{ "best_metric": null, "best_model_checkpoint": null, "epoch": 1.9996999699969997, "eval_steps": 500, "global_step": 3332, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0006000600060006001, "grad_norm": 38.75798416137695, "learning_rate": 5.9970014992503745e-09, "loss": 1.4595, "step": 1 }, { "epoch": 0.0012001200120012002, "grad_norm": 96.05699920654297, "learning_rate": 1.1994002998500749e-08, "loss": 3.0787, "step": 2 }, { "epoch": 0.0018001800180018, "grad_norm": 76.64619445800781, "learning_rate": 1.7991004497751123e-08, "loss": 1.1194, "step": 3 }, { "epoch": 0.0024002400240024004, "grad_norm": 31.713191986083984, "learning_rate": 2.3988005997001498e-08, "loss": 1.759, "step": 4 }, { "epoch": 0.003000300030003, "grad_norm": 35.938385009765625, "learning_rate": 2.9985007496251873e-08, "loss": 1.8701, "step": 5 }, { "epoch": 0.0036003600360036, "grad_norm": 14.757643699645996, "learning_rate": 3.5982008995502246e-08, "loss": 1.8829, "step": 6 }, { "epoch": 0.0042004200420042, "grad_norm": 55.48692321777344, "learning_rate": 4.1979010494752624e-08, "loss": 1.909, "step": 7 }, { "epoch": 0.004800480048004801, "grad_norm": 41.77190399169922, "learning_rate": 4.7976011994002996e-08, "loss": 1.1174, "step": 8 }, { "epoch": 0.0054005400540054005, "grad_norm": 25.10425567626953, "learning_rate": 5.3973013493253375e-08, "loss": 1.3052, "step": 9 }, { "epoch": 0.006000600060006, "grad_norm": 18.912269592285156, "learning_rate": 5.997001499250375e-08, "loss": 1.2979, "step": 10 }, { "epoch": 0.006600660066006601, "grad_norm": 22.325170516967773, "learning_rate": 6.596701649175413e-08, "loss": 2.226, "step": 11 }, { "epoch": 0.0072007200720072, "grad_norm": 23.70888900756836, "learning_rate": 7.196401799100449e-08, "loss": 1.1857, "step": 12 }, { "epoch": 0.007800780078007801, "grad_norm": 63.343963623046875, "learning_rate": 7.796101949025487e-08, "loss": 2.2046, "step": 13 }, { "epoch": 0.0084008400840084, "grad_norm": 96.36506652832031, "learning_rate": 8.395802098950525e-08, "loss": 2.362, "step": 14 }, { "epoch": 0.009000900090009001, "grad_norm": 56.5931282043457, "learning_rate": 8.995502248875563e-08, "loss": 1.4252, "step": 15 }, { "epoch": 0.009600960096009602, "grad_norm": 67.17568969726562, "learning_rate": 9.595202398800599e-08, "loss": 1.0341, "step": 16 }, { "epoch": 0.0102010201020102, "grad_norm": 52.61793518066406, "learning_rate": 1.0194902548725637e-07, "loss": 1.9016, "step": 17 }, { "epoch": 0.010801080108010801, "grad_norm": 10.97689437866211, "learning_rate": 1.0794602698650675e-07, "loss": 0.7514, "step": 18 }, { "epoch": 0.011401140114011402, "grad_norm": 27.393653869628906, "learning_rate": 1.1394302848575712e-07, "loss": 1.1424, "step": 19 }, { "epoch": 0.012001200120012, "grad_norm": 82.87772369384766, "learning_rate": 1.199400299850075e-07, "loss": 1.2667, "step": 20 }, { "epoch": 0.012601260126012601, "grad_norm": 76.98094940185547, "learning_rate": 1.2593703148425785e-07, "loss": 1.4009, "step": 21 }, { "epoch": 0.013201320132013201, "grad_norm": 46.3062858581543, "learning_rate": 1.3193403298350825e-07, "loss": 2.3306, "step": 22 }, { "epoch": 0.013801380138013802, "grad_norm": 22.549217224121094, "learning_rate": 1.379310344827586e-07, "loss": 1.1142, "step": 23 }, { "epoch": 0.0144014401440144, "grad_norm": 23.56785011291504, "learning_rate": 1.4392803598200898e-07, "loss": 1.9029, "step": 24 }, { "epoch": 0.015001500150015001, "grad_norm": 72.4839859008789, "learning_rate": 1.4992503748125936e-07, "loss": 1.8896, "step": 25 }, { "epoch": 0.015601560156015602, "grad_norm": 23.648746490478516, "learning_rate": 1.5592203898050974e-07, "loss": 1.6197, "step": 26 }, { "epoch": 0.016201620162016202, "grad_norm": 12.512746810913086, "learning_rate": 1.619190404797601e-07, "loss": 1.2592, "step": 27 }, { "epoch": 0.0168016801680168, "grad_norm": 17.471420288085938, "learning_rate": 1.679160419790105e-07, "loss": 1.5116, "step": 28 }, { "epoch": 0.0174017401740174, "grad_norm": 26.91971778869629, "learning_rate": 1.7391304347826085e-07, "loss": 2.0658, "step": 29 }, { "epoch": 0.018001800180018002, "grad_norm": 18.572778701782227, "learning_rate": 1.7991004497751125e-07, "loss": 2.38, "step": 30 }, { "epoch": 0.0186018601860186, "grad_norm": 33.125919342041016, "learning_rate": 1.859070464767616e-07, "loss": 1.283, "step": 31 }, { "epoch": 0.019201920192019203, "grad_norm": 16.327001571655273, "learning_rate": 1.9190404797601199e-07, "loss": 1.5216, "step": 32 }, { "epoch": 0.019801980198019802, "grad_norm": 10.471918106079102, "learning_rate": 1.9790104947526236e-07, "loss": 1.2493, "step": 33 }, { "epoch": 0.0204020402040204, "grad_norm": 20.844749450683594, "learning_rate": 2.0389805097451274e-07, "loss": 1.4903, "step": 34 }, { "epoch": 0.021002100210021003, "grad_norm": 15.855977058410645, "learning_rate": 2.098950524737631e-07, "loss": 1.9633, "step": 35 }, { "epoch": 0.021602160216021602, "grad_norm": 10.36643123626709, "learning_rate": 2.158920539730135e-07, "loss": 0.9556, "step": 36 }, { "epoch": 0.0222022202220222, "grad_norm": 21.997859954833984, "learning_rate": 2.2188905547226385e-07, "loss": 1.7223, "step": 37 }, { "epoch": 0.022802280228022803, "grad_norm": 10.40003776550293, "learning_rate": 2.2788605697151423e-07, "loss": 0.8939, "step": 38 }, { "epoch": 0.023402340234023402, "grad_norm": 11.553383827209473, "learning_rate": 2.338830584707646e-07, "loss": 1.5977, "step": 39 }, { "epoch": 0.024002400240024, "grad_norm": 13.087713241577148, "learning_rate": 2.39880059970015e-07, "loss": 1.2661, "step": 40 }, { "epoch": 0.024602460246024603, "grad_norm": 15.043306350708008, "learning_rate": 2.4587706146926537e-07, "loss": 2.017, "step": 41 }, { "epoch": 0.025202520252025202, "grad_norm": 17.3659725189209, "learning_rate": 2.518740629685157e-07, "loss": 1.7496, "step": 42 }, { "epoch": 0.025802580258025804, "grad_norm": 12.616116523742676, "learning_rate": 2.578710644677661e-07, "loss": 1.1949, "step": 43 }, { "epoch": 0.026402640264026403, "grad_norm": 12.659695625305176, "learning_rate": 2.638680659670165e-07, "loss": 1.1851, "step": 44 }, { "epoch": 0.027002700270027002, "grad_norm": 10.053406715393066, "learning_rate": 2.698650674662669e-07, "loss": 1.445, "step": 45 }, { "epoch": 0.027602760276027604, "grad_norm": 10.80860424041748, "learning_rate": 2.758620689655172e-07, "loss": 1.0659, "step": 46 }, { "epoch": 0.028202820282028203, "grad_norm": 13.7864990234375, "learning_rate": 2.818590704647676e-07, "loss": 2.1798, "step": 47 }, { "epoch": 0.0288028802880288, "grad_norm": 8.64850902557373, "learning_rate": 2.8785607196401796e-07, "loss": 0.6225, "step": 48 }, { "epoch": 0.029402940294029404, "grad_norm": 10.947604179382324, "learning_rate": 2.938530734632684e-07, "loss": 1.0932, "step": 49 }, { "epoch": 0.030003000300030003, "grad_norm": 12.049171447753906, "learning_rate": 2.998500749625187e-07, "loss": 1.3051, "step": 50 }, { "epoch": 0.0306030603060306, "grad_norm": 12.312448501586914, "learning_rate": 3.058470764617691e-07, "loss": 1.1293, "step": 51 }, { "epoch": 0.031203120312031204, "grad_norm": 10.2683687210083, "learning_rate": 3.118440779610195e-07, "loss": 0.8987, "step": 52 }, { "epoch": 0.0318031803180318, "grad_norm": 17.92226219177246, "learning_rate": 3.1784107946026986e-07, "loss": 1.6247, "step": 53 }, { "epoch": 0.032403240324032405, "grad_norm": 14.44575023651123, "learning_rate": 3.238380809595202e-07, "loss": 1.2135, "step": 54 }, { "epoch": 0.033003300330033, "grad_norm": 10.595660209655762, "learning_rate": 3.298350824587706e-07, "loss": 1.0651, "step": 55 }, { "epoch": 0.0336033603360336, "grad_norm": 12.00365161895752, "learning_rate": 3.35832083958021e-07, "loss": 0.9382, "step": 56 }, { "epoch": 0.034203420342034205, "grad_norm": 15.441823959350586, "learning_rate": 3.4182908545727137e-07, "loss": 1.2882, "step": 57 }, { "epoch": 0.0348034803480348, "grad_norm": 9.533059120178223, "learning_rate": 3.478260869565217e-07, "loss": 0.7565, "step": 58 }, { "epoch": 0.0354035403540354, "grad_norm": 6.318301200866699, "learning_rate": 3.538230884557721e-07, "loss": 0.3622, "step": 59 }, { "epoch": 0.036003600360036005, "grad_norm": 15.483139038085938, "learning_rate": 3.598200899550225e-07, "loss": 1.4072, "step": 60 }, { "epoch": 0.03660366036603661, "grad_norm": 10.341728210449219, "learning_rate": 3.658170914542729e-07, "loss": 1.2788, "step": 61 }, { "epoch": 0.0372037203720372, "grad_norm": 11.826828956604004, "learning_rate": 3.718140929535232e-07, "loss": 1.3286, "step": 62 }, { "epoch": 0.037803780378037805, "grad_norm": 12.155770301818848, "learning_rate": 3.778110944527736e-07, "loss": 1.1012, "step": 63 }, { "epoch": 0.03840384038403841, "grad_norm": 8.564728736877441, "learning_rate": 3.8380809595202397e-07, "loss": 0.5955, "step": 64 }, { "epoch": 0.039003900390039, "grad_norm": 10.083395004272461, "learning_rate": 3.8980509745127435e-07, "loss": 0.8961, "step": 65 }, { "epoch": 0.039603960396039604, "grad_norm": 37.70561981201172, "learning_rate": 3.9580209895052473e-07, "loss": 1.1213, "step": 66 }, { "epoch": 0.04020402040204021, "grad_norm": 13.810218811035156, "learning_rate": 4.017991004497751e-07, "loss": 0.7689, "step": 67 }, { "epoch": 0.0408040804080408, "grad_norm": 12.071134567260742, "learning_rate": 4.077961019490255e-07, "loss": 1.3754, "step": 68 }, { "epoch": 0.041404140414041404, "grad_norm": 8.201019287109375, "learning_rate": 4.1379310344827586e-07, "loss": 1.3238, "step": 69 }, { "epoch": 0.04200420042004201, "grad_norm": 11.849881172180176, "learning_rate": 4.197901049475262e-07, "loss": 0.8373, "step": 70 }, { "epoch": 0.0426042604260426, "grad_norm": 8.053994178771973, "learning_rate": 4.2578710644677657e-07, "loss": 0.587, "step": 71 }, { "epoch": 0.043204320432043204, "grad_norm": 9.343356132507324, "learning_rate": 4.31784107946027e-07, "loss": 0.822, "step": 72 }, { "epoch": 0.043804380438043806, "grad_norm": 8.319597244262695, "learning_rate": 4.377811094452774e-07, "loss": 0.5586, "step": 73 }, { "epoch": 0.0444044404440444, "grad_norm": 94.48623657226562, "learning_rate": 4.437781109445277e-07, "loss": 0.8654, "step": 74 }, { "epoch": 0.045004500450045004, "grad_norm": 10.176705360412598, "learning_rate": 4.497751124437781e-07, "loss": 1.0933, "step": 75 }, { "epoch": 0.045604560456045606, "grad_norm": 9.45789909362793, "learning_rate": 4.5577211394302846e-07, "loss": 0.7781, "step": 76 }, { "epoch": 0.0462046204620462, "grad_norm": 9.251814842224121, "learning_rate": 4.617691154422789e-07, "loss": 0.8394, "step": 77 }, { "epoch": 0.046804680468046804, "grad_norm": 8.508570671081543, "learning_rate": 4.677661169415292e-07, "loss": 0.727, "step": 78 }, { "epoch": 0.047404740474047406, "grad_norm": 12.958025932312012, "learning_rate": 4.737631184407796e-07, "loss": 0.5958, "step": 79 }, { "epoch": 0.048004800480048, "grad_norm": 10.419230461120605, "learning_rate": 4.7976011994003e-07, "loss": 0.8899, "step": 80 }, { "epoch": 0.048604860486048604, "grad_norm": 7.24143648147583, "learning_rate": 4.857571214392804e-07, "loss": 0.4877, "step": 81 }, { "epoch": 0.049204920492049206, "grad_norm": 14.3858003616333, "learning_rate": 4.917541229385307e-07, "loss": 1.2204, "step": 82 }, { "epoch": 0.04980498049804981, "grad_norm": 11.641541481018066, "learning_rate": 4.977511244377811e-07, "loss": 1.7632, "step": 83 }, { "epoch": 0.050405040504050404, "grad_norm": 10.203290939331055, "learning_rate": 5.037481259370314e-07, "loss": 0.8557, "step": 84 }, { "epoch": 0.051005100510051006, "grad_norm": 13.580658912658691, "learning_rate": 5.097451274362819e-07, "loss": 1.5538, "step": 85 }, { "epoch": 0.05160516051605161, "grad_norm": 8.561590194702148, "learning_rate": 5.157421289355322e-07, "loss": 1.1043, "step": 86 }, { "epoch": 0.052205220522052204, "grad_norm": 13.375717163085938, "learning_rate": 5.217391304347825e-07, "loss": 1.6642, "step": 87 }, { "epoch": 0.052805280528052806, "grad_norm": 8.091734886169434, "learning_rate": 5.27736131934033e-07, "loss": 0.7061, "step": 88 }, { "epoch": 0.05340534053405341, "grad_norm": 11.869145393371582, "learning_rate": 5.337331334332833e-07, "loss": 1.1912, "step": 89 }, { "epoch": 0.054005400540054004, "grad_norm": 9.191502571105957, "learning_rate": 5.397301349325338e-07, "loss": 0.638, "step": 90 }, { "epoch": 0.054605460546054606, "grad_norm": 14.66004753112793, "learning_rate": 5.45727136431784e-07, "loss": 1.3821, "step": 91 }, { "epoch": 0.05520552055205521, "grad_norm": 10.292122840881348, "learning_rate": 5.517241379310344e-07, "loss": 1.3274, "step": 92 }, { "epoch": 0.0558055805580558, "grad_norm": 8.960094451904297, "learning_rate": 5.577211394302849e-07, "loss": 0.5044, "step": 93 }, { "epoch": 0.056405640564056406, "grad_norm": 11.916205406188965, "learning_rate": 5.637181409295352e-07, "loss": 0.8245, "step": 94 }, { "epoch": 0.05700570057005701, "grad_norm": 11.27638053894043, "learning_rate": 5.697151424287855e-07, "loss": 0.8069, "step": 95 }, { "epoch": 0.0576057605760576, "grad_norm": 9.1249418258667, "learning_rate": 5.757121439280359e-07, "loss": 1.2682, "step": 96 }, { "epoch": 0.058205820582058206, "grad_norm": 8.240825653076172, "learning_rate": 5.817091454272863e-07, "loss": 0.5111, "step": 97 }, { "epoch": 0.05880588058805881, "grad_norm": 7.478789329528809, "learning_rate": 5.877061469265368e-07, "loss": 0.8843, "step": 98 }, { "epoch": 0.0594059405940594, "grad_norm": 8.775347709655762, "learning_rate": 5.937031484257871e-07, "loss": 0.5697, "step": 99 }, { "epoch": 0.060006000600060005, "grad_norm": 8.725658416748047, "learning_rate": 5.997001499250374e-07, "loss": 0.4685, "step": 100 }, { "epoch": 0.06060606060606061, "grad_norm": 9.164617538452148, "learning_rate": 6.056971514242878e-07, "loss": 0.587, "step": 101 }, { "epoch": 0.0612061206120612, "grad_norm": 9.725695610046387, "learning_rate": 6.116941529235382e-07, "loss": 0.9675, "step": 102 }, { "epoch": 0.061806180618061805, "grad_norm": 8.608172416687012, "learning_rate": 6.176911544227886e-07, "loss": 0.5436, "step": 103 }, { "epoch": 0.06240624062406241, "grad_norm": 8.208645820617676, "learning_rate": 6.23688155922039e-07, "loss": 0.5425, "step": 104 }, { "epoch": 0.063006300630063, "grad_norm": 9.499127388000488, "learning_rate": 6.296851574212893e-07, "loss": 0.6275, "step": 105 }, { "epoch": 0.0636063606360636, "grad_norm": 8.421340942382812, "learning_rate": 6.356821589205397e-07, "loss": 0.7017, "step": 106 }, { "epoch": 0.06420642064206421, "grad_norm": 8.829547882080078, "learning_rate": 6.416791604197901e-07, "loss": 0.5713, "step": 107 }, { "epoch": 0.06480648064806481, "grad_norm": 9.433995246887207, "learning_rate": 6.476761619190404e-07, "loss": 0.8124, "step": 108 }, { "epoch": 0.06540654065406541, "grad_norm": 11.59047794342041, "learning_rate": 6.536731634182909e-07, "loss": 0.5359, "step": 109 }, { "epoch": 0.066006600660066, "grad_norm": 7.573402404785156, "learning_rate": 6.596701649175412e-07, "loss": 0.5801, "step": 110 }, { "epoch": 0.0666066606660666, "grad_norm": 9.75740909576416, "learning_rate": 6.656671664167915e-07, "loss": 0.6464, "step": 111 }, { "epoch": 0.0672067206720672, "grad_norm": 7.501075267791748, "learning_rate": 6.71664167916042e-07, "loss": 0.5877, "step": 112 }, { "epoch": 0.06780678067806781, "grad_norm": 11.004350662231445, "learning_rate": 6.776611694152923e-07, "loss": 0.8027, "step": 113 }, { "epoch": 0.06840684068406841, "grad_norm": 9.127866744995117, "learning_rate": 6.836581709145427e-07, "loss": 0.4756, "step": 114 }, { "epoch": 0.06900690069006901, "grad_norm": 15.087956428527832, "learning_rate": 6.896551724137931e-07, "loss": 0.8714, "step": 115 }, { "epoch": 0.0696069606960696, "grad_norm": 8.250901222229004, "learning_rate": 6.956521739130434e-07, "loss": 0.4716, "step": 116 }, { "epoch": 0.0702070207020702, "grad_norm": 8.587376594543457, "learning_rate": 7.016491754122939e-07, "loss": 0.7369, "step": 117 }, { "epoch": 0.0708070807080708, "grad_norm": 11.42739486694336, "learning_rate": 7.076461769115442e-07, "loss": 0.5832, "step": 118 }, { "epoch": 0.07140714071407141, "grad_norm": 6.737912178039551, "learning_rate": 7.136431784107945e-07, "loss": 0.3928, "step": 119 }, { "epoch": 0.07200720072007201, "grad_norm": 7.417272090911865, "learning_rate": 7.19640179910045e-07, "loss": 0.5714, "step": 120 }, { "epoch": 0.07260726072607261, "grad_norm": 13.454451560974121, "learning_rate": 7.256371814092953e-07, "loss": 1.1646, "step": 121 }, { "epoch": 0.07320732073207321, "grad_norm": 6.8842997550964355, "learning_rate": 7.316341829085458e-07, "loss": 0.4471, "step": 122 }, { "epoch": 0.0738073807380738, "grad_norm": 8.181236267089844, "learning_rate": 7.37631184407796e-07, "loss": 0.5131, "step": 123 }, { "epoch": 0.0744074407440744, "grad_norm": 9.143996238708496, "learning_rate": 7.436281859070464e-07, "loss": 0.6176, "step": 124 }, { "epoch": 0.075007500750075, "grad_norm": 7.457053184509277, "learning_rate": 7.496251874062968e-07, "loss": 0.6493, "step": 125 }, { "epoch": 0.07560756075607561, "grad_norm": 12.07157039642334, "learning_rate": 7.556221889055472e-07, "loss": 0.9848, "step": 126 }, { "epoch": 0.07620762076207621, "grad_norm": 9.06683349609375, "learning_rate": 7.616191904047976e-07, "loss": 0.7751, "step": 127 }, { "epoch": 0.07680768076807681, "grad_norm": 6.484456539154053, "learning_rate": 7.676161919040479e-07, "loss": 0.4148, "step": 128 }, { "epoch": 0.0774077407740774, "grad_norm": 7.918304443359375, "learning_rate": 7.736131934032983e-07, "loss": 0.5498, "step": 129 }, { "epoch": 0.078007800780078, "grad_norm": 9.680126190185547, "learning_rate": 7.796101949025487e-07, "loss": 0.5261, "step": 130 }, { "epoch": 0.0786078607860786, "grad_norm": 11.818037986755371, "learning_rate": 7.856071964017991e-07, "loss": 1.1456, "step": 131 }, { "epoch": 0.07920792079207921, "grad_norm": 11.6779203414917, "learning_rate": 7.916041979010495e-07, "loss": 0.71, "step": 132 }, { "epoch": 0.07980798079807981, "grad_norm": 7.6779704093933105, "learning_rate": 7.976011994002998e-07, "loss": 0.4777, "step": 133 }, { "epoch": 0.08040804080408041, "grad_norm": 9.836710929870605, "learning_rate": 8.035982008995502e-07, "loss": 0.7281, "step": 134 }, { "epoch": 0.081008100810081, "grad_norm": 8.52563190460205, "learning_rate": 8.095952023988005e-07, "loss": 0.5691, "step": 135 }, { "epoch": 0.0816081608160816, "grad_norm": 6.298959732055664, "learning_rate": 8.15592203898051e-07, "loss": 0.5089, "step": 136 }, { "epoch": 0.0822082208220822, "grad_norm": 7.496734619140625, "learning_rate": 8.215892053973013e-07, "loss": 0.5282, "step": 137 }, { "epoch": 0.08280828082808281, "grad_norm": 10.532139778137207, "learning_rate": 8.275862068965517e-07, "loss": 0.5391, "step": 138 }, { "epoch": 0.08340834083408341, "grad_norm": 8.185991287231445, "learning_rate": 8.335832083958021e-07, "loss": 0.5971, "step": 139 }, { "epoch": 0.08400840084008401, "grad_norm": 8.296850204467773, "learning_rate": 8.395802098950524e-07, "loss": 0.6586, "step": 140 }, { "epoch": 0.0846084608460846, "grad_norm": 9.95767879486084, "learning_rate": 8.455772113943029e-07, "loss": 0.5997, "step": 141 }, { "epoch": 0.0852085208520852, "grad_norm": 9.168537139892578, "learning_rate": 8.515742128935531e-07, "loss": 0.8687, "step": 142 }, { "epoch": 0.0858085808580858, "grad_norm": 10.611588478088379, "learning_rate": 8.575712143928035e-07, "loss": 0.6814, "step": 143 }, { "epoch": 0.08640864086408641, "grad_norm": 8.318461418151855, "learning_rate": 8.63568215892054e-07, "loss": 0.8798, "step": 144 }, { "epoch": 0.08700870087008701, "grad_norm": 8.69716739654541, "learning_rate": 8.695652173913043e-07, "loss": 0.5963, "step": 145 }, { "epoch": 0.08760876087608761, "grad_norm": 9.090896606445312, "learning_rate": 8.755622188905548e-07, "loss": 0.6173, "step": 146 }, { "epoch": 0.08820882088208822, "grad_norm": 7.795445919036865, "learning_rate": 8.81559220389805e-07, "loss": 0.6956, "step": 147 }, { "epoch": 0.0888088808880888, "grad_norm": 6.203002452850342, "learning_rate": 8.875562218890554e-07, "loss": 0.5308, "step": 148 }, { "epoch": 0.0894089408940894, "grad_norm": 6.037863254547119, "learning_rate": 8.935532233883059e-07, "loss": 0.444, "step": 149 }, { "epoch": 0.09000900090009001, "grad_norm": 8.099892616271973, "learning_rate": 8.995502248875562e-07, "loss": 0.3992, "step": 150 }, { "epoch": 0.09060906090609061, "grad_norm": 7.160818576812744, "learning_rate": 9.055472263868065e-07, "loss": 0.5224, "step": 151 }, { "epoch": 0.09120912091209121, "grad_norm": 8.059781074523926, "learning_rate": 9.115442278860569e-07, "loss": 0.3335, "step": 152 }, { "epoch": 0.09180918091809182, "grad_norm": 9.989950180053711, "learning_rate": 9.175412293853073e-07, "loss": 0.4364, "step": 153 }, { "epoch": 0.0924092409240924, "grad_norm": 10.935335159301758, "learning_rate": 9.235382308845578e-07, "loss": 1.1819, "step": 154 }, { "epoch": 0.093009300930093, "grad_norm": 5.924015998840332, "learning_rate": 9.295352323838081e-07, "loss": 0.5241, "step": 155 }, { "epoch": 0.09360936093609361, "grad_norm": 5.291107177734375, "learning_rate": 9.355322338830584e-07, "loss": 0.4067, "step": 156 }, { "epoch": 0.09420942094209421, "grad_norm": 8.815766334533691, "learning_rate": 9.415292353823088e-07, "loss": 0.6009, "step": 157 }, { "epoch": 0.09480948094809481, "grad_norm": 7.753774642944336, "learning_rate": 9.475262368815592e-07, "loss": 0.6285, "step": 158 }, { "epoch": 0.09540954095409541, "grad_norm": 6.81179666519165, "learning_rate": 9.535232383808095e-07, "loss": 0.5815, "step": 159 }, { "epoch": 0.096009600960096, "grad_norm": 8.917765617370605, "learning_rate": 9.5952023988006e-07, "loss": 0.5882, "step": 160 }, { "epoch": 0.0966096609660966, "grad_norm": 5.107661247253418, "learning_rate": 9.655172413793103e-07, "loss": 0.2916, "step": 161 }, { "epoch": 0.09720972097209721, "grad_norm": 6.919626712799072, "learning_rate": 9.715142428785607e-07, "loss": 0.4641, "step": 162 }, { "epoch": 0.09780978097809781, "grad_norm": 7.785377025604248, "learning_rate": 9.77511244377811e-07, "loss": 0.5598, "step": 163 }, { "epoch": 0.09840984098409841, "grad_norm": 9.031327247619629, "learning_rate": 9.835082458770615e-07, "loss": 0.9036, "step": 164 }, { "epoch": 0.09900990099009901, "grad_norm": 9.290095329284668, "learning_rate": 9.895052473763118e-07, "loss": 0.5777, "step": 165 }, { "epoch": 0.09960996099609962, "grad_norm": 5.601505756378174, "learning_rate": 9.955022488755622e-07, "loss": 0.4318, "step": 166 }, { "epoch": 0.1002100210021002, "grad_norm": 8.431084632873535, "learning_rate": 1.0014992503748126e-06, "loss": 0.5867, "step": 167 }, { "epoch": 0.10081008100810081, "grad_norm": 9.108281135559082, "learning_rate": 1.0074962518740628e-06, "loss": 0.7197, "step": 168 }, { "epoch": 0.10141014101410141, "grad_norm": 10.175450325012207, "learning_rate": 1.0134932533733134e-06, "loss": 1.0207, "step": 169 }, { "epoch": 0.10201020102010201, "grad_norm": 7.984658718109131, "learning_rate": 1.0194902548725637e-06, "loss": 0.7823, "step": 170 }, { "epoch": 0.10261026102610261, "grad_norm": 8.058226585388184, "learning_rate": 1.025487256371814e-06, "loss": 0.4207, "step": 171 }, { "epoch": 0.10321032103210322, "grad_norm": 8.923624038696289, "learning_rate": 1.0314842578710645e-06, "loss": 0.8983, "step": 172 }, { "epoch": 0.1038103810381038, "grad_norm": 5.7458086013793945, "learning_rate": 1.0374812593703149e-06, "loss": 0.7088, "step": 173 }, { "epoch": 0.10441044104410441, "grad_norm": 6.782958030700684, "learning_rate": 1.043478260869565e-06, "loss": 0.6263, "step": 174 }, { "epoch": 0.10501050105010501, "grad_norm": 7.866609573364258, "learning_rate": 1.0494752623688154e-06, "loss": 0.5914, "step": 175 }, { "epoch": 0.10561056105610561, "grad_norm": 9.421751022338867, "learning_rate": 1.055472263868066e-06, "loss": 0.6869, "step": 176 }, { "epoch": 0.10621062106210621, "grad_norm": 9.969465255737305, "learning_rate": 1.0614692653673164e-06, "loss": 0.6217, "step": 177 }, { "epoch": 0.10681068106810682, "grad_norm": 10.541023254394531, "learning_rate": 1.0674662668665666e-06, "loss": 0.4619, "step": 178 }, { "epoch": 0.1074107410741074, "grad_norm": 8.102727890014648, "learning_rate": 1.0734632683658171e-06, "loss": 0.4457, "step": 179 }, { "epoch": 0.10801080108010801, "grad_norm": 6.7405219078063965, "learning_rate": 1.0794602698650675e-06, "loss": 0.4294, "step": 180 }, { "epoch": 0.10861086108610861, "grad_norm": 6.245920181274414, "learning_rate": 1.0854572713643177e-06, "loss": 0.3183, "step": 181 }, { "epoch": 0.10921092109210921, "grad_norm": 9.078633308410645, "learning_rate": 1.091454272863568e-06, "loss": 0.4801, "step": 182 }, { "epoch": 0.10981098109810981, "grad_norm": 4.423070907592773, "learning_rate": 1.0974512743628187e-06, "loss": 0.6532, "step": 183 }, { "epoch": 0.11041104110411042, "grad_norm": 7.858838081359863, "learning_rate": 1.1034482758620688e-06, "loss": 0.7436, "step": 184 }, { "epoch": 0.111011101110111, "grad_norm": 7.4374308586120605, "learning_rate": 1.1094452773613192e-06, "loss": 0.5568, "step": 185 }, { "epoch": 0.1116111611161116, "grad_norm": 6.039358615875244, "learning_rate": 1.1154422788605698e-06, "loss": 0.6455, "step": 186 }, { "epoch": 0.11221122112211221, "grad_norm": 6.043375492095947, "learning_rate": 1.12143928035982e-06, "loss": 0.449, "step": 187 }, { "epoch": 0.11281128112811281, "grad_norm": 9.298956871032715, "learning_rate": 1.1274362818590703e-06, "loss": 0.6884, "step": 188 }, { "epoch": 0.11341134113411341, "grad_norm": 11.00761604309082, "learning_rate": 1.133433283358321e-06, "loss": 0.6352, "step": 189 }, { "epoch": 0.11401140114011402, "grad_norm": 8.144611358642578, "learning_rate": 1.139430284857571e-06, "loss": 1.064, "step": 190 }, { "epoch": 0.11461146114611462, "grad_norm": 4.678433418273926, "learning_rate": 1.1454272863568215e-06, "loss": 0.3162, "step": 191 }, { "epoch": 0.1152115211521152, "grad_norm": 5.907443046569824, "learning_rate": 1.1514242878560719e-06, "loss": 0.5543, "step": 192 }, { "epoch": 0.11581158115811581, "grad_norm": 7.839261531829834, "learning_rate": 1.1574212893553224e-06, "loss": 0.4757, "step": 193 }, { "epoch": 0.11641164116411641, "grad_norm": 6.886834621429443, "learning_rate": 1.1634182908545726e-06, "loss": 0.6722, "step": 194 }, { "epoch": 0.11701170117011701, "grad_norm": 7.057409763336182, "learning_rate": 1.169415292353823e-06, "loss": 0.4867, "step": 195 }, { "epoch": 0.11761176117611762, "grad_norm": 6.749741554260254, "learning_rate": 1.1754122938530736e-06, "loss": 0.3998, "step": 196 }, { "epoch": 0.11821182118211822, "grad_norm": 8.023545265197754, "learning_rate": 1.1814092953523238e-06, "loss": 0.5104, "step": 197 }, { "epoch": 0.1188118811881188, "grad_norm": 6.353607654571533, "learning_rate": 1.1874062968515741e-06, "loss": 0.385, "step": 198 }, { "epoch": 0.11941194119411941, "grad_norm": 6.9470720291137695, "learning_rate": 1.1934032983508245e-06, "loss": 0.4368, "step": 199 }, { "epoch": 0.12001200120012001, "grad_norm": 4.995361328125, "learning_rate": 1.1994002998500749e-06, "loss": 0.4022, "step": 200 }, { "epoch": 0.12061206120612061, "grad_norm": 6.597985744476318, "learning_rate": 1.2053973013493253e-06, "loss": 0.6549, "step": 201 }, { "epoch": 0.12121212121212122, "grad_norm": 5.109239101409912, "learning_rate": 1.2113943028485756e-06, "loss": 0.3842, "step": 202 }, { "epoch": 0.12181218121812182, "grad_norm": 4.355035305023193, "learning_rate": 1.217391304347826e-06, "loss": 0.2821, "step": 203 }, { "epoch": 0.1224122412241224, "grad_norm": 5.6934003829956055, "learning_rate": 1.2233883058470764e-06, "loss": 0.3532, "step": 204 }, { "epoch": 0.12301230123012301, "grad_norm": 6.769897937774658, "learning_rate": 1.2293853073463268e-06, "loss": 0.3655, "step": 205 }, { "epoch": 0.12361236123612361, "grad_norm": 9.073859214782715, "learning_rate": 1.2353823088455772e-06, "loss": 0.6125, "step": 206 }, { "epoch": 0.12421242124212421, "grad_norm": 4.498748779296875, "learning_rate": 1.2413793103448275e-06, "loss": 0.3419, "step": 207 }, { "epoch": 0.12481248124812482, "grad_norm": 9.100799560546875, "learning_rate": 1.247376311844078e-06, "loss": 0.6314, "step": 208 }, { "epoch": 0.1254125412541254, "grad_norm": 7.444416522979736, "learning_rate": 1.253373313343328e-06, "loss": 0.4461, "step": 209 }, { "epoch": 0.126012601260126, "grad_norm": 7.765754699707031, "learning_rate": 1.2593703148425787e-06, "loss": 0.8715, "step": 210 }, { "epoch": 0.1266126612661266, "grad_norm": 6.605568885803223, "learning_rate": 1.265367316341829e-06, "loss": 0.5597, "step": 211 }, { "epoch": 0.1272127212721272, "grad_norm": 8.170440673828125, "learning_rate": 1.2713643178410794e-06, "loss": 0.5912, "step": 212 }, { "epoch": 0.1278127812781278, "grad_norm": 6.070854187011719, "learning_rate": 1.2773613193403298e-06, "loss": 0.4145, "step": 213 }, { "epoch": 0.12841284128412842, "grad_norm": 6.472310543060303, "learning_rate": 1.2833583208395802e-06, "loss": 0.7263, "step": 214 }, { "epoch": 0.12901290129012902, "grad_norm": 9.498833656311035, "learning_rate": 1.2893553223388306e-06, "loss": 0.9088, "step": 215 }, { "epoch": 0.12961296129612962, "grad_norm": 5.823427200317383, "learning_rate": 1.2953523238380807e-06, "loss": 0.3759, "step": 216 }, { "epoch": 0.13021302130213022, "grad_norm": 7.136300086975098, "learning_rate": 1.3013493253373313e-06, "loss": 0.599, "step": 217 }, { "epoch": 0.13081308130813082, "grad_norm": 9.19075870513916, "learning_rate": 1.3073463268365817e-06, "loss": 0.51, "step": 218 }, { "epoch": 0.13141314131413143, "grad_norm": 4.563392162322998, "learning_rate": 1.3133433283358319e-06, "loss": 0.3067, "step": 219 }, { "epoch": 0.132013201320132, "grad_norm": 8.576509475708008, "learning_rate": 1.3193403298350825e-06, "loss": 0.737, "step": 220 }, { "epoch": 0.1326132613261326, "grad_norm": 6.369603157043457, "learning_rate": 1.3253373313343328e-06, "loss": 0.4102, "step": 221 }, { "epoch": 0.1332133213321332, "grad_norm": 9.836021423339844, "learning_rate": 1.331334332833583e-06, "loss": 1.4195, "step": 222 }, { "epoch": 0.1338133813381338, "grad_norm": 6.055652141571045, "learning_rate": 1.3373313343328336e-06, "loss": 0.3502, "step": 223 }, { "epoch": 0.1344134413441344, "grad_norm": 7.641057014465332, "learning_rate": 1.343328335832084e-06, "loss": 0.5708, "step": 224 }, { "epoch": 0.135013501350135, "grad_norm": 7.476957321166992, "learning_rate": 1.3493253373313341e-06, "loss": 0.8824, "step": 225 }, { "epoch": 0.13561356135613561, "grad_norm": 6.457795143127441, "learning_rate": 1.3553223388305845e-06, "loss": 0.5423, "step": 226 }, { "epoch": 0.13621362136213622, "grad_norm": 4.067301273345947, "learning_rate": 1.3613193403298351e-06, "loss": 0.3493, "step": 227 }, { "epoch": 0.13681368136813682, "grad_norm": 5.405187606811523, "learning_rate": 1.3673163418290855e-06, "loss": 0.3916, "step": 228 }, { "epoch": 0.13741374137413742, "grad_norm": 5.908392429351807, "learning_rate": 1.3733133433283357e-06, "loss": 0.4348, "step": 229 }, { "epoch": 0.13801380138013802, "grad_norm": 6.958424091339111, "learning_rate": 1.3793103448275862e-06, "loss": 0.5541, "step": 230 }, { "epoch": 0.13861386138613863, "grad_norm": 4.8336381912231445, "learning_rate": 1.3853073463268366e-06, "loss": 0.3296, "step": 231 }, { "epoch": 0.1392139213921392, "grad_norm": 5.461909294128418, "learning_rate": 1.3913043478260868e-06, "loss": 0.2748, "step": 232 }, { "epoch": 0.1398139813981398, "grad_norm": 6.6668620109558105, "learning_rate": 1.3973013493253372e-06, "loss": 0.5, "step": 233 }, { "epoch": 0.1404140414041404, "grad_norm": 5.634387493133545, "learning_rate": 1.4032983508245878e-06, "loss": 0.5903, "step": 234 }, { "epoch": 0.141014101410141, "grad_norm": 7.218358516693115, "learning_rate": 1.409295352323838e-06, "loss": 0.5973, "step": 235 }, { "epoch": 0.1416141614161416, "grad_norm": 8.532759666442871, "learning_rate": 1.4152923538230883e-06, "loss": 1.0169, "step": 236 }, { "epoch": 0.1422142214221422, "grad_norm": 6.3129472732543945, "learning_rate": 1.421289355322339e-06, "loss": 0.2753, "step": 237 }, { "epoch": 0.14281428142814281, "grad_norm": 5.4125542640686035, "learning_rate": 1.427286356821589e-06, "loss": 0.3043, "step": 238 }, { "epoch": 0.14341434143414342, "grad_norm": 3.3531265258789062, "learning_rate": 1.4332833583208394e-06, "loss": 0.265, "step": 239 }, { "epoch": 0.14401440144014402, "grad_norm": 4.848817825317383, "learning_rate": 1.43928035982009e-06, "loss": 0.5623, "step": 240 }, { "epoch": 0.14461446144614462, "grad_norm": 9.69674301147461, "learning_rate": 1.4452773613193402e-06, "loss": 0.7621, "step": 241 }, { "epoch": 0.14521452145214522, "grad_norm": 9.197075843811035, "learning_rate": 1.4512743628185906e-06, "loss": 0.9026, "step": 242 }, { "epoch": 0.14581458145814583, "grad_norm": 7.583044528961182, "learning_rate": 1.457271364317841e-06, "loss": 0.5499, "step": 243 }, { "epoch": 0.14641464146414643, "grad_norm": 4.294769287109375, "learning_rate": 1.4632683658170915e-06, "loss": 0.3409, "step": 244 }, { "epoch": 0.147014701470147, "grad_norm": 5.3705925941467285, "learning_rate": 1.4692653673163417e-06, "loss": 0.3974, "step": 245 }, { "epoch": 0.1476147614761476, "grad_norm": 6.843561172485352, "learning_rate": 1.475262368815592e-06, "loss": 0.5015, "step": 246 }, { "epoch": 0.1482148214821482, "grad_norm": 6.447572708129883, "learning_rate": 1.4812593703148427e-06, "loss": 0.3506, "step": 247 }, { "epoch": 0.1488148814881488, "grad_norm": 8.008218765258789, "learning_rate": 1.4872563718140929e-06, "loss": 0.979, "step": 248 }, { "epoch": 0.1494149414941494, "grad_norm": 6.713864326477051, "learning_rate": 1.4932533733133432e-06, "loss": 0.3666, "step": 249 }, { "epoch": 0.15001500150015, "grad_norm": 4.318709373474121, "learning_rate": 1.4992503748125936e-06, "loss": 0.304, "step": 250 }, { "epoch": 0.15061506150615062, "grad_norm": 4.623086452484131, "learning_rate": 1.505247376311844e-06, "loss": 0.2822, "step": 251 }, { "epoch": 0.15121512151215122, "grad_norm": 7.760659217834473, "learning_rate": 1.5112443778110944e-06, "loss": 0.82, "step": 252 }, { "epoch": 0.15181518151815182, "grad_norm": 6.34232234954834, "learning_rate": 1.5172413793103447e-06, "loss": 0.4252, "step": 253 }, { "epoch": 0.15241524152415242, "grad_norm": 9.0075044631958, "learning_rate": 1.5232383808095951e-06, "loss": 0.6449, "step": 254 }, { "epoch": 0.15301530153015303, "grad_norm": 5.625248432159424, "learning_rate": 1.5292353823088455e-06, "loss": 0.3539, "step": 255 }, { "epoch": 0.15361536153615363, "grad_norm": 6.644010066986084, "learning_rate": 1.5352323838080959e-06, "loss": 0.8199, "step": 256 }, { "epoch": 0.1542154215421542, "grad_norm": 7.48920202255249, "learning_rate": 1.5412293853073463e-06, "loss": 0.7963, "step": 257 }, { "epoch": 0.1548154815481548, "grad_norm": 8.392667770385742, "learning_rate": 1.5472263868065966e-06, "loss": 0.5997, "step": 258 }, { "epoch": 0.1554155415541554, "grad_norm": 5.507591724395752, "learning_rate": 1.553223388305847e-06, "loss": 0.4376, "step": 259 }, { "epoch": 0.156015601560156, "grad_norm": 6.822197914123535, "learning_rate": 1.5592203898050974e-06, "loss": 0.5107, "step": 260 }, { "epoch": 0.1566156615661566, "grad_norm": 8.710319519042969, "learning_rate": 1.5652173913043478e-06, "loss": 0.6645, "step": 261 }, { "epoch": 0.1572157215721572, "grad_norm": 5.684533596038818, "learning_rate": 1.5712143928035982e-06, "loss": 0.4571, "step": 262 }, { "epoch": 0.15781578157815782, "grad_norm": 7.303412437438965, "learning_rate": 1.5772113943028485e-06, "loss": 0.3924, "step": 263 }, { "epoch": 0.15841584158415842, "grad_norm": 8.134766578674316, "learning_rate": 1.583208395802099e-06, "loss": 0.5602, "step": 264 }, { "epoch": 0.15901590159015902, "grad_norm": 6.197120666503906, "learning_rate": 1.5892053973013493e-06, "loss": 0.5664, "step": 265 }, { "epoch": 0.15961596159615962, "grad_norm": 4.928647994995117, "learning_rate": 1.5952023988005997e-06, "loss": 0.3781, "step": 266 }, { "epoch": 0.16021602160216022, "grad_norm": 6.314647674560547, "learning_rate": 1.6011994002998498e-06, "loss": 0.6408, "step": 267 }, { "epoch": 0.16081608160816083, "grad_norm": 9.50062084197998, "learning_rate": 1.6071964017991004e-06, "loss": 1.0235, "step": 268 }, { "epoch": 0.16141614161416143, "grad_norm": 5.6598591804504395, "learning_rate": 1.6131934032983508e-06, "loss": 0.428, "step": 269 }, { "epoch": 0.162016201620162, "grad_norm": 6.9630327224731445, "learning_rate": 1.619190404797601e-06, "loss": 0.7204, "step": 270 }, { "epoch": 0.1626162616261626, "grad_norm": 5.709423542022705, "learning_rate": 1.6251874062968516e-06, "loss": 0.6607, "step": 271 }, { "epoch": 0.1632163216321632, "grad_norm": 6.133080005645752, "learning_rate": 1.631184407796102e-06, "loss": 0.487, "step": 272 }, { "epoch": 0.1638163816381638, "grad_norm": 7.300407886505127, "learning_rate": 1.6371814092953521e-06, "loss": 0.8018, "step": 273 }, { "epoch": 0.1644164416441644, "grad_norm": 5.858170032501221, "learning_rate": 1.6431784107946027e-06, "loss": 0.6034, "step": 274 }, { "epoch": 0.16501650165016502, "grad_norm": 7.277597904205322, "learning_rate": 1.649175412293853e-06, "loss": 0.7364, "step": 275 }, { "epoch": 0.16561656165616562, "grad_norm": 7.352428436279297, "learning_rate": 1.6551724137931035e-06, "loss": 0.6064, "step": 276 }, { "epoch": 0.16621662166216622, "grad_norm": 5.7701416015625, "learning_rate": 1.6611694152923536e-06, "loss": 0.5965, "step": 277 }, { "epoch": 0.16681668166816682, "grad_norm": 6.885606288909912, "learning_rate": 1.6671664167916042e-06, "loss": 0.491, "step": 278 }, { "epoch": 0.16741674167416742, "grad_norm": 6.562391757965088, "learning_rate": 1.6731634182908546e-06, "loss": 1.0471, "step": 279 }, { "epoch": 0.16801680168016803, "grad_norm": 5.834752559661865, "learning_rate": 1.6791604197901048e-06, "loss": 0.4303, "step": 280 }, { "epoch": 0.16861686168616863, "grad_norm": 4.258505821228027, "learning_rate": 1.6851574212893553e-06, "loss": 0.3064, "step": 281 }, { "epoch": 0.1692169216921692, "grad_norm": 5.091777801513672, "learning_rate": 1.6911544227886057e-06, "loss": 0.4307, "step": 282 }, { "epoch": 0.1698169816981698, "grad_norm": 4.404598712921143, "learning_rate": 1.6971514242878559e-06, "loss": 0.298, "step": 283 }, { "epoch": 0.1704170417041704, "grad_norm": 9.639359474182129, "learning_rate": 1.7031484257871063e-06, "loss": 1.5271, "step": 284 }, { "epoch": 0.171017101710171, "grad_norm": 6.465576171875, "learning_rate": 1.7091454272863569e-06, "loss": 0.3678, "step": 285 }, { "epoch": 0.1716171617161716, "grad_norm": 7.25118350982666, "learning_rate": 1.715142428785607e-06, "loss": 0.3979, "step": 286 }, { "epoch": 0.17221722172217221, "grad_norm": 7.304763317108154, "learning_rate": 1.7211394302848574e-06, "loss": 0.828, "step": 287 }, { "epoch": 0.17281728172817282, "grad_norm": 8.074031829833984, "learning_rate": 1.727136431784108e-06, "loss": 0.7351, "step": 288 }, { "epoch": 0.17341734173417342, "grad_norm": 4.585132598876953, "learning_rate": 1.7331334332833582e-06, "loss": 0.5049, "step": 289 }, { "epoch": 0.17401740174017402, "grad_norm": 4.039261817932129, "learning_rate": 1.7391304347826085e-06, "loss": 0.5158, "step": 290 }, { "epoch": 0.17461746174617462, "grad_norm": 6.263817310333252, "learning_rate": 1.7451274362818591e-06, "loss": 0.459, "step": 291 }, { "epoch": 0.17521752175217523, "grad_norm": 5.674893379211426, "learning_rate": 1.7511244377811095e-06, "loss": 0.5184, "step": 292 }, { "epoch": 0.17581758175817583, "grad_norm": 7.1915693283081055, "learning_rate": 1.7571214392803597e-06, "loss": 1.1733, "step": 293 }, { "epoch": 0.17641764176417643, "grad_norm": 5.026513576507568, "learning_rate": 1.76311844077961e-06, "loss": 0.4074, "step": 294 }, { "epoch": 0.177017701770177, "grad_norm": 7.6640400886535645, "learning_rate": 1.7691154422788606e-06, "loss": 0.7027, "step": 295 }, { "epoch": 0.1776177617761776, "grad_norm": 6.685046195983887, "learning_rate": 1.7751124437781108e-06, "loss": 0.6643, "step": 296 }, { "epoch": 0.1782178217821782, "grad_norm": 5.2202653884887695, "learning_rate": 1.7811094452773612e-06, "loss": 0.3559, "step": 297 }, { "epoch": 0.1788178817881788, "grad_norm": 6.3877410888671875, "learning_rate": 1.7871064467766118e-06, "loss": 0.2489, "step": 298 }, { "epoch": 0.17941794179417941, "grad_norm": 7.613877773284912, "learning_rate": 1.793103448275862e-06, "loss": 0.3953, "step": 299 }, { "epoch": 0.18001800180018002, "grad_norm": 6.230800151824951, "learning_rate": 1.7991004497751123e-06, "loss": 0.363, "step": 300 }, { "epoch": 0.18061806180618062, "grad_norm": 7.228221416473389, "learning_rate": 1.8050974512743627e-06, "loss": 0.7411, "step": 301 }, { "epoch": 0.18121812181218122, "grad_norm": 5.493793487548828, "learning_rate": 1.811094452773613e-06, "loss": 0.4119, "step": 302 }, { "epoch": 0.18181818181818182, "grad_norm": 9.42112922668457, "learning_rate": 1.8170914542728635e-06, "loss": 0.7591, "step": 303 }, { "epoch": 0.18241824182418243, "grad_norm": 5.5126953125, "learning_rate": 1.8230884557721138e-06, "loss": 0.5657, "step": 304 }, { "epoch": 0.18301830183018303, "grad_norm": 7.516278266906738, "learning_rate": 1.8290854572713642e-06, "loss": 0.8147, "step": 305 }, { "epoch": 0.18361836183618363, "grad_norm": 5.271646499633789, "learning_rate": 1.8350824587706146e-06, "loss": 0.5709, "step": 306 }, { "epoch": 0.1842184218421842, "grad_norm": 6.1128435134887695, "learning_rate": 1.841079460269865e-06, "loss": 0.8701, "step": 307 }, { "epoch": 0.1848184818481848, "grad_norm": 6.004319667816162, "learning_rate": 1.8470764617691156e-06, "loss": 0.7289, "step": 308 }, { "epoch": 0.1854185418541854, "grad_norm": 3.9558732509613037, "learning_rate": 1.8530734632683657e-06, "loss": 0.3808, "step": 309 }, { "epoch": 0.186018601860186, "grad_norm": 5.99823522567749, "learning_rate": 1.8590704647676161e-06, "loss": 0.3426, "step": 310 }, { "epoch": 0.1866186618661866, "grad_norm": 6.418328762054443, "learning_rate": 1.8650674662668665e-06, "loss": 0.4064, "step": 311 }, { "epoch": 0.18721872187218722, "grad_norm": 5.233288288116455, "learning_rate": 1.8710644677661169e-06, "loss": 0.396, "step": 312 }, { "epoch": 0.18781878187818782, "grad_norm": 6.575157165527344, "learning_rate": 1.8770614692653673e-06, "loss": 0.5125, "step": 313 }, { "epoch": 0.18841884188418842, "grad_norm": 6.26651668548584, "learning_rate": 1.8830584707646176e-06, "loss": 0.5137, "step": 314 }, { "epoch": 0.18901890189018902, "grad_norm": 5.065598487854004, "learning_rate": 1.889055472263868e-06, "loss": 0.4142, "step": 315 }, { "epoch": 0.18961896189618963, "grad_norm": 5.294402122497559, "learning_rate": 1.8950524737631184e-06, "loss": 0.5424, "step": 316 }, { "epoch": 0.19021902190219023, "grad_norm": 5.073161602020264, "learning_rate": 1.9010494752623688e-06, "loss": 0.5121, "step": 317 }, { "epoch": 0.19081908190819083, "grad_norm": 7.366306304931641, "learning_rate": 1.907046476761619e-06, "loss": 0.6613, "step": 318 }, { "epoch": 0.19141914191419143, "grad_norm": 3.7527992725372314, "learning_rate": 1.9130434782608697e-06, "loss": 0.3793, "step": 319 }, { "epoch": 0.192019201920192, "grad_norm": 6.2676591873168945, "learning_rate": 1.91904047976012e-06, "loss": 0.3991, "step": 320 }, { "epoch": 0.1926192619261926, "grad_norm": 6.70792293548584, "learning_rate": 1.92503748125937e-06, "loss": 0.4493, "step": 321 }, { "epoch": 0.1932193219321932, "grad_norm": 6.598604202270508, "learning_rate": 1.9310344827586207e-06, "loss": 0.5066, "step": 322 }, { "epoch": 0.1938193819381938, "grad_norm": 5.219124794006348, "learning_rate": 1.937031484257871e-06, "loss": 0.5433, "step": 323 }, { "epoch": 0.19441944194419442, "grad_norm": 5.30233097076416, "learning_rate": 1.9430284857571214e-06, "loss": 0.8766, "step": 324 }, { "epoch": 0.19501950195019502, "grad_norm": 6.4207563400268555, "learning_rate": 1.949025487256372e-06, "loss": 0.3845, "step": 325 }, { "epoch": 0.19561956195619562, "grad_norm": 5.740743637084961, "learning_rate": 1.955022488755622e-06, "loss": 0.4191, "step": 326 }, { "epoch": 0.19621962196219622, "grad_norm": 6.473495006561279, "learning_rate": 1.9610194902548723e-06, "loss": 0.349, "step": 327 }, { "epoch": 0.19681968196819682, "grad_norm": 8.15526294708252, "learning_rate": 1.967016491754123e-06, "loss": 0.5686, "step": 328 }, { "epoch": 0.19741974197419743, "grad_norm": 6.82892370223999, "learning_rate": 1.973013493253373e-06, "loss": 0.5864, "step": 329 }, { "epoch": 0.19801980198019803, "grad_norm": 3.80432391166687, "learning_rate": 1.9790104947526237e-06, "loss": 0.3522, "step": 330 }, { "epoch": 0.19861986198619863, "grad_norm": 5.701436996459961, "learning_rate": 1.985007496251874e-06, "loss": 0.3793, "step": 331 }, { "epoch": 0.19921992199219923, "grad_norm": 5.490096092224121, "learning_rate": 1.9910044977511244e-06, "loss": 0.826, "step": 332 }, { "epoch": 0.1998199819981998, "grad_norm": 4.7950825691223145, "learning_rate": 1.9970014992503746e-06, "loss": 0.4007, "step": 333 }, { "epoch": 0.2004200420042004, "grad_norm": 5.749341011047363, "learning_rate": 1.999999305175261e-06, "loss": 0.407, "step": 334 }, { "epoch": 0.201020102010201, "grad_norm": 5.475814342498779, "learning_rate": 1.9999937465831456e-06, "loss": 0.4189, "step": 335 }, { "epoch": 0.20162016201620162, "grad_norm": 6.560266971588135, "learning_rate": 1.999982629429813e-06, "loss": 0.6753, "step": 336 }, { "epoch": 0.20222022202220222, "grad_norm": 5.729518890380859, "learning_rate": 1.9999659537770587e-06, "loss": 0.5988, "step": 337 }, { "epoch": 0.20282028202820282, "grad_norm": 6.309112071990967, "learning_rate": 1.999943719717576e-06, "loss": 0.5195, "step": 338 }, { "epoch": 0.20342034203420342, "grad_norm": 5.519045352935791, "learning_rate": 1.9999159273749548e-06, "loss": 0.4221, "step": 339 }, { "epoch": 0.20402040204020402, "grad_norm": 7.059902191162109, "learning_rate": 1.9998825769036817e-06, "loss": 0.5237, "step": 340 }, { "epoch": 0.20462046204620463, "grad_norm": 4.126767635345459, "learning_rate": 1.999843668489138e-06, "loss": 0.7019, "step": 341 }, { "epoch": 0.20522052205220523, "grad_norm": 7.387668609619141, "learning_rate": 1.9997992023476013e-06, "loss": 0.6022, "step": 342 }, { "epoch": 0.20582058205820583, "grad_norm": 6.597599029541016, "learning_rate": 1.9997491787262397e-06, "loss": 0.5279, "step": 343 }, { "epoch": 0.20642064206420643, "grad_norm": 5.105510234832764, "learning_rate": 1.999693597903114e-06, "loss": 0.456, "step": 344 }, { "epoch": 0.207020702070207, "grad_norm": 6.584147930145264, "learning_rate": 1.999632460187177e-06, "loss": 0.6511, "step": 345 }, { "epoch": 0.2076207620762076, "grad_norm": 5.605836391448975, "learning_rate": 1.999565765918267e-06, "loss": 0.4431, "step": 346 }, { "epoch": 0.2082208220822082, "grad_norm": 5.911015510559082, "learning_rate": 1.9994935154671115e-06, "loss": 0.8804, "step": 347 }, { "epoch": 0.20882088208820881, "grad_norm": 5.007447719573975, "learning_rate": 1.999415709235321e-06, "loss": 0.2773, "step": 348 }, { "epoch": 0.20942094209420942, "grad_norm": 5.576949119567871, "learning_rate": 1.9993323476553894e-06, "loss": 0.3737, "step": 349 }, { "epoch": 0.21002100210021002, "grad_norm": 6.843761920928955, "learning_rate": 1.9992434311906895e-06, "loss": 1.0277, "step": 350 }, { "epoch": 0.21062106210621062, "grad_norm": 5.87042760848999, "learning_rate": 1.9991489603354727e-06, "loss": 0.3957, "step": 351 }, { "epoch": 0.21122112211221122, "grad_norm": 6.3514723777771, "learning_rate": 1.9990489356148638e-06, "loss": 0.5436, "step": 352 }, { "epoch": 0.21182118211821183, "grad_norm": 5.197248935699463, "learning_rate": 1.99894335758486e-06, "loss": 0.4727, "step": 353 }, { "epoch": 0.21242124212421243, "grad_norm": 5.58435583114624, "learning_rate": 1.9988322268323264e-06, "loss": 0.6747, "step": 354 }, { "epoch": 0.21302130213021303, "grad_norm": 6.880096912384033, "learning_rate": 1.998715543974995e-06, "loss": 0.6061, "step": 355 }, { "epoch": 0.21362136213621363, "grad_norm": 5.878513813018799, "learning_rate": 1.9985933096614578e-06, "loss": 0.5235, "step": 356 }, { "epoch": 0.21422142214221424, "grad_norm": 6.000712871551514, "learning_rate": 1.998465524571166e-06, "loss": 0.9061, "step": 357 }, { "epoch": 0.2148214821482148, "grad_norm": 5.000283718109131, "learning_rate": 1.9983321894144255e-06, "loss": 0.5392, "step": 358 }, { "epoch": 0.2154215421542154, "grad_norm": 3.9003353118896484, "learning_rate": 1.9981933049323927e-06, "loss": 0.2065, "step": 359 }, { "epoch": 0.21602160216021601, "grad_norm": 4.967084884643555, "learning_rate": 1.9980488718970703e-06, "loss": 0.5861, "step": 360 }, { "epoch": 0.21662166216621662, "grad_norm": 6.546853542327881, "learning_rate": 1.997898891111303e-06, "loss": 0.5412, "step": 361 }, { "epoch": 0.21722172217221722, "grad_norm": 5.2185235023498535, "learning_rate": 1.9977433634087737e-06, "loss": 0.364, "step": 362 }, { "epoch": 0.21782178217821782, "grad_norm": 5.976794242858887, "learning_rate": 1.9975822896539977e-06, "loss": 0.3995, "step": 363 }, { "epoch": 0.21842184218421842, "grad_norm": 4.880700588226318, "learning_rate": 1.9974156707423185e-06, "loss": 0.296, "step": 364 }, { "epoch": 0.21902190219021903, "grad_norm": 5.075315475463867, "learning_rate": 1.9972435075999044e-06, "loss": 0.3706, "step": 365 }, { "epoch": 0.21962196219621963, "grad_norm": 6.266536235809326, "learning_rate": 1.9970658011837403e-06, "loss": 0.4064, "step": 366 }, { "epoch": 0.22022202220222023, "grad_norm": 3.3985109329223633, "learning_rate": 1.9968825524816243e-06, "loss": 0.166, "step": 367 }, { "epoch": 0.22082208220822083, "grad_norm": 4.806713581085205, "learning_rate": 1.9966937625121618e-06, "loss": 0.5559, "step": 368 }, { "epoch": 0.22142214221422143, "grad_norm": 5.291970252990723, "learning_rate": 1.99649943232476e-06, "loss": 0.5586, "step": 369 }, { "epoch": 0.222022202220222, "grad_norm": 6.054694652557373, "learning_rate": 1.996299562999622e-06, "loss": 0.6193, "step": 370 }, { "epoch": 0.2226222622262226, "grad_norm": 8.03508472442627, "learning_rate": 1.996094155647741e-06, "loss": 0.7489, "step": 371 }, { "epoch": 0.2232223222322232, "grad_norm": 7.679685592651367, "learning_rate": 1.9958832114108923e-06, "loss": 0.5312, "step": 372 }, { "epoch": 0.22382238223822382, "grad_norm": 3.7182741165161133, "learning_rate": 1.9956667314616308e-06, "loss": 0.2113, "step": 373 }, { "epoch": 0.22442244224422442, "grad_norm": 5.768306255340576, "learning_rate": 1.9954447170032804e-06, "loss": 0.6807, "step": 374 }, { "epoch": 0.22502250225022502, "grad_norm": 4.543365478515625, "learning_rate": 1.9952171692699307e-06, "loss": 0.7277, "step": 375 }, { "epoch": 0.22562256225622562, "grad_norm": 6.071779251098633, "learning_rate": 1.994984089526427e-06, "loss": 0.3022, "step": 376 }, { "epoch": 0.22622262226222623, "grad_norm": 5.131073474884033, "learning_rate": 1.994745479068365e-06, "loss": 0.4883, "step": 377 }, { "epoch": 0.22682268226822683, "grad_norm": 6.505067825317383, "learning_rate": 1.994501339222084e-06, "loss": 0.488, "step": 378 }, { "epoch": 0.22742274227422743, "grad_norm": 5.110593795776367, "learning_rate": 1.9942516713446596e-06, "loss": 0.5788, "step": 379 }, { "epoch": 0.22802280228022803, "grad_norm": 6.49658203125, "learning_rate": 1.9939964768238944e-06, "loss": 0.5587, "step": 380 }, { "epoch": 0.22862286228622863, "grad_norm": 7.897826194763184, "learning_rate": 1.993735757078311e-06, "loss": 0.6032, "step": 381 }, { "epoch": 0.22922292229222924, "grad_norm": 4.9207611083984375, "learning_rate": 1.993469513557145e-06, "loss": 0.4299, "step": 382 }, { "epoch": 0.2298229822982298, "grad_norm": 5.384866237640381, "learning_rate": 1.9931977477403375e-06, "loss": 0.4964, "step": 383 }, { "epoch": 0.2304230423042304, "grad_norm": 6.219894886016846, "learning_rate": 1.992920461138524e-06, "loss": 0.3125, "step": 384 }, { "epoch": 0.23102310231023102, "grad_norm": 4.724498748779297, "learning_rate": 1.99263765529303e-06, "loss": 0.6491, "step": 385 }, { "epoch": 0.23162316231623162, "grad_norm": 5.651078224182129, "learning_rate": 1.9923493317758575e-06, "loss": 0.4154, "step": 386 }, { "epoch": 0.23222322232223222, "grad_norm": 6.178045272827148, "learning_rate": 1.9920554921896806e-06, "loss": 0.3741, "step": 387 }, { "epoch": 0.23282328232823282, "grad_norm": 6.862026214599609, "learning_rate": 1.991756138167836e-06, "loss": 0.7942, "step": 388 }, { "epoch": 0.23342334233423342, "grad_norm": 5.807425022125244, "learning_rate": 1.99145127137431e-06, "loss": 0.6251, "step": 389 }, { "epoch": 0.23402340234023403, "grad_norm": 6.732903957366943, "learning_rate": 1.991140893503736e-06, "loss": 0.5478, "step": 390 }, { "epoch": 0.23462346234623463, "grad_norm": 6.130273818969727, "learning_rate": 1.990825006281377e-06, "loss": 0.6271, "step": 391 }, { "epoch": 0.23522352235223523, "grad_norm": 6.072498798370361, "learning_rate": 1.9905036114631245e-06, "loss": 0.5838, "step": 392 }, { "epoch": 0.23582358235823583, "grad_norm": 7.1707940101623535, "learning_rate": 1.990176710835481e-06, "loss": 0.7618, "step": 393 }, { "epoch": 0.23642364236423644, "grad_norm": 4.687925338745117, "learning_rate": 1.9898443062155555e-06, "loss": 0.3629, "step": 394 }, { "epoch": 0.237023702370237, "grad_norm": 6.434917449951172, "learning_rate": 1.989506399451051e-06, "loss": 0.8947, "step": 395 }, { "epoch": 0.2376237623762376, "grad_norm": 5.555397987365723, "learning_rate": 1.9891629924202545e-06, "loss": 0.71, "step": 396 }, { "epoch": 0.23822382238223822, "grad_norm": 4.822803974151611, "learning_rate": 1.9888140870320275e-06, "loss": 0.303, "step": 397 }, { "epoch": 0.23882388238823882, "grad_norm": 6.65578556060791, "learning_rate": 1.9884596852257934e-06, "loss": 0.6818, "step": 398 }, { "epoch": 0.23942394239423942, "grad_norm": 6.210423469543457, "learning_rate": 1.988099788971529e-06, "loss": 1.0374, "step": 399 }, { "epoch": 0.24002400240024002, "grad_norm": 4.355246543884277, "learning_rate": 1.9877344002697524e-06, "loss": 0.3914, "step": 400 }, { "epoch": 0.24062406240624062, "grad_norm": 5.137374401092529, "learning_rate": 1.987363521151511e-06, "loss": 0.4406, "step": 401 }, { "epoch": 0.24122412241224123, "grad_norm": 6.472471714019775, "learning_rate": 1.9869871536783727e-06, "loss": 0.4275, "step": 402 }, { "epoch": 0.24182418241824183, "grad_norm": 7.264206409454346, "learning_rate": 1.9866052999424123e-06, "loss": 0.6362, "step": 403 }, { "epoch": 0.24242424242424243, "grad_norm": 4.592499256134033, "learning_rate": 1.9862179620661993e-06, "loss": 0.3623, "step": 404 }, { "epoch": 0.24302430243024303, "grad_norm": 5.161081790924072, "learning_rate": 1.98582514220279e-06, "loss": 0.5764, "step": 405 }, { "epoch": 0.24362436243624364, "grad_norm": 4.577977180480957, "learning_rate": 1.9854268425357105e-06, "loss": 0.4576, "step": 406 }, { "epoch": 0.24422442244224424, "grad_norm": 5.286322116851807, "learning_rate": 1.9850230652789476e-06, "loss": 0.4444, "step": 407 }, { "epoch": 0.2448244824482448, "grad_norm": 4.4775261878967285, "learning_rate": 1.984613812676936e-06, "loss": 0.4521, "step": 408 }, { "epoch": 0.24542454245424541, "grad_norm": 5.9200921058654785, "learning_rate": 1.984199087004546e-06, "loss": 0.5987, "step": 409 }, { "epoch": 0.24602460246024602, "grad_norm": 4.811771869659424, "learning_rate": 1.9837788905670698e-06, "loss": 0.4603, "step": 410 }, { "epoch": 0.24662466246624662, "grad_norm": 5.397486686706543, "learning_rate": 1.9833532257002095e-06, "loss": 0.5674, "step": 411 }, { "epoch": 0.24722472247224722, "grad_norm": 6.971630096435547, "learning_rate": 1.9829220947700643e-06, "loss": 0.5053, "step": 412 }, { "epoch": 0.24782478247824782, "grad_norm": 5.47833776473999, "learning_rate": 1.982485500173117e-06, "loss": 0.3181, "step": 413 }, { "epoch": 0.24842484248424843, "grad_norm": 4.387160778045654, "learning_rate": 1.98204344433622e-06, "loss": 0.373, "step": 414 }, { "epoch": 0.24902490249024903, "grad_norm": 6.19027042388916, "learning_rate": 1.9815959297165837e-06, "loss": 0.7636, "step": 415 }, { "epoch": 0.24962496249624963, "grad_norm": 5.653426647186279, "learning_rate": 1.9811429588017605e-06, "loss": 0.4983, "step": 416 }, { "epoch": 0.2502250225022502, "grad_norm": 5.157104969024658, "learning_rate": 1.980684534109633e-06, "loss": 0.6623, "step": 417 }, { "epoch": 0.2508250825082508, "grad_norm": 6.880595684051514, "learning_rate": 1.980220658188399e-06, "loss": 0.8785, "step": 418 }, { "epoch": 0.2514251425142514, "grad_norm": 5.693664073944092, "learning_rate": 1.979751333616557e-06, "loss": 0.4842, "step": 419 }, { "epoch": 0.252025202520252, "grad_norm": 8.25198745727539, "learning_rate": 1.9792765630028935e-06, "loss": 0.787, "step": 420 }, { "epoch": 0.2526252625262526, "grad_norm": 4.165426731109619, "learning_rate": 1.9787963489864655e-06, "loss": 0.3425, "step": 421 }, { "epoch": 0.2532253225322532, "grad_norm": 4.626536846160889, "learning_rate": 1.9783106942365892e-06, "loss": 0.3726, "step": 422 }, { "epoch": 0.2538253825382538, "grad_norm": 4.1441450119018555, "learning_rate": 1.9778196014528227e-06, "loss": 0.2974, "step": 423 }, { "epoch": 0.2544254425442544, "grad_norm": 6.974517345428467, "learning_rate": 1.977323073364953e-06, "loss": 0.3423, "step": 424 }, { "epoch": 0.255025502550255, "grad_norm": 8.637796401977539, "learning_rate": 1.9768211127329785e-06, "loss": 0.6737, "step": 425 }, { "epoch": 0.2556255625562556, "grad_norm": 8.958054542541504, "learning_rate": 1.9763137223470964e-06, "loss": 0.648, "step": 426 }, { "epoch": 0.25622562256225623, "grad_norm": 5.755735874176025, "learning_rate": 1.975800905027684e-06, "loss": 0.5246, "step": 427 }, { "epoch": 0.25682568256825683, "grad_norm": 6.195178985595703, "learning_rate": 1.975282663625286e-06, "loss": 0.4535, "step": 428 }, { "epoch": 0.25742574257425743, "grad_norm": 14.15047836303711, "learning_rate": 1.974759001020597e-06, "loss": 0.3965, "step": 429 }, { "epoch": 0.25802580258025803, "grad_norm": 7.769376277923584, "learning_rate": 1.974229920124446e-06, "loss": 0.6619, "step": 430 }, { "epoch": 0.25862586258625864, "grad_norm": 5.7328033447265625, "learning_rate": 1.973695423877779e-06, "loss": 0.719, "step": 431 }, { "epoch": 0.25922592259225924, "grad_norm": 6.657202243804932, "learning_rate": 1.9731555152516456e-06, "loss": 0.9061, "step": 432 }, { "epoch": 0.25982598259825984, "grad_norm": 6.520764350891113, "learning_rate": 1.97261019724718e-06, "loss": 0.5444, "step": 433 }, { "epoch": 0.26042604260426044, "grad_norm": 6.443291664123535, "learning_rate": 1.9720594728955837e-06, "loss": 0.5844, "step": 434 }, { "epoch": 0.26102610261026105, "grad_norm": 1.962812900543213, "learning_rate": 1.9715033452581115e-06, "loss": 0.2524, "step": 435 }, { "epoch": 0.26162616261626165, "grad_norm": 4.576583385467529, "learning_rate": 1.970941817426052e-06, "loss": 0.4201, "step": 436 }, { "epoch": 0.26222622262226225, "grad_norm": 7.147463798522949, "learning_rate": 1.9703748925207116e-06, "loss": 0.6479, "step": 437 }, { "epoch": 0.26282628262826285, "grad_norm": 5.406599521636963, "learning_rate": 1.969802573693397e-06, "loss": 0.6882, "step": 438 }, { "epoch": 0.2634263426342634, "grad_norm": 7.032170295715332, "learning_rate": 1.969224864125397e-06, "loss": 0.6795, "step": 439 }, { "epoch": 0.264026402640264, "grad_norm": 6.125194549560547, "learning_rate": 1.9686417670279657e-06, "loss": 0.361, "step": 440 }, { "epoch": 0.2646264626462646, "grad_norm": 4.430140018463135, "learning_rate": 1.9680532856423048e-06, "loss": 0.374, "step": 441 }, { "epoch": 0.2652265226522652, "grad_norm": 4.4150214195251465, "learning_rate": 1.967459423239544e-06, "loss": 0.2641, "step": 442 }, { "epoch": 0.2658265826582658, "grad_norm": 5.866743564605713, "learning_rate": 1.966860183120725e-06, "loss": 0.8344, "step": 443 }, { "epoch": 0.2664266426642664, "grad_norm": 6.144595146179199, "learning_rate": 1.9662555686167805e-06, "loss": 0.6479, "step": 444 }, { "epoch": 0.267026702670267, "grad_norm": 4.794925212860107, "learning_rate": 1.9656455830885193e-06, "loss": 0.3894, "step": 445 }, { "epoch": 0.2676267626762676, "grad_norm": 6.289479732513428, "learning_rate": 1.965030229926604e-06, "loss": 0.6193, "step": 446 }, { "epoch": 0.2682268226822682, "grad_norm": 6.934781551361084, "learning_rate": 1.9644095125515345e-06, "loss": 0.3801, "step": 447 }, { "epoch": 0.2688268826882688, "grad_norm": 5.399415016174316, "learning_rate": 1.9637834344136278e-06, "loss": 0.4053, "step": 448 }, { "epoch": 0.2694269426942694, "grad_norm": 6.203494548797607, "learning_rate": 1.9631519989929986e-06, "loss": 0.4457, "step": 449 }, { "epoch": 0.27002700270027, "grad_norm": 8.30703067779541, "learning_rate": 1.9625152097995426e-06, "loss": 0.448, "step": 450 }, { "epoch": 0.2706270627062706, "grad_norm": 6.407390117645264, "learning_rate": 1.9618730703729128e-06, "loss": 0.555, "step": 451 }, { "epoch": 0.27122712271227123, "grad_norm": 6.8706440925598145, "learning_rate": 1.9612255842825033e-06, "loss": 0.5495, "step": 452 }, { "epoch": 0.27182718271827183, "grad_norm": 5.546620845794678, "learning_rate": 1.960572755127427e-06, "loss": 0.3676, "step": 453 }, { "epoch": 0.27242724272427243, "grad_norm": 4.748040199279785, "learning_rate": 1.959914586536498e-06, "loss": 0.6058, "step": 454 }, { "epoch": 0.27302730273027304, "grad_norm": 4.62808895111084, "learning_rate": 1.959251082168209e-06, "loss": 0.6018, "step": 455 }, { "epoch": 0.27362736273627364, "grad_norm": 4.551493167877197, "learning_rate": 1.9585822457107136e-06, "loss": 0.3489, "step": 456 }, { "epoch": 0.27422742274227424, "grad_norm": 7.1338300704956055, "learning_rate": 1.9579080808818032e-06, "loss": 0.5305, "step": 457 }, { "epoch": 0.27482748274827484, "grad_norm": 5.056223392486572, "learning_rate": 1.957228591428887e-06, "loss": 0.4305, "step": 458 }, { "epoch": 0.27542754275427545, "grad_norm": 7.488931179046631, "learning_rate": 1.9565437811289728e-06, "loss": 0.9453, "step": 459 }, { "epoch": 0.27602760276027605, "grad_norm": 6.5416412353515625, "learning_rate": 1.955853653788644e-06, "loss": 0.387, "step": 460 }, { "epoch": 0.27662766276627665, "grad_norm": 5.513499736785889, "learning_rate": 1.955158213244041e-06, "loss": 0.8376, "step": 461 }, { "epoch": 0.27722772277227725, "grad_norm": 4.96074104309082, "learning_rate": 1.9544574633608352e-06, "loss": 0.3819, "step": 462 }, { "epoch": 0.27782778277827785, "grad_norm": 7.192686080932617, "learning_rate": 1.953751408034213e-06, "loss": 0.5834, "step": 463 }, { "epoch": 0.2784278427842784, "grad_norm": 5.366602420806885, "learning_rate": 1.95304005118885e-06, "loss": 0.4373, "step": 464 }, { "epoch": 0.279027902790279, "grad_norm": 6.0042338371276855, "learning_rate": 1.9523233967788926e-06, "loss": 0.6197, "step": 465 }, { "epoch": 0.2796279627962796, "grad_norm": 5.146775245666504, "learning_rate": 1.951601448787932e-06, "loss": 0.6063, "step": 466 }, { "epoch": 0.2802280228022802, "grad_norm": 5.261302471160889, "learning_rate": 1.950874211228986e-06, "loss": 0.374, "step": 467 }, { "epoch": 0.2808280828082808, "grad_norm": 5.402990818023682, "learning_rate": 1.950141688144474e-06, "loss": 0.3572, "step": 468 }, { "epoch": 0.2814281428142814, "grad_norm": 5.545160293579102, "learning_rate": 1.949403883606196e-06, "loss": 0.2469, "step": 469 }, { "epoch": 0.282028202820282, "grad_norm": 4.7018046379089355, "learning_rate": 1.94866080171531e-06, "loss": 0.3612, "step": 470 }, { "epoch": 0.2826282628262826, "grad_norm": 5.198354721069336, "learning_rate": 1.947912446602307e-06, "loss": 0.5958, "step": 471 }, { "epoch": 0.2832283228322832, "grad_norm": 3.9956040382385254, "learning_rate": 1.947158822426991e-06, "loss": 0.3998, "step": 472 }, { "epoch": 0.2838283828382838, "grad_norm": 5.262460708618164, "learning_rate": 1.946399933378455e-06, "loss": 0.7611, "step": 473 }, { "epoch": 0.2844284428442844, "grad_norm": 4.820724964141846, "learning_rate": 1.945635783675056e-06, "loss": 0.4372, "step": 474 }, { "epoch": 0.285028502850285, "grad_norm": 4.822026252746582, "learning_rate": 1.944866377564393e-06, "loss": 0.5843, "step": 475 }, { "epoch": 0.28562856285628563, "grad_norm": 6.354537487030029, "learning_rate": 1.9440917193232852e-06, "loss": 0.5051, "step": 476 }, { "epoch": 0.28622862286228623, "grad_norm": 4.541317939758301, "learning_rate": 1.943311813257743e-06, "loss": 0.278, "step": 477 }, { "epoch": 0.28682868286828683, "grad_norm": 6.922798156738281, "learning_rate": 1.9425266637029504e-06, "loss": 0.5873, "step": 478 }, { "epoch": 0.28742874287428744, "grad_norm": 7.629828929901123, "learning_rate": 1.9417362750232358e-06, "loss": 0.4478, "step": 479 }, { "epoch": 0.28802880288028804, "grad_norm": 5.362582683563232, "learning_rate": 1.9409406516120513e-06, "loss": 0.6622, "step": 480 }, { "epoch": 0.28862886288628864, "grad_norm": 5.463460445404053, "learning_rate": 1.9401397978919453e-06, "loss": 0.3454, "step": 481 }, { "epoch": 0.28922892289228924, "grad_norm": 5.833940029144287, "learning_rate": 1.93933371831454e-06, "loss": 0.5375, "step": 482 }, { "epoch": 0.28982898289828984, "grad_norm": 5.3397064208984375, "learning_rate": 1.938522417360507e-06, "loss": 0.4391, "step": 483 }, { "epoch": 0.29042904290429045, "grad_norm": 4.736700534820557, "learning_rate": 1.9377058995395392e-06, "loss": 0.4767, "step": 484 }, { "epoch": 0.29102910291029105, "grad_norm": 6.818323612213135, "learning_rate": 1.9368841693903307e-06, "loss": 0.4425, "step": 485 }, { "epoch": 0.29162916291629165, "grad_norm": 6.223503112792969, "learning_rate": 1.9360572314805463e-06, "loss": 0.624, "step": 486 }, { "epoch": 0.29222922292229225, "grad_norm": 5.389606952667236, "learning_rate": 1.9352250904068006e-06, "loss": 0.6175, "step": 487 }, { "epoch": 0.29282928292829286, "grad_norm": 5.278392791748047, "learning_rate": 1.9343877507946286e-06, "loss": 0.4323, "step": 488 }, { "epoch": 0.2934293429342934, "grad_norm": 5.067900657653809, "learning_rate": 1.9335452172984637e-06, "loss": 0.6049, "step": 489 }, { "epoch": 0.294029402940294, "grad_norm": 5.84902286529541, "learning_rate": 1.932697494601609e-06, "loss": 0.4756, "step": 490 }, { "epoch": 0.2946294629462946, "grad_norm": 5.629978179931641, "learning_rate": 1.931844587416213e-06, "loss": 0.5168, "step": 491 }, { "epoch": 0.2952295229522952, "grad_norm": 5.198336124420166, "learning_rate": 1.9309865004832407e-06, "loss": 0.5728, "step": 492 }, { "epoch": 0.2958295829582958, "grad_norm": 3.5791053771972656, "learning_rate": 1.930123238572452e-06, "loss": 0.2606, "step": 493 }, { "epoch": 0.2964296429642964, "grad_norm": 7.149363994598389, "learning_rate": 1.9292548064823705e-06, "loss": 0.4851, "step": 494 }, { "epoch": 0.297029702970297, "grad_norm": 5.041487693786621, "learning_rate": 1.92838120904026e-06, "loss": 0.2905, "step": 495 }, { "epoch": 0.2976297629762976, "grad_norm": 5.366705417633057, "learning_rate": 1.927502451102095e-06, "loss": 0.3398, "step": 496 }, { "epoch": 0.2982298229822982, "grad_norm": 6.000150203704834, "learning_rate": 1.9266185375525354e-06, "loss": 0.6013, "step": 497 }, { "epoch": 0.2988298829882988, "grad_norm": 3.9614133834838867, "learning_rate": 1.9257294733049006e-06, "loss": 0.3763, "step": 498 }, { "epoch": 0.2994299429942994, "grad_norm": 6.153034210205078, "learning_rate": 1.924835263301139e-06, "loss": 0.6986, "step": 499 }, { "epoch": 0.3000300030003, "grad_norm": 7.163164138793945, "learning_rate": 1.9239359125118033e-06, "loss": 0.6606, "step": 500 }, { "epoch": 0.30063006300630063, "grad_norm": 6.254671573638916, "learning_rate": 1.92303142593602e-06, "loss": 0.482, "step": 501 }, { "epoch": 0.30123012301230123, "grad_norm": 4.0084733963012695, "learning_rate": 1.922121808601466e-06, "loss": 0.42, "step": 502 }, { "epoch": 0.30183018301830183, "grad_norm": 3.6666934490203857, "learning_rate": 1.9212070655643353e-06, "loss": 0.3626, "step": 503 }, { "epoch": 0.30243024302430244, "grad_norm": 4.088322639465332, "learning_rate": 1.9202872019093154e-06, "loss": 0.2117, "step": 504 }, { "epoch": 0.30303030303030304, "grad_norm": 5.708866119384766, "learning_rate": 1.919362222749557e-06, "loss": 0.7866, "step": 505 }, { "epoch": 0.30363036303630364, "grad_norm": 4.684825897216797, "learning_rate": 1.918432133226645e-06, "loss": 0.2946, "step": 506 }, { "epoch": 0.30423042304230424, "grad_norm": 4.817788124084473, "learning_rate": 1.9174969385105715e-06, "loss": 0.6847, "step": 507 }, { "epoch": 0.30483048304830485, "grad_norm": 5.989570140838623, "learning_rate": 1.916556643799706e-06, "loss": 0.4556, "step": 508 }, { "epoch": 0.30543054305430545, "grad_norm": 5.706479072570801, "learning_rate": 1.915611254320767e-06, "loss": 0.4813, "step": 509 }, { "epoch": 0.30603060306030605, "grad_norm": 5.699010372161865, "learning_rate": 1.914660775328793e-06, "loss": 0.4707, "step": 510 }, { "epoch": 0.30663066306630665, "grad_norm": 5.732868671417236, "learning_rate": 1.9137052121071122e-06, "loss": 0.4129, "step": 511 }, { "epoch": 0.30723072307230725, "grad_norm": 5.754509449005127, "learning_rate": 1.9127445699673147e-06, "loss": 0.544, "step": 512 }, { "epoch": 0.30783078307830786, "grad_norm": 4.6502251625061035, "learning_rate": 1.911778854249222e-06, "loss": 0.3864, "step": 513 }, { "epoch": 0.3084308430843084, "grad_norm": 5.141037940979004, "learning_rate": 1.910808070320857e-06, "loss": 0.4846, "step": 514 }, { "epoch": 0.309030903090309, "grad_norm": 6.9548797607421875, "learning_rate": 1.9098322235784164e-06, "loss": 0.4662, "step": 515 }, { "epoch": 0.3096309630963096, "grad_norm": 6.79717493057251, "learning_rate": 1.908851319446238e-06, "loss": 0.3949, "step": 516 }, { "epoch": 0.3102310231023102, "grad_norm": 6.619046211242676, "learning_rate": 1.9078653633767702e-06, "loss": 0.555, "step": 517 }, { "epoch": 0.3108310831083108, "grad_norm": 4.687836170196533, "learning_rate": 1.9068743608505452e-06, "loss": 0.5452, "step": 518 }, { "epoch": 0.3114311431143114, "grad_norm": 5.198296546936035, "learning_rate": 1.9058783173761462e-06, "loss": 0.6494, "step": 519 }, { "epoch": 0.312031203120312, "grad_norm": 6.167348861694336, "learning_rate": 1.9048772384901758e-06, "loss": 0.575, "step": 520 }, { "epoch": 0.3126312631263126, "grad_norm": 5.629940509796143, "learning_rate": 1.9038711297572276e-06, "loss": 0.5035, "step": 521 }, { "epoch": 0.3132313231323132, "grad_norm": 6.786480903625488, "learning_rate": 1.9028599967698532e-06, "loss": 0.8017, "step": 522 }, { "epoch": 0.3138313831383138, "grad_norm": 6.703796863555908, "learning_rate": 1.901843845148532e-06, "loss": 1.0136, "step": 523 }, { "epoch": 0.3144314431443144, "grad_norm": 4.356379985809326, "learning_rate": 1.900822680541641e-06, "loss": 0.3627, "step": 524 }, { "epoch": 0.31503150315031503, "grad_norm": 4.652871608734131, "learning_rate": 1.899796508625421e-06, "loss": 0.4017, "step": 525 }, { "epoch": 0.31563156315631563, "grad_norm": 6.003991603851318, "learning_rate": 1.8987653351039477e-06, "loss": 0.5133, "step": 526 }, { "epoch": 0.31623162316231623, "grad_norm": 7.495358943939209, "learning_rate": 1.897729165709098e-06, "loss": 0.5633, "step": 527 }, { "epoch": 0.31683168316831684, "grad_norm": 4.402565956115723, "learning_rate": 1.8966880062005186e-06, "loss": 0.2853, "step": 528 }, { "epoch": 0.31743174317431744, "grad_norm": 5.9103217124938965, "learning_rate": 1.8956418623655948e-06, "loss": 0.2775, "step": 529 }, { "epoch": 0.31803180318031804, "grad_norm": 3.5894100666046143, "learning_rate": 1.8945907400194175e-06, "loss": 0.3509, "step": 530 }, { "epoch": 0.31863186318631864, "grad_norm": 5.729333877563477, "learning_rate": 1.893534645004751e-06, "loss": 0.3826, "step": 531 }, { "epoch": 0.31923192319231924, "grad_norm": 2.486215829849243, "learning_rate": 1.8924735831920006e-06, "loss": 0.2616, "step": 532 }, { "epoch": 0.31983198319831985, "grad_norm": 4.915143013000488, "learning_rate": 1.891407560479181e-06, "loss": 0.5197, "step": 533 }, { "epoch": 0.32043204320432045, "grad_norm": 4.000769138336182, "learning_rate": 1.8903365827918812e-06, "loss": 0.2651, "step": 534 }, { "epoch": 0.32103210321032105, "grad_norm": 4.3584184646606445, "learning_rate": 1.8892606560832333e-06, "loss": 0.2791, "step": 535 }, { "epoch": 0.32163216321632165, "grad_norm": 6.118782997131348, "learning_rate": 1.8881797863338798e-06, "loss": 0.9188, "step": 536 }, { "epoch": 0.32223222322232226, "grad_norm": 4.442323684692383, "learning_rate": 1.8870939795519383e-06, "loss": 0.4471, "step": 537 }, { "epoch": 0.32283228322832286, "grad_norm": 7.480071067810059, "learning_rate": 1.8860032417729701e-06, "loss": 0.3995, "step": 538 }, { "epoch": 0.3234323432343234, "grad_norm": 4.523982048034668, "learning_rate": 1.8849075790599462e-06, "loss": 0.31, "step": 539 }, { "epoch": 0.324032403240324, "grad_norm": 7.006885051727295, "learning_rate": 1.883806997503213e-06, "loss": 0.3561, "step": 540 }, { "epoch": 0.3246324632463246, "grad_norm": 4.651212692260742, "learning_rate": 1.8827015032204582e-06, "loss": 0.6289, "step": 541 }, { "epoch": 0.3252325232523252, "grad_norm": 4.8181915283203125, "learning_rate": 1.881591102356678e-06, "loss": 0.4821, "step": 542 }, { "epoch": 0.3258325832583258, "grad_norm": 6.894742488861084, "learning_rate": 1.8804758010841426e-06, "loss": 0.4968, "step": 543 }, { "epoch": 0.3264326432643264, "grad_norm": 4.601960182189941, "learning_rate": 1.8793556056023607e-06, "loss": 0.5079, "step": 544 }, { "epoch": 0.327032703270327, "grad_norm": 2.6235568523406982, "learning_rate": 1.8782305221380467e-06, "loss": 0.2642, "step": 545 }, { "epoch": 0.3276327632763276, "grad_norm": 6.648951530456543, "learning_rate": 1.877100556945085e-06, "loss": 0.5544, "step": 546 }, { "epoch": 0.3282328232823282, "grad_norm": 6.406927108764648, "learning_rate": 1.875965716304495e-06, "loss": 0.4072, "step": 547 }, { "epoch": 0.3288328832883288, "grad_norm": 7.010688304901123, "learning_rate": 1.8748260065243984e-06, "loss": 0.4558, "step": 548 }, { "epoch": 0.32943294329432943, "grad_norm": 5.666876316070557, "learning_rate": 1.8736814339399805e-06, "loss": 0.5242, "step": 549 }, { "epoch": 0.33003300330033003, "grad_norm": 6.373556137084961, "learning_rate": 1.872532004913458e-06, "loss": 0.5246, "step": 550 }, { "epoch": 0.33063306330633063, "grad_norm": 6.213670253753662, "learning_rate": 1.8713777258340428e-06, "loss": 0.61, "step": 551 }, { "epoch": 0.33123312331233123, "grad_norm": 5.4165825843811035, "learning_rate": 1.8702186031179059e-06, "loss": 0.4686, "step": 552 }, { "epoch": 0.33183318331833184, "grad_norm": 5.045126438140869, "learning_rate": 1.869054643208142e-06, "loss": 0.5904, "step": 553 }, { "epoch": 0.33243324332433244, "grad_norm": 7.0957722663879395, "learning_rate": 1.867885852574734e-06, "loss": 0.7658, "step": 554 }, { "epoch": 0.33303330333033304, "grad_norm": 5.706569194793701, "learning_rate": 1.8667122377145166e-06, "loss": 0.4499, "step": 555 }, { "epoch": 0.33363336333633364, "grad_norm": 6.035883903503418, "learning_rate": 1.865533805151141e-06, "loss": 0.6208, "step": 556 }, { "epoch": 0.33423342334233425, "grad_norm": 4.452247619628906, "learning_rate": 1.8643505614350376e-06, "loss": 0.4604, "step": 557 }, { "epoch": 0.33483348334833485, "grad_norm": 4.626057147979736, "learning_rate": 1.86316251314338e-06, "loss": 0.418, "step": 558 }, { "epoch": 0.33543354335433545, "grad_norm": 4.946737766265869, "learning_rate": 1.861969666880049e-06, "loss": 0.4262, "step": 559 }, { "epoch": 0.33603360336033605, "grad_norm": 6.138003349304199, "learning_rate": 1.860772029275595e-06, "loss": 0.6104, "step": 560 }, { "epoch": 0.33663366336633666, "grad_norm": 3.97957181930542, "learning_rate": 1.859569606987201e-06, "loss": 0.3364, "step": 561 }, { "epoch": 0.33723372337233726, "grad_norm": 3.5116031169891357, "learning_rate": 1.8583624066986475e-06, "loss": 0.3195, "step": 562 }, { "epoch": 0.33783378337833786, "grad_norm": 5.363343238830566, "learning_rate": 1.8571504351202724e-06, "loss": 0.3606, "step": 563 }, { "epoch": 0.3384338433843384, "grad_norm": 5.393948078155518, "learning_rate": 1.8559336989889365e-06, "loss": 0.4828, "step": 564 }, { "epoch": 0.339033903390339, "grad_norm": 5.0839104652404785, "learning_rate": 1.8547122050679845e-06, "loss": 0.3006, "step": 565 }, { "epoch": 0.3396339633963396, "grad_norm": 6.097001552581787, "learning_rate": 1.8534859601472071e-06, "loss": 0.5794, "step": 566 }, { "epoch": 0.3402340234023402, "grad_norm": 5.513222694396973, "learning_rate": 1.8522549710428047e-06, "loss": 0.6876, "step": 567 }, { "epoch": 0.3408340834083408, "grad_norm": 8.855300903320312, "learning_rate": 1.8510192445973483e-06, "loss": 0.7596, "step": 568 }, { "epoch": 0.3414341434143414, "grad_norm": 5.234973430633545, "learning_rate": 1.849778787679742e-06, "loss": 0.3945, "step": 569 }, { "epoch": 0.342034203420342, "grad_norm": 5.368997097015381, "learning_rate": 1.848533607185185e-06, "loss": 0.5879, "step": 570 }, { "epoch": 0.3426342634263426, "grad_norm": 6.87369441986084, "learning_rate": 1.8472837100351314e-06, "loss": 0.3753, "step": 571 }, { "epoch": 0.3432343234323432, "grad_norm": 5.220376968383789, "learning_rate": 1.846029103177256e-06, "loss": 0.5522, "step": 572 }, { "epoch": 0.3438343834383438, "grad_norm": 6.004208087921143, "learning_rate": 1.8447697935854104e-06, "loss": 0.6935, "step": 573 }, { "epoch": 0.34443444344434443, "grad_norm": 7.575113773345947, "learning_rate": 1.8435057882595881e-06, "loss": 0.677, "step": 574 }, { "epoch": 0.34503450345034503, "grad_norm": 6.148303985595703, "learning_rate": 1.8422370942258842e-06, "loss": 0.7311, "step": 575 }, { "epoch": 0.34563456345634563, "grad_norm": 6.1329426765441895, "learning_rate": 1.8409637185364562e-06, "loss": 0.8202, "step": 576 }, { "epoch": 0.34623462346234624, "grad_norm": 4.923066139221191, "learning_rate": 1.8396856682694848e-06, "loss": 0.4052, "step": 577 }, { "epoch": 0.34683468346834684, "grad_norm": 4.47619104385376, "learning_rate": 1.8384029505291355e-06, "loss": 0.3461, "step": 578 }, { "epoch": 0.34743474347434744, "grad_norm": 6.155852317810059, "learning_rate": 1.8371155724455176e-06, "loss": 0.4526, "step": 579 }, { "epoch": 0.34803480348034804, "grad_norm": 6.356205463409424, "learning_rate": 1.835823541174646e-06, "loss": 0.5926, "step": 580 }, { "epoch": 0.34863486348634865, "grad_norm": 3.3957676887512207, "learning_rate": 1.8345268638984e-06, "loss": 0.3458, "step": 581 }, { "epoch": 0.34923492349234925, "grad_norm": 5.77099084854126, "learning_rate": 1.8332255478244853e-06, "loss": 0.3881, "step": 582 }, { "epoch": 0.34983498349834985, "grad_norm": 5.593924522399902, "learning_rate": 1.8319196001863923e-06, "loss": 0.3748, "step": 583 }, { "epoch": 0.35043504350435045, "grad_norm": 7.017669677734375, "learning_rate": 1.830609028243356e-06, "loss": 0.7032, "step": 584 }, { "epoch": 0.35103510351035105, "grad_norm": 2.8958375453948975, "learning_rate": 1.8292938392803158e-06, "loss": 0.6372, "step": 585 }, { "epoch": 0.35163516351635166, "grad_norm": 6.337704181671143, "learning_rate": 1.8279740406078768e-06, "loss": 0.572, "step": 586 }, { "epoch": 0.35223522352235226, "grad_norm": 5.722931861877441, "learning_rate": 1.826649639562266e-06, "loss": 0.7946, "step": 587 }, { "epoch": 0.35283528352835286, "grad_norm": 3.964047431945801, "learning_rate": 1.8253206435052934e-06, "loss": 0.4293, "step": 588 }, { "epoch": 0.3534353435343534, "grad_norm": 5.640673637390137, "learning_rate": 1.823987059824312e-06, "loss": 0.6634, "step": 589 }, { "epoch": 0.354035403540354, "grad_norm": 4.193467617034912, "learning_rate": 1.8226488959321739e-06, "loss": 0.3429, "step": 590 }, { "epoch": 0.3546354635463546, "grad_norm": 4.498065948486328, "learning_rate": 1.8213061592671921e-06, "loss": 0.3998, "step": 591 }, { "epoch": 0.3552355235523552, "grad_norm": 5.879246234893799, "learning_rate": 1.8199588572930968e-06, "loss": 0.688, "step": 592 }, { "epoch": 0.3558355835583558, "grad_norm": 4.253992557525635, "learning_rate": 1.8186069974989957e-06, "loss": 0.533, "step": 593 }, { "epoch": 0.3564356435643564, "grad_norm": 6.31081485748291, "learning_rate": 1.8172505873993309e-06, "loss": 0.5483, "step": 594 }, { "epoch": 0.357035703570357, "grad_norm": 4.684574127197266, "learning_rate": 1.8158896345338384e-06, "loss": 0.4072, "step": 595 }, { "epoch": 0.3576357635763576, "grad_norm": 3.585331678390503, "learning_rate": 1.814524146467505e-06, "loss": 0.2238, "step": 596 }, { "epoch": 0.3582358235823582, "grad_norm": 5.146244049072266, "learning_rate": 1.8131541307905275e-06, "loss": 0.4021, "step": 597 }, { "epoch": 0.35883588358835883, "grad_norm": 4.295935153961182, "learning_rate": 1.8117795951182693e-06, "loss": 0.4612, "step": 598 }, { "epoch": 0.35943594359435943, "grad_norm": 5.90098237991333, "learning_rate": 1.810400547091219e-06, "loss": 0.4352, "step": 599 }, { "epoch": 0.36003600360036003, "grad_norm": 5.341614723205566, "learning_rate": 1.8090169943749474e-06, "loss": 0.3719, "step": 600 }, { "epoch": 0.36063606360636064, "grad_norm": 7.679795265197754, "learning_rate": 1.807628944660065e-06, "loss": 0.6037, "step": 601 }, { "epoch": 0.36123612361236124, "grad_norm": 6.436129093170166, "learning_rate": 1.8062364056621792e-06, "loss": 0.4957, "step": 602 }, { "epoch": 0.36183618361836184, "grad_norm": 6.149515628814697, "learning_rate": 1.804839385121852e-06, "loss": 0.5326, "step": 603 }, { "epoch": 0.36243624362436244, "grad_norm": 5.574273586273193, "learning_rate": 1.803437890804556e-06, "loss": 0.4875, "step": 604 }, { "epoch": 0.36303630363036304, "grad_norm": 5.0180511474609375, "learning_rate": 1.802031930500632e-06, "loss": 0.501, "step": 605 }, { "epoch": 0.36363636363636365, "grad_norm": 4.308007717132568, "learning_rate": 1.800621512025245e-06, "loss": 0.3953, "step": 606 }, { "epoch": 0.36423642364236425, "grad_norm": 3.961611032485962, "learning_rate": 1.799206643218342e-06, "loss": 0.3149, "step": 607 }, { "epoch": 0.36483648364836485, "grad_norm": 6.376758575439453, "learning_rate": 1.7977873319446063e-06, "loss": 0.6528, "step": 608 }, { "epoch": 0.36543654365436545, "grad_norm": 3.8240039348602295, "learning_rate": 1.7963635860934164e-06, "loss": 0.2634, "step": 609 }, { "epoch": 0.36603660366036606, "grad_norm": 4.728359222412109, "learning_rate": 1.7949354135788003e-06, "loss": 0.5946, "step": 610 }, { "epoch": 0.36663666366636666, "grad_norm": 7.042294025421143, "learning_rate": 1.7935028223393914e-06, "loss": 0.4824, "step": 611 }, { "epoch": 0.36723672367236726, "grad_norm": 4.367953300476074, "learning_rate": 1.7920658203383861e-06, "loss": 0.4147, "step": 612 }, { "epoch": 0.36783678367836786, "grad_norm": 4.679347515106201, "learning_rate": 1.790624415563498e-06, "loss": 0.407, "step": 613 }, { "epoch": 0.3684368436843684, "grad_norm": 4.80855655670166, "learning_rate": 1.7891786160269135e-06, "loss": 0.7275, "step": 614 }, { "epoch": 0.369036903690369, "grad_norm": 4.392421245574951, "learning_rate": 1.7877284297652487e-06, "loss": 0.361, "step": 615 }, { "epoch": 0.3696369636963696, "grad_norm": 5.658859729766846, "learning_rate": 1.7862738648395022e-06, "loss": 0.3635, "step": 616 }, { "epoch": 0.3702370237023702, "grad_norm": 5.335471153259277, "learning_rate": 1.7848149293350137e-06, "loss": 0.3938, "step": 617 }, { "epoch": 0.3708370837083708, "grad_norm": 4.309281826019287, "learning_rate": 1.7833516313614155e-06, "loss": 0.2711, "step": 618 }, { "epoch": 0.3714371437143714, "grad_norm": 5.6702446937561035, "learning_rate": 1.7818839790525904e-06, "loss": 0.3873, "step": 619 }, { "epoch": 0.372037203720372, "grad_norm": 6.463081359863281, "learning_rate": 1.7804119805666241e-06, "loss": 0.7062, "step": 620 }, { "epoch": 0.3726372637263726, "grad_norm": 4.436067581176758, "learning_rate": 1.7789356440857618e-06, "loss": 0.3685, "step": 621 }, { "epoch": 0.3732373237323732, "grad_norm": 4.895203590393066, "learning_rate": 1.7774549778163616e-06, "loss": 0.4001, "step": 622 }, { "epoch": 0.37383738373837383, "grad_norm": 5.55206298828125, "learning_rate": 1.775969989988849e-06, "loss": 0.3376, "step": 623 }, { "epoch": 0.37443744374437443, "grad_norm": 4.76421594619751, "learning_rate": 1.7744806888576708e-06, "loss": 0.3706, "step": 624 }, { "epoch": 0.37503750375037503, "grad_norm": 5.808158874511719, "learning_rate": 1.7729870827012511e-06, "loss": 0.6678, "step": 625 }, { "epoch": 0.37563756375637564, "grad_norm": 3.8307242393493652, "learning_rate": 1.771489179821943e-06, "loss": 0.3382, "step": 626 }, { "epoch": 0.37623762376237624, "grad_norm": 4.0017828941345215, "learning_rate": 1.7699869885459826e-06, "loss": 0.4248, "step": 627 }, { "epoch": 0.37683768376837684, "grad_norm": 6.496377944946289, "learning_rate": 1.7684805172234452e-06, "loss": 0.8466, "step": 628 }, { "epoch": 0.37743774377437744, "grad_norm": 10.618154525756836, "learning_rate": 1.7669697742281958e-06, "loss": 0.4908, "step": 629 }, { "epoch": 0.37803780378037805, "grad_norm": 5.841583251953125, "learning_rate": 1.7654547679578441e-06, "loss": 0.5991, "step": 630 }, { "epoch": 0.37863786378637865, "grad_norm": 5.667387008666992, "learning_rate": 1.7639355068336985e-06, "loss": 0.4904, "step": 631 }, { "epoch": 0.37923792379237925, "grad_norm": 4.364107131958008, "learning_rate": 1.7624119993007173e-06, "loss": 0.5529, "step": 632 }, { "epoch": 0.37983798379837985, "grad_norm": 4.944308757781982, "learning_rate": 1.7608842538274638e-06, "loss": 0.5246, "step": 633 }, { "epoch": 0.38043804380438045, "grad_norm": 5.93478536605835, "learning_rate": 1.7593522789060571e-06, "loss": 0.4751, "step": 634 }, { "epoch": 0.38103810381038106, "grad_norm": 5.5711750984191895, "learning_rate": 1.7578160830521274e-06, "loss": 0.3304, "step": 635 }, { "epoch": 0.38163816381638166, "grad_norm": 3.4833922386169434, "learning_rate": 1.7562756748047667e-06, "loss": 0.5078, "step": 636 }, { "epoch": 0.38223822382238226, "grad_norm": 5.204996109008789, "learning_rate": 1.7547310627264817e-06, "loss": 0.2728, "step": 637 }, { "epoch": 0.38283828382838286, "grad_norm": 4.840295791625977, "learning_rate": 1.7531822554031478e-06, "loss": 0.3281, "step": 638 }, { "epoch": 0.38343834383438347, "grad_norm": 5.001806735992432, "learning_rate": 1.7516292614439584e-06, "loss": 0.3097, "step": 639 }, { "epoch": 0.384038403840384, "grad_norm": 4.348320484161377, "learning_rate": 1.7500720894813795e-06, "loss": 0.3006, "step": 640 }, { "epoch": 0.3846384638463846, "grad_norm": 5.249353885650635, "learning_rate": 1.748510748171101e-06, "loss": 0.354, "step": 641 }, { "epoch": 0.3852385238523852, "grad_norm": 6.78068733215332, "learning_rate": 1.7469452461919887e-06, "loss": 0.4066, "step": 642 }, { "epoch": 0.3858385838583858, "grad_norm": 5.4199323654174805, "learning_rate": 1.7453755922460354e-06, "loss": 0.8086, "step": 643 }, { "epoch": 0.3864386438643864, "grad_norm": 3.316554307937622, "learning_rate": 1.7438017950583131e-06, "loss": 0.1742, "step": 644 }, { "epoch": 0.387038703870387, "grad_norm": 4.080990314483643, "learning_rate": 1.7422238633769247e-06, "loss": 0.4405, "step": 645 }, { "epoch": 0.3876387638763876, "grad_norm": 5.687505722045898, "learning_rate": 1.7406418059729546e-06, "loss": 0.5722, "step": 646 }, { "epoch": 0.38823882388238823, "grad_norm": 4.291781425476074, "learning_rate": 1.7390556316404212e-06, "loss": 0.4158, "step": 647 }, { "epoch": 0.38883888388838883, "grad_norm": 3.9679338932037354, "learning_rate": 1.7374653491962263e-06, "loss": 0.3563, "step": 648 }, { "epoch": 0.38943894389438943, "grad_norm": 5.350450038909912, "learning_rate": 1.7358709674801082e-06, "loss": 0.4222, "step": 649 }, { "epoch": 0.39003900390039004, "grad_norm": 4.633026123046875, "learning_rate": 1.7342724953545897e-06, "loss": 0.4352, "step": 650 }, { "epoch": 0.39063906390639064, "grad_norm": 4.33645486831665, "learning_rate": 1.7326699417049322e-06, "loss": 0.549, "step": 651 }, { "epoch": 0.39123912391239124, "grad_norm": 5.41543436050415, "learning_rate": 1.731063315439084e-06, "loss": 0.4213, "step": 652 }, { "epoch": 0.39183918391839184, "grad_norm": 4.596231937408447, "learning_rate": 1.7294526254876306e-06, "loss": 0.4048, "step": 653 }, { "epoch": 0.39243924392439244, "grad_norm": 5.74515962600708, "learning_rate": 1.7278378808037476e-06, "loss": 0.8659, "step": 654 }, { "epoch": 0.39303930393039305, "grad_norm": 5.824306964874268, "learning_rate": 1.7262190903631483e-06, "loss": 0.6112, "step": 655 }, { "epoch": 0.39363936393639365, "grad_norm": 4.042995929718018, "learning_rate": 1.7245962631640341e-06, "loss": 0.3229, "step": 656 }, { "epoch": 0.39423942394239425, "grad_norm": 5.518403053283691, "learning_rate": 1.7229694082270464e-06, "loss": 0.5147, "step": 657 }, { "epoch": 0.39483948394839485, "grad_norm": 5.906860828399658, "learning_rate": 1.7213385345952136e-06, "loss": 0.3924, "step": 658 }, { "epoch": 0.39543954395439546, "grad_norm": 4.683358669281006, "learning_rate": 1.7197036513339042e-06, "loss": 0.4128, "step": 659 }, { "epoch": 0.39603960396039606, "grad_norm": 4.0641984939575195, "learning_rate": 1.7180647675307736e-06, "loss": 0.3087, "step": 660 }, { "epoch": 0.39663966396639666, "grad_norm": 4.0073981285095215, "learning_rate": 1.7164218922957142e-06, "loss": 0.3846, "step": 661 }, { "epoch": 0.39723972397239726, "grad_norm": 3.6291048526763916, "learning_rate": 1.714775034760806e-06, "loss": 0.4814, "step": 662 }, { "epoch": 0.39783978397839787, "grad_norm": 5.771547317504883, "learning_rate": 1.713124204080265e-06, "loss": 0.6665, "step": 663 }, { "epoch": 0.39843984398439847, "grad_norm": 5.576371192932129, "learning_rate": 1.7114694094303913e-06, "loss": 0.7304, "step": 664 }, { "epoch": 0.399039903990399, "grad_norm": 3.872398614883423, "learning_rate": 1.7098106600095203e-06, "loss": 0.34, "step": 665 }, { "epoch": 0.3996399639963996, "grad_norm": 5.0916666984558105, "learning_rate": 1.7081479650379696e-06, "loss": 0.3561, "step": 666 }, { "epoch": 0.4002400240024002, "grad_norm": 5.113712310791016, "learning_rate": 1.7064813337579889e-06, "loss": 0.4846, "step": 667 }, { "epoch": 0.4008400840084008, "grad_norm": 4.820123672485352, "learning_rate": 1.704810775433708e-06, "loss": 0.7192, "step": 668 }, { "epoch": 0.4014401440144014, "grad_norm": 4.823460578918457, "learning_rate": 1.7031362993510857e-06, "loss": 0.4532, "step": 669 }, { "epoch": 0.402040204020402, "grad_norm": 7.385868072509766, "learning_rate": 1.7014579148178583e-06, "loss": 0.631, "step": 670 }, { "epoch": 0.40264026402640263, "grad_norm": 4.980685234069824, "learning_rate": 1.6997756311634871e-06, "loss": 0.367, "step": 671 }, { "epoch": 0.40324032403240323, "grad_norm": 5.36509370803833, "learning_rate": 1.6980894577391073e-06, "loss": 0.5378, "step": 672 }, { "epoch": 0.40384038403840383, "grad_norm": 4.826319217681885, "learning_rate": 1.6963994039174754e-06, "loss": 0.6465, "step": 673 }, { "epoch": 0.40444044404440443, "grad_norm": 5.189273357391357, "learning_rate": 1.6947054790929186e-06, "loss": 0.5392, "step": 674 }, { "epoch": 0.40504050405040504, "grad_norm": 3.9050798416137695, "learning_rate": 1.6930076926812795e-06, "loss": 0.6411, "step": 675 }, { "epoch": 0.40564056405640564, "grad_norm": 5.283854007720947, "learning_rate": 1.6913060541198676e-06, "loss": 0.4222, "step": 676 }, { "epoch": 0.40624062406240624, "grad_norm": 5.372036457061768, "learning_rate": 1.6896005728674041e-06, "loss": 0.7492, "step": 677 }, { "epoch": 0.40684068406840684, "grad_norm": 7.499129295349121, "learning_rate": 1.6878912584039697e-06, "loss": 0.8807, "step": 678 }, { "epoch": 0.40744074407440745, "grad_norm": 5.732782363891602, "learning_rate": 1.6861781202309536e-06, "loss": 0.7381, "step": 679 }, { "epoch": 0.40804080408040805, "grad_norm": 5.280449390411377, "learning_rate": 1.6844611678709987e-06, "loss": 0.6198, "step": 680 }, { "epoch": 0.40864086408640865, "grad_norm": 3.0149168968200684, "learning_rate": 1.6827404108679484e-06, "loss": 0.2857, "step": 681 }, { "epoch": 0.40924092409240925, "grad_norm": 4.049551010131836, "learning_rate": 1.681015858786797e-06, "loss": 0.3259, "step": 682 }, { "epoch": 0.40984098409840986, "grad_norm": 3.577524423599243, "learning_rate": 1.6792875212136322e-06, "loss": 0.2893, "step": 683 }, { "epoch": 0.41044104410441046, "grad_norm": 5.052558422088623, "learning_rate": 1.6775554077555845e-06, "loss": 0.3248, "step": 684 }, { "epoch": 0.41104110411041106, "grad_norm": 5.709980487823486, "learning_rate": 1.6758195280407726e-06, "loss": 0.4751, "step": 685 }, { "epoch": 0.41164116411641166, "grad_norm": 3.9886090755462646, "learning_rate": 1.67407989171825e-06, "loss": 0.7437, "step": 686 }, { "epoch": 0.41224122412241226, "grad_norm": 2.705216884613037, "learning_rate": 1.672336508457953e-06, "loss": 0.8023, "step": 687 }, { "epoch": 0.41284128412841287, "grad_norm": 3.8731565475463867, "learning_rate": 1.6705893879506444e-06, "loss": 0.3608, "step": 688 }, { "epoch": 0.41344134413441347, "grad_norm": 4.443881988525391, "learning_rate": 1.6688385399078615e-06, "loss": 0.2983, "step": 689 }, { "epoch": 0.414041404140414, "grad_norm": 4.752226829528809, "learning_rate": 1.667083974061861e-06, "loss": 0.4387, "step": 690 }, { "epoch": 0.4146414641464146, "grad_norm": 3.676654100418091, "learning_rate": 1.665325700165565e-06, "loss": 0.2961, "step": 691 }, { "epoch": 0.4152415241524152, "grad_norm": 4.735508441925049, "learning_rate": 1.663563727992509e-06, "loss": 0.4279, "step": 692 }, { "epoch": 0.4158415841584158, "grad_norm": 4.938470363616943, "learning_rate": 1.6617980673367833e-06, "loss": 0.4743, "step": 693 }, { "epoch": 0.4164416441644164, "grad_norm": 4.228601932525635, "learning_rate": 1.6600287280129825e-06, "loss": 0.4789, "step": 694 }, { "epoch": 0.417041704170417, "grad_norm": 3.2888522148132324, "learning_rate": 1.6582557198561488e-06, "loss": 0.3789, "step": 695 }, { "epoch": 0.41764176417641763, "grad_norm": 2.7508606910705566, "learning_rate": 1.656479052721719e-06, "loss": 0.2172, "step": 696 }, { "epoch": 0.41824182418241823, "grad_norm": 5.45565938949585, "learning_rate": 1.654698736485467e-06, "loss": 0.4087, "step": 697 }, { "epoch": 0.41884188418841883, "grad_norm": 6.736683368682861, "learning_rate": 1.6529147810434515e-06, "loss": 0.7339, "step": 698 }, { "epoch": 0.41944194419441944, "grad_norm": 6.219265460968018, "learning_rate": 1.6511271963119609e-06, "loss": 0.5227, "step": 699 }, { "epoch": 0.42004200420042004, "grad_norm": 4.636746883392334, "learning_rate": 1.6493359922274556e-06, "loss": 0.4981, "step": 700 }, { "epoch": 0.42064206420642064, "grad_norm": 6.402501106262207, "learning_rate": 1.6475411787465162e-06, "loss": 1.1252, "step": 701 }, { "epoch": 0.42124212421242124, "grad_norm": 3.7206709384918213, "learning_rate": 1.6457427658457848e-06, "loss": 0.3603, "step": 702 }, { "epoch": 0.42184218421842185, "grad_norm": 4.448443412780762, "learning_rate": 1.6439407635219127e-06, "loss": 0.3609, "step": 703 }, { "epoch": 0.42244224422442245, "grad_norm": 5.7209930419921875, "learning_rate": 1.6421351817915023e-06, "loss": 0.5539, "step": 704 }, { "epoch": 0.42304230423042305, "grad_norm": 3.3060951232910156, "learning_rate": 1.640326030691054e-06, "loss": 0.3243, "step": 705 }, { "epoch": 0.42364236423642365, "grad_norm": 4.8098344802856445, "learning_rate": 1.6385133202769068e-06, "loss": 0.4655, "step": 706 }, { "epoch": 0.42424242424242425, "grad_norm": 7.097172737121582, "learning_rate": 1.636697060625186e-06, "loss": 0.992, "step": 707 }, { "epoch": 0.42484248424842486, "grad_norm": 5.236241817474365, "learning_rate": 1.6348772618317446e-06, "loss": 0.2561, "step": 708 }, { "epoch": 0.42544254425442546, "grad_norm": 4.426169395446777, "learning_rate": 1.6330539340121097e-06, "loss": 0.3868, "step": 709 }, { "epoch": 0.42604260426042606, "grad_norm": 4.224999904632568, "learning_rate": 1.6312270873014233e-06, "loss": 0.298, "step": 710 }, { "epoch": 0.42664266426642666, "grad_norm": 6.087056636810303, "learning_rate": 1.6293967318543885e-06, "loss": 0.4886, "step": 711 }, { "epoch": 0.42724272427242727, "grad_norm": 4.311059474945068, "learning_rate": 1.6275628778452118e-06, "loss": 0.5552, "step": 712 }, { "epoch": 0.42784278427842787, "grad_norm": 3.4417150020599365, "learning_rate": 1.6257255354675462e-06, "loss": 0.2054, "step": 713 }, { "epoch": 0.42844284428442847, "grad_norm": 4.526127338409424, "learning_rate": 1.6238847149344369e-06, "loss": 0.2884, "step": 714 }, { "epoch": 0.429042904290429, "grad_norm": 5.664350509643555, "learning_rate": 1.62204042647826e-06, "loss": 0.4304, "step": 715 }, { "epoch": 0.4296429642964296, "grad_norm": 7.69163703918457, "learning_rate": 1.6201926803506707e-06, "loss": 0.7485, "step": 716 }, { "epoch": 0.4302430243024302, "grad_norm": 6.344058513641357, "learning_rate": 1.618341486822543e-06, "loss": 0.9238, "step": 717 }, { "epoch": 0.4308430843084308, "grad_norm": 5.314466953277588, "learning_rate": 1.6164868561839136e-06, "loss": 0.6623, "step": 718 }, { "epoch": 0.4314431443144314, "grad_norm": 5.778144836425781, "learning_rate": 1.6146287987439254e-06, "loss": 0.6953, "step": 719 }, { "epoch": 0.43204320432043203, "grad_norm": 6.259482383728027, "learning_rate": 1.6127673248307687e-06, "loss": 0.4677, "step": 720 }, { "epoch": 0.43264326432643263, "grad_norm": 4.367031574249268, "learning_rate": 1.610902444791625e-06, "loss": 0.3888, "step": 721 }, { "epoch": 0.43324332433243323, "grad_norm": 4.706819534301758, "learning_rate": 1.6090341689926091e-06, "loss": 0.626, "step": 722 }, { "epoch": 0.43384338433843384, "grad_norm": 5.881278038024902, "learning_rate": 1.6071625078187112e-06, "loss": 0.8019, "step": 723 }, { "epoch": 0.43444344434443444, "grad_norm": 3.5819509029388428, "learning_rate": 1.6052874716737392e-06, "loss": 0.3111, "step": 724 }, { "epoch": 0.43504350435043504, "grad_norm": 3.4039242267608643, "learning_rate": 1.6034090709802622e-06, "loss": 0.4171, "step": 725 }, { "epoch": 0.43564356435643564, "grad_norm": 5.875030040740967, "learning_rate": 1.6015273161795505e-06, "loss": 0.5076, "step": 726 }, { "epoch": 0.43624362436243624, "grad_norm": 5.509462356567383, "learning_rate": 1.5996422177315182e-06, "loss": 0.6183, "step": 727 }, { "epoch": 0.43684368436843685, "grad_norm": 5.580371379852295, "learning_rate": 1.5977537861146667e-06, "loss": 0.9548, "step": 728 }, { "epoch": 0.43744374437443745, "grad_norm": 4.7416863441467285, "learning_rate": 1.5958620318260238e-06, "loss": 0.4039, "step": 729 }, { "epoch": 0.43804380438043805, "grad_norm": 6.079616546630859, "learning_rate": 1.593966965381088e-06, "loss": 0.3916, "step": 730 }, { "epoch": 0.43864386438643865, "grad_norm": 4.23826789855957, "learning_rate": 1.5920685973137671e-06, "loss": 0.5756, "step": 731 }, { "epoch": 0.43924392439243926, "grad_norm": 6.513110637664795, "learning_rate": 1.5901669381763228e-06, "loss": 0.4306, "step": 732 }, { "epoch": 0.43984398439843986, "grad_norm": 4.981919765472412, "learning_rate": 1.58826199853931e-06, "loss": 0.3981, "step": 733 }, { "epoch": 0.44044404440444046, "grad_norm": 4.52602481842041, "learning_rate": 1.5863537889915182e-06, "loss": 0.3435, "step": 734 }, { "epoch": 0.44104410441044106, "grad_norm": 3.6358017921447754, "learning_rate": 1.5844423201399133e-06, "loss": 0.5701, "step": 735 }, { "epoch": 0.44164416441644166, "grad_norm": 6.601095199584961, "learning_rate": 1.5825276026095788e-06, "loss": 0.6037, "step": 736 }, { "epoch": 0.44224422442244227, "grad_norm": 3.955205202102661, "learning_rate": 1.5806096470436553e-06, "loss": 0.3468, "step": 737 }, { "epoch": 0.44284428442844287, "grad_norm": 6.244051933288574, "learning_rate": 1.5786884641032833e-06, "loss": 0.2868, "step": 738 }, { "epoch": 0.44344434443444347, "grad_norm": 6.168961048126221, "learning_rate": 1.5767640644675427e-06, "loss": 0.6205, "step": 739 }, { "epoch": 0.444044404440444, "grad_norm": 5.227019309997559, "learning_rate": 1.5748364588333928e-06, "loss": 0.4284, "step": 740 }, { "epoch": 0.4446444644464446, "grad_norm": 3.526575803756714, "learning_rate": 1.5729056579156152e-06, "loss": 0.4416, "step": 741 }, { "epoch": 0.4452445244524452, "grad_norm": 4.596634387969971, "learning_rate": 1.570971672446752e-06, "loss": 0.4405, "step": 742 }, { "epoch": 0.4458445844584458, "grad_norm": 8.053309440612793, "learning_rate": 1.5690345131770473e-06, "loss": 0.5392, "step": 743 }, { "epoch": 0.4464446444644464, "grad_norm": 5.659903049468994, "learning_rate": 1.567094190874386e-06, "loss": 0.5917, "step": 744 }, { "epoch": 0.44704470447044703, "grad_norm": 5.025071620941162, "learning_rate": 1.5651507163242366e-06, "loss": 0.8622, "step": 745 }, { "epoch": 0.44764476447644763, "grad_norm": 6.308159828186035, "learning_rate": 1.5632041003295885e-06, "loss": 0.3572, "step": 746 }, { "epoch": 0.44824482448244823, "grad_norm": 5.619739055633545, "learning_rate": 1.561254353710894e-06, "loss": 0.4587, "step": 747 }, { "epoch": 0.44884488448844884, "grad_norm": 5.929537773132324, "learning_rate": 1.5593014873060064e-06, "loss": 0.5909, "step": 748 }, { "epoch": 0.44944494449444944, "grad_norm": 4.586866855621338, "learning_rate": 1.5573455119701212e-06, "loss": 0.3928, "step": 749 }, { "epoch": 0.45004500450045004, "grad_norm": 6.065807342529297, "learning_rate": 1.5553864385757149e-06, "loss": 0.4287, "step": 750 }, { "epoch": 0.45064506450645064, "grad_norm": 3.670203447341919, "learning_rate": 1.553424278012485e-06, "loss": 0.3528, "step": 751 }, { "epoch": 0.45124512451245125, "grad_norm": 3.782778739929199, "learning_rate": 1.5514590411872898e-06, "loss": 0.3204, "step": 752 }, { "epoch": 0.45184518451845185, "grad_norm": 5.6687421798706055, "learning_rate": 1.5494907390240864e-06, "loss": 0.5634, "step": 753 }, { "epoch": 0.45244524452445245, "grad_norm": 5.590949535369873, "learning_rate": 1.547519382463871e-06, "loss": 0.4775, "step": 754 }, { "epoch": 0.45304530453045305, "grad_norm": 5.091954231262207, "learning_rate": 1.5455449824646185e-06, "loss": 0.3522, "step": 755 }, { "epoch": 0.45364536453645365, "grad_norm": 4.521096706390381, "learning_rate": 1.5435675500012212e-06, "loss": 0.3114, "step": 756 }, { "epoch": 0.45424542454245426, "grad_norm": 3.2946131229400635, "learning_rate": 1.5415870960654265e-06, "loss": 0.2837, "step": 757 }, { "epoch": 0.45484548454845486, "grad_norm": 4.738945960998535, "learning_rate": 1.5396036316657783e-06, "loss": 0.4979, "step": 758 }, { "epoch": 0.45544554455445546, "grad_norm": 4.307953357696533, "learning_rate": 1.5376171678275535e-06, "loss": 0.4328, "step": 759 }, { "epoch": 0.45604560456045606, "grad_norm": 5.734379768371582, "learning_rate": 1.5356277155927022e-06, "loss": 0.4486, "step": 760 }, { "epoch": 0.45664566456645667, "grad_norm": 5.138350009918213, "learning_rate": 1.5336352860197857e-06, "loss": 0.5329, "step": 761 }, { "epoch": 0.45724572457245727, "grad_norm": 4.0475568771362305, "learning_rate": 1.5316398901839145e-06, "loss": 0.3165, "step": 762 }, { "epoch": 0.45784578457845787, "grad_norm": 5.590096950531006, "learning_rate": 1.5296415391766883e-06, "loss": 0.5292, "step": 763 }, { "epoch": 0.4584458445844585, "grad_norm": 3.0955121517181396, "learning_rate": 1.5276402441061327e-06, "loss": 0.2794, "step": 764 }, { "epoch": 0.459045904590459, "grad_norm": 5.91021728515625, "learning_rate": 1.5256360160966387e-06, "loss": 0.4807, "step": 765 }, { "epoch": 0.4596459645964596, "grad_norm": 7.01305627822876, "learning_rate": 1.5236288662888999e-06, "loss": 0.75, "step": 766 }, { "epoch": 0.4602460246024602, "grad_norm": 5.165713310241699, "learning_rate": 1.5216188058398508e-06, "loss": 0.5824, "step": 767 }, { "epoch": 0.4608460846084608, "grad_norm": 4.670100212097168, "learning_rate": 1.5196058459226062e-06, "loss": 0.4204, "step": 768 }, { "epoch": 0.46144614461446143, "grad_norm": 4.761223793029785, "learning_rate": 1.517589997726396e-06, "loss": 0.5139, "step": 769 }, { "epoch": 0.46204620462046203, "grad_norm": 6.22670841217041, "learning_rate": 1.515571272456507e-06, "loss": 1.0033, "step": 770 }, { "epoch": 0.46264626462646263, "grad_norm": 6.053716659545898, "learning_rate": 1.5135496813342169e-06, "loss": 0.55, "step": 771 }, { "epoch": 0.46324632463246324, "grad_norm": 6.135822296142578, "learning_rate": 1.511525235596733e-06, "loss": 0.6111, "step": 772 }, { "epoch": 0.46384638463846384, "grad_norm": 6.067349910736084, "learning_rate": 1.5094979464971324e-06, "loss": 0.496, "step": 773 }, { "epoch": 0.46444644464446444, "grad_norm": 3.7796874046325684, "learning_rate": 1.5074678253042956e-06, "loss": 0.2876, "step": 774 }, { "epoch": 0.46504650465046504, "grad_norm": 4.7136125564575195, "learning_rate": 1.5054348833028467e-06, "loss": 0.4425, "step": 775 }, { "epoch": 0.46564656465646564, "grad_norm": 3.941153049468994, "learning_rate": 1.5033991317930884e-06, "loss": 0.4476, "step": 776 }, { "epoch": 0.46624662466246625, "grad_norm": 6.139411449432373, "learning_rate": 1.5013605820909407e-06, "loss": 0.4264, "step": 777 }, { "epoch": 0.46684668466846685, "grad_norm": 3.976081371307373, "learning_rate": 1.4993192455278782e-06, "loss": 0.3482, "step": 778 }, { "epoch": 0.46744674467446745, "grad_norm": 4.396040916442871, "learning_rate": 1.497275133450866e-06, "loss": 0.6873, "step": 779 }, { "epoch": 0.46804680468046805, "grad_norm": 3.7363405227661133, "learning_rate": 1.4952282572222972e-06, "loss": 0.5052, "step": 780 }, { "epoch": 0.46864686468646866, "grad_norm": 4.7696380615234375, "learning_rate": 1.4931786282199297e-06, "loss": 0.3583, "step": 781 }, { "epoch": 0.46924692469246926, "grad_norm": 3.6509058475494385, "learning_rate": 1.491126257836823e-06, "loss": 0.4098, "step": 782 }, { "epoch": 0.46984698469846986, "grad_norm": 5.52258825302124, "learning_rate": 1.4890711574812752e-06, "loss": 0.6306, "step": 783 }, { "epoch": 0.47044704470447046, "grad_norm": 5.45673131942749, "learning_rate": 1.4870133385767587e-06, "loss": 0.3759, "step": 784 }, { "epoch": 0.47104710471047107, "grad_norm": 4.78626823425293, "learning_rate": 1.4849528125618572e-06, "loss": 0.6572, "step": 785 }, { "epoch": 0.47164716471647167, "grad_norm": 7.198662281036377, "learning_rate": 1.4828895908902026e-06, "loss": 0.7292, "step": 786 }, { "epoch": 0.47224722472247227, "grad_norm": 4.261144638061523, "learning_rate": 1.48082368503041e-06, "loss": 0.3564, "step": 787 }, { "epoch": 0.47284728472847287, "grad_norm": 4.75494384765625, "learning_rate": 1.4787551064660165e-06, "loss": 0.8001, "step": 788 }, { "epoch": 0.4734473447344735, "grad_norm": 5.557277202606201, "learning_rate": 1.4766838666954135e-06, "loss": 0.5019, "step": 789 }, { "epoch": 0.474047404740474, "grad_norm": 5.950959205627441, "learning_rate": 1.4746099772317865e-06, "loss": 0.6047, "step": 790 }, { "epoch": 0.4746474647464746, "grad_norm": 4.725796222686768, "learning_rate": 1.4725334496030491e-06, "loss": 0.5736, "step": 791 }, { "epoch": 0.4752475247524752, "grad_norm": 6.42291784286499, "learning_rate": 1.4704542953517794e-06, "loss": 0.4824, "step": 792 }, { "epoch": 0.47584758475847583, "grad_norm": 4.2159833908081055, "learning_rate": 1.468372526035156e-06, "loss": 0.434, "step": 793 }, { "epoch": 0.47644764476447643, "grad_norm": 5.091263294219971, "learning_rate": 1.4662881532248936e-06, "loss": 0.5487, "step": 794 }, { "epoch": 0.47704770477047703, "grad_norm": 3.6415717601776123, "learning_rate": 1.4642011885071779e-06, "loss": 0.3364, "step": 795 }, { "epoch": 0.47764776477647763, "grad_norm": 4.673677921295166, "learning_rate": 1.4621116434826029e-06, "loss": 0.397, "step": 796 }, { "epoch": 0.47824782478247824, "grad_norm": 3.4471774101257324, "learning_rate": 1.4600195297661053e-06, "loss": 0.5839, "step": 797 }, { "epoch": 0.47884788478847884, "grad_norm": 3.728508949279785, "learning_rate": 1.4579248589869e-06, "loss": 0.3934, "step": 798 }, { "epoch": 0.47944794479447944, "grad_norm": 5.190072536468506, "learning_rate": 1.4558276427884155e-06, "loss": 0.3482, "step": 799 }, { "epoch": 0.48004800480048004, "grad_norm": 4.97143030166626, "learning_rate": 1.4537278928282291e-06, "loss": 0.4275, "step": 800 }, { "epoch": 0.48064806480648065, "grad_norm": 3.9655086994171143, "learning_rate": 1.451625620778003e-06, "loss": 0.4131, "step": 801 }, { "epoch": 0.48124812481248125, "grad_norm": 5.337774276733398, "learning_rate": 1.4495208383234173e-06, "loss": 0.5663, "step": 802 }, { "epoch": 0.48184818481848185, "grad_norm": 5.165792465209961, "learning_rate": 1.4474135571641085e-06, "loss": 0.4324, "step": 803 }, { "epoch": 0.48244824482448245, "grad_norm": 4.7760162353515625, "learning_rate": 1.4453037890136002e-06, "loss": 0.4109, "step": 804 }, { "epoch": 0.48304830483048306, "grad_norm": 4.487942695617676, "learning_rate": 1.4431915455992414e-06, "loss": 0.4045, "step": 805 }, { "epoch": 0.48364836483648366, "grad_norm": 5.201391220092773, "learning_rate": 1.4410768386621397e-06, "loss": 0.5731, "step": 806 }, { "epoch": 0.48424842484248426, "grad_norm": 4.889127254486084, "learning_rate": 1.4389596799570973e-06, "loss": 0.3692, "step": 807 }, { "epoch": 0.48484848484848486, "grad_norm": 4.910383224487305, "learning_rate": 1.4368400812525433e-06, "loss": 0.5416, "step": 808 }, { "epoch": 0.48544854485448546, "grad_norm": 5.0979509353637695, "learning_rate": 1.4347180543304704e-06, "loss": 0.5639, "step": 809 }, { "epoch": 0.48604860486048607, "grad_norm": 6.374374866485596, "learning_rate": 1.4325936109863698e-06, "loss": 0.3805, "step": 810 }, { "epoch": 0.48664866486648667, "grad_norm": 4.882211208343506, "learning_rate": 1.430466763029163e-06, "loss": 0.869, "step": 811 }, { "epoch": 0.48724872487248727, "grad_norm": 4.3043317794799805, "learning_rate": 1.4283375222811388e-06, "loss": 0.372, "step": 812 }, { "epoch": 0.4878487848784879, "grad_norm": 5.973501682281494, "learning_rate": 1.4262059005778863e-06, "loss": 0.4921, "step": 813 }, { "epoch": 0.4884488448844885, "grad_norm": 4.475889682769775, "learning_rate": 1.424071909768229e-06, "loss": 0.6013, "step": 814 }, { "epoch": 0.489048904890489, "grad_norm": 7.119530200958252, "learning_rate": 1.4219355617141598e-06, "loss": 0.8999, "step": 815 }, { "epoch": 0.4896489648964896, "grad_norm": 3.166893720626831, "learning_rate": 1.4197968682907746e-06, "loss": 0.3002, "step": 816 }, { "epoch": 0.4902490249024902, "grad_norm": 3.747251033782959, "learning_rate": 1.417655841386206e-06, "loss": 0.3217, "step": 817 }, { "epoch": 0.49084908490849083, "grad_norm": 4.308593273162842, "learning_rate": 1.4155124929015571e-06, "loss": 0.3575, "step": 818 }, { "epoch": 0.49144914491449143, "grad_norm": 4.147584915161133, "learning_rate": 1.4133668347508368e-06, "loss": 0.3889, "step": 819 }, { "epoch": 0.49204920492049203, "grad_norm": 4.099583148956299, "learning_rate": 1.4112188788608913e-06, "loss": 0.7069, "step": 820 }, { "epoch": 0.49264926492649264, "grad_norm": 3.2067313194274902, "learning_rate": 1.40906863717134e-06, "loss": 0.1875, "step": 821 }, { "epoch": 0.49324932493249324, "grad_norm": 4.877295970916748, "learning_rate": 1.4069161216345073e-06, "loss": 0.3605, "step": 822 }, { "epoch": 0.49384938493849384, "grad_norm": 5.682559490203857, "learning_rate": 1.404761344215358e-06, "loss": 0.5934, "step": 823 }, { "epoch": 0.49444944494449444, "grad_norm": 3.741638422012329, "learning_rate": 1.4026043168914286e-06, "loss": 0.609, "step": 824 }, { "epoch": 0.49504950495049505, "grad_norm": 4.363954067230225, "learning_rate": 1.4004450516527628e-06, "loss": 0.2927, "step": 825 }, { "epoch": 0.49564956495649565, "grad_norm": 3.5540928840637207, "learning_rate": 1.3982835605018436e-06, "loss": 0.3625, "step": 826 }, { "epoch": 0.49624962496249625, "grad_norm": 3.571475028991699, "learning_rate": 1.3961198554535273e-06, "loss": 0.3152, "step": 827 }, { "epoch": 0.49684968496849685, "grad_norm": 13.052854537963867, "learning_rate": 1.3939539485349751e-06, "loss": 0.4063, "step": 828 }, { "epoch": 0.49744974497449745, "grad_norm": 3.021806240081787, "learning_rate": 1.3917858517855898e-06, "loss": 0.3545, "step": 829 }, { "epoch": 0.49804980498049806, "grad_norm": 5.264845371246338, "learning_rate": 1.3896155772569448e-06, "loss": 0.6545, "step": 830 }, { "epoch": 0.49864986498649866, "grad_norm": 4.914987564086914, "learning_rate": 1.3874431370127186e-06, "loss": 0.4722, "step": 831 }, { "epoch": 0.49924992499249926, "grad_norm": 5.442652702331543, "learning_rate": 1.38526854312863e-06, "loss": 0.4529, "step": 832 }, { "epoch": 0.49984998499849986, "grad_norm": 4.035576820373535, "learning_rate": 1.383091807692367e-06, "loss": 0.638, "step": 833 }, { "epoch": 0.5004500450045004, "grad_norm": 4.516945838928223, "learning_rate": 1.3809129428035227e-06, "loss": 0.3119, "step": 834 }, { "epoch": 0.5010501050105011, "grad_norm": 6.321439743041992, "learning_rate": 1.378731960573527e-06, "loss": 0.8218, "step": 835 }, { "epoch": 0.5016501650165016, "grad_norm": 6.273803234100342, "learning_rate": 1.3765488731255784e-06, "loss": 0.7983, "step": 836 }, { "epoch": 0.5022502250225023, "grad_norm": 5.16572380065918, "learning_rate": 1.374363692594578e-06, "loss": 0.4829, "step": 837 }, { "epoch": 0.5028502850285028, "grad_norm": 5.080145359039307, "learning_rate": 1.3721764311270623e-06, "loss": 0.667, "step": 838 }, { "epoch": 0.5034503450345035, "grad_norm": 3.6394031047821045, "learning_rate": 1.3699871008811332e-06, "loss": 0.3112, "step": 839 }, { "epoch": 0.504050405040504, "grad_norm": 5.384676456451416, "learning_rate": 1.3677957140263935e-06, "loss": 0.4471, "step": 840 }, { "epoch": 0.5046504650465047, "grad_norm": 4.483779430389404, "learning_rate": 1.365602282743877e-06, "loss": 0.3891, "step": 841 }, { "epoch": 0.5052505250525052, "grad_norm": 3.924795389175415, "learning_rate": 1.3634068192259825e-06, "loss": 0.262, "step": 842 }, { "epoch": 0.5058505850585059, "grad_norm": 5.761124610900879, "learning_rate": 1.3612093356764044e-06, "loss": 0.7282, "step": 843 }, { "epoch": 0.5064506450645064, "grad_norm": 4.37465763092041, "learning_rate": 1.3590098443100657e-06, "loss": 0.4562, "step": 844 }, { "epoch": 0.5070507050705071, "grad_norm": 4.682488441467285, "learning_rate": 1.3568083573530508e-06, "loss": 0.3809, "step": 845 }, { "epoch": 0.5076507650765076, "grad_norm": 7.359566688537598, "learning_rate": 1.3546048870425354e-06, "loss": 0.7534, "step": 846 }, { "epoch": 0.5082508250825083, "grad_norm": 5.779335021972656, "learning_rate": 1.3523994456267218e-06, "loss": 0.4813, "step": 847 }, { "epoch": 0.5088508850885088, "grad_norm": 4.4589738845825195, "learning_rate": 1.3501920453647667e-06, "loss": 0.3326, "step": 848 }, { "epoch": 0.5094509450945095, "grad_norm": 7.570057392120361, "learning_rate": 1.3479826985267175e-06, "loss": 0.5665, "step": 849 }, { "epoch": 0.51005100510051, "grad_norm": 5.007879734039307, "learning_rate": 1.3457714173934397e-06, "loss": 0.4519, "step": 850 }, { "epoch": 0.5106510651065107, "grad_norm": 3.2231342792510986, "learning_rate": 1.3435582142565519e-06, "loss": 0.236, "step": 851 }, { "epoch": 0.5112511251125113, "grad_norm": 5.481812477111816, "learning_rate": 1.341343101418356e-06, "loss": 0.467, "step": 852 }, { "epoch": 0.5118511851185118, "grad_norm": 5.100032329559326, "learning_rate": 1.3391260911917699e-06, "loss": 0.4878, "step": 853 }, { "epoch": 0.5124512451245125, "grad_norm": 5.158604621887207, "learning_rate": 1.3369071959002573e-06, "loss": 0.4288, "step": 854 }, { "epoch": 0.513051305130513, "grad_norm": 5.450224876403809, "learning_rate": 1.3346864278777604e-06, "loss": 0.4758, "step": 855 }, { "epoch": 0.5136513651365137, "grad_norm": 4.525572299957275, "learning_rate": 1.3324637994686322e-06, "loss": 0.3891, "step": 856 }, { "epoch": 0.5142514251425142, "grad_norm": 4.338691234588623, "learning_rate": 1.3302393230275654e-06, "loss": 0.2356, "step": 857 }, { "epoch": 0.5148514851485149, "grad_norm": 6.05755615234375, "learning_rate": 1.3280130109195263e-06, "loss": 0.5954, "step": 858 }, { "epoch": 0.5154515451545154, "grad_norm": 3.7356438636779785, "learning_rate": 1.3257848755196837e-06, "loss": 0.2966, "step": 859 }, { "epoch": 0.5160516051605161, "grad_norm": 6.882443904876709, "learning_rate": 1.3235549292133424e-06, "loss": 0.5976, "step": 860 }, { "epoch": 0.5166516651665166, "grad_norm": 6.206101894378662, "learning_rate": 1.3213231843958731e-06, "loss": 0.6154, "step": 861 }, { "epoch": 0.5172517251725173, "grad_norm": 4.316999912261963, "learning_rate": 1.3190896534726436e-06, "loss": 0.4926, "step": 862 }, { "epoch": 0.5178517851785178, "grad_norm": 6.382114887237549, "learning_rate": 1.3168543488589499e-06, "loss": 0.5406, "step": 863 }, { "epoch": 0.5184518451845185, "grad_norm": 3.2535629272460938, "learning_rate": 1.3146172829799467e-06, "loss": 0.2504, "step": 864 }, { "epoch": 0.519051905190519, "grad_norm": 4.231846809387207, "learning_rate": 1.3123784682705804e-06, "loss": 0.3765, "step": 865 }, { "epoch": 0.5196519651965197, "grad_norm": 4.752094745635986, "learning_rate": 1.3101379171755164e-06, "loss": 0.4377, "step": 866 }, { "epoch": 0.5202520252025202, "grad_norm": 5.269567966461182, "learning_rate": 1.3078956421490736e-06, "loss": 0.672, "step": 867 }, { "epoch": 0.5208520852085209, "grad_norm": 5.560888767242432, "learning_rate": 1.3056516556551528e-06, "loss": 0.6975, "step": 868 }, { "epoch": 0.5214521452145214, "grad_norm": 3.3761508464813232, "learning_rate": 1.3034059701671685e-06, "loss": 0.3095, "step": 869 }, { "epoch": 0.5220522052205221, "grad_norm": 4.933739185333252, "learning_rate": 1.301158598167979e-06, "loss": 0.5138, "step": 870 }, { "epoch": 0.5226522652265226, "grad_norm": 2.69443678855896, "learning_rate": 1.2989095521498165e-06, "loss": 0.2582, "step": 871 }, { "epoch": 0.5232523252325233, "grad_norm": 5.567372798919678, "learning_rate": 1.2966588446142204e-06, "loss": 0.566, "step": 872 }, { "epoch": 0.5238523852385238, "grad_norm": 3.241415500640869, "learning_rate": 1.2944064880719632e-06, "loss": 0.3143, "step": 873 }, { "epoch": 0.5244524452445245, "grad_norm": 4.12345552444458, "learning_rate": 1.2921524950429861e-06, "loss": 0.3616, "step": 874 }, { "epoch": 0.525052505250525, "grad_norm": 3.8729941844940186, "learning_rate": 1.289896878056325e-06, "loss": 0.5896, "step": 875 }, { "epoch": 0.5256525652565257, "grad_norm": 4.591861248016357, "learning_rate": 1.2876396496500437e-06, "loss": 0.4911, "step": 876 }, { "epoch": 0.5262526252625263, "grad_norm": 6.1741414070129395, "learning_rate": 1.285380822371163e-06, "loss": 0.4725, "step": 877 }, { "epoch": 0.5268526852685268, "grad_norm": 5.42276668548584, "learning_rate": 1.2831204087755906e-06, "loss": 0.4498, "step": 878 }, { "epoch": 0.5274527452745275, "grad_norm": 4.829990386962891, "learning_rate": 1.2808584214280531e-06, "loss": 0.3682, "step": 879 }, { "epoch": 0.528052805280528, "grad_norm": 4.656950950622559, "learning_rate": 1.2785948729020238e-06, "loss": 0.4669, "step": 880 }, { "epoch": 0.5286528652865287, "grad_norm": 4.976127624511719, "learning_rate": 1.2763297757796547e-06, "loss": 0.4052, "step": 881 }, { "epoch": 0.5292529252925292, "grad_norm": 4.461292743682861, "learning_rate": 1.2740631426517052e-06, "loss": 0.6839, "step": 882 }, { "epoch": 0.5298529852985299, "grad_norm": 3.3016202449798584, "learning_rate": 1.2717949861174736e-06, "loss": 0.2503, "step": 883 }, { "epoch": 0.5304530453045304, "grad_norm": 3.7708592414855957, "learning_rate": 1.2695253187847254e-06, "loss": 0.3193, "step": 884 }, { "epoch": 0.5310531053105311, "grad_norm": 5.480434417724609, "learning_rate": 1.267254153269624e-06, "loss": 0.4216, "step": 885 }, { "epoch": 0.5316531653165316, "grad_norm": 3.7073683738708496, "learning_rate": 1.264981502196662e-06, "loss": 0.4271, "step": 886 }, { "epoch": 0.5322532253225323, "grad_norm": 3.7778635025024414, "learning_rate": 1.262707378198587e-06, "loss": 0.3515, "step": 887 }, { "epoch": 0.5328532853285328, "grad_norm": 5.8483805656433105, "learning_rate": 1.2604317939163364e-06, "loss": 0.4945, "step": 888 }, { "epoch": 0.5334533453345335, "grad_norm": 4.762092590332031, "learning_rate": 1.2581547619989635e-06, "loss": 0.5464, "step": 889 }, { "epoch": 0.534053405340534, "grad_norm": 5.5262932777404785, "learning_rate": 1.2558762951035695e-06, "loss": 0.359, "step": 890 }, { "epoch": 0.5346534653465347, "grad_norm": 5.365754127502441, "learning_rate": 1.2535964058952303e-06, "loss": 0.718, "step": 891 }, { "epoch": 0.5352535253525352, "grad_norm": 3.9714651107788086, "learning_rate": 1.2513151070469297e-06, "loss": 0.4062, "step": 892 }, { "epoch": 0.5358535853585359, "grad_norm": 6.284926891326904, "learning_rate": 1.2490324112394858e-06, "loss": 0.6799, "step": 893 }, { "epoch": 0.5364536453645364, "grad_norm": 3.439039945602417, "learning_rate": 1.2467483311614823e-06, "loss": 0.4328, "step": 894 }, { "epoch": 0.5370537053705371, "grad_norm": 4.164103031158447, "learning_rate": 1.2444628795091983e-06, "loss": 0.2771, "step": 895 }, { "epoch": 0.5376537653765376, "grad_norm": 4.925335884094238, "learning_rate": 1.2421760689865348e-06, "loss": 0.3791, "step": 896 }, { "epoch": 0.5382538253825383, "grad_norm": 3.1198973655700684, "learning_rate": 1.2398879123049488e-06, "loss": 0.2343, "step": 897 }, { "epoch": 0.5388538853885388, "grad_norm": 2.925933361053467, "learning_rate": 1.2375984221833782e-06, "loss": 0.1875, "step": 898 }, { "epoch": 0.5394539453945395, "grad_norm": 5.397176742553711, "learning_rate": 1.235307611348174e-06, "loss": 0.4704, "step": 899 }, { "epoch": 0.54005400540054, "grad_norm": 4.536036491394043, "learning_rate": 1.2330154925330276e-06, "loss": 0.42, "step": 900 }, { "epoch": 0.5406540654065407, "grad_norm": 5.017679691314697, "learning_rate": 1.2307220784789016e-06, "loss": 0.4045, "step": 901 }, { "epoch": 0.5412541254125413, "grad_norm": 4.844695091247559, "learning_rate": 1.2284273819339585e-06, "loss": 0.812, "step": 902 }, { "epoch": 0.5418541854185418, "grad_norm": 5.168309211730957, "learning_rate": 1.226131415653489e-06, "loss": 0.3745, "step": 903 }, { "epoch": 0.5424542454245425, "grad_norm": 5.23054313659668, "learning_rate": 1.2238341923998419e-06, "loss": 0.5116, "step": 904 }, { "epoch": 0.543054305430543, "grad_norm": 4.186274528503418, "learning_rate": 1.221535724942353e-06, "loss": 0.3073, "step": 905 }, { "epoch": 0.5436543654365437, "grad_norm": 4.945333480834961, "learning_rate": 1.219236026057275e-06, "loss": 0.4026, "step": 906 }, { "epoch": 0.5442544254425442, "grad_norm": 3.9213879108428955, "learning_rate": 1.2169351085277045e-06, "loss": 0.4084, "step": 907 }, { "epoch": 0.5448544854485449, "grad_norm": 5.939628601074219, "learning_rate": 1.2146329851435118e-06, "loss": 0.9234, "step": 908 }, { "epoch": 0.5454545454545454, "grad_norm": 4.3374433517456055, "learning_rate": 1.2123296687012716e-06, "loss": 0.3066, "step": 909 }, { "epoch": 0.5460546054605461, "grad_norm": 5.156781196594238, "learning_rate": 1.2100251720041885e-06, "loss": 0.6856, "step": 910 }, { "epoch": 0.5466546654665466, "grad_norm": 3.23573637008667, "learning_rate": 1.2077195078620297e-06, "loss": 0.3313, "step": 911 }, { "epoch": 0.5472547254725473, "grad_norm": 4.5379319190979, "learning_rate": 1.2054126890910496e-06, "loss": 0.6511, "step": 912 }, { "epoch": 0.5478547854785478, "grad_norm": 4.34433126449585, "learning_rate": 1.2031047285139226e-06, "loss": 0.3283, "step": 913 }, { "epoch": 0.5484548454845485, "grad_norm": 3.9953761100769043, "learning_rate": 1.2007956389596683e-06, "loss": 0.3434, "step": 914 }, { "epoch": 0.549054905490549, "grad_norm": 6.892691135406494, "learning_rate": 1.198485433263583e-06, "loss": 0.5912, "step": 915 }, { "epoch": 0.5496549654965497, "grad_norm": 4.519745826721191, "learning_rate": 1.196174124267167e-06, "loss": 0.3737, "step": 916 }, { "epoch": 0.5502550255025502, "grad_norm": 5.590246677398682, "learning_rate": 1.1938617248180528e-06, "loss": 0.618, "step": 917 }, { "epoch": 0.5508550855085509, "grad_norm": 4.178394317626953, "learning_rate": 1.1915482477699349e-06, "loss": 0.411, "step": 918 }, { "epoch": 0.5514551455145514, "grad_norm": 5.420042037963867, "learning_rate": 1.1892337059824966e-06, "loss": 0.6167, "step": 919 }, { "epoch": 0.5520552055205521, "grad_norm": 4.4502458572387695, "learning_rate": 1.1869181123213424e-06, "loss": 0.7689, "step": 920 }, { "epoch": 0.5526552655265526, "grad_norm": 5.987793445587158, "learning_rate": 1.1846014796579204e-06, "loss": 0.4673, "step": 921 }, { "epoch": 0.5532553255325533, "grad_norm": 4.310242176055908, "learning_rate": 1.1822838208694563e-06, "loss": 0.3932, "step": 922 }, { "epoch": 0.5538553855385538, "grad_norm": 3.9067344665527344, "learning_rate": 1.1799651488388787e-06, "loss": 0.3704, "step": 923 }, { "epoch": 0.5544554455445545, "grad_norm": 4.163078784942627, "learning_rate": 1.1776454764547484e-06, "loss": 0.5374, "step": 924 }, { "epoch": 0.555055505550555, "grad_norm": 3.312878370285034, "learning_rate": 1.1753248166111879e-06, "loss": 0.4159, "step": 925 }, { "epoch": 0.5556555655565557, "grad_norm": 3.464552640914917, "learning_rate": 1.1730031822078063e-06, "loss": 0.3482, "step": 926 }, { "epoch": 0.5562556255625563, "grad_norm": 3.0913445949554443, "learning_rate": 1.1706805861496323e-06, "loss": 0.6813, "step": 927 }, { "epoch": 0.5568556855685568, "grad_norm": 7.397716522216797, "learning_rate": 1.1683570413470383e-06, "loss": 0.5433, "step": 928 }, { "epoch": 0.5574557455745575, "grad_norm": 3.8919754028320312, "learning_rate": 1.166032560715672e-06, "loss": 0.464, "step": 929 }, { "epoch": 0.558055805580558, "grad_norm": 3.5395705699920654, "learning_rate": 1.1637071571763815e-06, "loss": 0.3454, "step": 930 }, { "epoch": 0.5586558655865587, "grad_norm": 6.314044952392578, "learning_rate": 1.1613808436551453e-06, "loss": 0.4942, "step": 931 }, { "epoch": 0.5592559255925592, "grad_norm": 3.9766716957092285, "learning_rate": 1.159053633083001e-06, "loss": 0.3877, "step": 932 }, { "epoch": 0.5598559855985599, "grad_norm": 4.073610305786133, "learning_rate": 1.1567255383959711e-06, "loss": 0.3344, "step": 933 }, { "epoch": 0.5604560456045604, "grad_norm": 4.3134846687316895, "learning_rate": 1.1543965725349942e-06, "loss": 0.5799, "step": 934 }, { "epoch": 0.5610561056105611, "grad_norm": 4.0430588722229, "learning_rate": 1.1520667484458502e-06, "loss": 0.4177, "step": 935 }, { "epoch": 0.5616561656165616, "grad_norm": 3.4120073318481445, "learning_rate": 1.14973607907909e-06, "loss": 0.5804, "step": 936 }, { "epoch": 0.5622562256225623, "grad_norm": 3.831258535385132, "learning_rate": 1.147404577389963e-06, "loss": 0.3977, "step": 937 }, { "epoch": 0.5628562856285628, "grad_norm": 3.553619623184204, "learning_rate": 1.1450722563383448e-06, "loss": 0.4466, "step": 938 }, { "epoch": 0.5634563456345635, "grad_norm": 3.4493253231048584, "learning_rate": 1.1427391288886662e-06, "loss": 0.4651, "step": 939 }, { "epoch": 0.564056405640564, "grad_norm": 4.307346343994141, "learning_rate": 1.1404052080098402e-06, "loss": 0.4856, "step": 940 }, { "epoch": 0.5646564656465647, "grad_norm": 7.642573356628418, "learning_rate": 1.1380705066751893e-06, "loss": 0.833, "step": 941 }, { "epoch": 0.5652565256525652, "grad_norm": 4.258155345916748, "learning_rate": 1.1357350378623754e-06, "loss": 0.3261, "step": 942 }, { "epoch": 0.5658565856585659, "grad_norm": 4.205949783325195, "learning_rate": 1.1333988145533261e-06, "loss": 0.414, "step": 943 }, { "epoch": 0.5664566456645664, "grad_norm": 3.2299089431762695, "learning_rate": 1.131061849734163e-06, "loss": 0.2318, "step": 944 }, { "epoch": 0.5670567056705671, "grad_norm": 3.49491024017334, "learning_rate": 1.1287241563951289e-06, "loss": 0.537, "step": 945 }, { "epoch": 0.5676567656765676, "grad_norm": 4.2180256843566895, "learning_rate": 1.1263857475305166e-06, "loss": 0.5906, "step": 946 }, { "epoch": 0.5682568256825683, "grad_norm": 5.149070739746094, "learning_rate": 1.1240466361385968e-06, "loss": 0.4309, "step": 947 }, { "epoch": 0.5688568856885688, "grad_norm": 4.263235092163086, "learning_rate": 1.1217068352215443e-06, "loss": 0.3748, "step": 948 }, { "epoch": 0.5694569456945695, "grad_norm": 5.265423774719238, "learning_rate": 1.1193663577853671e-06, "loss": 0.6096, "step": 949 }, { "epoch": 0.57005700570057, "grad_norm": 2.420003890991211, "learning_rate": 1.1170252168398336e-06, "loss": 0.2477, "step": 950 }, { "epoch": 0.5706570657065707, "grad_norm": 5.448967456817627, "learning_rate": 1.1146834253984005e-06, "loss": 0.5157, "step": 951 }, { "epoch": 0.5712571257125713, "grad_norm": 3.1892151832580566, "learning_rate": 1.1123409964781401e-06, "loss": 0.2307, "step": 952 }, { "epoch": 0.5718571857185718, "grad_norm": 5.353104591369629, "learning_rate": 1.109997943099669e-06, "loss": 0.2984, "step": 953 }, { "epoch": 0.5724572457245725, "grad_norm": 3.5007283687591553, "learning_rate": 1.1076542782870734e-06, "loss": 0.2745, "step": 954 }, { "epoch": 0.573057305730573, "grad_norm": 5.598865985870361, "learning_rate": 1.1053100150678398e-06, "loss": 0.4867, "step": 955 }, { "epoch": 0.5736573657365737, "grad_norm": 4.899713516235352, "learning_rate": 1.1029651664727796e-06, "loss": 0.2766, "step": 956 }, { "epoch": 0.5742574257425742, "grad_norm": 4.45994758605957, "learning_rate": 1.1006197455359595e-06, "loss": 0.3029, "step": 957 }, { "epoch": 0.5748574857485749, "grad_norm": 3.051438093185425, "learning_rate": 1.0982737652946268e-06, "loss": 0.268, "step": 958 }, { "epoch": 0.5754575457545754, "grad_norm": 5.14425802230835, "learning_rate": 1.0959272387891377e-06, "loss": 0.4774, "step": 959 }, { "epoch": 0.5760576057605761, "grad_norm": 4.228065013885498, "learning_rate": 1.0935801790628846e-06, "loss": 0.3482, "step": 960 }, { "epoch": 0.5766576657665766, "grad_norm": 4.503816604614258, "learning_rate": 1.0912325991622244e-06, "loss": 0.393, "step": 961 }, { "epoch": 0.5772577257725773, "grad_norm": 5.425703525543213, "learning_rate": 1.0888845121364058e-06, "loss": 0.6611, "step": 962 }, { "epoch": 0.5778577857785778, "grad_norm": 5.469113349914551, "learning_rate": 1.0865359310374955e-06, "loss": 0.3561, "step": 963 }, { "epoch": 0.5784578457845785, "grad_norm": 5.6777496337890625, "learning_rate": 1.0841868689203072e-06, "loss": 0.4947, "step": 964 }, { "epoch": 0.579057905790579, "grad_norm": 3.718489646911621, "learning_rate": 1.0818373388423271e-06, "loss": 0.3638, "step": 965 }, { "epoch": 0.5796579657965797, "grad_norm": 4.680621147155762, "learning_rate": 1.0794873538636456e-06, "loss": 0.4041, "step": 966 }, { "epoch": 0.5802580258025802, "grad_norm": 6.350257396697998, "learning_rate": 1.077136927046878e-06, "loss": 0.6162, "step": 967 }, { "epoch": 0.5808580858085809, "grad_norm": 3.54060435295105, "learning_rate": 1.0747860714570982e-06, "loss": 0.424, "step": 968 }, { "epoch": 0.5814581458145814, "grad_norm": 5.870255947113037, "learning_rate": 1.0724348001617625e-06, "loss": 0.441, "step": 969 }, { "epoch": 0.5820582058205821, "grad_norm": 4.550197601318359, "learning_rate": 1.0700831262306377e-06, "loss": 0.2628, "step": 970 }, { "epoch": 0.5826582658265826, "grad_norm": 3.5639820098876953, "learning_rate": 1.0677310627357296e-06, "loss": 0.2869, "step": 971 }, { "epoch": 0.5832583258325833, "grad_norm": 4.517899036407471, "learning_rate": 1.0653786227512083e-06, "loss": 0.365, "step": 972 }, { "epoch": 0.5838583858385838, "grad_norm": 5.525387287139893, "learning_rate": 1.0630258193533379e-06, "loss": 0.7934, "step": 973 }, { "epoch": 0.5844584458445845, "grad_norm": 2.7125747203826904, "learning_rate": 1.0606726656204016e-06, "loss": 0.2829, "step": 974 }, { "epoch": 0.585058505850585, "grad_norm": 4.354297161102295, "learning_rate": 1.0583191746326296e-06, "loss": 0.4637, "step": 975 }, { "epoch": 0.5856585658565857, "grad_norm": 5.719192981719971, "learning_rate": 1.0559653594721287e-06, "loss": 0.3839, "step": 976 }, { "epoch": 0.5862586258625863, "grad_norm": 6.400244235992432, "learning_rate": 1.0536112332228056e-06, "loss": 0.3236, "step": 977 }, { "epoch": 0.5868586858685868, "grad_norm": 3.2432126998901367, "learning_rate": 1.0512568089702974e-06, "loss": 0.3084, "step": 978 }, { "epoch": 0.5874587458745875, "grad_norm": 5.412176132202148, "learning_rate": 1.0489020998018962e-06, "loss": 0.5592, "step": 979 }, { "epoch": 0.588058805880588, "grad_norm": 4.1277384757995605, "learning_rate": 1.0465471188064805e-06, "loss": 0.2461, "step": 980 }, { "epoch": 0.5886588658865887, "grad_norm": 3.7015607357025146, "learning_rate": 1.044191879074437e-06, "loss": 0.2984, "step": 981 }, { "epoch": 0.5892589258925892, "grad_norm": 3.9416425228118896, "learning_rate": 1.0418363936975927e-06, "loss": 0.2721, "step": 982 }, { "epoch": 0.5898589858985899, "grad_norm": 7.937212944030762, "learning_rate": 1.0394806757691384e-06, "loss": 0.6065, "step": 983 }, { "epoch": 0.5904590459045904, "grad_norm": 3.7717089653015137, "learning_rate": 1.0371247383835585e-06, "loss": 0.2756, "step": 984 }, { "epoch": 0.5910591059105911, "grad_norm": 6.935327053070068, "learning_rate": 1.0347685946365574e-06, "loss": 0.5801, "step": 985 }, { "epoch": 0.5916591659165916, "grad_norm": 3.9818968772888184, "learning_rate": 1.0324122576249855e-06, "loss": 0.5041, "step": 986 }, { "epoch": 0.5922592259225923, "grad_norm": 5.358791351318359, "learning_rate": 1.0300557404467693e-06, "loss": 0.5502, "step": 987 }, { "epoch": 0.5928592859285928, "grad_norm": 6.267082214355469, "learning_rate": 1.0276990562008348e-06, "loss": 0.7226, "step": 988 }, { "epoch": 0.5934593459345935, "grad_norm": 3.376723289489746, "learning_rate": 1.025342217987038e-06, "loss": 0.3306, "step": 989 }, { "epoch": 0.594059405940594, "grad_norm": 5.635215759277344, "learning_rate": 1.0229852389060904e-06, "loss": 0.6418, "step": 990 }, { "epoch": 0.5946594659465947, "grad_norm": 4.09062385559082, "learning_rate": 1.0206281320594863e-06, "loss": 0.4654, "step": 991 }, { "epoch": 0.5952595259525952, "grad_norm": 5.451848030090332, "learning_rate": 1.01827091054943e-06, "loss": 0.4809, "step": 992 }, { "epoch": 0.5958595859585959, "grad_norm": 3.4791746139526367, "learning_rate": 1.015913587478764e-06, "loss": 0.3472, "step": 993 }, { "epoch": 0.5964596459645964, "grad_norm": 2.553596019744873, "learning_rate": 1.0135561759508947e-06, "loss": 0.5734, "step": 994 }, { "epoch": 0.5970597059705971, "grad_norm": 4.173645973205566, "learning_rate": 1.01119868906972e-06, "loss": 0.332, "step": 995 }, { "epoch": 0.5976597659765976, "grad_norm": 4.746750354766846, "learning_rate": 1.0088411399395578e-06, "loss": 0.3642, "step": 996 }, { "epoch": 0.5982598259825983, "grad_norm": 4.4675517082214355, "learning_rate": 1.0064835416650703e-06, "loss": 0.2807, "step": 997 }, { "epoch": 0.5988598859885989, "grad_norm": 3.7586233615875244, "learning_rate": 1.0041259073511944e-06, "loss": 0.2879, "step": 998 }, { "epoch": 0.5994599459945995, "grad_norm": 3.4227406978607178, "learning_rate": 1.0017682501030664e-06, "loss": 0.2203, "step": 999 }, { "epoch": 0.6000600060006, "grad_norm": 4.244377136230469, "learning_rate": 9.994105830259502e-07, "loss": 0.2577, "step": 1000 }, { "epoch": 0.6006600660066007, "grad_norm": 3.3714451789855957, "learning_rate": 9.97052919225165e-07, "loss": 0.3092, "step": 1001 }, { "epoch": 0.6012601260126013, "grad_norm": 8.724556922912598, "learning_rate": 9.946952718060114e-07, "loss": 0.5734, "step": 1002 }, { "epoch": 0.6018601860186018, "grad_norm": 3.4722719192504883, "learning_rate": 9.923376538736983e-07, "loss": 0.4905, "step": 1003 }, { "epoch": 0.6024602460246025, "grad_norm": 6.5383620262146, "learning_rate": 9.899800785332716e-07, "loss": 0.6078, "step": 1004 }, { "epoch": 0.603060306030603, "grad_norm": 5.705877304077148, "learning_rate": 9.876225588895404e-07, "loss": 0.6699, "step": 1005 }, { "epoch": 0.6036603660366037, "grad_norm": 6.548628807067871, "learning_rate": 9.852651080470033e-07, "loss": 0.5355, "step": 1006 }, { "epoch": 0.6042604260426042, "grad_norm": 3.858586311340332, "learning_rate": 9.829077391097773e-07, "loss": 0.3376, "step": 1007 }, { "epoch": 0.6048604860486049, "grad_norm": 2.4900670051574707, "learning_rate": 9.80550465181524e-07, "loss": 0.241, "step": 1008 }, { "epoch": 0.6054605460546054, "grad_norm": 4.3862481117248535, "learning_rate": 9.781932993653765e-07, "loss": 0.5898, "step": 1009 }, { "epoch": 0.6060606060606061, "grad_norm": 6.3023505210876465, "learning_rate": 9.75836254763868e-07, "loss": 0.3457, "step": 1010 }, { "epoch": 0.6066606660666066, "grad_norm": 6.933469772338867, "learning_rate": 9.734793444788558e-07, "loss": 0.561, "step": 1011 }, { "epoch": 0.6072607260726073, "grad_norm": 4.735578536987305, "learning_rate": 9.711225816114534e-07, "loss": 0.3796, "step": 1012 }, { "epoch": 0.6078607860786078, "grad_norm": 5.041178226470947, "learning_rate": 9.687659792619522e-07, "loss": 0.4138, "step": 1013 }, { "epoch": 0.6084608460846085, "grad_norm": 8.968154907226562, "learning_rate": 9.664095505297531e-07, "loss": 0.6314, "step": 1014 }, { "epoch": 0.609060906090609, "grad_norm": 4.9882121086120605, "learning_rate": 9.640533085132918e-07, "loss": 0.3144, "step": 1015 }, { "epoch": 0.6096609660966097, "grad_norm": 5.669036388397217, "learning_rate": 9.616972663099646e-07, "loss": 0.4892, "step": 1016 }, { "epoch": 0.6102610261026102, "grad_norm": 4.483795642852783, "learning_rate": 9.59341437016059e-07, "loss": 0.4605, "step": 1017 }, { "epoch": 0.6108610861086109, "grad_norm": 4.997488021850586, "learning_rate": 9.569858337266783e-07, "loss": 0.4715, "step": 1018 }, { "epoch": 0.6114611461146114, "grad_norm": 5.3979172706604, "learning_rate": 9.54630469535669e-07, "loss": 0.4621, "step": 1019 }, { "epoch": 0.6120612061206121, "grad_norm": 3.7738680839538574, "learning_rate": 9.522753575355494e-07, "loss": 0.2616, "step": 1020 }, { "epoch": 0.6126612661266126, "grad_norm": 4.9967875480651855, "learning_rate": 9.499205108174353e-07, "loss": 0.4625, "step": 1021 }, { "epoch": 0.6132613261326133, "grad_norm": 4.867164611816406, "learning_rate": 9.475659424709684e-07, "loss": 0.4651, "step": 1022 }, { "epoch": 0.6138613861386139, "grad_norm": 5.8462018966674805, "learning_rate": 9.452116655842428e-07, "loss": 0.5628, "step": 1023 }, { "epoch": 0.6144614461446145, "grad_norm": 4.083488464355469, "learning_rate": 9.428576932437324e-07, "loss": 0.4726, "step": 1024 }, { "epoch": 0.6150615061506151, "grad_norm": 3.3948140144348145, "learning_rate": 9.405040385342187e-07, "loss": 0.3291, "step": 1025 }, { "epoch": 0.6156615661566157, "grad_norm": 5.040841579437256, "learning_rate": 9.381507145387169e-07, "loss": 0.2128, "step": 1026 }, { "epoch": 0.6162616261626163, "grad_norm": 4.98016357421875, "learning_rate": 9.357977343384043e-07, "loss": 0.4537, "step": 1027 }, { "epoch": 0.6168616861686168, "grad_norm": 4.55957555770874, "learning_rate": 9.334451110125478e-07, "loss": 0.3662, "step": 1028 }, { "epoch": 0.6174617461746175, "grad_norm": 4.0379319190979, "learning_rate": 9.310928576384293e-07, "loss": 0.4359, "step": 1029 }, { "epoch": 0.618061806180618, "grad_norm": 4.9916157722473145, "learning_rate": 9.287409872912753e-07, "loss": 0.5034, "step": 1030 }, { "epoch": 0.6186618661866187, "grad_norm": 4.714777946472168, "learning_rate": 9.263895130441824e-07, "loss": 0.5578, "step": 1031 }, { "epoch": 0.6192619261926192, "grad_norm": 4.963957786560059, "learning_rate": 9.240384479680462e-07, "loss": 0.3502, "step": 1032 }, { "epoch": 0.6198619861986199, "grad_norm": 3.646277666091919, "learning_rate": 9.216878051314881e-07, "loss": 0.3899, "step": 1033 }, { "epoch": 0.6204620462046204, "grad_norm": 3.352478265762329, "learning_rate": 9.193375976007808e-07, "loss": 0.257, "step": 1034 }, { "epoch": 0.6210621062106211, "grad_norm": 2.9363842010498047, "learning_rate": 9.169878384397796e-07, "loss": 0.2594, "step": 1035 }, { "epoch": 0.6216621662166216, "grad_norm": 3.988025665283203, "learning_rate": 9.146385407098451e-07, "loss": 0.2166, "step": 1036 }, { "epoch": 0.6222622262226223, "grad_norm": 3.5809860229492188, "learning_rate": 9.122897174697752e-07, "loss": 0.2864, "step": 1037 }, { "epoch": 0.6228622862286228, "grad_norm": 5.3678202629089355, "learning_rate": 9.099413817757293e-07, "loss": 0.4272, "step": 1038 }, { "epoch": 0.6234623462346235, "grad_norm": 4.28339958190918, "learning_rate": 9.075935466811557e-07, "loss": 0.47, "step": 1039 }, { "epoch": 0.624062406240624, "grad_norm": 3.146242618560791, "learning_rate": 9.052462252367221e-07, "loss": 0.215, "step": 1040 }, { "epoch": 0.6246624662466247, "grad_norm": 4.910057544708252, "learning_rate": 9.028994304902401e-07, "loss": 0.3585, "step": 1041 }, { "epoch": 0.6252625262526252, "grad_norm": 5.71312952041626, "learning_rate": 9.005531754865928e-07, "loss": 0.9182, "step": 1042 }, { "epoch": 0.6258625862586259, "grad_norm": 4.4007248878479, "learning_rate": 8.982074732676646e-07, "loss": 0.3007, "step": 1043 }, { "epoch": 0.6264626462646264, "grad_norm": 4.716728210449219, "learning_rate": 8.958623368722658e-07, "loss": 0.2905, "step": 1044 }, { "epoch": 0.6270627062706271, "grad_norm": 4.06003475189209, "learning_rate": 8.935177793360623e-07, "loss": 0.5239, "step": 1045 }, { "epoch": 0.6276627662766276, "grad_norm": 3.229593276977539, "learning_rate": 8.911738136915026e-07, "loss": 0.2827, "step": 1046 }, { "epoch": 0.6282628262826283, "grad_norm": 3.106814384460449, "learning_rate": 8.88830452967744e-07, "loss": 0.2478, "step": 1047 }, { "epoch": 0.6288628862886289, "grad_norm": 5.350484848022461, "learning_rate": 8.864877101905827e-07, "loss": 0.5292, "step": 1048 }, { "epoch": 0.6294629462946295, "grad_norm": 5.480916500091553, "learning_rate": 8.841455983823788e-07, "loss": 0.5096, "step": 1049 }, { "epoch": 0.6300630063006301, "grad_norm": 5.862973213195801, "learning_rate": 8.818041305619855e-07, "loss": 0.4533, "step": 1050 }, { "epoch": 0.6306630663066307, "grad_norm": 5.773388385772705, "learning_rate": 8.79463319744677e-07, "loss": 0.659, "step": 1051 }, { "epoch": 0.6312631263126313, "grad_norm": 4.671454429626465, "learning_rate": 8.771231789420743e-07, "loss": 0.4234, "step": 1052 }, { "epoch": 0.6318631863186318, "grad_norm": 6.451287746429443, "learning_rate": 8.747837211620752e-07, "loss": 0.6608, "step": 1053 }, { "epoch": 0.6324632463246325, "grad_norm": 4.256207466125488, "learning_rate": 8.724449594087796e-07, "loss": 0.3519, "step": 1054 }, { "epoch": 0.633063306330633, "grad_norm": 6.210073947906494, "learning_rate": 8.701069066824194e-07, "loss": 0.4393, "step": 1055 }, { "epoch": 0.6336633663366337, "grad_norm": 3.117661476135254, "learning_rate": 8.677695759792859e-07, "loss": 0.3182, "step": 1056 }, { "epoch": 0.6342634263426342, "grad_norm": 4.740177631378174, "learning_rate": 8.654329802916548e-07, "loss": 0.6466, "step": 1057 }, { "epoch": 0.6348634863486349, "grad_norm": 4.8576507568359375, "learning_rate": 8.630971326077188e-07, "loss": 0.4823, "step": 1058 }, { "epoch": 0.6354635463546354, "grad_norm": 3.178380250930786, "learning_rate": 8.607620459115102e-07, "loss": 0.2954, "step": 1059 }, { "epoch": 0.6360636063606361, "grad_norm": 2.6787965297698975, "learning_rate": 8.584277331828335e-07, "loss": 0.32, "step": 1060 }, { "epoch": 0.6366636663666366, "grad_norm": 4.581658363342285, "learning_rate": 8.5609420739719e-07, "loss": 0.3783, "step": 1061 }, { "epoch": 0.6372637263726373, "grad_norm": 6.217848300933838, "learning_rate": 8.537614815257057e-07, "loss": 0.7221, "step": 1062 }, { "epoch": 0.6378637863786378, "grad_norm": 5.1335530281066895, "learning_rate": 8.514295685350622e-07, "loss": 0.4344, "step": 1063 }, { "epoch": 0.6384638463846385, "grad_norm": 4.494945049285889, "learning_rate": 8.490984813874217e-07, "loss": 0.4301, "step": 1064 }, { "epoch": 0.639063906390639, "grad_norm": 7.480804920196533, "learning_rate": 8.467682330403552e-07, "loss": 1.0248, "step": 1065 }, { "epoch": 0.6396639663966397, "grad_norm": 3.39471697807312, "learning_rate": 8.444388364467726e-07, "loss": 0.3134, "step": 1066 }, { "epoch": 0.6402640264026402, "grad_norm": 3.9353625774383545, "learning_rate": 8.421103045548477e-07, "loss": 0.3133, "step": 1067 }, { "epoch": 0.6408640864086409, "grad_norm": 3.8598008155822754, "learning_rate": 8.397826503079488e-07, "loss": 0.4868, "step": 1068 }, { "epoch": 0.6414641464146414, "grad_norm": 4.148881912231445, "learning_rate": 8.374558866445658e-07, "loss": 0.2492, "step": 1069 }, { "epoch": 0.6420642064206421, "grad_norm": 6.0562424659729, "learning_rate": 8.351300264982371e-07, "loss": 0.4083, "step": 1070 }, { "epoch": 0.6426642664266426, "grad_norm": 5.60959005355835, "learning_rate": 8.328050827974801e-07, "loss": 0.4893, "step": 1071 }, { "epoch": 0.6432643264326433, "grad_norm": 4.428864479064941, "learning_rate": 8.304810684657173e-07, "loss": 0.3932, "step": 1072 }, { "epoch": 0.6438643864386439, "grad_norm": 5.3781328201293945, "learning_rate": 8.281579964212055e-07, "loss": 0.5564, "step": 1073 }, { "epoch": 0.6444644464446445, "grad_norm": 3.882985830307007, "learning_rate": 8.258358795769636e-07, "loss": 0.3019, "step": 1074 }, { "epoch": 0.6450645064506451, "grad_norm": 3.5522944927215576, "learning_rate": 8.235147308407008e-07, "loss": 0.2501, "step": 1075 }, { "epoch": 0.6456645664566457, "grad_norm": 4.01713228225708, "learning_rate": 8.211945631147457e-07, "loss": 0.4402, "step": 1076 }, { "epoch": 0.6462646264626463, "grad_norm": 5.010003089904785, "learning_rate": 8.188753892959724e-07, "loss": 0.2508, "step": 1077 }, { "epoch": 0.6468646864686468, "grad_norm": 3.8966097831726074, "learning_rate": 8.165572222757313e-07, "loss": 0.3048, "step": 1078 }, { "epoch": 0.6474647464746475, "grad_norm": 3.513282299041748, "learning_rate": 8.142400749397774e-07, "loss": 0.3816, "step": 1079 }, { "epoch": 0.648064806480648, "grad_norm": 5.278601169586182, "learning_rate": 8.119239601681951e-07, "loss": 0.347, "step": 1080 }, { "epoch": 0.6486648664866487, "grad_norm": 5.393117427825928, "learning_rate": 8.096088908353315e-07, "loss": 0.3485, "step": 1081 }, { "epoch": 0.6492649264926492, "grad_norm": 6.196635723114014, "learning_rate": 8.072948798097216e-07, "loss": 0.8028, "step": 1082 }, { "epoch": 0.6498649864986499, "grad_norm": 2.776512384414673, "learning_rate": 8.049819399540175e-07, "loss": 0.3649, "step": 1083 }, { "epoch": 0.6504650465046504, "grad_norm": 5.106352806091309, "learning_rate": 8.02670084124918e-07, "loss": 0.3808, "step": 1084 }, { "epoch": 0.6510651065106511, "grad_norm": 5.48502254486084, "learning_rate": 8.003593251730946e-07, "loss": 0.2869, "step": 1085 }, { "epoch": 0.6516651665166516, "grad_norm": 4.019291877746582, "learning_rate": 7.980496759431233e-07, "loss": 0.352, "step": 1086 }, { "epoch": 0.6522652265226523, "grad_norm": 3.941056251525879, "learning_rate": 7.957411492734113e-07, "loss": 0.347, "step": 1087 }, { "epoch": 0.6528652865286528, "grad_norm": 4.198221683502197, "learning_rate": 7.934337579961251e-07, "loss": 0.3163, "step": 1088 }, { "epoch": 0.6534653465346535, "grad_norm": 3.4438133239746094, "learning_rate": 7.91127514937121e-07, "loss": 0.4508, "step": 1089 }, { "epoch": 0.654065406540654, "grad_norm": 4.341343879699707, "learning_rate": 7.888224329158722e-07, "loss": 0.3207, "step": 1090 }, { "epoch": 0.6546654665466547, "grad_norm": 2.83504056930542, "learning_rate": 7.865185247453981e-07, "loss": 0.2447, "step": 1091 }, { "epoch": 0.6552655265526552, "grad_norm": 4.510803699493408, "learning_rate": 7.84215803232194e-07, "loss": 0.2884, "step": 1092 }, { "epoch": 0.6558655865586559, "grad_norm": 5.038809776306152, "learning_rate": 7.819142811761578e-07, "loss": 0.568, "step": 1093 }, { "epoch": 0.6564656465646564, "grad_norm": 5.112843990325928, "learning_rate": 7.796139713705213e-07, "loss": 0.454, "step": 1094 }, { "epoch": 0.6570657065706571, "grad_norm": 5.403368949890137, "learning_rate": 7.773148866017768e-07, "loss": 0.5394, "step": 1095 }, { "epoch": 0.6576657665766577, "grad_norm": 4.8240532875061035, "learning_rate": 7.75017039649608e-07, "loss": 0.3401, "step": 1096 }, { "epoch": 0.6582658265826583, "grad_norm": 4.006097316741943, "learning_rate": 7.727204432868178e-07, "loss": 0.4396, "step": 1097 }, { "epoch": 0.6588658865886589, "grad_norm": 3.367217540740967, "learning_rate": 7.704251102792571e-07, "loss": 0.513, "step": 1098 }, { "epoch": 0.6594659465946595, "grad_norm": 3.4011199474334717, "learning_rate": 7.681310533857552e-07, "loss": 0.4225, "step": 1099 }, { "epoch": 0.6600660066006601, "grad_norm": 5.045578956604004, "learning_rate": 7.658382853580472e-07, "loss": 0.4919, "step": 1100 }, { "epoch": 0.6606660666066607, "grad_norm": 7.741008281707764, "learning_rate": 7.635468189407041e-07, "loss": 0.9802, "step": 1101 }, { "epoch": 0.6612661266126613, "grad_norm": 3.7746899127960205, "learning_rate": 7.612566668710626e-07, "loss": 0.5192, "step": 1102 }, { "epoch": 0.6618661866186618, "grad_norm": 3.7375245094299316, "learning_rate": 7.589678418791519e-07, "loss": 0.4781, "step": 1103 }, { "epoch": 0.6624662466246625, "grad_norm": 3.5007903575897217, "learning_rate": 7.566803566876259e-07, "loss": 0.3465, "step": 1104 }, { "epoch": 0.663066306630663, "grad_norm": 4.082932949066162, "learning_rate": 7.543942240116906e-07, "loss": 0.3658, "step": 1105 }, { "epoch": 0.6636663666366637, "grad_norm": 5.619985103607178, "learning_rate": 7.521094565590337e-07, "loss": 0.5112, "step": 1106 }, { "epoch": 0.6642664266426642, "grad_norm": 4.4432501792907715, "learning_rate": 7.498260670297549e-07, "loss": 0.4175, "step": 1107 }, { "epoch": 0.6648664866486649, "grad_norm": 4.079854965209961, "learning_rate": 7.47544068116293e-07, "loss": 0.3456, "step": 1108 }, { "epoch": 0.6654665466546654, "grad_norm": 3.872283935546875, "learning_rate": 7.452634725033588e-07, "loss": 0.386, "step": 1109 }, { "epoch": 0.6660666066606661, "grad_norm": 5.059799671173096, "learning_rate": 7.429842928678618e-07, "loss": 0.3517, "step": 1110 }, { "epoch": 0.6666666666666666, "grad_norm": 3.2076282501220703, "learning_rate": 7.407065418788405e-07, "loss": 0.5427, "step": 1111 }, { "epoch": 0.6672667266726673, "grad_norm": 4.151808261871338, "learning_rate": 7.384302321973928e-07, "loss": 0.5929, "step": 1112 }, { "epoch": 0.6678667866786678, "grad_norm": 5.35268497467041, "learning_rate": 7.361553764766042e-07, "loss": 0.2987, "step": 1113 }, { "epoch": 0.6684668466846685, "grad_norm": 4.606880187988281, "learning_rate": 7.338819873614785e-07, "loss": 0.4205, "step": 1114 }, { "epoch": 0.669066906690669, "grad_norm": 3.5607717037200928, "learning_rate": 7.316100774888676e-07, "loss": 0.3109, "step": 1115 }, { "epoch": 0.6696669666966697, "grad_norm": 4.021890640258789, "learning_rate": 7.293396594874001e-07, "loss": 0.2858, "step": 1116 }, { "epoch": 0.6702670267026702, "grad_norm": 4.4409074783325195, "learning_rate": 7.270707459774132e-07, "loss": 0.328, "step": 1117 }, { "epoch": 0.6708670867086709, "grad_norm": 4.489919185638428, "learning_rate": 7.248033495708795e-07, "loss": 0.4574, "step": 1118 }, { "epoch": 0.6714671467146714, "grad_norm": 4.231625556945801, "learning_rate": 7.2253748287134e-07, "loss": 0.3763, "step": 1119 }, { "epoch": 0.6720672067206721, "grad_norm": 3.9258599281311035, "learning_rate": 7.202731584738322e-07, "loss": 0.3259, "step": 1120 }, { "epoch": 0.6726672667266727, "grad_norm": 4.8415656089782715, "learning_rate": 7.180103889648204e-07, "loss": 0.4112, "step": 1121 }, { "epoch": 0.6732673267326733, "grad_norm": 3.648428201675415, "learning_rate": 7.157491869221267e-07, "loss": 0.6243, "step": 1122 }, { "epoch": 0.6738673867386739, "grad_norm": 4.97957181930542, "learning_rate": 7.134895649148587e-07, "loss": 0.4379, "step": 1123 }, { "epoch": 0.6744674467446745, "grad_norm": 4.391280174255371, "learning_rate": 7.112315355033426e-07, "loss": 0.36, "step": 1124 }, { "epoch": 0.6750675067506751, "grad_norm": 4.285407066345215, "learning_rate": 7.089751112390523e-07, "loss": 0.5383, "step": 1125 }, { "epoch": 0.6756675667566757, "grad_norm": 5.267690181732178, "learning_rate": 7.067203046645376e-07, "loss": 0.5048, "step": 1126 }, { "epoch": 0.6762676267626763, "grad_norm": 6.130159378051758, "learning_rate": 7.044671283133578e-07, "loss": 0.669, "step": 1127 }, { "epoch": 0.6768676867686768, "grad_norm": 4.787133693695068, "learning_rate": 7.022155947100103e-07, "loss": 0.3272, "step": 1128 }, { "epoch": 0.6774677467746775, "grad_norm": 5.345201015472412, "learning_rate": 6.999657163698596e-07, "loss": 0.3679, "step": 1129 }, { "epoch": 0.678067806780678, "grad_norm": 4.411485195159912, "learning_rate": 6.977175057990716e-07, "loss": 0.3847, "step": 1130 }, { "epoch": 0.6786678667866787, "grad_norm": 5.594630241394043, "learning_rate": 6.954709754945393e-07, "loss": 0.3104, "step": 1131 }, { "epoch": 0.6792679267926792, "grad_norm": 3.276357412338257, "learning_rate": 6.93226137943818e-07, "loss": 0.4502, "step": 1132 }, { "epoch": 0.6798679867986799, "grad_norm": 4.338402271270752, "learning_rate": 6.909830056250526e-07, "loss": 0.4556, "step": 1133 }, { "epoch": 0.6804680468046804, "grad_norm": 4.468677043914795, "learning_rate": 6.88741591006909e-07, "loss": 0.3199, "step": 1134 }, { "epoch": 0.6810681068106811, "grad_norm": 3.9323384761810303, "learning_rate": 6.865019065485057e-07, "loss": 0.3944, "step": 1135 }, { "epoch": 0.6816681668166816, "grad_norm": 5.020145416259766, "learning_rate": 6.842639646993435e-07, "loss": 0.5972, "step": 1136 }, { "epoch": 0.6822682268226823, "grad_norm": 4.189634323120117, "learning_rate": 6.820277778992371e-07, "loss": 0.4223, "step": 1137 }, { "epoch": 0.6828682868286828, "grad_norm": 4.835778713226318, "learning_rate": 6.797933585782459e-07, "loss": 0.351, "step": 1138 }, { "epoch": 0.6834683468346835, "grad_norm": 4.933027267456055, "learning_rate": 6.775607191566032e-07, "loss": 0.9809, "step": 1139 }, { "epoch": 0.684068406840684, "grad_norm": 6.630913734436035, "learning_rate": 6.753298720446503e-07, "loss": 0.586, "step": 1140 }, { "epoch": 0.6846684668466847, "grad_norm": 4.569596767425537, "learning_rate": 6.731008296427646e-07, "loss": 0.6544, "step": 1141 }, { "epoch": 0.6852685268526852, "grad_norm": 7.379212856292725, "learning_rate": 6.708736043412924e-07, "loss": 0.567, "step": 1142 }, { "epoch": 0.6858685868586859, "grad_norm": 5.08457088470459, "learning_rate": 6.686482085204793e-07, "loss": 0.3899, "step": 1143 }, { "epoch": 0.6864686468646864, "grad_norm": 7.252013683319092, "learning_rate": 6.664246545504013e-07, "loss": 0.4762, "step": 1144 }, { "epoch": 0.6870687068706871, "grad_norm": 5.280087947845459, "learning_rate": 6.642029547908967e-07, "loss": 0.5143, "step": 1145 }, { "epoch": 0.6876687668766877, "grad_norm": 4.651090621948242, "learning_rate": 6.619831215914973e-07, "loss": 0.485, "step": 1146 }, { "epoch": 0.6882688268826883, "grad_norm": 3.232805013656616, "learning_rate": 6.597651672913582e-07, "loss": 0.2875, "step": 1147 }, { "epoch": 0.6888688868886889, "grad_norm": 8.39585018157959, "learning_rate": 6.575491042191922e-07, "loss": 0.5013, "step": 1148 }, { "epoch": 0.6894689468946895, "grad_norm": 3.0452401638031006, "learning_rate": 6.553349446931973e-07, "loss": 0.291, "step": 1149 }, { "epoch": 0.6900690069006901, "grad_norm": 4.297982692718506, "learning_rate": 6.531227010209928e-07, "loss": 0.3069, "step": 1150 }, { "epoch": 0.6906690669066907, "grad_norm": 2.9752161502838135, "learning_rate": 6.509123854995475e-07, "loss": 0.2324, "step": 1151 }, { "epoch": 0.6912691269126913, "grad_norm": 4.659989833831787, "learning_rate": 6.487040104151113e-07, "loss": 0.5529, "step": 1152 }, { "epoch": 0.6918691869186918, "grad_norm": 5.225297927856445, "learning_rate": 6.464975880431506e-07, "loss": 0.5013, "step": 1153 }, { "epoch": 0.6924692469246925, "grad_norm": 4.737961769104004, "learning_rate": 6.442931306482743e-07, "loss": 0.3919, "step": 1154 }, { "epoch": 0.693069306930693, "grad_norm": 3.7445244789123535, "learning_rate": 6.420906504841715e-07, "loss": 0.372, "step": 1155 }, { "epoch": 0.6936693669366937, "grad_norm": 3.6479735374450684, "learning_rate": 6.398901597935393e-07, "loss": 0.253, "step": 1156 }, { "epoch": 0.6942694269426942, "grad_norm": 5.36738920211792, "learning_rate": 6.376916708080164e-07, "loss": 0.3568, "step": 1157 }, { "epoch": 0.6948694869486949, "grad_norm": 3.6938629150390625, "learning_rate": 6.35495195748115e-07, "loss": 0.4806, "step": 1158 }, { "epoch": 0.6954695469546954, "grad_norm": 5.037597179412842, "learning_rate": 6.33300746823152e-07, "loss": 0.903, "step": 1159 }, { "epoch": 0.6960696069606961, "grad_norm": 3.0052452087402344, "learning_rate": 6.311083362311829e-07, "loss": 0.3438, "step": 1160 }, { "epoch": 0.6966696669666966, "grad_norm": 4.614321231842041, "learning_rate": 6.289179761589323e-07, "loss": 0.3276, "step": 1161 }, { "epoch": 0.6972697269726973, "grad_norm": 4.943059921264648, "learning_rate": 6.267296787817264e-07, "loss": 0.4215, "step": 1162 }, { "epoch": 0.6978697869786978, "grad_norm": 4.098533630371094, "learning_rate": 6.24543456263427e-07, "loss": 0.2903, "step": 1163 }, { "epoch": 0.6984698469846985, "grad_norm": 4.7396931648254395, "learning_rate": 6.223593207563613e-07, "loss": 0.4767, "step": 1164 }, { "epoch": 0.699069906990699, "grad_norm": 4.907295227050781, "learning_rate": 6.20177284401256e-07, "loss": 0.3484, "step": 1165 }, { "epoch": 0.6996699669966997, "grad_norm": 3.0594608783721924, "learning_rate": 6.179973593271702e-07, "loss": 0.3184, "step": 1166 }, { "epoch": 0.7002700270027002, "grad_norm": 5.21073579788208, "learning_rate": 6.158195576514261e-07, "loss": 0.4596, "step": 1167 }, { "epoch": 0.7008700870087009, "grad_norm": 3.2354979515075684, "learning_rate": 6.136438914795433e-07, "loss": 0.3286, "step": 1168 }, { "epoch": 0.7014701470147015, "grad_norm": 6.084530353546143, "learning_rate": 6.114703729051718e-07, "loss": 0.572, "step": 1169 }, { "epoch": 0.7020702070207021, "grad_norm": 4.100319862365723, "learning_rate": 6.092990140100222e-07, "loss": 0.4894, "step": 1170 }, { "epoch": 0.7026702670267027, "grad_norm": 4.408796310424805, "learning_rate": 6.071298268638024e-07, "loss": 0.4142, "step": 1171 }, { "epoch": 0.7032703270327033, "grad_norm": 3.0051193237304688, "learning_rate": 6.049628235241458e-07, "loss": 0.2482, "step": 1172 }, { "epoch": 0.7038703870387039, "grad_norm": 4.809086322784424, "learning_rate": 6.027980160365498e-07, "loss": 0.3259, "step": 1173 }, { "epoch": 0.7044704470447045, "grad_norm": 3.4639244079589844, "learning_rate": 6.006354164343046e-07, "loss": 0.6327, "step": 1174 }, { "epoch": 0.7050705070507051, "grad_norm": 8.053081512451172, "learning_rate": 5.984750367384266e-07, "loss": 0.5537, "step": 1175 }, { "epoch": 0.7056705670567057, "grad_norm": 5.874160289764404, "learning_rate": 5.96316888957595e-07, "loss": 0.4905, "step": 1176 }, { "epoch": 0.7062706270627063, "grad_norm": 4.823639869689941, "learning_rate": 5.9416098508808e-07, "loss": 0.3428, "step": 1177 }, { "epoch": 0.7068706870687068, "grad_norm": 3.933195114135742, "learning_rate": 5.920073371136809e-07, "loss": 0.4581, "step": 1178 }, { "epoch": 0.7074707470747075, "grad_norm": 4.471179485321045, "learning_rate": 5.898559570056571e-07, "loss": 0.4399, "step": 1179 }, { "epoch": 0.708070807080708, "grad_norm": 3.9619829654693604, "learning_rate": 5.877068567226605e-07, "loss": 0.4269, "step": 1180 }, { "epoch": 0.7086708670867087, "grad_norm": 3.49794864654541, "learning_rate": 5.855600482106721e-07, "loss": 0.612, "step": 1181 }, { "epoch": 0.7092709270927092, "grad_norm": 4.9656877517700195, "learning_rate": 5.834155434029325e-07, "loss": 0.4545, "step": 1182 }, { "epoch": 0.7098709870987099, "grad_norm": 3.380495309829712, "learning_rate": 5.812733542198773e-07, "loss": 0.5463, "step": 1183 }, { "epoch": 0.7104710471047104, "grad_norm": 5.213202476501465, "learning_rate": 5.79133492569072e-07, "loss": 0.5734, "step": 1184 }, { "epoch": 0.7110711071107111, "grad_norm": 4.404638767242432, "learning_rate": 5.769959703451413e-07, "loss": 0.473, "step": 1185 }, { "epoch": 0.7116711671167116, "grad_norm": 4.009857654571533, "learning_rate": 5.748607994297086e-07, "loss": 0.5026, "step": 1186 }, { "epoch": 0.7122712271227123, "grad_norm": 3.5211751461029053, "learning_rate": 5.727279916913258e-07, "loss": 0.2475, "step": 1187 }, { "epoch": 0.7128712871287128, "grad_norm": 4.726254940032959, "learning_rate": 5.705975589854102e-07, "loss": 0.4031, "step": 1188 }, { "epoch": 0.7134713471347135, "grad_norm": 2.2979869842529297, "learning_rate": 5.684695131541759e-07, "loss": 0.2242, "step": 1189 }, { "epoch": 0.714071407140714, "grad_norm": 4.552903652191162, "learning_rate": 5.663438660265697e-07, "loss": 0.6816, "step": 1190 }, { "epoch": 0.7146714671467147, "grad_norm": 4.189090728759766, "learning_rate": 5.642206294182059e-07, "loss": 0.5129, "step": 1191 }, { "epoch": 0.7152715271527152, "grad_norm": 5.466653347015381, "learning_rate": 5.620998151312984e-07, "loss": 0.4421, "step": 1192 }, { "epoch": 0.7158715871587159, "grad_norm": 3.566394329071045, "learning_rate": 5.59981434954597e-07, "loss": 0.3262, "step": 1193 }, { "epoch": 0.7164716471647165, "grad_norm": 6.010831832885742, "learning_rate": 5.578655006633215e-07, "loss": 0.6331, "step": 1194 }, { "epoch": 0.7170717071707171, "grad_norm": 4.916393756866455, "learning_rate": 5.557520240190956e-07, "loss": 0.6489, "step": 1195 }, { "epoch": 0.7176717671767177, "grad_norm": 4.818841457366943, "learning_rate": 5.536410167698817e-07, "loss": 0.3132, "step": 1196 }, { "epoch": 0.7182718271827183, "grad_norm": 4.924703121185303, "learning_rate": 5.51532490649917e-07, "loss": 0.2729, "step": 1197 }, { "epoch": 0.7188718871887189, "grad_norm": 4.654323577880859, "learning_rate": 5.49426457379646e-07, "loss": 0.4579, "step": 1198 }, { "epoch": 0.7194719471947195, "grad_norm": 3.687037706375122, "learning_rate": 5.473229286656564e-07, "loss": 0.4878, "step": 1199 }, { "epoch": 0.7200720072007201, "grad_norm": 4.111430644989014, "learning_rate": 5.452219162006145e-07, "loss": 0.3002, "step": 1200 }, { "epoch": 0.7206720672067207, "grad_norm": 5.348633766174316, "learning_rate": 5.431234316632003e-07, "loss": 0.7067, "step": 1201 }, { "epoch": 0.7212721272127213, "grad_norm": 4.030622959136963, "learning_rate": 5.41027486718041e-07, "loss": 0.3457, "step": 1202 }, { "epoch": 0.7218721872187218, "grad_norm": 3.111081123352051, "learning_rate": 5.389340930156476e-07, "loss": 0.2364, "step": 1203 }, { "epoch": 0.7224722472247225, "grad_norm": 4.601378917694092, "learning_rate": 5.368432621923504e-07, "loss": 0.5769, "step": 1204 }, { "epoch": 0.723072307230723, "grad_norm": 3.4696805477142334, "learning_rate": 5.347550058702333e-07, "loss": 0.3137, "step": 1205 }, { "epoch": 0.7236723672367237, "grad_norm": 4.216731071472168, "learning_rate": 5.326693356570686e-07, "loss": 0.2834, "step": 1206 }, { "epoch": 0.7242724272427242, "grad_norm": 6.099046230316162, "learning_rate": 5.305862631462554e-07, "loss": 0.5876, "step": 1207 }, { "epoch": 0.7248724872487249, "grad_norm": 5.612019062042236, "learning_rate": 5.285057999167512e-07, "loss": 0.4623, "step": 1208 }, { "epoch": 0.7254725472547254, "grad_norm": 3.8142495155334473, "learning_rate": 5.264279575330115e-07, "loss": 0.3047, "step": 1209 }, { "epoch": 0.7260726072607261, "grad_norm": 5.249258041381836, "learning_rate": 5.243527475449224e-07, "loss": 0.4036, "step": 1210 }, { "epoch": 0.7266726672667266, "grad_norm": 4.259760856628418, "learning_rate": 5.222801814877369e-07, "loss": 0.2514, "step": 1211 }, { "epoch": 0.7272727272727273, "grad_norm": 2.9422080516815186, "learning_rate": 5.202102708820135e-07, "loss": 0.3392, "step": 1212 }, { "epoch": 0.7278727872787278, "grad_norm": 4.505132675170898, "learning_rate": 5.181430272335486e-07, "loss": 0.4739, "step": 1213 }, { "epoch": 0.7284728472847285, "grad_norm": 4.98128080368042, "learning_rate": 5.160784620333138e-07, "loss": 0.5672, "step": 1214 }, { "epoch": 0.729072907290729, "grad_norm": 5.839948654174805, "learning_rate": 5.140165867573939e-07, "loss": 0.4548, "step": 1215 }, { "epoch": 0.7296729672967297, "grad_norm": 3.762537956237793, "learning_rate": 5.119574128669199e-07, "loss": 0.4505, "step": 1216 }, { "epoch": 0.7302730273027302, "grad_norm": 4.502995491027832, "learning_rate": 5.099009518080079e-07, "loss": 0.3704, "step": 1217 }, { "epoch": 0.7308730873087309, "grad_norm": 3.9570915699005127, "learning_rate": 5.078472150116933e-07, "loss": 0.2437, "step": 1218 }, { "epoch": 0.7314731473147315, "grad_norm": 4.680029392242432, "learning_rate": 5.057962138938701e-07, "loss": 0.4938, "step": 1219 }, { "epoch": 0.7320732073207321, "grad_norm": 3.6244075298309326, "learning_rate": 5.037479598552246e-07, "loss": 0.3831, "step": 1220 }, { "epoch": 0.7326732673267327, "grad_norm": 3.3677756786346436, "learning_rate": 5.017024642811728e-07, "loss": 0.4429, "step": 1221 }, { "epoch": 0.7332733273327333, "grad_norm": 4.904965877532959, "learning_rate": 4.996597385417991e-07, "loss": 0.7966, "step": 1222 }, { "epoch": 0.7338733873387339, "grad_norm": 5.589334011077881, "learning_rate": 4.976197939917904e-07, "loss": 0.4784, "step": 1223 }, { "epoch": 0.7344734473447345, "grad_norm": 3.7204127311706543, "learning_rate": 4.955826419703734e-07, "loss": 0.2981, "step": 1224 }, { "epoch": 0.7350735073507351, "grad_norm": 6.758481502532959, "learning_rate": 4.935482938012544e-07, "loss": 0.734, "step": 1225 }, { "epoch": 0.7356735673567357, "grad_norm": 5.258294582366943, "learning_rate": 4.915167607925522e-07, "loss": 0.5033, "step": 1226 }, { "epoch": 0.7362736273627363, "grad_norm": 4.491812705993652, "learning_rate": 4.894880542367382e-07, "loss": 0.2725, "step": 1227 }, { "epoch": 0.7368736873687368, "grad_norm": 2.793010711669922, "learning_rate": 4.874621854105722e-07, "loss": 0.2761, "step": 1228 }, { "epoch": 0.7374737473747375, "grad_norm": 4.398058891296387, "learning_rate": 4.854391655750406e-07, "loss": 0.2669, "step": 1229 }, { "epoch": 0.738073807380738, "grad_norm": 2.9231832027435303, "learning_rate": 4.834190059752943e-07, "loss": 0.4152, "step": 1230 }, { "epoch": 0.7386738673867387, "grad_norm": 5.5259809494018555, "learning_rate": 4.814017178405828e-07, "loss": 0.3727, "step": 1231 }, { "epoch": 0.7392739273927392, "grad_norm": 4.035454273223877, "learning_rate": 4.793873123841965e-07, "loss": 0.382, "step": 1232 }, { "epoch": 0.7398739873987399, "grad_norm": 4.224624156951904, "learning_rate": 4.773758008034019e-07, "loss": 0.4935, "step": 1233 }, { "epoch": 0.7404740474047404, "grad_norm": 3.1175146102905273, "learning_rate": 4.7536719427937866e-07, "loss": 0.2349, "step": 1234 }, { "epoch": 0.7410741074107411, "grad_norm": 3.580479860305786, "learning_rate": 4.733615039771591e-07, "loss": 0.3756, "step": 1235 }, { "epoch": 0.7416741674167416, "grad_norm": 6.428834915161133, "learning_rate": 4.7135874104556486e-07, "loss": 0.7232, "step": 1236 }, { "epoch": 0.7422742274227423, "grad_norm": 3.7545242309570312, "learning_rate": 4.6935891661714656e-07, "loss": 0.2573, "step": 1237 }, { "epoch": 0.7428742874287428, "grad_norm": 4.559093475341797, "learning_rate": 4.6736204180812e-07, "loss": 0.3512, "step": 1238 }, { "epoch": 0.7434743474347435, "grad_norm": 4.61916446685791, "learning_rate": 4.6536812771830503e-07, "loss": 0.6449, "step": 1239 }, { "epoch": 0.744074407440744, "grad_norm": 3.5689501762390137, "learning_rate": 4.633771854310652e-07, "loss": 0.2679, "step": 1240 }, { "epoch": 0.7446744674467447, "grad_norm": 4.1253981590271, "learning_rate": 4.613892260132438e-07, "loss": 0.5055, "step": 1241 }, { "epoch": 0.7452745274527453, "grad_norm": 5.0024895668029785, "learning_rate": 4.5940426051510397e-07, "loss": 0.4175, "step": 1242 }, { "epoch": 0.7458745874587459, "grad_norm": 4.019662857055664, "learning_rate": 4.574222999702675e-07, "loss": 0.1951, "step": 1243 }, { "epoch": 0.7464746474647465, "grad_norm": 2.9538493156433105, "learning_rate": 4.5544335539565206e-07, "loss": 0.2369, "step": 1244 }, { "epoch": 0.7470747074707471, "grad_norm": 4.233933448791504, "learning_rate": 4.5346743779141085e-07, "loss": 0.4433, "step": 1245 }, { "epoch": 0.7476747674767477, "grad_norm": 4.830684185028076, "learning_rate": 4.514945581408711e-07, "loss": 0.3592, "step": 1246 }, { "epoch": 0.7482748274827483, "grad_norm": 5.101471424102783, "learning_rate": 4.4952472741047467e-07, "loss": 0.4727, "step": 1247 }, { "epoch": 0.7488748874887489, "grad_norm": 5.345502853393555, "learning_rate": 4.475579565497143e-07, "loss": 0.4007, "step": 1248 }, { "epoch": 0.7494749474947495, "grad_norm": 5.368374824523926, "learning_rate": 4.4559425649107406e-07, "loss": 0.6028, "step": 1249 }, { "epoch": 0.7500750075007501, "grad_norm": 6.364988803863525, "learning_rate": 4.4363363814997e-07, "loss": 0.4616, "step": 1250 }, { "epoch": 0.7506750675067507, "grad_norm": 5.035074710845947, "learning_rate": 4.416761124246872e-07, "loss": 0.2517, "step": 1251 }, { "epoch": 0.7512751275127513, "grad_norm": 4.039533615112305, "learning_rate": 4.3972169019631954e-07, "loss": 0.4959, "step": 1252 }, { "epoch": 0.7518751875187519, "grad_norm": 4.877369403839111, "learning_rate": 4.3777038232871156e-07, "loss": 0.4516, "step": 1253 }, { "epoch": 0.7524752475247525, "grad_norm": 4.028416156768799, "learning_rate": 4.358221996683945e-07, "loss": 0.4536, "step": 1254 }, { "epoch": 0.753075307530753, "grad_norm": 3.977614402770996, "learning_rate": 4.3387715304452944e-07, "loss": 0.3619, "step": 1255 }, { "epoch": 0.7536753675367537, "grad_norm": 6.639956951141357, "learning_rate": 4.3193525326884426e-07, "loss": 0.6143, "step": 1256 }, { "epoch": 0.7542754275427542, "grad_norm": 2.3666493892669678, "learning_rate": 4.29996511135575e-07, "loss": 0.2266, "step": 1257 }, { "epoch": 0.7548754875487549, "grad_norm": 3.8589491844177246, "learning_rate": 4.2806093742140646e-07, "loss": 0.4975, "step": 1258 }, { "epoch": 0.7554755475547554, "grad_norm": 4.577023029327393, "learning_rate": 4.2612854288541076e-07, "loss": 0.3139, "step": 1259 }, { "epoch": 0.7560756075607561, "grad_norm": 3.9709291458129883, "learning_rate": 4.241993382689878e-07, "loss": 0.4504, "step": 1260 }, { "epoch": 0.7566756675667566, "grad_norm": 5.212405681610107, "learning_rate": 4.2227333429580747e-07, "loss": 0.605, "step": 1261 }, { "epoch": 0.7572757275727573, "grad_norm": 4.752591609954834, "learning_rate": 4.2035054167174724e-07, "loss": 0.3162, "step": 1262 }, { "epoch": 0.7578757875787578, "grad_norm": 4.838736534118652, "learning_rate": 4.184309710848346e-07, "loss": 0.4143, "step": 1263 }, { "epoch": 0.7584758475847585, "grad_norm": 4.584652900695801, "learning_rate": 4.165146332051863e-07, "loss": 0.2999, "step": 1264 }, { "epoch": 0.759075907590759, "grad_norm": 4.366139888763428, "learning_rate": 4.146015386849514e-07, "loss": 0.3331, "step": 1265 }, { "epoch": 0.7596759675967597, "grad_norm": 4.056859016418457, "learning_rate": 4.126916981582488e-07, "loss": 0.6682, "step": 1266 }, { "epoch": 0.7602760276027603, "grad_norm": 5.572482109069824, "learning_rate": 4.107851222411101e-07, "loss": 0.5473, "step": 1267 }, { "epoch": 0.7608760876087609, "grad_norm": 4.052997589111328, "learning_rate": 4.0888182153142125e-07, "loss": 0.3722, "step": 1268 }, { "epoch": 0.7614761476147615, "grad_norm": 5.690006256103516, "learning_rate": 4.069818066088615e-07, "loss": 0.5323, "step": 1269 }, { "epoch": 0.7620762076207621, "grad_norm": 4.740429878234863, "learning_rate": 4.05085088034846e-07, "loss": 0.367, "step": 1270 }, { "epoch": 0.7626762676267627, "grad_norm": 4.313534736633301, "learning_rate": 4.031916763524673e-07, "loss": 0.3624, "step": 1271 }, { "epoch": 0.7632763276327633, "grad_norm": 5.825881004333496, "learning_rate": 4.0130158208643605e-07, "loss": 0.6134, "step": 1272 }, { "epoch": 0.7638763876387639, "grad_norm": 5.217489719390869, "learning_rate": 3.9941481574302206e-07, "loss": 0.375, "step": 1273 }, { "epoch": 0.7644764476447645, "grad_norm": 4.60443115234375, "learning_rate": 3.9753138780999774e-07, "loss": 0.3425, "step": 1274 }, { "epoch": 0.7650765076507651, "grad_norm": 5.968270778656006, "learning_rate": 3.956513087565776e-07, "loss": 0.724, "step": 1275 }, { "epoch": 0.7656765676567657, "grad_norm": 4.4500226974487305, "learning_rate": 3.9377458903336223e-07, "loss": 0.3131, "step": 1276 }, { "epoch": 0.7662766276627663, "grad_norm": 5.364919185638428, "learning_rate": 3.919012390722772e-07, "loss": 0.4087, "step": 1277 }, { "epoch": 0.7668766876687669, "grad_norm": 5.130373954772949, "learning_rate": 3.9003126928651874e-07, "loss": 0.4122, "step": 1278 }, { "epoch": 0.7674767476747675, "grad_norm": 5.320981979370117, "learning_rate": 3.881646900704936e-07, "loss": 0.5013, "step": 1279 }, { "epoch": 0.768076807680768, "grad_norm": 4.132413387298584, "learning_rate": 3.8630151179976114e-07, "loss": 0.3545, "step": 1280 }, { "epoch": 0.7686768676867687, "grad_norm": 5.67943811416626, "learning_rate": 3.844417448309767e-07, "loss": 0.3887, "step": 1281 }, { "epoch": 0.7692769276927692, "grad_norm": 4.656854629516602, "learning_rate": 3.825853995018332e-07, "loss": 0.4359, "step": 1282 }, { "epoch": 0.7698769876987699, "grad_norm": 4.439621448516846, "learning_rate": 3.8073248613100483e-07, "loss": 0.4043, "step": 1283 }, { "epoch": 0.7704770477047704, "grad_norm": 4.985435485839844, "learning_rate": 3.7888301501808817e-07, "loss": 0.3438, "step": 1284 }, { "epoch": 0.7710771077107711, "grad_norm": 5.917595386505127, "learning_rate": 3.7703699644354547e-07, "loss": 0.5914, "step": 1285 }, { "epoch": 0.7716771677167716, "grad_norm": 4.784394264221191, "learning_rate": 3.751944406686489e-07, "loss": 0.4124, "step": 1286 }, { "epoch": 0.7722772277227723, "grad_norm": 3.868043899536133, "learning_rate": 3.7335535793542125e-07, "loss": 0.2978, "step": 1287 }, { "epoch": 0.7728772877287728, "grad_norm": 3.977839231491089, "learning_rate": 3.715197584665801e-07, "loss": 0.3556, "step": 1288 }, { "epoch": 0.7734773477347735, "grad_norm": 4.838659763336182, "learning_rate": 3.6968765246548196e-07, "loss": 0.61, "step": 1289 }, { "epoch": 0.774077407740774, "grad_norm": 4.323929309844971, "learning_rate": 3.6785905011606343e-07, "loss": 0.2997, "step": 1290 }, { "epoch": 0.7746774677467747, "grad_norm": 3.9462532997131348, "learning_rate": 3.660339615827862e-07, "loss": 0.3355, "step": 1291 }, { "epoch": 0.7752775277527753, "grad_norm": 7.459483623504639, "learning_rate": 3.642123970105797e-07, "loss": 0.668, "step": 1292 }, { "epoch": 0.7758775877587759, "grad_norm": 3.4036812782287598, "learning_rate": 3.6239436652478616e-07, "loss": 0.2269, "step": 1293 }, { "epoch": 0.7764776477647765, "grad_norm": 3.6945431232452393, "learning_rate": 3.605798802311023e-07, "loss": 0.9714, "step": 1294 }, { "epoch": 0.7770777077707771, "grad_norm": 4.41254997253418, "learning_rate": 3.5876894821552375e-07, "loss": 0.309, "step": 1295 }, { "epoch": 0.7776777677767777, "grad_norm": 5.083664894104004, "learning_rate": 3.5696158054429035e-07, "loss": 0.6724, "step": 1296 }, { "epoch": 0.7782778277827783, "grad_norm": 2.1821577548980713, "learning_rate": 3.551577872638296e-07, "loss": 0.2756, "step": 1297 }, { "epoch": 0.7788778877887789, "grad_norm": 3.3261382579803467, "learning_rate": 3.53357578400698e-07, "loss": 0.27, "step": 1298 }, { "epoch": 0.7794779477947795, "grad_norm": 4.042372703552246, "learning_rate": 3.515609639615306e-07, "loss": 0.3935, "step": 1299 }, { "epoch": 0.7800780078007801, "grad_norm": 4.100063323974609, "learning_rate": 3.497679539329801e-07, "loss": 0.356, "step": 1300 }, { "epoch": 0.7806780678067807, "grad_norm": 3.3702478408813477, "learning_rate": 3.479785582816659e-07, "loss": 0.2875, "step": 1301 }, { "epoch": 0.7812781278127813, "grad_norm": 3.7905967235565186, "learning_rate": 3.461927869541149e-07, "loss": 0.282, "step": 1302 }, { "epoch": 0.7818781878187819, "grad_norm": 4.3021440505981445, "learning_rate": 3.444106498767081e-07, "loss": 0.3127, "step": 1303 }, { "epoch": 0.7824782478247825, "grad_norm": 4.8544921875, "learning_rate": 3.426321569556263e-07, "loss": 0.3943, "step": 1304 }, { "epoch": 0.783078307830783, "grad_norm": 3.5257935523986816, "learning_rate": 3.4085731807679265e-07, "loss": 0.2431, "step": 1305 }, { "epoch": 0.7836783678367837, "grad_norm": 5.895580768585205, "learning_rate": 3.390861431058192e-07, "loss": 0.4881, "step": 1306 }, { "epoch": 0.7842784278427842, "grad_norm": 6.185301303863525, "learning_rate": 3.3731864188795247e-07, "loss": 0.5353, "step": 1307 }, { "epoch": 0.7848784878487849, "grad_norm": 3.053955078125, "learning_rate": 3.355548242480174e-07, "loss": 0.5113, "step": 1308 }, { "epoch": 0.7854785478547854, "grad_norm": 7.03208589553833, "learning_rate": 3.337946999903636e-07, "loss": 0.5693, "step": 1309 }, { "epoch": 0.7860786078607861, "grad_norm": 3.814887046813965, "learning_rate": 3.3203827889881043e-07, "loss": 0.5669, "step": 1310 }, { "epoch": 0.7866786678667866, "grad_norm": 4.010893821716309, "learning_rate": 3.3028557073659367e-07, "loss": 0.3752, "step": 1311 }, { "epoch": 0.7872787278727873, "grad_norm": 2.9045114517211914, "learning_rate": 3.2853658524630967e-07, "loss": 0.1818, "step": 1312 }, { "epoch": 0.7878787878787878, "grad_norm": 5.369817733764648, "learning_rate": 3.2679133214986167e-07, "loss": 0.3983, "step": 1313 }, { "epoch": 0.7884788478847885, "grad_norm": 4.355273246765137, "learning_rate": 3.2504982114840727e-07, "loss": 0.3871, "step": 1314 }, { "epoch": 0.789078907890789, "grad_norm": 5.559607028961182, "learning_rate": 3.233120619223021e-07, "loss": 0.7442, "step": 1315 }, { "epoch": 0.7896789678967897, "grad_norm": 2.7064874172210693, "learning_rate": 3.215780641310474e-07, "loss": 0.2256, "step": 1316 }, { "epoch": 0.7902790279027903, "grad_norm": 3.519108772277832, "learning_rate": 3.198478374132367e-07, "loss": 0.2474, "step": 1317 }, { "epoch": 0.7908790879087909, "grad_norm": 6.115477561950684, "learning_rate": 3.181213913865013e-07, "loss": 0.5358, "step": 1318 }, { "epoch": 0.7914791479147915, "grad_norm": 5.842758655548096, "learning_rate": 3.1639873564745665e-07, "loss": 0.6164, "step": 1319 }, { "epoch": 0.7920792079207921, "grad_norm": 5.848071098327637, "learning_rate": 3.1467987977165066e-07, "loss": 0.4073, "step": 1320 }, { "epoch": 0.7926792679267927, "grad_norm": 5.1477227210998535, "learning_rate": 3.12964833313508e-07, "loss": 0.413, "step": 1321 }, { "epoch": 0.7932793279327933, "grad_norm": 4.93935489654541, "learning_rate": 3.1125360580628e-07, "loss": 0.6892, "step": 1322 }, { "epoch": 0.7938793879387939, "grad_norm": 4.943698406219482, "learning_rate": 3.0954620676198784e-07, "loss": 0.8308, "step": 1323 }, { "epoch": 0.7944794479447945, "grad_norm": 2.9956541061401367, "learning_rate": 3.078426456713734e-07, "loss": 0.2087, "step": 1324 }, { "epoch": 0.7950795079507951, "grad_norm": 4.950900077819824, "learning_rate": 3.06142932003845e-07, "loss": 0.3552, "step": 1325 }, { "epoch": 0.7956795679567957, "grad_norm": 3.268460988998413, "learning_rate": 3.0444707520742384e-07, "loss": 0.3033, "step": 1326 }, { "epoch": 0.7962796279627963, "grad_norm": 3.3283262252807617, "learning_rate": 3.027550847086927e-07, "loss": 0.4622, "step": 1327 }, { "epoch": 0.7968796879687969, "grad_norm": 4.239066123962402, "learning_rate": 3.0106696991274274e-07, "loss": 0.2617, "step": 1328 }, { "epoch": 0.7974797479747975, "grad_norm": 6.173221111297607, "learning_rate": 2.993827402031228e-07, "loss": 0.5319, "step": 1329 }, { "epoch": 0.798079807980798, "grad_norm": 5.446516990661621, "learning_rate": 2.9770240494178513e-07, "loss": 0.3806, "step": 1330 }, { "epoch": 0.7986798679867987, "grad_norm": 4.569564342498779, "learning_rate": 2.96025973469034e-07, "loss": 0.4106, "step": 1331 }, { "epoch": 0.7992799279927992, "grad_norm": 5.962780475616455, "learning_rate": 2.943534551034754e-07, "loss": 0.4906, "step": 1332 }, { "epoch": 0.7998799879987999, "grad_norm": 6.702475547790527, "learning_rate": 2.9268485914196303e-07, "loss": 0.7538, "step": 1333 }, { "epoch": 0.8004800480048004, "grad_norm": 3.746778964996338, "learning_rate": 2.910201948595472e-07, "loss": 0.3144, "step": 1334 }, { "epoch": 0.8010801080108011, "grad_norm": 4.149717330932617, "learning_rate": 2.8935947150942476e-07, "loss": 0.2768, "step": 1335 }, { "epoch": 0.8016801680168016, "grad_norm": 5.430441856384277, "learning_rate": 2.8770269832288553e-07, "loss": 0.4204, "step": 1336 }, { "epoch": 0.8022802280228023, "grad_norm": 3.0930044651031494, "learning_rate": 2.8604988450926194e-07, "loss": 0.2551, "step": 1337 }, { "epoch": 0.8028802880288028, "grad_norm": 4.491976261138916, "learning_rate": 2.84401039255879e-07, "loss": 0.3153, "step": 1338 }, { "epoch": 0.8034803480348035, "grad_norm": 4.057061672210693, "learning_rate": 2.827561717280007e-07, "loss": 0.4778, "step": 1339 }, { "epoch": 0.804080408040804, "grad_norm": 4.78984260559082, "learning_rate": 2.811152910687813e-07, "loss": 0.384, "step": 1340 }, { "epoch": 0.8046804680468047, "grad_norm": 4.186589241027832, "learning_rate": 2.7947840639921303e-07, "loss": 0.2948, "step": 1341 }, { "epoch": 0.8052805280528053, "grad_norm": 5.38515043258667, "learning_rate": 2.778455268180767e-07, "loss": 0.5956, "step": 1342 }, { "epoch": 0.8058805880588059, "grad_norm": 5.838461875915527, "learning_rate": 2.762166614018909e-07, "loss": 0.5828, "step": 1343 }, { "epoch": 0.8064806480648065, "grad_norm": 3.7255406379699707, "learning_rate": 2.7459181920485905e-07, "loss": 0.3441, "step": 1344 }, { "epoch": 0.8070807080708071, "grad_norm": 6.00517463684082, "learning_rate": 2.7297100925882357e-07, "loss": 0.7202, "step": 1345 }, { "epoch": 0.8076807680768077, "grad_norm": 4.279200077056885, "learning_rate": 2.713542405732112e-07, "loss": 0.6257, "step": 1346 }, { "epoch": 0.8082808280828083, "grad_norm": 4.848310470581055, "learning_rate": 2.697415221349867e-07, "loss": 0.4068, "step": 1347 }, { "epoch": 0.8088808880888089, "grad_norm": 5.675711154937744, "learning_rate": 2.681328629085998e-07, "loss": 0.4406, "step": 1348 }, { "epoch": 0.8094809480948095, "grad_norm": 5.09115743637085, "learning_rate": 2.6652827183593705e-07, "loss": 0.5245, "step": 1349 }, { "epoch": 0.8100810081008101, "grad_norm": 3.573528528213501, "learning_rate": 2.6492775783627287e-07, "loss": 0.2633, "step": 1350 }, { "epoch": 0.8106810681068107, "grad_norm": 4.830117225646973, "learning_rate": 2.633313298062165e-07, "loss": 0.3439, "step": 1351 }, { "epoch": 0.8112811281128113, "grad_norm": 2.5437638759613037, "learning_rate": 2.6173899661966725e-07, "loss": 0.1835, "step": 1352 }, { "epoch": 0.8118811881188119, "grad_norm": 6.677098751068115, "learning_rate": 2.601507671277622e-07, "loss": 0.6954, "step": 1353 }, { "epoch": 0.8124812481248125, "grad_norm": 4.807258605957031, "learning_rate": 2.585666501588268e-07, "loss": 0.3259, "step": 1354 }, { "epoch": 0.813081308130813, "grad_norm": 4.647261142730713, "learning_rate": 2.569866545183278e-07, "loss": 0.7751, "step": 1355 }, { "epoch": 0.8136813681368137, "grad_norm": 2.2636678218841553, "learning_rate": 2.5541078898882185e-07, "loss": 0.2027, "step": 1356 }, { "epoch": 0.8142814281428142, "grad_norm": 4.560409069061279, "learning_rate": 2.538390623299096e-07, "loss": 0.3856, "step": 1357 }, { "epoch": 0.8148814881488149, "grad_norm": 6.554934978485107, "learning_rate": 2.5227148327818415e-07, "loss": 0.3564, "step": 1358 }, { "epoch": 0.8154815481548154, "grad_norm": 3.1876423358917236, "learning_rate": 2.5070806054718376e-07, "loss": 0.2767, "step": 1359 }, { "epoch": 0.8160816081608161, "grad_norm": 4.519199371337891, "learning_rate": 2.491488028273444e-07, "loss": 0.6105, "step": 1360 }, { "epoch": 0.8166816681668166, "grad_norm": 4.166067123413086, "learning_rate": 2.475937187859495e-07, "loss": 1.0499, "step": 1361 }, { "epoch": 0.8172817281728173, "grad_norm": 4.088628768920898, "learning_rate": 2.460428170670825e-07, "loss": 0.3777, "step": 1362 }, { "epoch": 0.8178817881788178, "grad_norm": 4.8367390632629395, "learning_rate": 2.4449610629158035e-07, "loss": 0.5347, "step": 1363 }, { "epoch": 0.8184818481848185, "grad_norm": 4.799557685852051, "learning_rate": 2.4295359505698277e-07, "loss": 0.403, "step": 1364 }, { "epoch": 0.819081908190819, "grad_norm": 4.156375408172607, "learning_rate": 2.4141529193748624e-07, "loss": 0.3255, "step": 1365 }, { "epoch": 0.8196819681968197, "grad_norm": 4.744760990142822, "learning_rate": 2.39881205483897e-07, "loss": 0.3711, "step": 1366 }, { "epoch": 0.8202820282028203, "grad_norm": 4.302761554718018, "learning_rate": 2.3835134422358117e-07, "loss": 0.3628, "step": 1367 }, { "epoch": 0.8208820882088209, "grad_norm": 4.355611801147461, "learning_rate": 2.368257166604203e-07, "loss": 0.4045, "step": 1368 }, { "epoch": 0.8214821482148215, "grad_norm": 3.7734901905059814, "learning_rate": 2.3530433127476045e-07, "loss": 0.3667, "step": 1369 }, { "epoch": 0.8220822082208221, "grad_norm": 3.9701430797576904, "learning_rate": 2.3378719652336898e-07, "loss": 0.4165, "step": 1370 }, { "epoch": 0.8226822682268227, "grad_norm": 4.873783588409424, "learning_rate": 2.3227432083938514e-07, "loss": 0.6398, "step": 1371 }, { "epoch": 0.8232823282328233, "grad_norm": 6.074627876281738, "learning_rate": 2.307657126322734e-07, "loss": 0.6347, "step": 1372 }, { "epoch": 0.8238823882388239, "grad_norm": 7.238354682922363, "learning_rate": 2.292613802877773e-07, "loss": 0.7469, "step": 1373 }, { "epoch": 0.8244824482448245, "grad_norm": 5.080560207366943, "learning_rate": 2.277613321678723e-07, "loss": 0.7507, "step": 1374 }, { "epoch": 0.8250825082508251, "grad_norm": 5.467433929443359, "learning_rate": 2.2626557661072033e-07, "loss": 0.4078, "step": 1375 }, { "epoch": 0.8256825682568257, "grad_norm": 5.363209247589111, "learning_rate": 2.2477412193062206e-07, "loss": 0.3892, "step": 1376 }, { "epoch": 0.8262826282628263, "grad_norm": 2.794264078140259, "learning_rate": 2.23286976417971e-07, "loss": 0.2083, "step": 1377 }, { "epoch": 0.8268826882688269, "grad_norm": 4.540343761444092, "learning_rate": 2.218041483392089e-07, "loss": 0.895, "step": 1378 }, { "epoch": 0.8274827482748275, "grad_norm": 3.943225622177124, "learning_rate": 2.2032564593677772e-07, "loss": 0.2976, "step": 1379 }, { "epoch": 0.828082808280828, "grad_norm": 3.776878595352173, "learning_rate": 2.188514774290746e-07, "loss": 0.2683, "step": 1380 }, { "epoch": 0.8286828682868287, "grad_norm": 6.20085334777832, "learning_rate": 2.173816510104073e-07, "loss": 0.5916, "step": 1381 }, { "epoch": 0.8292829282928292, "grad_norm": 4.997322082519531, "learning_rate": 2.159161748509467e-07, "loss": 0.3183, "step": 1382 }, { "epoch": 0.8298829882988299, "grad_norm": 4.523015975952148, "learning_rate": 2.1445505709668232e-07, "loss": 0.2984, "step": 1383 }, { "epoch": 0.8304830483048304, "grad_norm": 4.335378170013428, "learning_rate": 2.129983058693783e-07, "loss": 0.3816, "step": 1384 }, { "epoch": 0.8310831083108311, "grad_norm": 4.098750114440918, "learning_rate": 2.1154592926652547e-07, "loss": 0.345, "step": 1385 }, { "epoch": 0.8316831683168316, "grad_norm": 3.456987142562866, "learning_rate": 2.1009793536129882e-07, "loss": 0.4191, "step": 1386 }, { "epoch": 0.8322832283228323, "grad_norm": 4.99672269821167, "learning_rate": 2.0865433220251128e-07, "loss": 0.3738, "step": 1387 }, { "epoch": 0.8328832883288328, "grad_norm": 5.946048736572266, "learning_rate": 2.0721512781456951e-07, "loss": 0.6381, "step": 1388 }, { "epoch": 0.8334833483348335, "grad_norm": 6.745075702667236, "learning_rate": 2.0578033019743003e-07, "loss": 0.7986, "step": 1389 }, { "epoch": 0.834083408340834, "grad_norm": 4.25808572769165, "learning_rate": 2.0434994732655187e-07, "loss": 0.4512, "step": 1390 }, { "epoch": 0.8346834683468347, "grad_norm": 4.046769618988037, "learning_rate": 2.0292398715285652e-07, "loss": 0.4631, "step": 1391 }, { "epoch": 0.8352835283528353, "grad_norm": 6.396487712860107, "learning_rate": 2.015024576026797e-07, "loss": 0.5223, "step": 1392 }, { "epoch": 0.8358835883588359, "grad_norm": 4.121705055236816, "learning_rate": 2.0008536657773045e-07, "loss": 0.3586, "step": 1393 }, { "epoch": 0.8364836483648365, "grad_norm": 4.4463677406311035, "learning_rate": 1.9867272195504504e-07, "loss": 0.4367, "step": 1394 }, { "epoch": 0.8370837083708371, "grad_norm": 4.433170318603516, "learning_rate": 1.9726453158694378e-07, "loss": 0.329, "step": 1395 }, { "epoch": 0.8376837683768377, "grad_norm": 4.794647693634033, "learning_rate": 1.9586080330098898e-07, "loss": 0.3704, "step": 1396 }, { "epoch": 0.8382838283828383, "grad_norm": 2.206695795059204, "learning_rate": 1.9446154489993783e-07, "loss": 0.2124, "step": 1397 }, { "epoch": 0.8388838883888389, "grad_norm": 3.206564426422119, "learning_rate": 1.930667641617031e-07, "loss": 0.1984, "step": 1398 }, { "epoch": 0.8394839483948395, "grad_norm": 4.239818096160889, "learning_rate": 1.9167646883930754e-07, "loss": 0.4065, "step": 1399 }, { "epoch": 0.8400840084008401, "grad_norm": 4.069187641143799, "learning_rate": 1.9029066666084092e-07, "loss": 0.3022, "step": 1400 }, { "epoch": 0.8406840684068407, "grad_norm": 4.5489888191223145, "learning_rate": 1.8890936532941748e-07, "loss": 0.4933, "step": 1401 }, { "epoch": 0.8412841284128413, "grad_norm": 4.5652360916137695, "learning_rate": 1.8753257252313358e-07, "loss": 0.4271, "step": 1402 }, { "epoch": 0.8418841884188419, "grad_norm": 5.711679458618164, "learning_rate": 1.86160295895024e-07, "loss": 0.4554, "step": 1403 }, { "epoch": 0.8424842484248425, "grad_norm": 4.791299343109131, "learning_rate": 1.847925430730203e-07, "loss": 0.2845, "step": 1404 }, { "epoch": 0.843084308430843, "grad_norm": 4.721192359924316, "learning_rate": 1.8342932165990722e-07, "loss": 0.4644, "step": 1405 }, { "epoch": 0.8436843684368437, "grad_norm": 3.8138325214385986, "learning_rate": 1.8207063923328235e-07, "loss": 0.3568, "step": 1406 }, { "epoch": 0.8442844284428442, "grad_norm": 4.080888748168945, "learning_rate": 1.8071650334551248e-07, "loss": 0.4604, "step": 1407 }, { "epoch": 0.8448844884488449, "grad_norm": 5.671288013458252, "learning_rate": 1.7936692152369127e-07, "loss": 0.6185, "step": 1408 }, { "epoch": 0.8454845484548454, "grad_norm": 2.408132314682007, "learning_rate": 1.7802190126959949e-07, "loss": 0.5332, "step": 1409 }, { "epoch": 0.8460846084608461, "grad_norm": 4.482064723968506, "learning_rate": 1.7668145005966096e-07, "loss": 0.3289, "step": 1410 }, { "epoch": 0.8466846684668466, "grad_norm": 3.682008743286133, "learning_rate": 1.7534557534490224e-07, "loss": 0.3175, "step": 1411 }, { "epoch": 0.8472847284728473, "grad_norm": 4.292359352111816, "learning_rate": 1.7401428455091162e-07, "loss": 0.7252, "step": 1412 }, { "epoch": 0.8478847884788479, "grad_norm": 4.492998123168945, "learning_rate": 1.7268758507779613e-07, "loss": 0.3281, "step": 1413 }, { "epoch": 0.8484848484848485, "grad_norm": 4.906607627868652, "learning_rate": 1.713654843001431e-07, "loss": 0.3451, "step": 1414 }, { "epoch": 0.849084908490849, "grad_norm": 5.150009632110596, "learning_rate": 1.700479895669754e-07, "loss": 0.3931, "step": 1415 }, { "epoch": 0.8496849684968497, "grad_norm": 4.748948574066162, "learning_rate": 1.6873510820171465e-07, "loss": 0.7093, "step": 1416 }, { "epoch": 0.8502850285028503, "grad_norm": 3.2883808612823486, "learning_rate": 1.6742684750213797e-07, "loss": 0.2314, "step": 1417 }, { "epoch": 0.8508850885088509, "grad_norm": 3.7383460998535156, "learning_rate": 1.6612321474033786e-07, "loss": 0.3501, "step": 1418 }, { "epoch": 0.8514851485148515, "grad_norm": 3.758708953857422, "learning_rate": 1.6482421716268214e-07, "loss": 0.2385, "step": 1419 }, { "epoch": 0.8520852085208521, "grad_norm": 4.774543285369873, "learning_rate": 1.6352986198977325e-07, "loss": 0.3258, "step": 1420 }, { "epoch": 0.8526852685268527, "grad_norm": 5.575724124908447, "learning_rate": 1.622401564164092e-07, "loss": 0.4907, "step": 1421 }, { "epoch": 0.8532853285328533, "grad_norm": 5.0018439292907715, "learning_rate": 1.6095510761154185e-07, "loss": 0.4383, "step": 1422 }, { "epoch": 0.8538853885388539, "grad_norm": 4.332344055175781, "learning_rate": 1.5967472271823823e-07, "loss": 0.3921, "step": 1423 }, { "epoch": 0.8544854485448545, "grad_norm": 5.454362392425537, "learning_rate": 1.583990088536411e-07, "loss": 0.4839, "step": 1424 }, { "epoch": 0.8550855085508551, "grad_norm": 3.4520835876464844, "learning_rate": 1.57127973108928e-07, "loss": 0.3751, "step": 1425 }, { "epoch": 0.8556855685568557, "grad_norm": 4.080129146575928, "learning_rate": 1.5586162254927315e-07, "loss": 0.2746, "step": 1426 }, { "epoch": 0.8562856285628563, "grad_norm": 4.772724151611328, "learning_rate": 1.5459996421380795e-07, "loss": 0.5197, "step": 1427 }, { "epoch": 0.8568856885688569, "grad_norm": 3.8783793449401855, "learning_rate": 1.5334300511558108e-07, "loss": 0.3622, "step": 1428 }, { "epoch": 0.8574857485748575, "grad_norm": 5.060827732086182, "learning_rate": 1.5209075224152034e-07, "loss": 0.6262, "step": 1429 }, { "epoch": 0.858085808580858, "grad_norm": 2.5569818019866943, "learning_rate": 1.5084321255239375e-07, "loss": 0.5414, "step": 1430 }, { "epoch": 0.8586858685868587, "grad_norm": 3.8110437393188477, "learning_rate": 1.4960039298277028e-07, "loss": 0.2003, "step": 1431 }, { "epoch": 0.8592859285928592, "grad_norm": 3.5321569442749023, "learning_rate": 1.4836230044098162e-07, "loss": 0.4064, "step": 1432 }, { "epoch": 0.8598859885988599, "grad_norm": 4.297152996063232, "learning_rate": 1.471289418090841e-07, "loss": 0.5072, "step": 1433 }, { "epoch": 0.8604860486048604, "grad_norm": 5.451434135437012, "learning_rate": 1.4590032394282005e-07, "loss": 0.6099, "step": 1434 }, { "epoch": 0.8610861086108611, "grad_norm": 5.208282470703125, "learning_rate": 1.446764536715802e-07, "loss": 0.5497, "step": 1435 }, { "epoch": 0.8616861686168616, "grad_norm": 3.7708733081817627, "learning_rate": 1.4345733779836412e-07, "loss": 0.4894, "step": 1436 }, { "epoch": 0.8622862286228623, "grad_norm": 3.7889404296875, "learning_rate": 1.4224298309974515e-07, "loss": 0.3313, "step": 1437 }, { "epoch": 0.8628862886288629, "grad_norm": 4.150409698486328, "learning_rate": 1.4103339632582978e-07, "loss": 0.3105, "step": 1438 }, { "epoch": 0.8634863486348635, "grad_norm": 6.4231767654418945, "learning_rate": 1.3982858420022281e-07, "loss": 0.8777, "step": 1439 }, { "epoch": 0.8640864086408641, "grad_norm": 4.43938684463501, "learning_rate": 1.386285534199878e-07, "loss": 0.7396, "step": 1440 }, { "epoch": 0.8646864686468647, "grad_norm": 3.9243979454040527, "learning_rate": 1.374333106556107e-07, "loss": 0.4576, "step": 1441 }, { "epoch": 0.8652865286528653, "grad_norm": 4.475179672241211, "learning_rate": 1.3624286255096395e-07, "loss": 0.4742, "step": 1442 }, { "epoch": 0.8658865886588659, "grad_norm": 6.087238311767578, "learning_rate": 1.3505721572326667e-07, "loss": 0.6607, "step": 1443 }, { "epoch": 0.8664866486648665, "grad_norm": 3.5067522525787354, "learning_rate": 1.3387637676305086e-07, "loss": 0.4915, "step": 1444 }, { "epoch": 0.8670867086708671, "grad_norm": 3.4240007400512695, "learning_rate": 1.327003522341237e-07, "loss": 0.4586, "step": 1445 }, { "epoch": 0.8676867686768677, "grad_norm": 3.9521398544311523, "learning_rate": 1.315291486735298e-07, "loss": 0.2744, "step": 1446 }, { "epoch": 0.8682868286828683, "grad_norm": 4.469539642333984, "learning_rate": 1.3036277259151673e-07, "loss": 0.4997, "step": 1447 }, { "epoch": 0.8688868886888689, "grad_norm": 4.575442790985107, "learning_rate": 1.2920123047149812e-07, "loss": 0.4747, "step": 1448 }, { "epoch": 0.8694869486948695, "grad_norm": 4.575763702392578, "learning_rate": 1.2804452877001715e-07, "loss": 0.4111, "step": 1449 }, { "epoch": 0.8700870087008701, "grad_norm": 5.303211212158203, "learning_rate": 1.268926739167112e-07, "loss": 0.4311, "step": 1450 }, { "epoch": 0.8706870687068707, "grad_norm": 3.3651015758514404, "learning_rate": 1.257456723142759e-07, "loss": 0.263, "step": 1451 }, { "epoch": 0.8712871287128713, "grad_norm": 5.530414581298828, "learning_rate": 1.2460353033843007e-07, "loss": 0.3322, "step": 1452 }, { "epoch": 0.8718871887188719, "grad_norm": 4.91497802734375, "learning_rate": 1.2346625433787937e-07, "loss": 0.3511, "step": 1453 }, { "epoch": 0.8724872487248725, "grad_norm": 4.902407169342041, "learning_rate": 1.2233385063428135e-07, "loss": 0.3036, "step": 1454 }, { "epoch": 0.873087308730873, "grad_norm": 5.410004615783691, "learning_rate": 1.212063255222111e-07, "loss": 0.6134, "step": 1455 }, { "epoch": 0.8736873687368737, "grad_norm": 4.969468593597412, "learning_rate": 1.2008368526912505e-07, "loss": 0.3355, "step": 1456 }, { "epoch": 0.8742874287428742, "grad_norm": 3.267533779144287, "learning_rate": 1.1896593611532646e-07, "loss": 0.2208, "step": 1457 }, { "epoch": 0.8748874887488749, "grad_norm": 4.128666877746582, "learning_rate": 1.1785308427393181e-07, "loss": 0.3564, "step": 1458 }, { "epoch": 0.8754875487548754, "grad_norm": 4.309912204742432, "learning_rate": 1.1674513593083435e-07, "loss": 0.3752, "step": 1459 }, { "epoch": 0.8760876087608761, "grad_norm": 4.4663591384887695, "learning_rate": 1.1564209724467189e-07, "loss": 0.6067, "step": 1460 }, { "epoch": 0.8766876687668766, "grad_norm": 5.429699420928955, "learning_rate": 1.145439743467902e-07, "loss": 0.4409, "step": 1461 }, { "epoch": 0.8772877287728773, "grad_norm": 4.721487522125244, "learning_rate": 1.1345077334121101e-07, "loss": 0.5374, "step": 1462 }, { "epoch": 0.8778877887788779, "grad_norm": 5.377363681793213, "learning_rate": 1.1236250030459748e-07, "loss": 0.3538, "step": 1463 }, { "epoch": 0.8784878487848785, "grad_norm": 3.056407928466797, "learning_rate": 1.1127916128621907e-07, "loss": 0.2938, "step": 1464 }, { "epoch": 0.8790879087908791, "grad_norm": 3.3492915630340576, "learning_rate": 1.1020076230791985e-07, "loss": 0.2447, "step": 1465 }, { "epoch": 0.8796879687968797, "grad_norm": 4.417285442352295, "learning_rate": 1.0912730936408442e-07, "loss": 0.3629, "step": 1466 }, { "epoch": 0.8802880288028803, "grad_norm": 4.357728958129883, "learning_rate": 1.0805880842160375e-07, "loss": 0.3727, "step": 1467 }, { "epoch": 0.8808880888088809, "grad_norm": 4.824587345123291, "learning_rate": 1.0699526541984294e-07, "loss": 0.4011, "step": 1468 }, { "epoch": 0.8814881488148815, "grad_norm": 4.924090385437012, "learning_rate": 1.0593668627060748e-07, "loss": 0.3197, "step": 1469 }, { "epoch": 0.8820882088208821, "grad_norm": 4.946131229400635, "learning_rate": 1.0488307685811171e-07, "loss": 0.479, "step": 1470 }, { "epoch": 0.8826882688268827, "grad_norm": 4.4885149002075195, "learning_rate": 1.038344430389445e-07, "loss": 0.3015, "step": 1471 }, { "epoch": 0.8832883288328833, "grad_norm": 5.285086631774902, "learning_rate": 1.0279079064203721e-07, "loss": 0.4498, "step": 1472 }, { "epoch": 0.8838883888388839, "grad_norm": 6.624067306518555, "learning_rate": 1.0175212546863243e-07, "loss": 0.3504, "step": 1473 }, { "epoch": 0.8844884488448845, "grad_norm": 4.20982027053833, "learning_rate": 1.0071845329224993e-07, "loss": 0.4754, "step": 1474 }, { "epoch": 0.8850885088508851, "grad_norm": 5.925281524658203, "learning_rate": 9.968977985865557e-08, "loss": 0.8534, "step": 1475 }, { "epoch": 0.8856885688568857, "grad_norm": 5.400402545928955, "learning_rate": 9.866611088582966e-08, "loss": 0.3796, "step": 1476 }, { "epoch": 0.8862886288628863, "grad_norm": 4.694288730621338, "learning_rate": 9.764745206393432e-08, "loss": 0.4224, "step": 1477 }, { "epoch": 0.8868886888688869, "grad_norm": 4.4553632736206055, "learning_rate": 9.663380905528229e-08, "loss": 0.6999, "step": 1478 }, { "epoch": 0.8874887488748875, "grad_norm": 3.9808223247528076, "learning_rate": 9.562518749430548e-08, "loss": 0.4174, "step": 1479 }, { "epoch": 0.888088808880888, "grad_norm": 3.739577531814575, "learning_rate": 9.46215929875237e-08, "loss": 0.2294, "step": 1480 }, { "epoch": 0.8886888688868887, "grad_norm": 5.218336582183838, "learning_rate": 9.362303111351377e-08, "loss": 0.4256, "step": 1481 }, { "epoch": 0.8892889288928892, "grad_norm": 4.914505481719971, "learning_rate": 9.26295074228769e-08, "loss": 0.4671, "step": 1482 }, { "epoch": 0.8898889888988899, "grad_norm": 4.959753513336182, "learning_rate": 9.164102743821056e-08, "loss": 0.4639, "step": 1483 }, { "epoch": 0.8904890489048904, "grad_norm": 3.5947468280792236, "learning_rate": 9.065759665407513e-08, "loss": 0.3326, "step": 1484 }, { "epoch": 0.8910891089108911, "grad_norm": 4.241577625274658, "learning_rate": 8.967922053696542e-08, "loss": 0.4249, "step": 1485 }, { "epoch": 0.8916891689168917, "grad_norm": 4.578526973724365, "learning_rate": 8.870590452527882e-08, "loss": 0.4753, "step": 1486 }, { "epoch": 0.8922892289228923, "grad_norm": 3.2933125495910645, "learning_rate": 8.773765402928557e-08, "loss": 0.2873, "step": 1487 }, { "epoch": 0.8928892889288929, "grad_norm": 4.092649459838867, "learning_rate": 8.677447443109942e-08, "loss": 0.5227, "step": 1488 }, { "epoch": 0.8934893489348935, "grad_norm": 5.201653003692627, "learning_rate": 8.581637108464635e-08, "loss": 0.5597, "step": 1489 }, { "epoch": 0.8940894089408941, "grad_norm": 3.057697296142578, "learning_rate": 8.486334931563554e-08, "loss": 0.2701, "step": 1490 }, { "epoch": 0.8946894689468947, "grad_norm": 5.421611309051514, "learning_rate": 8.39154144215305e-08, "loss": 0.6269, "step": 1491 }, { "epoch": 0.8952895289528953, "grad_norm": 3.2117867469787598, "learning_rate": 8.297257167151794e-08, "loss": 0.232, "step": 1492 }, { "epoch": 0.8958895889588959, "grad_norm": 4.475595474243164, "learning_rate": 8.203482630647973e-08, "loss": 0.4811, "step": 1493 }, { "epoch": 0.8964896489648965, "grad_norm": 4.500247955322266, "learning_rate": 8.11021835389638e-08, "loss": 0.3633, "step": 1494 }, { "epoch": 0.8970897089708971, "grad_norm": 4.608755588531494, "learning_rate": 8.017464855315437e-08, "loss": 0.4901, "step": 1495 }, { "epoch": 0.8976897689768977, "grad_norm": 6.967527389526367, "learning_rate": 7.925222650484353e-08, "loss": 0.6111, "step": 1496 }, { "epoch": 0.8982898289828983, "grad_norm": 6.523125171661377, "learning_rate": 7.833492252140283e-08, "loss": 0.7785, "step": 1497 }, { "epoch": 0.8988898889888989, "grad_norm": 5.034212589263916, "learning_rate": 7.742274170175456e-08, "loss": 0.5443, "step": 1498 }, { "epoch": 0.8994899489948995, "grad_norm": 4.8867034912109375, "learning_rate": 7.651568911634343e-08, "loss": 0.48, "step": 1499 }, { "epoch": 0.9000900090009001, "grad_norm": 3.091367721557617, "learning_rate": 7.561376980710798e-08, "loss": 0.3781, "step": 1500 }, { "epoch": 0.9006900690069007, "grad_norm": 2.6262872219085693, "learning_rate": 7.47169887874537e-08, "loss": 0.3532, "step": 1501 }, { "epoch": 0.9012901290129013, "grad_norm": 3.857114791870117, "learning_rate": 7.382535104222364e-08, "loss": 0.3663, "step": 1502 }, { "epoch": 0.9018901890189019, "grad_norm": 3.8704721927642822, "learning_rate": 7.293886152767171e-08, "loss": 0.3305, "step": 1503 }, { "epoch": 0.9024902490249025, "grad_norm": 3.6741020679473877, "learning_rate": 7.205752517143527e-08, "loss": 0.3132, "step": 1504 }, { "epoch": 0.903090309030903, "grad_norm": 4.398244857788086, "learning_rate": 7.118134687250677e-08, "loss": 0.4927, "step": 1505 }, { "epoch": 0.9036903690369037, "grad_norm": 4.483433246612549, "learning_rate": 7.03103315012078e-08, "loss": 0.4437, "step": 1506 }, { "epoch": 0.9042904290429042, "grad_norm": 4.837071895599365, "learning_rate": 6.944448389916035e-08, "loss": 0.3834, "step": 1507 }, { "epoch": 0.9048904890489049, "grad_norm": 4.649288654327393, "learning_rate": 6.858380887926163e-08, "loss": 0.3929, "step": 1508 }, { "epoch": 0.9054905490549054, "grad_norm": 5.474113464355469, "learning_rate": 6.77283112256567e-08, "loss": 0.3309, "step": 1509 }, { "epoch": 0.9060906090609061, "grad_norm": 4.137057781219482, "learning_rate": 6.687799569371078e-08, "loss": 0.2843, "step": 1510 }, { "epoch": 0.9066906690669067, "grad_norm": 4.135790824890137, "learning_rate": 6.603286700998456e-08, "loss": 0.2851, "step": 1511 }, { "epoch": 0.9072907290729073, "grad_norm": 3.6358723640441895, "learning_rate": 6.519292987220726e-08, "loss": 0.4094, "step": 1512 }, { "epoch": 0.9078907890789079, "grad_norm": 5.165234565734863, "learning_rate": 6.435818894924982e-08, "loss": 0.2142, "step": 1513 }, { "epoch": 0.9084908490849085, "grad_norm": 4.94628381729126, "learning_rate": 6.352864888109977e-08, "loss": 0.4144, "step": 1514 }, { "epoch": 0.9090909090909091, "grad_norm": 3.1370742321014404, "learning_rate": 6.270431427883504e-08, "loss": 0.3833, "step": 1515 }, { "epoch": 0.9096909690969097, "grad_norm": 5.576760292053223, "learning_rate": 6.188518972459911e-08, "loss": 0.6191, "step": 1516 }, { "epoch": 0.9102910291029103, "grad_norm": 4.2969441413879395, "learning_rate": 6.107127977157401e-08, "loss": 0.3638, "step": 1517 }, { "epoch": 0.9108910891089109, "grad_norm": 4.5167555809021, "learning_rate": 6.026258894395642e-08, "loss": 0.5094, "step": 1518 }, { "epoch": 0.9114911491149115, "grad_norm": 5.548524379730225, "learning_rate": 5.945912173693202e-08, "loss": 0.47, "step": 1519 }, { "epoch": 0.9120912091209121, "grad_norm": 6.625799179077148, "learning_rate": 5.866088261665036e-08, "loss": 0.4843, "step": 1520 }, { "epoch": 0.9126912691269127, "grad_norm": 6.937636852264404, "learning_rate": 5.786787602020005e-08, "loss": 0.6152, "step": 1521 }, { "epoch": 0.9132913291329133, "grad_norm": 2.9338955879211426, "learning_rate": 5.708010635558469e-08, "loss": 0.4404, "step": 1522 }, { "epoch": 0.9138913891389139, "grad_norm": 4.4880781173706055, "learning_rate": 5.629757800169732e-08, "loss": 0.3116, "step": 1523 }, { "epoch": 0.9144914491449145, "grad_norm": 4.443666934967041, "learning_rate": 5.552029530829705e-08, "loss": 0.6261, "step": 1524 }, { "epoch": 0.9150915091509151, "grad_norm": 3.4446194171905518, "learning_rate": 5.4748262595983975e-08, "loss": 0.3696, "step": 1525 }, { "epoch": 0.9156915691569157, "grad_norm": 4.073325157165527, "learning_rate": 5.398148415617631e-08, "loss": 0.2084, "step": 1526 }, { "epoch": 0.9162916291629163, "grad_norm": 4.1618757247924805, "learning_rate": 5.3219964251085994e-08, "loss": 0.3303, "step": 1527 }, { "epoch": 0.916891689168917, "grad_norm": 4.0959906578063965, "learning_rate": 5.246370711369375e-08, "loss": 0.5026, "step": 1528 }, { "epoch": 0.9174917491749175, "grad_norm": 6.92683744430542, "learning_rate": 5.171271694772772e-08, "loss": 0.7697, "step": 1529 }, { "epoch": 0.918091809180918, "grad_norm": 4.019528865814209, "learning_rate": 5.096699792763914e-08, "loss": 0.5629, "step": 1530 }, { "epoch": 0.9186918691869187, "grad_norm": 3.734851837158203, "learning_rate": 5.0226554198578577e-08, "loss": 0.2335, "step": 1531 }, { "epoch": 0.9192919291929192, "grad_norm": 3.5829622745513916, "learning_rate": 4.949138987637347e-08, "loss": 0.3613, "step": 1532 }, { "epoch": 0.9198919891989199, "grad_norm": 3.8929781913757324, "learning_rate": 4.8761509047505203e-08, "loss": 0.3581, "step": 1533 }, { "epoch": 0.9204920492049204, "grad_norm": 5.255183696746826, "learning_rate": 4.8036915769086525e-08, "loss": 0.2891, "step": 1534 }, { "epoch": 0.9210921092109211, "grad_norm": 2.8817174434661865, "learning_rate": 4.731761406883883e-08, "loss": 0.2078, "step": 1535 }, { "epoch": 0.9216921692169217, "grad_norm": 7.300368785858154, "learning_rate": 4.6603607945069456e-08, "loss": 0.6256, "step": 1536 }, { "epoch": 0.9222922292229223, "grad_norm": 4.044728755950928, "learning_rate": 4.589490136665008e-08, "loss": 0.3015, "step": 1537 }, { "epoch": 0.9228922892289229, "grad_norm": 4.812488079071045, "learning_rate": 4.519149827299429e-08, "loss": 0.4373, "step": 1538 }, { "epoch": 0.9234923492349235, "grad_norm": 5.188470363616943, "learning_rate": 4.449340257403544e-08, "loss": 0.5897, "step": 1539 }, { "epoch": 0.9240924092409241, "grad_norm": 4.799597263336182, "learning_rate": 4.380061815020575e-08, "loss": 0.256, "step": 1540 }, { "epoch": 0.9246924692469247, "grad_norm": 4.018554210662842, "learning_rate": 4.311314885241391e-08, "loss": 0.4077, "step": 1541 }, { "epoch": 0.9252925292529253, "grad_norm": 4.783860683441162, "learning_rate": 4.243099850202392e-08, "loss": 0.4635, "step": 1542 }, { "epoch": 0.9258925892589259, "grad_norm": 3.7923502922058105, "learning_rate": 4.1754170890833774e-08, "loss": 0.3597, "step": 1543 }, { "epoch": 0.9264926492649265, "grad_norm": 4.701802730560303, "learning_rate": 4.1082669781055124e-08, "loss": 0.4687, "step": 1544 }, { "epoch": 0.9270927092709271, "grad_norm": 6.757736682891846, "learning_rate": 4.041649890529109e-08, "loss": 0.635, "step": 1545 }, { "epoch": 0.9276927692769277, "grad_norm": 3.6303136348724365, "learning_rate": 3.975566196651625e-08, "loss": 0.3437, "step": 1546 }, { "epoch": 0.9282928292829283, "grad_norm": 4.964653015136719, "learning_rate": 3.910016263805649e-08, "loss": 0.382, "step": 1547 }, { "epoch": 0.9288928892889289, "grad_norm": 3.950655937194824, "learning_rate": 3.845000456356773e-08, "loss": 0.4229, "step": 1548 }, { "epoch": 0.9294929492949295, "grad_norm": 4.497261047363281, "learning_rate": 3.780519135701565e-08, "loss": 0.4105, "step": 1549 }, { "epoch": 0.9300930093009301, "grad_norm": 5.461933135986328, "learning_rate": 3.7165726602656824e-08, "loss": 0.678, "step": 1550 }, { "epoch": 0.9306930693069307, "grad_norm": 5.146823883056641, "learning_rate": 3.653161385501702e-08, "loss": 0.606, "step": 1551 }, { "epoch": 0.9312931293129313, "grad_norm": 4.39808988571167, "learning_rate": 3.590285663887316e-08, "loss": 0.6308, "step": 1552 }, { "epoch": 0.931893189318932, "grad_norm": 4.352895259857178, "learning_rate": 3.527945844923252e-08, "loss": 0.3871, "step": 1553 }, { "epoch": 0.9324932493249325, "grad_norm": 4.272058486938477, "learning_rate": 3.466142275131356e-08, "loss": 0.2687, "step": 1554 }, { "epoch": 0.933093309330933, "grad_norm": 4.568643093109131, "learning_rate": 3.404875298052734e-08, "loss": 0.3029, "step": 1555 }, { "epoch": 0.9336933693369337, "grad_norm": 4.953271865844727, "learning_rate": 3.3441452542457224e-08, "loss": 0.4069, "step": 1556 }, { "epoch": 0.9342934293429342, "grad_norm": 4.5194573402404785, "learning_rate": 3.2839524812841134e-08, "loss": 0.4198, "step": 1557 }, { "epoch": 0.9348934893489349, "grad_norm": 3.8629751205444336, "learning_rate": 3.2242973137552196e-08, "loss": 0.4549, "step": 1558 }, { "epoch": 0.9354935493549354, "grad_norm": 3.050008535385132, "learning_rate": 3.1651800832580236e-08, "loss": 0.3009, "step": 1559 }, { "epoch": 0.9360936093609361, "grad_norm": 3.1828811168670654, "learning_rate": 3.106601118401297e-08, "loss": 0.2586, "step": 1560 }, { "epoch": 0.9366936693669367, "grad_norm": 4.526726245880127, "learning_rate": 3.048560744801853e-08, "loss": 0.3832, "step": 1561 }, { "epoch": 0.9372937293729373, "grad_norm": 2.429684638977051, "learning_rate": 2.991059285082698e-08, "loss": 0.2939, "step": 1562 }, { "epoch": 0.9378937893789379, "grad_norm": 4.97656774520874, "learning_rate": 2.9340970588711766e-08, "loss": 0.8935, "step": 1563 }, { "epoch": 0.9384938493849385, "grad_norm": 4.889397144317627, "learning_rate": 2.8776743827973125e-08, "loss": 0.4675, "step": 1564 }, { "epoch": 0.9390939093909391, "grad_norm": 4.462288856506348, "learning_rate": 2.8217915704919716e-08, "loss": 0.3238, "step": 1565 }, { "epoch": 0.9396939693969397, "grad_norm": 4.562056064605713, "learning_rate": 2.7664489325851192e-08, "loss": 0.3276, "step": 1566 }, { "epoch": 0.9402940294029403, "grad_norm": 4.4579691886901855, "learning_rate": 2.711646776704113e-08, "loss": 0.4423, "step": 1567 }, { "epoch": 0.9408940894089409, "grad_norm": 5.3042893409729, "learning_rate": 2.6573854074720237e-08, "loss": 0.4889, "step": 1568 }, { "epoch": 0.9414941494149415, "grad_norm": 3.9374210834503174, "learning_rate": 2.6036651265058494e-08, "loss": 0.4845, "step": 1569 }, { "epoch": 0.9420942094209421, "grad_norm": 5.349104404449463, "learning_rate": 2.55048623241495e-08, "loss": 0.4127, "step": 1570 }, { "epoch": 0.9426942694269427, "grad_norm": 5.877910614013672, "learning_rate": 2.497849020799281e-08, "loss": 0.3568, "step": 1571 }, { "epoch": 0.9432943294329433, "grad_norm": 4.195255279541016, "learning_rate": 2.4457537842478614e-08, "loss": 0.3099, "step": 1572 }, { "epoch": 0.9438943894389439, "grad_norm": 4.164703369140625, "learning_rate": 2.3942008123370772e-08, "loss": 0.3133, "step": 1573 }, { "epoch": 0.9444944494449445, "grad_norm": 4.730490684509277, "learning_rate": 2.343190391629035e-08, "loss": 0.3542, "step": 1574 }, { "epoch": 0.9450945094509451, "grad_norm": 2.6755969524383545, "learning_rate": 2.2927228056700777e-08, "loss": 0.1825, "step": 1575 }, { "epoch": 0.9456945694569457, "grad_norm": 4.409481525421143, "learning_rate": 2.2427983349891267e-08, "loss": 0.2994, "step": 1576 }, { "epoch": 0.9462946294629463, "grad_norm": 3.6513874530792236, "learning_rate": 2.1934172570961194e-08, "loss": 0.2525, "step": 1577 }, { "epoch": 0.946894689468947, "grad_norm": 6.896881580352783, "learning_rate": 2.1445798464805433e-08, "loss": 0.7197, "step": 1578 }, { "epoch": 0.9474947494749475, "grad_norm": 4.853761672973633, "learning_rate": 2.0962863746098235e-08, "loss": 0.3567, "step": 1579 }, { "epoch": 0.948094809480948, "grad_norm": 4.733894348144531, "learning_rate": 2.0485371099278502e-08, "loss": 0.5826, "step": 1580 }, { "epoch": 0.9486948694869487, "grad_norm": 3.0943777561187744, "learning_rate": 2.0013323178535102e-08, "loss": 0.1729, "step": 1581 }, { "epoch": 0.9492949294929492, "grad_norm": 4.286136627197266, "learning_rate": 1.9546722607791556e-08, "loss": 0.4999, "step": 1582 }, { "epoch": 0.9498949894989499, "grad_norm": 4.240255832672119, "learning_rate": 1.908557198069205e-08, "loss": 0.2772, "step": 1583 }, { "epoch": 0.9504950495049505, "grad_norm": 4.511148929595947, "learning_rate": 1.8629873860586564e-08, "loss": 0.4508, "step": 1584 }, { "epoch": 0.9510951095109511, "grad_norm": 5.663780689239502, "learning_rate": 1.8179630780516763e-08, "loss": 0.6586, "step": 1585 }, { "epoch": 0.9516951695169517, "grad_norm": 3.9681880474090576, "learning_rate": 1.7734845243202125e-08, "loss": 0.3237, "step": 1586 }, { "epoch": 0.9522952295229523, "grad_norm": 4.078896999359131, "learning_rate": 1.729551972102561e-08, "loss": 0.4274, "step": 1587 }, { "epoch": 0.9528952895289529, "grad_norm": 4.921993732452393, "learning_rate": 1.686165665602046e-08, "loss": 0.4688, "step": 1588 }, { "epoch": 0.9534953495349535, "grad_norm": 5.484593868255615, "learning_rate": 1.6433258459855992e-08, "loss": 0.6134, "step": 1589 }, { "epoch": 0.9540954095409541, "grad_norm": 3.8161003589630127, "learning_rate": 1.6010327513824917e-08, "loss": 0.338, "step": 1590 }, { "epoch": 0.9546954695469547, "grad_norm": 3.502756357192993, "learning_rate": 1.5592866168829376e-08, "loss": 0.242, "step": 1591 }, { "epoch": 0.9552955295529553, "grad_norm": 4.8645734786987305, "learning_rate": 1.5180876745368164e-08, "loss": 0.7262, "step": 1592 }, { "epoch": 0.9558955895589559, "grad_norm": 3.940401554107666, "learning_rate": 1.4774361533524183e-08, "loss": 0.2907, "step": 1593 }, { "epoch": 0.9564956495649565, "grad_norm": 3.2006027698516846, "learning_rate": 1.4373322792951448e-08, "loss": 0.3359, "step": 1594 }, { "epoch": 0.9570957095709571, "grad_norm": 3.9759905338287354, "learning_rate": 1.3977762752861889e-08, "loss": 0.3422, "step": 1595 }, { "epoch": 0.9576957695769577, "grad_norm": 5.010193347930908, "learning_rate": 1.3587683612014233e-08, "loss": 0.5637, "step": 1596 }, { "epoch": 0.9582958295829583, "grad_norm": 4.535565376281738, "learning_rate": 1.3203087538700696e-08, "loss": 0.4448, "step": 1597 }, { "epoch": 0.9588958895889589, "grad_norm": 2.576176166534424, "learning_rate": 1.2823976670735537e-08, "loss": 0.3512, "step": 1598 }, { "epoch": 0.9594959495949595, "grad_norm": 6.533446788787842, "learning_rate": 1.2450353115442958e-08, "loss": 0.8636, "step": 1599 }, { "epoch": 0.9600960096009601, "grad_norm": 4.357980728149414, "learning_rate": 1.2082218949645229e-08, "loss": 0.4587, "step": 1600 }, { "epoch": 0.9606960696069607, "grad_norm": 5.643572807312012, "learning_rate": 1.1719576219651584e-08, "loss": 0.6645, "step": 1601 }, { "epoch": 0.9612961296129613, "grad_norm": 7.259177207946777, "learning_rate": 1.1362426941246117e-08, "loss": 0.519, "step": 1602 }, { "epoch": 0.961896189618962, "grad_norm": 4.989030838012695, "learning_rate": 1.1010773099677683e-08, "loss": 0.4336, "step": 1603 }, { "epoch": 0.9624962496249625, "grad_norm": 6.617142677307129, "learning_rate": 1.0664616649647907e-08, "loss": 0.4481, "step": 1604 }, { "epoch": 0.963096309630963, "grad_norm": 6.936275482177734, "learning_rate": 1.0323959515300518e-08, "loss": 1.0002, "step": 1605 }, { "epoch": 0.9636963696369637, "grad_norm": 4.355704307556152, "learning_rate": 9.988803590211037e-09, "loss": 0.3137, "step": 1606 }, { "epoch": 0.9642964296429642, "grad_norm": 3.5749144554138184, "learning_rate": 9.659150737375555e-09, "loss": 0.2128, "step": 1607 }, { "epoch": 0.9648964896489649, "grad_norm": 3.590890407562256, "learning_rate": 9.335002789201407e-09, "loss": 0.3655, "step": 1608 }, { "epoch": 0.9654965496549655, "grad_norm": 2.661102771759033, "learning_rate": 9.016361547495965e-09, "loss": 0.326, "step": 1609 }, { "epoch": 0.9660966096609661, "grad_norm": 4.265824317932129, "learning_rate": 8.703228783456972e-09, "loss": 0.4493, "step": 1610 }, { "epoch": 0.9666966696669667, "grad_norm": 5.136455535888672, "learning_rate": 8.395606237663222e-09, "loss": 0.9684, "step": 1611 }, { "epoch": 0.9672967296729673, "grad_norm": 4.449375152587891, "learning_rate": 8.093495620064117e-09, "loss": 0.4172, "step": 1612 }, { "epoch": 0.9678967896789679, "grad_norm": 3.9327852725982666, "learning_rate": 7.796898609970348e-09, "loss": 0.3123, "step": 1613 }, { "epoch": 0.9684968496849685, "grad_norm": 4.850330352783203, "learning_rate": 7.505816856045011e-09, "loss": 0.4894, "step": 1614 }, { "epoch": 0.9690969096909691, "grad_norm": 5.01401948928833, "learning_rate": 7.220251976293945e-09, "loss": 0.5805, "step": 1615 }, { "epoch": 0.9696969696969697, "grad_norm": 6.547853946685791, "learning_rate": 6.9402055580568556e-09, "loss": 0.5369, "step": 1616 }, { "epoch": 0.9702970297029703, "grad_norm": 4.495151042938232, "learning_rate": 6.665679157998761e-09, "loss": 0.3822, "step": 1617 }, { "epoch": 0.9708970897089709, "grad_norm": 7.344977855682373, "learning_rate": 6.39667430210089e-09, "loss": 0.7268, "step": 1618 }, { "epoch": 0.9714971497149715, "grad_norm": 4.495357036590576, "learning_rate": 6.133192485652694e-09, "loss": 0.3375, "step": 1619 }, { "epoch": 0.9720972097209721, "grad_norm": 5.739585876464844, "learning_rate": 5.875235173243065e-09, "loss": 0.3563, "step": 1620 }, { "epoch": 0.9726972697269727, "grad_norm": 4.027656078338623, "learning_rate": 5.622803798752462e-09, "loss": 0.4276, "step": 1621 }, { "epoch": 0.9732973297329733, "grad_norm": 3.379265546798706, "learning_rate": 5.375899765344916e-09, "loss": 0.3336, "step": 1622 }, { "epoch": 0.9738973897389739, "grad_norm": 4.506401062011719, "learning_rate": 5.134524445460142e-09, "loss": 0.5015, "step": 1623 }, { "epoch": 0.9744974497449745, "grad_norm": 4.523036479949951, "learning_rate": 4.898679180806109e-09, "loss": 0.4069, "step": 1624 }, { "epoch": 0.9750975097509751, "grad_norm": 4.931277275085449, "learning_rate": 4.668365282351372e-09, "loss": 0.3418, "step": 1625 }, { "epoch": 0.9756975697569757, "grad_norm": 3.4074110984802246, "learning_rate": 4.443584030317748e-09, "loss": 0.4482, "step": 1626 }, { "epoch": 0.9762976297629763, "grad_norm": 4.963759422302246, "learning_rate": 4.224336674173545e-09, "loss": 0.3457, "step": 1627 }, { "epoch": 0.976897689768977, "grad_norm": 4.367631435394287, "learning_rate": 4.010624432626009e-09, "loss": 0.2755, "step": 1628 }, { "epoch": 0.9774977497749775, "grad_norm": 4.613311767578125, "learning_rate": 3.802448493615329e-09, "loss": 0.5081, "step": 1629 }, { "epoch": 0.978097809780978, "grad_norm": 7.097207069396973, "learning_rate": 3.5998100143074252e-09, "loss": 0.7856, "step": 1630 }, { "epoch": 0.9786978697869787, "grad_norm": 4.190742015838623, "learning_rate": 3.4027101210876154e-09, "loss": 0.6419, "step": 1631 }, { "epoch": 0.9792979297929792, "grad_norm": 5.420130252838135, "learning_rate": 3.2111499095547335e-09, "loss": 0.4621, "step": 1632 }, { "epoch": 0.9798979897989799, "grad_norm": 6.869644641876221, "learning_rate": 3.025130444514468e-09, "loss": 0.492, "step": 1633 }, { "epoch": 0.9804980498049805, "grad_norm": 3.277240514755249, "learning_rate": 2.8446527599739202e-09, "loss": 0.1594, "step": 1634 }, { "epoch": 0.9810981098109811, "grad_norm": 3.3887369632720947, "learning_rate": 2.669717859135723e-09, "loss": 0.2655, "step": 1635 }, { "epoch": 0.9816981698169817, "grad_norm": 4.074149131774902, "learning_rate": 2.5003267143921535e-09, "loss": 0.4571, "step": 1636 }, { "epoch": 0.9822982298229823, "grad_norm": 4.082927227020264, "learning_rate": 2.33648026732014e-09, "loss": 0.4292, "step": 1637 }, { "epoch": 0.9828982898289829, "grad_norm": 4.072002410888672, "learning_rate": 2.1781794286760414e-09, "loss": 0.3152, "step": 1638 }, { "epoch": 0.9834983498349835, "grad_norm": 3.3978285789489746, "learning_rate": 2.0254250783900974e-09, "loss": 0.469, "step": 1639 }, { "epoch": 0.9840984098409841, "grad_norm": 3.390193462371826, "learning_rate": 1.878218065562209e-09, "loss": 0.2863, "step": 1640 }, { "epoch": 0.9846984698469847, "grad_norm": 3.9765031337738037, "learning_rate": 1.7365592084565007e-09, "loss": 0.3653, "step": 1641 }, { "epoch": 0.9852985298529853, "grad_norm": 4.392426490783691, "learning_rate": 1.600449294497319e-09, "loss": 0.3526, "step": 1642 }, { "epoch": 0.9858985898589859, "grad_norm": 4.507305145263672, "learning_rate": 1.4698890802649077e-09, "loss": 0.5361, "step": 1643 }, { "epoch": 0.9864986498649865, "grad_norm": 4.619936943054199, "learning_rate": 1.3448792914905194e-09, "loss": 0.3671, "step": 1644 }, { "epoch": 0.9870987098709871, "grad_norm": 3.000737190246582, "learning_rate": 1.2254206230531972e-09, "loss": 0.2383, "step": 1645 }, { "epoch": 0.9876987698769877, "grad_norm": 7.061428070068359, "learning_rate": 1.1115137389754447e-09, "loss": 0.5765, "step": 1646 }, { "epoch": 0.9882988298829883, "grad_norm": 3.0841450691223145, "learning_rate": 1.0031592724194515e-09, "loss": 0.2493, "step": 1647 }, { "epoch": 0.9888988898889889, "grad_norm": 4.9119648933410645, "learning_rate": 9.003578256839839e-10, "loss": 0.5454, "step": 1648 }, { "epoch": 0.9894989498949895, "grad_norm": 4.197965621948242, "learning_rate": 8.031099702008326e-10, "loss": 0.5456, "step": 1649 }, { "epoch": 0.9900990099009901, "grad_norm": 3.653165817260742, "learning_rate": 7.114162465313711e-10, "loss": 0.3262, "step": 1650 }, { "epoch": 0.9906990699069907, "grad_norm": 5.752342700958252, "learning_rate": 6.25277164364113e-10, "loss": 0.6837, "step": 1651 }, { "epoch": 0.9912991299129913, "grad_norm": 3.329667806625366, "learning_rate": 5.446932025114925e-10, "loss": 0.2447, "step": 1652 }, { "epoch": 0.991899189918992, "grad_norm": 5.033096790313721, "learning_rate": 4.696648089068667e-10, "loss": 0.5276, "step": 1653 }, { "epoch": 0.9924992499249925, "grad_norm": 4.353885173797607, "learning_rate": 4.0019240060307214e-10, "loss": 0.3611, "step": 1654 }, { "epoch": 0.993099309930993, "grad_norm": 6.065013885498047, "learning_rate": 3.3627636376909465e-10, "loss": 0.3281, "step": 1655 }, { "epoch": 0.9936993699369937, "grad_norm": 4.70760440826416, "learning_rate": 2.779170536881814e-10, "loss": 0.4517, "step": 1656 }, { "epoch": 0.9942994299429943, "grad_norm": 4.7580766677856445, "learning_rate": 2.2511479475639804e-10, "loss": 0.6154, "step": 1657 }, { "epoch": 0.9948994899489949, "grad_norm": 3.8567116260528564, "learning_rate": 1.778698804800749e-10, "loss": 0.2673, "step": 1658 }, { "epoch": 0.9954995499549955, "grad_norm": 3.4135818481445312, "learning_rate": 1.3618257347447483e-10, "loss": 0.2842, "step": 1659 }, { "epoch": 0.9960996099609961, "grad_norm": 5.19088077545166, "learning_rate": 1.0005310546268298e-10, "loss": 0.3891, "step": 1660 }, { "epoch": 0.9966996699669967, "grad_norm": 6.608803749084473, "learning_rate": 6.948167727383047e-11, "loss": 0.718, "step": 1661 }, { "epoch": 0.9972997299729973, "grad_norm": 5.505403995513916, "learning_rate": 4.4468458841873115e-11, "loss": 0.4548, "step": 1662 }, { "epoch": 0.9978997899789979, "grad_norm": 3.555994987487793, "learning_rate": 2.5013589205480356e-11, "loss": 0.2924, "step": 1663 }, { "epoch": 0.9984998499849985, "grad_norm": 3.748823881149292, "learning_rate": 1.1117176506258985e-11, "loss": 0.2349, "step": 1664 }, { "epoch": 0.9990999099909991, "grad_norm": 4.713783264160156, "learning_rate": 2.7792979888641155e-12, "loss": 0.3052, "step": 1665 }, { "epoch": 0.9996999699969997, "grad_norm": 5.391319751739502, "learning_rate": 0.0, "loss": 0.2418, "step": 1666 }, { "epoch": 1.0003000300030003, "grad_norm": 1.7804044485092163, "learning_rate": 2.7792979888641155e-12, "loss": 0.3762, "step": 1667 }, { "epoch": 1.0009000900090008, "grad_norm": 3.7211201190948486, "learning_rate": 1.1117176506258985e-11, "loss": 0.5992, "step": 1668 }, { "epoch": 1.0015001500150016, "grad_norm": 2.102475881576538, "learning_rate": 2.5013589205480356e-11, "loss": 0.345, "step": 1669 }, { "epoch": 1.0021002100210021, "grad_norm": 2.5850071907043457, "learning_rate": 4.4468458841873115e-11, "loss": 0.5067, "step": 1670 }, { "epoch": 1.0027002700270027, "grad_norm": 3.4971611499786377, "learning_rate": 6.948167727383047e-11, "loss": 0.3881, "step": 1671 }, { "epoch": 1.0033003300330032, "grad_norm": 2.6511337757110596, "learning_rate": 1.0005310546268298e-10, "loss": 0.2988, "step": 1672 }, { "epoch": 1.003900390039004, "grad_norm": 1.532371997833252, "learning_rate": 1.3618257347447483e-10, "loss": 0.4777, "step": 1673 }, { "epoch": 1.0045004500450045, "grad_norm": 1.4274760484695435, "learning_rate": 1.778698804800749e-10, "loss": 0.2523, "step": 1674 }, { "epoch": 1.005100510051005, "grad_norm": 2.986931085586548, "learning_rate": 2.2511479475639804e-10, "loss": 0.2736, "step": 1675 }, { "epoch": 1.0057005700570056, "grad_norm": 2.6657845973968506, "learning_rate": 2.779170536881814e-10, "loss": 0.4912, "step": 1676 }, { "epoch": 1.0063006300630064, "grad_norm": 2.970472574234009, "learning_rate": 3.3627636376909465e-10, "loss": 0.2239, "step": 1677 }, { "epoch": 1.006900690069007, "grad_norm": 1.3853145837783813, "learning_rate": 4.0019240060307214e-10, "loss": 0.2485, "step": 1678 }, { "epoch": 1.0075007500750075, "grad_norm": 1.6184730529785156, "learning_rate": 4.696648089068667e-10, "loss": 0.4748, "step": 1679 }, { "epoch": 1.008100810081008, "grad_norm": 0.8617638945579529, "learning_rate": 5.446932025113815e-10, "loss": 0.5123, "step": 1680 }, { "epoch": 1.0087008700870086, "grad_norm": 2.9806065559387207, "learning_rate": 6.25277164364224e-10, "loss": 0.3516, "step": 1681 }, { "epoch": 1.0093009300930094, "grad_norm": 2.7340404987335205, "learning_rate": 7.114162465313711e-10, "loss": 0.3077, "step": 1682 }, { "epoch": 1.00990099009901, "grad_norm": 3.1809165477752686, "learning_rate": 8.031099702008326e-10, "loss": 0.3597, "step": 1683 }, { "epoch": 1.0105010501050105, "grad_norm": 1.2650384902954102, "learning_rate": 9.003578256839839e-10, "loss": 0.2905, "step": 1684 }, { "epoch": 1.011101110111011, "grad_norm": 2.1629083156585693, "learning_rate": 1.0031592724194515e-09, "loss": 0.5353, "step": 1685 }, { "epoch": 1.0117011701170118, "grad_norm": 2.5108299255371094, "learning_rate": 1.1115137389754447e-09, "loss": 0.4745, "step": 1686 }, { "epoch": 1.0123012301230123, "grad_norm": 1.9002095460891724, "learning_rate": 1.2254206230531972e-09, "loss": 0.2251, "step": 1687 }, { "epoch": 1.0129012901290129, "grad_norm": 2.57342529296875, "learning_rate": 1.3448792914905194e-09, "loss": 0.3496, "step": 1688 }, { "epoch": 1.0135013501350134, "grad_norm": 2.8935482501983643, "learning_rate": 1.4698890802649077e-09, "loss": 0.3208, "step": 1689 }, { "epoch": 1.0141014101410142, "grad_norm": 1.2411342859268188, "learning_rate": 1.600449294497319e-09, "loss": 0.3345, "step": 1690 }, { "epoch": 1.0147014701470147, "grad_norm": 2.97009015083313, "learning_rate": 1.7365592084565007e-09, "loss": 0.4126, "step": 1691 }, { "epoch": 1.0153015301530153, "grad_norm": 2.5400657653808594, "learning_rate": 1.8782180655620983e-09, "loss": 0.3616, "step": 1692 }, { "epoch": 1.0159015901590158, "grad_norm": 1.735724925994873, "learning_rate": 2.0254250783900974e-09, "loss": 0.4184, "step": 1693 }, { "epoch": 1.0165016501650166, "grad_norm": 2.0357658863067627, "learning_rate": 2.1781794286760414e-09, "loss": 0.3389, "step": 1694 }, { "epoch": 1.0171017101710171, "grad_norm": 1.8855786323547363, "learning_rate": 2.33648026732014e-09, "loss": 0.2987, "step": 1695 }, { "epoch": 1.0177017701770177, "grad_norm": 2.3233208656311035, "learning_rate": 2.5003267143920427e-09, "loss": 0.2547, "step": 1696 }, { "epoch": 1.0183018301830182, "grad_norm": 2.6293728351593018, "learning_rate": 2.6697178591356117e-09, "loss": 0.3374, "step": 1697 }, { "epoch": 1.018901890189019, "grad_norm": 2.3369927406311035, "learning_rate": 2.8446527599739202e-09, "loss": 1.0968, "step": 1698 }, { "epoch": 1.0195019501950195, "grad_norm": 2.8855113983154297, "learning_rate": 3.025130444514468e-09, "loss": 0.4669, "step": 1699 }, { "epoch": 1.02010201020102, "grad_norm": 2.401718854904175, "learning_rate": 3.2111499095547335e-09, "loss": 0.3156, "step": 1700 }, { "epoch": 1.021002100210021, "grad_norm": 4.002414703369141, "learning_rate": 3.4027101210876154e-09, "loss": 0.4909, "step": 1701 }, { "epoch": 1.0216021602160217, "grad_norm": 2.718543291091919, "learning_rate": 3.5998100143074252e-09, "loss": 0.2055, "step": 1702 }, { "epoch": 1.0222022202220222, "grad_norm": 5.036877632141113, "learning_rate": 3.802448493615329e-09, "loss": 0.56, "step": 1703 }, { "epoch": 1.0228022802280228, "grad_norm": 4.422957897186279, "learning_rate": 4.010624432626009e-09, "loss": 0.489, "step": 1704 }, { "epoch": 1.0234023402340233, "grad_norm": 6.388888359069824, "learning_rate": 4.224336674173545e-09, "loss": 0.7745, "step": 1705 }, { "epoch": 1.024002400240024, "grad_norm": 2.9437978267669678, "learning_rate": 4.443584030317748e-09, "loss": 0.21, "step": 1706 }, { "epoch": 1.0246024602460246, "grad_norm": 3.976762056350708, "learning_rate": 4.668365282351372e-09, "loss": 0.4899, "step": 1707 }, { "epoch": 1.0252025202520252, "grad_norm": 4.595272064208984, "learning_rate": 4.898679180806109e-09, "loss": 0.3368, "step": 1708 }, { "epoch": 1.0258025802580257, "grad_norm": 4.292851448059082, "learning_rate": 5.134524445460142e-09, "loss": 0.3016, "step": 1709 }, { "epoch": 1.0264026402640265, "grad_norm": 6.297183036804199, "learning_rate": 5.375899765344805e-09, "loss": 0.6132, "step": 1710 }, { "epoch": 1.027002700270027, "grad_norm": 2.7593820095062256, "learning_rate": 5.622803798752462e-09, "loss": 0.2143, "step": 1711 }, { "epoch": 1.0276027602760276, "grad_norm": 3.7385854721069336, "learning_rate": 5.875235173243065e-09, "loss": 0.3017, "step": 1712 }, { "epoch": 1.0282028202820281, "grad_norm": 4.392091274261475, "learning_rate": 6.133192485652694e-09, "loss": 0.8275, "step": 1713 }, { "epoch": 1.028802880288029, "grad_norm": 3.361018419265747, "learning_rate": 6.39667430210089e-09, "loss": 0.2219, "step": 1714 }, { "epoch": 1.0294029402940295, "grad_norm": 4.098636627197266, "learning_rate": 6.665679157998761e-09, "loss": 0.478, "step": 1715 }, { "epoch": 1.03000300030003, "grad_norm": 5.977883815765381, "learning_rate": 6.9402055580568556e-09, "loss": 0.5068, "step": 1716 }, { "epoch": 1.0306030603060305, "grad_norm": 3.955613136291504, "learning_rate": 7.220251976293834e-09, "loss": 0.4614, "step": 1717 }, { "epoch": 1.031203120312031, "grad_norm": 4.181906700134277, "learning_rate": 7.5058168560449e-09, "loss": 0.3847, "step": 1718 }, { "epoch": 1.0318031803180319, "grad_norm": 4.072266101837158, "learning_rate": 7.796898609970237e-09, "loss": 0.4075, "step": 1719 }, { "epoch": 1.0324032403240324, "grad_norm": 5.460573196411133, "learning_rate": 8.093495620064006e-09, "loss": 0.324, "step": 1720 }, { "epoch": 1.033003300330033, "grad_norm": 4.7909159660339355, "learning_rate": 8.395606237663222e-09, "loss": 0.2252, "step": 1721 }, { "epoch": 1.0336033603360335, "grad_norm": 3.6374239921569824, "learning_rate": 8.703228783456972e-09, "loss": 0.2921, "step": 1722 }, { "epoch": 1.0342034203420343, "grad_norm": 3.3665709495544434, "learning_rate": 9.016361547495854e-09, "loss": 0.5194, "step": 1723 }, { "epoch": 1.0348034803480348, "grad_norm": 5.361471176147461, "learning_rate": 9.335002789201407e-09, "loss": 0.3857, "step": 1724 }, { "epoch": 1.0354035403540354, "grad_norm": 3.3163976669311523, "learning_rate": 9.659150737375555e-09, "loss": 0.2559, "step": 1725 }, { "epoch": 1.036003600360036, "grad_norm": 4.326786041259766, "learning_rate": 9.988803590210926e-09, "loss": 0.3563, "step": 1726 }, { "epoch": 1.0366036603660367, "grad_norm": 4.650569438934326, "learning_rate": 1.0323959515300628e-08, "loss": 0.4656, "step": 1727 }, { "epoch": 1.0372037203720372, "grad_norm": 4.480536937713623, "learning_rate": 1.0664616649647907e-08, "loss": 0.3222, "step": 1728 }, { "epoch": 1.0378037803780378, "grad_norm": 6.078989028930664, "learning_rate": 1.1010773099677683e-08, "loss": 0.3538, "step": 1729 }, { "epoch": 1.0384038403840383, "grad_norm": 3.5233311653137207, "learning_rate": 1.1362426941246228e-08, "loss": 0.3423, "step": 1730 }, { "epoch": 1.039003900390039, "grad_norm": 4.9120612144470215, "learning_rate": 1.1719576219651473e-08, "loss": 0.2678, "step": 1731 }, { "epoch": 1.0396039603960396, "grad_norm": 4.01106595993042, "learning_rate": 1.2082218949645118e-08, "loss": 0.2641, "step": 1732 }, { "epoch": 1.0402040204020402, "grad_norm": 4.258695125579834, "learning_rate": 1.2450353115442847e-08, "loss": 0.2758, "step": 1733 }, { "epoch": 1.0408040804080407, "grad_norm": 3.5772664546966553, "learning_rate": 1.2823976670735647e-08, "loss": 0.4364, "step": 1734 }, { "epoch": 1.0414041404140415, "grad_norm": 5.136354446411133, "learning_rate": 1.3203087538700696e-08, "loss": 0.7171, "step": 1735 }, { "epoch": 1.042004200420042, "grad_norm": 4.991485595703125, "learning_rate": 1.3587683612014122e-08, "loss": 0.4412, "step": 1736 }, { "epoch": 1.0426042604260426, "grad_norm": 4.147801399230957, "learning_rate": 1.3977762752861889e-08, "loss": 0.3374, "step": 1737 }, { "epoch": 1.0432043204320431, "grad_norm": 6.087820529937744, "learning_rate": 1.4373322792951337e-08, "loss": 0.4464, "step": 1738 }, { "epoch": 1.043804380438044, "grad_norm": 4.802339553833008, "learning_rate": 1.4774361533524183e-08, "loss": 0.5104, "step": 1739 }, { "epoch": 1.0444044404440445, "grad_norm": 5.3612284660339355, "learning_rate": 1.5180876745368164e-08, "loss": 0.4198, "step": 1740 }, { "epoch": 1.045004500450045, "grad_norm": 4.923361778259277, "learning_rate": 1.5592866168829267e-08, "loss": 0.4375, "step": 1741 }, { "epoch": 1.0456045604560456, "grad_norm": 3.3030481338500977, "learning_rate": 1.6010327513824917e-08, "loss": 0.4599, "step": 1742 }, { "epoch": 1.046204620462046, "grad_norm": 3.4992899894714355, "learning_rate": 1.643325845985588e-08, "loss": 0.4355, "step": 1743 }, { "epoch": 1.0468046804680469, "grad_norm": 3.7810275554656982, "learning_rate": 1.686165665602046e-08, "loss": 0.3204, "step": 1744 }, { "epoch": 1.0474047404740474, "grad_norm": 5.9495344161987305, "learning_rate": 1.729551972102561e-08, "loss": 0.3225, "step": 1745 }, { "epoch": 1.048004800480048, "grad_norm": 5.515197277069092, "learning_rate": 1.7734845243202012e-08, "loss": 0.4924, "step": 1746 }, { "epoch": 1.0486048604860485, "grad_norm": 3.2263545989990234, "learning_rate": 1.8179630780516763e-08, "loss": 0.2861, "step": 1747 }, { "epoch": 1.0492049204920493, "grad_norm": 4.345129013061523, "learning_rate": 1.8629873860586564e-08, "loss": 0.3698, "step": 1748 }, { "epoch": 1.0498049804980498, "grad_norm": 6.259242057800293, "learning_rate": 1.908557198069205e-08, "loss": 0.8554, "step": 1749 }, { "epoch": 1.0504050405040504, "grad_norm": 3.933579921722412, "learning_rate": 1.9546722607791665e-08, "loss": 0.4287, "step": 1750 }, { "epoch": 1.051005100510051, "grad_norm": 5.408218860626221, "learning_rate": 2.0013323178535102e-08, "loss": 0.402, "step": 1751 }, { "epoch": 1.0516051605160517, "grad_norm": 5.1222357749938965, "learning_rate": 2.0485371099278502e-08, "loss": 0.7938, "step": 1752 }, { "epoch": 1.0522052205220522, "grad_norm": 6.204251289367676, "learning_rate": 2.0962863746098235e-08, "loss": 0.582, "step": 1753 }, { "epoch": 1.0528052805280528, "grad_norm": 3.601553201675415, "learning_rate": 2.1445798464805433e-08, "loss": 0.3878, "step": 1754 }, { "epoch": 1.0534053405340533, "grad_norm": 4.064268589019775, "learning_rate": 2.1934172570961194e-08, "loss": 0.4345, "step": 1755 }, { "epoch": 1.054005400540054, "grad_norm": 3.256706953048706, "learning_rate": 2.2427983349891154e-08, "loss": 0.3476, "step": 1756 }, { "epoch": 1.0546054605460546, "grad_norm": 6.95648193359375, "learning_rate": 2.2927228056700777e-08, "loss": 0.6258, "step": 1757 }, { "epoch": 1.0552055205520552, "grad_norm": 5.5816264152526855, "learning_rate": 2.343190391629035e-08, "loss": 0.6458, "step": 1758 }, { "epoch": 1.0558055805580557, "grad_norm": 3.717827081680298, "learning_rate": 2.394200812337066e-08, "loss": 0.2787, "step": 1759 }, { "epoch": 1.0564056405640565, "grad_norm": 3.800326108932495, "learning_rate": 2.4457537842478727e-08, "loss": 0.3064, "step": 1760 }, { "epoch": 1.057005700570057, "grad_norm": 4.941473960876465, "learning_rate": 2.497849020799281e-08, "loss": 0.3772, "step": 1761 }, { "epoch": 1.0576057605760576, "grad_norm": 4.953122615814209, "learning_rate": 2.550486232414928e-08, "loss": 0.6908, "step": 1762 }, { "epoch": 1.0582058205820581, "grad_norm": 3.9984705448150635, "learning_rate": 2.6036651265058494e-08, "loss": 0.3012, "step": 1763 }, { "epoch": 1.058805880588059, "grad_norm": 3.6176323890686035, "learning_rate": 2.6573854074720125e-08, "loss": 0.4312, "step": 1764 }, { "epoch": 1.0594059405940595, "grad_norm": 3.247000217437744, "learning_rate": 2.711646776704113e-08, "loss": 0.3046, "step": 1765 }, { "epoch": 1.06000600060006, "grad_norm": 3.769834280014038, "learning_rate": 2.7664489325851082e-08, "loss": 0.3584, "step": 1766 }, { "epoch": 1.0606060606060606, "grad_norm": 5.199070930480957, "learning_rate": 2.8217915704919716e-08, "loss": 0.3403, "step": 1767 }, { "epoch": 1.061206120612061, "grad_norm": 5.137094974517822, "learning_rate": 2.8776743827973125e-08, "loss": 0.6294, "step": 1768 }, { "epoch": 1.0618061806180619, "grad_norm": 3.776904821395874, "learning_rate": 2.9340970588711656e-08, "loss": 0.2937, "step": 1769 }, { "epoch": 1.0624062406240624, "grad_norm": 2.71752667427063, "learning_rate": 2.9910592850826865e-08, "loss": 0.1841, "step": 1770 }, { "epoch": 1.063006300630063, "grad_norm": 5.682762622833252, "learning_rate": 3.048560744801853e-08, "loss": 0.4303, "step": 1771 }, { "epoch": 1.0636063606360635, "grad_norm": 3.8252651691436768, "learning_rate": 3.106601118401286e-08, "loss": 0.4055, "step": 1772 }, { "epoch": 1.0642064206420643, "grad_norm": 4.149570941925049, "learning_rate": 3.1651800832580236e-08, "loss": 0.2641, "step": 1773 }, { "epoch": 1.0648064806480648, "grad_norm": 5.3055195808410645, "learning_rate": 3.2242973137552196e-08, "loss": 0.4562, "step": 1774 }, { "epoch": 1.0654065406540654, "grad_norm": 5.844550609588623, "learning_rate": 3.283952481284102e-08, "loss": 0.3441, "step": 1775 }, { "epoch": 1.066006600660066, "grad_norm": 4.031011581420898, "learning_rate": 3.3441452542457224e-08, "loss": 0.3093, "step": 1776 }, { "epoch": 1.0666066606660667, "grad_norm": 4.74403715133667, "learning_rate": 3.404875298052723e-08, "loss": 0.3482, "step": 1777 }, { "epoch": 1.0672067206720672, "grad_norm": 3.068814992904663, "learning_rate": 3.466142275131345e-08, "loss": 0.2224, "step": 1778 }, { "epoch": 1.0678067806780678, "grad_norm": 5.3198370933532715, "learning_rate": 3.52794584492323e-08, "loss": 0.4892, "step": 1779 }, { "epoch": 1.0684068406840683, "grad_norm": 3.180372714996338, "learning_rate": 3.590285663887327e-08, "loss": 0.3139, "step": 1780 }, { "epoch": 1.069006900690069, "grad_norm": 4.1368937492370605, "learning_rate": 3.653161385501702e-08, "loss": 0.3179, "step": 1781 }, { "epoch": 1.0696069606960696, "grad_norm": 3.813469648361206, "learning_rate": 3.71657266026566e-08, "loss": 0.3102, "step": 1782 }, { "epoch": 1.0702070207020702, "grad_norm": 3.5391225814819336, "learning_rate": 3.780519135701576e-08, "loss": 0.5943, "step": 1783 }, { "epoch": 1.0708070807080707, "grad_norm": 4.213769912719727, "learning_rate": 3.845000456356762e-08, "loss": 0.3472, "step": 1784 }, { "epoch": 1.0714071407140715, "grad_norm": 4.076124668121338, "learning_rate": 3.910016263805638e-08, "loss": 0.3383, "step": 1785 }, { "epoch": 1.072007200720072, "grad_norm": 3.52677321434021, "learning_rate": 3.975566196651625e-08, "loss": 0.3382, "step": 1786 }, { "epoch": 1.0726072607260726, "grad_norm": 5.563830375671387, "learning_rate": 4.0416498905290976e-08, "loss": 0.6098, "step": 1787 }, { "epoch": 1.0732073207320731, "grad_norm": 4.6055521965026855, "learning_rate": 4.108266978105501e-08, "loss": 0.4378, "step": 1788 }, { "epoch": 1.073807380738074, "grad_norm": 4.285024166107178, "learning_rate": 4.175417089083355e-08, "loss": 0.325, "step": 1789 }, { "epoch": 1.0744074407440745, "grad_norm": 3.9762771129608154, "learning_rate": 4.2430998502023806e-08, "loss": 0.3851, "step": 1790 }, { "epoch": 1.075007500750075, "grad_norm": 3.1769845485687256, "learning_rate": 4.311314885241391e-08, "loss": 0.288, "step": 1791 }, { "epoch": 1.0756075607560756, "grad_norm": 6.003036022186279, "learning_rate": 4.380061815020575e-08, "loss": 0.5646, "step": 1792 }, { "epoch": 1.076207620762076, "grad_norm": 5.070879936218262, "learning_rate": 4.4493402574035554e-08, "loss": 0.4571, "step": 1793 }, { "epoch": 1.0768076807680769, "grad_norm": 4.125925540924072, "learning_rate": 4.519149827299418e-08, "loss": 0.3587, "step": 1794 }, { "epoch": 1.0774077407740774, "grad_norm": 4.079013347625732, "learning_rate": 4.589490136664998e-08, "loss": 0.3698, "step": 1795 }, { "epoch": 1.078007800780078, "grad_norm": 4.820714473724365, "learning_rate": 4.6603607945069456e-08, "loss": 0.3144, "step": 1796 }, { "epoch": 1.0786078607860785, "grad_norm": 6.013705730438232, "learning_rate": 4.731761406883883e-08, "loss": 0.6704, "step": 1797 }, { "epoch": 1.0792079207920793, "grad_norm": 4.007145404815674, "learning_rate": 4.8036915769086525e-08, "loss": 0.3262, "step": 1798 }, { "epoch": 1.0798079807980798, "grad_norm": 4.065284252166748, "learning_rate": 4.8761509047505203e-08, "loss": 0.3214, "step": 1799 }, { "epoch": 1.0804080408040804, "grad_norm": 6.617237091064453, "learning_rate": 4.949138987637336e-08, "loss": 0.5408, "step": 1800 }, { "epoch": 1.081008100810081, "grad_norm": 4.964456081390381, "learning_rate": 5.0226554198578464e-08, "loss": 0.4006, "step": 1801 }, { "epoch": 1.0816081608160817, "grad_norm": 3.675870656967163, "learning_rate": 5.096699792763914e-08, "loss": 0.4078, "step": 1802 }, { "epoch": 1.0822082208220822, "grad_norm": 4.712167263031006, "learning_rate": 5.171271694772783e-08, "loss": 0.3298, "step": 1803 }, { "epoch": 1.0828082808280828, "grad_norm": 4.986452102661133, "learning_rate": 5.2463707113693634e-08, "loss": 0.3481, "step": 1804 }, { "epoch": 1.0834083408340833, "grad_norm": 5.0130534172058105, "learning_rate": 5.321996425108577e-08, "loss": 0.3389, "step": 1805 }, { "epoch": 1.084008400840084, "grad_norm": 4.534860134124756, "learning_rate": 5.3981484156176425e-08, "loss": 0.3748, "step": 1806 }, { "epoch": 1.0846084608460846, "grad_norm": 6.159364700317383, "learning_rate": 5.474826259598386e-08, "loss": 0.5193, "step": 1807 }, { "epoch": 1.0852085208520852, "grad_norm": 3.9033701419830322, "learning_rate": 5.552029530829683e-08, "loss": 0.3778, "step": 1808 }, { "epoch": 1.0858085808580857, "grad_norm": 5.008702278137207, "learning_rate": 5.629757800169721e-08, "loss": 0.3637, "step": 1809 }, { "epoch": 1.0864086408640865, "grad_norm": 5.589733600616455, "learning_rate": 5.7080106355584576e-08, "loss": 0.6482, "step": 1810 }, { "epoch": 1.087008700870087, "grad_norm": 5.197887420654297, "learning_rate": 5.786787602020005e-08, "loss": 0.4969, "step": 1811 }, { "epoch": 1.0876087608760876, "grad_norm": 5.97096061706543, "learning_rate": 5.8660882616650144e-08, "loss": 0.5024, "step": 1812 }, { "epoch": 1.0882088208820881, "grad_norm": 3.7932028770446777, "learning_rate": 5.9459121736931904e-08, "loss": 0.4773, "step": 1813 }, { "epoch": 1.088808880888089, "grad_norm": 3.677424907684326, "learning_rate": 6.026258894395631e-08, "loss": 0.3425, "step": 1814 }, { "epoch": 1.0894089408940895, "grad_norm": 3.0650482177734375, "learning_rate": 6.107127977157378e-08, "loss": 0.1834, "step": 1815 }, { "epoch": 1.09000900090009, "grad_norm": 4.176052093505859, "learning_rate": 6.188518972459899e-08, "loss": 0.2486, "step": 1816 }, { "epoch": 1.0906090609060906, "grad_norm": 4.9352803230285645, "learning_rate": 6.270431427883504e-08, "loss": 0.3776, "step": 1817 }, { "epoch": 1.091209120912091, "grad_norm": 2.692939519882202, "learning_rate": 6.352864888109955e-08, "loss": 0.1524, "step": 1818 }, { "epoch": 1.0918091809180919, "grad_norm": 3.7930545806884766, "learning_rate": 6.435818894924982e-08, "loss": 0.2764, "step": 1819 }, { "epoch": 1.0924092409240924, "grad_norm": 6.0519304275512695, "learning_rate": 6.519292987220715e-08, "loss": 0.6481, "step": 1820 }, { "epoch": 1.093009300930093, "grad_norm": 3.859498977661133, "learning_rate": 6.603286700998445e-08, "loss": 0.3803, "step": 1821 }, { "epoch": 1.0936093609360935, "grad_norm": 3.0641353130340576, "learning_rate": 6.687799569371078e-08, "loss": 0.2551, "step": 1822 }, { "epoch": 1.0942094209420943, "grad_norm": 4.673534393310547, "learning_rate": 6.772831122565659e-08, "loss": 0.337, "step": 1823 }, { "epoch": 1.0948094809480948, "grad_norm": 5.560605049133301, "learning_rate": 6.858380887926152e-08, "loss": 0.4685, "step": 1824 }, { "epoch": 1.0954095409540954, "grad_norm": 4.312337875366211, "learning_rate": 6.944448389916014e-08, "loss": 0.3497, "step": 1825 }, { "epoch": 1.096009600960096, "grad_norm": 5.170284748077393, "learning_rate": 7.03103315012078e-08, "loss": 0.3766, "step": 1826 }, { "epoch": 1.0966096609660967, "grad_norm": 2.24281644821167, "learning_rate": 7.118134687250665e-08, "loss": 0.1825, "step": 1827 }, { "epoch": 1.0972097209720972, "grad_norm": 4.0677266120910645, "learning_rate": 7.205752517143504e-08, "loss": 0.3759, "step": 1828 }, { "epoch": 1.0978097809780978, "grad_norm": 5.148793697357178, "learning_rate": 7.293886152767181e-08, "loss": 0.3979, "step": 1829 }, { "epoch": 1.0984098409840983, "grad_norm": 5.184237957000732, "learning_rate": 7.382535104222354e-08, "loss": 0.4536, "step": 1830 }, { "epoch": 1.099009900990099, "grad_norm": 4.055205345153809, "learning_rate": 7.471698878745337e-08, "loss": 0.3148, "step": 1831 }, { "epoch": 1.0996099609960996, "grad_norm": 3.567922353744507, "learning_rate": 7.56137698071081e-08, "loss": 0.4087, "step": 1832 }, { "epoch": 1.1002100210021002, "grad_norm": 4.841022968292236, "learning_rate": 7.651568911634332e-08, "loss": 0.2954, "step": 1833 }, { "epoch": 1.1008100810081007, "grad_norm": 5.564867973327637, "learning_rate": 7.742274170175444e-08, "loss": 0.4567, "step": 1834 }, { "epoch": 1.1014101410141015, "grad_norm": 6.165777206420898, "learning_rate": 7.83349225214025e-08, "loss": 0.5986, "step": 1835 }, { "epoch": 1.102010201020102, "grad_norm": 3.9242279529571533, "learning_rate": 7.925222650484353e-08, "loss": 0.284, "step": 1836 }, { "epoch": 1.1026102610261026, "grad_norm": 4.826714038848877, "learning_rate": 8.017464855315425e-08, "loss": 0.275, "step": 1837 }, { "epoch": 1.1032103210321031, "grad_norm": 5.548309326171875, "learning_rate": 8.11021835389637e-08, "loss": 0.4605, "step": 1838 }, { "epoch": 1.103810381038104, "grad_norm": 3.5885889530181885, "learning_rate": 8.203482630647984e-08, "loss": 0.4926, "step": 1839 }, { "epoch": 1.1044104410441045, "grad_norm": 3.659172296524048, "learning_rate": 8.297257167151784e-08, "loss": 0.4088, "step": 1840 }, { "epoch": 1.105010501050105, "grad_norm": 5.367453575134277, "learning_rate": 8.391541442153038e-08, "loss": 0.4557, "step": 1841 }, { "epoch": 1.1056105610561056, "grad_norm": 4.496574878692627, "learning_rate": 8.486334931563566e-08, "loss": 0.3324, "step": 1842 }, { "epoch": 1.106210621062106, "grad_norm": 4.464998245239258, "learning_rate": 8.581637108464623e-08, "loss": 0.3273, "step": 1843 }, { "epoch": 1.1068106810681069, "grad_norm": 5.841141223907471, "learning_rate": 8.67744744310993e-08, "loss": 0.3134, "step": 1844 }, { "epoch": 1.1074107410741074, "grad_norm": 4.567250728607178, "learning_rate": 8.773765402928568e-08, "loss": 0.2926, "step": 1845 }, { "epoch": 1.108010801080108, "grad_norm": 3.9290943145751953, "learning_rate": 8.87059045252787e-08, "loss": 0.3407, "step": 1846 }, { "epoch": 1.1086108610861085, "grad_norm": 3.207442283630371, "learning_rate": 8.967922053696531e-08, "loss": 0.1544, "step": 1847 }, { "epoch": 1.1092109210921093, "grad_norm": 4.68932580947876, "learning_rate": 9.065759665407502e-08, "loss": 0.2824, "step": 1848 }, { "epoch": 1.1098109810981098, "grad_norm": 2.992657423019409, "learning_rate": 9.164102743821046e-08, "loss": 0.4592, "step": 1849 }, { "epoch": 1.1104110411041104, "grad_norm": 5.417274475097656, "learning_rate": 9.26295074228769e-08, "loss": 0.5242, "step": 1850 }, { "epoch": 1.111011101110111, "grad_norm": 5.304010391235352, "learning_rate": 9.362303111351344e-08, "loss": 0.5223, "step": 1851 }, { "epoch": 1.1116111611161117, "grad_norm": 3.79485821723938, "learning_rate": 9.462159298752382e-08, "loss": 0.3764, "step": 1852 }, { "epoch": 1.1122112211221122, "grad_norm": 4.631716251373291, "learning_rate": 9.562518749430537e-08, "loss": 0.4054, "step": 1853 }, { "epoch": 1.1128112811281128, "grad_norm": 3.997802257537842, "learning_rate": 9.663380905528207e-08, "loss": 0.2887, "step": 1854 }, { "epoch": 1.1134113411341133, "grad_norm": 5.4967756271362305, "learning_rate": 9.76474520639342e-08, "loss": 0.4143, "step": 1855 }, { "epoch": 1.114011401140114, "grad_norm": 4.624125003814697, "learning_rate": 9.866611088582955e-08, "loss": 0.6386, "step": 1856 }, { "epoch": 1.1146114611461146, "grad_norm": 2.491835355758667, "learning_rate": 9.968977985865545e-08, "loss": 0.2675, "step": 1857 }, { "epoch": 1.1152115211521152, "grad_norm": 4.164661884307861, "learning_rate": 1.0071845329224981e-07, "loss": 0.3725, "step": 1858 }, { "epoch": 1.1158115811581157, "grad_norm": 4.515260696411133, "learning_rate": 1.0175212546863232e-07, "loss": 0.3001, "step": 1859 }, { "epoch": 1.1164116411641165, "grad_norm": 4.8481364250183105, "learning_rate": 1.0279079064203711e-07, "loss": 0.453, "step": 1860 }, { "epoch": 1.117011701170117, "grad_norm": 3.7929024696350098, "learning_rate": 1.0383444303894417e-07, "loss": 0.3164, "step": 1861 }, { "epoch": 1.1176117611761176, "grad_norm": 3.964097261428833, "learning_rate": 1.048830768581116e-07, "loss": 0.2831, "step": 1862 }, { "epoch": 1.1182118211821181, "grad_norm": 4.009713649749756, "learning_rate": 1.0593668627060736e-07, "loss": 0.2945, "step": 1863 }, { "epoch": 1.118811881188119, "grad_norm": 3.5930120944976807, "learning_rate": 1.0699526541984261e-07, "loss": 0.253, "step": 1864 }, { "epoch": 1.1194119411941195, "grad_norm": 4.698947429656982, "learning_rate": 1.0805880842160387e-07, "loss": 0.3177, "step": 1865 }, { "epoch": 1.12001200120012, "grad_norm": 2.924379825592041, "learning_rate": 1.0912730936408432e-07, "loss": 0.2372, "step": 1866 }, { "epoch": 1.1206120612061206, "grad_norm": 3.25258207321167, "learning_rate": 1.1020076230791975e-07, "loss": 0.3837, "step": 1867 }, { "epoch": 1.121212121212121, "grad_norm": 3.4342992305755615, "learning_rate": 1.1127916128621907e-07, "loss": 0.3092, "step": 1868 }, { "epoch": 1.1218121812181219, "grad_norm": 3.338958978652954, "learning_rate": 1.1236250030459737e-07, "loss": 0.2307, "step": 1869 }, { "epoch": 1.1224122412241224, "grad_norm": 4.8667683601379395, "learning_rate": 1.1345077334121089e-07, "loss": 0.3062, "step": 1870 }, { "epoch": 1.123012301230123, "grad_norm": 3.5539369583129883, "learning_rate": 1.1454397434678987e-07, "loss": 0.2155, "step": 1871 }, { "epoch": 1.1236123612361235, "grad_norm": 5.101792812347412, "learning_rate": 1.1564209724467177e-07, "loss": 0.3833, "step": 1872 }, { "epoch": 1.1242124212421243, "grad_norm": 3.581839084625244, "learning_rate": 1.1674513593083424e-07, "loss": 0.3181, "step": 1873 }, { "epoch": 1.1248124812481248, "grad_norm": 4.514209747314453, "learning_rate": 1.1785308427393148e-07, "loss": 0.3947, "step": 1874 }, { "epoch": 1.1254125412541254, "grad_norm": 4.520711421966553, "learning_rate": 1.1896593611532657e-07, "loss": 0.3059, "step": 1875 }, { "epoch": 1.126012601260126, "grad_norm": 4.361568450927734, "learning_rate": 1.2008368526912495e-07, "loss": 0.5834, "step": 1876 }, { "epoch": 1.1266126612661267, "grad_norm": 4.874344348907471, "learning_rate": 1.2120632552221076e-07, "loss": 0.3118, "step": 1877 }, { "epoch": 1.1272127212721272, "grad_norm": 4.262031078338623, "learning_rate": 1.2233385063428149e-07, "loss": 0.4175, "step": 1878 }, { "epoch": 1.1278127812781278, "grad_norm": 3.5924229621887207, "learning_rate": 1.2346625433787927e-07, "loss": 0.3161, "step": 1879 }, { "epoch": 1.1284128412841283, "grad_norm": 4.429491996765137, "learning_rate": 1.2460353033842996e-07, "loss": 0.4654, "step": 1880 }, { "epoch": 1.129012901290129, "grad_norm": 5.7674055099487305, "learning_rate": 1.257456723142759e-07, "loss": 0.4744, "step": 1881 }, { "epoch": 1.1296129612961296, "grad_norm": 3.7483224868774414, "learning_rate": 1.268926739167111e-07, "loss": 0.2393, "step": 1882 }, { "epoch": 1.1302130213021302, "grad_norm": 4.920829772949219, "learning_rate": 1.2804452877001705e-07, "loss": 0.3304, "step": 1883 }, { "epoch": 1.1308130813081307, "grad_norm": 5.6093034744262695, "learning_rate": 1.29201230471498e-07, "loss": 0.433, "step": 1884 }, { "epoch": 1.1314131413141315, "grad_norm": 4.557003498077393, "learning_rate": 1.3036277259151684e-07, "loss": 0.287, "step": 1885 }, { "epoch": 1.132013201320132, "grad_norm": 6.51400089263916, "learning_rate": 1.315291486735297e-07, "loss": 0.5156, "step": 1886 }, { "epoch": 1.1326132613261326, "grad_norm": 4.010222434997559, "learning_rate": 1.3270035223412345e-07, "loss": 0.2626, "step": 1887 }, { "epoch": 1.1332133213321331, "grad_norm": 6.843282699584961, "learning_rate": 1.3387637676305097e-07, "loss": 0.8676, "step": 1888 }, { "epoch": 1.133813381338134, "grad_norm": 4.195582866668701, "learning_rate": 1.3505721572326656e-07, "loss": 0.2726, "step": 1889 }, { "epoch": 1.1344134413441345, "grad_norm": 4.260000705718994, "learning_rate": 1.3624286255096363e-07, "loss": 0.3624, "step": 1890 }, { "epoch": 1.135013501350135, "grad_norm": 5.598803520202637, "learning_rate": 1.374333106556108e-07, "loss": 0.5339, "step": 1891 }, { "epoch": 1.1356135613561356, "grad_norm": 4.297807216644287, "learning_rate": 1.386285534199877e-07, "loss": 0.4018, "step": 1892 }, { "epoch": 1.136213621362136, "grad_norm": 3.4030420780181885, "learning_rate": 1.398285842002227e-07, "loss": 0.31, "step": 1893 }, { "epoch": 1.1368136813681369, "grad_norm": 2.8968842029571533, "learning_rate": 1.4103339632582967e-07, "loss": 0.273, "step": 1894 }, { "epoch": 1.1374137413741374, "grad_norm": 4.729235649108887, "learning_rate": 1.4224298309974504e-07, "loss": 0.3554, "step": 1895 }, { "epoch": 1.138013801380138, "grad_norm": 4.2607831954956055, "learning_rate": 1.4345733779836399e-07, "loss": 0.3625, "step": 1896 }, { "epoch": 1.1386138613861387, "grad_norm": 3.2270116806030273, "learning_rate": 1.4467645367157989e-07, "loss": 0.2152, "step": 1897 }, { "epoch": 1.1392139213921393, "grad_norm": 3.9942781925201416, "learning_rate": 1.4590032394282005e-07, "loss": 0.2263, "step": 1898 }, { "epoch": 1.1398139813981398, "grad_norm": 4.405048847198486, "learning_rate": 1.4712894180908398e-07, "loss": 0.2978, "step": 1899 }, { "epoch": 1.1404140414041404, "grad_norm": 4.422273635864258, "learning_rate": 1.483623004409813e-07, "loss": 0.4576, "step": 1900 }, { "epoch": 1.141014101410141, "grad_norm": 4.478857517242432, "learning_rate": 1.4960039298277004e-07, "loss": 0.4029, "step": 1901 }, { "epoch": 1.1416141614161417, "grad_norm": 5.612326145172119, "learning_rate": 1.5084321255239362e-07, "loss": 0.6952, "step": 1902 }, { "epoch": 1.1422142214221422, "grad_norm": 4.055355072021484, "learning_rate": 1.5209075224152012e-07, "loss": 0.2048, "step": 1903 }, { "epoch": 1.1428142814281428, "grad_norm": 3.531559944152832, "learning_rate": 1.5334300511558097e-07, "loss": 0.263, "step": 1904 }, { "epoch": 1.1434143414341433, "grad_norm": 2.310025930404663, "learning_rate": 1.5459996421380784e-07, "loss": 0.1744, "step": 1905 }, { "epoch": 1.144014401440144, "grad_norm": 4.427637577056885, "learning_rate": 1.5586162254927305e-07, "loss": 0.5093, "step": 1906 }, { "epoch": 1.1446144614461446, "grad_norm": 5.702352523803711, "learning_rate": 1.5712797310892768e-07, "loss": 0.4326, "step": 1907 }, { "epoch": 1.1452145214521452, "grad_norm": 5.597407341003418, "learning_rate": 1.5839900885364088e-07, "loss": 0.5092, "step": 1908 }, { "epoch": 1.1458145814581457, "grad_norm": 4.9115400314331055, "learning_rate": 1.5967472271823812e-07, "loss": 0.372, "step": 1909 }, { "epoch": 1.1464146414641465, "grad_norm": 3.163087844848633, "learning_rate": 1.6095510761154153e-07, "loss": 0.2885, "step": 1910 }, { "epoch": 1.147014701470147, "grad_norm": 4.717977523803711, "learning_rate": 1.6224015641640932e-07, "loss": 0.4114, "step": 1911 }, { "epoch": 1.1476147614761476, "grad_norm": 3.9551820755004883, "learning_rate": 1.6352986198977315e-07, "loss": 0.346, "step": 1912 }, { "epoch": 1.1482148214821482, "grad_norm": 4.385586261749268, "learning_rate": 1.648242171626817e-07, "loss": 0.2775, "step": 1913 }, { "epoch": 1.148814881488149, "grad_norm": 4.702469825744629, "learning_rate": 1.6612321474033797e-07, "loss": 0.517, "step": 1914 }, { "epoch": 1.1494149414941495, "grad_norm": 5.034040927886963, "learning_rate": 1.6742684750213776e-07, "loss": 0.2708, "step": 1915 }, { "epoch": 1.15001500150015, "grad_norm": 2.731804132461548, "learning_rate": 1.6873510820171444e-07, "loss": 0.159, "step": 1916 }, { "epoch": 1.1506150615061506, "grad_norm": 4.19761323928833, "learning_rate": 1.7004798956697508e-07, "loss": 0.2452, "step": 1917 }, { "epoch": 1.151215121512151, "grad_norm": 5.469825267791748, "learning_rate": 1.7136548430014298e-07, "loss": 0.4711, "step": 1918 }, { "epoch": 1.1518151815181519, "grad_norm": 4.5765581130981445, "learning_rate": 1.7268758507779603e-07, "loss": 0.3054, "step": 1919 }, { "epoch": 1.1524152415241524, "grad_norm": 5.5942864418029785, "learning_rate": 1.7401428455091117e-07, "loss": 0.4412, "step": 1920 }, { "epoch": 1.153015301530153, "grad_norm": 3.317305564880371, "learning_rate": 1.7534557534490235e-07, "loss": 0.2794, "step": 1921 }, { "epoch": 1.1536153615361537, "grad_norm": 4.988752841949463, "learning_rate": 1.7668145005966083e-07, "loss": 0.5442, "step": 1922 }, { "epoch": 1.1542154215421543, "grad_norm": 5.214664936065674, "learning_rate": 1.7802190126959904e-07, "loss": 0.5121, "step": 1923 }, { "epoch": 1.1548154815481548, "grad_norm": 5.3503313064575195, "learning_rate": 1.7936692152369138e-07, "loss": 0.4485, "step": 1924 }, { "epoch": 1.1554155415541554, "grad_norm": 3.0543928146362305, "learning_rate": 1.8071650334551224e-07, "loss": 0.2642, "step": 1925 }, { "epoch": 1.156015601560156, "grad_norm": 4.422058582305908, "learning_rate": 1.8207063923328225e-07, "loss": 0.3698, "step": 1926 }, { "epoch": 1.1566156615661567, "grad_norm": 6.291955947875977, "learning_rate": 1.8342932165990732e-07, "loss": 0.5177, "step": 1927 }, { "epoch": 1.1572157215721572, "grad_norm": 2.8523690700531006, "learning_rate": 1.8479254307302005e-07, "loss": 0.3172, "step": 1928 }, { "epoch": 1.1578157815781578, "grad_norm": 5.1559953689575195, "learning_rate": 1.861602958950239e-07, "loss": 0.3184, "step": 1929 }, { "epoch": 1.1584158415841583, "grad_norm": 4.939239025115967, "learning_rate": 1.8753257252313316e-07, "loss": 0.3726, "step": 1930 }, { "epoch": 1.159015901590159, "grad_norm": 3.7996504306793213, "learning_rate": 1.8890936532941759e-07, "loss": 0.4098, "step": 1931 }, { "epoch": 1.1596159615961597, "grad_norm": 3.8334591388702393, "learning_rate": 1.902906666608408e-07, "loss": 0.2567, "step": 1932 }, { "epoch": 1.1602160216021602, "grad_norm": 4.48914909362793, "learning_rate": 1.9167646883930743e-07, "loss": 0.4598, "step": 1933 }, { "epoch": 1.1608160816081607, "grad_norm": 6.045205116271973, "learning_rate": 1.930667641617032e-07, "loss": 0.6369, "step": 1934 }, { "epoch": 1.1614161416141615, "grad_norm": 4.31009578704834, "learning_rate": 1.9446154489993772e-07, "loss": 0.331, "step": 1935 }, { "epoch": 1.162016201620162, "grad_norm": 5.0770416259765625, "learning_rate": 1.9586080330098853e-07, "loss": 0.4412, "step": 1936 }, { "epoch": 1.1626162616261626, "grad_norm": 4.37962007522583, "learning_rate": 1.972645315869439e-07, "loss": 0.4834, "step": 1937 }, { "epoch": 1.1632163216321632, "grad_norm": 3.8173673152923584, "learning_rate": 1.986727219550448e-07, "loss": 0.3165, "step": 1938 }, { "epoch": 1.163816381638164, "grad_norm": 4.825254440307617, "learning_rate": 2.0008536657773024e-07, "loss": 0.4914, "step": 1939 }, { "epoch": 1.1644164416441645, "grad_norm": 3.608120918273926, "learning_rate": 2.0150245760267947e-07, "loss": 0.4124, "step": 1940 }, { "epoch": 1.165016501650165, "grad_norm": 4.484736919403076, "learning_rate": 2.029239871528563e-07, "loss": 0.5017, "step": 1941 }, { "epoch": 1.1656165616561656, "grad_norm": 5.083711624145508, "learning_rate": 2.0434994732655176e-07, "loss": 0.3347, "step": 1942 }, { "epoch": 1.166216621662166, "grad_norm": 4.3990478515625, "learning_rate": 2.0578033019742958e-07, "loss": 0.4449, "step": 1943 }, { "epoch": 1.1668166816681669, "grad_norm": 4.996182918548584, "learning_rate": 2.0721512781456962e-07, "loss": 0.3832, "step": 1944 }, { "epoch": 1.1674167416741674, "grad_norm": 4.846430778503418, "learning_rate": 2.0865433220251104e-07, "loss": 0.5743, "step": 1945 }, { "epoch": 1.168016801680168, "grad_norm": 3.6762731075286865, "learning_rate": 2.100979353612985e-07, "loss": 0.3157, "step": 1946 }, { "epoch": 1.1686168616861687, "grad_norm": 3.2126431465148926, "learning_rate": 2.1154592926652536e-07, "loss": 0.2147, "step": 1947 }, { "epoch": 1.1692169216921693, "grad_norm": 4.012036323547363, "learning_rate": 2.1299830586937805e-07, "loss": 0.3902, "step": 1948 }, { "epoch": 1.1698169816981698, "grad_norm": 3.746954917907715, "learning_rate": 2.144550570966822e-07, "loss": 0.3261, "step": 1949 }, { "epoch": 1.1704170417041704, "grad_norm": 7.109899520874023, "learning_rate": 2.1591617485094649e-07, "loss": 0.8229, "step": 1950 }, { "epoch": 1.171017101710171, "grad_norm": 4.848573684692383, "learning_rate": 2.1738165101040716e-07, "loss": 0.2643, "step": 1951 }, { "epoch": 1.1716171617161717, "grad_norm": 5.577190399169922, "learning_rate": 2.188514774290745e-07, "loss": 0.3241, "step": 1952 }, { "epoch": 1.1722172217221722, "grad_norm": 4.8242926597595215, "learning_rate": 2.2032564593677727e-07, "loss": 0.4357, "step": 1953 }, { "epoch": 1.1728172817281728, "grad_norm": 4.301931858062744, "learning_rate": 2.218041483392088e-07, "loss": 0.4258, "step": 1954 }, { "epoch": 1.1734173417341733, "grad_norm": 3.212376117706299, "learning_rate": 2.232869764179709e-07, "loss": 0.3472, "step": 1955 }, { "epoch": 1.174017401740174, "grad_norm": 2.936464786529541, "learning_rate": 2.247741219306216e-07, "loss": 0.3485, "step": 1956 }, { "epoch": 1.1746174617461747, "grad_norm": 5.016060829162598, "learning_rate": 2.2626557661072054e-07, "loss": 0.3193, "step": 1957 }, { "epoch": 1.1752175217521752, "grad_norm": 4.387333393096924, "learning_rate": 2.277613321678722e-07, "loss": 0.3737, "step": 1958 }, { "epoch": 1.1758175817581757, "grad_norm": 5.642590045928955, "learning_rate": 2.2926138028777686e-07, "loss": 0.6441, "step": 1959 }, { "epoch": 1.1764176417641765, "grad_norm": 4.4725213050842285, "learning_rate": 2.3076571263227352e-07, "loss": 0.3522, "step": 1960 }, { "epoch": 1.177017701770177, "grad_norm": 5.235065937042236, "learning_rate": 2.3227432083938504e-07, "loss": 0.4177, "step": 1961 }, { "epoch": 1.1776177617761776, "grad_norm": 3.6031739711761475, "learning_rate": 2.3378719652336876e-07, "loss": 0.4414, "step": 1962 }, { "epoch": 1.1782178217821782, "grad_norm": 3.507715940475464, "learning_rate": 2.3530433127476003e-07, "loss": 0.255, "step": 1963 }, { "epoch": 1.178817881788179, "grad_norm": 2.8797481060028076, "learning_rate": 2.3682571666042016e-07, "loss": 0.1616, "step": 1964 }, { "epoch": 1.1794179417941795, "grad_norm": 4.789570331573486, "learning_rate": 2.3835134422358106e-07, "loss": 0.3032, "step": 1965 }, { "epoch": 1.18001800180018, "grad_norm": 5.767952919006348, "learning_rate": 2.3988120548389656e-07, "loss": 0.349, "step": 1966 }, { "epoch": 1.1806180618061806, "grad_norm": 4.710083961486816, "learning_rate": 2.4141529193748634e-07, "loss": 0.4257, "step": 1967 }, { "epoch": 1.181218121812181, "grad_norm": 4.042532444000244, "learning_rate": 2.4295359505698256e-07, "loss": 0.3027, "step": 1968 }, { "epoch": 1.1818181818181819, "grad_norm": 4.078263759613037, "learning_rate": 2.4449610629157993e-07, "loss": 0.2869, "step": 1969 }, { "epoch": 1.1824182418241824, "grad_norm": 4.34612512588501, "learning_rate": 2.4604281706708273e-07, "loss": 0.3388, "step": 1970 }, { "epoch": 1.183018301830183, "grad_norm": 4.363104820251465, "learning_rate": 2.475937187859494e-07, "loss": 0.446, "step": 1971 }, { "epoch": 1.1836183618361837, "grad_norm": 4.242734432220459, "learning_rate": 2.491488028273443e-07, "loss": 0.4276, "step": 1972 }, { "epoch": 1.1842184218421843, "grad_norm": 5.206864833831787, "learning_rate": 2.5070806054718387e-07, "loss": 0.521, "step": 1973 }, { "epoch": 1.1848184818481848, "grad_norm": 5.033260822296143, "learning_rate": 2.5227148327818394e-07, "loss": 0.4958, "step": 1974 }, { "epoch": 1.1854185418541854, "grad_norm": 3.1892547607421875, "learning_rate": 2.5383906232990937e-07, "loss": 0.292, "step": 1975 }, { "epoch": 1.186018601860186, "grad_norm": 4.114774703979492, "learning_rate": 2.5541078898882143e-07, "loss": 0.2426, "step": 1976 }, { "epoch": 1.1866186618661867, "grad_norm": 5.108753681182861, "learning_rate": 2.569866545183276e-07, "loss": 0.2452, "step": 1977 }, { "epoch": 1.1872187218721872, "grad_norm": 3.417243480682373, "learning_rate": 2.585666501588267e-07, "loss": 0.275, "step": 1978 }, { "epoch": 1.1878187818781878, "grad_norm": 4.413401126861572, "learning_rate": 2.6015076712776194e-07, "loss": 0.3621, "step": 1979 }, { "epoch": 1.1884188418841883, "grad_norm": 4.64268159866333, "learning_rate": 2.6173899661966746e-07, "loss": 0.338, "step": 1980 }, { "epoch": 1.189018901890189, "grad_norm": 4.039518356323242, "learning_rate": 2.633313298062164e-07, "loss": 0.3497, "step": 1981 }, { "epoch": 1.1896189618961897, "grad_norm": 3.6425867080688477, "learning_rate": 2.649277578362724e-07, "loss": 0.4351, "step": 1982 }, { "epoch": 1.1902190219021902, "grad_norm": 3.7783522605895996, "learning_rate": 2.665282718359373e-07, "loss": 0.3541, "step": 1983 }, { "epoch": 1.1908190819081907, "grad_norm": 5.043895721435547, "learning_rate": 2.681328629085997e-07, "loss": 0.4533, "step": 1984 }, { "epoch": 1.1914191419141915, "grad_norm": 3.1534461975097656, "learning_rate": 2.6974152213498655e-07, "loss": 0.2755, "step": 1985 }, { "epoch": 1.192019201920192, "grad_norm": 4.711608409881592, "learning_rate": 2.713542405732113e-07, "loss": 0.2619, "step": 1986 }, { "epoch": 1.1926192619261926, "grad_norm": 4.794290542602539, "learning_rate": 2.7297100925882346e-07, "loss": 0.3192, "step": 1987 }, { "epoch": 1.1932193219321932, "grad_norm": 5.5348992347717285, "learning_rate": 2.7459181920485895e-07, "loss": 0.3865, "step": 1988 }, { "epoch": 1.193819381938194, "grad_norm": 3.8026018142700195, "learning_rate": 2.762166614018905e-07, "loss": 0.3495, "step": 1989 }, { "epoch": 1.1944194419441945, "grad_norm": 4.086058139801025, "learning_rate": 2.7784552681807685e-07, "loss": 0.5144, "step": 1990 }, { "epoch": 1.195019501950195, "grad_norm": 3.861203193664551, "learning_rate": 2.794784063992128e-07, "loss": 0.1807, "step": 1991 }, { "epoch": 1.1956195619561956, "grad_norm": 3.392936944961548, "learning_rate": 2.8111529106878086e-07, "loss": 0.314, "step": 1992 }, { "epoch": 1.1962196219621961, "grad_norm": 4.588399887084961, "learning_rate": 2.8275617172800047e-07, "loss": 0.2447, "step": 1993 }, { "epoch": 1.1968196819681969, "grad_norm": 6.356202602386475, "learning_rate": 2.844010392558788e-07, "loss": 0.4805, "step": 1994 }, { "epoch": 1.1974197419741974, "grad_norm": 4.478870391845703, "learning_rate": 2.8604988450926183e-07, "loss": 0.2939, "step": 1995 }, { "epoch": 1.198019801980198, "grad_norm": 3.2591936588287354, "learning_rate": 2.877026983228854e-07, "loss": 0.2508, "step": 1996 }, { "epoch": 1.1986198619861987, "grad_norm": 5.452743053436279, "learning_rate": 2.8935947150942465e-07, "loss": 0.2963, "step": 1997 }, { "epoch": 1.1992199219921993, "grad_norm": 4.3901495933532715, "learning_rate": 2.91020194859547e-07, "loss": 0.5051, "step": 1998 }, { "epoch": 1.1998199819981998, "grad_norm": 4.538329124450684, "learning_rate": 2.926848591419625e-07, "loss": 0.3514, "step": 1999 }, { "epoch": 1.2004200420042004, "grad_norm": 4.94241189956665, "learning_rate": 2.943534551034753e-07, "loss": 0.3009, "step": 2000 }, { "epoch": 1.201020102010201, "grad_norm": 4.134317398071289, "learning_rate": 2.960259734690338e-07, "loss": 0.3508, "step": 2001 }, { "epoch": 1.2016201620162017, "grad_norm": 4.110447406768799, "learning_rate": 2.9770240494178455e-07, "loss": 0.3215, "step": 2002 }, { "epoch": 1.2022202220222022, "grad_norm": 5.327750205993652, "learning_rate": 2.993827402031229e-07, "loss": 0.4164, "step": 2003 }, { "epoch": 1.2028202820282028, "grad_norm": 4.096363067626953, "learning_rate": 3.010669699127426e-07, "loss": 0.3492, "step": 2004 }, { "epoch": 1.2034203420342033, "grad_norm": 4.420214653015137, "learning_rate": 3.0275508470869214e-07, "loss": 0.3544, "step": 2005 }, { "epoch": 1.204020402040204, "grad_norm": 5.084394454956055, "learning_rate": 3.0444707520742395e-07, "loss": 0.3321, "step": 2006 }, { "epoch": 1.2046204620462047, "grad_norm": 3.0323355197906494, "learning_rate": 3.061429320038449e-07, "loss": 0.5016, "step": 2007 }, { "epoch": 1.2052205220522052, "grad_norm": 5.921281337738037, "learning_rate": 3.078426456713733e-07, "loss": 0.5074, "step": 2008 }, { "epoch": 1.2058205820582057, "grad_norm": 4.326046943664551, "learning_rate": 3.0954620676198794e-07, "loss": 0.3707, "step": 2009 }, { "epoch": 1.2064206420642065, "grad_norm": 4.3515706062316895, "learning_rate": 3.112536058062799e-07, "loss": 0.3173, "step": 2010 }, { "epoch": 1.207020702070207, "grad_norm": 4.6015729904174805, "learning_rate": 3.129648333135078e-07, "loss": 0.36, "step": 2011 }, { "epoch": 1.2076207620762076, "grad_norm": 3.8726089000701904, "learning_rate": 3.1467987977165013e-07, "loss": 0.3063, "step": 2012 }, { "epoch": 1.2082208220822082, "grad_norm": 4.658523082733154, "learning_rate": 3.1639873564745676e-07, "loss": 0.5381, "step": 2013 }, { "epoch": 1.208820882088209, "grad_norm": 4.68503999710083, "learning_rate": 3.181213913865012e-07, "loss": 0.2297, "step": 2014 }, { "epoch": 1.2094209420942095, "grad_norm": 4.890080451965332, "learning_rate": 3.198478374132363e-07, "loss": 0.3455, "step": 2015 }, { "epoch": 1.21002100210021, "grad_norm": 5.9134907722473145, "learning_rate": 3.215780641310475e-07, "loss": 0.6414, "step": 2016 }, { "epoch": 1.2106210621062106, "grad_norm": 6.003228187561035, "learning_rate": 3.23312061922302e-07, "loss": 0.3354, "step": 2017 }, { "epoch": 1.2112211221122111, "grad_norm": 5.26881742477417, "learning_rate": 3.2504982114840706e-07, "loss": 0.4133, "step": 2018 }, { "epoch": 1.2118211821182119, "grad_norm": 3.668071746826172, "learning_rate": 3.267913321498619e-07, "loss": 0.3041, "step": 2019 }, { "epoch": 1.2124212421242124, "grad_norm": 4.930903911590576, "learning_rate": 3.2853658524630945e-07, "loss": 0.6324, "step": 2020 }, { "epoch": 1.213021302130213, "grad_norm": 5.645089149475098, "learning_rate": 3.3028557073659356e-07, "loss": 0.4756, "step": 2021 }, { "epoch": 1.2136213621362137, "grad_norm": 4.2709126472473145, "learning_rate": 3.3203827889880985e-07, "loss": 0.3794, "step": 2022 }, { "epoch": 1.2142214221422143, "grad_norm": 5.057945251464844, "learning_rate": 3.337946999903635e-07, "loss": 0.6, "step": 2023 }, { "epoch": 1.2148214821482148, "grad_norm": 3.975846290588379, "learning_rate": 3.3555482424801716e-07, "loss": 0.3578, "step": 2024 }, { "epoch": 1.2154215421542154, "grad_norm": 3.705512046813965, "learning_rate": 3.373186418879522e-07, "loss": 0.2078, "step": 2025 }, { "epoch": 1.216021602160216, "grad_norm": 3.9279849529266357, "learning_rate": 3.390861431058193e-07, "loss": 0.4139, "step": 2026 }, { "epoch": 1.2166216621662167, "grad_norm": 5.944360256195068, "learning_rate": 3.4085731807679254e-07, "loss": 0.3637, "step": 2027 }, { "epoch": 1.2172217221722172, "grad_norm": 4.279694080352783, "learning_rate": 3.426321569556262e-07, "loss": 0.2405, "step": 2028 }, { "epoch": 1.2178217821782178, "grad_norm": 5.324751853942871, "learning_rate": 3.444106498767083e-07, "loss": 0.3211, "step": 2029 }, { "epoch": 1.2184218421842183, "grad_norm": 2.6368987560272217, "learning_rate": 3.461927869541147e-07, "loss": 0.1794, "step": 2030 }, { "epoch": 1.219021902190219, "grad_norm": 3.5432393550872803, "learning_rate": 3.4797855828166533e-07, "loss": 0.274, "step": 2031 }, { "epoch": 1.2196219621962197, "grad_norm": 3.7131967544555664, "learning_rate": 3.497679539329803e-07, "loss": 0.2246, "step": 2032 }, { "epoch": 1.2202220222022202, "grad_norm": 3.222508668899536, "learning_rate": 3.5156096396153037e-07, "loss": 0.1621, "step": 2033 }, { "epoch": 1.2208220822082207, "grad_norm": 4.72476053237915, "learning_rate": 3.533575784006979e-07, "loss": 0.3663, "step": 2034 }, { "epoch": 1.2214221422142215, "grad_norm": 3.6616029739379883, "learning_rate": 3.5515778726382904e-07, "loss": 0.3973, "step": 2035 }, { "epoch": 1.222022202220222, "grad_norm": 4.98753547668457, "learning_rate": 3.5696158054429093e-07, "loss": 0.3536, "step": 2036 }, { "epoch": 1.2226222622262226, "grad_norm": 6.0201287269592285, "learning_rate": 3.5876894821552396e-07, "loss": 0.5116, "step": 2037 }, { "epoch": 1.2232223222322232, "grad_norm": 5.5521721839904785, "learning_rate": 3.605798802311014e-07, "loss": 0.4424, "step": 2038 }, { "epoch": 1.223822382238224, "grad_norm": 3.3506360054016113, "learning_rate": 3.6239436652478605e-07, "loss": 0.2332, "step": 2039 }, { "epoch": 1.2244224422442245, "grad_norm": 4.327322959899902, "learning_rate": 3.642123970105795e-07, "loss": 0.3732, "step": 2040 }, { "epoch": 1.225022502250225, "grad_norm": 3.7913854122161865, "learning_rate": 3.6603396158278564e-07, "loss": 0.4528, "step": 2041 }, { "epoch": 1.2256225622562256, "grad_norm": 5.731356143951416, "learning_rate": 3.6785905011606353e-07, "loss": 0.2397, "step": 2042 }, { "epoch": 1.2262226222622261, "grad_norm": 3.7242867946624756, "learning_rate": 3.6968765246548206e-07, "loss": 0.3046, "step": 2043 }, { "epoch": 1.2268226822682269, "grad_norm": 4.557817459106445, "learning_rate": 3.715197584665803e-07, "loss": 0.3285, "step": 2044 }, { "epoch": 1.2274227422742274, "grad_norm": 4.454758167266846, "learning_rate": 3.733553579354205e-07, "loss": 0.398, "step": 2045 }, { "epoch": 1.228022802280228, "grad_norm": 4.992259502410889, "learning_rate": 3.751944406686488e-07, "loss": 0.3057, "step": 2046 }, { "epoch": 1.2286228622862287, "grad_norm": 5.469994068145752, "learning_rate": 3.7703699644354526e-07, "loss": 0.4174, "step": 2047 }, { "epoch": 1.2292229222922293, "grad_norm": 3.9419639110565186, "learning_rate": 3.7888301501808764e-07, "loss": 0.3447, "step": 2048 }, { "epoch": 1.2298229822982298, "grad_norm": 3.45694637298584, "learning_rate": 3.8073248613100493e-07, "loss": 0.2964, "step": 2049 }, { "epoch": 1.2304230423042304, "grad_norm": 4.986012935638428, "learning_rate": 3.825853995018333e-07, "loss": 0.228, "step": 2050 }, { "epoch": 1.231023102310231, "grad_norm": 3.6059744358062744, "learning_rate": 3.844417448309766e-07, "loss": 0.4159, "step": 2051 }, { "epoch": 1.2316231623162317, "grad_norm": 4.3036370277404785, "learning_rate": 3.86301511799761e-07, "loss": 0.3142, "step": 2052 }, { "epoch": 1.2322232223222322, "grad_norm": 5.026216983795166, "learning_rate": 3.8816469007049333e-07, "loss": 0.2779, "step": 2053 }, { "epoch": 1.2328232823282328, "grad_norm": 6.388001918792725, "learning_rate": 3.9003126928651853e-07, "loss": 0.4797, "step": 2054 }, { "epoch": 1.2334233423342333, "grad_norm": 4.256229400634766, "learning_rate": 3.919012390722773e-07, "loss": 0.3192, "step": 2055 }, { "epoch": 1.234023402340234, "grad_norm": 3.759974956512451, "learning_rate": 3.93774589033362e-07, "loss": 0.3246, "step": 2056 }, { "epoch": 1.2346234623462347, "grad_norm": 5.329896926879883, "learning_rate": 3.956513087565777e-07, "loss": 0.475, "step": 2057 }, { "epoch": 1.2352235223522352, "grad_norm": 5.569324970245361, "learning_rate": 3.9753138780999764e-07, "loss": 0.4151, "step": 2058 }, { "epoch": 1.2358235823582358, "grad_norm": 5.500924587249756, "learning_rate": 3.9941481574302185e-07, "loss": 0.5047, "step": 2059 }, { "epoch": 1.2364236423642365, "grad_norm": 3.557201623916626, "learning_rate": 4.0130158208643547e-07, "loss": 0.2305, "step": 2060 }, { "epoch": 1.237023702370237, "grad_norm": 4.394381523132324, "learning_rate": 4.0319167635246686e-07, "loss": 0.361, "step": 2061 }, { "epoch": 1.2376237623762376, "grad_norm": 4.781425952911377, "learning_rate": 4.050850880348461e-07, "loss": 0.4573, "step": 2062 }, { "epoch": 1.2382238223822382, "grad_norm": 3.713883399963379, "learning_rate": 4.069818066088614e-07, "loss": 0.2375, "step": 2063 }, { "epoch": 1.238823882388239, "grad_norm": 5.826539039611816, "learning_rate": 4.0888182153142104e-07, "loss": 0.5364, "step": 2064 }, { "epoch": 1.2394239423942395, "grad_norm": 5.371861934661865, "learning_rate": 4.1078512224110997e-07, "loss": 0.4849, "step": 2065 }, { "epoch": 1.24002400240024, "grad_norm": 3.308152914047241, "learning_rate": 4.1269169815824824e-07, "loss": 0.269, "step": 2066 }, { "epoch": 1.2406240624062406, "grad_norm": 4.685562610626221, "learning_rate": 4.1460153868495085e-07, "loss": 0.3399, "step": 2067 }, { "epoch": 1.2412241224122411, "grad_norm": 5.954644203186035, "learning_rate": 4.165146332051858e-07, "loss": 0.3653, "step": 2068 }, { "epoch": 1.2418241824182419, "grad_norm": 5.938551902770996, "learning_rate": 4.1843097108483437e-07, "loss": 0.4182, "step": 2069 }, { "epoch": 1.2424242424242424, "grad_norm": 3.288172483444214, "learning_rate": 4.203505416717471e-07, "loss": 0.3012, "step": 2070 }, { "epoch": 1.243024302430243, "grad_norm": 4.077911376953125, "learning_rate": 4.2227333429580726e-07, "loss": 0.3247, "step": 2071 }, { "epoch": 1.2436243624362437, "grad_norm": 4.342823505401611, "learning_rate": 4.2419933826898837e-07, "loss": 0.253, "step": 2072 }, { "epoch": 1.2442244224422443, "grad_norm": 4.3880295753479, "learning_rate": 4.2612854288541023e-07, "loss": 0.3451, "step": 2073 }, { "epoch": 1.2448244824482448, "grad_norm": 3.8655853271484375, "learning_rate": 4.280609374214059e-07, "loss": 0.3393, "step": 2074 }, { "epoch": 1.2454245424542454, "grad_norm": 4.732914447784424, "learning_rate": 4.299965111355752e-07, "loss": 0.3905, "step": 2075 }, { "epoch": 1.246024602460246, "grad_norm": 4.188107490539551, "learning_rate": 4.3193525326884405e-07, "loss": 0.3542, "step": 2076 }, { "epoch": 1.2466246624662467, "grad_norm": 3.8000123500823975, "learning_rate": 4.338771530445292e-07, "loss": 0.3901, "step": 2077 }, { "epoch": 1.2472247224722472, "grad_norm": 5.113257884979248, "learning_rate": 4.3582219966839505e-07, "loss": 0.3447, "step": 2078 }, { "epoch": 1.2478247824782478, "grad_norm": 4.550747394561768, "learning_rate": 4.3777038232871177e-07, "loss": 0.2693, "step": 2079 }, { "epoch": 1.2484248424842483, "grad_norm": 3.8475115299224854, "learning_rate": 4.39721690196319e-07, "loss": 0.2767, "step": 2080 }, { "epoch": 1.2490249024902491, "grad_norm": 5.054899215698242, "learning_rate": 4.4167611242468617e-07, "loss": 0.5251, "step": 2081 }, { "epoch": 1.2496249624962497, "grad_norm": 4.598382472991943, "learning_rate": 4.436336381499699e-07, "loss": 0.3169, "step": 2082 }, { "epoch": 1.2502250225022502, "grad_norm": 4.617363452911377, "learning_rate": 4.4559425649107385e-07, "loss": 0.397, "step": 2083 }, { "epoch": 1.2508250825082508, "grad_norm": 5.570669174194336, "learning_rate": 4.475579565497136e-07, "loss": 0.4604, "step": 2084 }, { "epoch": 1.2514251425142513, "grad_norm": 4.532995700836182, "learning_rate": 4.495247274104749e-07, "loss": 0.298, "step": 2085 }, { "epoch": 1.252025202520252, "grad_norm": 5.000243186950684, "learning_rate": 4.5149455814087137e-07, "loss": 0.4193, "step": 2086 }, { "epoch": 1.2526252625262526, "grad_norm": 3.963366985321045, "learning_rate": 4.534674377914106e-07, "loss": 0.2896, "step": 2087 }, { "epoch": 1.2532253225322532, "grad_norm": 4.32859468460083, "learning_rate": 4.5544335539565184e-07, "loss": 0.2828, "step": 2088 }, { "epoch": 1.253825382538254, "grad_norm": 3.2547664642333984, "learning_rate": 4.5742229997026725e-07, "loss": 0.2521, "step": 2089 }, { "epoch": 1.2544254425442545, "grad_norm": 5.955310821533203, "learning_rate": 4.594042605151037e-07, "loss": 0.2494, "step": 2090 }, { "epoch": 1.255025502550255, "grad_norm": 5.1886420249938965, "learning_rate": 4.613892260132433e-07, "loss": 0.432, "step": 2091 }, { "epoch": 1.2556255625562556, "grad_norm": 6.749106407165527, "learning_rate": 4.633771854310653e-07, "loss": 0.3984, "step": 2092 }, { "epoch": 1.2562256225622561, "grad_norm": 4.0624494552612305, "learning_rate": 4.6536812771830514e-07, "loss": 0.2257, "step": 2093 }, { "epoch": 1.2568256825682569, "grad_norm": 3.9786441326141357, "learning_rate": 4.673620418081198e-07, "loss": 0.3382, "step": 2094 }, { "epoch": 1.2574257425742574, "grad_norm": 5.8465471267700195, "learning_rate": 4.6935891661714646e-07, "loss": 0.2849, "step": 2095 }, { "epoch": 1.258025802580258, "grad_norm": 5.386751174926758, "learning_rate": 4.713587410455646e-07, "loss": 0.4003, "step": 2096 }, { "epoch": 1.2586258625862587, "grad_norm": 4.6902384757995605, "learning_rate": 4.733615039771586e-07, "loss": 0.4182, "step": 2097 }, { "epoch": 1.2592259225922593, "grad_norm": 3.6178998947143555, "learning_rate": 4.753671942793789e-07, "loss": 0.4658, "step": 2098 }, { "epoch": 1.2598259825982598, "grad_norm": 5.463256359100342, "learning_rate": 4.77375800803402e-07, "loss": 0.3252, "step": 2099 }, { "epoch": 1.2604260426042604, "grad_norm": 5.568304061889648, "learning_rate": 4.793873123841966e-07, "loss": 0.4205, "step": 2100 }, { "epoch": 1.261026102610261, "grad_norm": 1.545020341873169, "learning_rate": 4.814017178405826e-07, "loss": 0.1675, "step": 2101 }, { "epoch": 1.2616261626162617, "grad_norm": 3.686657667160034, "learning_rate": 4.834190059752938e-07, "loss": 0.2425, "step": 2102 }, { "epoch": 1.2622262226222623, "grad_norm": 4.826624870300293, "learning_rate": 4.854391655750404e-07, "loss": 0.5084, "step": 2103 }, { "epoch": 1.2628262826282628, "grad_norm": 5.708410263061523, "learning_rate": 4.874621854105716e-07, "loss": 0.5322, "step": 2104 }, { "epoch": 1.2634263426342633, "grad_norm": 6.040762901306152, "learning_rate": 4.89488054236738e-07, "loss": 0.445, "step": 2105 }, { "epoch": 1.2640264026402641, "grad_norm": 4.535456657409668, "learning_rate": 4.91516760792552e-07, "loss": 0.2654, "step": 2106 }, { "epoch": 1.2646264626462647, "grad_norm": 3.3325045108795166, "learning_rate": 4.935482938012542e-07, "loss": 0.271, "step": 2107 }, { "epoch": 1.2652265226522652, "grad_norm": 3.5051441192626953, "learning_rate": 4.955826419703732e-07, "loss": 0.2072, "step": 2108 }, { "epoch": 1.2658265826582658, "grad_norm": 4.30210018157959, "learning_rate": 4.976197939917896e-07, "loss": 0.5337, "step": 2109 }, { "epoch": 1.2664266426642663, "grad_norm": 5.143555641174316, "learning_rate": 4.996597385417985e-07, "loss": 0.4229, "step": 2110 }, { "epoch": 1.267026702670267, "grad_norm": 3.4103572368621826, "learning_rate": 5.01702464281173e-07, "loss": 0.2546, "step": 2111 }, { "epoch": 1.2676267626762676, "grad_norm": 4.631304740905762, "learning_rate": 5.037479598552243e-07, "loss": 0.3807, "step": 2112 }, { "epoch": 1.2682268226822682, "grad_norm": 6.192403316497803, "learning_rate": 5.057962138938699e-07, "loss": 0.3357, "step": 2113 }, { "epoch": 1.268826882688269, "grad_norm": 4.6526994705200195, "learning_rate": 5.078472150116939e-07, "loss": 0.2581, "step": 2114 }, { "epoch": 1.2694269426942695, "grad_norm": 5.391218662261963, "learning_rate": 5.099009518080073e-07, "loss": 0.3871, "step": 2115 }, { "epoch": 1.27002700270027, "grad_norm": 6.1139421463012695, "learning_rate": 5.119574128669194e-07, "loss": 0.3788, "step": 2116 }, { "epoch": 1.2706270627062706, "grad_norm": 4.857326030731201, "learning_rate": 5.140165867573934e-07, "loss": 0.385, "step": 2117 }, { "epoch": 1.2712271227122711, "grad_norm": 4.3262434005737305, "learning_rate": 5.160784620333139e-07, "loss": 0.3234, "step": 2118 }, { "epoch": 1.2718271827182719, "grad_norm": 3.816222667694092, "learning_rate": 5.181430272335483e-07, "loss": 0.2679, "step": 2119 }, { "epoch": 1.2724272427242724, "grad_norm": 3.4641263484954834, "learning_rate": 5.202102708820133e-07, "loss": 0.4522, "step": 2120 }, { "epoch": 1.273027302730273, "grad_norm": 3.749638795852661, "learning_rate": 5.222801814877375e-07, "loss": 0.4591, "step": 2121 }, { "epoch": 1.2736273627362737, "grad_norm": 3.027991771697998, "learning_rate": 5.243527475449216e-07, "loss": 0.2112, "step": 2122 }, { "epoch": 1.2742274227422743, "grad_norm": 5.493477821350098, "learning_rate": 5.26427957533011e-07, "loss": 0.4187, "step": 2123 }, { "epoch": 1.2748274827482748, "grad_norm": 4.637261867523193, "learning_rate": 5.285057999167513e-07, "loss": 0.2913, "step": 2124 }, { "epoch": 1.2754275427542754, "grad_norm": 5.213507652282715, "learning_rate": 5.30586263146255e-07, "loss": 0.3929, "step": 2125 }, { "epoch": 1.276027602760276, "grad_norm": 5.243996620178223, "learning_rate": 5.326693356570684e-07, "loss": 0.3631, "step": 2126 }, { "epoch": 1.2766276627662767, "grad_norm": 4.011785507202148, "learning_rate": 5.347550058702326e-07, "loss": 0.4053, "step": 2127 }, { "epoch": 1.2772277227722773, "grad_norm": 4.91314697265625, "learning_rate": 5.368432621923506e-07, "loss": 0.301, "step": 2128 }, { "epoch": 1.2778277827782778, "grad_norm": 5.193929195404053, "learning_rate": 5.389340930156477e-07, "loss": 0.4135, "step": 2129 }, { "epoch": 1.2784278427842783, "grad_norm": 4.20713996887207, "learning_rate": 5.4102748671804e-07, "loss": 0.2956, "step": 2130 }, { "epoch": 1.2790279027902791, "grad_norm": 4.59650993347168, "learning_rate": 5.431234316632e-07, "loss": 0.3354, "step": 2131 }, { "epoch": 1.2796279627962797, "grad_norm": 3.9051272869110107, "learning_rate": 5.452219162006143e-07, "loss": 0.3769, "step": 2132 }, { "epoch": 1.2802280228022802, "grad_norm": 4.7240519523620605, "learning_rate": 5.473229286656559e-07, "loss": 0.3153, "step": 2133 }, { "epoch": 1.2808280828082808, "grad_norm": 4.5497565269470215, "learning_rate": 5.494264573796461e-07, "loss": 0.2696, "step": 2134 }, { "epoch": 1.2814281428142813, "grad_norm": 4.58644437789917, "learning_rate": 5.515324906499172e-07, "loss": 0.1808, "step": 2135 }, { "epoch": 1.282028202820282, "grad_norm": 4.055230617523193, "learning_rate": 5.536410167698819e-07, "loss": 0.2677, "step": 2136 }, { "epoch": 1.2826282628262826, "grad_norm": 4.224995136260986, "learning_rate": 5.557520240190954e-07, "loss": 0.4342, "step": 2137 }, { "epoch": 1.2832283228322832, "grad_norm": 4.08761739730835, "learning_rate": 5.578655006633212e-07, "loss": 0.3288, "step": 2138 }, { "epoch": 1.283828382838284, "grad_norm": 4.118922233581543, "learning_rate": 5.599814349545967e-07, "loss": 0.4462, "step": 2139 }, { "epoch": 1.2844284428442845, "grad_norm": 3.7461812496185303, "learning_rate": 5.620998151312979e-07, "loss": 0.2894, "step": 2140 }, { "epoch": 1.285028502850285, "grad_norm": 4.536257266998291, "learning_rate": 5.64220629418206e-07, "loss": 0.4526, "step": 2141 }, { "epoch": 1.2856285628562856, "grad_norm": 5.254185199737549, "learning_rate": 5.663438660265698e-07, "loss": 0.3175, "step": 2142 }, { "epoch": 1.2862286228622861, "grad_norm": 3.6922614574432373, "learning_rate": 5.684695131541757e-07, "loss": 0.1761, "step": 2143 }, { "epoch": 1.2868286828682869, "grad_norm": 5.796041965484619, "learning_rate": 5.7059755898541e-07, "loss": 0.4258, "step": 2144 }, { "epoch": 1.2874287428742874, "grad_norm": 6.381557464599609, "learning_rate": 5.727279916913256e-07, "loss": 0.3868, "step": 2145 }, { "epoch": 1.288028802880288, "grad_norm": 3.811769723892212, "learning_rate": 5.74860799429708e-07, "loss": 0.4538, "step": 2146 }, { "epoch": 1.2886288628862888, "grad_norm": 4.4165358543396, "learning_rate": 5.769959703451415e-07, "loss": 0.2494, "step": 2147 }, { "epoch": 1.2892289228922893, "grad_norm": 5.28857946395874, "learning_rate": 5.791334925690718e-07, "loss": 0.2808, "step": 2148 }, { "epoch": 1.2898289828982898, "grad_norm": 4.419347286224365, "learning_rate": 5.812733542198775e-07, "loss": 0.3075, "step": 2149 }, { "epoch": 1.2904290429042904, "grad_norm": 4.370967864990234, "learning_rate": 5.834155434029322e-07, "loss": 0.343, "step": 2150 }, { "epoch": 1.291029102910291, "grad_norm": 4.844027042388916, "learning_rate": 5.855600482106718e-07, "loss": 0.3056, "step": 2151 }, { "epoch": 1.2916291629162917, "grad_norm": 4.535144805908203, "learning_rate": 5.877068567226602e-07, "loss": 0.3688, "step": 2152 }, { "epoch": 1.2922292229222923, "grad_norm": 4.128986835479736, "learning_rate": 5.898559570056563e-07, "loss": 0.4009, "step": 2153 }, { "epoch": 1.2928292829282928, "grad_norm": 4.691926002502441, "learning_rate": 5.920073371136811e-07, "loss": 0.3468, "step": 2154 }, { "epoch": 1.2934293429342933, "grad_norm": 3.925499677658081, "learning_rate": 5.941609850880799e-07, "loss": 0.4481, "step": 2155 }, { "epoch": 1.2940294029402941, "grad_norm": 4.76969575881958, "learning_rate": 5.963168889575944e-07, "loss": 0.2844, "step": 2156 }, { "epoch": 1.2946294629462947, "grad_norm": 6.361873626708984, "learning_rate": 5.984750367384263e-07, "loss": 0.3272, "step": 2157 }, { "epoch": 1.2952295229522952, "grad_norm": 4.27789306640625, "learning_rate": 6.006354164343039e-07, "loss": 0.43, "step": 2158 }, { "epoch": 1.2958295829582958, "grad_norm": 3.1931936740875244, "learning_rate": 6.027980160365494e-07, "loss": 0.2242, "step": 2159 }, { "epoch": 1.2964296429642963, "grad_norm": 5.060121536254883, "learning_rate": 6.049628235241461e-07, "loss": 0.3612, "step": 2160 }, { "epoch": 1.297029702970297, "grad_norm": 4.092342853546143, "learning_rate": 6.071298268638021e-07, "loss": 0.2638, "step": 2161 }, { "epoch": 1.2976297629762976, "grad_norm": 3.4008400440216064, "learning_rate": 6.092990140100222e-07, "loss": 0.259, "step": 2162 }, { "epoch": 1.2982298229822982, "grad_norm": 4.700977325439453, "learning_rate": 6.114703729051714e-07, "loss": 0.267, "step": 2163 }, { "epoch": 1.298829882988299, "grad_norm": 3.622107744216919, "learning_rate": 6.13643891479543e-07, "loss": 0.237, "step": 2164 }, { "epoch": 1.2994299429942995, "grad_norm": 5.265900611877441, "learning_rate": 6.158195576514255e-07, "loss": 0.428, "step": 2165 }, { "epoch": 1.3000300030003, "grad_norm": 6.067828178405762, "learning_rate": 6.179973593271694e-07, "loss": 0.4211, "step": 2166 }, { "epoch": 1.3006300630063006, "grad_norm": 5.350322246551514, "learning_rate": 6.20177284401256e-07, "loss": 0.4227, "step": 2167 }, { "epoch": 1.3012301230123011, "grad_norm": 3.7556192874908447, "learning_rate": 6.223593207563611e-07, "loss": 0.3914, "step": 2168 }, { "epoch": 1.301830183018302, "grad_norm": 2.6125943660736084, "learning_rate": 6.245434562634266e-07, "loss": 0.3043, "step": 2169 }, { "epoch": 1.3024302430243024, "grad_norm": 3.2942287921905518, "learning_rate": 6.267296787817269e-07, "loss": 0.1586, "step": 2170 }, { "epoch": 1.303030303030303, "grad_norm": 4.989749431610107, "learning_rate": 6.289179761589324e-07, "loss": 0.3522, "step": 2171 }, { "epoch": 1.3036303630363038, "grad_norm": 4.096138000488281, "learning_rate": 6.311083362311822e-07, "loss": 0.2581, "step": 2172 }, { "epoch": 1.3042304230423043, "grad_norm": 4.123734951019287, "learning_rate": 6.333007468231512e-07, "loss": 0.4099, "step": 2173 }, { "epoch": 1.3048304830483048, "grad_norm": 5.298449993133545, "learning_rate": 6.354951957481147e-07, "loss": 0.4087, "step": 2174 }, { "epoch": 1.3054305430543054, "grad_norm": 5.057365894317627, "learning_rate": 6.376916708080162e-07, "loss": 0.3221, "step": 2175 }, { "epoch": 1.306030603060306, "grad_norm": 4.316713333129883, "learning_rate": 6.398901597935389e-07, "loss": 0.3413, "step": 2176 }, { "epoch": 1.3066306630663067, "grad_norm": 4.799070835113525, "learning_rate": 6.420906504841719e-07, "loss": 0.2698, "step": 2177 }, { "epoch": 1.3072307230723073, "grad_norm": 4.032698154449463, "learning_rate": 6.442931306482745e-07, "loss": 0.3539, "step": 2178 }, { "epoch": 1.3078307830783078, "grad_norm": 3.3918819427490234, "learning_rate": 6.464975880431496e-07, "loss": 0.271, "step": 2179 }, { "epoch": 1.3084308430843083, "grad_norm": 4.34944486618042, "learning_rate": 6.487040104151113e-07, "loss": 0.3964, "step": 2180 }, { "epoch": 1.3090309030903091, "grad_norm": 5.068617343902588, "learning_rate": 6.509123854995471e-07, "loss": 0.3252, "step": 2181 }, { "epoch": 1.3096309630963097, "grad_norm": 6.17050313949585, "learning_rate": 6.531227010209926e-07, "loss": 0.2743, "step": 2182 }, { "epoch": 1.3102310231023102, "grad_norm": 5.300081729888916, "learning_rate": 6.553349446931977e-07, "loss": 0.4412, "step": 2183 }, { "epoch": 1.3108310831083108, "grad_norm": 3.9822301864624023, "learning_rate": 6.575491042191921e-07, "loss": 0.4468, "step": 2184 }, { "epoch": 1.3114311431143113, "grad_norm": 4.632898807525635, "learning_rate": 6.597651672913585e-07, "loss": 0.3802, "step": 2185 }, { "epoch": 1.312031203120312, "grad_norm": 5.178798675537109, "learning_rate": 6.619831215914971e-07, "loss": 0.4548, "step": 2186 }, { "epoch": 1.3126312631263126, "grad_norm": 4.187036991119385, "learning_rate": 6.642029547908966e-07, "loss": 0.3862, "step": 2187 }, { "epoch": 1.3132313231323132, "grad_norm": 5.641260623931885, "learning_rate": 6.664246545504009e-07, "loss": 0.5075, "step": 2188 }, { "epoch": 1.313831383138314, "grad_norm": 5.355376243591309, "learning_rate": 6.686482085204787e-07, "loss": 0.5606, "step": 2189 }, { "epoch": 1.3144314431443145, "grad_norm": 3.975053071975708, "learning_rate": 6.708736043412926e-07, "loss": 0.2867, "step": 2190 }, { "epoch": 1.315031503150315, "grad_norm": 3.987560272216797, "learning_rate": 6.731008296427646e-07, "loss": 0.2877, "step": 2191 }, { "epoch": 1.3156315631563156, "grad_norm": 5.818557262420654, "learning_rate": 6.753298720446501e-07, "loss": 0.355, "step": 2192 }, { "epoch": 1.3162316231623161, "grad_norm": 6.747314929962158, "learning_rate": 6.775607191566029e-07, "loss": 0.4101, "step": 2193 }, { "epoch": 1.316831683168317, "grad_norm": 4.0721635818481445, "learning_rate": 6.797933585782453e-07, "loss": 0.2405, "step": 2194 }, { "epoch": 1.3174317431743174, "grad_norm": 5.879698753356934, "learning_rate": 6.820277778992367e-07, "loss": 0.2403, "step": 2195 }, { "epoch": 1.318031803180318, "grad_norm": 3.0907132625579834, "learning_rate": 6.842639646993429e-07, "loss": 0.2328, "step": 2196 }, { "epoch": 1.3186318631863188, "grad_norm": 5.118244171142578, "learning_rate": 6.865019065485057e-07, "loss": 0.312, "step": 2197 }, { "epoch": 1.3192319231923193, "grad_norm": 2.4529709815979004, "learning_rate": 6.88741591006909e-07, "loss": 0.2689, "step": 2198 }, { "epoch": 1.3198319831983198, "grad_norm": 3.8394737243652344, "learning_rate": 6.909830056250524e-07, "loss": 0.2825, "step": 2199 }, { "epoch": 1.3204320432043204, "grad_norm": 3.4160969257354736, "learning_rate": 6.932261379438178e-07, "loss": 0.2243, "step": 2200 }, { "epoch": 1.321032103210321, "grad_norm": 3.7807748317718506, "learning_rate": 6.954709754945389e-07, "loss": 0.2111, "step": 2201 }, { "epoch": 1.3216321632163217, "grad_norm": 5.097783088684082, "learning_rate": 6.977175057990707e-07, "loss": 0.3624, "step": 2202 }, { "epoch": 1.3222322232223223, "grad_norm": 3.7680740356445312, "learning_rate": 6.999657163698597e-07, "loss": 0.2021, "step": 2203 }, { "epoch": 1.3228322832283228, "grad_norm": 6.11716365814209, "learning_rate": 7.0221559471001e-07, "loss": 0.2567, "step": 2204 }, { "epoch": 1.3234323432343233, "grad_norm": 4.431899070739746, "learning_rate": 7.044671283133578e-07, "loss": 0.2399, "step": 2205 }, { "epoch": 1.3240324032403241, "grad_norm": 5.304899215698242, "learning_rate": 7.067203046645382e-07, "loss": 0.2184, "step": 2206 }, { "epoch": 1.3246324632463247, "grad_norm": 3.9548728466033936, "learning_rate": 7.089751112390517e-07, "loss": 0.36, "step": 2207 }, { "epoch": 1.3252325232523252, "grad_norm": 4.45819091796875, "learning_rate": 7.112315355033421e-07, "loss": 0.3295, "step": 2208 }, { "epoch": 1.3258325832583258, "grad_norm": 6.525112152099609, "learning_rate": 7.134895649148578e-07, "loss": 0.4453, "step": 2209 }, { "epoch": 1.3264326432643263, "grad_norm": 4.037824630737305, "learning_rate": 7.157491869221263e-07, "loss": 0.3061, "step": 2210 }, { "epoch": 1.327032703270327, "grad_norm": 1.8174883127212524, "learning_rate": 7.180103889648202e-07, "loss": 0.1672, "step": 2211 }, { "epoch": 1.3276327632763276, "grad_norm": 5.967132568359375, "learning_rate": 7.202731584738318e-07, "loss": 0.3971, "step": 2212 }, { "epoch": 1.3282328232823282, "grad_norm": 4.709994792938232, "learning_rate": 7.225374828713403e-07, "loss": 0.2383, "step": 2213 }, { "epoch": 1.328832883288329, "grad_norm": 6.602879524230957, "learning_rate": 7.248033495708787e-07, "loss": 0.263, "step": 2214 }, { "epoch": 1.3294329432943295, "grad_norm": 6.014041900634766, "learning_rate": 7.270707459774123e-07, "loss": 0.4318, "step": 2215 }, { "epoch": 1.33003300330033, "grad_norm": 6.092250347137451, "learning_rate": 7.293396594874001e-07, "loss": 0.3555, "step": 2216 }, { "epoch": 1.3306330633063306, "grad_norm": 3.2950382232666016, "learning_rate": 7.316100774888674e-07, "loss": 0.2422, "step": 2217 }, { "epoch": 1.3312331233123311, "grad_norm": 5.318734169006348, "learning_rate": 7.338819873614783e-07, "loss": 0.4265, "step": 2218 }, { "epoch": 1.331833183318332, "grad_norm": 4.26210355758667, "learning_rate": 7.361553764766038e-07, "loss": 0.3536, "step": 2219 }, { "epoch": 1.3324332433243324, "grad_norm": 7.376886367797852, "learning_rate": 7.384302321973931e-07, "loss": 0.4294, "step": 2220 }, { "epoch": 1.333033303330333, "grad_norm": 4.9695963859558105, "learning_rate": 7.407065418788407e-07, "loss": 0.3939, "step": 2221 }, { "epoch": 1.3336333633363338, "grad_norm": 5.367372512817383, "learning_rate": 7.429842928678609e-07, "loss": 0.3565, "step": 2222 }, { "epoch": 1.3342334233423343, "grad_norm": 4.371079921722412, "learning_rate": 7.452634725033588e-07, "loss": 0.347, "step": 2223 }, { "epoch": 1.3348334833483348, "grad_norm": 3.2690489292144775, "learning_rate": 7.475440681162928e-07, "loss": 0.2622, "step": 2224 }, { "epoch": 1.3354335433543354, "grad_norm": 4.033148288726807, "learning_rate": 7.498260670297543e-07, "loss": 0.2308, "step": 2225 }, { "epoch": 1.336033603360336, "grad_norm": 4.958217144012451, "learning_rate": 7.521094565590341e-07, "loss": 0.3461, "step": 2226 }, { "epoch": 1.3366336633663367, "grad_norm": 3.5270307064056396, "learning_rate": 7.543942240116908e-07, "loss": 0.3956, "step": 2227 }, { "epoch": 1.3372337233723373, "grad_norm": 2.944647789001465, "learning_rate": 7.56680356687626e-07, "loss": 0.1833, "step": 2228 }, { "epoch": 1.3378337833783378, "grad_norm": 4.970795631408691, "learning_rate": 7.589678418791518e-07, "loss": 0.3059, "step": 2229 }, { "epoch": 1.3384338433843384, "grad_norm": 4.47990608215332, "learning_rate": 7.612566668710622e-07, "loss": 0.3927, "step": 2230 }, { "epoch": 1.3390339033903391, "grad_norm": 3.284497022628784, "learning_rate": 7.635468189407038e-07, "loss": 0.2234, "step": 2231 }, { "epoch": 1.3396339633963397, "grad_norm": 4.815840244293213, "learning_rate": 7.658382853580466e-07, "loss": 0.4702, "step": 2232 }, { "epoch": 1.3402340234023402, "grad_norm": 6.06868314743042, "learning_rate": 7.681310533857552e-07, "loss": 0.5363, "step": 2233 }, { "epoch": 1.3408340834083408, "grad_norm": 5.411320686340332, "learning_rate": 7.704251102792571e-07, "loss": 0.296, "step": 2234 }, { "epoch": 1.3414341434143413, "grad_norm": 4.458423137664795, "learning_rate": 7.727204432868175e-07, "loss": 0.3212, "step": 2235 }, { "epoch": 1.342034203420342, "grad_norm": 4.521159648895264, "learning_rate": 7.750170396496077e-07, "loss": 0.45, "step": 2236 }, { "epoch": 1.3426342634263426, "grad_norm": 5.115608215332031, "learning_rate": 7.773148866017763e-07, "loss": 0.2537, "step": 2237 }, { "epoch": 1.3432343234323432, "grad_norm": 4.925377368927002, "learning_rate": 7.796139713705206e-07, "loss": 0.4297, "step": 2238 }, { "epoch": 1.343834383438344, "grad_norm": 5.449639320373535, "learning_rate": 7.81914281176158e-07, "loss": 0.4115, "step": 2239 }, { "epoch": 1.3444344434443445, "grad_norm": 7.538498878479004, "learning_rate": 7.84215803232194e-07, "loss": 0.5073, "step": 2240 }, { "epoch": 1.345034503450345, "grad_norm": 5.408720016479492, "learning_rate": 7.865185247453981e-07, "loss": 0.4773, "step": 2241 }, { "epoch": 1.3456345634563456, "grad_norm": 4.978492259979248, "learning_rate": 7.888224329158718e-07, "loss": 0.5156, "step": 2242 }, { "epoch": 1.3462346234623461, "grad_norm": 4.432305335998535, "learning_rate": 7.911275149371206e-07, "loss": 0.3113, "step": 2243 }, { "epoch": 1.346834683468347, "grad_norm": 4.166386604309082, "learning_rate": 7.934337579961247e-07, "loss": 0.2464, "step": 2244 }, { "epoch": 1.3474347434743474, "grad_norm": 4.212772369384766, "learning_rate": 7.957411492734106e-07, "loss": 0.2629, "step": 2245 }, { "epoch": 1.348034803480348, "grad_norm": 4.907623767852783, "learning_rate": 7.980496759431235e-07, "loss": 0.3622, "step": 2246 }, { "epoch": 1.3486348634863488, "grad_norm": 3.535745143890381, "learning_rate": 8.003593251730945e-07, "loss": 0.2236, "step": 2247 }, { "epoch": 1.3492349234923493, "grad_norm": 4.342034339904785, "learning_rate": 8.026700841249175e-07, "loss": 0.1754, "step": 2248 }, { "epoch": 1.3498349834983498, "grad_norm": 4.662349224090576, "learning_rate": 8.049819399540173e-07, "loss": 0.3398, "step": 2249 }, { "epoch": 1.3504350435043504, "grad_norm": 5.725773334503174, "learning_rate": 8.072948798097212e-07, "loss": 0.4188, "step": 2250 }, { "epoch": 1.351035103510351, "grad_norm": 2.8462159633636475, "learning_rate": 8.09608890835331e-07, "loss": 0.3711, "step": 2251 }, { "epoch": 1.3516351635163517, "grad_norm": 5.729881763458252, "learning_rate": 8.119239601681953e-07, "loss": 0.3857, "step": 2252 }, { "epoch": 1.3522352235223523, "grad_norm": 5.395908355712891, "learning_rate": 8.142400749397772e-07, "loss": 0.486, "step": 2253 }, { "epoch": 1.3528352835283528, "grad_norm": 3.9597907066345215, "learning_rate": 8.165572222757313e-07, "loss": 0.3717, "step": 2254 }, { "epoch": 1.3534353435343534, "grad_norm": 4.793471336364746, "learning_rate": 8.188753892959719e-07, "loss": 0.373, "step": 2255 }, { "epoch": 1.3540354035403541, "grad_norm": 3.2296831607818604, "learning_rate": 8.211945631147448e-07, "loss": 0.2422, "step": 2256 }, { "epoch": 1.3546354635463547, "grad_norm": 4.0202860832214355, "learning_rate": 8.235147308407002e-07, "loss": 0.3335, "step": 2257 }, { "epoch": 1.3552355235523552, "grad_norm": 4.7178802490234375, "learning_rate": 8.258358795769628e-07, "loss": 0.3576, "step": 2258 }, { "epoch": 1.3558355835583558, "grad_norm": 4.321126461029053, "learning_rate": 8.281579964212054e-07, "loss": 0.4133, "step": 2259 }, { "epoch": 1.3564356435643563, "grad_norm": 5.921396732330322, "learning_rate": 8.304810684657171e-07, "loss": 0.3318, "step": 2260 }, { "epoch": 1.357035703570357, "grad_norm": 3.82661509513855, "learning_rate": 8.328050827974797e-07, "loss": 0.292, "step": 2261 }, { "epoch": 1.3576357635763576, "grad_norm": 3.7955000400543213, "learning_rate": 8.351300264982375e-07, "loss": 0.1909, "step": 2262 }, { "epoch": 1.3582358235823582, "grad_norm": 4.8397417068481445, "learning_rate": 8.37455886644566e-07, "loss": 0.3324, "step": 2263 }, { "epoch": 1.358835883588359, "grad_norm": 4.190946578979492, "learning_rate": 8.397826503079482e-07, "loss": 0.3542, "step": 2264 }, { "epoch": 1.3594359435943595, "grad_norm": 5.08449649810791, "learning_rate": 8.421103045548476e-07, "loss": 0.3373, "step": 2265 }, { "epoch": 1.36003600360036, "grad_norm": 4.833693981170654, "learning_rate": 8.444388364467724e-07, "loss": 0.3606, "step": 2266 }, { "epoch": 1.3606360636063606, "grad_norm": 6.814215183258057, "learning_rate": 8.46768233040355e-07, "loss": 0.4512, "step": 2267 }, { "epoch": 1.3612361236123611, "grad_norm": 6.072155475616455, "learning_rate": 8.490984813874212e-07, "loss": 0.3865, "step": 2268 }, { "epoch": 1.361836183618362, "grad_norm": 5.536653518676758, "learning_rate": 8.514295685350626e-07, "loss": 0.389, "step": 2269 }, { "epoch": 1.3624362436243624, "grad_norm": 4.764883518218994, "learning_rate": 8.537614815257058e-07, "loss": 0.2843, "step": 2270 }, { "epoch": 1.363036303630363, "grad_norm": 4.009110927581787, "learning_rate": 8.560942073971889e-07, "loss": 0.2559, "step": 2271 }, { "epoch": 1.3636363636363638, "grad_norm": 4.440279006958008, "learning_rate": 8.584277331828335e-07, "loss": 0.3359, "step": 2272 }, { "epoch": 1.3642364236423643, "grad_norm": 2.969604253768921, "learning_rate": 8.6076204591151e-07, "loss": 0.2472, "step": 2273 }, { "epoch": 1.3648364836483649, "grad_norm": 5.7347025871276855, "learning_rate": 8.630971326077182e-07, "loss": 0.3716, "step": 2274 }, { "epoch": 1.3654365436543654, "grad_norm": 3.68707013130188, "learning_rate": 8.654329802916553e-07, "loss": 0.2332, "step": 2275 }, { "epoch": 1.366036603660366, "grad_norm": 4.811226844787598, "learning_rate": 8.677695759792859e-07, "loss": 0.4856, "step": 2276 }, { "epoch": 1.3666366636663667, "grad_norm": 6.101363182067871, "learning_rate": 8.701069066824196e-07, "loss": 0.3815, "step": 2277 }, { "epoch": 1.3672367236723673, "grad_norm": 3.198434591293335, "learning_rate": 8.724449594087794e-07, "loss": 0.1856, "step": 2278 }, { "epoch": 1.3678367836783678, "grad_norm": 4.499966621398926, "learning_rate": 8.747837211620747e-07, "loss": 0.3271, "step": 2279 }, { "epoch": 1.3684368436843684, "grad_norm": 4.065590858459473, "learning_rate": 8.771231789420739e-07, "loss": 0.4207, "step": 2280 }, { "epoch": 1.3690369036903691, "grad_norm": 3.9055521488189697, "learning_rate": 8.794633197446764e-07, "loss": 0.2697, "step": 2281 }, { "epoch": 1.3696369636963697, "grad_norm": 4.243749618530273, "learning_rate": 8.818041305619857e-07, "loss": 0.2503, "step": 2282 }, { "epoch": 1.3702370237023702, "grad_norm": 5.13135290145874, "learning_rate": 8.841455983823787e-07, "loss": 0.2685, "step": 2283 }, { "epoch": 1.3708370837083708, "grad_norm": 3.9668266773223877, "learning_rate": 8.864877101905824e-07, "loss": 0.2439, "step": 2284 }, { "epoch": 1.3714371437143713, "grad_norm": 5.04547643661499, "learning_rate": 8.888304529677438e-07, "loss": 0.3233, "step": 2285 }, { "epoch": 1.372037203720372, "grad_norm": 5.038857936859131, "learning_rate": 8.911738136915022e-07, "loss": 0.3867, "step": 2286 }, { "epoch": 1.3726372637263726, "grad_norm": 3.4231040477752686, "learning_rate": 8.935177793360619e-07, "loss": 0.2924, "step": 2287 }, { "epoch": 1.3732373237323732, "grad_norm": 4.472795486450195, "learning_rate": 8.95862336872266e-07, "loss": 0.2792, "step": 2288 }, { "epoch": 1.373837383738374, "grad_norm": 4.7438530921936035, "learning_rate": 8.982074732676646e-07, "loss": 0.2993, "step": 2289 }, { "epoch": 1.3744374437443745, "grad_norm": 4.226728916168213, "learning_rate": 9.005531754865928e-07, "loss": 0.3108, "step": 2290 }, { "epoch": 1.375037503750375, "grad_norm": 5.270313739776611, "learning_rate": 9.028994304902398e-07, "loss": 0.4749, "step": 2291 }, { "epoch": 1.3756375637563756, "grad_norm": 2.985684633255005, "learning_rate": 9.052462252367219e-07, "loss": 0.206, "step": 2292 }, { "epoch": 1.3762376237623761, "grad_norm": 3.9120731353759766, "learning_rate": 9.075935466811553e-07, "loss": 0.3394, "step": 2293 }, { "epoch": 1.376837683768377, "grad_norm": 6.73698091506958, "learning_rate": 9.099413817757283e-07, "loss": 0.6264, "step": 2294 }, { "epoch": 1.3774377437743774, "grad_norm": 7.90812349319458, "learning_rate": 9.122897174697754e-07, "loss": 0.3257, "step": 2295 }, { "epoch": 1.378037803780378, "grad_norm": 5.3014912605285645, "learning_rate": 9.146385407098451e-07, "loss": 0.4567, "step": 2296 }, { "epoch": 1.3786378637863788, "grad_norm": 5.114983558654785, "learning_rate": 9.169878384397791e-07, "loss": 0.4133, "step": 2297 }, { "epoch": 1.3792379237923793, "grad_norm": 3.7575511932373047, "learning_rate": 9.193375976007815e-07, "loss": 0.3508, "step": 2298 }, { "epoch": 1.3798379837983799, "grad_norm": 4.15044641494751, "learning_rate": 9.216878051314874e-07, "loss": 0.3149, "step": 2299 }, { "epoch": 1.3804380438043804, "grad_norm": 5.497995853424072, "learning_rate": 9.240384479680457e-07, "loss": 0.4094, "step": 2300 }, { "epoch": 1.381038103810381, "grad_norm": 5.3556060791015625, "learning_rate": 9.263895130441816e-07, "loss": 0.2746, "step": 2301 }, { "epoch": 1.3816381638163817, "grad_norm": 2.9663705825805664, "learning_rate": 9.287409872912751e-07, "loss": 0.3535, "step": 2302 }, { "epoch": 1.3822382238223823, "grad_norm": 4.666641712188721, "learning_rate": 9.310928576384291e-07, "loss": 0.2419, "step": 2303 }, { "epoch": 1.3828382838283828, "grad_norm": 4.489226818084717, "learning_rate": 9.334451110125474e-07, "loss": 0.266, "step": 2304 }, { "epoch": 1.3834383438343836, "grad_norm": 4.658074855804443, "learning_rate": 9.357977343384048e-07, "loss": 0.2952, "step": 2305 }, { "epoch": 1.3840384038403841, "grad_norm": 4.894852638244629, "learning_rate": 9.381507145387161e-07, "loss": 0.2757, "step": 2306 }, { "epoch": 1.3846384638463847, "grad_norm": 4.64509916305542, "learning_rate": 9.405040385342178e-07, "loss": 0.2911, "step": 2307 }, { "epoch": 1.3852385238523852, "grad_norm": 6.220283031463623, "learning_rate": 9.428576932437323e-07, "loss": 0.255, "step": 2308 }, { "epoch": 1.3858385838583858, "grad_norm": 4.727911949157715, "learning_rate": 9.452116655842426e-07, "loss": 0.5397, "step": 2309 }, { "epoch": 1.3864386438643863, "grad_norm": 3.139216661453247, "learning_rate": 9.475659424709681e-07, "loss": 0.1315, "step": 2310 }, { "epoch": 1.387038703870387, "grad_norm": 3.437000036239624, "learning_rate": 9.499205108174358e-07, "loss": 0.2846, "step": 2311 }, { "epoch": 1.3876387638763876, "grad_norm": 5.202695369720459, "learning_rate": 9.522753575355497e-07, "loss": 0.3477, "step": 2312 }, { "epoch": 1.3882388238823882, "grad_norm": 3.6444664001464844, "learning_rate": 9.546304695356692e-07, "loss": 0.2609, "step": 2313 }, { "epoch": 1.388838883888389, "grad_norm": 3.654184579849243, "learning_rate": 9.569858337266775e-07, "loss": 0.3084, "step": 2314 }, { "epoch": 1.3894389438943895, "grad_norm": 5.11837100982666, "learning_rate": 9.59341437016059e-07, "loss": 0.3046, "step": 2315 }, { "epoch": 1.39003900390039, "grad_norm": 4.502711772918701, "learning_rate": 9.616972663099644e-07, "loss": 0.3832, "step": 2316 }, { "epoch": 1.3906390639063906, "grad_norm": 3.9008920192718506, "learning_rate": 9.640533085132912e-07, "loss": 0.3805, "step": 2317 }, { "epoch": 1.3912391239123911, "grad_norm": 5.247098922729492, "learning_rate": 9.664095505297536e-07, "loss": 0.3748, "step": 2318 }, { "epoch": 1.391839183918392, "grad_norm": 4.456699371337891, "learning_rate": 9.687659792619524e-07, "loss": 0.3013, "step": 2319 }, { "epoch": 1.3924392439243924, "grad_norm": 52.29407501220703, "learning_rate": 9.711225816114531e-07, "loss": 0.7068, "step": 2320 }, { "epoch": 1.393039303930393, "grad_norm": 244.79006958007812, "learning_rate": 9.734793444788558e-07, "loss": 1.242, "step": 2321 }, { "epoch": 1.3936393639363938, "grad_norm": 3.7335801124572754, "learning_rate": 9.758362547638675e-07, "loss": 0.6954, "step": 2322 }, { "epoch": 1.3942394239423943, "grad_norm": 33.20928955078125, "learning_rate": 9.781932993653763e-07, "loss": 0.7254, "step": 2323 }, { "epoch": 1.3948394839483949, "grad_norm": 17.70500946044922, "learning_rate": 9.805504651815234e-07, "loss": 0.3748, "step": 2324 }, { "epoch": 1.3954395439543954, "grad_norm": 4.928797721862793, "learning_rate": 9.829077391097773e-07, "loss": 0.2818, "step": 2325 }, { "epoch": 1.396039603960396, "grad_norm": 4.4264655113220215, "learning_rate": 9.852651080470033e-07, "loss": 0.2394, "step": 2326 }, { "epoch": 1.3966396639663967, "grad_norm": 26.290128707885742, "learning_rate": 9.876225588895402e-07, "loss": 0.4385, "step": 2327 }, { "epoch": 1.3972397239723973, "grad_norm": 4.8813982009887695, "learning_rate": 9.899800785332714e-07, "loss": 0.4269, "step": 2328 }, { "epoch": 1.3978397839783978, "grad_norm": 5.35105037689209, "learning_rate": 9.923376538736979e-07, "loss": 0.2892, "step": 2329 }, { "epoch": 1.3984398439843986, "grad_norm": 6.719480991363525, "learning_rate": 9.946952718060108e-07, "loss": 0.4126, "step": 2330 }, { "epoch": 1.3990399039903991, "grad_norm": 4.0741868019104, "learning_rate": 9.970529192251652e-07, "loss": 0.2367, "step": 2331 }, { "epoch": 1.3996399639963997, "grad_norm": 4.72567892074585, "learning_rate": 9.994105830259502e-07, "loss": 0.3055, "step": 2332 }, { "epoch": 1.4002400240024002, "grad_norm": 4.751362323760986, "learning_rate": 1.0017682501030662e-06, "loss": 0.3755, "step": 2333 }, { "epoch": 1.4008400840084008, "grad_norm": 4.735274314880371, "learning_rate": 1.0041259073511942e-06, "loss": 0.384, "step": 2334 }, { "epoch": 1.4014401440144013, "grad_norm": 5.158254146575928, "learning_rate": 1.0064835416650699e-06, "loss": 0.2984, "step": 2335 }, { "epoch": 1.402040204020402, "grad_norm": 6.91745662689209, "learning_rate": 1.0088411399395571e-06, "loss": 0.355, "step": 2336 }, { "epoch": 1.4026402640264026, "grad_norm": 4.870142936706543, "learning_rate": 1.0111986890697195e-06, "loss": 0.3157, "step": 2337 }, { "epoch": 1.4032403240324032, "grad_norm": 5.65952730178833, "learning_rate": 1.0135561759508947e-06, "loss": 0.3154, "step": 2338 }, { "epoch": 1.403840384038404, "grad_norm": 5.273636817932129, "learning_rate": 1.015913587478764e-06, "loss": 0.4628, "step": 2339 }, { "epoch": 1.4044404440444045, "grad_norm": 5.292807102203369, "learning_rate": 1.0182709105494298e-06, "loss": 0.3823, "step": 2340 }, { "epoch": 1.405040504050405, "grad_norm": 4.126208305358887, "learning_rate": 1.0206281320594859e-06, "loss": 0.4269, "step": 2341 }, { "epoch": 1.4056405640564056, "grad_norm": 4.461047172546387, "learning_rate": 1.02298523890609e-06, "loss": 0.3086, "step": 2342 }, { "epoch": 1.4062406240624061, "grad_norm": 5.248376369476318, "learning_rate": 1.0253422179870374e-06, "loss": 0.453, "step": 2343 }, { "epoch": 1.406840684068407, "grad_norm": 7.17417573928833, "learning_rate": 1.027699056200835e-06, "loss": 0.5971, "step": 2344 }, { "epoch": 1.4074407440744074, "grad_norm": 4.715506076812744, "learning_rate": 1.030055740446769e-06, "loss": 0.3611, "step": 2345 }, { "epoch": 1.408040804080408, "grad_norm": 5.4566969871521, "learning_rate": 1.0324122576249853e-06, "loss": 0.4538, "step": 2346 }, { "epoch": 1.4086408640864088, "grad_norm": 2.8033580780029297, "learning_rate": 1.034768594636557e-06, "loss": 0.215, "step": 2347 }, { "epoch": 1.4092409240924093, "grad_norm": 4.431277751922607, "learning_rate": 1.037124738383558e-06, "loss": 0.3002, "step": 2348 }, { "epoch": 1.4098409840984099, "grad_norm": 3.8191003799438477, "learning_rate": 1.0394806757691377e-06, "loss": 0.2614, "step": 2349 }, { "epoch": 1.4104410441044104, "grad_norm": 5.007168769836426, "learning_rate": 1.0418363936975919e-06, "loss": 0.2708, "step": 2350 }, { "epoch": 1.411041104110411, "grad_norm": 4.430918216705322, "learning_rate": 1.044191879074437e-06, "loss": 0.228, "step": 2351 }, { "epoch": 1.4116411641164117, "grad_norm": 4.2147746086120605, "learning_rate": 1.0465471188064803e-06, "loss": 0.4043, "step": 2352 }, { "epoch": 1.4122412241224123, "grad_norm": 2.841273307800293, "learning_rate": 1.048902099801896e-06, "loss": 0.4469, "step": 2353 }, { "epoch": 1.4128412841284128, "grad_norm": 3.569561243057251, "learning_rate": 1.0512568089702974e-06, "loss": 0.3169, "step": 2354 }, { "epoch": 1.4134413441344136, "grad_norm": 4.855161190032959, "learning_rate": 1.0536112332228058e-06, "loss": 0.2223, "step": 2355 }, { "epoch": 1.4140414041404141, "grad_norm": 4.644065856933594, "learning_rate": 1.0559653594721279e-06, "loss": 0.3654, "step": 2356 }, { "epoch": 1.4146414641464147, "grad_norm": 3.243558883666992, "learning_rate": 1.0583191746326296e-06, "loss": 0.228, "step": 2357 }, { "epoch": 1.4152415241524152, "grad_norm": 5.021285533905029, "learning_rate": 1.0606726656204014e-06, "loss": 0.3779, "step": 2358 }, { "epoch": 1.4158415841584158, "grad_norm": 4.795617580413818, "learning_rate": 1.0630258193533374e-06, "loss": 0.3209, "step": 2359 }, { "epoch": 1.4164416441644163, "grad_norm": 5.078552722930908, "learning_rate": 1.0653786227512079e-06, "loss": 0.2207, "step": 2360 }, { "epoch": 1.417041704170417, "grad_norm": 3.3108856678009033, "learning_rate": 1.0677310627357296e-06, "loss": 0.2145, "step": 2361 }, { "epoch": 1.4176417641764176, "grad_norm": 2.6704540252685547, "learning_rate": 1.0700831262306379e-06, "loss": 0.1897, "step": 2362 }, { "epoch": 1.4182418241824182, "grad_norm": 5.428061485290527, "learning_rate": 1.0724348001617614e-06, "loss": 0.3765, "step": 2363 }, { "epoch": 1.418841884188419, "grad_norm": 6.99592924118042, "learning_rate": 1.074786071457098e-06, "loss": 0.5904, "step": 2364 }, { "epoch": 1.4194419441944195, "grad_norm": 5.865040302276611, "learning_rate": 1.0771369270468778e-06, "loss": 0.4346, "step": 2365 }, { "epoch": 1.42004200420042, "grad_norm": 3.872910737991333, "learning_rate": 1.0794873538636451e-06, "loss": 0.3994, "step": 2366 }, { "epoch": 1.4206420642064206, "grad_norm": 6.1667609214782715, "learning_rate": 1.0818373388423276e-06, "loss": 0.6295, "step": 2367 }, { "epoch": 1.4212421242124211, "grad_norm": 3.6686313152313232, "learning_rate": 1.0841868689203072e-06, "loss": 0.2903, "step": 2368 }, { "epoch": 1.421842184218422, "grad_norm": 4.263485908508301, "learning_rate": 1.0865359310374955e-06, "loss": 0.2899, "step": 2369 }, { "epoch": 1.4224422442244224, "grad_norm": 5.323146343231201, "learning_rate": 1.0888845121364056e-06, "loss": 0.3793, "step": 2370 }, { "epoch": 1.423042304230423, "grad_norm": 3.2540786266326904, "learning_rate": 1.0912325991622242e-06, "loss": 0.3357, "step": 2371 }, { "epoch": 1.4236423642364238, "grad_norm": 4.725978374481201, "learning_rate": 1.093580179062884e-06, "loss": 0.4504, "step": 2372 }, { "epoch": 1.4242424242424243, "grad_norm": 7.07509708404541, "learning_rate": 1.0959272387891368e-06, "loss": 0.7124, "step": 2373 }, { "epoch": 1.4248424842484249, "grad_norm": 5.681119441986084, "learning_rate": 1.098273765294627e-06, "loss": 0.2336, "step": 2374 }, { "epoch": 1.4254425442544254, "grad_norm": 4.105746269226074, "learning_rate": 1.1006197455359595e-06, "loss": 0.2738, "step": 2375 }, { "epoch": 1.426042604260426, "grad_norm": 4.004136562347412, "learning_rate": 1.1029651664727796e-06, "loss": 0.1901, "step": 2376 }, { "epoch": 1.4266426642664267, "grad_norm": 5.6882734298706055, "learning_rate": 1.1053100150678393e-06, "loss": 0.3709, "step": 2377 }, { "epoch": 1.4272427242724273, "grad_norm": 4.019688129425049, "learning_rate": 1.107654278287073e-06, "loss": 0.4992, "step": 2378 }, { "epoch": 1.4278427842784278, "grad_norm": 3.2427890300750732, "learning_rate": 1.1099979430996683e-06, "loss": 0.1507, "step": 2379 }, { "epoch": 1.4284428442844286, "grad_norm": 4.510298252105713, "learning_rate": 1.1123409964781403e-06, "loss": 0.2383, "step": 2380 }, { "epoch": 1.4290429042904291, "grad_norm": 6.02182674407959, "learning_rate": 1.1146834253984005e-06, "loss": 0.3907, "step": 2381 }, { "epoch": 1.4296429642964297, "grad_norm": 6.08574914932251, "learning_rate": 1.1170252168398334e-06, "loss": 0.3795, "step": 2382 }, { "epoch": 1.4302430243024302, "grad_norm": 5.866267204284668, "learning_rate": 1.119366357785367e-06, "loss": 0.6948, "step": 2383 }, { "epoch": 1.4308430843084308, "grad_norm": 4.3688883781433105, "learning_rate": 1.121706835221544e-06, "loss": 0.356, "step": 2384 }, { "epoch": 1.4314431443144313, "grad_norm": 5.979387283325195, "learning_rate": 1.1240466361385963e-06, "loss": 0.4489, "step": 2385 }, { "epoch": 1.432043204320432, "grad_norm": 5.983216762542725, "learning_rate": 1.126385747530516e-06, "loss": 0.4039, "step": 2386 }, { "epoch": 1.4326432643264326, "grad_norm": 4.0121989250183105, "learning_rate": 1.1287241563951289e-06, "loss": 0.3503, "step": 2387 }, { "epoch": 1.4332433243324332, "grad_norm": 4.0432658195495605, "learning_rate": 1.1310618497341627e-06, "loss": 0.319, "step": 2388 }, { "epoch": 1.433843384338434, "grad_norm": 5.725636959075928, "learning_rate": 1.1333988145533257e-06, "loss": 0.4141, "step": 2389 }, { "epoch": 1.4344434443444345, "grad_norm": 3.4621920585632324, "learning_rate": 1.135735037862375e-06, "loss": 0.2961, "step": 2390 }, { "epoch": 1.435043504350435, "grad_norm": 3.309169292449951, "learning_rate": 1.1380705066751887e-06, "loss": 0.4307, "step": 2391 }, { "epoch": 1.4356435643564356, "grad_norm": 5.6097283363342285, "learning_rate": 1.1404052080098395e-06, "loss": 0.3839, "step": 2392 }, { "epoch": 1.4362436243624361, "grad_norm": 5.481887340545654, "learning_rate": 1.1427391288886662e-06, "loss": 0.3248, "step": 2393 }, { "epoch": 1.436843684368437, "grad_norm": 5.117669582366943, "learning_rate": 1.1450722563383448e-06, "loss": 0.5536, "step": 2394 }, { "epoch": 1.4374437443744374, "grad_norm": 4.465394020080566, "learning_rate": 1.1474045773899627e-06, "loss": 0.2782, "step": 2395 }, { "epoch": 1.438043804380438, "grad_norm": 5.763535499572754, "learning_rate": 1.1497360790790897e-06, "loss": 0.3268, "step": 2396 }, { "epoch": 1.4386438643864388, "grad_norm": 4.028225421905518, "learning_rate": 1.1520667484458506e-06, "loss": 0.39, "step": 2397 }, { "epoch": 1.4392439243924393, "grad_norm": 7.44259786605835, "learning_rate": 1.1543965725349936e-06, "loss": 0.2348, "step": 2398 }, { "epoch": 1.4398439843984399, "grad_norm": 3.9660990238189697, "learning_rate": 1.1567255383959703e-06, "loss": 0.293, "step": 2399 }, { "epoch": 1.4404440444044404, "grad_norm": 4.378739833831787, "learning_rate": 1.1590536330830009e-06, "loss": 0.2832, "step": 2400 }, { "epoch": 1.441044104410441, "grad_norm": 3.637000799179077, "learning_rate": 1.1613808436551451e-06, "loss": 0.4798, "step": 2401 }, { "epoch": 1.4416441644164417, "grad_norm": 5.54905366897583, "learning_rate": 1.163707157176381e-06, "loss": 0.3891, "step": 2402 }, { "epoch": 1.4422442244224423, "grad_norm": 3.8916938304901123, "learning_rate": 1.1660325607156724e-06, "loss": 0.2783, "step": 2403 }, { "epoch": 1.4428442844284428, "grad_norm": 5.736186981201172, "learning_rate": 1.1683570413470387e-06, "loss": 0.2374, "step": 2404 }, { "epoch": 1.4434443444344436, "grad_norm": 5.814486026763916, "learning_rate": 1.1706805861496313e-06, "loss": 0.5224, "step": 2405 }, { "epoch": 1.4440444044404441, "grad_norm": 6.047861099243164, "learning_rate": 1.1730031822078055e-06, "loss": 0.3081, "step": 2406 }, { "epoch": 1.4446444644464447, "grad_norm": 3.3361189365386963, "learning_rate": 1.1753248166111874e-06, "loss": 0.2898, "step": 2407 }, { "epoch": 1.4452445244524452, "grad_norm": 4.280752182006836, "learning_rate": 1.1776454764547482e-06, "loss": 0.3098, "step": 2408 }, { "epoch": 1.4458445844584458, "grad_norm": 7.319298267364502, "learning_rate": 1.1799651488388783e-06, "loss": 0.4824, "step": 2409 }, { "epoch": 1.4464446444644463, "grad_norm": 4.833072662353516, "learning_rate": 1.1822838208694565e-06, "loss": 0.4007, "step": 2410 }, { "epoch": 1.447044704470447, "grad_norm": 5.3264923095703125, "learning_rate": 1.1846014796579206e-06, "loss": 0.5217, "step": 2411 }, { "epoch": 1.4476447644764476, "grad_norm": 6.283980846405029, "learning_rate": 1.1869181123213424e-06, "loss": 0.3046, "step": 2412 }, { "epoch": 1.4482448244824482, "grad_norm": 5.1743316650390625, "learning_rate": 1.1892337059824966e-06, "loss": 0.4088, "step": 2413 }, { "epoch": 1.448844884488449, "grad_norm": 6.307787895202637, "learning_rate": 1.191548247769934e-06, "loss": 0.4936, "step": 2414 }, { "epoch": 1.4494449444944495, "grad_norm": 4.446811199188232, "learning_rate": 1.1938617248180523e-06, "loss": 0.359, "step": 2415 }, { "epoch": 1.45004500450045, "grad_norm": 5.764465808868408, "learning_rate": 1.1961741242671671e-06, "loss": 0.3251, "step": 2416 }, { "epoch": 1.4506450645064506, "grad_norm": 4.070602893829346, "learning_rate": 1.1984854332635831e-06, "loss": 0.2713, "step": 2417 }, { "epoch": 1.4512451245124511, "grad_norm": 3.5625205039978027, "learning_rate": 1.2007956389596683e-06, "loss": 0.2436, "step": 2418 }, { "epoch": 1.451845184518452, "grad_norm": 5.742155075073242, "learning_rate": 1.2031047285139224e-06, "loss": 0.4457, "step": 2419 }, { "epoch": 1.4524452445244525, "grad_norm": 5.167348384857178, "learning_rate": 1.2054126890910494e-06, "loss": 0.2835, "step": 2420 }, { "epoch": 1.453045304530453, "grad_norm": 5.0513811111450195, "learning_rate": 1.2077195078620293e-06, "loss": 0.3124, "step": 2421 }, { "epoch": 1.4536453645364538, "grad_norm": 4.702184200286865, "learning_rate": 1.210025172004188e-06, "loss": 0.2469, "step": 2422 }, { "epoch": 1.4542454245424543, "grad_norm": 2.7258763313293457, "learning_rate": 1.2123296687012716e-06, "loss": 0.2205, "step": 2423 }, { "epoch": 1.4548454845484549, "grad_norm": 3.986048698425293, "learning_rate": 1.2146329851435118e-06, "loss": 0.2841, "step": 2424 }, { "epoch": 1.4554455445544554, "grad_norm": 4.495619297027588, "learning_rate": 1.216935108527704e-06, "loss": 0.2797, "step": 2425 }, { "epoch": 1.456045604560456, "grad_norm": 4.606714248657227, "learning_rate": 1.2192360260572746e-06, "loss": 0.2501, "step": 2426 }, { "epoch": 1.4566456645664567, "grad_norm": 4.794416904449463, "learning_rate": 1.2215357249423528e-06, "loss": 0.3858, "step": 2427 }, { "epoch": 1.4572457245724573, "grad_norm": 3.330829620361328, "learning_rate": 1.2238341923998412e-06, "loss": 0.1732, "step": 2428 }, { "epoch": 1.4578457845784578, "grad_norm": 4.910092830657959, "learning_rate": 1.2261314156534884e-06, "loss": 0.4286, "step": 2429 }, { "epoch": 1.4584458445844586, "grad_norm": 2.9232981204986572, "learning_rate": 1.2284273819339585e-06, "loss": 0.2462, "step": 2430 }, { "epoch": 1.4590459045904591, "grad_norm": 5.568304061889648, "learning_rate": 1.2307220784789016e-06, "loss": 0.4146, "step": 2431 }, { "epoch": 1.4596459645964597, "grad_norm": 5.194649696350098, "learning_rate": 1.2330154925330274e-06, "loss": 0.4904, "step": 2432 }, { "epoch": 1.4602460246024602, "grad_norm": 4.993518829345703, "learning_rate": 1.2353076113481736e-06, "loss": 0.3976, "step": 2433 }, { "epoch": 1.4608460846084608, "grad_norm": 4.768033504486084, "learning_rate": 1.2375984221833778e-06, "loss": 0.3439, "step": 2434 }, { "epoch": 1.4614461446144613, "grad_norm": 4.986067295074463, "learning_rate": 1.2398879123049481e-06, "loss": 0.3686, "step": 2435 }, { "epoch": 1.462046204620462, "grad_norm": 5.666953086853027, "learning_rate": 1.2421760689865348e-06, "loss": 0.5932, "step": 2436 }, { "epoch": 1.4626462646264626, "grad_norm": 5.301604747772217, "learning_rate": 1.244462879509198e-06, "loss": 0.4493, "step": 2437 }, { "epoch": 1.4632463246324632, "grad_norm": 5.86802864074707, "learning_rate": 1.2467483311614821e-06, "loss": 0.4515, "step": 2438 }, { "epoch": 1.463846384638464, "grad_norm": 5.775759220123291, "learning_rate": 1.2490324112394862e-06, "loss": 0.4135, "step": 2439 }, { "epoch": 1.4644464446444645, "grad_norm": 3.855421304702759, "learning_rate": 1.2513151070469293e-06, "loss": 0.2518, "step": 2440 }, { "epoch": 1.465046504650465, "grad_norm": 4.977358818054199, "learning_rate": 1.2535964058952297e-06, "loss": 0.398, "step": 2441 }, { "epoch": 1.4656465646564656, "grad_norm": 3.8735597133636475, "learning_rate": 1.2558762951035686e-06, "loss": 0.385, "step": 2442 }, { "epoch": 1.4662466246624661, "grad_norm": 6.871440410614014, "learning_rate": 1.2581547619989635e-06, "loss": 0.357, "step": 2443 }, { "epoch": 1.466846684668467, "grad_norm": 3.8245162963867188, "learning_rate": 1.2604317939163362e-06, "loss": 0.2783, "step": 2444 }, { "epoch": 1.4674467446744675, "grad_norm": 4.191982746124268, "learning_rate": 1.2627073781985863e-06, "loss": 0.4349, "step": 2445 }, { "epoch": 1.468046804680468, "grad_norm": 3.4960756301879883, "learning_rate": 1.2649815021966622e-06, "loss": 0.2883, "step": 2446 }, { "epoch": 1.4686468646864688, "grad_norm": 4.507322788238525, "learning_rate": 1.2672541532696243e-06, "loss": 0.3607, "step": 2447 }, { "epoch": 1.4692469246924693, "grad_norm": 3.4417052268981934, "learning_rate": 1.2695253187847246e-06, "loss": 0.2902, "step": 2448 }, { "epoch": 1.4698469846984699, "grad_norm": 4.442574977874756, "learning_rate": 1.2717949861174736e-06, "loss": 0.3766, "step": 2449 }, { "epoch": 1.4704470447044704, "grad_norm": 4.96922492980957, "learning_rate": 1.274063142651705e-06, "loss": 0.2924, "step": 2450 }, { "epoch": 1.471047104710471, "grad_norm": 4.578376770019531, "learning_rate": 1.2763297757796543e-06, "loss": 0.4411, "step": 2451 }, { "epoch": 1.4716471647164717, "grad_norm": 7.145125389099121, "learning_rate": 1.2785948729020233e-06, "loss": 0.5664, "step": 2452 }, { "epoch": 1.4722472247224723, "grad_norm": 4.30225133895874, "learning_rate": 1.2808584214280531e-06, "loss": 0.3092, "step": 2453 }, { "epoch": 1.4728472847284728, "grad_norm": 3.9841625690460205, "learning_rate": 1.2831204087755908e-06, "loss": 0.3916, "step": 2454 }, { "epoch": 1.4734473447344736, "grad_norm": 5.334994316101074, "learning_rate": 1.285380822371162e-06, "loss": 0.3617, "step": 2455 }, { "epoch": 1.4740474047404741, "grad_norm": 5.271627902984619, "learning_rate": 1.2876396496500435e-06, "loss": 0.3045, "step": 2456 }, { "epoch": 1.4746474647464747, "grad_norm": 4.796658515930176, "learning_rate": 1.2898968780563245e-06, "loss": 0.3996, "step": 2457 }, { "epoch": 1.4752475247524752, "grad_norm": 6.179181098937988, "learning_rate": 1.2921524950429857e-06, "loss": 0.4303, "step": 2458 }, { "epoch": 1.4758475847584758, "grad_norm": 4.259331226348877, "learning_rate": 1.2944064880719636e-06, "loss": 0.3657, "step": 2459 }, { "epoch": 1.4764476447644763, "grad_norm": 4.853321552276611, "learning_rate": 1.2966588446142202e-06, "loss": 0.3051, "step": 2460 }, { "epoch": 1.477047704770477, "grad_norm": 3.402398109436035, "learning_rate": 1.2989095521498165e-06, "loss": 0.3138, "step": 2461 }, { "epoch": 1.4776477647764776, "grad_norm": 4.556654453277588, "learning_rate": 1.3011585981679786e-06, "loss": 0.3839, "step": 2462 }, { "epoch": 1.4782478247824782, "grad_norm": 3.1267857551574707, "learning_rate": 1.3034059701671682e-06, "loss": 0.3463, "step": 2463 }, { "epoch": 1.478847884788479, "grad_norm": 3.2105064392089844, "learning_rate": 1.3056516556551524e-06, "loss": 0.2502, "step": 2464 }, { "epoch": 1.4794479447944795, "grad_norm": 4.802481174468994, "learning_rate": 1.3078956421490732e-06, "loss": 0.3199, "step": 2465 }, { "epoch": 1.48004800480048, "grad_norm": 4.969095706939697, "learning_rate": 1.3101379171755164e-06, "loss": 0.3646, "step": 2466 }, { "epoch": 1.4806480648064806, "grad_norm": 4.108684062957764, "learning_rate": 1.3123784682705804e-06, "loss": 0.344, "step": 2467 }, { "epoch": 1.4812481248124811, "grad_norm": 5.263178825378418, "learning_rate": 1.3146172829799467e-06, "loss": 0.3133, "step": 2468 }, { "epoch": 1.481848184818482, "grad_norm": 5.094577789306641, "learning_rate": 1.3168543488589495e-06, "loss": 0.3963, "step": 2469 }, { "epoch": 1.4824482448244825, "grad_norm": 4.4634528160095215, "learning_rate": 1.3190896534726432e-06, "loss": 0.297, "step": 2470 }, { "epoch": 1.483048304830483, "grad_norm": 4.410720348358154, "learning_rate": 1.3213231843958725e-06, "loss": 0.316, "step": 2471 }, { "epoch": 1.4836483648364838, "grad_norm": 4.321625709533691, "learning_rate": 1.3235549292133426e-06, "loss": 0.3264, "step": 2472 }, { "epoch": 1.4842484248424843, "grad_norm": 4.62605094909668, "learning_rate": 1.3257848755196837e-06, "loss": 0.2734, "step": 2473 }, { "epoch": 1.4848484848484849, "grad_norm": 4.64015007019043, "learning_rate": 1.328013010919526e-06, "loss": 0.4342, "step": 2474 }, { "epoch": 1.4854485448544854, "grad_norm": 5.232458591461182, "learning_rate": 1.3302393230275652e-06, "loss": 0.5983, "step": 2475 }, { "epoch": 1.486048604860486, "grad_norm": 6.0165629386901855, "learning_rate": 1.3324637994686318e-06, "loss": 0.3147, "step": 2476 }, { "epoch": 1.4866486648664867, "grad_norm": 4.647317409515381, "learning_rate": 1.33468642787776e-06, "loss": 0.4384, "step": 2477 }, { "epoch": 1.4872487248724873, "grad_norm": 4.301257133483887, "learning_rate": 1.3369071959002565e-06, "loss": 0.2501, "step": 2478 }, { "epoch": 1.4878487848784878, "grad_norm": 5.797022342681885, "learning_rate": 1.3391260911917699e-06, "loss": 0.3772, "step": 2479 }, { "epoch": 1.4884488448844886, "grad_norm": 4.504927158355713, "learning_rate": 1.341343101418356e-06, "loss": 0.4579, "step": 2480 }, { "epoch": 1.4890489048904891, "grad_norm": 5.503726005554199, "learning_rate": 1.3435582142565514e-06, "loss": 0.4734, "step": 2481 }, { "epoch": 1.4896489648964897, "grad_norm": 3.3242809772491455, "learning_rate": 1.345771417393439e-06, "loss": 0.2522, "step": 2482 }, { "epoch": 1.4902490249024902, "grad_norm": 3.57509446144104, "learning_rate": 1.3479826985267168e-06, "loss": 0.2802, "step": 2483 }, { "epoch": 1.4908490849084908, "grad_norm": 4.1982951164245605, "learning_rate": 1.3501920453647663e-06, "loss": 0.2967, "step": 2484 }, { "epoch": 1.4914491449144913, "grad_norm": 4.038732528686523, "learning_rate": 1.3523994456267218e-06, "loss": 0.3525, "step": 2485 }, { "epoch": 1.492049204920492, "grad_norm": 4.766671180725098, "learning_rate": 1.3546048870425354e-06, "loss": 0.4963, "step": 2486 }, { "epoch": 1.4926492649264926, "grad_norm": 3.2172975540161133, "learning_rate": 1.3568083573530505e-06, "loss": 0.1612, "step": 2487 }, { "epoch": 1.4932493249324932, "grad_norm": 4.983397006988525, "learning_rate": 1.3590098443100653e-06, "loss": 0.3508, "step": 2488 }, { "epoch": 1.493849384938494, "grad_norm": 5.694849491119385, "learning_rate": 1.3612093356764048e-06, "loss": 0.4422, "step": 2489 }, { "epoch": 1.4944494449444945, "grad_norm": 3.506338119506836, "learning_rate": 1.363406819225982e-06, "loss": 0.4279, "step": 2490 }, { "epoch": 1.495049504950495, "grad_norm": 4.338222503662109, "learning_rate": 1.3656022827438763e-06, "loss": 0.2525, "step": 2491 }, { "epoch": 1.4956495649564956, "grad_norm": 2.9459784030914307, "learning_rate": 1.3677957140263933e-06, "loss": 0.2535, "step": 2492 }, { "epoch": 1.4962496249624961, "grad_norm": 3.4614672660827637, "learning_rate": 1.369987100881133e-06, "loss": 0.2463, "step": 2493 }, { "epoch": 1.496849684968497, "grad_norm": 4.8337578773498535, "learning_rate": 1.3721764311270618e-06, "loss": 0.3512, "step": 2494 }, { "epoch": 1.4974497449744975, "grad_norm": 2.5629122257232666, "learning_rate": 1.3743636925945785e-06, "loss": 0.2847, "step": 2495 }, { "epoch": 1.498049804980498, "grad_norm": 4.833345413208008, "learning_rate": 1.3765488731255786e-06, "loss": 0.399, "step": 2496 }, { "epoch": 1.4986498649864988, "grad_norm": 4.926424026489258, "learning_rate": 1.3787319605735261e-06, "loss": 0.4599, "step": 2497 }, { "epoch": 1.4992499249924993, "grad_norm": 3.353069543838501, "learning_rate": 1.3809129428035227e-06, "loss": 0.2822, "step": 2498 }, { "epoch": 1.4998499849984999, "grad_norm": 4.16192102432251, "learning_rate": 1.3830918076923668e-06, "loss": 0.4961, "step": 2499 }, { "epoch": 1.5004500450045004, "grad_norm": 5.175436496734619, "learning_rate": 1.3852685431286298e-06, "loss": 0.2683, "step": 2500 }, { "epoch": 1.501050105010501, "grad_norm": 6.547866344451904, "learning_rate": 1.3874431370127181e-06, "loss": 0.5258, "step": 2501 }, { "epoch": 1.5016501650165015, "grad_norm": 6.312436580657959, "learning_rate": 1.389615577256945e-06, "loss": 0.5442, "step": 2502 }, { "epoch": 1.5022502250225023, "grad_norm": 5.259655952453613, "learning_rate": 1.39178585178559e-06, "loss": 0.4254, "step": 2503 }, { "epoch": 1.5028502850285028, "grad_norm": 4.926884651184082, "learning_rate": 1.3939539485349751e-06, "loss": 0.4046, "step": 2504 }, { "epoch": 1.5034503450345036, "grad_norm": 3.642936944961548, "learning_rate": 1.3961198554535266e-06, "loss": 0.3273, "step": 2505 }, { "epoch": 1.5040504050405041, "grad_norm": 5.525953769683838, "learning_rate": 1.3982835605018432e-06, "loss": 0.3306, "step": 2506 }, { "epoch": 1.5046504650465047, "grad_norm": 4.5712480545043945, "learning_rate": 1.4004450516527624e-06, "loss": 0.3362, "step": 2507 }, { "epoch": 1.5052505250525052, "grad_norm": 3.9245314598083496, "learning_rate": 1.4026043168914288e-06, "loss": 0.2474, "step": 2508 }, { "epoch": 1.5058505850585058, "grad_norm": 5.730712413787842, "learning_rate": 1.4047613442153582e-06, "loss": 0.5027, "step": 2509 }, { "epoch": 1.5064506450645063, "grad_norm": 4.709815979003906, "learning_rate": 1.4069161216345073e-06, "loss": 0.354, "step": 2510 }, { "epoch": 1.507050705070507, "grad_norm": 4.440188407897949, "learning_rate": 1.4090686371713396e-06, "loss": 0.3523, "step": 2511 }, { "epoch": 1.5076507650765076, "grad_norm": 6.311851501464844, "learning_rate": 1.411218878860891e-06, "loss": 0.463, "step": 2512 }, { "epoch": 1.5082508250825084, "grad_norm": 5.140951633453369, "learning_rate": 1.4133668347508363e-06, "loss": 0.3586, "step": 2513 }, { "epoch": 1.508850885088509, "grad_norm": 4.716785430908203, "learning_rate": 1.4155124929015565e-06, "loss": 0.3289, "step": 2514 }, { "epoch": 1.5094509450945095, "grad_norm": 8.135713577270508, "learning_rate": 1.417655841386206e-06, "loss": 0.5285, "step": 2515 }, { "epoch": 1.51005100510051, "grad_norm": 5.588953018188477, "learning_rate": 1.4197968682907746e-06, "loss": 0.4745, "step": 2516 }, { "epoch": 1.5106510651065106, "grad_norm": 3.2999889850616455, "learning_rate": 1.4219355617141598e-06, "loss": 0.1832, "step": 2517 }, { "epoch": 1.5112511251125111, "grad_norm": 5.886038780212402, "learning_rate": 1.4240719097682287e-06, "loss": 0.388, "step": 2518 }, { "epoch": 1.5118511851185117, "grad_norm": 4.972931861877441, "learning_rate": 1.426205900577886e-06, "loss": 0.3072, "step": 2519 }, { "epoch": 1.5124512451245125, "grad_norm": 5.4018874168396, "learning_rate": 1.4283375222811382e-06, "loss": 0.3626, "step": 2520 }, { "epoch": 1.513051305130513, "grad_norm": 5.280306816101074, "learning_rate": 1.4304667630291633e-06, "loss": 0.4609, "step": 2521 }, { "epoch": 1.5136513651365138, "grad_norm": 3.8994271755218506, "learning_rate": 1.4325936109863698e-06, "loss": 0.3155, "step": 2522 }, { "epoch": 1.5142514251425143, "grad_norm": 4.645979881286621, "learning_rate": 1.4347180543304704e-06, "loss": 0.2412, "step": 2523 }, { "epoch": 1.5148514851485149, "grad_norm": 6.260888576507568, "learning_rate": 1.436840081252543e-06, "loss": 0.4959, "step": 2524 }, { "epoch": 1.5154515451545154, "grad_norm": 3.635568141937256, "learning_rate": 1.438959679957097e-06, "loss": 0.2623, "step": 2525 }, { "epoch": 1.516051605160516, "grad_norm": 5.058308124542236, "learning_rate": 1.4410768386621393e-06, "loss": 0.3691, "step": 2526 }, { "epoch": 1.5166516651665165, "grad_norm": 5.867679595947266, "learning_rate": 1.4431915455992408e-06, "loss": 0.4157, "step": 2527 }, { "epoch": 1.5172517251725173, "grad_norm": 4.263551712036133, "learning_rate": 1.4453037890136002e-06, "loss": 0.376, "step": 2528 }, { "epoch": 1.5178517851785178, "grad_norm": 5.613828182220459, "learning_rate": 1.4474135571641082e-06, "loss": 0.3804, "step": 2529 }, { "epoch": 1.5184518451845186, "grad_norm": 3.553940534591675, "learning_rate": 1.4495208383234171e-06, "loss": 0.2794, "step": 2530 }, { "epoch": 1.5190519051905191, "grad_norm": 4.696595668792725, "learning_rate": 1.4516256207780033e-06, "loss": 0.3868, "step": 2531 }, { "epoch": 1.5196519651965197, "grad_norm": 4.593923091888428, "learning_rate": 1.4537278928282285e-06, "loss": 0.399, "step": 2532 }, { "epoch": 1.5202520252025202, "grad_norm": 5.336577892303467, "learning_rate": 1.4558276427884149e-06, "loss": 0.5306, "step": 2533 }, { "epoch": 1.5208520852085208, "grad_norm": 5.091892242431641, "learning_rate": 1.457924858986899e-06, "loss": 0.4855, "step": 2534 }, { "epoch": 1.5214521452145213, "grad_norm": 3.4288406372070312, "learning_rate": 1.4600195297661053e-06, "loss": 0.2888, "step": 2535 }, { "epoch": 1.522052205220522, "grad_norm": 4.870142936706543, "learning_rate": 1.4621116434826027e-06, "loss": 0.4077, "step": 2536 }, { "epoch": 1.5226522652265226, "grad_norm": 2.7674591541290283, "learning_rate": 1.4642011885071775e-06, "loss": 0.1773, "step": 2537 }, { "epoch": 1.5232523252325234, "grad_norm": 5.136094093322754, "learning_rate": 1.4662881532248936e-06, "loss": 0.4091, "step": 2538 }, { "epoch": 1.523852385238524, "grad_norm": 3.440871000289917, "learning_rate": 1.4683725260351562e-06, "loss": 0.2738, "step": 2539 }, { "epoch": 1.5244524452445245, "grad_norm": 4.1428422927856445, "learning_rate": 1.4704542953517788e-06, "loss": 0.351, "step": 2540 }, { "epoch": 1.525052505250525, "grad_norm": 3.57185959815979, "learning_rate": 1.4725334496030491e-06, "loss": 0.4226, "step": 2541 }, { "epoch": 1.5256525652565256, "grad_norm": 4.912846565246582, "learning_rate": 1.4746099772317862e-06, "loss": 0.4483, "step": 2542 }, { "epoch": 1.5262526252625261, "grad_norm": 6.106168270111084, "learning_rate": 1.476683866695413e-06, "loss": 0.3778, "step": 2543 }, { "epoch": 1.5268526852685267, "grad_norm": 4.685081958770752, "learning_rate": 1.4787551064660167e-06, "loss": 0.3845, "step": 2544 }, { "epoch": 1.5274527452745275, "grad_norm": 4.722394943237305, "learning_rate": 1.4808236850304103e-06, "loss": 0.3671, "step": 2545 }, { "epoch": 1.528052805280528, "grad_norm": 4.773656368255615, "learning_rate": 1.4828895908902026e-06, "loss": 0.4049, "step": 2546 }, { "epoch": 1.5286528652865288, "grad_norm": 5.190947532653809, "learning_rate": 1.4849528125618565e-06, "loss": 0.3622, "step": 2547 }, { "epoch": 1.5292529252925293, "grad_norm": 4.157620906829834, "learning_rate": 1.4870133385767585e-06, "loss": 0.4917, "step": 2548 }, { "epoch": 1.5298529852985299, "grad_norm": 3.361722707748413, "learning_rate": 1.4890711574812752e-06, "loss": 0.2153, "step": 2549 }, { "epoch": 1.5304530453045304, "grad_norm": 3.488349676132202, "learning_rate": 1.4911262578368229e-06, "loss": 0.2589, "step": 2550 }, { "epoch": 1.531053105310531, "grad_norm": 5.87144136428833, "learning_rate": 1.49317862821993e-06, "loss": 0.3166, "step": 2551 }, { "epoch": 1.5316531653165315, "grad_norm": 3.630364418029785, "learning_rate": 1.4952282572222972e-06, "loss": 0.2609, "step": 2552 }, { "epoch": 1.5322532253225323, "grad_norm": 3.7589337825775146, "learning_rate": 1.497275133450866e-06, "loss": 0.2547, "step": 2553 }, { "epoch": 1.5328532853285328, "grad_norm": 6.163331508636475, "learning_rate": 1.499319245527878e-06, "loss": 0.4549, "step": 2554 }, { "epoch": 1.5334533453345336, "grad_norm": 4.4309892654418945, "learning_rate": 1.5013605820909405e-06, "loss": 0.3385, "step": 2555 }, { "epoch": 1.5340534053405341, "grad_norm": 6.241473197937012, "learning_rate": 1.503399131793088e-06, "loss": 0.3931, "step": 2556 }, { "epoch": 1.5346534653465347, "grad_norm": 5.300980091094971, "learning_rate": 1.505434883302846e-06, "loss": 0.4403, "step": 2557 }, { "epoch": 1.5352535253525352, "grad_norm": 3.898510456085205, "learning_rate": 1.507467825304296e-06, "loss": 0.3423, "step": 2558 }, { "epoch": 1.5358535853585358, "grad_norm": 5.818594932556152, "learning_rate": 1.5094979464971324e-06, "loss": 0.5297, "step": 2559 }, { "epoch": 1.5364536453645363, "grad_norm": 3.768698215484619, "learning_rate": 1.511525235596733e-06, "loss": 0.3145, "step": 2560 }, { "epoch": 1.537053705370537, "grad_norm": 4.463555812835693, "learning_rate": 1.5135496813342164e-06, "loss": 0.2853, "step": 2561 }, { "epoch": 1.5376537653765376, "grad_norm": 4.698781967163086, "learning_rate": 1.5155712724565066e-06, "loss": 0.3406, "step": 2562 }, { "epoch": 1.5382538253825384, "grad_norm": 2.9717462062835693, "learning_rate": 1.5175899977263959e-06, "loss": 0.1987, "step": 2563 }, { "epoch": 1.538853885388539, "grad_norm": 2.8739559650421143, "learning_rate": 1.5196058459226064e-06, "loss": 0.1572, "step": 2564 }, { "epoch": 1.5394539453945395, "grad_norm": 5.290642738342285, "learning_rate": 1.5216188058398508e-06, "loss": 0.3606, "step": 2565 }, { "epoch": 1.54005400540054, "grad_norm": 4.615499019622803, "learning_rate": 1.5236288662888997e-06, "loss": 0.3962, "step": 2566 }, { "epoch": 1.5406540654065406, "grad_norm": 4.034870624542236, "learning_rate": 1.5256360160966385e-06, "loss": 0.2983, "step": 2567 }, { "epoch": 1.5412541254125411, "grad_norm": 5.206980228424072, "learning_rate": 1.5276402441061325e-06, "loss": 0.5325, "step": 2568 }, { "epoch": 1.5418541854185417, "grad_norm": 5.576469898223877, "learning_rate": 1.5296415391766876e-06, "loss": 0.3223, "step": 2569 }, { "epoch": 1.5424542454245425, "grad_norm": 5.762587547302246, "learning_rate": 1.5316398901839139e-06, "loss": 0.4364, "step": 2570 }, { "epoch": 1.543054305430543, "grad_norm": 3.980804681777954, "learning_rate": 1.5336352860197857e-06, "loss": 0.279, "step": 2571 }, { "epoch": 1.5436543654365438, "grad_norm": 4.892871856689453, "learning_rate": 1.5356277155927022e-06, "loss": 0.3925, "step": 2572 }, { "epoch": 1.5442544254425443, "grad_norm": 3.881976366043091, "learning_rate": 1.5376171678275535e-06, "loss": 0.3319, "step": 2573 }, { "epoch": 1.5448544854485449, "grad_norm": 6.875019550323486, "learning_rate": 1.5396036316657778e-06, "loss": 0.6211, "step": 2574 }, { "epoch": 1.5454545454545454, "grad_norm": 4.418248653411865, "learning_rate": 1.541587096065426e-06, "loss": 0.2658, "step": 2575 }, { "epoch": 1.546054605460546, "grad_norm": 5.133599281311035, "learning_rate": 1.5435675500012203e-06, "loss": 0.4986, "step": 2576 }, { "epoch": 1.5466546654665465, "grad_norm": 3.4625771045684814, "learning_rate": 1.5455449824646185e-06, "loss": 0.2624, "step": 2577 }, { "epoch": 1.5472547254725473, "grad_norm": 4.568177700042725, "learning_rate": 1.5475193824638708e-06, "loss": 0.4374, "step": 2578 }, { "epoch": 1.5478547854785478, "grad_norm": 4.184535980224609, "learning_rate": 1.549490739024086e-06, "loss": 0.2886, "step": 2579 }, { "epoch": 1.5484548454845486, "grad_norm": 3.630941152572632, "learning_rate": 1.5514590411872894e-06, "loss": 0.2902, "step": 2580 }, { "epoch": 1.5490549054905491, "grad_norm": 6.0939836502075195, "learning_rate": 1.5534242780124855e-06, "loss": 0.3618, "step": 2581 }, { "epoch": 1.5496549654965497, "grad_norm": 4.43941593170166, "learning_rate": 1.5553864385757142e-06, "loss": 0.306, "step": 2582 }, { "epoch": 1.5502550255025502, "grad_norm": 5.244941234588623, "learning_rate": 1.5573455119701207e-06, "loss": 0.5139, "step": 2583 }, { "epoch": 1.5508550855085508, "grad_norm": 4.101751327514648, "learning_rate": 1.5593014873060062e-06, "loss": 0.3727, "step": 2584 }, { "epoch": 1.5514551455145513, "grad_norm": 5.530610084533691, "learning_rate": 1.5612543537108937e-06, "loss": 0.5507, "step": 2585 }, { "epoch": 1.552055205520552, "grad_norm": 4.421948432922363, "learning_rate": 1.5632041003295883e-06, "loss": 0.5663, "step": 2586 }, { "epoch": 1.5526552655265526, "grad_norm": 6.379489421844482, "learning_rate": 1.5651507163242368e-06, "loss": 0.4083, "step": 2587 }, { "epoch": 1.5532553255325534, "grad_norm": 4.599510192871094, "learning_rate": 1.5670941908743863e-06, "loss": 0.2954, "step": 2588 }, { "epoch": 1.553855385538554, "grad_norm": 3.4459660053253174, "learning_rate": 1.5690345131770465e-06, "loss": 0.2593, "step": 2589 }, { "epoch": 1.5544554455445545, "grad_norm": 4.14581298828125, "learning_rate": 1.570971672446752e-06, "loss": 0.4424, "step": 2590 }, { "epoch": 1.555055505550555, "grad_norm": 3.2548766136169434, "learning_rate": 1.5729056579156152e-06, "loss": 0.415, "step": 2591 }, { "epoch": 1.5556555655565556, "grad_norm": 3.628591775894165, "learning_rate": 1.5748364588333924e-06, "loss": 0.337, "step": 2592 }, { "epoch": 1.5562556255625561, "grad_norm": 2.7993178367614746, "learning_rate": 1.5767640644675422e-06, "loss": 0.5344, "step": 2593 }, { "epoch": 1.5568556855685567, "grad_norm": 4.325109004974365, "learning_rate": 1.5786884641032837e-06, "loss": 0.3308, "step": 2594 }, { "epoch": 1.5574557455745575, "grad_norm": 3.7445337772369385, "learning_rate": 1.5806096470436553e-06, "loss": 0.4096, "step": 2595 }, { "epoch": 1.558055805580558, "grad_norm": 3.3951001167297363, "learning_rate": 1.5825276026095788e-06, "loss": 0.2801, "step": 2596 }, { "epoch": 1.5586558655865588, "grad_norm": 6.142571449279785, "learning_rate": 1.5844423201399133e-06, "loss": 0.4671, "step": 2597 }, { "epoch": 1.5592559255925593, "grad_norm": 4.234132766723633, "learning_rate": 1.5863537889915178e-06, "loss": 0.3989, "step": 2598 }, { "epoch": 1.5598559855985599, "grad_norm": 4.249710559844971, "learning_rate": 1.5882619985393096e-06, "loss": 0.3225, "step": 2599 }, { "epoch": 1.5604560456045604, "grad_norm": 4.342567443847656, "learning_rate": 1.5901669381763232e-06, "loss": 0.3419, "step": 2600 }, { "epoch": 1.561056105610561, "grad_norm": 4.08341646194458, "learning_rate": 1.5920685973137671e-06, "loss": 0.3711, "step": 2601 }, { "epoch": 1.5616561656165615, "grad_norm": 3.44064998626709, "learning_rate": 1.5939669653810876e-06, "loss": 0.33, "step": 2602 }, { "epoch": 1.5622562256225623, "grad_norm": 3.9174985885620117, "learning_rate": 1.5958620318260236e-06, "loss": 0.2904, "step": 2603 }, { "epoch": 1.5628562856285628, "grad_norm": 3.7782886028289795, "learning_rate": 1.597753786114666e-06, "loss": 0.43, "step": 2604 }, { "epoch": 1.5634563456345636, "grad_norm": 3.436164617538452, "learning_rate": 1.5996422177315178e-06, "loss": 0.5031, "step": 2605 }, { "epoch": 1.5640564056405641, "grad_norm": 4.397095680236816, "learning_rate": 1.60152731617955e-06, "loss": 0.4424, "step": 2606 }, { "epoch": 1.5646564656465647, "grad_norm": 6.729672431945801, "learning_rate": 1.6034090709802624e-06, "loss": 0.5985, "step": 2607 }, { "epoch": 1.5652565256525652, "grad_norm": 4.268892765045166, "learning_rate": 1.6052874716737392e-06, "loss": 0.249, "step": 2608 }, { "epoch": 1.5658565856585658, "grad_norm": 4.285787582397461, "learning_rate": 1.607162507818711e-06, "loss": 0.3295, "step": 2609 }, { "epoch": 1.5664566456645663, "grad_norm": 3.2359602451324463, "learning_rate": 1.609034168992609e-06, "loss": 0.2036, "step": 2610 }, { "epoch": 1.567056705670567, "grad_norm": 3.399799108505249, "learning_rate": 1.6109024447916248e-06, "loss": 0.3875, "step": 2611 }, { "epoch": 1.5676567656765676, "grad_norm": 3.399493455886841, "learning_rate": 1.6127673248307683e-06, "loss": 0.3497, "step": 2612 }, { "epoch": 1.5682568256825684, "grad_norm": 5.24096155166626, "learning_rate": 1.6146287987439258e-06, "loss": 0.3753, "step": 2613 }, { "epoch": 1.568856885688569, "grad_norm": 4.44097375869751, "learning_rate": 1.6164868561839138e-06, "loss": 0.3343, "step": 2614 }, { "epoch": 1.5694569456945695, "grad_norm": 5.540931224822998, "learning_rate": 1.6183414868225426e-06, "loss": 0.4147, "step": 2615 }, { "epoch": 1.57005700570057, "grad_norm": 2.439009666442871, "learning_rate": 1.6201926803506702e-06, "loss": 0.2523, "step": 2616 }, { "epoch": 1.5706570657065706, "grad_norm": 4.713293075561523, "learning_rate": 1.6220404264782594e-06, "loss": 0.3434, "step": 2617 }, { "epoch": 1.5712571257125711, "grad_norm": 3.140237331390381, "learning_rate": 1.6238847149344364e-06, "loss": 0.2097, "step": 2618 }, { "epoch": 1.5718571857185717, "grad_norm": 5.752660274505615, "learning_rate": 1.6257255354675458e-06, "loss": 0.3202, "step": 2619 }, { "epoch": 1.5724572457245725, "grad_norm": 3.2149455547332764, "learning_rate": 1.6275628778452118e-06, "loss": 0.261, "step": 2620 }, { "epoch": 1.573057305730573, "grad_norm": 5.670743942260742, "learning_rate": 1.6293967318543885e-06, "loss": 0.428, "step": 2621 }, { "epoch": 1.5736573657365738, "grad_norm": 4.786375999450684, "learning_rate": 1.631227087301423e-06, "loss": 0.2557, "step": 2622 }, { "epoch": 1.5742574257425743, "grad_norm": 4.466300010681152, "learning_rate": 1.6330539340121099e-06, "loss": 0.3351, "step": 2623 }, { "epoch": 1.5748574857485749, "grad_norm": 2.6659598350524902, "learning_rate": 1.6348772618317442e-06, "loss": 0.2554, "step": 2624 }, { "epoch": 1.5754575457545754, "grad_norm": 4.5973992347717285, "learning_rate": 1.6366970606251851e-06, "loss": 0.3573, "step": 2625 }, { "epoch": 1.576057605760576, "grad_norm": 3.8288910388946533, "learning_rate": 1.6385133202769068e-06, "loss": 0.2956, "step": 2626 }, { "epoch": 1.5766576657665765, "grad_norm": 4.529533863067627, "learning_rate": 1.640326030691054e-06, "loss": 0.3775, "step": 2627 }, { "epoch": 1.5772577257725773, "grad_norm": 5.917947769165039, "learning_rate": 1.6421351817915023e-06, "loss": 0.5115, "step": 2628 }, { "epoch": 1.5778577857785778, "grad_norm": 5.114860534667969, "learning_rate": 1.6439407635219125e-06, "loss": 0.2399, "step": 2629 }, { "epoch": 1.5784578457845786, "grad_norm": 5.677206039428711, "learning_rate": 1.645742765845785e-06, "loss": 0.4698, "step": 2630 }, { "epoch": 1.5790579057905791, "grad_norm": 3.020110845565796, "learning_rate": 1.6475411787465155e-06, "loss": 0.2171, "step": 2631 }, { "epoch": 1.5796579657965797, "grad_norm": 4.485629081726074, "learning_rate": 1.649335992227455e-06, "loss": 0.3487, "step": 2632 }, { "epoch": 1.5802580258025802, "grad_norm": 8.602441787719727, "learning_rate": 1.6511271963119607e-06, "loss": 0.6939, "step": 2633 }, { "epoch": 1.5808580858085808, "grad_norm": 3.3998539447784424, "learning_rate": 1.6529147810434515e-06, "loss": 0.4123, "step": 2634 }, { "epoch": 1.5814581458145813, "grad_norm": 5.361044406890869, "learning_rate": 1.6546987364854666e-06, "loss": 0.3632, "step": 2635 }, { "epoch": 1.582058205820582, "grad_norm": 4.32744836807251, "learning_rate": 1.656479052721719e-06, "loss": 0.207, "step": 2636 }, { "epoch": 1.5826582658265826, "grad_norm": 3.4945099353790283, "learning_rate": 1.658255719856149e-06, "loss": 0.2913, "step": 2637 }, { "epoch": 1.5832583258325834, "grad_norm": 4.6483330726623535, "learning_rate": 1.6600287280129823e-06, "loss": 0.3737, "step": 2638 }, { "epoch": 1.583858385838584, "grad_norm": 6.3462042808532715, "learning_rate": 1.6617980673367824e-06, "loss": 0.5277, "step": 2639 }, { "epoch": 1.5844584458445845, "grad_norm": 2.629729986190796, "learning_rate": 1.6635637279925088e-06, "loss": 0.1952, "step": 2640 }, { "epoch": 1.585058505850585, "grad_norm": 4.265350818634033, "learning_rate": 1.665325700165565e-06, "loss": 0.4534, "step": 2641 }, { "epoch": 1.5856585658565856, "grad_norm": 5.7001118659973145, "learning_rate": 1.6670839740618605e-06, "loss": 0.3713, "step": 2642 }, { "epoch": 1.5862586258625861, "grad_norm": 6.429010391235352, "learning_rate": 1.6688385399078617e-06, "loss": 0.2765, "step": 2643 }, { "epoch": 1.5868586858685867, "grad_norm": 3.1087849140167236, "learning_rate": 1.6705893879506444e-06, "loss": 0.2537, "step": 2644 }, { "epoch": 1.5874587458745875, "grad_norm": 4.307229042053223, "learning_rate": 1.672336508457953e-06, "loss": 0.4255, "step": 2645 }, { "epoch": 1.588058805880588, "grad_norm": 3.5462772846221924, "learning_rate": 1.6740798917182498e-06, "loss": 0.2142, "step": 2646 }, { "epoch": 1.5886588658865888, "grad_norm": 3.7435734272003174, "learning_rate": 1.6758195280407722e-06, "loss": 0.2682, "step": 2647 }, { "epoch": 1.5892589258925893, "grad_norm": 3.7049684524536133, "learning_rate": 1.677555407755584e-06, "loss": 0.2602, "step": 2648 }, { "epoch": 1.5898589858985899, "grad_norm": 7.466597557067871, "learning_rate": 1.6792875212136326e-06, "loss": 0.5373, "step": 2649 }, { "epoch": 1.5904590459045904, "grad_norm": 3.8174779415130615, "learning_rate": 1.681015858786797e-06, "loss": 0.2583, "step": 2650 }, { "epoch": 1.591059105910591, "grad_norm": 7.194674968719482, "learning_rate": 1.6827404108679484e-06, "loss": 0.5023, "step": 2651 }, { "epoch": 1.5916591659165915, "grad_norm": 3.7568199634552, "learning_rate": 1.684461167870998e-06, "loss": 0.3063, "step": 2652 }, { "epoch": 1.5922592259225923, "grad_norm": 5.328989028930664, "learning_rate": 1.6861781202309536e-06, "loss": 0.4216, "step": 2653 }, { "epoch": 1.5928592859285928, "grad_norm": 5.230381965637207, "learning_rate": 1.6878912584039693e-06, "loss": 0.4522, "step": 2654 }, { "epoch": 1.5934593459345936, "grad_norm": 3.614877462387085, "learning_rate": 1.6896005728674037e-06, "loss": 0.3033, "step": 2655 }, { "epoch": 1.5940594059405941, "grad_norm": 6.010671138763428, "learning_rate": 1.6913060541198676e-06, "loss": 0.4793, "step": 2656 }, { "epoch": 1.5946594659465947, "grad_norm": 4.099325180053711, "learning_rate": 1.6930076926812795e-06, "loss": 0.4192, "step": 2657 }, { "epoch": 1.5952595259525952, "grad_norm": 5.393776893615723, "learning_rate": 1.6947054790929184e-06, "loss": 0.4221, "step": 2658 }, { "epoch": 1.5958595859585958, "grad_norm": 2.585317373275757, "learning_rate": 1.6963994039174754e-06, "loss": 0.3047, "step": 2659 }, { "epoch": 1.5964596459645963, "grad_norm": 2.4448764324188232, "learning_rate": 1.698089457739107e-06, "loss": 0.4533, "step": 2660 }, { "epoch": 1.597059705970597, "grad_norm": 4.248186111450195, "learning_rate": 1.6997756311634867e-06, "loss": 0.3087, "step": 2661 }, { "epoch": 1.5976597659765976, "grad_norm": 3.9211251735687256, "learning_rate": 1.701457914817858e-06, "loss": 0.3624, "step": 2662 }, { "epoch": 1.5982598259825984, "grad_norm": 4.10072135925293, "learning_rate": 1.7031362993510857e-06, "loss": 0.2712, "step": 2663 }, { "epoch": 1.598859885988599, "grad_norm": 3.6377999782562256, "learning_rate": 1.704810775433708e-06, "loss": 0.2829, "step": 2664 }, { "epoch": 1.5994599459945995, "grad_norm": 3.5159523487091064, "learning_rate": 1.7064813337579886e-06, "loss": 0.1842, "step": 2665 }, { "epoch": 1.6000600060006, "grad_norm": 4.350778579711914, "learning_rate": 1.7081479650379693e-06, "loss": 0.2589, "step": 2666 }, { "epoch": 1.6006600660066006, "grad_norm": 3.765014171600342, "learning_rate": 1.7098106600095199e-06, "loss": 0.2825, "step": 2667 }, { "epoch": 1.6012601260126011, "grad_norm": 5.074987411499023, "learning_rate": 1.7114694094303907e-06, "loss": 0.5168, "step": 2668 }, { "epoch": 1.6018601860186017, "grad_norm": 3.5296058654785156, "learning_rate": 1.713124204080265e-06, "loss": 0.4369, "step": 2669 }, { "epoch": 1.6024602460246025, "grad_norm": 5.289811134338379, "learning_rate": 1.714775034760806e-06, "loss": 0.339, "step": 2670 }, { "epoch": 1.603060306030603, "grad_norm": 4.918704986572266, "learning_rate": 1.716421892295714e-06, "loss": 0.3258, "step": 2671 }, { "epoch": 1.6036603660366038, "grad_norm": 4.476973056793213, "learning_rate": 1.7180647675307738e-06, "loss": 0.302, "step": 2672 }, { "epoch": 1.6042604260426043, "grad_norm": 3.859330177307129, "learning_rate": 1.7197036513339044e-06, "loss": 0.2928, "step": 2673 }, { "epoch": 1.6048604860486049, "grad_norm": 2.460667133331299, "learning_rate": 1.7213385345952132e-06, "loss": 0.1988, "step": 2674 }, { "epoch": 1.6054605460546054, "grad_norm": 5.902770519256592, "learning_rate": 1.7229694082270455e-06, "loss": 0.4616, "step": 2675 }, { "epoch": 1.606060606060606, "grad_norm": 6.213374614715576, "learning_rate": 1.7245962631640341e-06, "loss": 0.3, "step": 2676 }, { "epoch": 1.6066606660666065, "grad_norm": 7.145264625549316, "learning_rate": 1.726219090363148e-06, "loss": 0.512, "step": 2677 }, { "epoch": 1.6072607260726073, "grad_norm": 4.31134557723999, "learning_rate": 1.7278378808037476e-06, "loss": 0.3515, "step": 2678 }, { "epoch": 1.6078607860786078, "grad_norm": 4.86958122253418, "learning_rate": 1.7294526254876308e-06, "loss": 0.4214, "step": 2679 }, { "epoch": 1.6084608460846086, "grad_norm": 9.057579040527344, "learning_rate": 1.731063315439084e-06, "loss": 0.5678, "step": 2680 }, { "epoch": 1.6090609060906091, "grad_norm": 5.107901573181152, "learning_rate": 1.7326699417049318e-06, "loss": 0.2923, "step": 2681 }, { "epoch": 1.6096609660966097, "grad_norm": 5.233755588531494, "learning_rate": 1.7342724953545895e-06, "loss": 0.4402, "step": 2682 }, { "epoch": 1.6102610261026102, "grad_norm": 4.155186653137207, "learning_rate": 1.7358709674801078e-06, "loss": 0.4201, "step": 2683 }, { "epoch": 1.6108610861086108, "grad_norm": 5.250776290893555, "learning_rate": 1.7374653491962263e-06, "loss": 0.3367, "step": 2684 }, { "epoch": 1.6114611461146113, "grad_norm": 5.447802543640137, "learning_rate": 1.7390556316404207e-06, "loss": 0.3885, "step": 2685 }, { "epoch": 1.612061206120612, "grad_norm": 4.173274517059326, "learning_rate": 1.7406418059729548e-06, "loss": 0.2543, "step": 2686 }, { "epoch": 1.6126612661266126, "grad_norm": 4.772523403167725, "learning_rate": 1.7422238633769247e-06, "loss": 0.3217, "step": 2687 }, { "epoch": 1.6132613261326134, "grad_norm": 5.366300582885742, "learning_rate": 1.7438017950583131e-06, "loss": 0.4493, "step": 2688 }, { "epoch": 1.613861386138614, "grad_norm": 4.843292236328125, "learning_rate": 1.7453755922460351e-06, "loss": 0.3598, "step": 2689 }, { "epoch": 1.6144614461446145, "grad_norm": 4.007680416107178, "learning_rate": 1.7469452461919885e-06, "loss": 0.4177, "step": 2690 }, { "epoch": 1.615061506150615, "grad_norm": 3.4740986824035645, "learning_rate": 1.7485107481711005e-06, "loss": 0.2894, "step": 2691 }, { "epoch": 1.6156615661566156, "grad_norm": 4.6730828285217285, "learning_rate": 1.7500720894813795e-06, "loss": 0.1919, "step": 2692 }, { "epoch": 1.6162616261626161, "grad_norm": 4.866513252258301, "learning_rate": 1.7516292614439584e-06, "loss": 0.3733, "step": 2693 }, { "epoch": 1.6168616861686167, "grad_norm": 4.463509559631348, "learning_rate": 1.7531822554031478e-06, "loss": 0.3417, "step": 2694 }, { "epoch": 1.6174617461746175, "grad_norm": 4.097817897796631, "learning_rate": 1.7547310627264817e-06, "loss": 0.423, "step": 2695 }, { "epoch": 1.618061806180618, "grad_norm": 5.29617977142334, "learning_rate": 1.7562756748047663e-06, "loss": 0.4874, "step": 2696 }, { "epoch": 1.6186618661866188, "grad_norm": 3.66845965385437, "learning_rate": 1.757816083052127e-06, "loss": 0.4031, "step": 2697 }, { "epoch": 1.6192619261926193, "grad_norm": 5.017975330352783, "learning_rate": 1.7593522789060567e-06, "loss": 0.37, "step": 2698 }, { "epoch": 1.6198619861986199, "grad_norm": 3.4474380016326904, "learning_rate": 1.7608842538274638e-06, "loss": 0.3534, "step": 2699 }, { "epoch": 1.6204620462046204, "grad_norm": 3.3607561588287354, "learning_rate": 1.7624119993007173e-06, "loss": 0.243, "step": 2700 }, { "epoch": 1.621062106210621, "grad_norm": 4.869565486907959, "learning_rate": 1.7639355068336985e-06, "loss": 0.3173, "step": 2701 }, { "epoch": 1.6216621662166215, "grad_norm": 3.699211597442627, "learning_rate": 1.765454767957844e-06, "loss": 0.1901, "step": 2702 }, { "epoch": 1.6222622262226223, "grad_norm": 3.205925703048706, "learning_rate": 1.7669697742281954e-06, "loss": 0.2574, "step": 2703 }, { "epoch": 1.6228622862286228, "grad_norm": 5.548807144165039, "learning_rate": 1.7684805172234448e-06, "loss": 0.4094, "step": 2704 }, { "epoch": 1.6234623462346236, "grad_norm": 4.0309319496154785, "learning_rate": 1.7699869885459826e-06, "loss": 0.477, "step": 2705 }, { "epoch": 1.6240624062406241, "grad_norm": 2.8962862491607666, "learning_rate": 1.771489179821943e-06, "loss": 0.2084, "step": 2706 }, { "epoch": 1.6246624662466247, "grad_norm": 5.127158164978027, "learning_rate": 1.7729870827012511e-06, "loss": 0.4152, "step": 2707 }, { "epoch": 1.6252625262526252, "grad_norm": 5.370419502258301, "learning_rate": 1.7744806888576708e-06, "loss": 0.7481, "step": 2708 }, { "epoch": 1.6258625862586258, "grad_norm": 4.3360161781311035, "learning_rate": 1.7759699899888486e-06, "loss": 0.2839, "step": 2709 }, { "epoch": 1.6264626462646263, "grad_norm": 4.4906439781188965, "learning_rate": 1.7774549778163612e-06, "loss": 0.2839, "step": 2710 }, { "epoch": 1.627062706270627, "grad_norm": 4.201595783233643, "learning_rate": 1.7789356440857614e-06, "loss": 0.4894, "step": 2711 }, { "epoch": 1.6276627662766276, "grad_norm": 3.1352474689483643, "learning_rate": 1.7804119805666241e-06, "loss": 0.2136, "step": 2712 }, { "epoch": 1.6282628262826284, "grad_norm": 3.0171658992767334, "learning_rate": 1.7818839790525902e-06, "loss": 0.212, "step": 2713 }, { "epoch": 1.628862886288629, "grad_norm": 4.912055969238281, "learning_rate": 1.7833516313614151e-06, "loss": 0.379, "step": 2714 }, { "epoch": 1.6294629462946295, "grad_norm": 5.9543890953063965, "learning_rate": 1.784814929335014e-06, "loss": 0.4936, "step": 2715 }, { "epoch": 1.63006300630063, "grad_norm": 4.9395432472229, "learning_rate": 1.7862738648395018e-06, "loss": 0.2917, "step": 2716 }, { "epoch": 1.6306630663066306, "grad_norm": 5.680269241333008, "learning_rate": 1.787728429765248e-06, "loss": 0.4165, "step": 2717 }, { "epoch": 1.6312631263126312, "grad_norm": 4.02926778793335, "learning_rate": 1.7891786160269135e-06, "loss": 0.3616, "step": 2718 }, { "epoch": 1.6318631863186317, "grad_norm": 4.710684776306152, "learning_rate": 1.7906244155634978e-06, "loss": 0.5102, "step": 2719 }, { "epoch": 1.6324632463246325, "grad_norm": 4.833359718322754, "learning_rate": 1.7920658203383861e-06, "loss": 0.2997, "step": 2720 }, { "epoch": 1.633063306330633, "grad_norm": 5.926268100738525, "learning_rate": 1.7935028223393908e-06, "loss": 0.3684, "step": 2721 }, { "epoch": 1.6336633663366338, "grad_norm": 3.0371382236480713, "learning_rate": 1.7949354135788003e-06, "loss": 0.3213, "step": 2722 }, { "epoch": 1.6342634263426343, "grad_norm": 4.811895370483398, "learning_rate": 1.7963635860934158e-06, "loss": 0.5254, "step": 2723 }, { "epoch": 1.6348634863486349, "grad_norm": 4.760283470153809, "learning_rate": 1.7977873319446057e-06, "loss": 0.3944, "step": 2724 }, { "epoch": 1.6354635463546354, "grad_norm": 3.143402576446533, "learning_rate": 1.799206643218342e-06, "loss": 0.2756, "step": 2725 }, { "epoch": 1.636063606360636, "grad_norm": 2.687922477722168, "learning_rate": 1.8006215120252448e-06, "loss": 0.2971, "step": 2726 }, { "epoch": 1.6366636663666365, "grad_norm": 4.500201225280762, "learning_rate": 1.8020319305006317e-06, "loss": 0.3963, "step": 2727 }, { "epoch": 1.6372637263726373, "grad_norm": 6.399655818939209, "learning_rate": 1.8034378908045563e-06, "loss": 0.532, "step": 2728 }, { "epoch": 1.6378637863786378, "grad_norm": 4.682260513305664, "learning_rate": 1.8048393851218521e-06, "loss": 0.3825, "step": 2729 }, { "epoch": 1.6384638463846386, "grad_norm": 4.58604621887207, "learning_rate": 1.8062364056621792e-06, "loss": 0.386, "step": 2730 }, { "epoch": 1.6390639063906391, "grad_norm": 6.998022079467773, "learning_rate": 1.8076289446600644e-06, "loss": 0.8747, "step": 2731 }, { "epoch": 1.6396639663966397, "grad_norm": 3.423837661743164, "learning_rate": 1.8090169943749474e-06, "loss": 0.2928, "step": 2732 }, { "epoch": 1.6402640264026402, "grad_norm": 4.135504722595215, "learning_rate": 1.810400547091219e-06, "loss": 0.272, "step": 2733 }, { "epoch": 1.6408640864086408, "grad_norm": 4.162041187286377, "learning_rate": 1.811779595118269e-06, "loss": 0.4617, "step": 2734 }, { "epoch": 1.6414641464146413, "grad_norm": 3.628476142883301, "learning_rate": 1.8131541307905275e-06, "loss": 0.2576, "step": 2735 }, { "epoch": 1.642064206420642, "grad_norm": 6.105793476104736, "learning_rate": 1.814524146467505e-06, "loss": 0.3829, "step": 2736 }, { "epoch": 1.6426642664266426, "grad_norm": 5.541685581207275, "learning_rate": 1.8158896345338382e-06, "loss": 0.4289, "step": 2737 }, { "epoch": 1.6432643264326434, "grad_norm": 4.260804176330566, "learning_rate": 1.8172505873993309e-06, "loss": 0.3391, "step": 2738 }, { "epoch": 1.643864386438644, "grad_norm": 5.58978796005249, "learning_rate": 1.8186069974989955e-06, "loss": 0.3948, "step": 2739 }, { "epoch": 1.6444644464446445, "grad_norm": 3.910862922668457, "learning_rate": 1.8199588572930966e-06, "loss": 0.2633, "step": 2740 }, { "epoch": 1.645064506450645, "grad_norm": 4.000960350036621, "learning_rate": 1.8213061592671921e-06, "loss": 0.2194, "step": 2741 }, { "epoch": 1.6456645664566456, "grad_norm": 4.357994079589844, "learning_rate": 1.8226488959321739e-06, "loss": 0.3867, "step": 2742 }, { "epoch": 1.6462646264626462, "grad_norm": 6.118843078613281, "learning_rate": 1.823987059824312e-06, "loss": 0.2434, "step": 2743 }, { "epoch": 1.6468646864686467, "grad_norm": 3.905249834060669, "learning_rate": 1.8253206435052934e-06, "loss": 0.2925, "step": 2744 }, { "epoch": 1.6474647464746475, "grad_norm": 3.353607177734375, "learning_rate": 1.8266496395622655e-06, "loss": 0.3435, "step": 2745 }, { "epoch": 1.648064806480648, "grad_norm": 6.135016441345215, "learning_rate": 1.8279740406078763e-06, "loss": 0.4043, "step": 2746 }, { "epoch": 1.6486648664866488, "grad_norm": 5.767273426055908, "learning_rate": 1.8292938392803156e-06, "loss": 0.3882, "step": 2747 }, { "epoch": 1.6492649264926493, "grad_norm": 5.616554260253906, "learning_rate": 1.830609028243356e-06, "loss": 0.6471, "step": 2748 }, { "epoch": 1.6498649864986499, "grad_norm": 2.7337353229522705, "learning_rate": 1.8319196001863923e-06, "loss": 0.3449, "step": 2749 }, { "epoch": 1.6504650465046504, "grad_norm": 5.2091450691223145, "learning_rate": 1.8332255478244853e-06, "loss": 0.4174, "step": 2750 }, { "epoch": 1.651065106510651, "grad_norm": 6.2082109451293945, "learning_rate": 1.8345268638983999e-06, "loss": 0.3216, "step": 2751 }, { "epoch": 1.6516651665166515, "grad_norm": 4.947379112243652, "learning_rate": 1.8358235411746455e-06, "loss": 0.3817, "step": 2752 }, { "epoch": 1.6522652265226523, "grad_norm": 3.931992769241333, "learning_rate": 1.8371155724455172e-06, "loss": 0.3111, "step": 2753 }, { "epoch": 1.6528652865286528, "grad_norm": 4.3004584312438965, "learning_rate": 1.8384029505291357e-06, "loss": 0.3133, "step": 2754 }, { "epoch": 1.6534653465346536, "grad_norm": 3.82171630859375, "learning_rate": 1.8396856682694848e-06, "loss": 0.4206, "step": 2755 }, { "epoch": 1.6540654065406541, "grad_norm": 4.511987209320068, "learning_rate": 1.840963718536456e-06, "loss": 0.2886, "step": 2756 }, { "epoch": 1.6546654665466547, "grad_norm": 2.9685747623443604, "learning_rate": 1.8422370942258842e-06, "loss": 0.189, "step": 2757 }, { "epoch": 1.6552655265526552, "grad_norm": 4.38961935043335, "learning_rate": 1.8435057882595881e-06, "loss": 0.2827, "step": 2758 }, { "epoch": 1.6558655865586558, "grad_norm": 4.848137855529785, "learning_rate": 1.84476979358541e-06, "loss": 0.5095, "step": 2759 }, { "epoch": 1.6564656465646563, "grad_norm": 5.5019965171813965, "learning_rate": 1.8460291031772556e-06, "loss": 0.4185, "step": 2760 }, { "epoch": 1.657065706570657, "grad_norm": 5.765497207641602, "learning_rate": 1.8472837100351314e-06, "loss": 0.4987, "step": 2761 }, { "epoch": 1.6576657665766577, "grad_norm": 3.972341537475586, "learning_rate": 1.8485336071851845e-06, "loss": 0.2185, "step": 2762 }, { "epoch": 1.6582658265826584, "grad_norm": 3.6481869220733643, "learning_rate": 1.849778787679742e-06, "loss": 0.3997, "step": 2763 }, { "epoch": 1.658865886588659, "grad_norm": 3.52909779548645, "learning_rate": 1.8510192445973485e-06, "loss": 0.4183, "step": 2764 }, { "epoch": 1.6594659465946595, "grad_norm": 3.632376194000244, "learning_rate": 1.8522549710428049e-06, "loss": 0.419, "step": 2765 }, { "epoch": 1.66006600660066, "grad_norm": 5.516716957092285, "learning_rate": 1.8534859601472065e-06, "loss": 0.4913, "step": 2766 }, { "epoch": 1.6606660666066606, "grad_norm": 9.113051414489746, "learning_rate": 1.854712205067984e-06, "loss": 0.8117, "step": 2767 }, { "epoch": 1.6612661266126612, "grad_norm": 3.991542100906372, "learning_rate": 1.8559336989889365e-06, "loss": 0.4371, "step": 2768 }, { "epoch": 1.6618661866186617, "grad_norm": 3.7364888191223145, "learning_rate": 1.8571504351202722e-06, "loss": 0.4502, "step": 2769 }, { "epoch": 1.6624662466246625, "grad_norm": 3.5573785305023193, "learning_rate": 1.8583624066986472e-06, "loss": 0.3062, "step": 2770 }, { "epoch": 1.663066306630663, "grad_norm": 4.315479755401611, "learning_rate": 1.8595696069872013e-06, "loss": 0.3667, "step": 2771 }, { "epoch": 1.6636663666366638, "grad_norm": 5.739681243896484, "learning_rate": 1.860772029275595e-06, "loss": 0.4486, "step": 2772 }, { "epoch": 1.6642664266426643, "grad_norm": 4.021652698516846, "learning_rate": 1.8619696668800486e-06, "loss": 0.3618, "step": 2773 }, { "epoch": 1.6648664866486649, "grad_norm": 3.7746644020080566, "learning_rate": 1.86316251314338e-06, "loss": 0.3104, "step": 2774 }, { "epoch": 1.6654665466546654, "grad_norm": 3.915433883666992, "learning_rate": 1.8643505614350374e-06, "loss": 0.3895, "step": 2775 }, { "epoch": 1.666066606660666, "grad_norm": 4.905813694000244, "learning_rate": 1.8655338051511408e-06, "loss": 0.3461, "step": 2776 }, { "epoch": 1.6666666666666665, "grad_norm": 3.092043399810791, "learning_rate": 1.8667122377145168e-06, "loss": 0.5146, "step": 2777 }, { "epoch": 1.6672667266726673, "grad_norm": 4.3236308097839355, "learning_rate": 1.8678858525747342e-06, "loss": 0.5157, "step": 2778 }, { "epoch": 1.6678667866786678, "grad_norm": 4.919466495513916, "learning_rate": 1.869054643208142e-06, "loss": 0.27, "step": 2779 }, { "epoch": 1.6684668466846686, "grad_norm": 5.272736549377441, "learning_rate": 1.8702186031179059e-06, "loss": 0.534, "step": 2780 }, { "epoch": 1.6690669066906691, "grad_norm": 5.26390266418457, "learning_rate": 1.8713777258340428e-06, "loss": 0.3064, "step": 2781 }, { "epoch": 1.6696669666966697, "grad_norm": 4.364483833312988, "learning_rate": 1.872532004913458e-06, "loss": 0.2739, "step": 2782 }, { "epoch": 1.6702670267026702, "grad_norm": 4.265388011932373, "learning_rate": 1.8736814339399802e-06, "loss": 0.2566, "step": 2783 }, { "epoch": 1.6708670867086708, "grad_norm": 4.055014133453369, "learning_rate": 1.8748260065243984e-06, "loss": 0.3336, "step": 2784 }, { "epoch": 1.6714671467146713, "grad_norm": 4.247943878173828, "learning_rate": 1.875965716304495e-06, "loss": 0.3416, "step": 2785 }, { "epoch": 1.672067206720672, "grad_norm": 3.6733267307281494, "learning_rate": 1.877100556945085e-06, "loss": 0.3994, "step": 2786 }, { "epoch": 1.6726672667266727, "grad_norm": 4.611927032470703, "learning_rate": 1.8782305221380465e-06, "loss": 0.3492, "step": 2787 }, { "epoch": 1.6732673267326734, "grad_norm": 3.492692708969116, "learning_rate": 1.8793556056023604e-06, "loss": 0.5322, "step": 2788 }, { "epoch": 1.673867386738674, "grad_norm": 5.05100154876709, "learning_rate": 1.8804758010841422e-06, "loss": 0.4114, "step": 2789 }, { "epoch": 1.6744674467446745, "grad_norm": 3.9963319301605225, "learning_rate": 1.8815911023566778e-06, "loss": 0.2971, "step": 2790 }, { "epoch": 1.675067506750675, "grad_norm": 4.356730937957764, "learning_rate": 1.8827015032204582e-06, "loss": 0.5264, "step": 2791 }, { "epoch": 1.6756675667566756, "grad_norm": 7.870824337005615, "learning_rate": 1.8838069975032127e-06, "loss": 0.6342, "step": 2792 }, { "epoch": 1.6762676267626762, "grad_norm": 5.7294087409973145, "learning_rate": 1.8849075790599462e-06, "loss": 0.5686, "step": 2793 }, { "epoch": 1.6768676867686767, "grad_norm": 4.257359504699707, "learning_rate": 1.8860032417729701e-06, "loss": 0.2422, "step": 2794 }, { "epoch": 1.6774677467746775, "grad_norm": 5.170255661010742, "learning_rate": 1.8870939795519379e-06, "loss": 0.3758, "step": 2795 }, { "epoch": 1.678067806780678, "grad_norm": 4.763425827026367, "learning_rate": 1.8881797863338793e-06, "loss": 0.3485, "step": 2796 }, { "epoch": 1.6786678667866788, "grad_norm": 5.381784439086914, "learning_rate": 1.8892606560832335e-06, "loss": 0.3083, "step": 2797 }, { "epoch": 1.6792679267926793, "grad_norm": 3.0328140258789062, "learning_rate": 1.8903365827918812e-06, "loss": 0.4557, "step": 2798 }, { "epoch": 1.6798679867986799, "grad_norm": 3.8596079349517822, "learning_rate": 1.8914075604791808e-06, "loss": 0.408, "step": 2799 }, { "epoch": 1.6804680468046804, "grad_norm": 5.258942127227783, "learning_rate": 1.8924735831920006e-06, "loss": 0.331, "step": 2800 }, { "epoch": 1.681068106810681, "grad_norm": 4.3965349197387695, "learning_rate": 1.8935346450047507e-06, "loss": 0.3975, "step": 2801 }, { "epoch": 1.6816681668166815, "grad_norm": 4.715716361999512, "learning_rate": 1.8945907400194173e-06, "loss": 0.5289, "step": 2802 }, { "epoch": 1.6822682268226823, "grad_norm": 4.009110927581787, "learning_rate": 1.8956418623655944e-06, "loss": 0.3532, "step": 2803 }, { "epoch": 1.6828682868286828, "grad_norm": 5.082313060760498, "learning_rate": 1.8966880062005186e-06, "loss": 0.3584, "step": 2804 }, { "epoch": 1.6834683468346836, "grad_norm": 4.588597297668457, "learning_rate": 1.897729165709098e-06, "loss": 0.7453, "step": 2805 }, { "epoch": 1.6840684068406842, "grad_norm": 5.815594673156738, "learning_rate": 1.8987653351039477e-06, "loss": 0.585, "step": 2806 }, { "epoch": 1.6846684668466847, "grad_norm": 4.502045631408691, "learning_rate": 1.8997965086254212e-06, "loss": 0.6282, "step": 2807 }, { "epoch": 1.6852685268526852, "grad_norm": 5.418011665344238, "learning_rate": 1.9008226805416405e-06, "loss": 0.479, "step": 2808 }, { "epoch": 1.6858685868586858, "grad_norm": 5.162413597106934, "learning_rate": 1.9018438451485315e-06, "loss": 0.352, "step": 2809 }, { "epoch": 1.6864686468646863, "grad_norm": 6.994037628173828, "learning_rate": 1.9028599967698532e-06, "loss": 0.5526, "step": 2810 }, { "epoch": 1.687068706870687, "grad_norm": 5.201590061187744, "learning_rate": 1.9038711297572276e-06, "loss": 0.4536, "step": 2811 }, { "epoch": 1.6876687668766877, "grad_norm": 4.690576076507568, "learning_rate": 1.9048772384901758e-06, "loss": 0.4391, "step": 2812 }, { "epoch": 1.6882688268826884, "grad_norm": 3.1576552391052246, "learning_rate": 1.9058783173761462e-06, "loss": 0.2667, "step": 2813 }, { "epoch": 1.688868886888689, "grad_norm": 7.693470001220703, "learning_rate": 1.9068743608505454e-06, "loss": 0.4945, "step": 2814 }, { "epoch": 1.6894689468946895, "grad_norm": 3.030806541442871, "learning_rate": 1.90786536337677e-06, "loss": 0.272, "step": 2815 }, { "epoch": 1.69006900690069, "grad_norm": 4.288325786590576, "learning_rate": 1.908851319446237e-06, "loss": 0.2998, "step": 2816 }, { "epoch": 1.6906690669066906, "grad_norm": 2.7267374992370605, "learning_rate": 1.9098322235784164e-06, "loss": 0.2137, "step": 2817 }, { "epoch": 1.6912691269126912, "grad_norm": 4.667387962341309, "learning_rate": 1.910808070320857e-06, "loss": 0.4402, "step": 2818 }, { "epoch": 1.6918691869186917, "grad_norm": 4.4948201179504395, "learning_rate": 1.9117788542492215e-06, "loss": 0.511, "step": 2819 }, { "epoch": 1.6924692469246925, "grad_norm": 4.526422023773193, "learning_rate": 1.9127445699673147e-06, "loss": 0.3829, "step": 2820 }, { "epoch": 1.693069306930693, "grad_norm": 3.637216806411743, "learning_rate": 1.9137052121071122e-06, "loss": 0.3473, "step": 2821 }, { "epoch": 1.6936693669366938, "grad_norm": 3.591986894607544, "learning_rate": 1.914660775328793e-06, "loss": 0.2286, "step": 2822 }, { "epoch": 1.6942694269426943, "grad_norm": 5.21217679977417, "learning_rate": 1.915611254320767e-06, "loss": 0.2552, "step": 2823 }, { "epoch": 1.6948694869486949, "grad_norm": 3.350207805633545, "learning_rate": 1.916556643799706e-06, "loss": 0.4397, "step": 2824 }, { "epoch": 1.6954695469546954, "grad_norm": 4.075357437133789, "learning_rate": 1.917496938510571e-06, "loss": 0.6592, "step": 2825 }, { "epoch": 1.696069606960696, "grad_norm": 3.805753469467163, "learning_rate": 1.918432133226645e-06, "loss": 0.2688, "step": 2826 }, { "epoch": 1.6966696669666965, "grad_norm": 4.047800540924072, "learning_rate": 1.919362222749557e-06, "loss": 0.2993, "step": 2827 }, { "epoch": 1.6972697269726973, "grad_norm": 4.87150764465332, "learning_rate": 1.9202872019093154e-06, "loss": 0.4086, "step": 2828 }, { "epoch": 1.6978697869786978, "grad_norm": 4.276446342468262, "learning_rate": 1.9212070655643353e-06, "loss": 0.3245, "step": 2829 }, { "epoch": 1.6984698469846986, "grad_norm": 5.438924789428711, "learning_rate": 1.922121808601466e-06, "loss": 0.4935, "step": 2830 }, { "epoch": 1.6990699069906992, "grad_norm": 5.202275276184082, "learning_rate": 1.92303142593602e-06, "loss": 0.2602, "step": 2831 }, { "epoch": 1.6996699669966997, "grad_norm": 3.188985824584961, "learning_rate": 1.9239359125118033e-06, "loss": 0.3867, "step": 2832 }, { "epoch": 1.7002700270027002, "grad_norm": 4.975285530090332, "learning_rate": 1.924835263301139e-06, "loss": 0.4023, "step": 2833 }, { "epoch": 1.7008700870087008, "grad_norm": 3.198725461959839, "learning_rate": 1.9257294733049006e-06, "loss": 0.2503, "step": 2834 }, { "epoch": 1.7014701470147013, "grad_norm": 5.389831066131592, "learning_rate": 1.9266185375525354e-06, "loss": 0.4958, "step": 2835 }, { "epoch": 1.702070207020702, "grad_norm": 3.740307331085205, "learning_rate": 1.9275024511020944e-06, "loss": 0.4559, "step": 2836 }, { "epoch": 1.7026702670267027, "grad_norm": 4.263598918914795, "learning_rate": 1.9283812090402594e-06, "loss": 0.4421, "step": 2837 }, { "epoch": 1.7032703270327034, "grad_norm": 3.1471173763275146, "learning_rate": 1.9292548064823705e-06, "loss": 0.2532, "step": 2838 }, { "epoch": 1.703870387038704, "grad_norm": 5.427884578704834, "learning_rate": 1.9301232385724517e-06, "loss": 0.3755, "step": 2839 }, { "epoch": 1.7044704470447045, "grad_norm": 3.2970707416534424, "learning_rate": 1.9309865004832407e-06, "loss": 0.5418, "step": 2840 }, { "epoch": 1.705070507050705, "grad_norm": 8.415224075317383, "learning_rate": 1.9318445874162124e-06, "loss": 0.5792, "step": 2841 }, { "epoch": 1.7056705670567056, "grad_norm": 5.821825981140137, "learning_rate": 1.932697494601609e-06, "loss": 0.4628, "step": 2842 }, { "epoch": 1.7062706270627062, "grad_norm": 5.071554660797119, "learning_rate": 1.9335452172984637e-06, "loss": 0.3496, "step": 2843 }, { "epoch": 1.7068706870687067, "grad_norm": 3.682290554046631, "learning_rate": 1.9343877507946286e-06, "loss": 0.3902, "step": 2844 }, { "epoch": 1.7074707470747075, "grad_norm": 4.216845989227295, "learning_rate": 1.9352250904068e-06, "loss": 0.376, "step": 2845 }, { "epoch": 1.708070807080708, "grad_norm": 3.7820379734039307, "learning_rate": 1.9360572314805467e-06, "loss": 0.3943, "step": 2846 }, { "epoch": 1.7086708670867088, "grad_norm": 3.753103256225586, "learning_rate": 1.9368841693903307e-06, "loss": 0.5015, "step": 2847 }, { "epoch": 1.7092709270927093, "grad_norm": 5.411949157714844, "learning_rate": 1.9377058995395392e-06, "loss": 0.4458, "step": 2848 }, { "epoch": 1.7098709870987099, "grad_norm": 3.6868715286254883, "learning_rate": 1.9385224173605066e-06, "loss": 0.5777, "step": 2849 }, { "epoch": 1.7104710471047104, "grad_norm": 5.171012878417969, "learning_rate": 1.9393337183145397e-06, "loss": 0.4886, "step": 2850 }, { "epoch": 1.711071107110711, "grad_norm": 4.377120018005371, "learning_rate": 1.940139797891945e-06, "loss": 0.483, "step": 2851 }, { "epoch": 1.7116711671167115, "grad_norm": 4.084187984466553, "learning_rate": 1.940940651612051e-06, "loss": 0.4597, "step": 2852 }, { "epoch": 1.7122712271227123, "grad_norm": 3.680248737335205, "learning_rate": 1.9417362750232358e-06, "loss": 0.2544, "step": 2853 }, { "epoch": 1.7128712871287128, "grad_norm": 4.903841495513916, "learning_rate": 1.9425266637029504e-06, "loss": 0.4434, "step": 2854 }, { "epoch": 1.7134713471347136, "grad_norm": 2.363847494125366, "learning_rate": 1.943311813257743e-06, "loss": 0.2443, "step": 2855 }, { "epoch": 1.7140714071407142, "grad_norm": 4.51836633682251, "learning_rate": 1.9440917193232852e-06, "loss": 0.5398, "step": 2856 }, { "epoch": 1.7146714671467147, "grad_norm": 4.317435264587402, "learning_rate": 1.944866377564393e-06, "loss": 0.5039, "step": 2857 }, { "epoch": 1.7152715271527152, "grad_norm": 5.967813968658447, "learning_rate": 1.9456357836750556e-06, "loss": 0.4386, "step": 2858 }, { "epoch": 1.7158715871587158, "grad_norm": 3.2964115142822266, "learning_rate": 1.946399933378455e-06, "loss": 0.3199, "step": 2859 }, { "epoch": 1.7164716471647163, "grad_norm": 6.571217060089111, "learning_rate": 1.947158822426991e-06, "loss": 0.6304, "step": 2860 }, { "epoch": 1.717071707170717, "grad_norm": 4.916797161102295, "learning_rate": 1.947912446602307e-06, "loss": 0.5421, "step": 2861 }, { "epoch": 1.7176717671767177, "grad_norm": 5.106446743011475, "learning_rate": 1.94866080171531e-06, "loss": 0.3533, "step": 2862 }, { "epoch": 1.7182718271827184, "grad_norm": 5.154559135437012, "learning_rate": 1.949403883606196e-06, "loss": 0.2878, "step": 2863 }, { "epoch": 1.718871887188719, "grad_norm": 4.629251003265381, "learning_rate": 1.950141688144474e-06, "loss": 0.4498, "step": 2864 }, { "epoch": 1.7194719471947195, "grad_norm": 3.6095314025878906, "learning_rate": 1.9508742112289856e-06, "loss": 0.4246, "step": 2865 }, { "epoch": 1.72007200720072, "grad_norm": 4.829667091369629, "learning_rate": 1.951601448787932e-06, "loss": 0.3115, "step": 2866 }, { "epoch": 1.7206720672067206, "grad_norm": 5.224366188049316, "learning_rate": 1.952323396778892e-06, "loss": 0.6718, "step": 2867 }, { "epoch": 1.7212721272127212, "grad_norm": 3.5908827781677246, "learning_rate": 1.95304005118885e-06, "loss": 0.3287, "step": 2868 }, { "epoch": 1.7218721872187217, "grad_norm": 3.0154478549957275, "learning_rate": 1.953751408034213e-06, "loss": 0.2325, "step": 2869 }, { "epoch": 1.7224722472247225, "grad_norm": 4.073731899261475, "learning_rate": 1.9544574633608352e-06, "loss": 0.5052, "step": 2870 }, { "epoch": 1.723072307230723, "grad_norm": 3.4070281982421875, "learning_rate": 1.955158213244041e-06, "loss": 0.3086, "step": 2871 }, { "epoch": 1.7236723672367238, "grad_norm": 4.440038681030273, "learning_rate": 1.955853653788644e-06, "loss": 0.2587, "step": 2872 }, { "epoch": 1.7242724272427243, "grad_norm": 6.087347507476807, "learning_rate": 1.9565437811289728e-06, "loss": 0.5964, "step": 2873 }, { "epoch": 1.7248724872487249, "grad_norm": 5.277322292327881, "learning_rate": 1.957228591428887e-06, "loss": 0.3901, "step": 2874 }, { "epoch": 1.7254725472547254, "grad_norm": 4.026293754577637, "learning_rate": 1.957908080881803e-06, "loss": 0.3332, "step": 2875 }, { "epoch": 1.726072607260726, "grad_norm": 5.360611915588379, "learning_rate": 1.9585822457107136e-06, "loss": 0.4089, "step": 2876 }, { "epoch": 1.7266726672667265, "grad_norm": 4.20773983001709, "learning_rate": 1.959251082168209e-06, "loss": 0.2393, "step": 2877 }, { "epoch": 1.7272727272727273, "grad_norm": 3.284853219985962, "learning_rate": 1.959914586536498e-06, "loss": 0.3523, "step": 2878 }, { "epoch": 1.7278727872787278, "grad_norm": 4.015425682067871, "learning_rate": 1.960572755127427e-06, "loss": 0.3906, "step": 2879 }, { "epoch": 1.7284728472847286, "grad_norm": 5.143618106842041, "learning_rate": 1.961225584282503e-06, "loss": 0.4996, "step": 2880 }, { "epoch": 1.7290729072907292, "grad_norm": 5.2226972579956055, "learning_rate": 1.9618730703729128e-06, "loss": 0.5143, "step": 2881 }, { "epoch": 1.7296729672967297, "grad_norm": 4.171618461608887, "learning_rate": 1.9625152097995426e-06, "loss": 0.4223, "step": 2882 }, { "epoch": 1.7302730273027302, "grad_norm": 4.668267726898193, "learning_rate": 1.963151998992999e-06, "loss": 0.3707, "step": 2883 }, { "epoch": 1.7308730873087308, "grad_norm": 3.893111228942871, "learning_rate": 1.9637834344136274e-06, "loss": 0.2417, "step": 2884 }, { "epoch": 1.7314731473147313, "grad_norm": 4.558563232421875, "learning_rate": 1.9644095125515345e-06, "loss": 0.4585, "step": 2885 }, { "epoch": 1.7320732073207321, "grad_norm": 3.7976465225219727, "learning_rate": 1.9650302299266037e-06, "loss": 0.4117, "step": 2886 }, { "epoch": 1.7326732673267327, "grad_norm": 3.7722442150115967, "learning_rate": 1.9656455830885193e-06, "loss": 0.4638, "step": 2887 }, { "epoch": 1.7332733273327334, "grad_norm": 4.862000942230225, "learning_rate": 1.9662555686167805e-06, "loss": 0.7933, "step": 2888 }, { "epoch": 1.733873387338734, "grad_norm": 5.057265281677246, "learning_rate": 1.966860183120725e-06, "loss": 0.3805, "step": 2889 }, { "epoch": 1.7344734473447345, "grad_norm": 4.34938383102417, "learning_rate": 1.967459423239544e-06, "loss": 0.3316, "step": 2890 }, { "epoch": 1.735073507350735, "grad_norm": 6.453917980194092, "learning_rate": 1.9680532856423048e-06, "loss": 0.6188, "step": 2891 }, { "epoch": 1.7356735673567356, "grad_norm": 5.795566558837891, "learning_rate": 1.9686417670279657e-06, "loss": 0.4808, "step": 2892 }, { "epoch": 1.7362736273627362, "grad_norm": 4.402827262878418, "learning_rate": 1.969224864125397e-06, "loss": 0.2695, "step": 2893 }, { "epoch": 1.7368736873687367, "grad_norm": 2.4901156425476074, "learning_rate": 1.969802573693397e-06, "loss": 0.2839, "step": 2894 }, { "epoch": 1.7374737473747375, "grad_norm": 4.851304531097412, "learning_rate": 1.9703748925207116e-06, "loss": 0.3146, "step": 2895 }, { "epoch": 1.738073807380738, "grad_norm": 2.701453685760498, "learning_rate": 1.970941817426052e-06, "loss": 0.3499, "step": 2896 }, { "epoch": 1.7386738673867388, "grad_norm": 5.110682010650635, "learning_rate": 1.9715033452581115e-06, "loss": 0.348, "step": 2897 }, { "epoch": 1.7392739273927393, "grad_norm": 3.957247257232666, "learning_rate": 1.9720594728955837e-06, "loss": 0.3296, "step": 2898 }, { "epoch": 1.7398739873987399, "grad_norm": 4.170825958251953, "learning_rate": 1.97261019724718e-06, "loss": 0.519, "step": 2899 }, { "epoch": 1.7404740474047404, "grad_norm": 3.8081424236297607, "learning_rate": 1.9731555152516456e-06, "loss": 0.2388, "step": 2900 }, { "epoch": 1.741074107410741, "grad_norm": 3.3383445739746094, "learning_rate": 1.973695423877779e-06, "loss": 0.3617, "step": 2901 }, { "epoch": 1.7416741674167415, "grad_norm": 6.565427780151367, "learning_rate": 1.974229920124446e-06, "loss": 0.5796, "step": 2902 }, { "epoch": 1.7422742274227423, "grad_norm": 3.6068716049194336, "learning_rate": 1.974759001020597e-06, "loss": 0.2538, "step": 2903 }, { "epoch": 1.7428742874287428, "grad_norm": 5.0792646408081055, "learning_rate": 1.975282663625286e-06, "loss": 0.4435, "step": 2904 }, { "epoch": 1.7434743474347436, "grad_norm": 4.769862174987793, "learning_rate": 1.975800905027684e-06, "loss": 0.5497, "step": 2905 }, { "epoch": 1.7440744074407442, "grad_norm": 3.9483959674835205, "learning_rate": 1.9763137223470964e-06, "loss": 0.3088, "step": 2906 }, { "epoch": 1.7446744674467447, "grad_norm": 4.099682807922363, "learning_rate": 1.9768211127329785e-06, "loss": 0.5423, "step": 2907 }, { "epoch": 1.7452745274527453, "grad_norm": 5.354432582855225, "learning_rate": 1.977323073364953e-06, "loss": 0.3793, "step": 2908 }, { "epoch": 1.7458745874587458, "grad_norm": 3.7250447273254395, "learning_rate": 1.9778196014528227e-06, "loss": 0.1839, "step": 2909 }, { "epoch": 1.7464746474647463, "grad_norm": 2.892665386199951, "learning_rate": 1.9783106942365892e-06, "loss": 0.1853, "step": 2910 }, { "epoch": 1.7470747074707471, "grad_norm": 4.223822593688965, "learning_rate": 1.9787963489864655e-06, "loss": 0.4472, "step": 2911 }, { "epoch": 1.7476747674767477, "grad_norm": 4.662725925445557, "learning_rate": 1.9792765630028935e-06, "loss": 0.3271, "step": 2912 }, { "epoch": 1.7482748274827484, "grad_norm": 5.040627956390381, "learning_rate": 1.9797513336165574e-06, "loss": 0.461, "step": 2913 }, { "epoch": 1.748874887488749, "grad_norm": 5.095671653747559, "learning_rate": 1.980220658188399e-06, "loss": 0.4134, "step": 2914 }, { "epoch": 1.7494749474947495, "grad_norm": 6.541509628295898, "learning_rate": 1.980684534109633e-06, "loss": 0.668, "step": 2915 }, { "epoch": 1.75007500750075, "grad_norm": 6.5446577072143555, "learning_rate": 1.9811429588017605e-06, "loss": 0.4661, "step": 2916 }, { "epoch": 1.7506750675067506, "grad_norm": 4.924023151397705, "learning_rate": 1.9815959297165833e-06, "loss": 0.2847, "step": 2917 }, { "epoch": 1.7512751275127512, "grad_norm": 4.697022438049316, "learning_rate": 1.98204344433622e-06, "loss": 0.548, "step": 2918 }, { "epoch": 1.751875187518752, "grad_norm": 4.687170505523682, "learning_rate": 1.982485500173117e-06, "loss": 0.3741, "step": 2919 }, { "epoch": 1.7524752475247525, "grad_norm": 3.973388671875, "learning_rate": 1.9829220947700643e-06, "loss": 0.4477, "step": 2920 }, { "epoch": 1.753075307530753, "grad_norm": 4.177355766296387, "learning_rate": 1.9833532257002095e-06, "loss": 0.3411, "step": 2921 }, { "epoch": 1.7536753675367538, "grad_norm": 6.601873874664307, "learning_rate": 1.9837788905670698e-06, "loss": 0.5528, "step": 2922 }, { "epoch": 1.7542754275427543, "grad_norm": 2.3434174060821533, "learning_rate": 1.9841990870045458e-06, "loss": 0.2173, "step": 2923 }, { "epoch": 1.7548754875487549, "grad_norm": 3.996250629425049, "learning_rate": 1.984613812676936e-06, "loss": 0.4673, "step": 2924 }, { "epoch": 1.7554755475547554, "grad_norm": 4.6574225425720215, "learning_rate": 1.9850230652789476e-06, "loss": 0.441, "step": 2925 }, { "epoch": 1.756075607560756, "grad_norm": 3.787480592727661, "learning_rate": 1.9854268425357105e-06, "loss": 0.437, "step": 2926 }, { "epoch": 1.7566756675667565, "grad_norm": 5.352320671081543, "learning_rate": 1.98582514220279e-06, "loss": 0.5996, "step": 2927 }, { "epoch": 1.7572757275727573, "grad_norm": 4.784830570220947, "learning_rate": 1.9862179620661993e-06, "loss": 0.3987, "step": 2928 }, { "epoch": 1.7578757875787578, "grad_norm": 4.747738361358643, "learning_rate": 1.9866052999424123e-06, "loss": 0.4029, "step": 2929 }, { "epoch": 1.7584758475847586, "grad_norm": 4.769784450531006, "learning_rate": 1.9869871536783727e-06, "loss": 0.2492, "step": 2930 }, { "epoch": 1.7590759075907592, "grad_norm": 4.580743789672852, "learning_rate": 1.987363521151511e-06, "loss": 0.3225, "step": 2931 }, { "epoch": 1.7596759675967597, "grad_norm": 3.829263210296631, "learning_rate": 1.9877344002697524e-06, "loss": 0.5708, "step": 2932 }, { "epoch": 1.7602760276027603, "grad_norm": 5.282235622406006, "learning_rate": 1.988099788971529e-06, "loss": 0.5404, "step": 2933 }, { "epoch": 1.7608760876087608, "grad_norm": 4.321379661560059, "learning_rate": 1.9884596852257934e-06, "loss": 0.3909, "step": 2934 }, { "epoch": 1.7614761476147613, "grad_norm": 5.980418682098389, "learning_rate": 1.9888140870320275e-06, "loss": 0.4946, "step": 2935 }, { "epoch": 1.7620762076207621, "grad_norm": 4.5693206787109375, "learning_rate": 1.9891629924202545e-06, "loss": 0.3448, "step": 2936 }, { "epoch": 1.7626762676267627, "grad_norm": 4.614274978637695, "learning_rate": 1.9895063994510508e-06, "loss": 0.3761, "step": 2937 }, { "epoch": 1.7632763276327634, "grad_norm": 5.81251335144043, "learning_rate": 1.9898443062155555e-06, "loss": 0.6319, "step": 2938 }, { "epoch": 1.763876387638764, "grad_norm": 5.202101230621338, "learning_rate": 1.990176710835481e-06, "loss": 0.3826, "step": 2939 }, { "epoch": 1.7644764476447645, "grad_norm": 4.600955963134766, "learning_rate": 1.9905036114631245e-06, "loss": 0.2956, "step": 2940 }, { "epoch": 1.765076507650765, "grad_norm": 5.769155025482178, "learning_rate": 1.990825006281377e-06, "loss": 0.6538, "step": 2941 }, { "epoch": 1.7656765676567656, "grad_norm": 4.676945686340332, "learning_rate": 1.9911408935037355e-06, "loss": 0.3629, "step": 2942 }, { "epoch": 1.7662766276627662, "grad_norm": 5.14892578125, "learning_rate": 1.99145127137431e-06, "loss": 0.413, "step": 2943 }, { "epoch": 1.766876687668767, "grad_norm": 5.0199432373046875, "learning_rate": 1.9917561381678354e-06, "loss": 0.4263, "step": 2944 }, { "epoch": 1.7674767476747675, "grad_norm": 5.0815300941467285, "learning_rate": 1.9920554921896806e-06, "loss": 0.505, "step": 2945 }, { "epoch": 1.768076807680768, "grad_norm": 4.394809246063232, "learning_rate": 1.9923493317758575e-06, "loss": 0.3361, "step": 2946 }, { "epoch": 1.7686768676867688, "grad_norm": 4.9445013999938965, "learning_rate": 1.99263765529303e-06, "loss": 0.3633, "step": 2947 }, { "epoch": 1.7692769276927693, "grad_norm": 3.9828715324401855, "learning_rate": 1.992920461138524e-06, "loss": 0.4274, "step": 2948 }, { "epoch": 1.7698769876987699, "grad_norm": 4.290691375732422, "learning_rate": 1.9931977477403375e-06, "loss": 0.4795, "step": 2949 }, { "epoch": 1.7704770477047704, "grad_norm": 4.457010269165039, "learning_rate": 1.993469513557145e-06, "loss": 0.3416, "step": 2950 }, { "epoch": 1.771077107710771, "grad_norm": 6.2294816970825195, "learning_rate": 1.993735757078311e-06, "loss": 0.5443, "step": 2951 }, { "epoch": 1.7716771677167715, "grad_norm": 5.2475409507751465, "learning_rate": 1.9939964768238944e-06, "loss": 0.4822, "step": 2952 }, { "epoch": 1.7722772277227723, "grad_norm": 3.7490086555480957, "learning_rate": 1.9942516713446596e-06, "loss": 0.2638, "step": 2953 }, { "epoch": 1.7728772877287728, "grad_norm": 3.9201419353485107, "learning_rate": 1.994501339222084e-06, "loss": 0.3621, "step": 2954 }, { "epoch": 1.7734773477347736, "grad_norm": 4.977602005004883, "learning_rate": 1.994745479068365e-06, "loss": 0.5543, "step": 2955 }, { "epoch": 1.7740774077407742, "grad_norm": 4.6076507568359375, "learning_rate": 1.994984089526427e-06, "loss": 0.3527, "step": 2956 }, { "epoch": 1.7746774677467747, "grad_norm": 4.018723964691162, "learning_rate": 1.9952171692699307e-06, "loss": 0.3387, "step": 2957 }, { "epoch": 1.7752775277527753, "grad_norm": 8.548005104064941, "learning_rate": 1.9954447170032804e-06, "loss": 0.7677, "step": 2958 }, { "epoch": 1.7758775877587758, "grad_norm": 3.338003158569336, "learning_rate": 1.9956667314616308e-06, "loss": 0.2455, "step": 2959 }, { "epoch": 1.7764776477647763, "grad_norm": 3.632143497467041, "learning_rate": 1.9958832114108923e-06, "loss": 0.8769, "step": 2960 }, { "epoch": 1.7770777077707771, "grad_norm": 4.53968620300293, "learning_rate": 1.996094155647741e-06, "loss": 0.3249, "step": 2961 }, { "epoch": 1.7776777677767777, "grad_norm": 4.584840297698975, "learning_rate": 1.996299562999622e-06, "loss": 0.6905, "step": 2962 }, { "epoch": 1.7782778277827784, "grad_norm": 3.14747953414917, "learning_rate": 1.99649943232476e-06, "loss": 0.3601, "step": 2963 }, { "epoch": 1.778877887788779, "grad_norm": 3.4910316467285156, "learning_rate": 1.9966937625121618e-06, "loss": 0.2863, "step": 2964 }, { "epoch": 1.7794779477947795, "grad_norm": 3.8966615200042725, "learning_rate": 1.9968825524816243e-06, "loss": 0.4249, "step": 2965 }, { "epoch": 1.78007800780078, "grad_norm": 4.280808448791504, "learning_rate": 1.9970658011837403e-06, "loss": 0.3405, "step": 2966 }, { "epoch": 1.7806780678067806, "grad_norm": 3.444267988204956, "learning_rate": 1.9972435075999044e-06, "loss": 0.2932, "step": 2967 }, { "epoch": 1.7812781278127812, "grad_norm": 4.13287353515625, "learning_rate": 1.9974156707423185e-06, "loss": 0.2762, "step": 2968 }, { "epoch": 1.781878187818782, "grad_norm": 4.280770778656006, "learning_rate": 1.9975822896539977e-06, "loss": 0.2973, "step": 2969 }, { "epoch": 1.7824782478247825, "grad_norm": 4.488853931427002, "learning_rate": 1.9977433634087737e-06, "loss": 0.3917, "step": 2970 }, { "epoch": 1.783078307830783, "grad_norm": 3.5219216346740723, "learning_rate": 1.997898891111303e-06, "loss": 0.2278, "step": 2971 }, { "epoch": 1.7836783678367838, "grad_norm": 6.617701053619385, "learning_rate": 1.9980488718970703e-06, "loss": 0.5532, "step": 2972 }, { "epoch": 1.7842784278427843, "grad_norm": 7.537948131561279, "learning_rate": 1.9981933049323927e-06, "loss": 0.5469, "step": 2973 }, { "epoch": 1.784878487848785, "grad_norm": 3.571521520614624, "learning_rate": 1.9983321894144255e-06, "loss": 0.4976, "step": 2974 }, { "epoch": 1.7854785478547854, "grad_norm": 7.26825475692749, "learning_rate": 1.998465524571166e-06, "loss": 0.5653, "step": 2975 }, { "epoch": 1.786078607860786, "grad_norm": 4.163456916809082, "learning_rate": 1.9985933096614578e-06, "loss": 0.6292, "step": 2976 }, { "epoch": 1.7866786678667865, "grad_norm": 4.136758327484131, "learning_rate": 1.998715543974995e-06, "loss": 0.3788, "step": 2977 }, { "epoch": 1.7872787278727873, "grad_norm": 2.9665722846984863, "learning_rate": 1.9988322268323264e-06, "loss": 0.1943, "step": 2978 }, { "epoch": 1.7878787878787878, "grad_norm": 5.149068832397461, "learning_rate": 1.99894335758486e-06, "loss": 0.4047, "step": 2979 }, { "epoch": 1.7884788478847886, "grad_norm": 4.091248512268066, "learning_rate": 1.9990489356148638e-06, "loss": 0.3914, "step": 2980 }, { "epoch": 1.7890789078907892, "grad_norm": 5.318684101104736, "learning_rate": 1.9991489603354727e-06, "loss": 0.7347, "step": 2981 }, { "epoch": 1.7896789678967897, "grad_norm": 2.743460178375244, "learning_rate": 1.9992434311906895e-06, "loss": 0.2851, "step": 2982 }, { "epoch": 1.7902790279027903, "grad_norm": 3.5907087326049805, "learning_rate": 1.9993323476553894e-06, "loss": 0.2336, "step": 2983 }, { "epoch": 1.7908790879087908, "grad_norm": 6.001973628997803, "learning_rate": 1.999415709235321e-06, "loss": 0.5342, "step": 2984 }, { "epoch": 1.7914791479147913, "grad_norm": 6.319153785705566, "learning_rate": 1.9994935154671115e-06, "loss": 0.7309, "step": 2985 }, { "epoch": 1.7920792079207921, "grad_norm": 5.804060935974121, "learning_rate": 1.999565765918267e-06, "loss": 0.4271, "step": 2986 }, { "epoch": 1.7926792679267927, "grad_norm": 4.275216102600098, "learning_rate": 1.999632460187177e-06, "loss": 0.3083, "step": 2987 }, { "epoch": 1.7932793279327934, "grad_norm": 5.576540470123291, "learning_rate": 1.999693597903114e-06, "loss": 0.7563, "step": 2988 }, { "epoch": 1.793879387938794, "grad_norm": 4.621789932250977, "learning_rate": 1.9997491787262397e-06, "loss": 0.8189, "step": 2989 }, { "epoch": 1.7944794479447945, "grad_norm": 2.952420473098755, "learning_rate": 1.9997992023476013e-06, "loss": 0.2354, "step": 2990 }, { "epoch": 1.795079507950795, "grad_norm": 5.1786208152771, "learning_rate": 1.999843668489138e-06, "loss": 0.3798, "step": 2991 }, { "epoch": 1.7956795679567956, "grad_norm": 2.9973044395446777, "learning_rate": 1.9998825769036817e-06, "loss": 0.32, "step": 2992 }, { "epoch": 1.7962796279627962, "grad_norm": 3.0108282566070557, "learning_rate": 1.9999159273749548e-06, "loss": 0.4469, "step": 2993 }, { "epoch": 1.796879687968797, "grad_norm": 4.003215789794922, "learning_rate": 1.999943719717576e-06, "loss": 0.2543, "step": 2994 }, { "epoch": 1.7974797479747975, "grad_norm": 6.023523330688477, "learning_rate": 1.9999659537770587e-06, "loss": 0.5297, "step": 2995 }, { "epoch": 1.798079807980798, "grad_norm": 5.000070095062256, "learning_rate": 1.999982629429813e-06, "loss": 0.398, "step": 2996 }, { "epoch": 1.7986798679867988, "grad_norm": 4.071102619171143, "learning_rate": 1.9999937465831456e-06, "loss": 0.3495, "step": 2997 }, { "epoch": 1.7992799279927993, "grad_norm": 5.653615474700928, "learning_rate": 1.999999305175261e-06, "loss": 0.4018, "step": 2998 }, { "epoch": 1.7998799879988, "grad_norm": 5.7093658447265625, "learning_rate": 1.999999305175261e-06, "loss": 0.6205, "step": 2999 }, { "epoch": 1.8004800480048004, "grad_norm": 3.78901743888855, "learning_rate": 1.9999937465831456e-06, "loss": 0.3103, "step": 3000 }, { "epoch": 1.801080108010801, "grad_norm": 4.074042320251465, "learning_rate": 1.999982629429813e-06, "loss": 0.2872, "step": 3001 }, { "epoch": 1.8016801680168015, "grad_norm": 4.797094821929932, "learning_rate": 1.9999659537770587e-06, "loss": 0.3949, "step": 3002 }, { "epoch": 1.8022802280228023, "grad_norm": 2.230381488800049, "learning_rate": 1.999943719717576e-06, "loss": 0.2217, "step": 3003 }, { "epoch": 1.8028802880288028, "grad_norm": 4.599475383758545, "learning_rate": 1.9999159273749548e-06, "loss": 0.3218, "step": 3004 }, { "epoch": 1.8034803480348036, "grad_norm": 4.273711204528809, "learning_rate": 1.9998825769036817e-06, "loss": 0.5275, "step": 3005 }, { "epoch": 1.8040804080408042, "grad_norm": 5.128468990325928, "learning_rate": 1.999843668489138e-06, "loss": 0.355, "step": 3006 }, { "epoch": 1.8046804680468047, "grad_norm": 4.323599815368652, "learning_rate": 1.9997992023476013e-06, "loss": 0.3368, "step": 3007 }, { "epoch": 1.8052805280528053, "grad_norm": 4.953749656677246, "learning_rate": 1.9997491787262397e-06, "loss": 0.5759, "step": 3008 }, { "epoch": 1.8058805880588058, "grad_norm": 5.945502758026123, "learning_rate": 1.999693597903114e-06, "loss": 0.5817, "step": 3009 }, { "epoch": 1.8064806480648063, "grad_norm": 3.4682295322418213, "learning_rate": 1.999632460187177e-06, "loss": 0.3562, "step": 3010 }, { "epoch": 1.8070807080708071, "grad_norm": 5.701772212982178, "learning_rate": 1.999565765918267e-06, "loss": 0.703, "step": 3011 }, { "epoch": 1.8076807680768077, "grad_norm": 4.090503215789795, "learning_rate": 1.9994935154671115e-06, "loss": 0.6024, "step": 3012 }, { "epoch": 1.8082808280828084, "grad_norm": 5.7858381271362305, "learning_rate": 1.999415709235321e-06, "loss": 0.4283, "step": 3013 }, { "epoch": 1.808880888088809, "grad_norm": 5.147058486938477, "learning_rate": 1.9993323476553894e-06, "loss": 0.418, "step": 3014 }, { "epoch": 1.8094809480948095, "grad_norm": 5.224234104156494, "learning_rate": 1.9992434311906895e-06, "loss": 0.5041, "step": 3015 }, { "epoch": 1.81008100810081, "grad_norm": 3.7795944213867188, "learning_rate": 1.9991489603354727e-06, "loss": 0.2778, "step": 3016 }, { "epoch": 1.8106810681068106, "grad_norm": 5.358236789703369, "learning_rate": 1.9990489356148638e-06, "loss": 0.3881, "step": 3017 }, { "epoch": 1.8112811281128112, "grad_norm": 2.5093607902526855, "learning_rate": 1.99894335758486e-06, "loss": 0.1848, "step": 3018 }, { "epoch": 1.811881188118812, "grad_norm": 6.118066310882568, "learning_rate": 1.9988322268323264e-06, "loss": 0.5638, "step": 3019 }, { "epoch": 1.8124812481248125, "grad_norm": 5.4575958251953125, "learning_rate": 1.998715543974995e-06, "loss": 0.3378, "step": 3020 }, { "epoch": 1.813081308130813, "grad_norm": 4.8723883628845215, "learning_rate": 1.9985933096614578e-06, "loss": 0.7329, "step": 3021 }, { "epoch": 1.8136813681368138, "grad_norm": 2.5586612224578857, "learning_rate": 1.998465524571166e-06, "loss": 0.2607, "step": 3022 }, { "epoch": 1.8142814281428143, "grad_norm": 4.227959156036377, "learning_rate": 1.9983321894144255e-06, "loss": 0.3722, "step": 3023 }, { "epoch": 1.814881488148815, "grad_norm": 8.62540340423584, "learning_rate": 1.9981933049323927e-06, "loss": 0.3363, "step": 3024 }, { "epoch": 1.8154815481548154, "grad_norm": 3.7287416458129883, "learning_rate": 1.9980488718970703e-06, "loss": 0.313, "step": 3025 }, { "epoch": 1.816081608160816, "grad_norm": 4.408341407775879, "learning_rate": 1.997898891111303e-06, "loss": 0.591, "step": 3026 }, { "epoch": 1.8166816681668165, "grad_norm": 4.155221462249756, "learning_rate": 1.9977433634087737e-06, "loss": 1.0794, "step": 3027 }, { "epoch": 1.8172817281728173, "grad_norm": 3.4794657230377197, "learning_rate": 1.9975822896539977e-06, "loss": 0.3619, "step": 3028 }, { "epoch": 1.8178817881788178, "grad_norm": 4.419746398925781, "learning_rate": 1.9974156707423185e-06, "loss": 0.5161, "step": 3029 }, { "epoch": 1.8184818481848186, "grad_norm": 4.3867926597595215, "learning_rate": 1.9972435075999044e-06, "loss": 0.4011, "step": 3030 }, { "epoch": 1.8190819081908192, "grad_norm": 3.980454206466675, "learning_rate": 1.9970658011837403e-06, "loss": 0.3205, "step": 3031 }, { "epoch": 1.8196819681968197, "grad_norm": 4.674145221710205, "learning_rate": 1.9968825524816243e-06, "loss": 0.4405, "step": 3032 }, { "epoch": 1.8202820282028203, "grad_norm": 4.476678848266602, "learning_rate": 1.9966937625121618e-06, "loss": 0.3761, "step": 3033 }, { "epoch": 1.8208820882088208, "grad_norm": 4.268208026885986, "learning_rate": 1.99649943232476e-06, "loss": 0.464, "step": 3034 }, { "epoch": 1.8214821482148214, "grad_norm": 3.5988516807556152, "learning_rate": 1.996299562999622e-06, "loss": 0.3594, "step": 3035 }, { "epoch": 1.8220822082208221, "grad_norm": 3.8204939365386963, "learning_rate": 1.996094155647741e-06, "loss": 0.3774, "step": 3036 }, { "epoch": 1.8226822682268227, "grad_norm": 5.250488758087158, "learning_rate": 1.9958832114108923e-06, "loss": 0.7097, "step": 3037 }, { "epoch": 1.8232823282328234, "grad_norm": 6.312888145446777, "learning_rate": 1.9956667314616308e-06, "loss": 0.6613, "step": 3038 }, { "epoch": 1.823882388238824, "grad_norm": 7.479755401611328, "learning_rate": 1.9954447170032804e-06, "loss": 0.7549, "step": 3039 }, { "epoch": 1.8244824482448245, "grad_norm": 4.105556011199951, "learning_rate": 1.9952171692699307e-06, "loss": 0.699, "step": 3040 }, { "epoch": 1.825082508250825, "grad_norm": 5.113758563995361, "learning_rate": 1.994984089526427e-06, "loss": 0.4397, "step": 3041 }, { "epoch": 1.8256825682568256, "grad_norm": 5.4055399894714355, "learning_rate": 1.994745479068365e-06, "loss": 0.3861, "step": 3042 }, { "epoch": 1.8262826282628262, "grad_norm": 2.648775577545166, "learning_rate": 1.994501339222084e-06, "loss": 0.2216, "step": 3043 }, { "epoch": 1.826882688268827, "grad_norm": 3.8362085819244385, "learning_rate": 1.99425167134466e-06, "loss": 0.7661, "step": 3044 }, { "epoch": 1.8274827482748275, "grad_norm": 3.440412998199463, "learning_rate": 1.9939964768238944e-06, "loss": 0.2775, "step": 3045 }, { "epoch": 1.828082808280828, "grad_norm": 4.6528801918029785, "learning_rate": 1.993735757078311e-06, "loss": 0.3377, "step": 3046 }, { "epoch": 1.8286828682868288, "grad_norm": 5.219436168670654, "learning_rate": 1.993469513557145e-06, "loss": 0.4922, "step": 3047 }, { "epoch": 1.8292829282928293, "grad_norm": 4.991407871246338, "learning_rate": 1.9931977477403375e-06, "loss": 0.3983, "step": 3048 }, { "epoch": 1.82988298829883, "grad_norm": 4.526730060577393, "learning_rate": 1.992920461138524e-06, "loss": 0.3745, "step": 3049 }, { "epoch": 1.8304830483048304, "grad_norm": 4.527935981750488, "learning_rate": 1.99263765529303e-06, "loss": 0.4135, "step": 3050 }, { "epoch": 1.831083108310831, "grad_norm": 3.8802146911621094, "learning_rate": 1.9923493317758575e-06, "loss": 0.3082, "step": 3051 }, { "epoch": 1.8316831683168315, "grad_norm": 2.824157476425171, "learning_rate": 1.992055492189681e-06, "loss": 0.3767, "step": 3052 }, { "epoch": 1.8322832283228323, "grad_norm": 5.626308441162109, "learning_rate": 1.991756138167836e-06, "loss": 0.466, "step": 3053 }, { "epoch": 1.8328832883288328, "grad_norm": 5.65870475769043, "learning_rate": 1.9914512713743105e-06, "loss": 0.598, "step": 3054 }, { "epoch": 1.8334833483348336, "grad_norm": 7.183869361877441, "learning_rate": 1.991140893503736e-06, "loss": 0.8026, "step": 3055 }, { "epoch": 1.8340834083408342, "grad_norm": 3.74118971824646, "learning_rate": 1.990825006281377e-06, "loss": 0.435, "step": 3056 }, { "epoch": 1.8346834683468347, "grad_norm": 4.002430438995361, "learning_rate": 1.9905036114631245e-06, "loss": 0.491, "step": 3057 }, { "epoch": 1.8352835283528353, "grad_norm": 5.546755313873291, "learning_rate": 1.990176710835481e-06, "loss": 0.5172, "step": 3058 }, { "epoch": 1.8358835883588358, "grad_norm": 3.7978992462158203, "learning_rate": 1.9898443062155555e-06, "loss": 0.3295, "step": 3059 }, { "epoch": 1.8364836483648364, "grad_norm": 4.027442932128906, "learning_rate": 1.989506399451051e-06, "loss": 0.4807, "step": 3060 }, { "epoch": 1.8370837083708371, "grad_norm": 3.9436721801757812, "learning_rate": 1.9891629924202545e-06, "loss": 0.3766, "step": 3061 }, { "epoch": 1.8376837683768377, "grad_norm": 5.605512619018555, "learning_rate": 1.9888140870320275e-06, "loss": 0.4548, "step": 3062 }, { "epoch": 1.8382838283828384, "grad_norm": 2.148266315460205, "learning_rate": 1.9884596852257934e-06, "loss": 0.2048, "step": 3063 }, { "epoch": 1.838883888388839, "grad_norm": 3.143216609954834, "learning_rate": 1.988099788971529e-06, "loss": 0.2104, "step": 3064 }, { "epoch": 1.8394839483948395, "grad_norm": 3.9943885803222656, "learning_rate": 1.9877344002697524e-06, "loss": 0.4217, "step": 3065 }, { "epoch": 1.84008400840084, "grad_norm": 4.224294185638428, "learning_rate": 1.9873635211515113e-06, "loss": 0.3773, "step": 3066 }, { "epoch": 1.8406840684068406, "grad_norm": 4.919049263000488, "learning_rate": 1.986987153678373e-06, "loss": 0.7017, "step": 3067 }, { "epoch": 1.8412841284128412, "grad_norm": 4.68359899520874, "learning_rate": 1.9866052999424123e-06, "loss": 0.4144, "step": 3068 }, { "epoch": 1.841884188418842, "grad_norm": 5.23379373550415, "learning_rate": 1.9862179620661997e-06, "loss": 0.4706, "step": 3069 }, { "epoch": 1.8424842484248425, "grad_norm": 4.192351818084717, "learning_rate": 1.98582514220279e-06, "loss": 0.2742, "step": 3070 }, { "epoch": 1.843084308430843, "grad_norm": 4.308108806610107, "learning_rate": 1.9854268425357105e-06, "loss": 0.4652, "step": 3071 }, { "epoch": 1.8436843684368438, "grad_norm": 3.3525547981262207, "learning_rate": 1.9850230652789476e-06, "loss": 0.355, "step": 3072 }, { "epoch": 1.8442844284428443, "grad_norm": 4.2396368980407715, "learning_rate": 1.984613812676936e-06, "loss": 0.465, "step": 3073 }, { "epoch": 1.844884488448845, "grad_norm": 5.4823384284973145, "learning_rate": 1.9841990870045458e-06, "loss": 0.5928, "step": 3074 }, { "epoch": 1.8454845484548454, "grad_norm": 2.9552810192108154, "learning_rate": 1.9837788905670698e-06, "loss": 0.5364, "step": 3075 }, { "epoch": 1.846084608460846, "grad_norm": 4.3693342208862305, "learning_rate": 1.9833532257002095e-06, "loss": 0.3446, "step": 3076 }, { "epoch": 1.8466846684668465, "grad_norm": 4.109833717346191, "learning_rate": 1.9829220947700643e-06, "loss": 0.3286, "step": 3077 }, { "epoch": 1.8472847284728473, "grad_norm": 6.0814313888549805, "learning_rate": 1.982485500173117e-06, "loss": 0.7949, "step": 3078 }, { "epoch": 1.8478847884788479, "grad_norm": 4.976912975311279, "learning_rate": 1.9820434443362203e-06, "loss": 0.4269, "step": 3079 }, { "epoch": 1.8484848484848486, "grad_norm": 4.968029975891113, "learning_rate": 1.9815959297165837e-06, "loss": 0.3772, "step": 3080 }, { "epoch": 1.8490849084908492, "grad_norm": 4.596724510192871, "learning_rate": 1.9811429588017605e-06, "loss": 0.3925, "step": 3081 }, { "epoch": 1.8496849684968497, "grad_norm": 4.756577968597412, "learning_rate": 1.980684534109633e-06, "loss": 0.6873, "step": 3082 }, { "epoch": 1.8502850285028503, "grad_norm": 2.9205644130706787, "learning_rate": 1.9802206581883995e-06, "loss": 0.213, "step": 3083 }, { "epoch": 1.8508850885088508, "grad_norm": 3.540381669998169, "learning_rate": 1.9797513336165574e-06, "loss": 0.3619, "step": 3084 }, { "epoch": 1.8514851485148514, "grad_norm": 3.23294734954834, "learning_rate": 1.9792765630028935e-06, "loss": 0.2293, "step": 3085 }, { "epoch": 1.8520852085208521, "grad_norm": 5.308998107910156, "learning_rate": 1.9787963489864655e-06, "loss": 0.3578, "step": 3086 }, { "epoch": 1.8526852685268527, "grad_norm": 5.699153900146484, "learning_rate": 1.9783106942365892e-06, "loss": 0.522, "step": 3087 }, { "epoch": 1.8532853285328534, "grad_norm": 5.067724227905273, "learning_rate": 1.9778196014528227e-06, "loss": 0.5212, "step": 3088 }, { "epoch": 1.853885388538854, "grad_norm": 3.9015634059906006, "learning_rate": 1.977323073364953e-06, "loss": 0.3826, "step": 3089 }, { "epoch": 1.8544854485448545, "grad_norm": 5.527675628662109, "learning_rate": 1.9768211127329785e-06, "loss": 0.5408, "step": 3090 }, { "epoch": 1.855085508550855, "grad_norm": 3.5135045051574707, "learning_rate": 1.9763137223470964e-06, "loss": 0.3784, "step": 3091 }, { "epoch": 1.8556855685568556, "grad_norm": 4.084710121154785, "learning_rate": 1.9758009050276844e-06, "loss": 0.3127, "step": 3092 }, { "epoch": 1.8562856285628562, "grad_norm": 4.772141933441162, "learning_rate": 1.9752826636252864e-06, "loss": 0.5425, "step": 3093 }, { "epoch": 1.856885688568857, "grad_norm": 3.652043104171753, "learning_rate": 1.974759001020597e-06, "loss": 0.3668, "step": 3094 }, { "epoch": 1.8574857485748575, "grad_norm": 4.613080024719238, "learning_rate": 1.9742299201244454e-06, "loss": 0.5993, "step": 3095 }, { "epoch": 1.858085808580858, "grad_norm": 3.1195790767669678, "learning_rate": 1.973695423877779e-06, "loss": 0.4762, "step": 3096 }, { "epoch": 1.8586858685868588, "grad_norm": 3.2031614780426025, "learning_rate": 1.9731555152516456e-06, "loss": 0.2116, "step": 3097 }, { "epoch": 1.8592859285928593, "grad_norm": 4.010169506072998, "learning_rate": 1.97261019724718e-06, "loss": 0.4298, "step": 3098 }, { "epoch": 1.85988598859886, "grad_norm": 4.757573127746582, "learning_rate": 1.9720594728955837e-06, "loss": 0.5603, "step": 3099 }, { "epoch": 1.8604860486048604, "grad_norm": 5.697109222412109, "learning_rate": 1.9715033452581115e-06, "loss": 0.5831, "step": 3100 }, { "epoch": 1.861086108610861, "grad_norm": 5.30643367767334, "learning_rate": 1.970941817426052e-06, "loss": 0.4989, "step": 3101 }, { "epoch": 1.8616861686168615, "grad_norm": 4.44270658493042, "learning_rate": 1.9703748925207116e-06, "loss": 0.5501, "step": 3102 }, { "epoch": 1.8622862286228623, "grad_norm": 4.0601959228515625, "learning_rate": 1.969802573693397e-06, "loss": 0.3437, "step": 3103 }, { "epoch": 1.8628862886288629, "grad_norm": 4.117134094238281, "learning_rate": 1.969224864125397e-06, "loss": 0.3414, "step": 3104 }, { "epoch": 1.8634863486348636, "grad_norm": 6.615224361419678, "learning_rate": 1.9686417670279657e-06, "loss": 0.8394, "step": 3105 }, { "epoch": 1.8640864086408642, "grad_norm": 4.671651840209961, "learning_rate": 1.968053285642305e-06, "loss": 0.7188, "step": 3106 }, { "epoch": 1.8646864686468647, "grad_norm": 4.068033218383789, "learning_rate": 1.967459423239544e-06, "loss": 0.4901, "step": 3107 }, { "epoch": 1.8652865286528653, "grad_norm": 4.413945198059082, "learning_rate": 1.966860183120725e-06, "loss": 0.451, "step": 3108 }, { "epoch": 1.8658865886588658, "grad_norm": 6.1333513259887695, "learning_rate": 1.9662555686167805e-06, "loss": 0.7174, "step": 3109 }, { "epoch": 1.8664866486648664, "grad_norm": 3.5632660388946533, "learning_rate": 1.9656455830885193e-06, "loss": 0.5017, "step": 3110 }, { "epoch": 1.8670867086708671, "grad_norm": 3.6966795921325684, "learning_rate": 1.965030229926604e-06, "loss": 0.5017, "step": 3111 }, { "epoch": 1.8676867686768677, "grad_norm": 3.8583154678344727, "learning_rate": 1.964409512551535e-06, "loss": 0.2709, "step": 3112 }, { "epoch": 1.8682868286828684, "grad_norm": 4.149963855743408, "learning_rate": 1.9637834344136278e-06, "loss": 0.5235, "step": 3113 }, { "epoch": 1.868886888688869, "grad_norm": 4.812741756439209, "learning_rate": 1.9631519989929986e-06, "loss": 0.458, "step": 3114 }, { "epoch": 1.8694869486948695, "grad_norm": 4.491985321044922, "learning_rate": 1.9625152097995426e-06, "loss": 0.41, "step": 3115 }, { "epoch": 1.87008700870087, "grad_norm": 5.509454727172852, "learning_rate": 1.9618730703729128e-06, "loss": 0.4115, "step": 3116 }, { "epoch": 1.8706870687068706, "grad_norm": 3.1970996856689453, "learning_rate": 1.9612255842825033e-06, "loss": 0.2737, "step": 3117 }, { "epoch": 1.8712871287128712, "grad_norm": 5.173172473907471, "learning_rate": 1.960572755127427e-06, "loss": 0.3276, "step": 3118 }, { "epoch": 1.871887188718872, "grad_norm": 5.506079196929932, "learning_rate": 1.9599145865364982e-06, "loss": 0.3997, "step": 3119 }, { "epoch": 1.8724872487248725, "grad_norm": 4.690070152282715, "learning_rate": 1.959251082168209e-06, "loss": 0.2978, "step": 3120 }, { "epoch": 1.873087308730873, "grad_norm": 5.560013294219971, "learning_rate": 1.9585822457107136e-06, "loss": 0.6211, "step": 3121 }, { "epoch": 1.8736873687368738, "grad_norm": 5.10435152053833, "learning_rate": 1.9579080808818032e-06, "loss": 0.3913, "step": 3122 }, { "epoch": 1.8742874287428744, "grad_norm": 3.4873738288879395, "learning_rate": 1.957228591428887e-06, "loss": 0.2151, "step": 3123 }, { "epoch": 1.874887488748875, "grad_norm": 4.442539215087891, "learning_rate": 1.9565437811289728e-06, "loss": 0.4599, "step": 3124 }, { "epoch": 1.8754875487548754, "grad_norm": 4.88346004486084, "learning_rate": 1.9558536537886445e-06, "loss": 0.4009, "step": 3125 }, { "epoch": 1.876087608760876, "grad_norm": 4.568445205688477, "learning_rate": 1.955158213244041e-06, "loss": 0.6648, "step": 3126 }, { "epoch": 1.8766876687668765, "grad_norm": 6.036667823791504, "learning_rate": 1.9544574633608352e-06, "loss": 0.5631, "step": 3127 }, { "epoch": 1.8772877287728773, "grad_norm": 5.149491310119629, "learning_rate": 1.953751408034213e-06, "loss": 0.5378, "step": 3128 }, { "epoch": 1.8778877887788779, "grad_norm": 5.098063945770264, "learning_rate": 1.95304005118885e-06, "loss": 0.3861, "step": 3129 }, { "epoch": 1.8784878487848786, "grad_norm": 3.0684640407562256, "learning_rate": 1.9523233967788926e-06, "loss": 0.2829, "step": 3130 }, { "epoch": 1.8790879087908792, "grad_norm": 3.7031848430633545, "learning_rate": 1.9516014487879323e-06, "loss": 0.3141, "step": 3131 }, { "epoch": 1.8796879687968797, "grad_norm": 4.586817264556885, "learning_rate": 1.950874211228986e-06, "loss": 0.3904, "step": 3132 }, { "epoch": 1.8802880288028803, "grad_norm": 4.231616497039795, "learning_rate": 1.950141688144474e-06, "loss": 0.4307, "step": 3133 }, { "epoch": 1.8808880888088808, "grad_norm": 5.2744293212890625, "learning_rate": 1.949403883606196e-06, "loss": 0.4371, "step": 3134 }, { "epoch": 1.8814881488148814, "grad_norm": 4.48583984375, "learning_rate": 1.94866080171531e-06, "loss": 0.3015, "step": 3135 }, { "epoch": 1.8820882088208821, "grad_norm": 5.174496650695801, "learning_rate": 1.947912446602307e-06, "loss": 0.5397, "step": 3136 }, { "epoch": 1.8826882688268827, "grad_norm": 4.673559188842773, "learning_rate": 1.9471588224269915e-06, "loss": 0.3149, "step": 3137 }, { "epoch": 1.8832883288328834, "grad_norm": 5.160360813140869, "learning_rate": 1.9463999333784554e-06, "loss": 0.473, "step": 3138 }, { "epoch": 1.883888388838884, "grad_norm": 6.520471096038818, "learning_rate": 1.945635783675056e-06, "loss": 0.3752, "step": 3139 }, { "epoch": 1.8844884488448845, "grad_norm": 4.273012638092041, "learning_rate": 1.944866377564393e-06, "loss": 0.4554, "step": 3140 }, { "epoch": 1.885088508850885, "grad_norm": 6.345595359802246, "learning_rate": 1.9440917193232852e-06, "loss": 0.8892, "step": 3141 }, { "epoch": 1.8856885688568856, "grad_norm": 4.262005805969238, "learning_rate": 1.943311813257743e-06, "loss": 0.378, "step": 3142 }, { "epoch": 1.8862886288628862, "grad_norm": 5.43730354309082, "learning_rate": 1.9425266637029504e-06, "loss": 0.4786, "step": 3143 }, { "epoch": 1.886888688868887, "grad_norm": 4.555086135864258, "learning_rate": 1.941736275023236e-06, "loss": 0.7276, "step": 3144 }, { "epoch": 1.8874887488748875, "grad_norm": 3.7726247310638428, "learning_rate": 1.9409406516120513e-06, "loss": 0.4186, "step": 3145 }, { "epoch": 1.888088808880888, "grad_norm": 3.705965757369995, "learning_rate": 1.9401397978919453e-06, "loss": 0.2417, "step": 3146 }, { "epoch": 1.8886888688868888, "grad_norm": 5.275814533233643, "learning_rate": 1.93933371831454e-06, "loss": 0.3859, "step": 3147 }, { "epoch": 1.8892889288928894, "grad_norm": 4.546793460845947, "learning_rate": 1.938522417360507e-06, "loss": 0.4415, "step": 3148 }, { "epoch": 1.88988898889889, "grad_norm": 5.201100826263428, "learning_rate": 1.9377058995395392e-06, "loss": 0.4646, "step": 3149 }, { "epoch": 1.8904890489048904, "grad_norm": 3.768951892852783, "learning_rate": 1.9368841693903307e-06, "loss": 0.3526, "step": 3150 }, { "epoch": 1.891089108910891, "grad_norm": 4.1884331703186035, "learning_rate": 1.9360572314805467e-06, "loss": 0.4338, "step": 3151 }, { "epoch": 1.8916891689168915, "grad_norm": 4.584714889526367, "learning_rate": 1.9352250904068006e-06, "loss": 0.4956, "step": 3152 }, { "epoch": 1.8922892289228923, "grad_norm": 3.1969902515411377, "learning_rate": 1.9343877507946286e-06, "loss": 0.3075, "step": 3153 }, { "epoch": 1.8928892889288929, "grad_norm": 4.015214443206787, "learning_rate": 1.9335452172984637e-06, "loss": 0.4254, "step": 3154 }, { "epoch": 1.8934893489348936, "grad_norm": 5.459714889526367, "learning_rate": 1.932697494601609e-06, "loss": 0.5887, "step": 3155 }, { "epoch": 1.8940894089408942, "grad_norm": 2.9952268600463867, "learning_rate": 1.931844587416213e-06, "loss": 0.3374, "step": 3156 }, { "epoch": 1.8946894689468947, "grad_norm": 5.847341060638428, "learning_rate": 1.9309865004832407e-06, "loss": 0.7578, "step": 3157 }, { "epoch": 1.8952895289528953, "grad_norm": 2.459209442138672, "learning_rate": 1.9301232385724526e-06, "loss": 0.2153, "step": 3158 }, { "epoch": 1.8958895889588958, "grad_norm": 4.495054721832275, "learning_rate": 1.929254806482371e-06, "loss": 0.5125, "step": 3159 }, { "epoch": 1.8964896489648964, "grad_norm": 4.66908597946167, "learning_rate": 1.92838120904026e-06, "loss": 0.3856, "step": 3160 }, { "epoch": 1.8970897089708971, "grad_norm": 4.502060413360596, "learning_rate": 1.927502451102095e-06, "loss": 0.4077, "step": 3161 }, { "epoch": 1.8976897689768977, "grad_norm": 7.636842727661133, "learning_rate": 1.926618537552536e-06, "loss": 0.7367, "step": 3162 }, { "epoch": 1.8982898289828984, "grad_norm": 6.02102518081665, "learning_rate": 1.925729473304901e-06, "loss": 0.7214, "step": 3163 }, { "epoch": 1.898889888988899, "grad_norm": 5.3656134605407715, "learning_rate": 1.924835263301139e-06, "loss": 0.5873, "step": 3164 }, { "epoch": 1.8994899489948995, "grad_norm": 4.9498090744018555, "learning_rate": 1.9239359125118037e-06, "loss": 0.49, "step": 3165 }, { "epoch": 1.9000900090009, "grad_norm": 3.1972618103027344, "learning_rate": 1.92303142593602e-06, "loss": 0.4713, "step": 3166 }, { "epoch": 1.9006900690069006, "grad_norm": 2.6769192218780518, "learning_rate": 1.9221218086014655e-06, "loss": 0.339, "step": 3167 }, { "epoch": 1.9012901290129012, "grad_norm": 3.9279239177703857, "learning_rate": 1.9212070655643357e-06, "loss": 0.4157, "step": 3168 }, { "epoch": 1.901890189018902, "grad_norm": 3.898646354675293, "learning_rate": 1.920287201909316e-06, "loss": 0.3665, "step": 3169 }, { "epoch": 1.9024902490249025, "grad_norm": 3.945338010787964, "learning_rate": 1.919362222749557e-06, "loss": 0.375, "step": 3170 }, { "epoch": 1.903090309030903, "grad_norm": 4.753093719482422, "learning_rate": 1.9184321332266454e-06, "loss": 0.5657, "step": 3171 }, { "epoch": 1.9036903690369038, "grad_norm": 4.122659206390381, "learning_rate": 1.917496938510572e-06, "loss": 0.4281, "step": 3172 }, { "epoch": 1.9042904290429044, "grad_norm": 4.740236282348633, "learning_rate": 1.9165566437997058e-06, "loss": 0.3899, "step": 3173 }, { "epoch": 1.904890489048905, "grad_norm": 4.541654586791992, "learning_rate": 1.915611254320767e-06, "loss": 0.4402, "step": 3174 }, { "epoch": 1.9054905490549054, "grad_norm": 5.262488842010498, "learning_rate": 1.9146607753287934e-06, "loss": 0.3814, "step": 3175 }, { "epoch": 1.906090609060906, "grad_norm": 4.5017194747924805, "learning_rate": 1.9137052121071122e-06, "loss": 0.4017, "step": 3176 }, { "epoch": 1.9066906690669065, "grad_norm": 4.43848180770874, "learning_rate": 1.912744569967315e-06, "loss": 0.2893, "step": 3177 }, { "epoch": 1.9072907290729073, "grad_norm": 3.1320290565490723, "learning_rate": 1.9117788542492223e-06, "loss": 0.4223, "step": 3178 }, { "epoch": 1.9078907890789079, "grad_norm": 4.776401042938232, "learning_rate": 1.9108080703208576e-06, "loss": 0.2104, "step": 3179 }, { "epoch": 1.9084908490849086, "grad_norm": 4.7513628005981445, "learning_rate": 1.9098322235784164e-06, "loss": 0.4138, "step": 3180 }, { "epoch": 1.9090909090909092, "grad_norm": 2.9377219676971436, "learning_rate": 1.908851319446237e-06, "loss": 0.41, "step": 3181 }, { "epoch": 1.9096909690969097, "grad_norm": 5.616049766540527, "learning_rate": 1.9078653633767702e-06, "loss": 0.6572, "step": 3182 }, { "epoch": 1.9102910291029103, "grad_norm": 4.396068096160889, "learning_rate": 1.9068743608505454e-06, "loss": 0.3909, "step": 3183 }, { "epoch": 1.9108910891089108, "grad_norm": 3.6062510013580322, "learning_rate": 1.9058783173761466e-06, "loss": 0.3843, "step": 3184 }, { "epoch": 1.9114911491149114, "grad_norm": 5.359102249145508, "learning_rate": 1.9048772384901763e-06, "loss": 0.5337, "step": 3185 }, { "epoch": 1.9120912091209121, "grad_norm": 7.055089473724365, "learning_rate": 1.9038711297572272e-06, "loss": 0.545, "step": 3186 }, { "epoch": 1.9126912691269127, "grad_norm": 6.6224751472473145, "learning_rate": 1.9028599967698528e-06, "loss": 0.7044, "step": 3187 }, { "epoch": 1.9132913291329134, "grad_norm": 2.5611467361450195, "learning_rate": 1.901843845148532e-06, "loss": 0.4452, "step": 3188 }, { "epoch": 1.913891389138914, "grad_norm": 4.5638203620910645, "learning_rate": 1.9008226805416407e-06, "loss": 0.3595, "step": 3189 }, { "epoch": 1.9144914491449145, "grad_norm": 4.481800556182861, "learning_rate": 1.8997965086254214e-06, "loss": 0.6515, "step": 3190 }, { "epoch": 1.915091509150915, "grad_norm": 3.6091935634613037, "learning_rate": 1.8987653351039482e-06, "loss": 0.4346, "step": 3191 }, { "epoch": 1.9156915691569156, "grad_norm": 4.15469217300415, "learning_rate": 1.8977291657090984e-06, "loss": 0.2332, "step": 3192 }, { "epoch": 1.9162916291629162, "grad_norm": 4.050782680511475, "learning_rate": 1.8966880062005184e-06, "loss": 0.3442, "step": 3193 }, { "epoch": 1.916891689168917, "grad_norm": 3.770266532897949, "learning_rate": 1.8956418623655948e-06, "loss": 0.5218, "step": 3194 }, { "epoch": 1.9174917491749175, "grad_norm": 6.650766849517822, "learning_rate": 1.8945907400194173e-06, "loss": 0.7381, "step": 3195 }, { "epoch": 1.918091809180918, "grad_norm": 4.018327236175537, "learning_rate": 1.893534645004751e-06, "loss": 0.6302, "step": 3196 }, { "epoch": 1.9186918691869188, "grad_norm": 3.471893072128296, "learning_rate": 1.8924735831920009e-06, "loss": 0.2346, "step": 3197 }, { "epoch": 1.9192919291929194, "grad_norm": 3.1956303119659424, "learning_rate": 1.8914075604791817e-06, "loss": 0.3535, "step": 3198 }, { "epoch": 1.91989198919892, "grad_norm": 3.6241471767425537, "learning_rate": 1.890336582791881e-06, "loss": 0.3693, "step": 3199 }, { "epoch": 1.9204920492049204, "grad_norm": 4.458338260650635, "learning_rate": 1.8892606560832331e-06, "loss": 0.2693, "step": 3200 }, { "epoch": 1.921092109210921, "grad_norm": 3.1847660541534424, "learning_rate": 1.8881797863338798e-06, "loss": 0.2171, "step": 3201 }, { "epoch": 1.9216921692169215, "grad_norm": 7.690542697906494, "learning_rate": 1.8870939795519383e-06, "loss": 0.5991, "step": 3202 }, { "epoch": 1.9222922292229223, "grad_norm": 4.063722133636475, "learning_rate": 1.8860032417729701e-06, "loss": 0.2897, "step": 3203 }, { "epoch": 1.9228922892289229, "grad_norm": 5.121891021728516, "learning_rate": 1.8849075790599464e-06, "loss": 0.507, "step": 3204 }, { "epoch": 1.9234923492349236, "grad_norm": 5.523748397827148, "learning_rate": 1.8838069975032135e-06, "loss": 0.6227, "step": 3205 }, { "epoch": 1.9240924092409242, "grad_norm": 5.478145122528076, "learning_rate": 1.8827015032204582e-06, "loss": 0.2821, "step": 3206 }, { "epoch": 1.9246924692469247, "grad_norm": 4.644611358642578, "learning_rate": 1.881591102356678e-06, "loss": 0.5159, "step": 3207 }, { "epoch": 1.9252925292529253, "grad_norm": 4.797715187072754, "learning_rate": 1.8804758010841426e-06, "loss": 0.5201, "step": 3208 }, { "epoch": 1.9258925892589258, "grad_norm": 4.49611234664917, "learning_rate": 1.8793556056023609e-06, "loss": 0.4512, "step": 3209 }, { "epoch": 1.9264926492649264, "grad_norm": 5.148773193359375, "learning_rate": 1.8782305221380467e-06, "loss": 0.5515, "step": 3210 }, { "epoch": 1.9270927092709271, "grad_norm": 6.859930992126465, "learning_rate": 1.8771005569450852e-06, "loss": 0.7347, "step": 3211 }, { "epoch": 1.9276927692769277, "grad_norm": 3.349146604537964, "learning_rate": 1.875965716304495e-06, "loss": 0.3506, "step": 3212 }, { "epoch": 1.9282928292829284, "grad_norm": 4.558826446533203, "learning_rate": 1.8748260065243984e-06, "loss": 0.4011, "step": 3213 }, { "epoch": 1.928892889288929, "grad_norm": 4.1078104972839355, "learning_rate": 1.8736814339399805e-06, "loss": 0.4078, "step": 3214 }, { "epoch": 1.9294929492949295, "grad_norm": 4.013668537139893, "learning_rate": 1.872532004913458e-06, "loss": 0.4199, "step": 3215 }, { "epoch": 1.93009300930093, "grad_norm": 5.714425563812256, "learning_rate": 1.871377725834043e-06, "loss": 0.7791, "step": 3216 }, { "epoch": 1.9306930693069306, "grad_norm": 4.924493789672852, "learning_rate": 1.870218603117906e-06, "loss": 0.5248, "step": 3217 }, { "epoch": 1.9312931293129312, "grad_norm": 4.101346015930176, "learning_rate": 1.8690546432081422e-06, "loss": 0.6254, "step": 3218 }, { "epoch": 1.931893189318932, "grad_norm": 4.017963409423828, "learning_rate": 1.8678858525747337e-06, "loss": 0.39, "step": 3219 }, { "epoch": 1.9324932493249325, "grad_norm": 3.673525333404541, "learning_rate": 1.8667122377145166e-06, "loss": 0.2378, "step": 3220 }, { "epoch": 1.933093309330933, "grad_norm": 3.784472703933716, "learning_rate": 1.865533805151141e-06, "loss": 0.2631, "step": 3221 }, { "epoch": 1.9336933693369338, "grad_norm": 5.135961055755615, "learning_rate": 1.8643505614350378e-06, "loss": 0.4727, "step": 3222 }, { "epoch": 1.9342934293429344, "grad_norm": 4.455993175506592, "learning_rate": 1.8631625131433805e-06, "loss": 0.4892, "step": 3223 }, { "epoch": 1.934893489348935, "grad_norm": 3.4106783866882324, "learning_rate": 1.8619696668800494e-06, "loss": 0.4487, "step": 3224 }, { "epoch": 1.9354935493549354, "grad_norm": 3.3612656593322754, "learning_rate": 1.8607720292755948e-06, "loss": 0.3498, "step": 3225 }, { "epoch": 1.936093609360936, "grad_norm": 3.0298233032226562, "learning_rate": 1.8595696069872008e-06, "loss": 0.2989, "step": 3226 }, { "epoch": 1.9366936693669365, "grad_norm": 4.35872745513916, "learning_rate": 1.8583624066986475e-06, "loss": 0.3804, "step": 3227 }, { "epoch": 1.9372937293729373, "grad_norm": 4.440506935119629, "learning_rate": 1.8571504351202724e-06, "loss": 0.3915, "step": 3228 }, { "epoch": 1.9378937893789379, "grad_norm": 4.53342342376709, "learning_rate": 1.8559336989889367e-06, "loss": 0.8465, "step": 3229 }, { "epoch": 1.9384938493849386, "grad_norm": 4.776180267333984, "learning_rate": 1.8547122050679845e-06, "loss": 0.4766, "step": 3230 }, { "epoch": 1.9390939093909392, "grad_norm": 4.8462677001953125, "learning_rate": 1.8534859601472076e-06, "loss": 0.3547, "step": 3231 }, { "epoch": 1.9396939693969397, "grad_norm": 4.698449611663818, "learning_rate": 1.8522549710428047e-06, "loss": 0.3924, "step": 3232 }, { "epoch": 1.9402940294029403, "grad_norm": 4.662041664123535, "learning_rate": 1.8510192445973485e-06, "loss": 0.5129, "step": 3233 }, { "epoch": 1.9408940894089408, "grad_norm": 4.5406904220581055, "learning_rate": 1.8497787876797421e-06, "loss": 0.4547, "step": 3234 }, { "epoch": 1.9414941494149414, "grad_norm": 4.215600967407227, "learning_rate": 1.848533607185185e-06, "loss": 0.5176, "step": 3235 }, { "epoch": 1.9420942094209421, "grad_norm": 5.132110595703125, "learning_rate": 1.847283710035132e-06, "loss": 0.3891, "step": 3236 }, { "epoch": 1.9426942694269427, "grad_norm": 5.654878616333008, "learning_rate": 1.846029103177256e-06, "loss": 0.3544, "step": 3237 }, { "epoch": 1.9432943294329434, "grad_norm": 4.243818283081055, "learning_rate": 1.844769793585411e-06, "loss": 0.338, "step": 3238 }, { "epoch": 1.943894389438944, "grad_norm": 3.980043888092041, "learning_rate": 1.8435057882595881e-06, "loss": 0.3231, "step": 3239 }, { "epoch": 1.9444944494449445, "grad_norm": 4.621479034423828, "learning_rate": 1.8422370942258842e-06, "loss": 0.369, "step": 3240 }, { "epoch": 1.945094509450945, "grad_norm": 3.2655601501464844, "learning_rate": 1.8409637185364564e-06, "loss": 0.227, "step": 3241 }, { "epoch": 1.9456945694569456, "grad_norm": 3.9239377975463867, "learning_rate": 1.8396856682694853e-06, "loss": 0.2505, "step": 3242 }, { "epoch": 1.9462946294629462, "grad_norm": 3.1987082958221436, "learning_rate": 1.8384029505291357e-06, "loss": 0.242, "step": 3243 }, { "epoch": 1.946894689468947, "grad_norm": 7.039597988128662, "learning_rate": 1.8371155724455178e-06, "loss": 0.7396, "step": 3244 }, { "epoch": 1.9474947494749475, "grad_norm": 4.794628620147705, "learning_rate": 1.835823541174646e-06, "loss": 0.3689, "step": 3245 }, { "epoch": 1.948094809480948, "grad_norm": 5.519976615905762, "learning_rate": 1.8345268638984e-06, "loss": 0.5875, "step": 3246 }, { "epoch": 1.9486948694869488, "grad_norm": 3.33164381980896, "learning_rate": 1.8332255478244859e-06, "loss": 0.1921, "step": 3247 }, { "epoch": 1.9492949294929494, "grad_norm": 6.382607936859131, "learning_rate": 1.8319196001863925e-06, "loss": 0.5453, "step": 3248 }, { "epoch": 1.94989498949895, "grad_norm": 5.009519100189209, "learning_rate": 1.8306090282433562e-06, "loss": 0.2917, "step": 3249 }, { "epoch": 1.9504950495049505, "grad_norm": 4.592884063720703, "learning_rate": 1.8292938392803162e-06, "loss": 0.4396, "step": 3250 }, { "epoch": 1.951095109510951, "grad_norm": 5.735835075378418, "learning_rate": 1.8279740406078772e-06, "loss": 0.6106, "step": 3251 }, { "epoch": 1.9516951695169515, "grad_norm": 3.9179811477661133, "learning_rate": 1.826649639562266e-06, "loss": 0.3523, "step": 3252 }, { "epoch": 1.9522952295229523, "grad_norm": 4.440522193908691, "learning_rate": 1.8253206435052934e-06, "loss": 0.5087, "step": 3253 }, { "epoch": 1.9528952895289529, "grad_norm": 5.096816539764404, "learning_rate": 1.8239870598243121e-06, "loss": 0.5478, "step": 3254 }, { "epoch": 1.9534953495349536, "grad_norm": 5.545229911804199, "learning_rate": 1.822648895932174e-06, "loss": 0.7025, "step": 3255 }, { "epoch": 1.9540954095409542, "grad_norm": 4.525580883026123, "learning_rate": 1.8213061592671926e-06, "loss": 0.3971, "step": 3256 }, { "epoch": 1.9546954695469547, "grad_norm": 3.5006325244903564, "learning_rate": 1.8199588572930974e-06, "loss": 0.2564, "step": 3257 }, { "epoch": 1.9552955295529553, "grad_norm": 4.862902641296387, "learning_rate": 1.8186069974989953e-06, "loss": 0.7219, "step": 3258 }, { "epoch": 1.9558955895589558, "grad_norm": 3.9016127586364746, "learning_rate": 1.8172505873993305e-06, "loss": 0.329, "step": 3259 }, { "epoch": 1.9564956495649564, "grad_norm": 3.0488297939300537, "learning_rate": 1.8158896345338386e-06, "loss": 0.2786, "step": 3260 }, { "epoch": 1.9570957095709571, "grad_norm": 3.8198864459991455, "learning_rate": 1.8145241464675053e-06, "loss": 0.3671, "step": 3261 }, { "epoch": 1.9576957695769577, "grad_norm": 4.63950252532959, "learning_rate": 1.8131541307905281e-06, "loss": 0.6826, "step": 3262 }, { "epoch": 1.9582958295829584, "grad_norm": 4.407132625579834, "learning_rate": 1.8117795951182697e-06, "loss": 0.458, "step": 3263 }, { "epoch": 1.958895889588959, "grad_norm": 2.9634041786193848, "learning_rate": 1.8104005470912196e-06, "loss": 0.3806, "step": 3264 }, { "epoch": 1.9594959495949595, "grad_norm": 6.901950836181641, "learning_rate": 1.809016994374947e-06, "loss": 0.9415, "step": 3265 }, { "epoch": 1.96009600960096, "grad_norm": 4.692847728729248, "learning_rate": 1.8076289446600646e-06, "loss": 0.4976, "step": 3266 }, { "epoch": 1.9606960696069606, "grad_norm": 5.176902770996094, "learning_rate": 1.8062364056621794e-06, "loss": 0.6805, "step": 3267 }, { "epoch": 1.9612961296129612, "grad_norm": 8.029229164123535, "learning_rate": 1.8048393851218524e-06, "loss": 0.5789, "step": 3268 }, { "epoch": 1.961896189618962, "grad_norm": 6.440118312835693, "learning_rate": 1.8034378908045563e-06, "loss": 0.5144, "step": 3269 }, { "epoch": 1.9624962496249625, "grad_norm": 6.195245742797852, "learning_rate": 1.8020319305006325e-06, "loss": 0.4475, "step": 3270 }, { "epoch": 1.963096309630963, "grad_norm": 6.670688629150391, "learning_rate": 1.8006215120252448e-06, "loss": 0.9892, "step": 3271 }, { "epoch": 1.9636963696369638, "grad_norm": 4.5147480964660645, "learning_rate": 1.7992066432183415e-06, "loss": 0.3703, "step": 3272 }, { "epoch": 1.9642964296429644, "grad_norm": 4.148499965667725, "learning_rate": 1.797787331944606e-06, "loss": 0.2649, "step": 3273 }, { "epoch": 1.964896489648965, "grad_norm": 3.464407205581665, "learning_rate": 1.7963635860934164e-06, "loss": 0.3283, "step": 3274 }, { "epoch": 1.9654965496549655, "grad_norm": 2.0239665508270264, "learning_rate": 1.7949354135788007e-06, "loss": 0.3112, "step": 3275 }, { "epoch": 1.966096609660966, "grad_norm": 3.722435474395752, "learning_rate": 1.7935028223393918e-06, "loss": 0.4526, "step": 3276 }, { "epoch": 1.9666966696669665, "grad_norm": 4.526747226715088, "learning_rate": 1.7920658203383868e-06, "loss": 0.9143, "step": 3277 }, { "epoch": 1.9672967296729673, "grad_norm": 4.222426891326904, "learning_rate": 1.7906244155634976e-06, "loss": 0.4336, "step": 3278 }, { "epoch": 1.9678967896789679, "grad_norm": 3.521415948867798, "learning_rate": 1.789178616026913e-06, "loss": 0.3199, "step": 3279 }, { "epoch": 1.9684968496849686, "grad_norm": 4.415598392486572, "learning_rate": 1.7877284297652483e-06, "loss": 0.5315, "step": 3280 }, { "epoch": 1.9690969096909692, "grad_norm": 5.800054550170898, "learning_rate": 1.7862738648395022e-06, "loss": 0.6771, "step": 3281 }, { "epoch": 1.9696969696969697, "grad_norm": 5.765393257141113, "learning_rate": 1.7848149293350141e-06, "loss": 0.5561, "step": 3282 }, { "epoch": 1.9702970297029703, "grad_norm": 4.4153594970703125, "learning_rate": 1.7833516313614162e-06, "loss": 0.433, "step": 3283 }, { "epoch": 1.9708970897089708, "grad_norm": 7.0038676261901855, "learning_rate": 1.781883979052591e-06, "loss": 0.7509, "step": 3284 }, { "epoch": 1.9714971497149714, "grad_norm": 4.408714294433594, "learning_rate": 1.7804119805666237e-06, "loss": 0.3691, "step": 3285 }, { "epoch": 1.9720972097209721, "grad_norm": 5.716054916381836, "learning_rate": 1.7789356440857616e-06, "loss": 0.3833, "step": 3286 }, { "epoch": 1.9726972697269727, "grad_norm": 3.9210453033447266, "learning_rate": 1.7774549778163616e-06, "loss": 0.4092, "step": 3287 }, { "epoch": 1.9732973297329734, "grad_norm": 2.933715581893921, "learning_rate": 1.775969989988849e-06, "loss": 0.3293, "step": 3288 }, { "epoch": 1.973897389738974, "grad_norm": 3.9885008335113525, "learning_rate": 1.7744806888576712e-06, "loss": 0.5174, "step": 3289 }, { "epoch": 1.9744974497449745, "grad_norm": 4.661534309387207, "learning_rate": 1.7729870827012522e-06, "loss": 0.457, "step": 3290 }, { "epoch": 1.975097509750975, "grad_norm": 5.137984275817871, "learning_rate": 1.7714891798219425e-06, "loss": 0.3758, "step": 3291 }, { "epoch": 1.9756975697569756, "grad_norm": 3.0099141597747803, "learning_rate": 1.7699869885459826e-06, "loss": 0.4873, "step": 3292 }, { "epoch": 1.9762976297629762, "grad_norm": 5.016388893127441, "learning_rate": 1.7684805172234452e-06, "loss": 0.3398, "step": 3293 }, { "epoch": 1.976897689768977, "grad_norm": 4.402853488922119, "learning_rate": 1.7669697742281958e-06, "loss": 0.2995, "step": 3294 }, { "epoch": 1.9774977497749775, "grad_norm": 4.661759853363037, "learning_rate": 1.7654547679578443e-06, "loss": 0.5352, "step": 3295 }, { "epoch": 1.978097809780978, "grad_norm": 6.547240734100342, "learning_rate": 1.7639355068336988e-06, "loss": 0.8293, "step": 3296 }, { "epoch": 1.9786978697869788, "grad_norm": 4.108229637145996, "learning_rate": 1.7624119993007184e-06, "loss": 0.7251, "step": 3297 }, { "epoch": 1.9792979297929794, "grad_norm": 5.000249862670898, "learning_rate": 1.7608842538274632e-06, "loss": 0.5033, "step": 3298 }, { "epoch": 1.97989798979898, "grad_norm": 6.818604469299316, "learning_rate": 1.7593522789060571e-06, "loss": 0.5476, "step": 3299 }, { "epoch": 1.9804980498049805, "grad_norm": 2.667914390563965, "learning_rate": 1.7578160830521274e-06, "loss": 0.1721, "step": 3300 }, { "epoch": 1.981098109810981, "grad_norm": 3.1914987564086914, "learning_rate": 1.7562756748047667e-06, "loss": 0.2682, "step": 3301 }, { "epoch": 1.9816981698169815, "grad_norm": 4.02640438079834, "learning_rate": 1.7547310627264823e-06, "loss": 0.4635, "step": 3302 }, { "epoch": 1.9822982298229823, "grad_norm": 4.184319019317627, "learning_rate": 1.7531822554031482e-06, "loss": 0.4719, "step": 3303 }, { "epoch": 1.9828982898289829, "grad_norm": 4.201557159423828, "learning_rate": 1.751629261443958e-06, "loss": 0.4019, "step": 3304 }, { "epoch": 1.9834983498349836, "grad_norm": 3.3874945640563965, "learning_rate": 1.7500720894813795e-06, "loss": 0.4576, "step": 3305 }, { "epoch": 1.9840984098409842, "grad_norm": 3.3212316036224365, "learning_rate": 1.748510748171101e-06, "loss": 0.3057, "step": 3306 }, { "epoch": 1.9846984698469847, "grad_norm": 3.5236291885375977, "learning_rate": 1.7469452461919887e-06, "loss": 0.362, "step": 3307 }, { "epoch": 1.9852985298529853, "grad_norm": 3.6592328548431396, "learning_rate": 1.7453755922460354e-06, "loss": 0.3069, "step": 3308 }, { "epoch": 1.9858985898589858, "grad_norm": 4.273094177246094, "learning_rate": 1.7438017950583133e-06, "loss": 0.6016, "step": 3309 }, { "epoch": 1.9864986498649864, "grad_norm": 4.53010368347168, "learning_rate": 1.742223863376925e-06, "loss": 0.3883, "step": 3310 }, { "epoch": 1.9870987098709871, "grad_norm": 3.033599376678467, "learning_rate": 1.7406418059729546e-06, "loss": 0.2549, "step": 3311 }, { "epoch": 1.9876987698769877, "grad_norm": 5.335675239562988, "learning_rate": 1.7390556316404212e-06, "loss": 0.5429, "step": 3312 }, { "epoch": 1.9882988298829884, "grad_norm": 3.004674196243286, "learning_rate": 1.7374653491962265e-06, "loss": 0.2607, "step": 3313 }, { "epoch": 1.988898889888989, "grad_norm": 4.670130252838135, "learning_rate": 1.7358709674801082e-06, "loss": 0.528, "step": 3314 }, { "epoch": 1.9894989498949895, "grad_norm": 4.514538288116455, "learning_rate": 1.73427249535459e-06, "loss": 0.5638, "step": 3315 }, { "epoch": 1.99009900990099, "grad_norm": 3.362515926361084, "learning_rate": 1.7326699417049326e-06, "loss": 0.3153, "step": 3316 }, { "epoch": 1.9906990699069906, "grad_norm": 5.462673664093018, "learning_rate": 1.7310633154390837e-06, "loss": 0.7125, "step": 3317 }, { "epoch": 1.9912991299129912, "grad_norm": 2.8387725353240967, "learning_rate": 1.7294526254876306e-06, "loss": 0.235, "step": 3318 }, { "epoch": 1.991899189918992, "grad_norm": 4.325708389282227, "learning_rate": 1.7278378808037478e-06, "loss": 0.5186, "step": 3319 }, { "epoch": 1.9924992499249925, "grad_norm": 4.3261260986328125, "learning_rate": 1.7262190903631483e-06, "loss": 0.403, "step": 3320 }, { "epoch": 1.993099309930993, "grad_norm": 5.565634250640869, "learning_rate": 1.7245962631640346e-06, "loss": 0.3238, "step": 3321 }, { "epoch": 1.9936993699369938, "grad_norm": 4.289806842803955, "learning_rate": 1.7229694082270468e-06, "loss": 0.4135, "step": 3322 }, { "epoch": 1.9942994299429944, "grad_norm": 4.468098163604736, "learning_rate": 1.721338534595214e-06, "loss": 0.6128, "step": 3323 }, { "epoch": 1.994899489948995, "grad_norm": 3.9858357906341553, "learning_rate": 1.7197036513339042e-06, "loss": 0.2532, "step": 3324 }, { "epoch": 1.9954995499549955, "grad_norm": 3.327194929122925, "learning_rate": 1.7180647675307736e-06, "loss": 0.3271, "step": 3325 }, { "epoch": 1.996099609960996, "grad_norm": 5.02089262008667, "learning_rate": 1.7164218922957142e-06, "loss": 0.4146, "step": 3326 }, { "epoch": 1.9966996699669965, "grad_norm": 5.972522258758545, "learning_rate": 1.7147750347608066e-06, "loss": 0.7795, "step": 3327 }, { "epoch": 1.9972997299729973, "grad_norm": 5.448775768280029, "learning_rate": 1.7131242040802651e-06, "loss": 0.4461, "step": 3328 }, { "epoch": 1.9978997899789979, "grad_norm": 3.6218602657318115, "learning_rate": 1.7114694094303918e-06, "loss": 0.3156, "step": 3329 }, { "epoch": 1.9984998499849986, "grad_norm": 4.543081283569336, "learning_rate": 1.70981066000952e-06, "loss": 0.2551, "step": 3330 }, { "epoch": 1.9990999099909992, "grad_norm": 4.532882213592529, "learning_rate": 1.7081479650379696e-06, "loss": 0.365, "step": 3331 }, { "epoch": 1.9996999699969997, "grad_norm": 5.6424241065979, "learning_rate": 1.7064813337579889e-06, "loss": 0.3384, "step": 3332 }, { "epoch": 1.9996999699969997, "step": 3332, "total_flos": 1.8039698824678605e+17, "train_loss": 0.03151041264383017, "train_runtime": 20032.1669, "train_samples_per_second": 1.997, "train_steps_per_second": 0.166 } ], "logging_steps": 1.0, "max_steps": 3332, "num_input_tokens_seen": 0, "num_train_epochs": 2, "save_steps": 100, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 1.8039698824678605e+17, "train_batch_size": 1, "trial_name": null, "trial_params": null }