": 1.7965571205007825e-07, + "epoch": 4.133535660091047 + }, + { + "current_steps": 2724, + "loss": 2.6725, + "learning_rate": 1.7934272300469483e-07, + "epoch": 4.1350531107738995 + }, + { + "current_steps": 2725, + "loss": 2.4998, + "learning_rate": 1.7902973395931142e-07, + "epoch": 4.136570561456753 + }, + { + "current_steps": 2726, + "loss": 2.4381, + "learning_rate": 1.7871674491392798e-07, + "epoch": 4.1380880121396055 + }, + { + "current_steps": 2727, + "loss": 2.672, + "learning_rate": 1.784037558685446e-07, + "epoch": 4.139605462822458 + }, + { + "current_steps": 2728, + "loss": 2.453, + "learning_rate": 1.7809076682316118e-07, + "epoch": 4.141122913505311 + }, + { + "current_steps": 2729, + "loss": 2.8178, + "learning_rate": 1.7777777777777776e-07, + "epoch": 4.142640364188164 + }, + { + "current_steps": 2730, + "loss": 2.6648, + "learning_rate": 1.7746478873239438e-07, + "epoch": 4.144157814871017 + }, + { + "current_steps": 2731, + "loss": 2.6018, + "learning_rate": 1.7715179968701094e-07, + "epoch": 4.145675265553869 + }, + { + "current_steps": 2732, + "loss": 2.5898, + "learning_rate": 1.7683881064162752e-07, + "epoch": 4.147192716236722 + }, + { + "current_steps": 2733, + "loss": 2.518, + "learning_rate": 1.7652582159624413e-07, + "epoch": 4.148710166919575 + }, + { + "current_steps": 2734, + "loss": 2.5222, + "learning_rate": 1.7621283255086072e-07, + "epoch": 4.150227617602428 + }, + { + "current_steps": 2735, + "loss": 2.5868, + "learning_rate": 1.7589984350547728e-07, + "epoch": 4.151745068285281 + }, + { + "current_steps": 2736, + "loss": 2.2374, + "learning_rate": 1.755868544600939e-07, + "epoch": 4.153262518968133 + }, + { + "current_steps": 2737, + "loss": 2.5455, + "learning_rate": 1.7527386541471048e-07, + "epoch": 4.154779969650987 + }, + { + "current_steps": 2738, + "loss": 2.0065, + "learning_rate": 1.7496087636932707e-07, + "epoch": 4.156297420333839 + }, + { + "current_steps": 2739, + "loss": 2.6102, + "learning_rate": 1.7464788732394365e-07, + "epoch": 4.157814871016692 + }, + { + "current_steps": 2740, + "loss": 2.5838, + "learning_rate": 1.7433489827856024e-07, + "epoch": 4.159332321699544 + }, + { + "current_steps": 2741, + "loss": 2.1926, + "learning_rate": 1.7402190923317682e-07, + "epoch": 4.160849772382398 + }, + { + "current_steps": 2742, + "loss": 2.449, + "learning_rate": 1.7370892018779344e-07, + "epoch": 4.16236722306525 + }, + { + "current_steps": 2743, + "loss": 2.4964, + "learning_rate": 1.7339593114241e-07, + "epoch": 4.163884673748103 + }, + { + "current_steps": 2744, + "loss": 2.3993, + "learning_rate": 1.7308294209702658e-07, + "epoch": 4.165402124430956 + }, + { + "current_steps": 2745, + "loss": 2.6532, + "learning_rate": 1.727699530516432e-07, + "epoch": 4.166919575113809 + }, + { + "current_steps": 2746, + "loss": 2.466, + "learning_rate": 1.7245696400625978e-07, + "epoch": 4.168437025796662 + }, + { + "current_steps": 2747, + "loss": 2.4694, + "learning_rate": 1.7214397496087634e-07, + "epoch": 4.169954476479514 + }, + { + "current_steps": 2748, + "loss": 2.5563, + "learning_rate": 1.7183098591549295e-07, + "epoch": 4.171471927162367 + }, + { + "current_steps": 2749, + "loss": 2.588, + "learning_rate": 1.7151799687010954e-07, + "epoch": 4.17298937784522 + }, + { + "current_steps": 2750, + "loss": 2.4647, + "learning_rate": 1.7120500782472613e-07, + "epoch": 4.174506828528073 + }, + { + "current_steps": 2751, + "loss": 2.4342, + "learning_rate": 1.7089201877934274e-07, + "epoch": 4.1760242792109254 + }, + { + "current_steps": 2752, + "loss": 2.5521, + "learning_rate": 1.705790297339593e-07, + "epoch": 4.177541729893778 + }, + { + "current_steps": 2753, + "loss": 2.5207, + "learning_rate": 1.7026604068857588e-07, + "epoch": 4.1790591805766315 + }, + { + "current_steps": 2754, + "loss": 2.6649, + "learning_rate": 1.699530516431925e-07, + "epoch": 4.180576631259484 + }, + { + "current_steps": 2755, + "loss": 2.149, + "learning_rate": 1.6964006259780908e-07, + "epoch": 4.182094081942337 + }, + { + "current_steps": 2756, + "loss": 2.4312, + "learning_rate": 1.6932707355242564e-07, + "epoch": 4.183611532625189 + }, + { + "current_steps": 2757, + "loss": 2.5259, + "learning_rate": 1.6901408450704225e-07, + "epoch": 4.185128983308043 + }, + { + "current_steps": 2758, + "loss": 2.5495, + "learning_rate": 1.6870109546165884e-07, + "epoch": 4.186646433990895 + }, + { + "current_steps": 2759, + "loss": 2.3394, + "learning_rate": 1.6838810641627543e-07, + "epoch": 4.188163884673748 + }, + { + "current_steps": 2760, + "loss": 2.539, + "learning_rate": 1.68075117370892e-07, + "epoch": 4.189681335356601 + }, + { + "current_steps": 2761, + "loss": 2.4563, + "learning_rate": 1.677621283255086e-07, + "epoch": 4.191198786039454 + }, + { + "current_steps": 2762, + "loss": 2.622, + "learning_rate": 1.6744913928012519e-07, + "epoch": 4.1927162367223065 + }, + { + "current_steps": 2763, + "loss": 2.4814, + "learning_rate": 1.671361502347418e-07, + "epoch": 4.194233687405159 + }, + { + "current_steps": 2764, + "loss": 2.569, + "learning_rate": 1.6682316118935836e-07, + "epoch": 4.195751138088012 + }, + { + "current_steps": 2765, + "loss": 2.4958, + "learning_rate": 1.6651017214397494e-07, + "epoch": 4.197268588770865 + }, + { + "current_steps": 2766, + "loss": 2.4074, + "learning_rate": 1.6619718309859153e-07, + "epoch": 4.198786039453718 + }, + { + "current_steps": 2767, + "loss": 2.4891, + "learning_rate": 1.6588419405320814e-07, + "epoch": 4.20030349013657 + }, + { + "current_steps": 2768, + "loss": 2.5409, + "learning_rate": 1.6557120500782473e-07, + "epoch": 4.201820940819424 + }, + { + "current_steps": 2769, + "loss": 2.6354, + "learning_rate": 1.652582159624413e-07, + "epoch": 4.203338391502276 + }, + { + "current_steps": 2770, + "loss": 2.5206, + "learning_rate": 1.649452269170579e-07, + "epoch": 4.204855842185129 + }, + { + "current_steps": 2771, + "loss": 2.457, + "learning_rate": 1.6463223787167449e-07, + "epoch": 4.206373292867982 + }, + { + "current_steps": 2772, + "loss": 2.5721, + "learning_rate": 1.6431924882629107e-07, + "epoch": 4.207890743550834 + }, + { + "current_steps": 2773, + "loss": 2.5236, + "learning_rate": 1.6400625978090766e-07, + "epoch": 4.209408194233688 + }, + { + "current_steps": 2774, + "loss": 2.5146, + "learning_rate": 1.6369327073552424e-07, + "epoch": 4.21092564491654 + }, + { + "current_steps": 2775, + "loss": 2.4603, + "learning_rate": 1.6338028169014083e-07, + "epoch": 4.212443095599393 + }, + { + "current_steps": 2776, + "loss": 2.6269, + "learning_rate": 1.6306729264475744e-07, + "epoch": 4.213960546282246 + }, + { + "current_steps": 2777, + "loss": 2.5269, + "learning_rate": 1.62754303599374e-07, + "epoch": 4.215477996965099 + }, + { + "current_steps": 2778, + "loss": 2.6818, + "learning_rate": 1.624413145539906e-07, + "epoch": 4.216995447647951 + }, + { + "current_steps": 2779, + "loss": 2.5155, + "learning_rate": 1.621283255086072e-07, + "epoch": 4.218512898330804 + }, + { + "current_steps": 2780, + "loss": 2.5036, + "learning_rate": 1.618153364632238e-07, + "epoch": 4.2200303490136575 + }, + { + "current_steps": 2781, + "loss": 2.6026, + "learning_rate": 1.6150234741784035e-07, + "epoch": 4.22154779969651 + }, + { + "current_steps": 2782, + "loss": 2.4704, + "learning_rate": 1.6118935837245696e-07, + "epoch": 4.223065250379363 + }, + { + "current_steps": 2783, + "loss": 2.4749, + "learning_rate": 1.6087636932707355e-07, + "epoch": 4.224582701062215 + }, + { + "current_steps": 2784, + "loss": 2.5457, + "learning_rate": 1.6056338028169013e-07, + "epoch": 4.226100151745069 + }, + { + "current_steps": 2785, + "loss": 2.5584, + "learning_rate": 1.6025039123630672e-07, + "epoch": 4.227617602427921 + }, + { + "current_steps": 2786, + "loss": 2.4755, + "learning_rate": 1.599374021909233e-07, + "epoch": 4.229135053110774 + }, + { + "current_steps": 2787, + "loss": 2.5375, + "learning_rate": 1.596244131455399e-07, + "epoch": 4.2306525037936265 + }, + { + "current_steps": 2788, + "loss": 2.4748, + "learning_rate": 1.593114241001565e-07, + "epoch": 4.23216995447648 + }, + { + "current_steps": 2789, + "loss": 2.5736, + "learning_rate": 1.589984350547731e-07, + "epoch": 4.2336874051593325 + }, + { + "current_steps": 2790, + "loss": 2.6935, + "learning_rate": 1.5868544600938965e-07, + "epoch": 4.235204855842185 + }, + { + "current_steps": 2791, + "loss": 2.7121, + "learning_rate": 1.5837245696400626e-07, + "epoch": 4.236722306525038 + }, + { + "current_steps": 2792, + "loss": 2.5392, + "learning_rate": 1.5805946791862285e-07, + "epoch": 4.238239757207891 + }, + { + "current_steps": 2793, + "loss": 2.457, + "learning_rate": 1.5774647887323943e-07, + "epoch": 4.239757207890744 + }, + { + "current_steps": 2794, + "loss": 2.4674, + "learning_rate": 1.5743348982785602e-07, + "epoch": 4.241274658573596 + }, + { + "current_steps": 2795, + "loss": 2.5756, + "learning_rate": 1.571205007824726e-07, + "epoch": 4.242792109256449 + }, + { + "current_steps": 2796, + "loss": 2.653, + "learning_rate": 1.568075117370892e-07, + "epoch": 4.244309559939302 + }, + { + "current_steps": 2797, + "loss": 2.549, + "learning_rate": 1.564945226917058e-07, + "epoch": 4.245827010622155 + }, + { + "current_steps": 2798, + "loss": 2.6379, + "learning_rate": 1.5618153364632236e-07, + "epoch": 4.2473444613050075 + }, + { + "current_steps": 2799, + "loss": 2.1145, + "learning_rate": 1.5586854460093895e-07, + "epoch": 4.24886191198786 + }, + { + "current_steps": 2800, + "loss": 2.4131, + "learning_rate": 1.5555555555555556e-07, + "epoch": 4.250379362670714 + }, + { + "current_steps": 2801, + "loss": 2.6039, + "learning_rate": 1.5524256651017215e-07, + "epoch": 4.251896813353566 + }, + { + "current_steps": 2802, + "loss": 2.4294, + "learning_rate": 1.549295774647887e-07, + "epoch": 4.253414264036419 + }, + { + "current_steps": 2803, + "loss": 2.661, + "learning_rate": 1.546165884194053e-07, + "epoch": 4.254931714719271 + }, + { + "current_steps": 2804, + "loss": 2.5375, + "learning_rate": 1.543035993740219e-07, + "epoch": 4.256449165402125 + }, + { + "current_steps": 2805, + "loss": 2.6201, + "learning_rate": 1.539906103286385e-07, + "epoch": 4.257966616084977 + }, + { + "current_steps": 2806, + "loss": 2.558, + "learning_rate": 1.5367762128325505e-07, + "epoch": 4.25948406676783 + }, + { + "current_steps": 2807, + "loss": 2.4028, + "learning_rate": 1.5336463223787167e-07, + "epoch": 4.261001517450683 + }, + { + "current_steps": 2808, + "loss": 2.8459, + "learning_rate": 1.5305164319248825e-07, + "epoch": 4.262518968133536 + }, + { + "current_steps": 2809, + "loss": 2.0741, + "learning_rate": 1.5273865414710484e-07, + "epoch": 4.264036418816389 + }, + { + "current_steps": 2810, + "loss": 2.7114, + "learning_rate": 1.5242566510172145e-07, + "epoch": 4.265553869499241 + }, + { + "current_steps": 2811, + "loss": 2.6018, + "learning_rate": 1.52112676056338e-07, + "epoch": 4.267071320182094 + }, + { + "current_steps": 2812, + "loss": 2.2776, + "learning_rate": 1.517996870109546e-07, + "epoch": 4.268588770864947 + }, + { + "current_steps": 2813, + "loss": 2.375, + "learning_rate": 1.514866979655712e-07, + "epoch": 4.2701062215478 + }, + { + "current_steps": 2814, + "loss": 2.6654, + "learning_rate": 1.511737089201878e-07, + "epoch": 4.271623672230652 + }, + { + "current_steps": 2815, + "loss": 2.4828, + "learning_rate": 1.5086071987480435e-07, + "epoch": 4.273141122913505 + }, + { + "current_steps": 2816, + "loss": 2.5061, + "learning_rate": 1.5054773082942097e-07, + "epoch": 4.2746585735963585 + }, + { + "current_steps": 2817, + "loss": 2.6446, + "learning_rate": 1.5023474178403755e-07, + "epoch": 4.276176024279211 + }, + { + "current_steps": 2818, + "loss": 2.6691, + "learning_rate": 1.4992175273865414e-07, + "epoch": 4.277693474962064 + }, + { + "current_steps": 2819, + "loss": 2.5225, + "learning_rate": 1.4960876369327073e-07, + "epoch": 4.279210925644916 + }, + { + "current_steps": 2820, + "loss": 2.4716, + "learning_rate": 1.492957746478873e-07, + "epoch": 4.28072837632777 + }, + { + "current_steps": 2821, + "loss": 2.5549, + "learning_rate": 1.489827856025039e-07, + "epoch": 4.282245827010622 + }, + { + "current_steps": 2822, + "loss": 2.4668, + "learning_rate": 1.486697965571205e-07, + "epoch": 4.283763277693475 + }, + { + "current_steps": 2823, + "loss": 2.5456, + "learning_rate": 1.4835680751173707e-07, + "epoch": 4.2852807283763275 + }, + { + "current_steps": 2824, + "loss": 2.5062, + "learning_rate": 1.4804381846635366e-07, + "epoch": 4.286798179059181 + }, + { + "current_steps": 2825, + "loss": 2.4983, + "learning_rate": 1.4773082942097027e-07, + "epoch": 4.2883156297420335 + }, + { + "current_steps": 2826, + "loss": 2.4818, + "learning_rate": 1.4741784037558686e-07, + "epoch": 4.289833080424886 + }, + { + "current_steps": 2827, + "loss": 2.4756, + "learning_rate": 1.4710485133020344e-07, + "epoch": 4.291350531107739 + }, + { + "current_steps": 2828, + "loss": 2.4579, + "learning_rate": 1.4679186228482003e-07, + "epoch": 4.292867981790592 + }, + { + "current_steps": 2829, + "loss": 2.6288, + "learning_rate": 1.4647887323943661e-07, + "epoch": 4.294385432473445 + }, + { + "current_steps": 2830, + "loss": 2.5041, + "learning_rate": 1.461658841940532e-07, + "epoch": 4.295902883156297 + }, + { + "current_steps": 2831, + "loss": 2.261, + "learning_rate": 1.458528951486698e-07, + "epoch": 4.29742033383915 + }, + { + "current_steps": 2832, + "loss": 2.4979, + "learning_rate": 1.4553990610328637e-07, + "epoch": 4.298937784522003 + }, + { + "current_steps": 2833, + "loss": 2.6361, + "learning_rate": 1.4522691705790296e-07, + "epoch": 4.300455235204856 + }, + { + "current_steps": 2834, + "loss": 2.3938, + "learning_rate": 1.4491392801251957e-07, + "epoch": 4.3019726858877085 + }, + { + "current_steps": 2835, + "loss": 2.5871, + "learning_rate": 1.4460093896713616e-07, + "epoch": 4.303490136570561 + }, + { + "current_steps": 2836, + "loss": 2.7173, + "learning_rate": 1.4428794992175272e-07, + "epoch": 4.305007587253415 + }, + { + "current_steps": 2837, + "loss": 2.5911, + "learning_rate": 1.4397496087636933e-07, + "epoch": 4.306525037936267 + }, + { + "current_steps": 2838, + "loss": 2.567, + "learning_rate": 1.4366197183098591e-07, + "epoch": 4.30804248861912 + }, + { + "current_steps": 2839, + "loss": 2.633, + "learning_rate": 1.433489827856025e-07, + "epoch": 4.309559939301972 + }, + { + "current_steps": 2840, + "loss": 2.4644, + "learning_rate": 1.430359937402191e-07, + "epoch": 4.311077389984826 + }, + { + "current_steps": 2841, + "loss": 2.5483, + "learning_rate": 1.4272300469483567e-07, + "epoch": 4.312594840667678 + }, + { + "current_steps": 2842, + "loss": 2.5231, + "learning_rate": 1.4241001564945226e-07, + "epoch": 4.314112291350531 + }, + { + "current_steps": 2843, + "loss": 2.478, + "learning_rate": 1.4209702660406887e-07, + "epoch": 4.315629742033384 + }, + { + "current_steps": 2844, + "loss": 2.7939, + "learning_rate": 1.4178403755868543e-07, + "epoch": 4.317147192716237 + }, + { + "current_steps": 2845, + "loss": 2.5292, + "learning_rate": 1.4147104851330202e-07, + "epoch": 4.31866464339909 + }, + { + "current_steps": 2846, + "loss": 2.5741, + "learning_rate": 1.411580594679186e-07, + "epoch": 4.320182094081942 + }, + { + "current_steps": 2847, + "loss": 2.4945, + "learning_rate": 1.4084507042253522e-07, + "epoch": 4.321699544764795 + }, + { + "current_steps": 2848, + "loss": 2.7066, + "learning_rate": 1.405320813771518e-07, + "epoch": 4.323216995447648 + }, + { + "current_steps": 2849, + "loss": 2.4059, + "learning_rate": 1.4021909233176836e-07, + "epoch": 4.324734446130501 + }, + { + "current_steps": 2850, + "loss": 2.8335, + "learning_rate": 1.3990610328638497e-07, + "epoch": 4.326251896813353 + }, + { + "current_steps": 2851, + "loss": 2.6699, + "learning_rate": 1.3959311424100156e-07, + "epoch": 4.327769347496206 + }, + { + "current_steps": 2852, + "loss": 2.313, + "learning_rate": 1.3928012519561815e-07, + "epoch": 4.3292867981790595 + }, + { + "current_steps": 2853, + "loss": 2.4986, + "learning_rate": 1.3896713615023473e-07, + "epoch": 4.330804248861912 + }, + { + "current_steps": 2854, + "loss": 2.6032, + "learning_rate": 1.3865414710485132e-07, + "epoch": 4.332321699544765 + }, + { + "current_steps": 2855, + "loss": 2.6018, + "learning_rate": 1.383411580594679e-07, + "epoch": 4.333839150227617 + }, + { + "current_steps": 2856, + "loss": 2.4738, + "learning_rate": 1.3802816901408452e-07, + "epoch": 4.335356600910471 + }, + { + "current_steps": 2857, + "loss": 2.5325, + "learning_rate": 1.3771517996870108e-07, + "epoch": 4.336874051593323 + }, + { + "current_steps": 2858, + "loss": 2.6312, + "learning_rate": 1.3740219092331766e-07, + "epoch": 4.338391502276176 + }, + { + "current_steps": 2859, + "loss": 2.788, + "learning_rate": 1.3708920187793428e-07, + "epoch": 4.3399089529590285 + }, + { + "current_steps": 2860, + "loss": 2.4567, + "learning_rate": 1.3677621283255086e-07, + "epoch": 4.341426403641882 + }, + { + "current_steps": 2861, + "loss": 2.8114, + "learning_rate": 1.3646322378716742e-07, + "epoch": 4.3429438543247345 + }, + { + "current_steps": 2862, + "loss": 2.6788, + "learning_rate": 1.3615023474178403e-07, + "epoch": 4.344461305007587 + }, + { + "current_steps": 2863, + "loss": 2.6731, + "learning_rate": 1.3583724569640062e-07, + "epoch": 4.34597875569044 + }, + { + "current_steps": 2864, + "loss": 1.9686, + "learning_rate": 1.355242566510172e-07, + "epoch": 4.347496206373293 + }, + { + "current_steps": 2865, + "loss": 2.5446, + "learning_rate": 1.352112676056338e-07, + "epoch": 4.349013657056146 + }, + { + "current_steps": 2866, + "loss": 2.6885, + "learning_rate": 1.3489827856025038e-07, + "epoch": 4.350531107738998 + }, + { + "current_steps": 2867, + "loss": 2.6182, + "learning_rate": 1.3458528951486697e-07, + "epoch": 4.352048558421851 + }, + { + "current_steps": 2868, + "loss": 2.6472, + "learning_rate": 1.3427230046948358e-07, + "epoch": 4.353566009104704 + }, + { + "current_steps": 2869, + "loss": 2.0513, + "learning_rate": 1.3395931142410016e-07, + "epoch": 4.355083459787557 + }, + { + "current_steps": 2870, + "loss": 2.512, + "learning_rate": 1.3364632237871672e-07, + "epoch": 4.3566009104704095 + }, + { + "current_steps": 2871, + "loss": 2.5109, + "learning_rate": 1.3333333333333334e-07, + "epoch": 4.358118361153262 + }, + { + "current_steps": 2872, + "loss": 2.0361, + "learning_rate": 1.3302034428794992e-07, + "epoch": 4.359635811836116 + }, + { + "current_steps": 2873, + "loss": 2.6609, + "learning_rate": 1.327073552425665e-07, + "epoch": 4.361153262518968 + }, + { + "current_steps": 2874, + "loss": 2.5303, + "learning_rate": 1.323943661971831e-07, + "epoch": 4.362670713201821 + }, + { + "current_steps": 2875, + "loss": 2.109, + "learning_rate": 1.3208137715179968e-07, + "epoch": 4.364188163884673 + }, + { + "current_steps": 2876, + "loss": 2.4102, + "learning_rate": 1.3176838810641627e-07, + "epoch": 4.365705614567527 + }, + { + "current_steps": 2877, + "loss": 2.6624, + "learning_rate": 1.3145539906103288e-07, + "epoch": 4.367223065250379 + }, + { + "current_steps": 2878, + "loss": 2.6263, + "learning_rate": 1.3114241001564944e-07, + "epoch": 4.368740515933232 + }, + { + "current_steps": 2879, + "loss": 2.5507, + "learning_rate": 1.3082942097026603e-07, + "epoch": 4.370257966616085 + }, + { + "current_steps": 2880, + "loss": 2.6315, + "learning_rate": 1.3051643192488264e-07, + "epoch": 4.371775417298938 + }, + { + "current_steps": 2881, + "loss": 2.4281, + "learning_rate": 1.3020344287949922e-07, + "epoch": 4.373292867981791 + }, + { + "current_steps": 2882, + "loss": 2.4323, + "learning_rate": 1.2989045383411578e-07, + "epoch": 4.374810318664643 + }, + { + "current_steps": 2883, + "loss": 2.682, + "learning_rate": 1.2957746478873237e-07, + "epoch": 4.376327769347496 + }, + { + "current_steps": 2884, + "loss": 2.0029, + "learning_rate": 1.2926447574334898e-07, + "epoch": 4.377845220030349 + }, + { + "current_steps": 2885, + "loss": 2.2122, + "learning_rate": 1.2895148669796557e-07, + "epoch": 4.379362670713202 + }, + { + "current_steps": 2886, + "loss": 2.5237, + "learning_rate": 1.2863849765258215e-07, + "epoch": 4.380880121396054 + }, + { + "current_steps": 2887, + "loss": 2.4224, + "learning_rate": 1.2832550860719874e-07, + "epoch": 4.382397572078908 + }, + { + "current_steps": 2888, + "loss": 2.1662, + "learning_rate": 1.2801251956181533e-07, + "epoch": 4.3839150227617605 + }, + { + "current_steps": 2889, + "loss": 2.5406, + "learning_rate": 1.276995305164319e-07, + "epoch": 4.385432473444613 + }, + { + "current_steps": 2890, + "loss": 2.4788, + "learning_rate": 1.2738654147104853e-07, + "epoch": 4.386949924127466 + }, + { + "current_steps": 2891, + "loss": 2.5512, + "learning_rate": 1.2707355242566508e-07, + "epoch": 4.388467374810318 + }, + { + "current_steps": 2892, + "loss": 2.4782, + "learning_rate": 1.2676056338028167e-07, + "epoch": 4.389984825493172 + }, + { + "current_steps": 2893, + "loss": 2.7279, + "learning_rate": 1.2644757433489828e-07, + "epoch": 4.391502276176024 + }, + { + "current_steps": 2894, + "loss": 2.3887, + "learning_rate": 1.2613458528951487e-07, + "epoch": 4.393019726858877 + }, + { + "current_steps": 2895, + "loss": 2.2786, + "learning_rate": 1.2582159624413143e-07, + "epoch": 4.39453717754173 + }, + { + "current_steps": 2896, + "loss": 2.5244, + "learning_rate": 1.2550860719874804e-07, + "epoch": 4.396054628224583 + }, + { + "current_steps": 2897, + "loss": 2.7122, + "learning_rate": 1.2519561815336463e-07, + "epoch": 4.3975720789074355 + }, + { + "current_steps": 2898, + "loss": 2.4861, + "learning_rate": 1.2488262910798121e-07, + "epoch": 4.399089529590288 + }, + { + "current_steps": 2899, + "loss": 2.4784, + "learning_rate": 1.245696400625978e-07, + "epoch": 4.400606980273141 + }, + { + "current_steps": 2900, + "loss": 2.6189, + "learning_rate": 1.2425665101721439e-07, + "epoch": 4.402124430955994 + }, + { + "current_steps": 2901, + "loss": 2.4348, + "learning_rate": 1.2394366197183097e-07, + "epoch": 4.403641881638847 + }, + { + "current_steps": 2902, + "loss": 2.5022, + "learning_rate": 1.2363067292644756e-07, + "epoch": 4.405159332321699 + }, + { + "current_steps": 2903, + "loss": 2.4958, + "learning_rate": 1.2331768388106414e-07, + "epoch": 4.406676783004553 + }, + { + "current_steps": 2904, + "loss": 2.4349, + "learning_rate": 1.2300469483568073e-07, + "epoch": 4.408194233687405 + }, + { + "current_steps": 2905, + "loss": 2.514, + "learning_rate": 1.2269170579029734e-07, + "epoch": 4.409711684370258 + }, + { + "current_steps": 2906, + "loss": 2.5261, + "learning_rate": 1.2237871674491393e-07, + "epoch": 4.4112291350531105 + }, + { + "current_steps": 2907, + "loss": 2.5423, + "learning_rate": 1.2206572769953052e-07, + "epoch": 4.412746585735963 + }, + { + "current_steps": 2908, + "loss": 2.5986, + "learning_rate": 1.217527386541471e-07, + "epoch": 4.414264036418817 + }, + { + "current_steps": 2909, + "loss": 2.3572, + "learning_rate": 1.214397496087637e-07, + "epoch": 4.415781487101669 + }, + { + "current_steps": 2910, + "loss": 2.4394, + "learning_rate": 1.2112676056338027e-07, + "epoch": 4.417298937784522 + }, + { + "current_steps": 2911, + "loss": 2.6651, + "learning_rate": 1.2081377151799686e-07, + "epoch": 4.418816388467375 + }, + { + "current_steps": 2912, + "loss": 2.2453, + "learning_rate": 1.2050078247261345e-07, + "epoch": 4.420333839150228 + }, + { + "current_steps": 2913, + "loss": 2.458, + "learning_rate": 1.2018779342723003e-07, + "epoch": 4.42185128983308 + }, + { + "current_steps": 2914, + "loss": 2.5364, + "learning_rate": 1.1987480438184664e-07, + "epoch": 4.423368740515933 + }, + { + "current_steps": 2915, + "loss": 2.5297, + "learning_rate": 1.195618153364632e-07, + "epoch": 4.424886191198786 + }, + { + "current_steps": 2916, + "loss": 2.5735, + "learning_rate": 1.1924882629107982e-07, + "epoch": 4.426403641881639 + }, + { + "current_steps": 2917, + "loss": 2.5894, + "learning_rate": 1.1893583724569639e-07, + "epoch": 4.427921092564492 + }, + { + "current_steps": 2918, + "loss": 2.7295, + "learning_rate": 1.1862284820031299e-07, + "epoch": 4.429438543247344 + }, + { + "current_steps": 2919, + "loss": 2.578, + "learning_rate": 1.1830985915492956e-07, + "epoch": 4.430955993930198 + }, + { + "current_steps": 2920, + "loss": 2.6512, + "learning_rate": 1.1799687010954616e-07, + "epoch": 4.43247344461305 + }, + { + "current_steps": 2921, + "loss": 2.5584, + "learning_rate": 1.1768388106416275e-07, + "epoch": 4.433990895295903 + }, + { + "current_steps": 2922, + "loss": 2.4331, + "learning_rate": 1.1737089201877933e-07, + "epoch": 4.435508345978755 + }, + { + "current_steps": 2923, + "loss": 2.6094, + "learning_rate": 1.1705790297339592e-07, + "epoch": 4.437025796661609 + }, + { + "current_steps": 2924, + "loss": 2.6257, + "learning_rate": 1.1674491392801252e-07, + "epoch": 4.4385432473444615 + }, + { + "current_steps": 2925, + "loss": 2.7199, + "learning_rate": 1.164319248826291e-07, + "epoch": 4.440060698027314 + }, + { + "current_steps": 2926, + "loss": 2.4569, + "learning_rate": 1.1611893583724569e-07, + "epoch": 4.441578148710167 + }, + { + "current_steps": 2927, + "loss": 2.5124, + "learning_rate": 1.1580594679186229e-07, + "epoch": 4.44309559939302 + }, + { + "current_steps": 2928, + "loss": 2.674, + "learning_rate": 1.1549295774647886e-07, + "epoch": 4.444613050075873 + }, + { + "current_steps": 2929, + "loss": 2.5451, + "learning_rate": 1.1517996870109546e-07, + "epoch": 4.446130500758725 + }, + { + "current_steps": 2930, + "loss": 2.3404, + "learning_rate": 1.1486697965571205e-07, + "epoch": 4.447647951441578 + }, + { + "current_steps": 2931, + "loss": 2.5872, + "learning_rate": 1.1455399061032864e-07, + "epoch": 4.449165402124431 + }, + { + "current_steps": 2932, + "loss": 2.7247, + "learning_rate": 1.1424100156494522e-07, + "epoch": 4.450682852807284 + }, + { + "current_steps": 2933, + "loss": 2.4419, + "learning_rate": 1.1392801251956181e-07, + "epoch": 4.4522003034901365 + }, + { + "current_steps": 2934, + "loss": 2.3443, + "learning_rate": 1.136150234741784e-07, + "epoch": 4.453717754172989 + }, + { + "current_steps": 2935, + "loss": 2.7083, + "learning_rate": 1.1330203442879499e-07, + "epoch": 4.455235204855843 + }, + { + "current_steps": 2936, + "loss": 2.4466, + "learning_rate": 1.1298904538341157e-07, + "epoch": 4.456752655538695 + }, + { + "current_steps": 2937, + "loss": 2.6634, + "learning_rate": 1.1267605633802817e-07, + "epoch": 4.458270106221548 + }, + { + "current_steps": 2938, + "loss": 2.4202, + "learning_rate": 1.1236306729264475e-07, + "epoch": 4.4597875569044 + }, + { + "current_steps": 2939, + "loss": 2.5742, + "learning_rate": 1.1205007824726134e-07, + "epoch": 4.461305007587254 + }, + { + "current_steps": 2940, + "loss": 2.6888, + "learning_rate": 1.1173708920187792e-07, + "epoch": 4.462822458270106 + }, + { + "current_steps": 2941, + "loss": 2.5507, + "learning_rate": 1.1142410015649452e-07, + "epoch": 4.464339908952959 + }, + { + "current_steps": 2942, + "loss": 2.7111, + "learning_rate": 1.111111111111111e-07, + "epoch": 4.4658573596358115 + }, + { + "current_steps": 2943, + "loss": 2.5366, + "learning_rate": 1.107981220657277e-07, + "epoch": 4.467374810318665 + }, + { + "current_steps": 2944, + "loss": 2.6747, + "learning_rate": 1.1048513302034428e-07, + "epoch": 4.468892261001518 + }, + { + "current_steps": 2945, + "loss": 2.6928, + "learning_rate": 1.1017214397496087e-07, + "epoch": 4.47040971168437 + }, + { + "current_steps": 2946, + "loss": 2.7366, + "learning_rate": 1.0985915492957747e-07, + "epoch": 4.471927162367223 + }, + { + "current_steps": 2947, + "loss": 2.6674, + "learning_rate": 1.0954616588419405e-07, + "epoch": 4.473444613050076 + }, + { + "current_steps": 2948, + "loss": 2.6192, + "learning_rate": 1.0923317683881064e-07, + "epoch": 4.474962063732929 + }, + { + "current_steps": 2949, + "loss": 2.5447, + "learning_rate": 1.0892018779342723e-07, + "epoch": 4.476479514415781 + }, + { + "current_steps": 2950, + "loss": 2.3601, + "learning_rate": 1.0860719874804382e-07, + "epoch": 4.477996965098634 + }, + { + "current_steps": 2951, + "loss": 2.4569, + "learning_rate": 1.082942097026604e-07, + "epoch": 4.4795144157814875 + }, + { + "current_steps": 2952, + "loss": 2.6092, + "learning_rate": 1.07981220657277e-07, + "epoch": 4.48103186646434 + }, + { + "current_steps": 2953, + "loss": 2.5483, + "learning_rate": 1.0766823161189357e-07, + "epoch": 4.482549317147193 + }, + { + "current_steps": 2954, + "loss": 2.2883, + "learning_rate": 1.0735524256651017e-07, + "epoch": 4.484066767830045 + }, + { + "current_steps": 2955, + "loss": 2.5427, + "learning_rate": 1.0704225352112675e-07, + "epoch": 4.485584218512899 + }, + { + "current_steps": 2956, + "loss": 2.411, + "learning_rate": 1.0672926447574334e-07, + "epoch": 4.487101669195751 + }, + { + "current_steps": 2957, + "loss": 2.5344, + "learning_rate": 1.0641627543035993e-07, + "epoch": 4.488619119878604 + }, + { + "current_steps": 2958, + "loss": 2.4661, + "learning_rate": 1.0610328638497653e-07, + "epoch": 4.490136570561456 + }, + { + "current_steps": 2959, + "loss": 2.3711, + "learning_rate": 1.057902973395931e-07, + "epoch": 4.49165402124431 + }, + { + "current_steps": 2960, + "loss": 2.4178, + "learning_rate": 1.054773082942097e-07, + "epoch": 4.4931714719271625 + }, + { + "current_steps": 2961, + "loss": 2.5514, + "learning_rate": 1.0516431924882628e-07, + "epoch": 4.494688922610015 + }, + { + "current_steps": 2962, + "loss": 2.4914, + "learning_rate": 1.0485133020344287e-07, + "epoch": 4.496206373292868 + }, + { + "current_steps": 2963, + "loss": 2.2603, + "learning_rate": 1.0453834115805946e-07, + "epoch": 4.497723823975721 + }, + { + "current_steps": 2964, + "loss": 2.4895, + "learning_rate": 1.0422535211267606e-07, + "epoch": 4.499241274658574 + }, + { + "current_steps": 2965, + "loss": 2.6517, + "learning_rate": 1.0391236306729264e-07, + "epoch": 4.500758725341426 + }, + { + "current_steps": 2966, + "loss": 2.4575, + "learning_rate": 1.0359937402190923e-07, + "epoch": 4.502276176024279 + }, + { + "current_steps": 2967, + "loss": 2.4993, + "learning_rate": 1.0328638497652583e-07, + "epoch": 4.503793626707132 + }, + { + "current_steps": 2968, + "loss": 2.26, + "learning_rate": 1.029733959311424e-07, + "epoch": 4.505311077389985 + }, + { + "current_steps": 2969, + "loss": 2.5241, + "learning_rate": 1.02660406885759e-07, + "epoch": 4.5068285280728375 + }, + { + "current_steps": 2970, + "loss": 2.5937, + "learning_rate": 1.0234741784037559e-07, + "epoch": 4.50834597875569 + }, + { + "current_steps": 2971, + "loss": 2.5593, + "learning_rate": 1.0203442879499217e-07, + "epoch": 4.509863429438544 + }, + { + "current_steps": 2972, + "loss": 2.1839, + "learning_rate": 1.0172143974960876e-07, + "epoch": 4.511380880121396 + }, + { + "current_steps": 2973, + "loss": 2.4398, + "learning_rate": 1.0140845070422534e-07, + "epoch": 4.512898330804249 + }, + { + "current_steps": 2974, + "loss": 2.5598, + "learning_rate": 1.0109546165884193e-07, + "epoch": 4.514415781487101 + }, + { + "current_steps": 2975, + "loss": 2.6346, + "learning_rate": 1.0078247261345853e-07, + "epoch": 4.515933232169955 + }, + { + "current_steps": 2976, + "loss": 2.3776, + "learning_rate": 1.004694835680751e-07, + "epoch": 4.517450682852807 + }, + { + "current_steps": 2977, + "loss": 2.3609, + "learning_rate": 1.001564945226917e-07, + "epoch": 4.51896813353566 + }, + { + "current_steps": 2978, + "loss": 2.6339, + "learning_rate": 9.984350547730829e-08, + "epoch": 4.5204855842185125 + }, + { + "current_steps": 2979, + "loss": 2.4637, + "learning_rate": 9.953051643192487e-08, + "epoch": 4.522003034901366 + }, + { + "current_steps": 2980, + "loss": 2.6335, + "learning_rate": 9.921752738654146e-08, + "epoch": 4.523520485584219 + }, + { + "current_steps": 2981, + "loss": 2.7719, + "learning_rate": 9.890453834115806e-08, + "epoch": 4.525037936267071 + }, + { + "current_steps": 2982, + "loss": 2.2782, + "learning_rate": 9.859154929577463e-08, + "epoch": 4.526555386949924 + }, + { + "current_steps": 2983, + "loss": 2.4146, + "learning_rate": 9.827856025039123e-08, + "epoch": 4.528072837632777 + }, + { + "current_steps": 2984, + "loss": 2.5564, + "learning_rate": 9.796557120500783e-08, + "epoch": 4.52959028831563 + }, + { + "current_steps": 2985, + "loss": 2.5659, + "learning_rate": 9.76525821596244e-08, + "epoch": 4.531107738998482 + }, + { + "current_steps": 2986, + "loss": 2.3172, + "learning_rate": 9.7339593114241e-08, + "epoch": 4.532625189681335 + }, + { + "current_steps": 2987, + "loss": 2.4542, + "learning_rate": 9.702660406885759e-08, + "epoch": 4.5341426403641885 + }, + { + "current_steps": 2988, + "loss": 2.4837, + "learning_rate": 9.671361502347418e-08, + "epoch": 4.535660091047041 + }, + { + "current_steps": 2989, + "loss": 2.4604, + "learning_rate": 9.640062597809076e-08, + "epoch": 4.537177541729894 + }, + { + "current_steps": 2990, + "loss": 2.543, + "learning_rate": 9.608763693270736e-08, + "epoch": 4.538694992412746 + }, + { + "current_steps": 2991, + "loss": 2.6134, + "learning_rate": 9.577464788732393e-08, + "epoch": 4.5402124430956 + }, + { + "current_steps": 2992, + "loss": 2.5481, + "learning_rate": 9.546165884194053e-08, + "epoch": 4.541729893778452 + }, + { + "current_steps": 2993, + "loss": 2.641, + "learning_rate": 9.514866979655711e-08, + "epoch": 4.543247344461305 + }, + { + "current_steps": 2994, + "loss": 2.5058, + "learning_rate": 9.48356807511737e-08, + "epoch": 4.544764795144157 + }, + { + "current_steps": 2995, + "loss": 2.7372, + "learning_rate": 9.452269170579029e-08, + "epoch": 4.546282245827011 + }, + { + "current_steps": 2996, + "loss": 2.4143, + "learning_rate": 9.420970266040688e-08, + "epoch": 4.5477996965098635 + }, + { + "current_steps": 2997, + "loss": 2.6505, + "learning_rate": 9.389671361502346e-08, + "epoch": 4.549317147192716 + }, + { + "current_steps": 2998, + "loss": 2.8514, + "learning_rate": 9.358372456964006e-08, + "epoch": 4.5508345978755695 + }, + { + "current_steps": 2999, + "loss": 2.498, + "learning_rate": 9.327073552425664e-08, + "epoch": 4.552352048558422 + }, + { + "current_steps": 3000, + "loss": 2.4155, + "learning_rate": 9.295774647887324e-08, + "epoch": 4.553869499241275 + }, + { + "current_steps": 3001, + "loss": 2.417, + "learning_rate": 9.264475743348982e-08, + "epoch": 4.555386949924127 + }, + { + "current_steps": 3002, + "loss": 2.6118, + "learning_rate": 9.233176838810641e-08, + "epoch": 4.55690440060698 + }, + { + "current_steps": 3003, + "loss": 2.616, + "learning_rate": 9.201877934272301e-08, + "epoch": 4.558421851289833 + }, + { + "current_steps": 3004, + "loss": 2.5673, + "learning_rate": 9.17057902973396e-08, + "epoch": 4.559939301972686 + }, + { + "current_steps": 3005, + "loss": 2.494, + "learning_rate": 9.139280125195618e-08, + "epoch": 4.5614567526555385 + }, + { + "current_steps": 3006, + "loss": 2.4908, + "learning_rate": 9.107981220657277e-08, + "epoch": 4.562974203338392 + }, + { + "current_steps": 3007, + "loss": 2.7107, + "learning_rate": 9.076682316118937e-08, + "epoch": 4.564491654021245 + }, + { + "current_steps": 3008, + "loss": 2.7537, + "learning_rate": 9.045383411580594e-08, + "epoch": 4.566009104704097 + }, + { + "current_steps": 3009, + "loss": 2.5213, + "learning_rate": 9.014084507042254e-08, + "epoch": 4.56752655538695 + }, + { + "current_steps": 3010, + "loss": 2.5221, + "learning_rate": 8.982785602503912e-08, + "epoch": 4.569044006069802 + }, + { + "current_steps": 3011, + "loss": 2.6217, + "learning_rate": 8.951486697965571e-08, + "epoch": 4.570561456752656 + }, + { + "current_steps": 3012, + "loss": 2.5457, + "learning_rate": 8.92018779342723e-08, + "epoch": 4.572078907435508 + }, + { + "current_steps": 3013, + "loss": 2.1022, + "learning_rate": 8.888888888888888e-08, + "epoch": 4.573596358118361 + }, + { + "current_steps": 3014, + "loss": 2.8111, + "learning_rate": 8.857589984350547e-08, + "epoch": 4.575113808801214 + }, + { + "current_steps": 3015, + "loss": 2.4242, + "learning_rate": 8.826291079812207e-08, + "epoch": 4.576631259484067 + }, + { + "current_steps": 3016, + "loss": 2.4584, + "learning_rate": 8.794992175273864e-08, + "epoch": 4.57814871016692 + }, + { + "current_steps": 3017, + "loss": 2.7369, + "learning_rate": 8.763693270735524e-08, + "epoch": 4.579666160849772 + }, + { + "current_steps": 3018, + "loss": 2.3103, + "learning_rate": 8.732394366197183e-08, + "epoch": 4.581183611532625 + }, + { + "current_steps": 3019, + "loss": 2.5741, + "learning_rate": 8.701095461658841e-08, + "epoch": 4.582701062215478 + }, + { + "current_steps": 3020, + "loss": 2.512, + "learning_rate": 8.6697965571205e-08, + "epoch": 4.584218512898331 + }, + { + "current_steps": 3021, + "loss": 2.6593, + "learning_rate": 8.63849765258216e-08, + "epoch": 4.585735963581183 + }, + { + "current_steps": 3022, + "loss": 2.4588, + "learning_rate": 8.607198748043817e-08, + "epoch": 4.587253414264037 + }, + { + "current_steps": 3023, + "loss": 2.7325, + "learning_rate": 8.575899843505477e-08, + "epoch": 4.5887708649468895 + }, + { + "current_steps": 3024, + "loss": 2.5713, + "learning_rate": 8.544600938967137e-08, + "epoch": 4.590288315629742 + }, + { + "current_steps": 3025, + "loss": 2.4343, + "learning_rate": 8.513302034428794e-08, + "epoch": 4.591805766312595 + }, + { + "current_steps": 3026, + "loss": 2.4312, + "learning_rate": 8.482003129890454e-08, + "epoch": 4.593323216995447 + }, + { + "current_steps": 3027, + "loss": 2.311, + "learning_rate": 8.450704225352113e-08, + "epoch": 4.594840667678301 + }, + { + "current_steps": 3028, + "loss": 2.331, + "learning_rate": 8.419405320813771e-08, + "epoch": 4.596358118361153 + }, + { + "current_steps": 3029, + "loss": 2.6002, + "learning_rate": 8.38810641627543e-08, + "epoch": 4.597875569044006 + }, + { + "current_steps": 3030, + "loss": 2.6662, + "learning_rate": 8.35680751173709e-08, + "epoch": 4.599393019726859 + }, + { + "current_steps": 3031, + "loss": 2.5964, + "learning_rate": 8.325508607198747e-08, + "epoch": 4.600910470409712 + }, + { + "current_steps": 3032, + "loss": 2.398, + "learning_rate": 8.294209702660407e-08, + "epoch": 4.6024279210925645 + }, + { + "current_steps": 3033, + "loss": 2.645, + "learning_rate": 8.262910798122064e-08, + "epoch": 4.603945371775417 + }, + { + "current_steps": 3034, + "loss": 2.6763, + "learning_rate": 8.231611893583724e-08, + "epoch": 4.60546282245827 + }, + { + "current_steps": 3035, + "loss": 2.681, + "learning_rate": 8.200312989045383e-08, + "epoch": 4.606980273141123 + }, + { + "current_steps": 3036, + "loss": 2.5008, + "learning_rate": 8.169014084507042e-08, + "epoch": 4.608497723823976 + }, + { + "current_steps": 3037, + "loss": 2.2098, + "learning_rate": 8.1377151799687e-08, + "epoch": 4.610015174506828 + }, + { + "current_steps": 3038, + "loss": 2.5056, + "learning_rate": 8.10641627543036e-08, + "epoch": 4.611532625189682 + }, + { + "current_steps": 3039, + "loss": 2.72, + "learning_rate": 8.075117370892017e-08, + "epoch": 4.613050075872534 + }, + { + "current_steps": 3040, + "loss": 2.1152, + "learning_rate": 8.043818466353677e-08, + "epoch": 4.614567526555387 + }, + { + "current_steps": 3041, + "loss": 2.4383, + "learning_rate": 8.012519561815336e-08, + "epoch": 4.6160849772382395 + }, + { + "current_steps": 3042, + "loss": 2.3332, + "learning_rate": 7.981220657276995e-08, + "epoch": 4.617602427921092 + }, + { + "current_steps": 3043, + "loss": 2.4902, + "learning_rate": 7.949921752738654e-08, + "epoch": 4.619119878603946 + }, + { + "current_steps": 3044, + "loss": 2.6976, + "learning_rate": 7.918622848200313e-08, + "epoch": 4.620637329286798 + }, + { + "current_steps": 3045, + "loss": 2.5447, + "learning_rate": 7.887323943661972e-08, + "epoch": 4.622154779969651 + }, + { + "current_steps": 3046, + "loss": 2.7036, + "learning_rate": 7.85602503912363e-08, + "epoch": 4.623672230652504 + }, + { + "current_steps": 3047, + "loss": 2.7466, + "learning_rate": 7.82472613458529e-08, + "epoch": 4.625189681335357 + }, + { + "current_steps": 3048, + "loss": 2.4856, + "learning_rate": 7.793427230046948e-08, + "epoch": 4.626707132018209 + }, + { + "current_steps": 3049, + "loss": 2.4081, + "learning_rate": 7.762128325508607e-08, + "epoch": 4.628224582701062 + }, + { + "current_steps": 3050, + "loss": 1.916, + "learning_rate": 7.730829420970265e-08, + "epoch": 4.6297420333839145 + }, + { + "current_steps": 3051, + "loss": 2.5507, + "learning_rate": 7.699530516431925e-08, + "epoch": 4.631259484066768 + }, + { + "current_steps": 3052, + "loss": 2.5224, + "learning_rate": 7.668231611893583e-08, + "epoch": 4.632776934749621 + }, + { + "current_steps": 3053, + "loss": 2.5687, + "learning_rate": 7.636932707355242e-08, + "epoch": 4.634294385432473 + }, + { + "current_steps": 3054, + "loss": 2.6017, + "learning_rate": 7.6056338028169e-08, + "epoch": 4.635811836115327 + }, + { + "current_steps": 3055, + "loss": 2.5406, + "learning_rate": 7.57433489827856e-08, + "epoch": 4.637329286798179 + }, + { + "current_steps": 3056, + "loss": 2.5498, + "learning_rate": 7.543035993740218e-08, + "epoch": 4.638846737481032 + }, + { + "current_steps": 3057, + "loss": 2.5526, + "learning_rate": 7.511737089201878e-08, + "epoch": 4.640364188163884 + }, + { + "current_steps": 3058, + "loss": 2.497, + "learning_rate": 7.480438184663536e-08, + "epoch": 4.641881638846737 + }, + { + "current_steps": 3059, + "loss": 2.6177, + "learning_rate": 7.449139280125195e-08, + "epoch": 4.6433990895295905 + }, + { + "current_steps": 3060, + "loss": 2.6954, + "learning_rate": 7.417840375586854e-08, + "epoch": 4.644916540212443 + }, + { + "current_steps": 3061, + "loss": 2.6173, + "learning_rate": 7.386541471048513e-08, + "epoch": 4.646433990895296 + }, + { + "current_steps": 3062, + "loss": 2.6052, + "learning_rate": 7.355242566510172e-08, + "epoch": 4.647951441578149 + }, + { + "current_steps": 3063, + "loss": 2.4928, + "learning_rate": 7.323943661971831e-08, + "epoch": 4.649468892261002 + }, + { + "current_steps": 3064, + "loss": 2.4765, + "learning_rate": 7.29264475743349e-08, + "epoch": 4.650986342943854 + }, + { + "current_steps": 3065, + "loss": 2.5192, + "learning_rate": 7.261345852895148e-08, + "epoch": 4.652503793626707 + }, + { + "current_steps": 3066, + "loss": 2.3843, + "learning_rate": 7.230046948356808e-08, + "epoch": 4.65402124430956 + }, + { + "current_steps": 3067, + "loss": 2.4558, + "learning_rate": 7.198748043818466e-08, + "epoch": 4.655538694992413 + }, + { + "current_steps": 3068, + "loss": 2.4117, + "learning_rate": 7.167449139280125e-08, + "epoch": 4.6570561456752655 + }, + { + "current_steps": 3069, + "loss": 2.0276, + "learning_rate": 7.136150234741784e-08, + "epoch": 4.658573596358118 + }, + { + "current_steps": 3070, + "loss": 2.4775, + "learning_rate": 7.104851330203444e-08, + "epoch": 4.6600910470409715 + }, + { + "current_steps": 3071, + "loss": 2.4447, + "learning_rate": 7.073552425665101e-08, + "epoch": 4.661608497723824 + }, + { + "current_steps": 3072, + "loss": 2.537, + "learning_rate": 7.042253521126761e-08, + "epoch": 4.663125948406677 + }, + { + "current_steps": 3073, + "loss": 2.5572, + "learning_rate": 7.010954616588418e-08, + "epoch": 4.664643399089529 + }, + { + "current_steps": 3074, + "loss": 2.4499, + "learning_rate": 6.979655712050078e-08, + "epoch": 4.666160849772383 + }, + { + "current_steps": 3075, + "loss": 2.5611, + "learning_rate": 6.948356807511737e-08, + "epoch": 4.667678300455235 + }, + { + "current_steps": 3076, + "loss": 2.6164, + "learning_rate": 6.917057902973395e-08, + "epoch": 4.669195751138088 + }, + { + "current_steps": 3077, + "loss": 1.846, + "learning_rate": 6.885758998435054e-08, + "epoch": 4.6707132018209405 + }, + { + "current_steps": 3078, + "loss": 2.6418, + "learning_rate": 6.854460093896714e-08, + "epoch": 4.672230652503794 + }, + { + "current_steps": 3079, + "loss": 2.6206, + "learning_rate": 6.823161189358371e-08, + "epoch": 4.673748103186647 + }, + { + "current_steps": 3080, + "loss": 2.5561, + "learning_rate": 6.791862284820031e-08, + "epoch": 4.675265553869499 + }, + { + "current_steps": 3081, + "loss": 2.6604, + "learning_rate": 6.76056338028169e-08, + "epoch": 4.676783004552352 + }, + { + "current_steps": 3082, + "loss": 2.6497, + "learning_rate": 6.729264475743348e-08, + "epoch": 4.678300455235205 + }, + { + "current_steps": 3083, + "loss": 2.5745, + "learning_rate": 6.697965571205008e-08, + "epoch": 4.679817905918058 + }, + { + "current_steps": 3084, + "loss": 2.4229, + "learning_rate": 6.666666666666667e-08, + "epoch": 4.68133535660091 + }, + { + "current_steps": 3085, + "loss": 2.3443, + "learning_rate": 6.635367762128325e-08, + "epoch": 4.682852807283763 + }, + { + "current_steps": 3086, + "loss": 2.5798, + "learning_rate": 6.604068857589984e-08, + "epoch": 4.684370257966616 + }, + { + "current_steps": 3087, + "loss": 2.6634, + "learning_rate": 6.572769953051644e-08, + "epoch": 4.685887708649469 + }, + { + "current_steps": 3088, + "loss": 2.4955, + "learning_rate": 6.541471048513301e-08, + "epoch": 4.687405159332322 + }, + { + "current_steps": 3089, + "loss": 2.4283, + "learning_rate": 6.510172143974961e-08, + "epoch": 4.688922610015174 + }, + { + "current_steps": 3090, + "loss": 2.4785, + "learning_rate": 6.478873239436618e-08, + "epoch": 4.690440060698028 + }, + { + "current_steps": 3091, + "loss": 2.5668, + "learning_rate": 6.447574334898278e-08, + "epoch": 4.69195751138088 + }, + { + "current_steps": 3092, + "loss": 2.5143, + "learning_rate": 6.416275430359937e-08, + "epoch": 4.693474962063733 + }, + { + "current_steps": 3093, + "loss": 2.4044, + "learning_rate": 6.384976525821596e-08, + "epoch": 4.694992412746585 + }, + { + "current_steps": 3094, + "loss": 2.4565, + "learning_rate": 6.353677621283254e-08, + "epoch": 4.696509863429439 + }, + { + "current_steps": 3095, + "loss": 2.5539, + "learning_rate": 6.322378716744914e-08, + "epoch": 4.6980273141122915 + }, + { + "current_steps": 3096, + "loss": 2.5532, + "learning_rate": 6.291079812206571e-08, + "epoch": 4.699544764795144 + }, + { + "current_steps": 3097, + "loss": 2.3191, + "learning_rate": 6.259780907668231e-08, + "epoch": 4.701062215477997 + }, + { + "current_steps": 3098, + "loss": 2.5924, + "learning_rate": 6.22848200312989e-08, + "epoch": 4.70257966616085 + }, + { + "current_steps": 3099, + "loss": 2.7173, + "learning_rate": 6.197183098591549e-08, + "epoch": 4.704097116843703 + }, + { + "current_steps": 3100, + "loss": 2.4868, + "learning_rate": 6.165884194053207e-08, + "epoch": 4.705614567526555 + }, + { + "current_steps": 3101, + "loss": 2.6167, + "learning_rate": 6.134585289514867e-08, + "epoch": 4.707132018209408 + }, + { + "current_steps": 3102, + "loss": 2.5107, + "learning_rate": 6.103286384976526e-08, + "epoch": 4.708649468892261 + }, + { + "current_steps": 3103, + "loss": 2.3878, + "learning_rate": 6.071987480438184e-08, + "epoch": 4.710166919575114 + }, + { + "current_steps": 3104, + "loss": 2.6226, + "learning_rate": 6.040688575899843e-08, + "epoch": 4.7116843702579665 + }, + { + "current_steps": 3105, + "loss": 2.3412, + "learning_rate": 6.009389671361502e-08, + "epoch": 4.713201820940819 + }, + { + "current_steps": 3106, + "loss": 1.7847, + "learning_rate": 5.97809076682316e-08, + "epoch": 4.7147192716236725 + }, + { + "current_steps": 3107, + "loss": 2.3681, + "learning_rate": 5.9467918622848195e-08, + "epoch": 4.716236722306525 + }, + { + "current_steps": 3108, + "loss": 2.887, + "learning_rate": 5.915492957746478e-08, + "epoch": 4.717754172989378 + }, + { + "current_steps": 3109, + "loss": 2.3768, + "learning_rate": 5.8841940532081374e-08, + "epoch": 4.71927162367223 + }, + { + "current_steps": 3110, + "loss": 2.4861, + "learning_rate": 5.852895148669796e-08, + "epoch": 4.720789074355084 + }, + { + "current_steps": 3111, + "loss": 2.5033, + "learning_rate": 5.821596244131455e-08, + "epoch": 4.722306525037936 + }, + { + "current_steps": 3112, + "loss": 2.7033, + "learning_rate": 5.7902973395931145e-08, + "epoch": 4.723823975720789 + }, + { + "current_steps": 3113, + "loss": 2.6065, + "learning_rate": 5.758998435054773e-08, + "epoch": 4.7253414264036415 + }, + { + "current_steps": 3114, + "loss": 2.4113, + "learning_rate": 5.727699530516432e-08, + "epoch": 4.726858877086495 + }, + { + "current_steps": 3115, + "loss": 2.4761, + "learning_rate": 5.6964006259780904e-08, + "epoch": 4.728376327769348 + }, + { + "current_steps": 3116, + "loss": 2.5996, + "learning_rate": 5.6651017214397496e-08, + "epoch": 4.7298937784522 + }, + { + "current_steps": 3117, + "loss": 2.9602, + "learning_rate": 5.633802816901408e-08, + "epoch": 4.731411229135053 + }, + { + "current_steps": 3118, + "loss": 2.5489, + "learning_rate": 5.602503912363067e-08, + "epoch": 4.732928679817906 + }, + { + "current_steps": 3119, + "loss": 2.5638, + "learning_rate": 5.571205007824726e-08, + "epoch": 4.734446130500759 + }, + { + "current_steps": 3120, + "loss": 2.2355, + "learning_rate": 5.539906103286385e-08, + "epoch": 4.735963581183611 + }, + { + "current_steps": 3121, + "loss": 2.5485, + "learning_rate": 5.5086071987480434e-08, + "epoch": 4.737481031866464 + }, + { + "current_steps": 3122, + "loss": 2.4697, + "learning_rate": 5.4773082942097026e-08, + "epoch": 4.738998482549317 + }, + { + "current_steps": 3123, + "loss": 2.5251, + "learning_rate": 5.446009389671361e-08, + "epoch": 4.74051593323217 + }, + { + "current_steps": 3124, + "loss": 2.6709, + "learning_rate": 5.41471048513302e-08, + "epoch": 4.742033383915023 + }, + { + "current_steps": 3125, + "loss": 2.6508, + "learning_rate": 5.3834115805946785e-08, + "epoch": 4.743550834597875 + }, + { + "current_steps": 3126, + "loss": 2.718, + "learning_rate": 5.352112676056338e-08, + "epoch": 4.745068285280729 + }, + { + "current_steps": 3127, + "loss": 2.3552, + "learning_rate": 5.3208137715179964e-08, + "epoch": 4.746585735963581 + }, + { + "current_steps": 3128, + "loss": 2.3488, + "learning_rate": 5.289514866979655e-08, + "epoch": 4.748103186646434 + }, + { + "current_steps": 3129, + "loss": 2.4701, + "learning_rate": 5.258215962441314e-08, + "epoch": 4.749620637329286 + }, + { + "current_steps": 3130, + "loss": 2.5615, + "learning_rate": 5.226917057902973e-08, + "epoch": 4.75113808801214 + }, + { + "current_steps": 3131, + "loss": 2.7922, + "learning_rate": 5.195618153364632e-08, + "epoch": 4.7526555386949925 + }, + { + "current_steps": 3132, + "loss": 1.9752, + "learning_rate": 5.1643192488262914e-08, + "epoch": 4.754172989377845 + }, + { + "current_steps": 3133, + "loss": 2.6238, + "learning_rate": 5.13302034428795e-08, + "epoch": 4.7556904400606985 + }, + { + "current_steps": 3134, + "loss": 2.0786, + "learning_rate": 5.1017214397496086e-08, + "epoch": 4.757207890743551 + }, + { + "current_steps": 3135, + "loss": 2.4342, + "learning_rate": 5.070422535211267e-08, + "epoch": 4.758725341426404 + }, + { + "current_steps": 3136, + "loss": 2.3822, + "learning_rate": 5.0391236306729265e-08, + "epoch": 4.760242792109256 + }, + { + "current_steps": 3137, + "loss": 2.5905, + "learning_rate": 5.007824726134585e-08, + "epoch": 4.761760242792109 + }, + { + "current_steps": 3138, + "loss": 2.3962, + "learning_rate": 4.976525821596244e-08, + "epoch": 4.763277693474962 + }, + { + "current_steps": 3139, + "loss": 2.4783, + "learning_rate": 4.945226917057903e-08, + "epoch": 4.764795144157815 + }, + { + "current_steps": 3140, + "loss": 2.2927, + "learning_rate": 4.9139280125195616e-08, + "epoch": 4.7663125948406675 + }, + { + "current_steps": 3141, + "loss": 1.9252, + "learning_rate": 4.88262910798122e-08, + "epoch": 4.767830045523521 + }, + { + "current_steps": 3142, + "loss": 2.6579, + "learning_rate": 4.8513302034428795e-08, + "epoch": 4.7693474962063735 + }, + { + "current_steps": 3143, + "loss": 2.552, + "learning_rate": 4.820031298904538e-08, + "epoch": 4.770864946889226 + }, + { + "current_steps": 3144, + "loss": 2.4288, + "learning_rate": 4.788732394366197e-08, + "epoch": 4.772382397572079 + }, + { + "current_steps": 3145, + "loss": 2.6054, + "learning_rate": 4.7574334898278553e-08, + "epoch": 4.773899848254931 + }, + { + "current_steps": 3146, + "loss": 2.3533, + "learning_rate": 4.7261345852895146e-08, + "epoch": 4.775417298937785 + }, + { + "current_steps": 3147, + "loss": 2.5231, + "learning_rate": 4.694835680751173e-08, + "epoch": 4.776934749620637 + }, + { + "current_steps": 3148, + "loss": 2.4944, + "learning_rate": 4.663536776212832e-08, + "epoch": 4.77845220030349 + }, + { + "current_steps": 3149, + "loss": 2.5841, + "learning_rate": 4.632237871674491e-08, + "epoch": 4.779969650986343 + }, + { + "current_steps": 3150, + "loss": 2.2972, + "learning_rate": 4.6009389671361504e-08, + "epoch": 4.781487101669196 + }, + { + "current_steps": 3151, + "loss": 2.6778, + "learning_rate": 4.569640062597809e-08, + "epoch": 4.783004552352049 + }, + { + "current_steps": 3152, + "loss": 2.6718, + "learning_rate": 4.538341158059468e-08, + "epoch": 4.784522003034901 + }, + { + "current_steps": 3153, + "loss": 2.564, + "learning_rate": 4.507042253521127e-08, + "epoch": 4.786039453717754 + }, + { + "current_steps": 3154, + "loss": 2.6495, + "learning_rate": 4.4757433489827855e-08, + "epoch": 4.787556904400607 + }, + { + "current_steps": 3155, + "loss": 2.4842, + "learning_rate": 4.444444444444444e-08, + "epoch": 4.78907435508346 + }, + { + "current_steps": 3156, + "loss": 2.6013, + "learning_rate": 4.4131455399061034e-08, + "epoch": 4.790591805766312 + }, + { + "current_steps": 3157, + "loss": 2.6208, + "learning_rate": 4.381846635367762e-08, + "epoch": 4.792109256449166 + }, + { + "current_steps": 3158, + "loss": 2.6126, + "learning_rate": 4.3505477308294206e-08, + "epoch": 4.793626707132018 + }, + { + "current_steps": 3159, + "loss": 2.4361, + "learning_rate": 4.31924882629108e-08, + "epoch": 4.795144157814871 + }, + { + "current_steps": 3160, + "loss": 2.1047, + "learning_rate": 4.2879499217527385e-08, + "epoch": 4.796661608497724 + }, + { + "current_steps": 3161, + "loss": 2.0062, + "learning_rate": 4.256651017214397e-08, + "epoch": 4.798179059180576 + }, + { + "current_steps": 3162, + "loss": 2.5474, + "learning_rate": 4.2253521126760564e-08, + "epoch": 4.79969650986343 + }, + { + "current_steps": 3163, + "loss": 2.5555, + "learning_rate": 4.194053208137715e-08, + "epoch": 4.801213960546282 + }, + { + "current_steps": 3164, + "loss": 2.5719, + "learning_rate": 4.1627543035993736e-08, + "epoch": 4.802731411229135 + }, + { + "current_steps": 3165, + "loss": 2.3863, + "learning_rate": 4.131455399061032e-08, + "epoch": 4.804248861911988 + }, + { + "current_steps": 3166, + "loss": 2.4713, + "learning_rate": 4.1001564945226915e-08, + "epoch": 4.805766312594841 + }, + { + "current_steps": 3167, + "loss": 2.4573, + "learning_rate": 4.06885758998435e-08, + "epoch": 4.8072837632776935 + }, + { + "current_steps": 3168, + "loss": 2.8503, + "learning_rate": 4.037558685446009e-08, + "epoch": 4.808801213960546 + }, + { + "current_steps": 3169, + "loss": 2.8029, + "learning_rate": 4.006259780907668e-08, + "epoch": 4.810318664643399 + }, + { + "current_steps": 3170, + "loss": 2.5439, + "learning_rate": 3.974960876369327e-08, + "epoch": 4.811836115326252 + }, + { + "current_steps": 3171, + "loss": 2.464, + "learning_rate": 3.943661971830986e-08, + "epoch": 4.813353566009105 + }, + { + "current_steps": 3172, + "loss": 2.5578, + "learning_rate": 3.912363067292645e-08, + "epoch": 4.814871016691957 + }, + { + "current_steps": 3173, + "loss": 2.4684, + "learning_rate": 3.881064162754304e-08, + "epoch": 4.816388467374811 + }, + { + "current_steps": 3174, + "loss": 2.4561, + "learning_rate": 3.8497652582159623e-08, + "epoch": 4.817905918057663 + }, + { + "current_steps": 3175, + "loss": 2.4683, + "learning_rate": 3.818466353677621e-08, + "epoch": 4.819423368740516 + }, + { + "current_steps": 3176, + "loss": 2.5262, + "learning_rate": 3.78716744913928e-08, + "epoch": 4.8209408194233685 + }, + { + "current_steps": 3177, + "loss": 2.811, + "learning_rate": 3.755868544600939e-08, + "epoch": 4.822458270106221 + }, + { + "current_steps": 3178, + "loss": 2.5171, + "learning_rate": 3.7245696400625975e-08, + "epoch": 4.8239757207890746 + }, + { + "current_steps": 3179, + "loss": 2.6772, + "learning_rate": 3.693270735524257e-08, + "epoch": 4.825493171471927 + }, + { + "current_steps": 3180, + "loss": 2.4962, + "learning_rate": 3.6619718309859153e-08, + "epoch": 4.82701062215478 + }, + { + "current_steps": 3181, + "loss": 2.6548, + "learning_rate": 3.630672926447574e-08, + "epoch": 4.828528072837633 + }, + { + "current_steps": 3182, + "loss": 2.4318, + "learning_rate": 3.599374021909233e-08, + "epoch": 4.830045523520486 + }, + { + "current_steps": 3183, + "loss": 2.4988, + "learning_rate": 3.568075117370892e-08, + "epoch": 4.831562974203338 + }, + { + "current_steps": 3184, + "loss": 2.5334, + "learning_rate": 3.5367762128325504e-08, + "epoch": 4.833080424886191 + }, + { + "current_steps": 3185, + "loss": 2.4097, + "learning_rate": 3.505477308294209e-08, + "epoch": 4.8345978755690435 + }, + { + "current_steps": 3186, + "loss": 2.7232, + "learning_rate": 3.474178403755868e-08, + "epoch": 4.836115326251897 + }, + { + "current_steps": 3187, + "loss": 2.6669, + "learning_rate": 3.442879499217527e-08, + "epoch": 4.83763277693475 + }, + { + "current_steps": 3188, + "loss": 2.5014, + "learning_rate": 3.4115805946791856e-08, + "epoch": 4.839150227617602 + }, + { + "current_steps": 3189, + "loss": 2.5367, + "learning_rate": 3.380281690140845e-08, + "epoch": 4.840667678300456 + }, + { + "current_steps": 3190, + "loss": 2.4383, + "learning_rate": 3.348982785602504e-08, + "epoch": 4.842185128983308 + }, + { + "current_steps": 3191, + "loss": 2.5975, + "learning_rate": 3.317683881064163e-08, + "epoch": 4.843702579666161 + }, + { + "current_steps": 3192, + "loss": 2.7816, + "learning_rate": 3.286384976525822e-08, + "epoch": 4.845220030349013 + }, + { + "current_steps": 3193, + "loss": 2.7373, + "learning_rate": 3.2550860719874806e-08, + "epoch": 4.846737481031866 + }, + { + "current_steps": 3194, + "loss": 2.5939, + "learning_rate": 3.223787167449139e-08, + "epoch": 4.848254931714719 + }, + { + "current_steps": 3195, + "loss": 2.6174, + "learning_rate": 3.192488262910798e-08, + "epoch": 4.849772382397572 + }, + { + "current_steps": 3196, + "loss": 2.7251, + "learning_rate": 3.161189358372457e-08, + "epoch": 4.851289833080425 + }, + { + "current_steps": 3197, + "loss": 2.6056, + "learning_rate": 3.129890453834116e-08, + "epoch": 4.852807283763278 + }, + { + "current_steps": 3198, + "loss": 2.6731, + "learning_rate": 3.098591549295774e-08, + "epoch": 4.854324734446131 + }, + { + "current_steps": 3199, + "loss": 2.4129, + "learning_rate": 3.0672926447574336e-08, + "epoch": 4.855842185128983 + }, + { + "current_steps": 3200, + "loss": 2.5097, + "learning_rate": 3.035993740219092e-08, + "epoch": 4.857359635811836 + }, + { + "current_steps": 3201, + "loss": 2.6877, + "learning_rate": 3.004694835680751e-08, + "epoch": 4.858877086494689 + }, + { + "current_steps": 3202, + "loss": 2.804, + "learning_rate": 2.9733959311424098e-08, + "epoch": 4.860394537177542 + }, + { + "current_steps": 3203, + "loss": 2.5958, + "learning_rate": 2.9420970266040687e-08, + "epoch": 4.8619119878603945 + }, + { + "current_steps": 3204, + "loss": 2.4189, + "learning_rate": 2.9107981220657276e-08, + "epoch": 4.863429438543247 + }, + { + "current_steps": 3205, + "loss": 2.3951, + "learning_rate": 2.8794992175273866e-08, + "epoch": 4.8649468892261005 + }, + { + "current_steps": 3206, + "loss": 2.5349, + "learning_rate": 2.8482003129890452e-08, + "epoch": 4.866464339908953 + }, + { + "current_steps": 3207, + "loss": 2.5455, + "learning_rate": 2.816901408450704e-08, + "epoch": 4.867981790591806 + }, + { + "current_steps": 3208, + "loss": 2.6583, + "learning_rate": 2.785602503912363e-08, + "epoch": 4.869499241274658 + }, + { + "current_steps": 3209, + "loss": 2.4414, + "learning_rate": 2.7543035993740217e-08, + "epoch": 4.871016691957512 + }, + { + "current_steps": 3210, + "loss": 2.3626, + "learning_rate": 2.7230046948356806e-08, + "epoch": 4.872534142640364 + }, + { + "current_steps": 3211, + "loss": 2.6347, + "learning_rate": 2.6917057902973392e-08, + "epoch": 4.874051593323217 + }, + { + "current_steps": 3212, + "loss": 2.6792, + "learning_rate": 2.6604068857589982e-08, + "epoch": 4.8755690440060695 + }, + { + "current_steps": 3213, + "loss": 2.4508, + "learning_rate": 2.629107981220657e-08, + "epoch": 4.877086494688923 + }, + { + "current_steps": 3214, + "loss": 2.6584, + "learning_rate": 2.597809076682316e-08, + "epoch": 4.8786039453717756 + }, + { + "current_steps": 3215, + "loss": 2.6155, + "learning_rate": 2.566510172143975e-08, + "epoch": 4.880121396054628 + }, + { + "current_steps": 3216, + "loss": 2.5484, + "learning_rate": 2.5352112676056336e-08, + "epoch": 4.881638846737481 + }, + { + "current_steps": 3217, + "loss": 2.6919, + "learning_rate": 2.5039123630672926e-08, + "epoch": 4.883156297420334 + }, + { + "current_steps": 3218, + "loss": 2.4177, + "learning_rate": 2.4726134585289515e-08, + "epoch": 4.884673748103187 + }, + { + "current_steps": 3219, + "loss": 2.4689, + "learning_rate": 2.44131455399061e-08, + "epoch": 4.886191198786039 + }, + { + "current_steps": 3220, + "loss": 2.5064, + "learning_rate": 2.410015649452269e-08, + "epoch": 4.887708649468892 + }, + { + "current_steps": 3221, + "loss": 2.6758, + "learning_rate": 2.3787167449139277e-08, + "epoch": 4.889226100151745 + }, + { + "current_steps": 3222, + "loss": 2.6201, + "learning_rate": 2.3474178403755866e-08, + "epoch": 4.890743550834598 + }, + { + "current_steps": 3223, + "loss": 2.4595, + "learning_rate": 2.3161189358372456e-08, + "epoch": 4.892261001517451 + }, + { + "current_steps": 3224, + "loss": 2.4977, + "learning_rate": 2.2848200312989045e-08, + "epoch": 4.893778452200303 + }, + { + "current_steps": 3225, + "loss": 2.7359, + "learning_rate": 2.2535211267605634e-08, + "epoch": 4.895295902883157 + }, + { + "current_steps": 3226, + "loss": 2.4727, + "learning_rate": 2.222222222222222e-08, + "epoch": 4.896813353566009 + }, + { + "current_steps": 3227, + "loss": 2.7363, + "learning_rate": 2.190923317683881e-08, + "epoch": 4.898330804248862 + }, + { + "current_steps": 3228, + "loss": 2.5007, + "learning_rate": 2.15962441314554e-08, + "epoch": 4.899848254931714 + }, + { + "current_steps": 3229, + "loss": 2.5058, + "learning_rate": 2.1283255086071985e-08, + "epoch": 4.901365705614568 + }, + { + "current_steps": 3230, + "loss": 2.4789, + "learning_rate": 2.0970266040688575e-08, + "epoch": 4.90288315629742 + }, + { + "current_steps": 3231, + "loss": 2.4936, + "learning_rate": 2.065727699530516e-08, + "epoch": 4.904400606980273 + }, + { + "current_steps": 3232, + "loss": 2.6366, + "learning_rate": 2.034428794992175e-08, + "epoch": 4.905918057663126 + }, + { + "current_steps": 3233, + "loss": 2.6121, + "learning_rate": 2.003129890453834e-08, + "epoch": 4.907435508345979 + }, + { + "current_steps": 3234, + "loss": 2.5837, + "learning_rate": 1.971830985915493e-08, + "epoch": 4.908952959028832 + }, + { + "current_steps": 3235, + "loss": 2.679, + "learning_rate": 1.940532081377152e-08, + "epoch": 4.910470409711684 + }, + { + "current_steps": 3236, + "loss": 2.5189, + "learning_rate": 1.9092331768388105e-08, + "epoch": 4.911987860394537 + }, + { + "current_steps": 3237, + "loss": 2.4327, + "learning_rate": 1.8779342723004694e-08, + "epoch": 4.91350531107739 + }, + { + "current_steps": 3238, + "loss": 2.6021, + "learning_rate": 1.8466353677621284e-08, + "epoch": 4.915022761760243 + }, + { + "current_steps": 3239, + "loss": 2.5649, + "learning_rate": 1.815336463223787e-08, + "epoch": 4.9165402124430955 + }, + { + "current_steps": 3240, + "loss": 2.5218, + "learning_rate": 1.784037558685446e-08, + "epoch": 4.918057663125948 + }, + { + "current_steps": 3241, + "loss": 2.7303, + "learning_rate": 1.7527386541471045e-08, + "epoch": 4.9195751138088015 + }, + { + "current_steps": 3242, + "loss": 2.1451, + "learning_rate": 1.7214397496087635e-08, + "epoch": 4.921092564491654 + }, + { + "current_steps": 3243, + "loss": 2.6651, + "learning_rate": 1.6901408450704224e-08, + "epoch": 4.922610015174507 + }, + { + "current_steps": 3244, + "loss": 2.4061, + "learning_rate": 1.6588419405320814e-08, + "epoch": 4.924127465857359 + }, + { + "current_steps": 3245, + "loss": 2.553, + "learning_rate": 1.6275430359937403e-08, + "epoch": 4.925644916540213 + }, + { + "current_steps": 3246, + "loss": 2.5645, + "learning_rate": 1.596244131455399e-08, + "epoch": 4.927162367223065 + }, + { + "current_steps": 3247, + "loss": 2.2545, + "learning_rate": 1.564945226917058e-08, + "epoch": 4.928679817905918 + }, + { + "current_steps": 3248, + "loss": 2.4864, + "learning_rate": 1.5336463223787168e-08, + "epoch": 4.9301972685887705 + }, + { + "current_steps": 3249, + "loss": 2.3894, + "learning_rate": 1.5023474178403754e-08, + "epoch": 4.931714719271624 + }, + { + "current_steps": 3250, + "loss": 2.573, + "learning_rate": 1.4710485133020343e-08, + "epoch": 4.9332321699544766 + }, + { + "current_steps": 3251, + "loss": 2.62, + "learning_rate": 1.4397496087636933e-08, + "epoch": 4.934749620637329 + }, + { + "current_steps": 3252, + "loss": 2.4349, + "learning_rate": 1.408450704225352e-08, + "epoch": 4.936267071320182 + }, + { + "current_steps": 3253, + "loss": 2.405, + "learning_rate": 1.3771517996870108e-08, + "epoch": 4.937784522003035 + }, + { + "current_steps": 3254, + "loss": 2.5963, + "learning_rate": 1.3458528951486696e-08, + "epoch": 4.939301972685888 + }, + { + "current_steps": 3255, + "loss": 2.4716, + "learning_rate": 1.3145539906103286e-08, + "epoch": 4.94081942336874 + }, + { + "current_steps": 3256, + "loss": 2.5403, + "learning_rate": 1.2832550860719875e-08, + "epoch": 4.942336874051593 + }, + { + "current_steps": 3257, + "loss": 2.6199, + "learning_rate": 1.2519561815336463e-08, + "epoch": 4.943854324734446 + }, + { + "current_steps": 3258, + "loss": 2.6489, + "learning_rate": 1.220657276995305e-08, + "epoch": 4.945371775417299 + }, + { + "current_steps": 3259, + "loss": 2.3673, + "learning_rate": 1.1893583724569638e-08, + "epoch": 4.946889226100152 + }, + { + "current_steps": 3260, + "loss": 2.3638, + "learning_rate": 1.1580594679186228e-08, + "epoch": 4.948406676783004 + }, + { + "current_steps": 3261, + "loss": 2.6567, + "learning_rate": 1.1267605633802817e-08, + "epoch": 4.949924127465858 + }, + { + "current_steps": 3262, + "loss": 2.6394, + "learning_rate": 1.0954616588419405e-08, + "epoch": 4.95144157814871 + }, + { + "current_steps": 3263, + "loss": 2.5653, + "learning_rate": 1.0641627543035993e-08, + "epoch": 4.952959028831563 + }, + { + "current_steps": 3264, + "loss": 2.7724, + "learning_rate": 1.032863849765258e-08, + "epoch": 4.954476479514415 + }, + { + "current_steps": 3265, + "loss": 2.3172, + "learning_rate": 1.001564945226917e-08, + "epoch": 4.955993930197269 + }, + { + "current_steps": 3266, + "loss": 2.5505, + "learning_rate": 9.70266040688576e-09, + "epoch": 4.957511380880121 + }, + { + "current_steps": 3267, + "loss": 2.6118, + "learning_rate": 9.389671361502347e-09, + "epoch": 4.959028831562974 + }, + { + "current_steps": 3268, + "loss": 2.7074, + "learning_rate": 9.076682316118935e-09, + "epoch": 4.9605462822458275 + }, + { + "current_steps": 3269, + "loss": 2.5463, + "learning_rate": 8.763693270735523e-09, + "epoch": 4.96206373292868 + }, + { + "current_steps": 3270, + "loss": 2.636, + "learning_rate": 8.450704225352112e-09, + "epoch": 4.963581183611533 + }, + { + "current_steps": 3271, + "loss": 2.5259, + "learning_rate": 8.137715179968701e-09, + "epoch": 4.965098634294385 + }, + { + "current_steps": 3272, + "loss": 2.471, + "learning_rate": 7.82472613458529e-09, + "epoch": 4.966616084977238 + }, + { + "current_steps": 3273, + "loss": 2.7518, + "learning_rate": 7.511737089201877e-09, + "epoch": 4.968133535660091 + }, + { + "current_steps": 3274, + "loss": 2.4642, + "learning_rate": 7.1987480438184664e-09, + "epoch": 4.969650986342944 + }, + { + "current_steps": 3275, + "loss": 2.4654, + "learning_rate": 6.885758998435054e-09, + "epoch": 4.9711684370257965 + }, + { + "current_steps": 3276, + "loss": 2.7571, + "learning_rate": 6.572769953051643e-09, + "epoch": 4.97268588770865 + }, + { + "current_steps": 3277, + "loss": 2.4181, + "learning_rate": 6.259780907668231e-09, + "epoch": 4.9742033383915025 + }, + { + "current_steps": 3278, + "loss": 2.37, + "learning_rate": 5.946791862284819e-09, + "epoch": 4.975720789074355 + }, + { + "current_steps": 3279, + "loss": 2.5886, + "learning_rate": 5.633802816901409e-09, + "epoch": 4.977238239757208 + }, + { + "current_steps": 3280, + "loss": 2.4197, + "learning_rate": 5.320813771517996e-09, + "epoch": 4.97875569044006 + }, + { + "current_steps": 3281, + "loss": 2.6019, + "learning_rate": 5.007824726134585e-09, + "epoch": 4.980273141122914 + }, + { + "current_steps": 3282, + "loss": 2.4473, + "learning_rate": 4.6948356807511736e-09, + "epoch": 4.981790591805766 + }, + { + "current_steps": 3283, + "loss": 2.4812, + "learning_rate": 4.381846635367761e-09, + "epoch": 4.983308042488619 + }, + { + "current_steps": 3284, + "loss": 2.496, + "learning_rate": 4.068857589984351e-09, + "epoch": 4.984825493171472 + }, + { + "current_steps": 3285, + "loss": 2.1431, + "learning_rate": 3.7558685446009385e-09, + "epoch": 4.986342943854325 + }, + { + "current_steps": 3286, + "loss": 2.4534, + "learning_rate": 3.442879499217527e-09, + "epoch": 4.9878603945371776 + }, + { + "current_steps": 3287, + "loss": 2.5058, + "learning_rate": 3.1298904538341157e-09, + "epoch": 4.98937784522003 + }, + { + "current_steps": 3288, + "loss": 2.4329, + "learning_rate": 2.8169014084507043e-09, + "epoch": 4.990895295902883 + }, + { + "current_steps": 3289, + "loss": 2.8197, + "learning_rate": 2.5039123630672925e-09, + "epoch": 4.992412746585736 + }, + { + "current_steps": 3290, + "loss": 2.1189, + "learning_rate": 2.1909233176838807e-09, + "epoch": 4.993930197268589 + }, + { + "current_steps": 3291, + "loss": 2.5118, + "learning_rate": 1.8779342723004693e-09, + "epoch": 4.995447647951441 + }, + { + "current_steps": 3292, + "loss": 2.2892, + "learning_rate": 1.5649452269170579e-09, + "epoch": 4.996965098634295 + }, + { + "current_steps": 3293, + "loss": 2.5148, + "learning_rate": 1.2519561815336462e-09, + "epoch": 4.998482549317147 + }, + { + "current_steps": 3294, + "loss": 2.3151, + "learning_rate": 9.389671361502346e-10, + "epoch": 5.0 + }, + { + "current_steps": 3294, + "loss": 2.3151, + "learning_rate": 9.389671361502346e-10, + "epoch": 5.0 + } +] \ No newline at end of file