{ "best_metric": null, "best_model_checkpoint": null, "epoch": 4.988354430379747, "eval_steps": 500, "global_step": 1230, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.004050632911392405, "grad_norm": 5.9653273128314686, "learning_rate": 3.2520325203252037e-07, "loss": 1.0072, "step": 1 }, { "epoch": 0.00810126582278481, "grad_norm": 6.1685297878199, "learning_rate": 6.504065040650407e-07, "loss": 1.0288, "step": 2 }, { "epoch": 0.012151898734177215, "grad_norm": 6.023312151915269, "learning_rate": 9.75609756097561e-07, "loss": 1.0723, "step": 3 }, { "epoch": 0.01620253164556962, "grad_norm": 5.786753166699721, "learning_rate": 1.3008130081300815e-06, "loss": 0.9985, "step": 4 }, { "epoch": 0.020253164556962026, "grad_norm": 5.574995716585662, "learning_rate": 1.6260162601626018e-06, "loss": 1.024, "step": 5 }, { "epoch": 0.02430379746835443, "grad_norm": 5.431779049612622, "learning_rate": 1.951219512195122e-06, "loss": 0.9678, "step": 6 }, { "epoch": 0.028354430379746835, "grad_norm": 4.40751742474846, "learning_rate": 2.2764227642276426e-06, "loss": 0.9898, "step": 7 }, { "epoch": 0.03240506329113924, "grad_norm": 4.027370103590811, "learning_rate": 2.601626016260163e-06, "loss": 0.9382, "step": 8 }, { "epoch": 0.03645569620253165, "grad_norm": 2.4357221754606204, "learning_rate": 2.926829268292683e-06, "loss": 0.9396, "step": 9 }, { "epoch": 0.04050632911392405, "grad_norm": 2.1176657614650445, "learning_rate": 3.2520325203252037e-06, "loss": 0.8955, "step": 10 }, { "epoch": 0.044556962025316456, "grad_norm": 2.007840182542556, "learning_rate": 3.577235772357724e-06, "loss": 0.9389, "step": 11 }, { "epoch": 0.04860759493670886, "grad_norm": 3.7496305618842656, "learning_rate": 3.902439024390244e-06, "loss": 0.884, "step": 12 }, { "epoch": 0.052658227848101265, "grad_norm": 4.301550487931581, "learning_rate": 4.227642276422765e-06, "loss": 0.9108, "step": 13 }, { "epoch": 0.05670886075949367, "grad_norm": 4.140812130121513, "learning_rate": 4.552845528455285e-06, "loss": 0.8708, "step": 14 }, { "epoch": 0.060759493670886074, "grad_norm": 3.864210241409669, "learning_rate": 4.8780487804878055e-06, "loss": 0.8731, "step": 15 }, { "epoch": 0.06481012658227848, "grad_norm": 2.6593490397694186, "learning_rate": 5.203252032520326e-06, "loss": 0.8279, "step": 16 }, { "epoch": 0.06886075949367089, "grad_norm": 2.272840283124272, "learning_rate": 5.528455284552846e-06, "loss": 0.7824, "step": 17 }, { "epoch": 0.0729113924050633, "grad_norm": 1.9868597956875627, "learning_rate": 5.853658536585366e-06, "loss": 0.8141, "step": 18 }, { "epoch": 0.0769620253164557, "grad_norm": 1.8648937748861811, "learning_rate": 6.178861788617887e-06, "loss": 0.8203, "step": 19 }, { "epoch": 0.0810126582278481, "grad_norm": 1.822365603926386, "learning_rate": 6.504065040650407e-06, "loss": 0.774, "step": 20 }, { "epoch": 0.08506329113924051, "grad_norm": 1.7142982733670298, "learning_rate": 6.829268292682928e-06, "loss": 0.7791, "step": 21 }, { "epoch": 0.08911392405063291, "grad_norm": 1.5362506770650068, "learning_rate": 7.154471544715448e-06, "loss": 0.7555, "step": 22 }, { "epoch": 0.09316455696202532, "grad_norm": 1.373975691891637, "learning_rate": 7.4796747967479676e-06, "loss": 0.7681, "step": 23 }, { "epoch": 0.09721518987341772, "grad_norm": 1.2458855274537997, "learning_rate": 7.804878048780489e-06, "loss": 0.7942, "step": 24 }, { "epoch": 0.10126582278481013, "grad_norm": 1.1927423003066036, "learning_rate": 8.130081300813009e-06, "loss": 0.7666, "step": 25 }, { "epoch": 0.10531645569620253, "grad_norm": 1.4084280316865705, "learning_rate": 8.45528455284553e-06, "loss": 0.7425, "step": 26 }, { "epoch": 0.10936708860759493, "grad_norm": 1.3478987781419043, "learning_rate": 8.78048780487805e-06, "loss": 0.7463, "step": 27 }, { "epoch": 0.11341772151898734, "grad_norm": 0.9363845296891505, "learning_rate": 9.10569105691057e-06, "loss": 0.7683, "step": 28 }, { "epoch": 0.11746835443037974, "grad_norm": 0.8697143573114954, "learning_rate": 9.43089430894309e-06, "loss": 0.7358, "step": 29 }, { "epoch": 0.12151898734177215, "grad_norm": 1.1752182505566322, "learning_rate": 9.756097560975611e-06, "loss": 0.7185, "step": 30 }, { "epoch": 0.12556962025316457, "grad_norm": 1.0819198032361925, "learning_rate": 1.008130081300813e-05, "loss": 0.7473, "step": 31 }, { "epoch": 0.12962025316455697, "grad_norm": 0.7410716455672041, "learning_rate": 1.0406504065040652e-05, "loss": 0.7358, "step": 32 }, { "epoch": 0.13367088607594937, "grad_norm": 0.8007690217830975, "learning_rate": 1.0731707317073172e-05, "loss": 0.7148, "step": 33 }, { "epoch": 0.13772151898734178, "grad_norm": 0.8331863677056375, "learning_rate": 1.1056910569105692e-05, "loss": 0.7191, "step": 34 }, { "epoch": 0.14177215189873418, "grad_norm": 0.7601241012286892, "learning_rate": 1.1382113821138213e-05, "loss": 0.7293, "step": 35 }, { "epoch": 0.1458227848101266, "grad_norm": 0.614767916268878, "learning_rate": 1.1707317073170731e-05, "loss": 0.7112, "step": 36 }, { "epoch": 0.149873417721519, "grad_norm": 0.7604244069356352, "learning_rate": 1.2032520325203254e-05, "loss": 0.7034, "step": 37 }, { "epoch": 0.1539240506329114, "grad_norm": 0.6329441312783859, "learning_rate": 1.2357723577235774e-05, "loss": 0.6967, "step": 38 }, { "epoch": 0.1579746835443038, "grad_norm": 0.6016292650252295, "learning_rate": 1.2682926829268294e-05, "loss": 0.7159, "step": 39 }, { "epoch": 0.1620253164556962, "grad_norm": 0.6886272197377965, "learning_rate": 1.3008130081300815e-05, "loss": 0.7379, "step": 40 }, { "epoch": 0.1660759493670886, "grad_norm": 0.707055123713355, "learning_rate": 1.3333333333333333e-05, "loss": 0.6934, "step": 41 }, { "epoch": 0.17012658227848101, "grad_norm": 0.6924576429156993, "learning_rate": 1.3658536585365855e-05, "loss": 0.7344, "step": 42 }, { "epoch": 0.17417721518987342, "grad_norm": 0.6250896866271889, "learning_rate": 1.3983739837398376e-05, "loss": 0.7237, "step": 43 }, { "epoch": 0.17822784810126582, "grad_norm": 0.6456215742423801, "learning_rate": 1.4308943089430896e-05, "loss": 0.7005, "step": 44 }, { "epoch": 0.18227848101265823, "grad_norm": 0.6343160376080823, "learning_rate": 1.4634146341463415e-05, "loss": 0.6911, "step": 45 }, { "epoch": 0.18632911392405063, "grad_norm": 0.6735170640484767, "learning_rate": 1.4959349593495935e-05, "loss": 0.6664, "step": 46 }, { "epoch": 0.19037974683544304, "grad_norm": 0.6840755352693586, "learning_rate": 1.528455284552846e-05, "loss": 0.7073, "step": 47 }, { "epoch": 0.19443037974683544, "grad_norm": 0.6424623172281843, "learning_rate": 1.5609756097560978e-05, "loss": 0.7029, "step": 48 }, { "epoch": 0.19848101265822785, "grad_norm": 0.7523210542479413, "learning_rate": 1.5934959349593496e-05, "loss": 0.7171, "step": 49 }, { "epoch": 0.20253164556962025, "grad_norm": 0.5748850510515238, "learning_rate": 1.6260162601626018e-05, "loss": 0.7208, "step": 50 }, { "epoch": 0.20658227848101265, "grad_norm": 0.6950855505875903, "learning_rate": 1.6585365853658537e-05, "loss": 0.6949, "step": 51 }, { "epoch": 0.21063291139240506, "grad_norm": 0.64704383717688, "learning_rate": 1.691056910569106e-05, "loss": 0.6733, "step": 52 }, { "epoch": 0.21468354430379746, "grad_norm": 0.5909129310330549, "learning_rate": 1.7235772357723578e-05, "loss": 0.7015, "step": 53 }, { "epoch": 0.21873417721518987, "grad_norm": 0.659581113434757, "learning_rate": 1.75609756097561e-05, "loss": 0.6871, "step": 54 }, { "epoch": 0.22278481012658227, "grad_norm": 0.6288314260846469, "learning_rate": 1.788617886178862e-05, "loss": 0.7024, "step": 55 }, { "epoch": 0.22683544303797468, "grad_norm": 0.6093825262239607, "learning_rate": 1.821138211382114e-05, "loss": 0.6682, "step": 56 }, { "epoch": 0.23088607594936708, "grad_norm": 0.5217414583847938, "learning_rate": 1.8536585365853663e-05, "loss": 0.6544, "step": 57 }, { "epoch": 0.23493670886075949, "grad_norm": 0.5620826849677341, "learning_rate": 1.886178861788618e-05, "loss": 0.6743, "step": 58 }, { "epoch": 0.2389873417721519, "grad_norm": 0.6697689121136997, "learning_rate": 1.91869918699187e-05, "loss": 0.7078, "step": 59 }, { "epoch": 0.2430379746835443, "grad_norm": 0.5842520770811517, "learning_rate": 1.9512195121951222e-05, "loss": 0.6967, "step": 60 }, { "epoch": 0.2470886075949367, "grad_norm": 0.5426469391399618, "learning_rate": 1.983739837398374e-05, "loss": 0.6885, "step": 61 }, { "epoch": 0.25113924050632913, "grad_norm": 0.7003619709756373, "learning_rate": 2.016260162601626e-05, "loss": 0.6861, "step": 62 }, { "epoch": 0.25518987341772154, "grad_norm": 0.6029037387825323, "learning_rate": 2.048780487804878e-05, "loss": 0.6716, "step": 63 }, { "epoch": 0.25924050632911394, "grad_norm": 0.6733895983820918, "learning_rate": 2.0813008130081303e-05, "loss": 0.6955, "step": 64 }, { "epoch": 0.26329113924050634, "grad_norm": 51.2808129483069, "learning_rate": 2.1138211382113822e-05, "loss": 0.7399, "step": 65 }, { "epoch": 0.26734177215189875, "grad_norm": 4.598963971288827, "learning_rate": 2.1463414634146344e-05, "loss": 0.6921, "step": 66 }, { "epoch": 0.27139240506329115, "grad_norm": 0.9018572839095363, "learning_rate": 2.1788617886178863e-05, "loss": 0.6875, "step": 67 }, { "epoch": 0.27544303797468356, "grad_norm": 0.6517863991010744, "learning_rate": 2.2113821138211385e-05, "loss": 0.6919, "step": 68 }, { "epoch": 0.27949367088607596, "grad_norm": 23.33721556636592, "learning_rate": 2.2439024390243907e-05, "loss": 0.6874, "step": 69 }, { "epoch": 0.28354430379746837, "grad_norm": 1.0912920100652825, "learning_rate": 2.2764227642276426e-05, "loss": 0.6751, "step": 70 }, { "epoch": 0.28759493670886077, "grad_norm": 0.7739196341135076, "learning_rate": 2.3089430894308948e-05, "loss": 0.6949, "step": 71 }, { "epoch": 0.2916455696202532, "grad_norm": 0.9309346310282163, "learning_rate": 2.3414634146341463e-05, "loss": 0.6386, "step": 72 }, { "epoch": 0.2956962025316456, "grad_norm": 0.7935981909175578, "learning_rate": 2.3739837398373985e-05, "loss": 0.6842, "step": 73 }, { "epoch": 0.299746835443038, "grad_norm": 0.885764136165014, "learning_rate": 2.4065040650406507e-05, "loss": 0.6741, "step": 74 }, { "epoch": 0.3037974683544304, "grad_norm": 0.6679604500883396, "learning_rate": 2.4390243902439026e-05, "loss": 0.6876, "step": 75 }, { "epoch": 0.3078481012658228, "grad_norm": 0.795620920562152, "learning_rate": 2.4715447154471548e-05, "loss": 0.6975, "step": 76 }, { "epoch": 0.3118987341772152, "grad_norm": 0.7794007179278049, "learning_rate": 2.5040650406504066e-05, "loss": 0.6655, "step": 77 }, { "epoch": 0.3159493670886076, "grad_norm": 0.6411129751300728, "learning_rate": 2.536585365853659e-05, "loss": 0.67, "step": 78 }, { "epoch": 0.32, "grad_norm": 0.8690744106665249, "learning_rate": 2.569105691056911e-05, "loss": 0.7069, "step": 79 }, { "epoch": 0.3240506329113924, "grad_norm": 0.7584939223710574, "learning_rate": 2.601626016260163e-05, "loss": 0.6478, "step": 80 }, { "epoch": 0.3281012658227848, "grad_norm": 0.8636000881868927, "learning_rate": 2.634146341463415e-05, "loss": 0.7098, "step": 81 }, { "epoch": 0.3321518987341772, "grad_norm": 0.7165014488264277, "learning_rate": 2.6666666666666667e-05, "loss": 0.6836, "step": 82 }, { "epoch": 0.3362025316455696, "grad_norm": 0.9772112019548278, "learning_rate": 2.699186991869919e-05, "loss": 0.6735, "step": 83 }, { "epoch": 0.34025316455696203, "grad_norm": 0.6894442354008121, "learning_rate": 2.731707317073171e-05, "loss": 0.6806, "step": 84 }, { "epoch": 0.34430379746835443, "grad_norm": 0.8634108798267301, "learning_rate": 2.764227642276423e-05, "loss": 0.6786, "step": 85 }, { "epoch": 0.34835443037974684, "grad_norm": 0.6210825494287873, "learning_rate": 2.796747967479675e-05, "loss": 0.6777, "step": 86 }, { "epoch": 0.35240506329113924, "grad_norm": 0.7125940083183058, "learning_rate": 2.829268292682927e-05, "loss": 0.7033, "step": 87 }, { "epoch": 0.35645569620253165, "grad_norm": 0.6624111261797143, "learning_rate": 2.8617886178861792e-05, "loss": 0.6878, "step": 88 }, { "epoch": 0.36050632911392405, "grad_norm": 0.7230820153503832, "learning_rate": 2.8943089430894314e-05, "loss": 0.6686, "step": 89 }, { "epoch": 0.36455696202531646, "grad_norm": 0.7686199163761198, "learning_rate": 2.926829268292683e-05, "loss": 0.6936, "step": 90 }, { "epoch": 0.36860759493670886, "grad_norm": 0.614144891863096, "learning_rate": 2.959349593495935e-05, "loss": 0.6736, "step": 91 }, { "epoch": 0.37265822784810126, "grad_norm": 0.715470157266548, "learning_rate": 2.991869918699187e-05, "loss": 0.6871, "step": 92 }, { "epoch": 0.37670886075949367, "grad_norm": 0.6534807691595567, "learning_rate": 3.0243902439024392e-05, "loss": 0.6943, "step": 93 }, { "epoch": 0.3807594936708861, "grad_norm": 0.7566066777230498, "learning_rate": 3.056910569105692e-05, "loss": 0.6789, "step": 94 }, { "epoch": 0.3848101265822785, "grad_norm": 0.5718940374560756, "learning_rate": 3.089430894308943e-05, "loss": 0.6635, "step": 95 }, { "epoch": 0.3888607594936709, "grad_norm": 0.7226548264458745, "learning_rate": 3.1219512195121955e-05, "loss": 0.6941, "step": 96 }, { "epoch": 0.3929113924050633, "grad_norm": 0.7664457849612513, "learning_rate": 3.154471544715447e-05, "loss": 0.6526, "step": 97 }, { "epoch": 0.3969620253164557, "grad_norm": 0.8971921338559296, "learning_rate": 3.186991869918699e-05, "loss": 0.6744, "step": 98 }, { "epoch": 0.4010126582278481, "grad_norm": 0.602819433057168, "learning_rate": 3.2195121951219514e-05, "loss": 0.6424, "step": 99 }, { "epoch": 0.4050632911392405, "grad_norm": 0.7662021305531703, "learning_rate": 3.2520325203252037e-05, "loss": 0.6649, "step": 100 }, { "epoch": 0.4091139240506329, "grad_norm": 0.6602687746488867, "learning_rate": 3.284552845528456e-05, "loss": 0.6909, "step": 101 }, { "epoch": 0.4131645569620253, "grad_norm": 0.6395588304987234, "learning_rate": 3.3170731707317074e-05, "loss": 0.672, "step": 102 }, { "epoch": 0.4172151898734177, "grad_norm": 0.7018670894470183, "learning_rate": 3.3495934959349596e-05, "loss": 0.669, "step": 103 }, { "epoch": 0.4212658227848101, "grad_norm": 0.6218892623411141, "learning_rate": 3.382113821138212e-05, "loss": 0.694, "step": 104 }, { "epoch": 0.4253164556962025, "grad_norm": 0.6962670591997273, "learning_rate": 3.414634146341463e-05, "loss": 0.6755, "step": 105 }, { "epoch": 0.4293670886075949, "grad_norm": 0.659859072200168, "learning_rate": 3.4471544715447155e-05, "loss": 0.6632, "step": 106 }, { "epoch": 0.43341772151898733, "grad_norm": 0.7495470873003227, "learning_rate": 3.479674796747968e-05, "loss": 0.6965, "step": 107 }, { "epoch": 0.43746835443037974, "grad_norm": 0.6426495381723629, "learning_rate": 3.51219512195122e-05, "loss": 0.6968, "step": 108 }, { "epoch": 0.44151898734177214, "grad_norm": 0.6863557948140806, "learning_rate": 3.544715447154472e-05, "loss": 0.6885, "step": 109 }, { "epoch": 0.44556962025316454, "grad_norm": 0.6477890898419979, "learning_rate": 3.577235772357724e-05, "loss": 0.6385, "step": 110 }, { "epoch": 0.44962025316455695, "grad_norm": 0.6298293048993389, "learning_rate": 3.609756097560976e-05, "loss": 0.7036, "step": 111 }, { "epoch": 0.45367088607594935, "grad_norm": 0.7233448013399941, "learning_rate": 3.642276422764228e-05, "loss": 0.6755, "step": 112 }, { "epoch": 0.45772151898734176, "grad_norm": 0.5479331169008168, "learning_rate": 3.67479674796748e-05, "loss": 0.6799, "step": 113 }, { "epoch": 0.46177215189873416, "grad_norm": 0.7356676126161068, "learning_rate": 3.7073170731707325e-05, "loss": 0.6668, "step": 114 }, { "epoch": 0.46582278481012657, "grad_norm": 0.5748646504190883, "learning_rate": 3.739837398373984e-05, "loss": 0.676, "step": 115 }, { "epoch": 0.46987341772151897, "grad_norm": 0.7307948858340639, "learning_rate": 3.772357723577236e-05, "loss": 0.6915, "step": 116 }, { "epoch": 0.4739240506329114, "grad_norm": 0.9316770746020587, "learning_rate": 3.804878048780488e-05, "loss": 0.6857, "step": 117 }, { "epoch": 0.4779746835443038, "grad_norm": 0.8864520933096941, "learning_rate": 3.83739837398374e-05, "loss": 0.6721, "step": 118 }, { "epoch": 0.4820253164556962, "grad_norm": 0.8685935972635128, "learning_rate": 3.869918699186992e-05, "loss": 0.6742, "step": 119 }, { "epoch": 0.4860759493670886, "grad_norm": 0.5666035908910901, "learning_rate": 3.9024390243902444e-05, "loss": 0.6415, "step": 120 }, { "epoch": 0.490126582278481, "grad_norm": 0.8688634856084404, "learning_rate": 3.9349593495934966e-05, "loss": 0.6444, "step": 121 }, { "epoch": 0.4941772151898734, "grad_norm": 0.8251766752793942, "learning_rate": 3.967479674796748e-05, "loss": 0.6963, "step": 122 }, { "epoch": 0.4982278481012658, "grad_norm": 1.0690973899004503, "learning_rate": 4e-05, "loss": 0.7333, "step": 123 }, { "epoch": 0.5022784810126583, "grad_norm": 0.6626767138623266, "learning_rate": 3.999991946137476e-05, "loss": 0.6908, "step": 124 }, { "epoch": 0.5063291139240507, "grad_norm": 0.9230592189787598, "learning_rate": 3.999967784614766e-05, "loss": 0.6511, "step": 125 }, { "epoch": 0.5103797468354431, "grad_norm": 0.7339024282311433, "learning_rate": 3.9999275156264656e-05, "loss": 0.6633, "step": 126 }, { "epoch": 0.5144303797468355, "grad_norm": 0.7180841880537463, "learning_rate": 3.999871139496895e-05, "loss": 0.7006, "step": 127 }, { "epoch": 0.5184810126582279, "grad_norm": 0.7007507599303358, "learning_rate": 3.9997986566800995e-05, "loss": 0.6872, "step": 128 }, { "epoch": 0.5225316455696203, "grad_norm": 0.8153206460030816, "learning_rate": 3.999710067759846e-05, "loss": 0.6645, "step": 129 }, { "epoch": 0.5265822784810127, "grad_norm": 0.7349189453018423, "learning_rate": 3.999605373449617e-05, "loss": 0.6712, "step": 130 }, { "epoch": 0.5306329113924051, "grad_norm": 0.6886177195029991, "learning_rate": 3.9994845745926075e-05, "loss": 0.6589, "step": 131 }, { "epoch": 0.5346835443037975, "grad_norm": 0.8295139495567869, "learning_rate": 3.999347672161713e-05, "loss": 0.6453, "step": 132 }, { "epoch": 0.5387341772151899, "grad_norm": 0.7935364251029555, "learning_rate": 3.999194667259528e-05, "loss": 0.6517, "step": 133 }, { "epoch": 0.5427848101265823, "grad_norm": 0.5691949097995066, "learning_rate": 3.999025561118334e-05, "loss": 0.6802, "step": 134 }, { "epoch": 0.5468354430379747, "grad_norm": 0.8262306577064575, "learning_rate": 3.998840355100086e-05, "loss": 0.688, "step": 135 }, { "epoch": 0.5508860759493671, "grad_norm": 0.6246801899998351, "learning_rate": 3.998639050696409e-05, "loss": 0.6765, "step": 136 }, { "epoch": 0.5549367088607595, "grad_norm": 0.7428170430264085, "learning_rate": 3.998421649528582e-05, "loss": 0.7108, "step": 137 }, { "epoch": 0.5589873417721519, "grad_norm": 0.8768979391466819, "learning_rate": 3.9981881533475234e-05, "loss": 0.6932, "step": 138 }, { "epoch": 0.5630379746835443, "grad_norm": 0.6373483395711393, "learning_rate": 3.997938564033779e-05, "loss": 0.6627, "step": 139 }, { "epoch": 0.5670886075949367, "grad_norm": 0.6126204093216814, "learning_rate": 3.9976728835975064e-05, "loss": 0.6699, "step": 140 }, { "epoch": 0.5711392405063291, "grad_norm": 0.7859296501636697, "learning_rate": 3.9973911141784605e-05, "loss": 0.6988, "step": 141 }, { "epoch": 0.5751898734177215, "grad_norm": 0.5722784500004687, "learning_rate": 3.997093258045973e-05, "loss": 0.6705, "step": 142 }, { "epoch": 0.579240506329114, "grad_norm": 0.73059039191431, "learning_rate": 3.996779317598936e-05, "loss": 0.6788, "step": 143 }, { "epoch": 0.5832911392405064, "grad_norm": 0.7558974385187035, "learning_rate": 3.996449295365782e-05, "loss": 0.6662, "step": 144 }, { "epoch": 0.5873417721518988, "grad_norm": 0.8161013071376181, "learning_rate": 3.996103194004467e-05, "loss": 0.6779, "step": 145 }, { "epoch": 0.5913924050632912, "grad_norm": 0.9045935376921952, "learning_rate": 3.995741016302441e-05, "loss": 0.6657, "step": 146 }, { "epoch": 0.5954430379746836, "grad_norm": 0.695967069222087, "learning_rate": 3.9953627651766364e-05, "loss": 0.6865, "step": 147 }, { "epoch": 0.599493670886076, "grad_norm": 0.6829261494233934, "learning_rate": 3.9949684436734325e-05, "loss": 0.6659, "step": 148 }, { "epoch": 0.6035443037974684, "grad_norm": 0.6413606462322627, "learning_rate": 3.994558054968643e-05, "loss": 0.6449, "step": 149 }, { "epoch": 0.6075949367088608, "grad_norm": 0.5789767975556366, "learning_rate": 3.994131602367481e-05, "loss": 0.6696, "step": 150 }, { "epoch": 0.6116455696202532, "grad_norm": 0.6219548625646258, "learning_rate": 3.9936890893045376e-05, "loss": 0.6761, "step": 151 }, { "epoch": 0.6156962025316456, "grad_norm": 0.545585502116287, "learning_rate": 3.993230519343752e-05, "loss": 0.658, "step": 152 }, { "epoch": 0.619746835443038, "grad_norm": 0.6985173759222896, "learning_rate": 3.992755896178383e-05, "loss": 0.6653, "step": 153 }, { "epoch": 0.6237974683544304, "grad_norm": 0.6355805078457287, "learning_rate": 3.992265223630981e-05, "loss": 0.6562, "step": 154 }, { "epoch": 0.6278481012658228, "grad_norm": 0.5508888931901409, "learning_rate": 3.991758505653355e-05, "loss": 0.6598, "step": 155 }, { "epoch": 0.6318987341772152, "grad_norm": 0.6516754358140808, "learning_rate": 3.991235746326543e-05, "loss": 0.6649, "step": 156 }, { "epoch": 0.6359493670886076, "grad_norm": 0.5071724847395258, "learning_rate": 3.9906969498607745e-05, "loss": 0.6299, "step": 157 }, { "epoch": 0.64, "grad_norm": 0.6345212177495141, "learning_rate": 3.990142120595444e-05, "loss": 0.6845, "step": 158 }, { "epoch": 0.6440506329113924, "grad_norm": 0.5339341688020346, "learning_rate": 3.98957126299907e-05, "loss": 0.6379, "step": 159 }, { "epoch": 0.6481012658227848, "grad_norm": 0.678253459306987, "learning_rate": 3.9889843816692596e-05, "loss": 0.6234, "step": 160 }, { "epoch": 0.6521518987341772, "grad_norm": 0.5552467649207307, "learning_rate": 3.9883814813326766e-05, "loss": 0.6721, "step": 161 }, { "epoch": 0.6562025316455696, "grad_norm": 0.5472557365448996, "learning_rate": 3.9877625668449956e-05, "loss": 0.6337, "step": 162 }, { "epoch": 0.660253164556962, "grad_norm": 0.6676492928515829, "learning_rate": 3.98712764319087e-05, "loss": 0.6882, "step": 163 }, { "epoch": 0.6643037974683544, "grad_norm": 0.6743042859229, "learning_rate": 3.9864767154838864e-05, "loss": 0.662, "step": 164 }, { "epoch": 0.6683544303797468, "grad_norm": 0.5188655685146508, "learning_rate": 3.9858097889665277e-05, "loss": 0.6815, "step": 165 }, { "epoch": 0.6724050632911392, "grad_norm": 0.6894528278551348, "learning_rate": 3.985126869010129e-05, "loss": 0.6579, "step": 166 }, { "epoch": 0.6764556962025317, "grad_norm": 0.49883499511250895, "learning_rate": 3.984427961114833e-05, "loss": 0.6478, "step": 167 }, { "epoch": 0.6805063291139241, "grad_norm": 0.5693471655643146, "learning_rate": 3.9837130709095475e-05, "loss": 0.6922, "step": 168 }, { "epoch": 0.6845569620253165, "grad_norm": 0.6207905438633471, "learning_rate": 3.982982204151901e-05, "loss": 0.6494, "step": 169 }, { "epoch": 0.6886075949367089, "grad_norm": 0.5287810967150083, "learning_rate": 3.982235366728193e-05, "loss": 0.6448, "step": 170 }, { "epoch": 0.6926582278481013, "grad_norm": 0.4876566802407022, "learning_rate": 3.9814725646533505e-05, "loss": 0.6353, "step": 171 }, { "epoch": 0.6967088607594937, "grad_norm": 0.644187249597131, "learning_rate": 3.9806938040708746e-05, "loss": 0.6714, "step": 172 }, { "epoch": 0.7007594936708861, "grad_norm": 0.6343584340568386, "learning_rate": 3.9798990912527976e-05, "loss": 0.6757, "step": 173 }, { "epoch": 0.7048101265822785, "grad_norm": 0.5367356552304908, "learning_rate": 3.979088432599627e-05, "loss": 0.6588, "step": 174 }, { "epoch": 0.7088607594936709, "grad_norm": 0.6560680611774174, "learning_rate": 3.9782618346402964e-05, "loss": 0.703, "step": 175 }, { "epoch": 0.7129113924050633, "grad_norm": 0.4922901615429702, "learning_rate": 3.977419304032111e-05, "loss": 0.649, "step": 176 }, { "epoch": 0.7169620253164557, "grad_norm": 0.5849071772599316, "learning_rate": 3.976560847560697e-05, "loss": 0.6574, "step": 177 }, { "epoch": 0.7210126582278481, "grad_norm": 0.4931260030910971, "learning_rate": 3.9756864721399456e-05, "loss": 0.6766, "step": 178 }, { "epoch": 0.7250632911392405, "grad_norm": 0.49513931702577885, "learning_rate": 3.974796184811956e-05, "loss": 0.6691, "step": 179 }, { "epoch": 0.7291139240506329, "grad_norm": 0.5459514985022029, "learning_rate": 3.973889992746979e-05, "loss": 0.6572, "step": 180 }, { "epoch": 0.7331645569620253, "grad_norm": 0.5429337570625526, "learning_rate": 3.972967903243361e-05, "loss": 0.665, "step": 181 }, { "epoch": 0.7372151898734177, "grad_norm": 0.49449255118471863, "learning_rate": 3.972029923727486e-05, "loss": 0.6595, "step": 182 }, { "epoch": 0.7412658227848101, "grad_norm": 0.5777574111079277, "learning_rate": 3.971076061753709e-05, "loss": 0.6721, "step": 183 }, { "epoch": 0.7453164556962025, "grad_norm": 0.49014246597283256, "learning_rate": 3.9701063250043066e-05, "loss": 0.6382, "step": 184 }, { "epoch": 0.7493670886075949, "grad_norm": 0.5512917207796271, "learning_rate": 3.969120721289402e-05, "loss": 0.6589, "step": 185 }, { "epoch": 0.7534177215189873, "grad_norm": 0.5196625833667552, "learning_rate": 3.9681192585469146e-05, "loss": 0.6737, "step": 186 }, { "epoch": 0.7574683544303797, "grad_norm": 0.5662646665915096, "learning_rate": 3.9671019448424865e-05, "loss": 0.6699, "step": 187 }, { "epoch": 0.7615189873417721, "grad_norm": 0.4905448027454576, "learning_rate": 3.966068788369422e-05, "loss": 0.6316, "step": 188 }, { "epoch": 0.7655696202531646, "grad_norm": 0.7431615664363561, "learning_rate": 3.965019797448622e-05, "loss": 0.6692, "step": 189 }, { "epoch": 0.769620253164557, "grad_norm": 0.5934967444262957, "learning_rate": 3.963954980528515e-05, "loss": 0.665, "step": 190 }, { "epoch": 0.7736708860759494, "grad_norm": 0.6246441557532207, "learning_rate": 3.9628743461849905e-05, "loss": 0.6536, "step": 191 }, { "epoch": 0.7777215189873418, "grad_norm": 0.5582628193865345, "learning_rate": 3.961777903121329e-05, "loss": 0.6873, "step": 192 }, { "epoch": 0.7817721518987342, "grad_norm": 0.6051928391792623, "learning_rate": 3.960665660168131e-05, "loss": 0.6466, "step": 193 }, { "epoch": 0.7858227848101266, "grad_norm": 0.5343506002727002, "learning_rate": 3.9595376262832485e-05, "loss": 0.6552, "step": 194 }, { "epoch": 0.789873417721519, "grad_norm": 0.738772488850437, "learning_rate": 3.9583938105517127e-05, "loss": 0.7164, "step": 195 }, { "epoch": 0.7939240506329114, "grad_norm": 0.6036762982927697, "learning_rate": 3.957234222185657e-05, "loss": 0.6788, "step": 196 }, { "epoch": 0.7979746835443038, "grad_norm": 0.5831620456207598, "learning_rate": 3.9560588705242474e-05, "loss": 0.6406, "step": 197 }, { "epoch": 0.8020253164556962, "grad_norm": 0.564513036939861, "learning_rate": 3.954867765033605e-05, "loss": 0.6784, "step": 198 }, { "epoch": 0.8060759493670886, "grad_norm": 0.5095577449065419, "learning_rate": 3.953660915306728e-05, "loss": 0.6472, "step": 199 }, { "epoch": 0.810126582278481, "grad_norm": 0.4961911177941573, "learning_rate": 3.952438331063419e-05, "loss": 0.6828, "step": 200 }, { "epoch": 0.8141772151898734, "grad_norm": 0.5119461070116865, "learning_rate": 3.951200022150205e-05, "loss": 0.63, "step": 201 }, { "epoch": 0.8182278481012658, "grad_norm": 0.497683223313219, "learning_rate": 3.949945998540253e-05, "loss": 0.6033, "step": 202 }, { "epoch": 0.8222784810126582, "grad_norm": 0.6050402001747106, "learning_rate": 3.9486762703332993e-05, "loss": 0.657, "step": 203 }, { "epoch": 0.8263291139240506, "grad_norm": 0.5089184116320216, "learning_rate": 3.947390847755559e-05, "loss": 0.711, "step": 204 }, { "epoch": 0.830379746835443, "grad_norm": 0.5828564751990262, "learning_rate": 3.946089741159648e-05, "loss": 0.6895, "step": 205 }, { "epoch": 0.8344303797468354, "grad_norm": 0.5147548202688172, "learning_rate": 3.944772961024501e-05, "loss": 0.6824, "step": 206 }, { "epoch": 0.8384810126582278, "grad_norm": 0.6561525604275191, "learning_rate": 3.943440517955285e-05, "loss": 0.6886, "step": 207 }, { "epoch": 0.8425316455696202, "grad_norm": 0.50680240420473, "learning_rate": 3.9420924226833126e-05, "loss": 0.6796, "step": 208 }, { "epoch": 0.8465822784810126, "grad_norm": 0.6296679259127017, "learning_rate": 3.9407286860659566e-05, "loss": 0.6621, "step": 209 }, { "epoch": 0.850632911392405, "grad_norm": 0.5029028735799916, "learning_rate": 3.9393493190865657e-05, "loss": 0.6207, "step": 210 }, { "epoch": 0.8546835443037974, "grad_norm": 0.6331872521866384, "learning_rate": 3.937954332854371e-05, "loss": 0.6508, "step": 211 }, { "epoch": 0.8587341772151899, "grad_norm": 0.5215165649384496, "learning_rate": 3.9365437386044016e-05, "loss": 0.6645, "step": 212 }, { "epoch": 0.8627848101265823, "grad_norm": 0.5739054327687274, "learning_rate": 3.935117547697387e-05, "loss": 0.6493, "step": 213 }, { "epoch": 0.8668354430379747, "grad_norm": 0.501411228795912, "learning_rate": 3.933675771619675e-05, "loss": 0.6584, "step": 214 }, { "epoch": 0.8708860759493671, "grad_norm": 0.6021929719651046, "learning_rate": 3.932218421983131e-05, "loss": 0.6437, "step": 215 }, { "epoch": 0.8749367088607595, "grad_norm": 0.529952160952587, "learning_rate": 3.9307455105250484e-05, "loss": 0.6747, "step": 216 }, { "epoch": 0.8789873417721519, "grad_norm": 0.5436575688172298, "learning_rate": 3.929257049108054e-05, "loss": 0.6359, "step": 217 }, { "epoch": 0.8830379746835443, "grad_norm": 0.5469599288213067, "learning_rate": 3.927753049720011e-05, "loss": 0.6659, "step": 218 }, { "epoch": 0.8870886075949367, "grad_norm": 0.48880175341542614, "learning_rate": 3.9262335244739234e-05, "loss": 0.6444, "step": 219 }, { "epoch": 0.8911392405063291, "grad_norm": 0.51736724746964, "learning_rate": 3.92469848560784e-05, "loss": 0.652, "step": 220 }, { "epoch": 0.8951898734177215, "grad_norm": 0.5189671405934762, "learning_rate": 3.923147945484751e-05, "loss": 0.6573, "step": 221 }, { "epoch": 0.8992405063291139, "grad_norm": 0.5412865386054138, "learning_rate": 3.9215819165924956e-05, "loss": 0.6802, "step": 222 }, { "epoch": 0.9032911392405063, "grad_norm": 0.5276054367738454, "learning_rate": 3.920000411543654e-05, "loss": 0.6652, "step": 223 }, { "epoch": 0.9073417721518987, "grad_norm": 0.5275162914252375, "learning_rate": 3.9184034430754495e-05, "loss": 0.6551, "step": 224 }, { "epoch": 0.9113924050632911, "grad_norm": 0.5180823200955641, "learning_rate": 3.916791024049648e-05, "loss": 0.6604, "step": 225 }, { "epoch": 0.9154430379746835, "grad_norm": 0.5513368198861623, "learning_rate": 3.91516316745245e-05, "loss": 0.6741, "step": 226 }, { "epoch": 0.9194936708860759, "grad_norm": 0.5222816815602969, "learning_rate": 3.913519886394389e-05, "loss": 0.6818, "step": 227 }, { "epoch": 0.9235443037974683, "grad_norm": 0.7325540999733936, "learning_rate": 3.911861194110225e-05, "loss": 0.6596, "step": 228 }, { "epoch": 0.9275949367088607, "grad_norm": 0.4839711837713124, "learning_rate": 3.910187103958837e-05, "loss": 0.6513, "step": 229 }, { "epoch": 0.9316455696202531, "grad_norm": 0.6874030569912508, "learning_rate": 3.908497629423117e-05, "loss": 0.6584, "step": 230 }, { "epoch": 0.9356962025316455, "grad_norm": 0.5247672610250803, "learning_rate": 3.9067927841098614e-05, "loss": 0.6344, "step": 231 }, { "epoch": 0.9397468354430379, "grad_norm": 0.619734056890781, "learning_rate": 3.9050725817496594e-05, "loss": 0.6508, "step": 232 }, { "epoch": 0.9437974683544303, "grad_norm": 0.5286682590945826, "learning_rate": 3.9033370361967844e-05, "loss": 0.669, "step": 233 }, { "epoch": 0.9478481012658228, "grad_norm": 0.5546491650038724, "learning_rate": 3.901586161429081e-05, "loss": 0.6637, "step": 234 }, { "epoch": 0.9518987341772152, "grad_norm": 0.5239769720635296, "learning_rate": 3.8998199715478545e-05, "loss": 0.6597, "step": 235 }, { "epoch": 0.9559493670886076, "grad_norm": 0.7369200861125692, "learning_rate": 3.8980384807777564e-05, "loss": 0.6268, "step": 236 }, { "epoch": 0.96, "grad_norm": 0.684216668770548, "learning_rate": 3.896241703466667e-05, "loss": 0.6568, "step": 237 }, { "epoch": 0.9640506329113924, "grad_norm": 0.7368144056214774, "learning_rate": 3.894429654085585e-05, "loss": 0.63, "step": 238 }, { "epoch": 0.9681012658227848, "grad_norm": 0.7299452698933845, "learning_rate": 3.892602347228505e-05, "loss": 0.6698, "step": 239 }, { "epoch": 0.9721518987341772, "grad_norm": 0.6016366701664058, "learning_rate": 3.890759797612307e-05, "loss": 0.6578, "step": 240 }, { "epoch": 0.9762025316455696, "grad_norm": 0.764646479520876, "learning_rate": 3.888902020076632e-05, "loss": 0.6627, "step": 241 }, { "epoch": 0.980253164556962, "grad_norm": 0.5721923678485998, "learning_rate": 3.887029029583764e-05, "loss": 0.643, "step": 242 }, { "epoch": 0.9843037974683544, "grad_norm": 0.5050281739085063, "learning_rate": 3.8851408412185125e-05, "loss": 0.6161, "step": 243 }, { "epoch": 0.9883544303797468, "grad_norm": 0.5096459976037129, "learning_rate": 3.8832374701880855e-05, "loss": 0.6385, "step": 244 }, { "epoch": 0.9924050632911392, "grad_norm": 0.5092059026421215, "learning_rate": 3.881318931821972e-05, "loss": 0.65, "step": 245 }, { "epoch": 0.9964556962025316, "grad_norm": 0.5480759894630823, "learning_rate": 3.879385241571817e-05, "loss": 0.6662, "step": 246 }, { "epoch": 1.0020253164556963, "grad_norm": 0.5633173876314511, "learning_rate": 3.8774364150112955e-05, "loss": 0.5697, "step": 247 }, { "epoch": 1.0060759493670886, "grad_norm": 0.6912874836339888, "learning_rate": 3.8754724678359884e-05, "loss": 0.5226, "step": 248 }, { "epoch": 1.010126582278481, "grad_norm": 0.6153647783924325, "learning_rate": 3.873493415863256e-05, "loss": 0.5364, "step": 249 }, { "epoch": 1.0141772151898734, "grad_norm": 0.7299762772801596, "learning_rate": 3.871499275032111e-05, "loss": 0.4926, "step": 250 }, { "epoch": 1.0182278481012659, "grad_norm": 0.637295054516586, "learning_rate": 3.869490061403091e-05, "loss": 0.5054, "step": 251 }, { "epoch": 1.0222784810126582, "grad_norm": 0.6651988933022397, "learning_rate": 3.867465791158124e-05, "loss": 0.4984, "step": 252 }, { "epoch": 1.0263291139240507, "grad_norm": 0.5892052269880511, "learning_rate": 3.865426480600407e-05, "loss": 0.4768, "step": 253 }, { "epoch": 1.030379746835443, "grad_norm": 0.6973894434322551, "learning_rate": 3.863372146154264e-05, "loss": 0.5179, "step": 254 }, { "epoch": 1.0344303797468355, "grad_norm": 0.5632252029494603, "learning_rate": 3.861302804365024e-05, "loss": 0.4979, "step": 255 }, { "epoch": 1.0384810126582278, "grad_norm": 0.5495096542920141, "learning_rate": 3.85921847189888e-05, "loss": 0.4973, "step": 256 }, { "epoch": 1.0425316455696203, "grad_norm": 0.5190654042333683, "learning_rate": 3.85711916554276e-05, "loss": 0.5339, "step": 257 }, { "epoch": 1.0465822784810126, "grad_norm": 0.600657540416428, "learning_rate": 3.85500490220419e-05, "loss": 0.5121, "step": 258 }, { "epoch": 1.0506329113924051, "grad_norm": 0.5348690559488856, "learning_rate": 3.852875698911154e-05, "loss": 0.4641, "step": 259 }, { "epoch": 1.0546835443037974, "grad_norm": 0.6161352548482458, "learning_rate": 3.850731572811963e-05, "loss": 0.5152, "step": 260 }, { "epoch": 1.05873417721519, "grad_norm": 0.5643985033609311, "learning_rate": 3.848572541175116e-05, "loss": 0.4941, "step": 261 }, { "epoch": 1.0627848101265822, "grad_norm": 0.5782380701735336, "learning_rate": 3.846398621389154e-05, "loss": 0.4921, "step": 262 }, { "epoch": 1.0668354430379747, "grad_norm": 0.5242762713437595, "learning_rate": 3.84420983096253e-05, "loss": 0.5007, "step": 263 }, { "epoch": 1.070886075949367, "grad_norm": 0.5524278562830558, "learning_rate": 3.8420061875234606e-05, "loss": 0.509, "step": 264 }, { "epoch": 1.0749367088607595, "grad_norm": 0.6161876127029539, "learning_rate": 3.839787708819787e-05, "loss": 0.529, "step": 265 }, { "epoch": 1.0789873417721518, "grad_norm": 0.4861542036474607, "learning_rate": 3.8375544127188325e-05, "loss": 0.4864, "step": 266 }, { "epoch": 1.0830379746835443, "grad_norm": 0.60449088288614, "learning_rate": 3.8353063172072564e-05, "loss": 0.5017, "step": 267 }, { "epoch": 1.0870886075949366, "grad_norm": 0.5638381705348728, "learning_rate": 3.8330434403909105e-05, "loss": 0.5094, "step": 268 }, { "epoch": 1.0911392405063292, "grad_norm": 0.5368542640072127, "learning_rate": 3.8307658004946934e-05, "loss": 0.5049, "step": 269 }, { "epoch": 1.0951898734177214, "grad_norm": 0.5472693405125091, "learning_rate": 3.8284734158624046e-05, "loss": 0.4962, "step": 270 }, { "epoch": 1.099240506329114, "grad_norm": 0.5513695377658225, "learning_rate": 3.826166304956594e-05, "loss": 0.4785, "step": 271 }, { "epoch": 1.1032911392405063, "grad_norm": 0.5736575009211294, "learning_rate": 3.8238444863584164e-05, "loss": 0.5132, "step": 272 }, { "epoch": 1.1073417721518988, "grad_norm": 0.5534834720423816, "learning_rate": 3.821507978767479e-05, "loss": 0.5074, "step": 273 }, { "epoch": 1.111392405063291, "grad_norm": 0.5519380884916774, "learning_rate": 3.819156801001693e-05, "loss": 0.4909, "step": 274 }, { "epoch": 1.1154430379746836, "grad_norm": 0.5931944063697848, "learning_rate": 3.816790971997121e-05, "loss": 0.49, "step": 275 }, { "epoch": 1.1194936708860759, "grad_norm": 0.6074012250197438, "learning_rate": 3.8144105108078246e-05, "loss": 0.5, "step": 276 }, { "epoch": 1.1235443037974684, "grad_norm": 0.6979536389190363, "learning_rate": 3.81201543660571e-05, "loss": 0.4828, "step": 277 }, { "epoch": 1.1275949367088607, "grad_norm": 0.6139758886859065, "learning_rate": 3.809605768680377e-05, "loss": 0.4855, "step": 278 }, { "epoch": 1.1316455696202532, "grad_norm": 0.7344489198131261, "learning_rate": 3.807181526438958e-05, "loss": 0.5012, "step": 279 }, { "epoch": 1.1356962025316455, "grad_norm": 0.6536359256620797, "learning_rate": 3.8047427294059697e-05, "loss": 0.5041, "step": 280 }, { "epoch": 1.139746835443038, "grad_norm": 0.757024555652282, "learning_rate": 3.802289397223145e-05, "loss": 0.4981, "step": 281 }, { "epoch": 1.1437974683544303, "grad_norm": 0.6671851870287755, "learning_rate": 3.7998215496492854e-05, "loss": 0.4892, "step": 282 }, { "epoch": 1.1478481012658228, "grad_norm": 0.7009657604001279, "learning_rate": 3.797339206560096e-05, "loss": 0.4893, "step": 283 }, { "epoch": 1.1518987341772151, "grad_norm": 0.7447742250067785, "learning_rate": 3.794842387948027e-05, "loss": 0.499, "step": 284 }, { "epoch": 1.1559493670886076, "grad_norm": 0.6906503983481183, "learning_rate": 3.7923311139221114e-05, "loss": 0.5102, "step": 285 }, { "epoch": 1.16, "grad_norm": 0.6494060275565782, "learning_rate": 3.7898054047078054e-05, "loss": 0.4984, "step": 286 }, { "epoch": 1.1640506329113924, "grad_norm": 0.6720608608318112, "learning_rate": 3.787265280646825e-05, "loss": 0.5049, "step": 287 }, { "epoch": 1.1681012658227847, "grad_norm": 0.6395179724771874, "learning_rate": 3.7847107621969786e-05, "loss": 0.4937, "step": 288 }, { "epoch": 1.1721518987341772, "grad_norm": 0.6000705827037229, "learning_rate": 3.7821418699320064e-05, "loss": 0.485, "step": 289 }, { "epoch": 1.1762025316455695, "grad_norm": 0.546203494666136, "learning_rate": 3.7795586245414145e-05, "loss": 0.4938, "step": 290 }, { "epoch": 1.180253164556962, "grad_norm": 0.6193556781344189, "learning_rate": 3.776961046830306e-05, "loss": 0.511, "step": 291 }, { "epoch": 1.1843037974683543, "grad_norm": 0.5060869412064011, "learning_rate": 3.774349157719215e-05, "loss": 0.5292, "step": 292 }, { "epoch": 1.1883544303797469, "grad_norm": 0.6330339085178774, "learning_rate": 3.7717229782439365e-05, "loss": 0.4917, "step": 293 }, { "epoch": 1.1924050632911392, "grad_norm": 0.5232226782073877, "learning_rate": 3.769082529555359e-05, "loss": 0.5117, "step": 294 }, { "epoch": 1.1964556962025317, "grad_norm": 0.5616604415476034, "learning_rate": 3.766427832919294e-05, "loss": 0.4995, "step": 295 }, { "epoch": 1.200506329113924, "grad_norm": 0.5703643758469359, "learning_rate": 3.7637589097163024e-05, "loss": 0.4756, "step": 296 }, { "epoch": 1.2045569620253165, "grad_norm": 0.5240690554543521, "learning_rate": 3.761075781441526e-05, "loss": 0.5001, "step": 297 }, { "epoch": 1.2086075949367088, "grad_norm": 0.6309565239625404, "learning_rate": 3.75837846970451e-05, "loss": 0.482, "step": 298 }, { "epoch": 1.2126582278481013, "grad_norm": 0.5855666534404472, "learning_rate": 3.755666996229032e-05, "loss": 0.4904, "step": 299 }, { "epoch": 1.2167088607594936, "grad_norm": 0.5568732957897233, "learning_rate": 3.752941382852927e-05, "loss": 0.519, "step": 300 }, { "epoch": 1.220759493670886, "grad_norm": 0.5553374385089477, "learning_rate": 3.7502016515279115e-05, "loss": 0.5313, "step": 301 }, { "epoch": 1.2248101265822784, "grad_norm": 0.6276596015808792, "learning_rate": 3.7474478243194043e-05, "loss": 0.5161, "step": 302 }, { "epoch": 1.228860759493671, "grad_norm": 0.5126361155823284, "learning_rate": 3.744679923406351e-05, "loss": 0.4956, "step": 303 }, { "epoch": 1.2329113924050632, "grad_norm": 0.5717799165196343, "learning_rate": 3.741897971081043e-05, "loss": 0.4857, "step": 304 }, { "epoch": 1.2369620253164557, "grad_norm": 0.562263210224109, "learning_rate": 3.739101989748946e-05, "loss": 0.5203, "step": 305 }, { "epoch": 1.241012658227848, "grad_norm": 0.5200393564581356, "learning_rate": 3.7362920019285066e-05, "loss": 0.5023, "step": 306 }, { "epoch": 1.2450632911392405, "grad_norm": 0.6485739827597827, "learning_rate": 3.73346803025098e-05, "loss": 0.4963, "step": 307 }, { "epoch": 1.2491139240506328, "grad_norm": 0.4649451058535051, "learning_rate": 3.730630097460247e-05, "loss": 0.5031, "step": 308 }, { "epoch": 1.2531645569620253, "grad_norm": 0.6621576514935927, "learning_rate": 3.727778226412628e-05, "loss": 0.5159, "step": 309 }, { "epoch": 1.2572151898734178, "grad_norm": 0.5118854188094253, "learning_rate": 3.7249124400767006e-05, "loss": 0.5056, "step": 310 }, { "epoch": 1.2612658227848101, "grad_norm": 0.4930991054790259, "learning_rate": 3.722032761533114e-05, "loss": 0.503, "step": 311 }, { "epoch": 1.2653164556962024, "grad_norm": 0.5100371280169915, "learning_rate": 3.719139213974403e-05, "loss": 0.5038, "step": 312 }, { "epoch": 1.269367088607595, "grad_norm": 0.5104215648314444, "learning_rate": 3.7162318207048006e-05, "loss": 0.4841, "step": 313 }, { "epoch": 1.2734177215189875, "grad_norm": 0.5217125041203684, "learning_rate": 3.713310605140055e-05, "loss": 0.5191, "step": 314 }, { "epoch": 1.2774683544303798, "grad_norm": 0.4874644326407009, "learning_rate": 3.710375590807233e-05, "loss": 0.4858, "step": 315 }, { "epoch": 1.281518987341772, "grad_norm": 0.5877277796835875, "learning_rate": 3.7074268013445365e-05, "loss": 0.5297, "step": 316 }, { "epoch": 1.2855696202531646, "grad_norm": 0.49305371815240506, "learning_rate": 3.7044642605011114e-05, "loss": 0.4914, "step": 317 }, { "epoch": 1.289620253164557, "grad_norm": 0.5557025523510771, "learning_rate": 3.701487992136854e-05, "loss": 0.5027, "step": 318 }, { "epoch": 1.2936708860759494, "grad_norm": 0.45737642903936865, "learning_rate": 3.69849802022222e-05, "loss": 0.4961, "step": 319 }, { "epoch": 1.2977215189873417, "grad_norm": 0.5340041910973147, "learning_rate": 3.6954943688380334e-05, "loss": 0.4944, "step": 320 }, { "epoch": 1.3017721518987342, "grad_norm": 0.5789121361417399, "learning_rate": 3.692477062175289e-05, "loss": 0.4956, "step": 321 }, { "epoch": 1.3058227848101267, "grad_norm": 0.5281427283726504, "learning_rate": 3.689446124534958e-05, "loss": 0.5303, "step": 322 }, { "epoch": 1.309873417721519, "grad_norm": 0.5515669005509105, "learning_rate": 3.686401580327799e-05, "loss": 0.5143, "step": 323 }, { "epoch": 1.3139240506329113, "grad_norm": 0.5290163081258216, "learning_rate": 3.683343454074149e-05, "loss": 0.4893, "step": 324 }, { "epoch": 1.3179746835443038, "grad_norm": 0.5705688221663016, "learning_rate": 3.6802717704037386e-05, "loss": 0.4917, "step": 325 }, { "epoch": 1.3220253164556963, "grad_norm": 0.5756767393154624, "learning_rate": 3.6771865540554855e-05, "loss": 0.5068, "step": 326 }, { "epoch": 1.3260759493670886, "grad_norm": 0.5399090621809659, "learning_rate": 3.674087829877297e-05, "loss": 0.5194, "step": 327 }, { "epoch": 1.330126582278481, "grad_norm": 0.5738529521785012, "learning_rate": 3.6709756228258735e-05, "loss": 0.4879, "step": 328 }, { "epoch": 1.3341772151898734, "grad_norm": 0.5299272073316522, "learning_rate": 3.667849957966501e-05, "loss": 0.5135, "step": 329 }, { "epoch": 1.338227848101266, "grad_norm": 0.5695265215221803, "learning_rate": 3.6647108604728546e-05, "loss": 0.534, "step": 330 }, { "epoch": 1.3422784810126582, "grad_norm": 0.5035839470222868, "learning_rate": 3.661558355626795e-05, "loss": 0.4895, "step": 331 }, { "epoch": 1.3463291139240505, "grad_norm": 0.5399336146292637, "learning_rate": 3.658392468818163e-05, "loss": 0.5168, "step": 332 }, { "epoch": 1.350379746835443, "grad_norm": 0.5519479984999787, "learning_rate": 3.655213225544574e-05, "loss": 0.5161, "step": 333 }, { "epoch": 1.3544303797468356, "grad_norm": 0.5994016250110185, "learning_rate": 3.652020651411218e-05, "loss": 0.5007, "step": 334 }, { "epoch": 1.3584810126582278, "grad_norm": 0.5859772693378843, "learning_rate": 3.6488147721306474e-05, "loss": 0.5076, "step": 335 }, { "epoch": 1.3625316455696201, "grad_norm": 0.5292551442440819, "learning_rate": 3.645595613522574e-05, "loss": 0.5181, "step": 336 }, { "epoch": 1.3665822784810127, "grad_norm": 0.5649509441576297, "learning_rate": 3.642363201513657e-05, "loss": 0.5033, "step": 337 }, { "epoch": 1.3706329113924052, "grad_norm": 0.5046383621618952, "learning_rate": 3.6391175621373006e-05, "loss": 0.4947, "step": 338 }, { "epoch": 1.3746835443037975, "grad_norm": 0.517489177957339, "learning_rate": 3.6358587215334355e-05, "loss": 0.4993, "step": 339 }, { "epoch": 1.3787341772151898, "grad_norm": 0.5064866502486751, "learning_rate": 3.632586705948318e-05, "loss": 0.5073, "step": 340 }, { "epoch": 1.3827848101265823, "grad_norm": 0.5213783922307612, "learning_rate": 3.629301541734311e-05, "loss": 0.5083, "step": 341 }, { "epoch": 1.3868354430379748, "grad_norm": 0.5098955881496724, "learning_rate": 3.626003255349676e-05, "loss": 0.5108, "step": 342 }, { "epoch": 1.390886075949367, "grad_norm": 0.49412846913278236, "learning_rate": 3.622691873358357e-05, "loss": 0.5203, "step": 343 }, { "epoch": 1.3949367088607594, "grad_norm": 0.5229992175604281, "learning_rate": 3.61936742242977e-05, "loss": 0.4922, "step": 344 }, { "epoch": 1.398987341772152, "grad_norm": 0.5404566464010857, "learning_rate": 3.6160299293385864e-05, "loss": 0.5159, "step": 345 }, { "epoch": 1.4030379746835444, "grad_norm": 0.5330608846658038, "learning_rate": 3.612679420964516e-05, "loss": 0.5168, "step": 346 }, { "epoch": 1.4070886075949367, "grad_norm": 0.5565922232070477, "learning_rate": 3.609315924292092e-05, "loss": 0.5397, "step": 347 }, { "epoch": 1.411139240506329, "grad_norm": 0.5208898226654466, "learning_rate": 3.6059394664104554e-05, "loss": 0.4978, "step": 348 }, { "epoch": 1.4151898734177215, "grad_norm": 0.5739975737954179, "learning_rate": 3.602550074513133e-05, "loss": 0.5422, "step": 349 }, { "epoch": 1.419240506329114, "grad_norm": 0.5236812067892401, "learning_rate": 3.599147775897822e-05, "loss": 0.5026, "step": 350 }, { "epoch": 1.4232911392405063, "grad_norm": 0.5381486520948756, "learning_rate": 3.595732597966167e-05, "loss": 0.5082, "step": 351 }, { "epoch": 1.4273417721518986, "grad_norm": 0.560852711679103, "learning_rate": 3.592304568223542e-05, "loss": 0.4959, "step": 352 }, { "epoch": 1.4313924050632911, "grad_norm": 0.47198809869893715, "learning_rate": 3.588863714278826e-05, "loss": 0.4735, "step": 353 }, { "epoch": 1.4354430379746836, "grad_norm": 0.575117401486915, "learning_rate": 3.585410063844186e-05, "loss": 0.5178, "step": 354 }, { "epoch": 1.439493670886076, "grad_norm": 0.5187107821283244, "learning_rate": 3.581943644734846e-05, "loss": 0.5236, "step": 355 }, { "epoch": 1.4435443037974682, "grad_norm": 0.4802734341412175, "learning_rate": 3.578464484868869e-05, "loss": 0.4952, "step": 356 }, { "epoch": 1.4475949367088607, "grad_norm": 0.4882213308629254, "learning_rate": 3.5749726122669316e-05, "loss": 0.498, "step": 357 }, { "epoch": 1.4516455696202533, "grad_norm": 0.537279769225554, "learning_rate": 3.5714680550520943e-05, "loss": 0.5121, "step": 358 }, { "epoch": 1.4556962025316456, "grad_norm": 0.5057191470218594, "learning_rate": 3.5679508414495794e-05, "loss": 0.4854, "step": 359 }, { "epoch": 1.4597468354430378, "grad_norm": 0.4953719729967976, "learning_rate": 3.564420999786543e-05, "loss": 0.5239, "step": 360 }, { "epoch": 1.4637974683544304, "grad_norm": 0.5279864461695507, "learning_rate": 3.560878558491842e-05, "loss": 0.5004, "step": 361 }, { "epoch": 1.4678481012658229, "grad_norm": 0.46820368919620825, "learning_rate": 3.5573235460958145e-05, "loss": 0.5221, "step": 362 }, { "epoch": 1.4718987341772152, "grad_norm": 0.5167814873203079, "learning_rate": 3.553755991230039e-05, "loss": 0.5072, "step": 363 }, { "epoch": 1.4759493670886075, "grad_norm": 0.5254273040896952, "learning_rate": 3.5501759226271144e-05, "loss": 0.5212, "step": 364 }, { "epoch": 1.48, "grad_norm": 0.4642310655267102, "learning_rate": 3.546583369120419e-05, "loss": 0.4952, "step": 365 }, { "epoch": 1.4840506329113925, "grad_norm": 0.5216608157327455, "learning_rate": 3.5429783596438864e-05, "loss": 0.5321, "step": 366 }, { "epoch": 1.4881012658227848, "grad_norm": 0.45631611003910943, "learning_rate": 3.539360923231766e-05, "loss": 0.5159, "step": 367 }, { "epoch": 1.492151898734177, "grad_norm": 0.46856954172044535, "learning_rate": 3.535731089018394e-05, "loss": 0.4866, "step": 368 }, { "epoch": 1.4962025316455696, "grad_norm": 0.46711778976776314, "learning_rate": 3.532088886237956e-05, "loss": 0.5421, "step": 369 }, { "epoch": 1.5002531645569621, "grad_norm": 0.4649469587560329, "learning_rate": 3.528434344224253e-05, "loss": 0.506, "step": 370 }, { "epoch": 1.5043037974683544, "grad_norm": 0.4780952118843178, "learning_rate": 3.524767492410464e-05, "loss": 0.4942, "step": 371 }, { "epoch": 1.5083544303797467, "grad_norm": 0.5152115459150736, "learning_rate": 3.521088360328908e-05, "loss": 0.5188, "step": 372 }, { "epoch": 1.5124050632911392, "grad_norm": 0.5371644973608477, "learning_rate": 3.517396977610811e-05, "loss": 0.4976, "step": 373 }, { "epoch": 1.5164556962025317, "grad_norm": 0.49347090050405834, "learning_rate": 3.5136933739860595e-05, "loss": 0.5004, "step": 374 }, { "epoch": 1.520506329113924, "grad_norm": 0.5687837985245757, "learning_rate": 3.509977579282971e-05, "loss": 0.49, "step": 375 }, { "epoch": 1.5245569620253163, "grad_norm": 0.4582949566906621, "learning_rate": 3.5062496234280424e-05, "loss": 0.4898, "step": 376 }, { "epoch": 1.5286075949367088, "grad_norm": 0.5356488253540134, "learning_rate": 3.502509536445719e-05, "loss": 0.5118, "step": 377 }, { "epoch": 1.5326582278481014, "grad_norm": 0.48553106038460675, "learning_rate": 3.498757348458147e-05, "loss": 0.499, "step": 378 }, { "epoch": 1.5367088607594936, "grad_norm": 0.5709507667267254, "learning_rate": 3.4949930896849324e-05, "loss": 0.5025, "step": 379 }, { "epoch": 1.540759493670886, "grad_norm": 0.47687044848879545, "learning_rate": 3.491216790442899e-05, "loss": 0.5239, "step": 380 }, { "epoch": 1.5448101265822785, "grad_norm": 0.5679065673141849, "learning_rate": 3.487428481145839e-05, "loss": 0.5155, "step": 381 }, { "epoch": 1.548860759493671, "grad_norm": 0.4786156930791156, "learning_rate": 3.483628192304278e-05, "loss": 0.5251, "step": 382 }, { "epoch": 1.5529113924050633, "grad_norm": 0.5436621961754096, "learning_rate": 3.479815954525219e-05, "loss": 0.5277, "step": 383 }, { "epoch": 1.5569620253164556, "grad_norm": 0.5728321782923985, "learning_rate": 3.475991798511899e-05, "loss": 0.5226, "step": 384 }, { "epoch": 1.561012658227848, "grad_norm": 0.5652438493319508, "learning_rate": 3.4721557550635464e-05, "loss": 0.5306, "step": 385 }, { "epoch": 1.5650632911392406, "grad_norm": 0.5787671157237091, "learning_rate": 3.468307855075128e-05, "loss": 0.53, "step": 386 }, { "epoch": 1.5691139240506329, "grad_norm": 0.55069197025856, "learning_rate": 3.4644481295371005e-05, "loss": 0.4988, "step": 387 }, { "epoch": 1.5731645569620252, "grad_norm": 0.5202100813223759, "learning_rate": 3.460576609535163e-05, "loss": 0.5047, "step": 388 }, { "epoch": 1.5772151898734177, "grad_norm": 0.5050015143374722, "learning_rate": 3.456693326250006e-05, "loss": 0.4952, "step": 389 }, { "epoch": 1.5812658227848102, "grad_norm": 0.5487556308409635, "learning_rate": 3.452798310957058e-05, "loss": 0.5241, "step": 390 }, { "epoch": 1.5853164556962025, "grad_norm": 0.4837328638509593, "learning_rate": 3.4488915950262386e-05, "loss": 0.4837, "step": 391 }, { "epoch": 1.5893670886075948, "grad_norm": 0.4435760970028467, "learning_rate": 3.4449732099216985e-05, "loss": 0.4961, "step": 392 }, { "epoch": 1.5934177215189873, "grad_norm": 0.48516796937696804, "learning_rate": 3.441043187201574e-05, "loss": 0.5003, "step": 393 }, { "epoch": 1.5974683544303798, "grad_norm": 0.4465420547118496, "learning_rate": 3.437101558517728e-05, "loss": 0.5184, "step": 394 }, { "epoch": 1.6015189873417721, "grad_norm": 0.49728568199748413, "learning_rate": 3.433148355615496e-05, "loss": 0.5379, "step": 395 }, { "epoch": 1.6055696202531644, "grad_norm": 0.44335943608135364, "learning_rate": 3.4291836103334294e-05, "loss": 0.5084, "step": 396 }, { "epoch": 1.609620253164557, "grad_norm": 0.45464489427640475, "learning_rate": 3.425207354603043e-05, "loss": 0.5306, "step": 397 }, { "epoch": 1.6136708860759494, "grad_norm": 0.44552621613261956, "learning_rate": 3.421219620448553e-05, "loss": 0.5046, "step": 398 }, { "epoch": 1.6177215189873417, "grad_norm": 0.43914528116709456, "learning_rate": 3.417220439986623e-05, "loss": 0.484, "step": 399 }, { "epoch": 1.621772151898734, "grad_norm": 0.4333460343652091, "learning_rate": 3.4132098454261024e-05, "loss": 0.5029, "step": 400 }, { "epoch": 1.6258227848101265, "grad_norm": 0.5055946950405908, "learning_rate": 3.4091878690677676e-05, "loss": 0.5419, "step": 401 }, { "epoch": 1.629873417721519, "grad_norm": 0.4624835105530372, "learning_rate": 3.405154543304065e-05, "loss": 0.4805, "step": 402 }, { "epoch": 1.6339240506329114, "grad_norm": 0.45917317596828194, "learning_rate": 3.401109900618843e-05, "loss": 0.4788, "step": 403 }, { "epoch": 1.6379746835443036, "grad_norm": 0.48021873942058646, "learning_rate": 3.3970539735870996e-05, "loss": 0.5089, "step": 404 }, { "epoch": 1.6420253164556962, "grad_norm": 0.4820527964687769, "learning_rate": 3.392986794874714e-05, "loss": 0.492, "step": 405 }, { "epoch": 1.6460759493670887, "grad_norm": 0.5224795189460181, "learning_rate": 3.388908397238184e-05, "loss": 0.4995, "step": 406 }, { "epoch": 1.650126582278481, "grad_norm": 0.49364104068375086, "learning_rate": 3.384818813524362e-05, "loss": 0.5245, "step": 407 }, { "epoch": 1.6541772151898733, "grad_norm": 0.5516943452708151, "learning_rate": 3.380718076670195e-05, "loss": 0.512, "step": 408 }, { "epoch": 1.6582278481012658, "grad_norm": 0.42756022661430826, "learning_rate": 3.376606219702454e-05, "loss": 0.5126, "step": 409 }, { "epoch": 1.6622784810126583, "grad_norm": 0.5478783272009239, "learning_rate": 3.372483275737468e-05, "loss": 0.492, "step": 410 }, { "epoch": 1.6663291139240506, "grad_norm": 0.47481567370484695, "learning_rate": 3.368349277980861e-05, "loss": 0.5119, "step": 411 }, { "epoch": 1.6703797468354429, "grad_norm": 0.5210510339966057, "learning_rate": 3.3642042597272844e-05, "loss": 0.5326, "step": 412 }, { "epoch": 1.6744303797468354, "grad_norm": 0.49644779065224387, "learning_rate": 3.360048254360144e-05, "loss": 0.5356, "step": 413 }, { "epoch": 1.678481012658228, "grad_norm": 0.537834383789003, "learning_rate": 3.355881295351336e-05, "loss": 0.4874, "step": 414 }, { "epoch": 1.6825316455696202, "grad_norm": 0.4930641952795078, "learning_rate": 3.351703416260975e-05, "loss": 0.5128, "step": 415 }, { "epoch": 1.6865822784810125, "grad_norm": 0.4850448231284859, "learning_rate": 3.347514650737126e-05, "loss": 0.5023, "step": 416 }, { "epoch": 1.690632911392405, "grad_norm": 0.520277833103286, "learning_rate": 3.3433150325155295e-05, "loss": 0.5265, "step": 417 }, { "epoch": 1.6946835443037975, "grad_norm": 0.4438815842749711, "learning_rate": 3.339104595419334e-05, "loss": 0.4945, "step": 418 }, { "epoch": 1.6987341772151898, "grad_norm": 0.5081972596578884, "learning_rate": 3.3348833733588204e-05, "loss": 0.5103, "step": 419 }, { "epoch": 1.7027848101265821, "grad_norm": 0.4562900066182483, "learning_rate": 3.3306514003311305e-05, "loss": 0.4988, "step": 420 }, { "epoch": 1.7068354430379746, "grad_norm": 0.5762098368668033, "learning_rate": 3.326408710419996e-05, "loss": 0.5202, "step": 421 }, { "epoch": 1.7108860759493671, "grad_norm": 0.5793278740935136, "learning_rate": 3.322155337795454e-05, "loss": 0.5274, "step": 422 }, { "epoch": 1.7149367088607594, "grad_norm": 0.5269733157455307, "learning_rate": 3.317891316713587e-05, "loss": 0.5119, "step": 423 }, { "epoch": 1.7189873417721517, "grad_norm": 0.6287331891358214, "learning_rate": 3.313616681516231e-05, "loss": 0.5132, "step": 424 }, { "epoch": 1.7230379746835442, "grad_norm": 0.5319692787269498, "learning_rate": 3.309331466630713e-05, "loss": 0.4922, "step": 425 }, { "epoch": 1.7270886075949368, "grad_norm": 0.664115639761484, "learning_rate": 3.305035706569563e-05, "loss": 0.4934, "step": 426 }, { "epoch": 1.7311392405063293, "grad_norm": 0.5829293476073981, "learning_rate": 3.3007294359302433e-05, "loss": 0.5026, "step": 427 }, { "epoch": 1.7351898734177216, "grad_norm": 0.6921154334664464, "learning_rate": 3.296412689394864e-05, "loss": 0.5037, "step": 428 }, { "epoch": 1.7392405063291139, "grad_norm": 0.5758059606683713, "learning_rate": 3.292085501729909e-05, "loss": 0.504, "step": 429 }, { "epoch": 1.7432911392405064, "grad_norm": 0.5967023040406372, "learning_rate": 3.2877479077859534e-05, "loss": 0.4812, "step": 430 }, { "epoch": 1.747341772151899, "grad_norm": 0.5156442134534577, "learning_rate": 3.283399942497381e-05, "loss": 0.459, "step": 431 }, { "epoch": 1.7513924050632912, "grad_norm": 0.47497984824648476, "learning_rate": 3.279041640882108e-05, "loss": 0.4935, "step": 432 }, { "epoch": 1.7554430379746835, "grad_norm": 0.5877460686201668, "learning_rate": 3.2746730380412964e-05, "loss": 0.5172, "step": 433 }, { "epoch": 1.759493670886076, "grad_norm": 0.4843244394573877, "learning_rate": 3.2702941691590726e-05, "loss": 0.5061, "step": 434 }, { "epoch": 1.7635443037974685, "grad_norm": 0.5297139864613143, "learning_rate": 3.265905069502244e-05, "loss": 0.5009, "step": 435 }, { "epoch": 1.7675949367088608, "grad_norm": 0.5672034878755462, "learning_rate": 3.261505774420016e-05, "loss": 0.5153, "step": 436 }, { "epoch": 1.771645569620253, "grad_norm": 0.503272714785477, "learning_rate": 3.257096319343707e-05, "loss": 0.5208, "step": 437 }, { "epoch": 1.7756962025316456, "grad_norm": 0.4855205969346905, "learning_rate": 3.2526767397864614e-05, "loss": 0.5098, "step": 438 }, { "epoch": 1.7797468354430381, "grad_norm": 0.49537140935644314, "learning_rate": 3.248247071342966e-05, "loss": 0.5048, "step": 439 }, { "epoch": 1.7837974683544304, "grad_norm": 0.437320740773694, "learning_rate": 3.243807349689161e-05, "loss": 0.5063, "step": 440 }, { "epoch": 1.7878481012658227, "grad_norm": 0.5044126743502103, "learning_rate": 3.2393576105819544e-05, "loss": 0.512, "step": 441 }, { "epoch": 1.7918987341772152, "grad_norm": 0.4356159539658758, "learning_rate": 3.2348978898589333e-05, "loss": 0.4853, "step": 442 }, { "epoch": 1.7959493670886078, "grad_norm": 0.4882391896886391, "learning_rate": 3.230428223438075e-05, "loss": 0.5051, "step": 443 }, { "epoch": 1.8, "grad_norm": 0.4257756062380817, "learning_rate": 3.225948647317459e-05, "loss": 0.5049, "step": 444 }, { "epoch": 1.8040506329113923, "grad_norm": 0.46440449598050515, "learning_rate": 3.2214591975749745e-05, "loss": 0.5204, "step": 445 }, { "epoch": 1.8081012658227849, "grad_norm": 0.5368921229622033, "learning_rate": 3.216959910368034e-05, "loss": 0.5303, "step": 446 }, { "epoch": 1.8121518987341774, "grad_norm": 0.4549379457703107, "learning_rate": 3.212450821933277e-05, "loss": 0.4949, "step": 447 }, { "epoch": 1.8162025316455697, "grad_norm": 0.5440826581828124, "learning_rate": 3.207931968586281e-05, "loss": 0.4867, "step": 448 }, { "epoch": 1.820253164556962, "grad_norm": 0.45185069744700584, "learning_rate": 3.203403386721272e-05, "loss": 0.5195, "step": 449 }, { "epoch": 1.8243037974683545, "grad_norm": 0.47001851203384326, "learning_rate": 3.1988651128108245e-05, "loss": 0.498, "step": 450 }, { "epoch": 1.828354430379747, "grad_norm": 0.5381535708290869, "learning_rate": 3.194317183405573e-05, "loss": 0.5401, "step": 451 }, { "epoch": 1.8324050632911393, "grad_norm": 0.4316675227977884, "learning_rate": 3.189759635133914e-05, "loss": 0.4975, "step": 452 }, { "epoch": 1.8364556962025316, "grad_norm": 0.46195631594255937, "learning_rate": 3.185192504701718e-05, "loss": 0.4902, "step": 453 }, { "epoch": 1.840506329113924, "grad_norm": 0.43964299707607485, "learning_rate": 3.1806158288920234e-05, "loss": 0.5018, "step": 454 }, { "epoch": 1.8445569620253166, "grad_norm": 0.5049236741584867, "learning_rate": 3.1760296445647477e-05, "loss": 0.5093, "step": 455 }, { "epoch": 1.848607594936709, "grad_norm": 0.456580366089132, "learning_rate": 3.1714339886563896e-05, "loss": 0.531, "step": 456 }, { "epoch": 1.8526582278481012, "grad_norm": 0.49213579187956374, "learning_rate": 3.166828898179731e-05, "loss": 0.4925, "step": 457 }, { "epoch": 1.8567088607594937, "grad_norm": 0.4897487308160895, "learning_rate": 3.162214410223536e-05, "loss": 0.5148, "step": 458 }, { "epoch": 1.8607594936708862, "grad_norm": 0.45111142496479, "learning_rate": 3.157590561952257e-05, "loss": 0.4949, "step": 459 }, { "epoch": 1.8648101265822785, "grad_norm": 0.48890167591197536, "learning_rate": 3.152957390605732e-05, "loss": 0.5003, "step": 460 }, { "epoch": 1.8688607594936708, "grad_norm": 0.45624401286421024, "learning_rate": 3.148314933498886e-05, "loss": 0.5153, "step": 461 }, { "epoch": 1.8729113924050633, "grad_norm": 0.4598358624683551, "learning_rate": 3.143663228021431e-05, "loss": 0.489, "step": 462 }, { "epoch": 1.8769620253164558, "grad_norm": 0.5160017336480487, "learning_rate": 3.1390023116375624e-05, "loss": 0.486, "step": 463 }, { "epoch": 1.8810126582278481, "grad_norm": 0.45877740686791657, "learning_rate": 3.134332221885661e-05, "loss": 0.5186, "step": 464 }, { "epoch": 1.8850632911392404, "grad_norm": 0.48672113490164676, "learning_rate": 3.129652996377987e-05, "loss": 0.522, "step": 465 }, { "epoch": 1.889113924050633, "grad_norm": 0.5204734085923506, "learning_rate": 3.12496467280038e-05, "loss": 0.4862, "step": 466 }, { "epoch": 1.8931645569620255, "grad_norm": 0.48912267975913015, "learning_rate": 3.120267288911952e-05, "loss": 0.4993, "step": 467 }, { "epoch": 1.8972151898734178, "grad_norm": 0.4653067923078138, "learning_rate": 3.11556088254479e-05, "loss": 0.5177, "step": 468 }, { "epoch": 1.90126582278481, "grad_norm": 0.5099165571022584, "learning_rate": 3.11084549160364e-05, "loss": 0.4855, "step": 469 }, { "epoch": 1.9053164556962026, "grad_norm": 0.4700437220884076, "learning_rate": 3.106121154065615e-05, "loss": 0.5012, "step": 470 }, { "epoch": 1.909367088607595, "grad_norm": 0.5512195550989787, "learning_rate": 3.1013879079798805e-05, "loss": 0.5344, "step": 471 }, { "epoch": 1.9134177215189874, "grad_norm": 0.4335541518290855, "learning_rate": 3.096645791467348e-05, "loss": 0.4859, "step": 472 }, { "epoch": 1.9174683544303797, "grad_norm": 0.4489389319318141, "learning_rate": 3.091894842720373e-05, "loss": 0.5175, "step": 473 }, { "epoch": 1.9215189873417722, "grad_norm": 0.4456810770229312, "learning_rate": 3.0871351000024425e-05, "loss": 0.5172, "step": 474 }, { "epoch": 1.9255696202531647, "grad_norm": 0.44705049101110267, "learning_rate": 3.0823666016478716e-05, "loss": 0.494, "step": 475 }, { "epoch": 1.929620253164557, "grad_norm": 0.43788436295512706, "learning_rate": 3.0775893860614896e-05, "loss": 0.5027, "step": 476 }, { "epoch": 1.9336708860759493, "grad_norm": 0.4405029333846628, "learning_rate": 3.0728034917183336e-05, "loss": 0.4896, "step": 477 }, { "epoch": 1.9377215189873418, "grad_norm": 0.4336173053426806, "learning_rate": 3.06800895716334e-05, "loss": 0.5028, "step": 478 }, { "epoch": 1.9417721518987343, "grad_norm": 0.49762028896225113, "learning_rate": 3.063205821011029e-05, "loss": 0.5123, "step": 479 }, { "epoch": 1.9458227848101266, "grad_norm": 0.43884295123242145, "learning_rate": 3.0583941219452016e-05, "loss": 0.5174, "step": 480 }, { "epoch": 1.949873417721519, "grad_norm": 0.4597913376132753, "learning_rate": 3.053573898718618e-05, "loss": 0.487, "step": 481 }, { "epoch": 1.9539240506329114, "grad_norm": 0.47636949725959704, "learning_rate": 3.0487451901526956e-05, "loss": 0.5134, "step": 482 }, { "epoch": 1.957974683544304, "grad_norm": 0.5096765767822631, "learning_rate": 3.0439080351371875e-05, "loss": 0.5034, "step": 483 }, { "epoch": 1.9620253164556962, "grad_norm": 0.5816010799274285, "learning_rate": 3.0390624726298764e-05, "loss": 0.542, "step": 484 }, { "epoch": 1.9660759493670885, "grad_norm": 0.5381631334715389, "learning_rate": 3.034208541656255e-05, "loss": 0.5125, "step": 485 }, { "epoch": 1.970126582278481, "grad_norm": 0.41782865969307775, "learning_rate": 3.029346281309218e-05, "loss": 0.4681, "step": 486 }, { "epoch": 1.9741772151898735, "grad_norm": 0.4955083254577125, "learning_rate": 3.0244757307487415e-05, "loss": 0.4997, "step": 487 }, { "epoch": 1.9782278481012658, "grad_norm": 0.4247969519826701, "learning_rate": 3.019596929201569e-05, "loss": 0.4806, "step": 488 }, { "epoch": 1.9822784810126581, "grad_norm": 0.4761478227828633, "learning_rate": 3.0147099159608985e-05, "loss": 0.5058, "step": 489 }, { "epoch": 1.9863291139240506, "grad_norm": 0.39787635879065203, "learning_rate": 3.0098147303860616e-05, "loss": 0.4839, "step": 490 }, { "epoch": 1.9903797468354432, "grad_norm": 0.480539642212192, "learning_rate": 3.0049114119022117e-05, "loss": 0.5282, "step": 491 }, { "epoch": 1.9944303797468355, "grad_norm": 0.42426493380009034, "learning_rate": 3.0000000000000004e-05, "loss": 0.5066, "step": 492 }, { "epoch": 1.9984810126582278, "grad_norm": 0.5068873600816867, "learning_rate": 2.995080534235264e-05, "loss": 0.5, "step": 493 }, { "epoch": 2.0040506329113925, "grad_norm": 0.7765670556927495, "learning_rate": 2.9901530542287044e-05, "loss": 0.3157, "step": 494 }, { "epoch": 2.008101265822785, "grad_norm": 0.5985690978241689, "learning_rate": 2.9852175996655676e-05, "loss": 0.3406, "step": 495 }, { "epoch": 2.012151898734177, "grad_norm": 1.00210289659429, "learning_rate": 2.980274210295326e-05, "loss": 0.3425, "step": 496 }, { "epoch": 2.0162025316455696, "grad_norm": 0.6273229236570318, "learning_rate": 2.9753229259313578e-05, "loss": 0.3236, "step": 497 }, { "epoch": 2.020253164556962, "grad_norm": 0.5758831013451515, "learning_rate": 2.9703637864506274e-05, "loss": 0.3513, "step": 498 }, { "epoch": 2.0243037974683546, "grad_norm": 0.5488676854140356, "learning_rate": 2.965396831793362e-05, "loss": 0.3108, "step": 499 }, { "epoch": 2.0283544303797467, "grad_norm": 0.5779842295157481, "learning_rate": 2.9604221019627316e-05, "loss": 0.3312, "step": 500 }, { "epoch": 2.0324050632911392, "grad_norm": 0.5808144458136909, "learning_rate": 2.955439637024526e-05, "loss": 0.3358, "step": 501 }, { "epoch": 2.0364556962025318, "grad_norm": 0.5896373767612464, "learning_rate": 2.9504494771068334e-05, "loss": 0.3375, "step": 502 }, { "epoch": 2.0405063291139243, "grad_norm": 0.6353222409783966, "learning_rate": 2.9454516623997156e-05, "loss": 0.3528, "step": 503 }, { "epoch": 2.0445569620253163, "grad_norm": 0.4767078006948149, "learning_rate": 2.9404462331548847e-05, "loss": 0.3171, "step": 504 }, { "epoch": 2.048607594936709, "grad_norm": 0.6852234167253837, "learning_rate": 2.93543322968538e-05, "loss": 0.3306, "step": 505 }, { "epoch": 2.0526582278481014, "grad_norm": 0.5387506006318528, "learning_rate": 2.9304126923652428e-05, "loss": 0.3391, "step": 506 }, { "epoch": 2.056708860759494, "grad_norm": 0.5060436033864198, "learning_rate": 2.9253846616291896e-05, "loss": 0.3354, "step": 507 }, { "epoch": 2.060759493670886, "grad_norm": 0.5672837568118445, "learning_rate": 2.9203491779722896e-05, "loss": 0.3246, "step": 508 }, { "epoch": 2.0648101265822785, "grad_norm": 0.5022336908878812, "learning_rate": 2.9153062819496357e-05, "loss": 0.3155, "step": 509 }, { "epoch": 2.068860759493671, "grad_norm": 0.5543143586811958, "learning_rate": 2.9102560141760178e-05, "loss": 0.3412, "step": 510 }, { "epoch": 2.0729113924050635, "grad_norm": 0.4318928189570988, "learning_rate": 2.9051984153256004e-05, "loss": 0.3214, "step": 511 }, { "epoch": 2.0769620253164556, "grad_norm": 0.5356672135700727, "learning_rate": 2.900133526131588e-05, "loss": 0.3347, "step": 512 }, { "epoch": 2.081012658227848, "grad_norm": 0.45600339669495227, "learning_rate": 2.8950613873859025e-05, "loss": 0.3354, "step": 513 }, { "epoch": 2.0850632911392406, "grad_norm": 0.4285917352307144, "learning_rate": 2.8899820399388515e-05, "loss": 0.3267, "step": 514 }, { "epoch": 2.089113924050633, "grad_norm": 0.4916591119518606, "learning_rate": 2.8848955246988012e-05, "loss": 0.319, "step": 515 }, { "epoch": 2.093164556962025, "grad_norm": 0.48695419983864796, "learning_rate": 2.879801882631847e-05, "loss": 0.3353, "step": 516 }, { "epoch": 2.0972151898734177, "grad_norm": 0.45263575043066145, "learning_rate": 2.8747011547614808e-05, "loss": 0.3256, "step": 517 }, { "epoch": 2.1012658227848102, "grad_norm": 0.44871544353350284, "learning_rate": 2.8695933821682635e-05, "loss": 0.3454, "step": 518 }, { "epoch": 2.1053164556962027, "grad_norm": 0.41656553478823216, "learning_rate": 2.864478605989494e-05, "loss": 0.3093, "step": 519 }, { "epoch": 2.109367088607595, "grad_norm": 0.4413848745046321, "learning_rate": 2.8593568674188765e-05, "loss": 0.333, "step": 520 }, { "epoch": 2.1134177215189873, "grad_norm": 0.4475285511992101, "learning_rate": 2.8542282077061892e-05, "loss": 0.3227, "step": 521 }, { "epoch": 2.11746835443038, "grad_norm": 0.43900673975185167, "learning_rate": 2.8490926681569523e-05, "loss": 0.3406, "step": 522 }, { "epoch": 2.1215189873417724, "grad_norm": 0.46134864007485793, "learning_rate": 2.8439502901320956e-05, "loss": 0.3229, "step": 523 }, { "epoch": 2.1255696202531644, "grad_norm": 0.4629594820810415, "learning_rate": 2.8388011150476237e-05, "loss": 0.3129, "step": 524 }, { "epoch": 2.129620253164557, "grad_norm": 0.42097566710295714, "learning_rate": 2.8336451843742866e-05, "loss": 0.3095, "step": 525 }, { "epoch": 2.1336708860759495, "grad_norm": 0.4873776351713206, "learning_rate": 2.8284825396372387e-05, "loss": 0.3373, "step": 526 }, { "epoch": 2.137721518987342, "grad_norm": 0.42173940851060704, "learning_rate": 2.8233132224157132e-05, "loss": 0.3267, "step": 527 }, { "epoch": 2.141772151898734, "grad_norm": 0.47435124711130283, "learning_rate": 2.8181372743426805e-05, "loss": 0.3314, "step": 528 }, { "epoch": 2.1458227848101266, "grad_norm": 0.4502566744390225, "learning_rate": 2.8129547371045128e-05, "loss": 0.3325, "step": 529 }, { "epoch": 2.149873417721519, "grad_norm": 0.4263935452384684, "learning_rate": 2.8077656524406534e-05, "loss": 0.3318, "step": 530 }, { "epoch": 2.1539240506329116, "grad_norm": 0.4897882251144961, "learning_rate": 2.802570062143278e-05, "loss": 0.3541, "step": 531 }, { "epoch": 2.1579746835443037, "grad_norm": 0.4503789007438496, "learning_rate": 2.7973680080569555e-05, "loss": 0.3466, "step": 532 }, { "epoch": 2.162025316455696, "grad_norm": 0.4564059814273227, "learning_rate": 2.792159532078314e-05, "loss": 0.3038, "step": 533 }, { "epoch": 2.1660759493670887, "grad_norm": 0.5149822185653082, "learning_rate": 2.7869446761557033e-05, "loss": 0.3605, "step": 534 }, { "epoch": 2.170126582278481, "grad_norm": 0.4418184036943725, "learning_rate": 2.781723482288857e-05, "loss": 0.3144, "step": 535 }, { "epoch": 2.1741772151898733, "grad_norm": 0.440519765561029, "learning_rate": 2.7764959925285517e-05, "loss": 0.3389, "step": 536 }, { "epoch": 2.178227848101266, "grad_norm": 0.4664822706313033, "learning_rate": 2.771262248976272e-05, "loss": 0.3293, "step": 537 }, { "epoch": 2.1822784810126583, "grad_norm": 0.4525285480163086, "learning_rate": 2.7660222937838677e-05, "loss": 0.3304, "step": 538 }, { "epoch": 2.186329113924051, "grad_norm": 0.4826406027575446, "learning_rate": 2.7607761691532186e-05, "loss": 0.3298, "step": 539 }, { "epoch": 2.190379746835443, "grad_norm": 0.44647842795808546, "learning_rate": 2.7555239173358916e-05, "loss": 0.3342, "step": 540 }, { "epoch": 2.1944303797468354, "grad_norm": 0.47830094594793654, "learning_rate": 2.7502655806328e-05, "loss": 0.3302, "step": 541 }, { "epoch": 2.198481012658228, "grad_norm": 0.4489002170970145, "learning_rate": 2.7450012013938648e-05, "loss": 0.3016, "step": 542 }, { "epoch": 2.2025316455696204, "grad_norm": 0.40019045224903943, "learning_rate": 2.739730822017673e-05, "loss": 0.3342, "step": 543 }, { "epoch": 2.2065822784810125, "grad_norm": 0.4398851443466071, "learning_rate": 2.7344544849511355e-05, "loss": 0.327, "step": 544 }, { "epoch": 2.210632911392405, "grad_norm": 0.421323626654178, "learning_rate": 2.7291722326891456e-05, "loss": 0.3431, "step": 545 }, { "epoch": 2.2146835443037975, "grad_norm": 0.4086125816925401, "learning_rate": 2.723884107774236e-05, "loss": 0.3178, "step": 546 }, { "epoch": 2.21873417721519, "grad_norm": 0.4294792089359497, "learning_rate": 2.718590152796239e-05, "loss": 0.3324, "step": 547 }, { "epoch": 2.222784810126582, "grad_norm": 0.4306426600480398, "learning_rate": 2.71329041039194e-05, "loss": 0.3272, "step": 548 }, { "epoch": 2.2268354430379746, "grad_norm": 0.39189555890503647, "learning_rate": 2.7079849232447357e-05, "loss": 0.3189, "step": 549 }, { "epoch": 2.230886075949367, "grad_norm": 0.39857324985553116, "learning_rate": 2.7026737340842895e-05, "loss": 0.3352, "step": 550 }, { "epoch": 2.2349367088607597, "grad_norm": 0.4160301197934556, "learning_rate": 2.697356885686189e-05, "loss": 0.3591, "step": 551 }, { "epoch": 2.2389873417721518, "grad_norm": 0.42053747728162827, "learning_rate": 2.6920344208716014e-05, "loss": 0.3197, "step": 552 }, { "epoch": 2.2430379746835443, "grad_norm": 0.4095291034238958, "learning_rate": 2.6867063825069252e-05, "loss": 0.3374, "step": 553 }, { "epoch": 2.247088607594937, "grad_norm": 0.40842530039092917, "learning_rate": 2.6813728135034494e-05, "loss": 0.3382, "step": 554 }, { "epoch": 2.2511392405063293, "grad_norm": 0.39823995611327556, "learning_rate": 2.6760337568170056e-05, "loss": 0.3476, "step": 555 }, { "epoch": 2.2551898734177214, "grad_norm": 0.4025789478190868, "learning_rate": 2.6706892554476226e-05, "loss": 0.3192, "step": 556 }, { "epoch": 2.259240506329114, "grad_norm": 0.3950904639432971, "learning_rate": 2.6653393524391795e-05, "loss": 0.3205, "step": 557 }, { "epoch": 2.2632911392405064, "grad_norm": 0.4307249476255024, "learning_rate": 2.6599840908790592e-05, "loss": 0.3492, "step": 558 }, { "epoch": 2.267341772151899, "grad_norm": 0.4103453110032612, "learning_rate": 2.6546235138978028e-05, "loss": 0.3235, "step": 559 }, { "epoch": 2.271392405063291, "grad_norm": 0.4203710912471226, "learning_rate": 2.6492576646687597e-05, "loss": 0.3053, "step": 560 }, { "epoch": 2.2754430379746835, "grad_norm": 0.42550628560981074, "learning_rate": 2.6438865864077425e-05, "loss": 0.3415, "step": 561 }, { "epoch": 2.279493670886076, "grad_norm": 0.4084896044080585, "learning_rate": 2.6385103223726766e-05, "loss": 0.3308, "step": 562 }, { "epoch": 2.2835443037974685, "grad_norm": 0.41165117525908845, "learning_rate": 2.6331289158632537e-05, "loss": 0.3126, "step": 563 }, { "epoch": 2.2875949367088606, "grad_norm": 0.40194084120895357, "learning_rate": 2.6277424102205817e-05, "loss": 0.3402, "step": 564 }, { "epoch": 2.291645569620253, "grad_norm": 0.44789306737888585, "learning_rate": 2.6223508488268374e-05, "loss": 0.3181, "step": 565 }, { "epoch": 2.2956962025316456, "grad_norm": 0.41359152271889155, "learning_rate": 2.6169542751049148e-05, "loss": 0.3228, "step": 566 }, { "epoch": 2.299746835443038, "grad_norm": 0.45713552184532263, "learning_rate": 2.6115527325180754e-05, "loss": 0.3219, "step": 567 }, { "epoch": 2.3037974683544302, "grad_norm": 0.3964078048592353, "learning_rate": 2.606146264569603e-05, "loss": 0.3307, "step": 568 }, { "epoch": 2.3078481012658227, "grad_norm": 0.3998199146324187, "learning_rate": 2.6007349148024447e-05, "loss": 0.3211, "step": 569 }, { "epoch": 2.3118987341772153, "grad_norm": 0.4000769300891566, "learning_rate": 2.5953187267988694e-05, "loss": 0.3287, "step": 570 }, { "epoch": 2.3159493670886078, "grad_norm": 0.4105005552832255, "learning_rate": 2.5898977441801097e-05, "loss": 0.3513, "step": 571 }, { "epoch": 2.32, "grad_norm": 0.4121221230439003, "learning_rate": 2.584472010606015e-05, "loss": 0.3199, "step": 572 }, { "epoch": 2.3240506329113924, "grad_norm": 0.4511483968252781, "learning_rate": 2.5790415697746976e-05, "loss": 0.3038, "step": 573 }, { "epoch": 2.328101265822785, "grad_norm": 0.4054418024038849, "learning_rate": 2.5736064654221808e-05, "loss": 0.3077, "step": 574 }, { "epoch": 2.3321518987341774, "grad_norm": 0.4572973934621174, "learning_rate": 2.568166741322048e-05, "loss": 0.3326, "step": 575 }, { "epoch": 2.3362025316455695, "grad_norm": 0.40296449738403217, "learning_rate": 2.56272244128509e-05, "loss": 0.3204, "step": 576 }, { "epoch": 2.340253164556962, "grad_norm": 0.4526291528756784, "learning_rate": 2.55727360915895e-05, "loss": 0.3172, "step": 577 }, { "epoch": 2.3443037974683545, "grad_norm": 0.41046763550264526, "learning_rate": 2.5518202888277734e-05, "loss": 0.3324, "step": 578 }, { "epoch": 2.348354430379747, "grad_norm": 0.44865581099303975, "learning_rate": 2.5463625242118523e-05, "loss": 0.3489, "step": 579 }, { "epoch": 2.352405063291139, "grad_norm": 0.41759992810009583, "learning_rate": 2.5409003592672723e-05, "loss": 0.331, "step": 580 }, { "epoch": 2.3564556962025316, "grad_norm": 0.42115096400699814, "learning_rate": 2.535433837985559e-05, "loss": 0.3193, "step": 581 }, { "epoch": 2.360506329113924, "grad_norm": 0.40712873849443176, "learning_rate": 2.529963004393324e-05, "loss": 0.3341, "step": 582 }, { "epoch": 2.3645569620253166, "grad_norm": 0.44736272985075176, "learning_rate": 2.524487902551908e-05, "loss": 0.35, "step": 583 }, { "epoch": 2.3686075949367087, "grad_norm": 0.4282793095405336, "learning_rate": 2.519008576557029e-05, "loss": 0.3425, "step": 584 }, { "epoch": 2.372658227848101, "grad_norm": 0.4251122770987717, "learning_rate": 2.5135250705384254e-05, "loss": 0.3361, "step": 585 }, { "epoch": 2.3767088607594937, "grad_norm": 0.47880580979767734, "learning_rate": 2.5080374286595007e-05, "loss": 0.3416, "step": 586 }, { "epoch": 2.3807594936708862, "grad_norm": 0.4624273572281527, "learning_rate": 2.5025456951169677e-05, "loss": 0.3189, "step": 587 }, { "epoch": 2.3848101265822783, "grad_norm": 0.45360229813074393, "learning_rate": 2.4970499141404942e-05, "loss": 0.3501, "step": 588 }, { "epoch": 2.388860759493671, "grad_norm": 0.4394455173164524, "learning_rate": 2.491550129992345e-05, "loss": 0.3234, "step": 589 }, { "epoch": 2.3929113924050633, "grad_norm": 0.43249763534311975, "learning_rate": 2.486046386967024e-05, "loss": 0.3474, "step": 590 }, { "epoch": 2.396962025316456, "grad_norm": 0.4290576516912069, "learning_rate": 2.4805387293909214e-05, "loss": 0.3318, "step": 591 }, { "epoch": 2.401012658227848, "grad_norm": 0.4788918279511497, "learning_rate": 2.4750272016219552e-05, "loss": 0.3188, "step": 592 }, { "epoch": 2.4050632911392404, "grad_norm": 0.4101174330902734, "learning_rate": 2.4695118480492114e-05, "loss": 0.3299, "step": 593 }, { "epoch": 2.409113924050633, "grad_norm": 0.48864553734030136, "learning_rate": 2.4639927130925898e-05, "loss": 0.32, "step": 594 }, { "epoch": 2.4131645569620255, "grad_norm": 0.45513450490907237, "learning_rate": 2.458469841202444e-05, "loss": 0.3543, "step": 595 }, { "epoch": 2.4172151898734175, "grad_norm": 0.42965654838602263, "learning_rate": 2.452943276859226e-05, "loss": 0.3238, "step": 596 }, { "epoch": 2.42126582278481, "grad_norm": 0.501531958152436, "learning_rate": 2.447413064573125e-05, "loss": 0.3285, "step": 597 }, { "epoch": 2.4253164556962026, "grad_norm": 0.4061499689720444, "learning_rate": 2.4418792488837095e-05, "loss": 0.3258, "step": 598 }, { "epoch": 2.429367088607595, "grad_norm": 0.4409254200210434, "learning_rate": 2.4363418743595713e-05, "loss": 0.3326, "step": 599 }, { "epoch": 2.433417721518987, "grad_norm": 0.4174575691134592, "learning_rate": 2.430800985597963e-05, "loss": 0.2969, "step": 600 }, { "epoch": 2.4374683544303797, "grad_norm": 0.44498435418827814, "learning_rate": 2.4252566272244415e-05, "loss": 0.331, "step": 601 }, { "epoch": 2.441518987341772, "grad_norm": 0.402384818446818, "learning_rate": 2.4197088438925063e-05, "loss": 0.323, "step": 602 }, { "epoch": 2.4455696202531647, "grad_norm": 0.42995835374882135, "learning_rate": 2.4141576802832417e-05, "loss": 0.3154, "step": 603 }, { "epoch": 2.449620253164557, "grad_norm": 0.411804201583391, "learning_rate": 2.408603181104957e-05, "loss": 0.3543, "step": 604 }, { "epoch": 2.4536708860759493, "grad_norm": 0.43303943228475755, "learning_rate": 2.4030453910928245e-05, "loss": 0.3226, "step": 605 }, { "epoch": 2.457721518987342, "grad_norm": 0.4189570905959132, "learning_rate": 2.397484355008521e-05, "loss": 0.328, "step": 606 }, { "epoch": 2.4617721518987343, "grad_norm": 0.4305577899740304, "learning_rate": 2.3919201176398662e-05, "loss": 0.3289, "step": 607 }, { "epoch": 2.4658227848101264, "grad_norm": 0.44186220670713666, "learning_rate": 2.3863527238004633e-05, "loss": 0.325, "step": 608 }, { "epoch": 2.469873417721519, "grad_norm": 0.3988180936098625, "learning_rate": 2.380782218329337e-05, "loss": 0.3261, "step": 609 }, { "epoch": 2.4739240506329114, "grad_norm": 0.4219974275514998, "learning_rate": 2.3752086460905725e-05, "loss": 0.3165, "step": 610 }, { "epoch": 2.477974683544304, "grad_norm": 0.4006658333316978, "learning_rate": 2.3696320519729544e-05, "loss": 0.3415, "step": 611 }, { "epoch": 2.482025316455696, "grad_norm": 0.39469510123427526, "learning_rate": 2.3640524808896045e-05, "loss": 0.3251, "step": 612 }, { "epoch": 2.4860759493670885, "grad_norm": 0.3908486991439945, "learning_rate": 2.3584699777776222e-05, "loss": 0.3146, "step": 613 }, { "epoch": 2.490126582278481, "grad_norm": 0.4132403286532323, "learning_rate": 2.3528845875977195e-05, "loss": 0.3304, "step": 614 }, { "epoch": 2.4941772151898736, "grad_norm": 0.4023271942638728, "learning_rate": 2.3472963553338614e-05, "loss": 0.3462, "step": 615 }, { "epoch": 2.4982278481012656, "grad_norm": 0.3848662703734672, "learning_rate": 2.341705325992901e-05, "loss": 0.3064, "step": 616 }, { "epoch": 2.502278481012658, "grad_norm": 0.4430996202160207, "learning_rate": 2.336111544604222e-05, "loss": 0.3316, "step": 617 }, { "epoch": 2.5063291139240507, "grad_norm": 0.45345021260241114, "learning_rate": 2.33051505621937e-05, "loss": 0.3358, "step": 618 }, { "epoch": 2.510379746835443, "grad_norm": 0.4140220526119758, "learning_rate": 2.324915905911693e-05, "loss": 0.3402, "step": 619 }, { "epoch": 2.5144303797468357, "grad_norm": 0.45410153196918207, "learning_rate": 2.319314138775977e-05, "loss": 0.3379, "step": 620 }, { "epoch": 2.5184810126582278, "grad_norm": 0.41261044783513484, "learning_rate": 2.3137097999280856e-05, "loss": 0.3294, "step": 621 }, { "epoch": 2.5225316455696203, "grad_norm": 0.3888896276695912, "learning_rate": 2.308102934504593e-05, "loss": 0.3178, "step": 622 }, { "epoch": 2.526582278481013, "grad_norm": 0.4605416339615832, "learning_rate": 2.3024935876624222e-05, "loss": 0.3346, "step": 623 }, { "epoch": 2.530632911392405, "grad_norm": 0.4231083060766833, "learning_rate": 2.2968818045784813e-05, "loss": 0.3249, "step": 624 }, { "epoch": 2.5346835443037974, "grad_norm": 0.39962889257868717, "learning_rate": 2.2912676304493006e-05, "loss": 0.3185, "step": 625 }, { "epoch": 2.53873417721519, "grad_norm": 0.4161227677467347, "learning_rate": 2.2856511104906668e-05, "loss": 0.3338, "step": 626 }, { "epoch": 2.5427848101265824, "grad_norm": 0.40854024487449775, "learning_rate": 2.2800322899372586e-05, "loss": 0.3225, "step": 627 }, { "epoch": 2.546835443037975, "grad_norm": 0.4152606607280664, "learning_rate": 2.2744112140422844e-05, "loss": 0.3233, "step": 628 }, { "epoch": 2.550886075949367, "grad_norm": 0.4384102494396027, "learning_rate": 2.2687879280771177e-05, "loss": 0.3101, "step": 629 }, { "epoch": 2.5549367088607595, "grad_norm": 0.39012864451557827, "learning_rate": 2.26316247733093e-05, "loss": 0.2981, "step": 630 }, { "epoch": 2.558987341772152, "grad_norm": 0.42388580931856384, "learning_rate": 2.257534907110328e-05, "loss": 0.3366, "step": 631 }, { "epoch": 2.563037974683544, "grad_norm": 0.4229985264340442, "learning_rate": 2.2519052627389882e-05, "loss": 0.31, "step": 632 }, { "epoch": 2.5670886075949366, "grad_norm": 0.4013604466181965, "learning_rate": 2.246273589557294e-05, "loss": 0.3287, "step": 633 }, { "epoch": 2.571139240506329, "grad_norm": 0.4323493816039653, "learning_rate": 2.240639932921966e-05, "loss": 0.3123, "step": 634 }, { "epoch": 2.5751898734177217, "grad_norm": 0.4089845158680504, "learning_rate": 2.2350043382056995e-05, "loss": 0.3197, "step": 635 }, { "epoch": 2.579240506329114, "grad_norm": 0.381989488619138, "learning_rate": 2.2293668507968015e-05, "loss": 0.3315, "step": 636 }, { "epoch": 2.5832911392405062, "grad_norm": 0.45503308601712045, "learning_rate": 2.2237275160988186e-05, "loss": 0.3409, "step": 637 }, { "epoch": 2.5873417721518988, "grad_norm": 0.4188743497724964, "learning_rate": 2.2180863795301787e-05, "loss": 0.329, "step": 638 }, { "epoch": 2.5913924050632913, "grad_norm": 0.40439099796339134, "learning_rate": 2.212443486523819e-05, "loss": 0.3048, "step": 639 }, { "epoch": 2.5954430379746833, "grad_norm": 0.4406387564900216, "learning_rate": 2.2067988825268243e-05, "loss": 0.3342, "step": 640 }, { "epoch": 2.599493670886076, "grad_norm": 0.4065921670728348, "learning_rate": 2.2011526130000596e-05, "loss": 0.3189, "step": 641 }, { "epoch": 2.6035443037974684, "grad_norm": 0.4297338974380593, "learning_rate": 2.1955047234178038e-05, "loss": 0.3222, "step": 642 }, { "epoch": 2.607594936708861, "grad_norm": 0.39140043291733767, "learning_rate": 2.1898552592673825e-05, "loss": 0.3188, "step": 643 }, { "epoch": 2.6116455696202534, "grad_norm": 0.411131984736716, "learning_rate": 2.184204266048803e-05, "loss": 0.3173, "step": 644 }, { "epoch": 2.6156962025316455, "grad_norm": 0.4090983649089622, "learning_rate": 2.1785517892743887e-05, "loss": 0.351, "step": 645 }, { "epoch": 2.619746835443038, "grad_norm": 0.41054278801701644, "learning_rate": 2.17289787446841e-05, "loss": 0.3454, "step": 646 }, { "epoch": 2.6237974683544305, "grad_norm": 0.41080728546275014, "learning_rate": 2.1672425671667198e-05, "loss": 0.3303, "step": 647 }, { "epoch": 2.6278481012658226, "grad_norm": 0.40526372403099625, "learning_rate": 2.161585912916385e-05, "loss": 0.3322, "step": 648 }, { "epoch": 2.631898734177215, "grad_norm": 0.3812988696044687, "learning_rate": 2.1559279572753214e-05, "loss": 0.3521, "step": 649 }, { "epoch": 2.6359493670886076, "grad_norm": 0.4081366815070622, "learning_rate": 2.1502687458119268e-05, "loss": 0.328, "step": 650 }, { "epoch": 2.64, "grad_norm": 0.38549938742459383, "learning_rate": 2.1446083241047116e-05, "loss": 0.3342, "step": 651 }, { "epoch": 2.6440506329113926, "grad_norm": 0.3818317145724041, "learning_rate": 2.1389467377419333e-05, "loss": 0.3434, "step": 652 }, { "epoch": 2.6481012658227847, "grad_norm": 0.38925143557397135, "learning_rate": 2.133284032321232e-05, "loss": 0.3277, "step": 653 }, { "epoch": 2.6521518987341772, "grad_norm": 0.40406272811888183, "learning_rate": 2.1276202534492566e-05, "loss": 0.3296, "step": 654 }, { "epoch": 2.6562025316455697, "grad_norm": 0.3686080067806467, "learning_rate": 2.121955446741306e-05, "loss": 0.3227, "step": 655 }, { "epoch": 2.660253164556962, "grad_norm": 0.40516101410758754, "learning_rate": 2.1162896578209517e-05, "loss": 0.3429, "step": 656 }, { "epoch": 2.6643037974683543, "grad_norm": 0.41264168770350906, "learning_rate": 2.1106229323196813e-05, "loss": 0.3091, "step": 657 }, { "epoch": 2.668354430379747, "grad_norm": 0.38647504697529883, "learning_rate": 2.1049553158765214e-05, "loss": 0.3374, "step": 658 }, { "epoch": 2.6724050632911394, "grad_norm": 0.39045444396855317, "learning_rate": 2.0992868541376764e-05, "loss": 0.3383, "step": 659 }, { "epoch": 2.676455696202532, "grad_norm": 0.40704449396468123, "learning_rate": 2.093617592756158e-05, "loss": 0.3211, "step": 660 }, { "epoch": 2.680506329113924, "grad_norm": 0.4115072280978434, "learning_rate": 2.0879475773914167e-05, "loss": 0.3232, "step": 661 }, { "epoch": 2.6845569620253165, "grad_norm": 0.3889440481605901, "learning_rate": 2.082276853708978e-05, "loss": 0.3344, "step": 662 }, { "epoch": 2.688607594936709, "grad_norm": 0.41282183070639455, "learning_rate": 2.076605467380071e-05, "loss": 0.3365, "step": 663 }, { "epoch": 2.692658227848101, "grad_norm": 0.4063288459355731, "learning_rate": 2.0709334640812613e-05, "loss": 0.3483, "step": 664 }, { "epoch": 2.6967088607594936, "grad_norm": 0.38408035940381197, "learning_rate": 2.0652608894940824e-05, "loss": 0.3098, "step": 665 }, { "epoch": 2.700759493670886, "grad_norm": 0.42201561478495125, "learning_rate": 2.0595877893046722e-05, "loss": 0.3465, "step": 666 }, { "epoch": 2.7048101265822786, "grad_norm": 0.3985140429596199, "learning_rate": 2.0539142092033985e-05, "loss": 0.3202, "step": 667 }, { "epoch": 2.708860759493671, "grad_norm": 0.3992186670808986, "learning_rate": 2.048240194884496e-05, "loss": 0.3239, "step": 668 }, { "epoch": 2.712911392405063, "grad_norm": 0.38964192612689574, "learning_rate": 2.042565792045695e-05, "loss": 0.3386, "step": 669 }, { "epoch": 2.7169620253164557, "grad_norm": 0.4108035774640765, "learning_rate": 2.036891046387857e-05, "loss": 0.3538, "step": 670 }, { "epoch": 2.721012658227848, "grad_norm": 0.3793020245842747, "learning_rate": 2.0312160036146036e-05, "loss": 0.321, "step": 671 }, { "epoch": 2.7250632911392403, "grad_norm": 0.39843923663880293, "learning_rate": 2.025540709431948e-05, "loss": 0.3132, "step": 672 }, { "epoch": 2.729113924050633, "grad_norm": 0.40241167556722984, "learning_rate": 2.0198652095479298e-05, "loss": 0.34, "step": 673 }, { "epoch": 2.7331645569620253, "grad_norm": 0.40910827038076575, "learning_rate": 2.014189549672245e-05, "loss": 0.3293, "step": 674 }, { "epoch": 2.737215189873418, "grad_norm": 0.4240521499469889, "learning_rate": 2.0085137755158776e-05, "loss": 0.3246, "step": 675 }, { "epoch": 2.7412658227848103, "grad_norm": 0.37775294720855035, "learning_rate": 2.0028379327907327e-05, "loss": 0.3418, "step": 676 }, { "epoch": 2.7453164556962024, "grad_norm": 0.4184299403168046, "learning_rate": 1.9971620672092676e-05, "loss": 0.3071, "step": 677 }, { "epoch": 2.749367088607595, "grad_norm": 0.3873688592341908, "learning_rate": 1.991486224484123e-05, "loss": 0.3286, "step": 678 }, { "epoch": 2.7534177215189874, "grad_norm": 0.41433107009329284, "learning_rate": 1.985810450327756e-05, "loss": 0.3201, "step": 679 }, { "epoch": 2.7574683544303795, "grad_norm": 0.3920915074089174, "learning_rate": 1.9801347904520706e-05, "loss": 0.3299, "step": 680 }, { "epoch": 2.761518987341772, "grad_norm": 0.3940207796037459, "learning_rate": 1.974459290568053e-05, "loss": 0.3283, "step": 681 }, { "epoch": 2.7655696202531646, "grad_norm": 0.38441082038845076, "learning_rate": 1.968783996385397e-05, "loss": 0.3028, "step": 682 }, { "epoch": 2.769620253164557, "grad_norm": 0.42979536191195916, "learning_rate": 1.963108953612143e-05, "loss": 0.3382, "step": 683 }, { "epoch": 2.7736708860759496, "grad_norm": 0.37620332977504456, "learning_rate": 1.9574342079543056e-05, "loss": 0.3214, "step": 684 }, { "epoch": 2.7777215189873417, "grad_norm": 0.4075846259124541, "learning_rate": 1.9517598051155046e-05, "loss": 0.34, "step": 685 }, { "epoch": 2.781772151898734, "grad_norm": 0.3804977107932351, "learning_rate": 1.9460857907966025e-05, "loss": 0.3264, "step": 686 }, { "epoch": 2.7858227848101267, "grad_norm": 0.41805171920405704, "learning_rate": 1.9404122106953285e-05, "loss": 0.3385, "step": 687 }, { "epoch": 2.7898734177215188, "grad_norm": 0.398340833688588, "learning_rate": 1.9347391105059176e-05, "loss": 0.3206, "step": 688 }, { "epoch": 2.7939240506329113, "grad_norm": 0.4086201529180501, "learning_rate": 1.92906653591874e-05, "loss": 0.3264, "step": 689 }, { "epoch": 2.797974683544304, "grad_norm": 0.38478064737154577, "learning_rate": 1.9233945326199295e-05, "loss": 0.3396, "step": 690 }, { "epoch": 2.8020253164556963, "grad_norm": 0.4094094922982664, "learning_rate": 1.917723146291022e-05, "loss": 0.3249, "step": 691 }, { "epoch": 2.806075949367089, "grad_norm": 0.3981090679021828, "learning_rate": 1.912052422608584e-05, "loss": 0.3007, "step": 692 }, { "epoch": 2.810126582278481, "grad_norm": 0.3854991736404417, "learning_rate": 1.9063824072438428e-05, "loss": 0.3325, "step": 693 }, { "epoch": 2.8141772151898734, "grad_norm": 0.3980232930574957, "learning_rate": 1.9007131458623246e-05, "loss": 0.3304, "step": 694 }, { "epoch": 2.818227848101266, "grad_norm": 0.40934677723934676, "learning_rate": 1.895044684123479e-05, "loss": 0.3101, "step": 695 }, { "epoch": 2.822278481012658, "grad_norm": 0.4594063496956142, "learning_rate": 1.8893770676803194e-05, "loss": 0.3617, "step": 696 }, { "epoch": 2.8263291139240505, "grad_norm": 0.38470049262398326, "learning_rate": 1.8837103421790486e-05, "loss": 0.3587, "step": 697 }, { "epoch": 2.830379746835443, "grad_norm": 0.3959675615739193, "learning_rate": 1.8780445532586952e-05, "loss": 0.3337, "step": 698 }, { "epoch": 2.8344303797468355, "grad_norm": 0.42961176656788047, "learning_rate": 1.872379746550743e-05, "loss": 0.3187, "step": 699 }, { "epoch": 2.838481012658228, "grad_norm": 0.4018827796828831, "learning_rate": 1.866715967678769e-05, "loss": 0.3212, "step": 700 }, { "epoch": 2.84253164556962, "grad_norm": 0.38759344313905486, "learning_rate": 1.861053262258067e-05, "loss": 0.3307, "step": 701 }, { "epoch": 2.8465822784810126, "grad_norm": 0.3915219836429391, "learning_rate": 1.8553916758952897e-05, "loss": 0.3329, "step": 702 }, { "epoch": 2.850632911392405, "grad_norm": 0.41628555126478517, "learning_rate": 1.8497312541880735e-05, "loss": 0.3408, "step": 703 }, { "epoch": 2.8546835443037972, "grad_norm": 0.3934759590425271, "learning_rate": 1.8440720427246786e-05, "loss": 0.3142, "step": 704 }, { "epoch": 2.8587341772151897, "grad_norm": 0.3803142041728906, "learning_rate": 1.8384140870836157e-05, "loss": 0.3108, "step": 705 }, { "epoch": 2.8627848101265823, "grad_norm": 0.3900119191468328, "learning_rate": 1.8327574328332806e-05, "loss": 0.3103, "step": 706 }, { "epoch": 2.8668354430379748, "grad_norm": 0.3906872339628664, "learning_rate": 1.8271021255315906e-05, "loss": 0.3049, "step": 707 }, { "epoch": 2.8708860759493673, "grad_norm": 0.4015670494083242, "learning_rate": 1.8214482107256117e-05, "loss": 0.3191, "step": 708 }, { "epoch": 2.8749367088607594, "grad_norm": 0.3898228209815284, "learning_rate": 1.8157957339511968e-05, "loss": 0.3374, "step": 709 }, { "epoch": 2.878987341772152, "grad_norm": 0.38186876304219763, "learning_rate": 1.8101447407326182e-05, "loss": 0.3208, "step": 710 }, { "epoch": 2.8830379746835444, "grad_norm": 0.3971598371185141, "learning_rate": 1.8044952765821966e-05, "loss": 0.3174, "step": 711 }, { "epoch": 2.8870886075949365, "grad_norm": 0.38644422028768805, "learning_rate": 1.7988473869999407e-05, "loss": 0.3397, "step": 712 }, { "epoch": 2.891139240506329, "grad_norm": 0.39447801441103897, "learning_rate": 1.7932011174731764e-05, "loss": 0.3362, "step": 713 }, { "epoch": 2.8951898734177215, "grad_norm": 0.3742388987908757, "learning_rate": 1.7875565134761817e-05, "loss": 0.3302, "step": 714 }, { "epoch": 2.899240506329114, "grad_norm": 0.37363249104734825, "learning_rate": 1.7819136204698226e-05, "loss": 0.3331, "step": 715 }, { "epoch": 2.9032911392405065, "grad_norm": 0.4246607689196345, "learning_rate": 1.776272483901182e-05, "loss": 0.3181, "step": 716 }, { "epoch": 2.9073417721518986, "grad_norm": 0.38963798014776146, "learning_rate": 1.7706331492031995e-05, "loss": 0.3054, "step": 717 }, { "epoch": 2.911392405063291, "grad_norm": 0.4145366406569367, "learning_rate": 1.764995661794301e-05, "loss": 0.3056, "step": 718 }, { "epoch": 2.9154430379746836, "grad_norm": 0.41772585623104896, "learning_rate": 1.759360067078035e-05, "loss": 0.3226, "step": 719 }, { "epoch": 2.9194936708860757, "grad_norm": 0.3612949821719407, "learning_rate": 1.7537264104427064e-05, "loss": 0.3314, "step": 720 }, { "epoch": 2.923544303797468, "grad_norm": 0.40385111119860995, "learning_rate": 1.748094737261012e-05, "loss": 0.3278, "step": 721 }, { "epoch": 2.9275949367088607, "grad_norm": 0.39235107345862025, "learning_rate": 1.7424650928896726e-05, "loss": 0.3266, "step": 722 }, { "epoch": 2.9316455696202532, "grad_norm": 0.3792584888600509, "learning_rate": 1.7368375226690712e-05, "loss": 0.3315, "step": 723 }, { "epoch": 2.9356962025316458, "grad_norm": 0.4014949811565457, "learning_rate": 1.731212071922883e-05, "loss": 0.3656, "step": 724 }, { "epoch": 2.939746835443038, "grad_norm": 0.39497478228891, "learning_rate": 1.7255887859577156e-05, "loss": 0.3416, "step": 725 }, { "epoch": 2.9437974683544303, "grad_norm": 0.37518553435489965, "learning_rate": 1.7199677100627427e-05, "loss": 0.3294, "step": 726 }, { "epoch": 2.947848101265823, "grad_norm": 0.397526784671672, "learning_rate": 1.7143488895093343e-05, "loss": 0.3417, "step": 727 }, { "epoch": 2.951898734177215, "grad_norm": 0.4065745118572031, "learning_rate": 1.7087323695506994e-05, "loss": 0.3146, "step": 728 }, { "epoch": 2.9559493670886074, "grad_norm": 0.3986912232645647, "learning_rate": 1.7031181954215194e-05, "loss": 0.3287, "step": 729 }, { "epoch": 2.96, "grad_norm": 0.3935030188872615, "learning_rate": 1.6975064123375788e-05, "loss": 0.3263, "step": 730 }, { "epoch": 2.9640506329113925, "grad_norm": 0.4000335506993536, "learning_rate": 1.6918970654954084e-05, "loss": 0.34, "step": 731 }, { "epoch": 2.968101265822785, "grad_norm": 0.4024507861433965, "learning_rate": 1.686290200071915e-05, "loss": 0.3287, "step": 732 }, { "epoch": 2.972151898734177, "grad_norm": 0.3963137871584757, "learning_rate": 1.6806858612240234e-05, "loss": 0.3203, "step": 733 }, { "epoch": 2.9762025316455696, "grad_norm": 0.3738682697421089, "learning_rate": 1.6750840940883078e-05, "loss": 0.3213, "step": 734 }, { "epoch": 2.980253164556962, "grad_norm": 0.38143726683217455, "learning_rate": 1.6694849437806305e-05, "loss": 0.3302, "step": 735 }, { "epoch": 2.984303797468354, "grad_norm": 0.4045263026819074, "learning_rate": 1.663888455395778e-05, "loss": 0.3387, "step": 736 }, { "epoch": 2.9883544303797467, "grad_norm": 0.3888610631869071, "learning_rate": 1.6582946740070995e-05, "loss": 0.3258, "step": 737 }, { "epoch": 2.992405063291139, "grad_norm": 0.4062215492622613, "learning_rate": 1.6527036446661396e-05, "loss": 0.3308, "step": 738 }, { "epoch": 2.9964556962025317, "grad_norm": 0.38302078353387126, "learning_rate": 1.6471154124022818e-05, "loss": 0.3146, "step": 739 }, { "epoch": 3.002025316455696, "grad_norm": 0.43784304316565964, "learning_rate": 1.6415300222223788e-05, "loss": 0.2491, "step": 740 }, { "epoch": 3.0060759493670886, "grad_norm": 0.4708260010402041, "learning_rate": 1.6359475191103958e-05, "loss": 0.2025, "step": 741 }, { "epoch": 3.010126582278481, "grad_norm": 0.3484290495528778, "learning_rate": 1.6303679480270466e-05, "loss": 0.1913, "step": 742 }, { "epoch": 3.0141772151898736, "grad_norm": 0.4733982651346105, "learning_rate": 1.624791353909428e-05, "loss": 0.1955, "step": 743 }, { "epoch": 3.0182278481012657, "grad_norm": 0.619909454797516, "learning_rate": 1.619217781670663e-05, "loss": 0.1995, "step": 744 }, { "epoch": 3.022278481012658, "grad_norm": 0.49373721277604415, "learning_rate": 1.6136472761995373e-05, "loss": 0.2199, "step": 745 }, { "epoch": 3.0263291139240507, "grad_norm": 0.4273102463514907, "learning_rate": 1.608079882360134e-05, "loss": 0.2198, "step": 746 }, { "epoch": 3.030379746835443, "grad_norm": 0.4721380961389463, "learning_rate": 1.60251564499148e-05, "loss": 0.2082, "step": 747 }, { "epoch": 3.0344303797468353, "grad_norm": 0.4221103220496691, "learning_rate": 1.596954608907176e-05, "loss": 0.2077, "step": 748 }, { "epoch": 3.038481012658228, "grad_norm": 0.39239706130766344, "learning_rate": 1.591396818895043e-05, "loss": 0.2065, "step": 749 }, { "epoch": 3.0425316455696203, "grad_norm": 0.3669639778105104, "learning_rate": 1.585842319716759e-05, "loss": 0.2091, "step": 750 }, { "epoch": 3.046582278481013, "grad_norm": 0.3989450214783606, "learning_rate": 1.5802911561074944e-05, "loss": 0.19, "step": 751 }, { "epoch": 3.050632911392405, "grad_norm": 0.4300096238914108, "learning_rate": 1.5747433727755595e-05, "loss": 0.1892, "step": 752 }, { "epoch": 3.0546835443037974, "grad_norm": 0.4072631003478725, "learning_rate": 1.5691990144020376e-05, "loss": 0.21, "step": 753 }, { "epoch": 3.05873417721519, "grad_norm": 0.3593078025461522, "learning_rate": 1.5636581256404297e-05, "loss": 0.196, "step": 754 }, { "epoch": 3.0627848101265824, "grad_norm": 0.35465867561580167, "learning_rate": 1.558120751116291e-05, "loss": 0.1912, "step": 755 }, { "epoch": 3.0668354430379745, "grad_norm": 0.3848267441982377, "learning_rate": 1.552586935426876e-05, "loss": 0.2306, "step": 756 }, { "epoch": 3.070886075949367, "grad_norm": 0.3573003255058979, "learning_rate": 1.547056723140774e-05, "loss": 0.2094, "step": 757 }, { "epoch": 3.0749367088607595, "grad_norm": 0.341427815267297, "learning_rate": 1.5415301587975565e-05, "loss": 0.1962, "step": 758 }, { "epoch": 3.078987341772152, "grad_norm": 0.3506459443896491, "learning_rate": 1.536007286907411e-05, "loss": 0.216, "step": 759 }, { "epoch": 3.083037974683544, "grad_norm": 0.38309578243072057, "learning_rate": 1.5304881519507896e-05, "loss": 0.2093, "step": 760 }, { "epoch": 3.0870886075949366, "grad_norm": 0.3659138163132928, "learning_rate": 1.5249727983780453e-05, "loss": 0.212, "step": 761 }, { "epoch": 3.091139240506329, "grad_norm": 0.3496387718061204, "learning_rate": 1.5194612706090786e-05, "loss": 0.1797, "step": 762 }, { "epoch": 3.0951898734177217, "grad_norm": 0.3700754655573619, "learning_rate": 1.5139536130329771e-05, "loss": 0.1967, "step": 763 }, { "epoch": 3.0992405063291137, "grad_norm": 0.33697680662209334, "learning_rate": 1.508449870007656e-05, "loss": 0.1967, "step": 764 }, { "epoch": 3.1032911392405063, "grad_norm": 0.3528556593742356, "learning_rate": 1.5029500858595056e-05, "loss": 0.2177, "step": 765 }, { "epoch": 3.1073417721518988, "grad_norm": 0.34762886687280253, "learning_rate": 1.4974543048830328e-05, "loss": 0.218, "step": 766 }, { "epoch": 3.1113924050632913, "grad_norm": 0.3314730223985731, "learning_rate": 1.4919625713405e-05, "loss": 0.2144, "step": 767 }, { "epoch": 3.1154430379746834, "grad_norm": 0.34169268007912756, "learning_rate": 1.4864749294615756e-05, "loss": 0.2024, "step": 768 }, { "epoch": 3.119493670886076, "grad_norm": 0.34178694140765725, "learning_rate": 1.4809914234429716e-05, "loss": 0.1875, "step": 769 }, { "epoch": 3.1235443037974684, "grad_norm": 0.33972218091168876, "learning_rate": 1.4755120974480923e-05, "loss": 0.2011, "step": 770 }, { "epoch": 3.127594936708861, "grad_norm": 0.33056271375989893, "learning_rate": 1.4700369956066771e-05, "loss": 0.2097, "step": 771 }, { "epoch": 3.131645569620253, "grad_norm": 0.3425225915808171, "learning_rate": 1.4645661620144413e-05, "loss": 0.1955, "step": 772 }, { "epoch": 3.1356962025316455, "grad_norm": 0.3336537947293304, "learning_rate": 1.4590996407327284e-05, "loss": 0.2095, "step": 773 }, { "epoch": 3.139746835443038, "grad_norm": 0.31683963017263417, "learning_rate": 1.4536374757881487e-05, "loss": 0.1994, "step": 774 }, { "epoch": 3.1437974683544305, "grad_norm": 0.33111067669876054, "learning_rate": 1.4481797111722271e-05, "loss": 0.2109, "step": 775 }, { "epoch": 3.1478481012658226, "grad_norm": 0.3359799727794626, "learning_rate": 1.4427263908410507e-05, "loss": 0.2095, "step": 776 }, { "epoch": 3.151898734177215, "grad_norm": 0.3225469836676971, "learning_rate": 1.4372775587149108e-05, "loss": 0.206, "step": 777 }, { "epoch": 3.1559493670886076, "grad_norm": 0.3158142644289823, "learning_rate": 1.4318332586779522e-05, "loss": 0.2232, "step": 778 }, { "epoch": 3.16, "grad_norm": 0.34234033073541054, "learning_rate": 1.4263935345778202e-05, "loss": 0.2005, "step": 779 }, { "epoch": 3.164050632911392, "grad_norm": 0.3349016942244178, "learning_rate": 1.420958430225303e-05, "loss": 0.2221, "step": 780 }, { "epoch": 3.1681012658227847, "grad_norm": 0.3164007460552129, "learning_rate": 1.415527989393985e-05, "loss": 0.1963, "step": 781 }, { "epoch": 3.1721518987341772, "grad_norm": 0.32334268881564293, "learning_rate": 1.410102255819891e-05, "loss": 0.2108, "step": 782 }, { "epoch": 3.1762025316455698, "grad_norm": 0.3252954893013907, "learning_rate": 1.404681273201131e-05, "loss": 0.2324, "step": 783 }, { "epoch": 3.180253164556962, "grad_norm": 0.33109785724650237, "learning_rate": 1.399265085197556e-05, "loss": 0.1969, "step": 784 }, { "epoch": 3.1843037974683543, "grad_norm": 0.3283943804815649, "learning_rate": 1.393853735430398e-05, "loss": 0.2143, "step": 785 }, { "epoch": 3.188354430379747, "grad_norm": 0.32645015030265445, "learning_rate": 1.3884472674819246e-05, "loss": 0.2096, "step": 786 }, { "epoch": 3.1924050632911394, "grad_norm": 0.31885884946817217, "learning_rate": 1.3830457248950864e-05, "loss": 0.2028, "step": 787 }, { "epoch": 3.1964556962025314, "grad_norm": 0.3118961326288749, "learning_rate": 1.377649151173163e-05, "loss": 0.2044, "step": 788 }, { "epoch": 3.200506329113924, "grad_norm": 0.3364917898647318, "learning_rate": 1.3722575897794181e-05, "loss": 0.1878, "step": 789 }, { "epoch": 3.2045569620253165, "grad_norm": 0.3288751983533457, "learning_rate": 1.3668710841367472e-05, "loss": 0.2113, "step": 790 }, { "epoch": 3.208607594936709, "grad_norm": 0.3187876067382938, "learning_rate": 1.361489677627324e-05, "loss": 0.1931, "step": 791 }, { "epoch": 3.212658227848101, "grad_norm": 0.32386662182988446, "learning_rate": 1.3561134135922585e-05, "loss": 0.2195, "step": 792 }, { "epoch": 3.2167088607594936, "grad_norm": 0.3270813122191261, "learning_rate": 1.350742335331241e-05, "loss": 0.2057, "step": 793 }, { "epoch": 3.220759493670886, "grad_norm": 0.3265827801302091, "learning_rate": 1.345376486102198e-05, "loss": 0.1984, "step": 794 }, { "epoch": 3.2248101265822786, "grad_norm": 0.3236642954059231, "learning_rate": 1.3400159091209414e-05, "loss": 0.2286, "step": 795 }, { "epoch": 3.2288607594936707, "grad_norm": 0.32789166957615906, "learning_rate": 1.3346606475608216e-05, "loss": 0.2242, "step": 796 }, { "epoch": 3.232911392405063, "grad_norm": 0.3185412372658369, "learning_rate": 1.3293107445523781e-05, "loss": 0.1937, "step": 797 }, { "epoch": 3.2369620253164557, "grad_norm": 0.327067645251514, "learning_rate": 1.3239662431829949e-05, "loss": 0.2016, "step": 798 }, { "epoch": 3.2410126582278482, "grad_norm": 0.3201174138581836, "learning_rate": 1.3186271864965509e-05, "loss": 0.1994, "step": 799 }, { "epoch": 3.2450632911392403, "grad_norm": 0.32945104805719705, "learning_rate": 1.3132936174930756e-05, "loss": 0.2033, "step": 800 }, { "epoch": 3.249113924050633, "grad_norm": 0.3316231379740153, "learning_rate": 1.3079655791283995e-05, "loss": 0.1888, "step": 801 }, { "epoch": 3.2531645569620253, "grad_norm": 0.3283843484892877, "learning_rate": 1.3026431143138108e-05, "loss": 0.1989, "step": 802 }, { "epoch": 3.257215189873418, "grad_norm": 0.31852514030808293, "learning_rate": 1.2973262659157114e-05, "loss": 0.2112, "step": 803 }, { "epoch": 3.26126582278481, "grad_norm": 0.31633531224918005, "learning_rate": 1.2920150767552651e-05, "loss": 0.2048, "step": 804 }, { "epoch": 3.2653164556962024, "grad_norm": 0.33108045620831283, "learning_rate": 1.2867095896080607e-05, "loss": 0.209, "step": 805 }, { "epoch": 3.269367088607595, "grad_norm": 0.3393875372779905, "learning_rate": 1.2814098472037612e-05, "loss": 0.2016, "step": 806 }, { "epoch": 3.2734177215189875, "grad_norm": 0.31872047383048013, "learning_rate": 1.276115892225764e-05, "loss": 0.1927, "step": 807 }, { "epoch": 3.27746835443038, "grad_norm": 0.32331751434202116, "learning_rate": 1.2708277673108555e-05, "loss": 0.1961, "step": 808 }, { "epoch": 3.281518987341772, "grad_norm": 0.31992880084539466, "learning_rate": 1.2655455150488649e-05, "loss": 0.211, "step": 809 }, { "epoch": 3.2855696202531646, "grad_norm": 0.3183047883693086, "learning_rate": 1.2602691779823272e-05, "loss": 0.2274, "step": 810 }, { "epoch": 3.289620253164557, "grad_norm": 0.3399150479528007, "learning_rate": 1.2549987986061355e-05, "loss": 0.2058, "step": 811 }, { "epoch": 3.293670886075949, "grad_norm": 0.3254920834052391, "learning_rate": 1.2497344193672005e-05, "loss": 0.2015, "step": 812 }, { "epoch": 3.2977215189873417, "grad_norm": 0.31561661757786597, "learning_rate": 1.2444760826641092e-05, "loss": 0.1904, "step": 813 }, { "epoch": 3.301772151898734, "grad_norm": 0.32177558481454427, "learning_rate": 1.2392238308467817e-05, "loss": 0.219, "step": 814 }, { "epoch": 3.3058227848101267, "grad_norm": 0.3198936986922515, "learning_rate": 1.2339777062161326e-05, "loss": 0.1968, "step": 815 }, { "epoch": 3.309873417721519, "grad_norm": 0.3052187824888727, "learning_rate": 1.2287377510237293e-05, "loss": 0.2116, "step": 816 }, { "epoch": 3.3139240506329113, "grad_norm": 0.318229153281501, "learning_rate": 1.2235040074714488e-05, "loss": 0.1924, "step": 817 }, { "epoch": 3.317974683544304, "grad_norm": 0.3152189768987375, "learning_rate": 1.2182765177111434e-05, "loss": 0.1986, "step": 818 }, { "epoch": 3.3220253164556963, "grad_norm": 0.32713532593203354, "learning_rate": 1.213055323844297e-05, "loss": 0.1917, "step": 819 }, { "epoch": 3.3260759493670884, "grad_norm": 0.3239614175889763, "learning_rate": 1.2078404679216864e-05, "loss": 0.2034, "step": 820 }, { "epoch": 3.330126582278481, "grad_norm": 0.3074570690001113, "learning_rate": 1.2026319919430458e-05, "loss": 0.2068, "step": 821 }, { "epoch": 3.3341772151898734, "grad_norm": 0.32556757533499076, "learning_rate": 1.1974299378567227e-05, "loss": 0.1953, "step": 822 }, { "epoch": 3.338227848101266, "grad_norm": 0.3349956639946452, "learning_rate": 1.1922343475593462e-05, "loss": 0.1972, "step": 823 }, { "epoch": 3.3422784810126585, "grad_norm": 0.32584269986676834, "learning_rate": 1.187045262895488e-05, "loss": 0.2081, "step": 824 }, { "epoch": 3.3463291139240505, "grad_norm": 0.3229810009129396, "learning_rate": 1.1818627256573203e-05, "loss": 0.1913, "step": 825 }, { "epoch": 3.350379746835443, "grad_norm": 0.3103439619935549, "learning_rate": 1.1766867775842864e-05, "loss": 0.2092, "step": 826 }, { "epoch": 3.3544303797468356, "grad_norm": 0.31949085287496193, "learning_rate": 1.1715174603627615e-05, "loss": 0.184, "step": 827 }, { "epoch": 3.3584810126582276, "grad_norm": 0.32762015861351085, "learning_rate": 1.1663548156257147e-05, "loss": 0.2121, "step": 828 }, { "epoch": 3.36253164556962, "grad_norm": 0.33030792135187215, "learning_rate": 1.161198884952377e-05, "loss": 0.2062, "step": 829 }, { "epoch": 3.3665822784810127, "grad_norm": 0.3237665027681939, "learning_rate": 1.1560497098679056e-05, "loss": 0.1852, "step": 830 }, { "epoch": 3.370632911392405, "grad_norm": 0.32741883325747423, "learning_rate": 1.1509073318430479e-05, "loss": 0.2022, "step": 831 }, { "epoch": 3.3746835443037977, "grad_norm": 0.32624927890903527, "learning_rate": 1.1457717922938116e-05, "loss": 0.2131, "step": 832 }, { "epoch": 3.3787341772151898, "grad_norm": 0.3230903699580633, "learning_rate": 1.1406431325811233e-05, "loss": 0.1997, "step": 833 }, { "epoch": 3.3827848101265823, "grad_norm": 0.31459124294015006, "learning_rate": 1.135521394010506e-05, "loss": 0.189, "step": 834 }, { "epoch": 3.386835443037975, "grad_norm": 0.3184829919894181, "learning_rate": 1.1304066178317367e-05, "loss": 0.204, "step": 835 }, { "epoch": 3.390886075949367, "grad_norm": 0.3177927477352706, "learning_rate": 1.1252988452385199e-05, "loss": 0.192, "step": 836 }, { "epoch": 3.3949367088607594, "grad_norm": 0.3051777945639093, "learning_rate": 1.1201981173681536e-05, "loss": 0.2018, "step": 837 }, { "epoch": 3.398987341772152, "grad_norm": 0.3307347440810253, "learning_rate": 1.1151044753011991e-05, "loss": 0.1673, "step": 838 }, { "epoch": 3.4030379746835444, "grad_norm": 0.316468072146968, "learning_rate": 1.1100179600611491e-05, "loss": 0.2127, "step": 839 }, { "epoch": 3.407088607594937, "grad_norm": 0.3094240098375453, "learning_rate": 1.1049386126140985e-05, "loss": 0.2023, "step": 840 }, { "epoch": 3.411139240506329, "grad_norm": 0.3237603678615661, "learning_rate": 1.0998664738684128e-05, "loss": 0.2181, "step": 841 }, { "epoch": 3.4151898734177215, "grad_norm": 0.3111580650542039, "learning_rate": 1.0948015846744e-05, "loss": 0.1999, "step": 842 }, { "epoch": 3.419240506329114, "grad_norm": 0.30334591567888164, "learning_rate": 1.0897439858239832e-05, "loss": 0.1985, "step": 843 }, { "epoch": 3.423291139240506, "grad_norm": 0.3285997839407913, "learning_rate": 1.0846937180503652e-05, "loss": 0.2016, "step": 844 }, { "epoch": 3.4273417721518986, "grad_norm": 0.30662570104430964, "learning_rate": 1.0796508220277117e-05, "loss": 0.2035, "step": 845 }, { "epoch": 3.431392405063291, "grad_norm": 0.3233737156872189, "learning_rate": 1.0746153383708107e-05, "loss": 0.2106, "step": 846 }, { "epoch": 3.4354430379746836, "grad_norm": 0.32724700756743924, "learning_rate": 1.0695873076347579e-05, "loss": 0.1818, "step": 847 }, { "epoch": 3.439493670886076, "grad_norm": 0.31517232530777045, "learning_rate": 1.0645667703146205e-05, "loss": 0.229, "step": 848 }, { "epoch": 3.4435443037974682, "grad_norm": 0.3196524149927718, "learning_rate": 1.0595537668451161e-05, "loss": 0.2067, "step": 849 }, { "epoch": 3.4475949367088607, "grad_norm": 0.3184267833013356, "learning_rate": 1.0545483376002854e-05, "loss": 0.2067, "step": 850 }, { "epoch": 3.4516455696202533, "grad_norm": 0.32611401726361455, "learning_rate": 1.0495505228931676e-05, "loss": 0.1986, "step": 851 }, { "epoch": 3.4556962025316453, "grad_norm": 0.3052491585691639, "learning_rate": 1.044560362975474e-05, "loss": 0.185, "step": 852 }, { "epoch": 3.459746835443038, "grad_norm": 0.33165149079243056, "learning_rate": 1.0395778980372695e-05, "loss": 0.204, "step": 853 }, { "epoch": 3.4637974683544304, "grad_norm": 0.32390753002228867, "learning_rate": 1.0346031682066381e-05, "loss": 0.1863, "step": 854 }, { "epoch": 3.467848101265823, "grad_norm": 0.32079360987433536, "learning_rate": 1.0296362135493724e-05, "loss": 0.2128, "step": 855 }, { "epoch": 3.4718987341772154, "grad_norm": 0.31098935119623944, "learning_rate": 1.0246770740686422e-05, "loss": 0.1948, "step": 856 }, { "epoch": 3.4759493670886075, "grad_norm": 0.3180022501937225, "learning_rate": 1.0197257897046743e-05, "loss": 0.1894, "step": 857 }, { "epoch": 3.48, "grad_norm": 0.32693237110931295, "learning_rate": 1.014782400334433e-05, "loss": 0.1898, "step": 858 }, { "epoch": 3.4840506329113925, "grad_norm": 0.312609812795995, "learning_rate": 1.009846945771296e-05, "loss": 0.2088, "step": 859 }, { "epoch": 3.4881012658227846, "grad_norm": 0.3315031122433456, "learning_rate": 1.0049194657647363e-05, "loss": 0.1832, "step": 860 }, { "epoch": 3.492151898734177, "grad_norm": 0.3162044023768207, "learning_rate": 1.0000000000000006e-05, "loss": 0.2093, "step": 861 }, { "epoch": 3.4962025316455696, "grad_norm": 0.31403208107840125, "learning_rate": 9.950885880977891e-06, "loss": 0.1945, "step": 862 }, { "epoch": 3.500253164556962, "grad_norm": 0.3116876365277568, "learning_rate": 9.901852696139382e-06, "loss": 0.2122, "step": 863 }, { "epoch": 3.5043037974683546, "grad_norm": 0.32353343357748854, "learning_rate": 9.852900840391027e-06, "loss": 0.1945, "step": 864 }, { "epoch": 3.5083544303797467, "grad_norm": 0.31548637421669884, "learning_rate": 9.804030707984313e-06, "loss": 0.2302, "step": 865 }, { "epoch": 3.512405063291139, "grad_norm": 0.31331601485754146, "learning_rate": 9.755242692512599e-06, "loss": 0.2282, "step": 866 }, { "epoch": 3.5164556962025317, "grad_norm": 0.32570215214596154, "learning_rate": 9.70653718690782e-06, "loss": 0.195, "step": 867 }, { "epoch": 3.520506329113924, "grad_norm": 0.3111682244884875, "learning_rate": 9.657914583437454e-06, "loss": 0.2129, "step": 868 }, { "epoch": 3.5245569620253163, "grad_norm": 0.3117307665233226, "learning_rate": 9.609375273701246e-06, "loss": 0.209, "step": 869 }, { "epoch": 3.528607594936709, "grad_norm": 0.3071434338651524, "learning_rate": 9.560919648628133e-06, "loss": 0.2099, "step": 870 }, { "epoch": 3.5326582278481014, "grad_norm": 0.32141554000089784, "learning_rate": 9.512548098473047e-06, "loss": 0.1771, "step": 871 }, { "epoch": 3.536708860759494, "grad_norm": 0.32689816051399373, "learning_rate": 9.464261012813825e-06, "loss": 0.1823, "step": 872 }, { "epoch": 3.540759493670886, "grad_norm": 0.30417162827073146, "learning_rate": 9.416058780547987e-06, "loss": 0.1906, "step": 873 }, { "epoch": 3.5448101265822785, "grad_norm": 0.3235436682615015, "learning_rate": 9.367941789889714e-06, "loss": 0.2101, "step": 874 }, { "epoch": 3.548860759493671, "grad_norm": 0.31895694217045056, "learning_rate": 9.319910428366607e-06, "loss": 0.202, "step": 875 }, { "epoch": 3.552911392405063, "grad_norm": 0.2980772901487747, "learning_rate": 9.271965082816667e-06, "loss": 0.1842, "step": 876 }, { "epoch": 3.5569620253164556, "grad_norm": 0.3201455661010293, "learning_rate": 9.224106139385111e-06, "loss": 0.1847, "step": 877 }, { "epoch": 3.561012658227848, "grad_norm": 0.31356515132751234, "learning_rate": 9.176333983521291e-06, "loss": 0.1944, "step": 878 }, { "epoch": 3.5650632911392406, "grad_norm": 0.30706994402846927, "learning_rate": 9.12864899997558e-06, "loss": 0.185, "step": 879 }, { "epoch": 3.569113924050633, "grad_norm": 0.312038501901489, "learning_rate": 9.08105157279628e-06, "loss": 0.1898, "step": 880 }, { "epoch": 3.573164556962025, "grad_norm": 0.3052054690878307, "learning_rate": 9.03354208532653e-06, "loss": 0.1893, "step": 881 }, { "epoch": 3.5772151898734177, "grad_norm": 0.32589967050523705, "learning_rate": 8.986120920201205e-06, "loss": 0.191, "step": 882 }, { "epoch": 3.58126582278481, "grad_norm": 0.31562576833659683, "learning_rate": 8.938788459343852e-06, "loss": 0.2106, "step": 883 }, { "epoch": 3.5853164556962023, "grad_norm": 0.31576610736302047, "learning_rate": 8.8915450839636e-06, "loss": 0.1924, "step": 884 }, { "epoch": 3.589367088607595, "grad_norm": 0.32218389411895154, "learning_rate": 8.844391174552116e-06, "loss": 0.1964, "step": 885 }, { "epoch": 3.5934177215189873, "grad_norm": 0.30071965920125904, "learning_rate": 8.797327110880479e-06, "loss": 0.1781, "step": 886 }, { "epoch": 3.59746835443038, "grad_norm": 0.3164575666264173, "learning_rate": 8.750353271996206e-06, "loss": 0.1825, "step": 887 }, { "epoch": 3.6015189873417723, "grad_norm": 0.3278057186501414, "learning_rate": 8.703470036220132e-06, "loss": 0.2178, "step": 888 }, { "epoch": 3.6055696202531644, "grad_norm": 0.29424352889906225, "learning_rate": 8.656677781143394e-06, "loss": 0.2069, "step": 889 }, { "epoch": 3.609620253164557, "grad_norm": 0.3203843335027609, "learning_rate": 8.609976883624377e-06, "loss": 0.2026, "step": 890 }, { "epoch": 3.6136708860759494, "grad_norm": 0.3096083761319811, "learning_rate": 8.563367719785698e-06, "loss": 0.2049, "step": 891 }, { "epoch": 3.6177215189873415, "grad_norm": 0.31150411060144895, "learning_rate": 8.516850665011138e-06, "loss": 0.2197, "step": 892 }, { "epoch": 3.621772151898734, "grad_norm": 0.31945796493037787, "learning_rate": 8.47042609394269e-06, "loss": 0.1947, "step": 893 }, { "epoch": 3.6258227848101265, "grad_norm": 0.30829149788713817, "learning_rate": 8.424094380477432e-06, "loss": 0.2046, "step": 894 }, { "epoch": 3.629873417721519, "grad_norm": 0.3148327687675797, "learning_rate": 8.37785589776465e-06, "loss": 0.1946, "step": 895 }, { "epoch": 3.6339240506329116, "grad_norm": 0.3286942690019244, "learning_rate": 8.331711018202694e-06, "loss": 0.1828, "step": 896 }, { "epoch": 3.6379746835443036, "grad_norm": 0.3205974671387487, "learning_rate": 8.285660113436104e-06, "loss": 0.217, "step": 897 }, { "epoch": 3.642025316455696, "grad_norm": 0.31943313417722363, "learning_rate": 8.239703554352527e-06, "loss": 0.1924, "step": 898 }, { "epoch": 3.6460759493670887, "grad_norm": 0.31696905914511775, "learning_rate": 8.193841711079775e-06, "loss": 0.2085, "step": 899 }, { "epoch": 3.6501265822784807, "grad_norm": 0.3084533816835001, "learning_rate": 8.148074952982828e-06, "loss": 0.1905, "step": 900 }, { "epoch": 3.6541772151898733, "grad_norm": 0.31764347065367543, "learning_rate": 8.102403648660859e-06, "loss": 0.2098, "step": 901 }, { "epoch": 3.6582278481012658, "grad_norm": 0.3123439843558076, "learning_rate": 8.056828165944282e-06, "loss": 0.2111, "step": 902 }, { "epoch": 3.6622784810126583, "grad_norm": 0.31226223970467815, "learning_rate": 8.011348871891762e-06, "loss": 0.2084, "step": 903 }, { "epoch": 3.666329113924051, "grad_norm": 0.3208198313948209, "learning_rate": 7.965966132787287e-06, "loss": 0.2026, "step": 904 }, { "epoch": 3.670379746835443, "grad_norm": 0.33074816184305006, "learning_rate": 7.920680314137189e-06, "loss": 0.2075, "step": 905 }, { "epoch": 3.6744303797468354, "grad_norm": 0.31989561012915674, "learning_rate": 7.875491780667246e-06, "loss": 0.1842, "step": 906 }, { "epoch": 3.678481012658228, "grad_norm": 0.314739739556296, "learning_rate": 7.830400896319667e-06, "loss": 0.1969, "step": 907 }, { "epoch": 3.68253164556962, "grad_norm": 0.3083218312086622, "learning_rate": 7.785408024250259e-06, "loss": 0.1993, "step": 908 }, { "epoch": 3.6865822784810125, "grad_norm": 0.31328605880319194, "learning_rate": 7.74051352682542e-06, "loss": 0.1958, "step": 909 }, { "epoch": 3.690632911392405, "grad_norm": 0.3149906770572804, "learning_rate": 7.695717765619257e-06, "loss": 0.1864, "step": 910 }, { "epoch": 3.6946835443037975, "grad_norm": 0.31484364539268056, "learning_rate": 7.651021101410673e-06, "loss": 0.1863, "step": 911 }, { "epoch": 3.69873417721519, "grad_norm": 0.3123634458984149, "learning_rate": 7.606423894180464e-06, "loss": 0.2016, "step": 912 }, { "epoch": 3.702784810126582, "grad_norm": 0.3112693058387494, "learning_rate": 7.56192650310839e-06, "loss": 0.1969, "step": 913 }, { "epoch": 3.7068354430379746, "grad_norm": 0.317026628949349, "learning_rate": 7.517529286570349e-06, "loss": 0.21, "step": 914 }, { "epoch": 3.710886075949367, "grad_norm": 0.30480734106750407, "learning_rate": 7.473232602135387e-06, "loss": 0.1954, "step": 915 }, { "epoch": 3.714936708860759, "grad_norm": 0.3179157194925446, "learning_rate": 7.429036806562935e-06, "loss": 0.1756, "step": 916 }, { "epoch": 3.7189873417721517, "grad_norm": 0.31741754395527033, "learning_rate": 7.3849422557998455e-06, "loss": 0.1918, "step": 917 }, { "epoch": 3.7230379746835442, "grad_norm": 0.32105914217464315, "learning_rate": 7.340949304977567e-06, "loss": 0.2084, "step": 918 }, { "epoch": 3.7270886075949368, "grad_norm": 0.3082396153629489, "learning_rate": 7.297058308409282e-06, "loss": 0.2064, "step": 919 }, { "epoch": 3.7311392405063293, "grad_norm": 0.2998709871392136, "learning_rate": 7.25326961958704e-06, "loss": 0.1734, "step": 920 }, { "epoch": 3.7351898734177214, "grad_norm": 0.2952280355770756, "learning_rate": 7.209583591178921e-06, "loss": 0.1959, "step": 921 }, { "epoch": 3.739240506329114, "grad_norm": 0.3160351013665965, "learning_rate": 7.1660005750261925e-06, "loss": 0.2221, "step": 922 }, { "epoch": 3.7432911392405064, "grad_norm": 0.3172585677382446, "learning_rate": 7.1225209221404765e-06, "loss": 0.2096, "step": 923 }, { "epoch": 3.747341772151899, "grad_norm": 0.31127702286671693, "learning_rate": 7.079144982700909e-06, "loss": 0.1926, "step": 924 }, { "epoch": 3.7513924050632914, "grad_norm": 0.3186727463507646, "learning_rate": 7.0358731060513695e-06, "loss": 0.2043, "step": 925 }, { "epoch": 3.7554430379746835, "grad_norm": 0.3096556935757275, "learning_rate": 6.99270564069757e-06, "loss": 0.2277, "step": 926 }, { "epoch": 3.759493670886076, "grad_norm": 0.3130596681465081, "learning_rate": 6.949642934304375e-06, "loss": 0.2165, "step": 927 }, { "epoch": 3.7635443037974685, "grad_norm": 0.323786319326206, "learning_rate": 6.906685333692871e-06, "loss": 0.2115, "step": 928 }, { "epoch": 3.7675949367088606, "grad_norm": 0.3327041012940426, "learning_rate": 6.86383318483769e-06, "loss": 0.2005, "step": 929 }, { "epoch": 3.771645569620253, "grad_norm": 0.31089546088218417, "learning_rate": 6.821086832864139e-06, "loss": 0.2043, "step": 930 }, { "epoch": 3.7756962025316456, "grad_norm": 0.31567604170484864, "learning_rate": 6.77844662204546e-06, "loss": 0.221, "step": 931 }, { "epoch": 3.779746835443038, "grad_norm": 0.31839453777644267, "learning_rate": 6.7359128958000455e-06, "loss": 0.201, "step": 932 }, { "epoch": 3.7837974683544306, "grad_norm": 0.30756313850132744, "learning_rate": 6.693485996688695e-06, "loss": 0.1906, "step": 933 }, { "epoch": 3.7878481012658227, "grad_norm": 0.3209994767182923, "learning_rate": 6.651166266411801e-06, "loss": 0.1909, "step": 934 }, { "epoch": 3.7918987341772152, "grad_norm": 0.3039569560825705, "learning_rate": 6.6089540458066725e-06, "loss": 0.214, "step": 935 }, { "epoch": 3.7959493670886078, "grad_norm": 0.32004966774297383, "learning_rate": 6.566849674844711e-06, "loss": 0.2293, "step": 936 }, { "epoch": 3.8, "grad_norm": 0.3228718666044321, "learning_rate": 6.524853492628747e-06, "loss": 0.207, "step": 937 }, { "epoch": 3.8040506329113923, "grad_norm": 0.316590532750054, "learning_rate": 6.4829658373902536e-06, "loss": 0.1949, "step": 938 }, { "epoch": 3.808101265822785, "grad_norm": 0.3252952578465448, "learning_rate": 6.441187046486648e-06, "loss": 0.1984, "step": 939 }, { "epoch": 3.8121518987341774, "grad_norm": 0.31364813805108893, "learning_rate": 6.399517456398567e-06, "loss": 0.2008, "step": 940 }, { "epoch": 3.81620253164557, "grad_norm": 0.31825424460436685, "learning_rate": 6.357957402727164e-06, "loss": 0.1956, "step": 941 }, { "epoch": 3.820253164556962, "grad_norm": 0.30035095115988375, "learning_rate": 6.316507220191395e-06, "loss": 0.2124, "step": 942 }, { "epoch": 3.8243037974683545, "grad_norm": 0.3101716448705399, "learning_rate": 6.275167242625331e-06, "loss": 0.1846, "step": 943 }, { "epoch": 3.828354430379747, "grad_norm": 0.3086279733733083, "learning_rate": 6.233937802975471e-06, "loss": 0.2039, "step": 944 }, { "epoch": 3.832405063291139, "grad_norm": 0.3062226616781802, "learning_rate": 6.192819233298046e-06, "loss": 0.2075, "step": 945 }, { "epoch": 3.8364556962025316, "grad_norm": 0.30270160535227614, "learning_rate": 6.151811864756383e-06, "loss": 0.1925, "step": 946 }, { "epoch": 3.840506329113924, "grad_norm": 0.30711807751975373, "learning_rate": 6.1109160276181655e-06, "loss": 0.21, "step": 947 }, { "epoch": 3.8445569620253166, "grad_norm": 0.3088998483013543, "learning_rate": 6.070132051252868e-06, "loss": 0.2, "step": 948 }, { "epoch": 3.848607594936709, "grad_norm": 0.3052924035051728, "learning_rate": 6.0294602641290034e-06, "loss": 0.2399, "step": 949 }, { "epoch": 3.852658227848101, "grad_norm": 0.3123626945555963, "learning_rate": 5.988900993811575e-06, "loss": 0.2091, "step": 950 }, { "epoch": 3.8567088607594937, "grad_norm": 0.3208166213444505, "learning_rate": 5.948454566959363e-06, "loss": 0.1863, "step": 951 }, { "epoch": 3.8607594936708862, "grad_norm": 0.30845213449127956, "learning_rate": 5.908121309322328e-06, "loss": 0.2197, "step": 952 }, { "epoch": 3.8648101265822783, "grad_norm": 0.30880665771902255, "learning_rate": 5.867901545738976e-06, "loss": 0.1987, "step": 953 }, { "epoch": 3.868860759493671, "grad_norm": 0.2991152314270791, "learning_rate": 5.827795600133774e-06, "loss": 0.2005, "step": 954 }, { "epoch": 3.8729113924050633, "grad_norm": 0.3036826167782594, "learning_rate": 5.787803795514466e-06, "loss": 0.1842, "step": 955 }, { "epoch": 3.876962025316456, "grad_norm": 0.3200621974835426, "learning_rate": 5.747926453969576e-06, "loss": 0.1792, "step": 956 }, { "epoch": 3.8810126582278484, "grad_norm": 0.32079484250090345, "learning_rate": 5.708163896665708e-06, "loss": 0.2102, "step": 957 }, { "epoch": 3.8850632911392404, "grad_norm": 0.31924511660715915, "learning_rate": 5.668516443845047e-06, "loss": 0.2058, "step": 958 }, { "epoch": 3.889113924050633, "grad_norm": 0.30933053115332, "learning_rate": 5.6289844148227225e-06, "loss": 0.205, "step": 959 }, { "epoch": 3.8931645569620255, "grad_norm": 0.32265010591434407, "learning_rate": 5.5895681279842615e-06, "loss": 0.1959, "step": 960 }, { "epoch": 3.8972151898734175, "grad_norm": 0.3029373907292283, "learning_rate": 5.550267900783019e-06, "loss": 0.1933, "step": 961 }, { "epoch": 3.90126582278481, "grad_norm": 0.3086536462589818, "learning_rate": 5.511084049737623e-06, "loss": 0.2025, "step": 962 }, { "epoch": 3.9053164556962026, "grad_norm": 0.30281995911283266, "learning_rate": 5.4720168904294215e-06, "loss": 0.1765, "step": 963 }, { "epoch": 3.909367088607595, "grad_norm": 0.3115986712937317, "learning_rate": 5.433066737499948e-06, "loss": 0.2082, "step": 964 }, { "epoch": 3.9134177215189876, "grad_norm": 0.3103894412798085, "learning_rate": 5.394233904648376e-06, "loss": 0.2099, "step": 965 }, { "epoch": 3.9174683544303797, "grad_norm": 0.30896317601890866, "learning_rate": 5.355518704628997e-06, "loss": 0.2203, "step": 966 }, { "epoch": 3.921518987341772, "grad_norm": 0.3051295802724828, "learning_rate": 5.316921449248731e-06, "loss": 0.1756, "step": 967 }, { "epoch": 3.9255696202531647, "grad_norm": 0.296628290000514, "learning_rate": 5.278442449364538e-06, "loss": 0.2016, "step": 968 }, { "epoch": 3.9296202531645568, "grad_norm": 0.32434836327648975, "learning_rate": 5.240082014881016e-06, "loss": 0.186, "step": 969 }, { "epoch": 3.9336708860759493, "grad_norm": 0.3235332067511575, "learning_rate": 5.201840454747822e-06, "loss": 0.2066, "step": 970 }, { "epoch": 3.937721518987342, "grad_norm": 0.3064656416947726, "learning_rate": 5.163718076957223e-06, "loss": 0.1955, "step": 971 }, { "epoch": 3.9417721518987343, "grad_norm": 0.30057430449861866, "learning_rate": 5.125715188541609e-06, "loss": 0.189, "step": 972 }, { "epoch": 3.945822784810127, "grad_norm": 0.2990584528164743, "learning_rate": 5.087832095571021e-06, "loss": 0.2221, "step": 973 }, { "epoch": 3.949873417721519, "grad_norm": 0.29908452067405833, "learning_rate": 5.0500691031506766e-06, "loss": 0.1892, "step": 974 }, { "epoch": 3.9539240506329114, "grad_norm": 0.3047284859427485, "learning_rate": 5.01242651541854e-06, "loss": 0.2057, "step": 975 }, { "epoch": 3.957974683544304, "grad_norm": 0.2985826212648293, "learning_rate": 4.974904635542815e-06, "loss": 0.1975, "step": 976 }, { "epoch": 3.962025316455696, "grad_norm": 0.3108577892051785, "learning_rate": 4.937503765719582e-06, "loss": 0.1787, "step": 977 }, { "epoch": 3.9660759493670885, "grad_norm": 0.30450794086651406, "learning_rate": 4.900224207170299e-06, "loss": 0.1842, "step": 978 }, { "epoch": 3.970126582278481, "grad_norm": 0.3029584127133561, "learning_rate": 4.8630662601394065e-06, "loss": 0.2075, "step": 979 }, { "epoch": 3.9741772151898735, "grad_norm": 0.30411067774418665, "learning_rate": 4.8260302238918995e-06, "loss": 0.1926, "step": 980 }, { "epoch": 3.978227848101266, "grad_norm": 0.2999294465931261, "learning_rate": 4.789116396710924e-06, "loss": 0.1914, "step": 981 }, { "epoch": 3.982278481012658, "grad_norm": 0.3105856104679666, "learning_rate": 4.752325075895368e-06, "loss": 0.2099, "step": 982 }, { "epoch": 3.9863291139240506, "grad_norm": 0.2972769296210853, "learning_rate": 4.715656557757473e-06, "loss": 0.1979, "step": 983 }, { "epoch": 3.990379746835443, "grad_norm": 0.2982532670726368, "learning_rate": 4.679111137620442e-06, "loss": 0.2201, "step": 984 }, { "epoch": 3.9944303797468352, "grad_norm": 0.29965939256167096, "learning_rate": 4.6426891098160585e-06, "loss": 0.2014, "step": 985 }, { "epoch": 3.9984810126582278, "grad_norm": 0.3042074669442136, "learning_rate": 4.6063907676823474e-06, "loss": 0.1893, "step": 986 }, { "epoch": 4.004050632911392, "grad_norm": 0.4094382506875454, "learning_rate": 4.570216403561141e-06, "loss": 0.1555, "step": 987 }, { "epoch": 4.008101265822785, "grad_norm": 0.3461261536499375, "learning_rate": 4.534166308795815e-06, "loss": 0.1481, "step": 988 }, { "epoch": 4.012151898734177, "grad_norm": 0.29207618725677365, "learning_rate": 4.498240773728859e-06, "loss": 0.159, "step": 989 }, { "epoch": 4.01620253164557, "grad_norm": 0.24076511670011055, "learning_rate": 4.462440087699609e-06, "loss": 0.148, "step": 990 }, { "epoch": 4.020253164556962, "grad_norm": 0.2499697073262268, "learning_rate": 4.426764539041861e-06, "loss": 0.1458, "step": 991 }, { "epoch": 4.024303797468354, "grad_norm": 0.3482061548688361, "learning_rate": 4.391214415081582e-06, "loss": 0.1654, "step": 992 }, { "epoch": 4.028354430379747, "grad_norm": 0.33131832458776667, "learning_rate": 4.355790002134579e-06, "loss": 0.1352, "step": 993 }, { "epoch": 4.032405063291139, "grad_norm": 0.3990624595760026, "learning_rate": 4.320491585504207e-06, "loss": 0.167, "step": 994 }, { "epoch": 4.036455696202531, "grad_norm": 0.3177426778064951, "learning_rate": 4.2853194494790615e-06, "loss": 0.1571, "step": 995 }, { "epoch": 4.040506329113924, "grad_norm": 0.28908223954410134, "learning_rate": 4.250273877330691e-06, "loss": 0.1485, "step": 996 }, { "epoch": 4.044556962025316, "grad_norm": 0.26869611456214865, "learning_rate": 4.215355151311313e-06, "loss": 0.1378, "step": 997 }, { "epoch": 4.048607594936709, "grad_norm": 0.31541537446732176, "learning_rate": 4.180563552651542e-06, "loss": 0.1669, "step": 998 }, { "epoch": 4.052658227848101, "grad_norm": 0.2792565098551352, "learning_rate": 4.145899361558147e-06, "loss": 0.1472, "step": 999 }, { "epoch": 4.056708860759493, "grad_norm": 0.25882205456070784, "learning_rate": 4.111362857211738e-06, "loss": 0.1366, "step": 1000 }, { "epoch": 4.060759493670886, "grad_norm": 0.2557742139098667, "learning_rate": 4.076954317764592e-06, "loss": 0.125, "step": 1001 }, { "epoch": 4.0648101265822785, "grad_norm": 0.2574407098923326, "learning_rate": 4.042674020338335e-06, "loss": 0.1494, "step": 1002 }, { "epoch": 4.0688607594936705, "grad_norm": 0.2487536455889468, "learning_rate": 4.0085222410217835e-06, "loss": 0.1509, "step": 1003 }, { "epoch": 4.0729113924050635, "grad_norm": 0.2586724711628194, "learning_rate": 3.974499254868674e-06, "loss": 0.1427, "step": 1004 }, { "epoch": 4.076962025316456, "grad_norm": 0.2470634879920264, "learning_rate": 3.940605335895451e-06, "loss": 0.1222, "step": 1005 }, { "epoch": 4.0810126582278485, "grad_norm": 0.2784919833794957, "learning_rate": 3.90684075707908e-06, "loss": 0.1622, "step": 1006 }, { "epoch": 4.085063291139241, "grad_norm": 0.25561070688936716, "learning_rate": 3.8732057903548505e-06, "loss": 0.1153, "step": 1007 }, { "epoch": 4.089113924050633, "grad_norm": 0.2708043122012161, "learning_rate": 3.8397007066141375e-06, "loss": 0.1625, "step": 1008 }, { "epoch": 4.093164556962026, "grad_norm": 0.24297757340351545, "learning_rate": 3.806325775702304e-06, "loss": 0.1298, "step": 1009 }, { "epoch": 4.097215189873418, "grad_norm": 0.26002480874702066, "learning_rate": 3.773081266416434e-06, "loss": 0.1356, "step": 1010 }, { "epoch": 4.10126582278481, "grad_norm": 0.24091321376806935, "learning_rate": 3.739967446503245e-06, "loss": 0.1065, "step": 1011 }, { "epoch": 4.105316455696203, "grad_norm": 0.23764410453910695, "learning_rate": 3.706984582656894e-06, "loss": 0.1437, "step": 1012 }, { "epoch": 4.109367088607595, "grad_norm": 0.26342347555449175, "learning_rate": 3.6741329405168237e-06, "loss": 0.1314, "step": 1013 }, { "epoch": 4.113417721518988, "grad_norm": 0.24911191280861456, "learning_rate": 3.641412784665648e-06, "loss": 0.1475, "step": 1014 }, { "epoch": 4.11746835443038, "grad_norm": 0.25488226744692655, "learning_rate": 3.608824378627005e-06, "loss": 0.14, "step": 1015 }, { "epoch": 4.121518987341772, "grad_norm": 0.24154018193334123, "learning_rate": 3.5763679848634337e-06, "loss": 0.143, "step": 1016 }, { "epoch": 4.125569620253165, "grad_norm": 0.22153802205199202, "learning_rate": 3.544043864774269e-06, "loss": 0.1236, "step": 1017 }, { "epoch": 4.129620253164557, "grad_norm": 0.24033713908341983, "learning_rate": 3.5118522786935282e-06, "loss": 0.1316, "step": 1018 }, { "epoch": 4.133670886075949, "grad_norm": 0.2491135023354228, "learning_rate": 3.479793485887819e-06, "loss": 0.1272, "step": 1019 }, { "epoch": 4.137721518987342, "grad_norm": 0.23633306941347743, "learning_rate": 3.4478677445542653e-06, "loss": 0.1392, "step": 1020 }, { "epoch": 4.141772151898734, "grad_norm": 0.24115607029602246, "learning_rate": 3.4160753118183767e-06, "loss": 0.1363, "step": 1021 }, { "epoch": 4.145822784810127, "grad_norm": 0.2491193895959141, "learning_rate": 3.3844164437320527e-06, "loss": 0.1256, "step": 1022 }, { "epoch": 4.149873417721519, "grad_norm": 0.24120022313242676, "learning_rate": 3.3528913952714558e-06, "loss": 0.1053, "step": 1023 }, { "epoch": 4.153924050632911, "grad_norm": 0.25271086757863154, "learning_rate": 3.321500420335e-06, "loss": 0.1418, "step": 1024 }, { "epoch": 4.157974683544304, "grad_norm": 0.2425303236701978, "learning_rate": 3.290243771741275e-06, "loss": 0.1513, "step": 1025 }, { "epoch": 4.162025316455696, "grad_norm": 0.2381071919554052, "learning_rate": 3.2591217012270325e-06, "loss": 0.1358, "step": 1026 }, { "epoch": 4.166075949367088, "grad_norm": 0.23790100769554273, "learning_rate": 3.228134459445149e-06, "loss": 0.1462, "step": 1027 }, { "epoch": 4.170126582278481, "grad_norm": 0.23571487556412332, "learning_rate": 3.1972822959626205e-06, "loss": 0.1435, "step": 1028 }, { "epoch": 4.174177215189873, "grad_norm": 0.24492260804367857, "learning_rate": 3.166565459258513e-06, "loss": 0.1349, "step": 1029 }, { "epoch": 4.178227848101266, "grad_norm": 0.2407313316299334, "learning_rate": 3.1359841967220193e-06, "loss": 0.1439, "step": 1030 }, { "epoch": 4.182278481012658, "grad_norm": 0.23825983516210184, "learning_rate": 3.105538754650419e-06, "loss": 0.1341, "step": 1031 }, { "epoch": 4.18632911392405, "grad_norm": 0.24351685553016886, "learning_rate": 3.07522937824712e-06, "loss": 0.146, "step": 1032 }, { "epoch": 4.190379746835443, "grad_norm": 0.24435270481595778, "learning_rate": 3.0450563116196697e-06, "loss": 0.1323, "step": 1033 }, { "epoch": 4.194430379746835, "grad_norm": 0.25034237614433075, "learning_rate": 3.0150197977778008e-06, "loss": 0.1485, "step": 1034 }, { "epoch": 4.1984810126582275, "grad_norm": 0.23316116462475894, "learning_rate": 2.985120078631465e-06, "loss": 0.1489, "step": 1035 }, { "epoch": 4.2025316455696204, "grad_norm": 0.24962885131938176, "learning_rate": 2.9553573949888893e-06, "loss": 0.1336, "step": 1036 }, { "epoch": 4.2065822784810125, "grad_norm": 0.25036315054539354, "learning_rate": 2.9257319865546384e-06, "loss": 0.1305, "step": 1037 }, { "epoch": 4.2106329113924055, "grad_norm": 0.23519993256742083, "learning_rate": 2.896244091927678e-06, "loss": 0.135, "step": 1038 }, { "epoch": 4.2146835443037975, "grad_norm": 0.23728646920211896, "learning_rate": 2.8668939485994584e-06, "loss": 0.1305, "step": 1039 }, { "epoch": 4.21873417721519, "grad_norm": 0.23505311286555158, "learning_rate": 2.837681792951994e-06, "loss": 0.15, "step": 1040 }, { "epoch": 4.222784810126583, "grad_norm": 0.23947979363549632, "learning_rate": 2.808607860255981e-06, "loss": 0.1374, "step": 1041 }, { "epoch": 4.226835443037975, "grad_norm": 0.2429314471102928, "learning_rate": 2.7796723846688634e-06, "loss": 0.1454, "step": 1042 }, { "epoch": 4.230886075949367, "grad_norm": 0.24496999749483792, "learning_rate": 2.7508755992329937e-06, "loss": 0.1306, "step": 1043 }, { "epoch": 4.23493670886076, "grad_norm": 0.22098489906546687, "learning_rate": 2.722217735873718e-06, "loss": 0.1283, "step": 1044 }, { "epoch": 4.238987341772152, "grad_norm": 0.2452732553026733, "learning_rate": 2.6936990253975315e-06, "loss": 0.17, "step": 1045 }, { "epoch": 4.243037974683545, "grad_norm": 0.23712640064901874, "learning_rate": 2.665319697490205e-06, "loss": 0.1559, "step": 1046 }, { "epoch": 4.247088607594937, "grad_norm": 0.22654713119665382, "learning_rate": 2.637079980714945e-06, "loss": 0.1327, "step": 1047 }, { "epoch": 4.251139240506329, "grad_norm": 0.24224995277077602, "learning_rate": 2.6089801025105453e-06, "loss": 0.154, "step": 1048 }, { "epoch": 4.255189873417722, "grad_norm": 0.24254055109512218, "learning_rate": 2.581020289189571e-06, "loss": 0.1272, "step": 1049 }, { "epoch": 4.259240506329114, "grad_norm": 0.24684675857999525, "learning_rate": 2.553200765936501e-06, "loss": 0.1941, "step": 1050 }, { "epoch": 4.263291139240506, "grad_norm": 0.24147221681986172, "learning_rate": 2.525521756805962e-06, "loss": 0.1259, "step": 1051 }, { "epoch": 4.267341772151899, "grad_norm": 0.22667933460484754, "learning_rate": 2.497983484720885e-06, "loss": 0.1417, "step": 1052 }, { "epoch": 4.271392405063291, "grad_norm": 0.24290198256665227, "learning_rate": 2.470586171470728e-06, "loss": 0.1362, "step": 1053 }, { "epoch": 4.275443037974684, "grad_norm": 0.23778958148313203, "learning_rate": 2.4433300377096836e-06, "loss": 0.1419, "step": 1054 }, { "epoch": 4.279493670886076, "grad_norm": 0.23563531440076763, "learning_rate": 2.4162153029549073e-06, "loss": 0.1455, "step": 1055 }, { "epoch": 4.283544303797468, "grad_norm": 0.22922823020220193, "learning_rate": 2.3892421855847458e-06, "loss": 0.1468, "step": 1056 }, { "epoch": 4.287594936708861, "grad_norm": 0.24337623624595975, "learning_rate": 2.362410902836978e-06, "loss": 0.1385, "step": 1057 }, { "epoch": 4.291645569620253, "grad_norm": 0.23851964262228423, "learning_rate": 2.3357216708070653e-06, "loss": 0.1395, "step": 1058 }, { "epoch": 4.295696202531645, "grad_norm": 0.23762913695760607, "learning_rate": 2.309174704446411e-06, "loss": 0.1679, "step": 1059 }, { "epoch": 4.299746835443038, "grad_norm": 0.24023355093263632, "learning_rate": 2.2827702175606437e-06, "loss": 0.1238, "step": 1060 }, { "epoch": 4.30379746835443, "grad_norm": 0.24703406115869675, "learning_rate": 2.256508422807855e-06, "loss": 0.1416, "step": 1061 }, { "epoch": 4.307848101265823, "grad_norm": 0.25513910880573265, "learning_rate": 2.230389531696946e-06, "loss": 0.1442, "step": 1062 }, { "epoch": 4.311898734177215, "grad_norm": 0.2440504663464166, "learning_rate": 2.204413754585857e-06, "loss": 0.1543, "step": 1063 }, { "epoch": 4.315949367088607, "grad_norm": 0.2358477350729724, "learning_rate": 2.1785813006799406e-06, "loss": 0.1429, "step": 1064 }, { "epoch": 4.32, "grad_norm": 0.23099161643204627, "learning_rate": 2.1528923780302224e-06, "loss": 0.1396, "step": 1065 }, { "epoch": 4.324050632911392, "grad_norm": 0.2307695118030417, "learning_rate": 2.127347193531757e-06, "loss": 0.144, "step": 1066 }, { "epoch": 4.328101265822784, "grad_norm": 0.25537135590954674, "learning_rate": 2.101945952921942e-06, "loss": 0.153, "step": 1067 }, { "epoch": 4.332151898734177, "grad_norm": 0.24148897023157778, "learning_rate": 2.0766888607788906e-06, "loss": 0.1314, "step": 1068 }, { "epoch": 4.3362025316455695, "grad_norm": 0.24155565916552105, "learning_rate": 2.0515761205197337e-06, "loss": 0.1586, "step": 1069 }, { "epoch": 4.340253164556962, "grad_norm": 0.24283048539064556, "learning_rate": 2.0266079343990453e-06, "loss": 0.1477, "step": 1070 }, { "epoch": 4.3443037974683545, "grad_norm": 0.2294209108851659, "learning_rate": 2.0017845035071494e-06, "loss": 0.1644, "step": 1071 }, { "epoch": 4.348354430379747, "grad_norm": 0.23590284759027091, "learning_rate": 1.9771060277685537e-06, "loss": 0.1365, "step": 1072 }, { "epoch": 4.3524050632911395, "grad_norm": 0.24540069922661623, "learning_rate": 1.95257270594031e-06, "loss": 0.1553, "step": 1073 }, { "epoch": 4.356455696202532, "grad_norm": 0.22855395123743463, "learning_rate": 1.9281847356104188e-06, "loss": 0.1451, "step": 1074 }, { "epoch": 4.360506329113924, "grad_norm": 0.23748309242385082, "learning_rate": 1.9039423131962365e-06, "loss": 0.1213, "step": 1075 }, { "epoch": 4.364556962025317, "grad_norm": 0.24368091241399636, "learning_rate": 1.8798456339429027e-06, "loss": 0.1589, "step": 1076 }, { "epoch": 4.368607594936709, "grad_norm": 0.24182072463150195, "learning_rate": 1.8558948919217612e-06, "loss": 0.1477, "step": 1077 }, { "epoch": 4.372658227848102, "grad_norm": 0.242693488044687, "learning_rate": 1.8320902800287954e-06, "loss": 0.1442, "step": 1078 }, { "epoch": 4.376708860759494, "grad_norm": 0.2346853411707708, "learning_rate": 1.8084319899830726e-06, "loss": 0.1388, "step": 1079 }, { "epoch": 4.380759493670886, "grad_norm": 0.23931962931868328, "learning_rate": 1.7849202123252097e-06, "loss": 0.1634, "step": 1080 }, { "epoch": 4.384810126582279, "grad_norm": 0.2361522283026376, "learning_rate": 1.7615551364158401e-06, "loss": 0.1393, "step": 1081 }, { "epoch": 4.388860759493671, "grad_norm": 0.24537774933542444, "learning_rate": 1.738336950434061e-06, "loss": 0.1398, "step": 1082 }, { "epoch": 4.392911392405063, "grad_norm": 0.2367226947698229, "learning_rate": 1.715265841375957e-06, "loss": 0.151, "step": 1083 }, { "epoch": 4.396962025316456, "grad_norm": 0.24440716888260383, "learning_rate": 1.6923419950530684e-06, "loss": 0.1512, "step": 1084 }, { "epoch": 4.401012658227848, "grad_norm": 0.23004444009717126, "learning_rate": 1.6695655960909008e-06, "loss": 0.119, "step": 1085 }, { "epoch": 4.405063291139241, "grad_norm": 0.23558236330489088, "learning_rate": 1.646936827927441e-06, "loss": 0.1486, "step": 1086 }, { "epoch": 4.409113924050633, "grad_norm": 0.23384286829950918, "learning_rate": 1.6244558728116766e-06, "loss": 0.1294, "step": 1087 }, { "epoch": 4.413164556962025, "grad_norm": 0.2301134018343506, "learning_rate": 1.6021229118021265e-06, "loss": 0.1413, "step": 1088 }, { "epoch": 4.417215189873418, "grad_norm": 0.2373757529402448, "learning_rate": 1.5799381247653967e-06, "loss": 0.1465, "step": 1089 }, { "epoch": 4.42126582278481, "grad_norm": 0.24225057506014747, "learning_rate": 1.5579016903747013e-06, "loss": 0.1604, "step": 1090 }, { "epoch": 4.425316455696202, "grad_norm": 0.2299036536896677, "learning_rate": 1.5360137861084656e-06, "loss": 0.162, "step": 1091 }, { "epoch": 4.429367088607595, "grad_norm": 0.23548409926426073, "learning_rate": 1.5142745882488475e-06, "loss": 0.1461, "step": 1092 }, { "epoch": 4.433417721518987, "grad_norm": 0.24721376266738923, "learning_rate": 1.4926842718803691e-06, "loss": 0.1612, "step": 1093 }, { "epoch": 4.43746835443038, "grad_norm": 0.23095964906490438, "learning_rate": 1.4712430108884657e-06, "loss": 0.1224, "step": 1094 }, { "epoch": 4.441518987341772, "grad_norm": 0.23700850510798424, "learning_rate": 1.4499509779581078e-06, "loss": 0.1495, "step": 1095 }, { "epoch": 4.445569620253164, "grad_norm": 0.2345636046758427, "learning_rate": 1.4288083445723988e-06, "loss": 0.1307, "step": 1096 }, { "epoch": 4.449620253164557, "grad_norm": 0.24230589477662984, "learning_rate": 1.4078152810112045e-06, "loss": 0.1546, "step": 1097 }, { "epoch": 4.453670886075949, "grad_norm": 0.23382366970583285, "learning_rate": 1.3869719563497697e-06, "loss": 0.1287, "step": 1098 }, { "epoch": 4.457721518987341, "grad_norm": 0.2444974916663798, "learning_rate": 1.3662785384573663e-06, "loss": 0.1386, "step": 1099 }, { "epoch": 4.461772151898734, "grad_norm": 0.23755476293676717, "learning_rate": 1.3457351939959383e-06, "loss": 0.1401, "step": 1100 }, { "epoch": 4.465822784810126, "grad_norm": 0.24045098054670097, "learning_rate": 1.3253420884187551e-06, "loss": 0.1261, "step": 1101 }, { "epoch": 4.469873417721519, "grad_norm": 0.22108789488747976, "learning_rate": 1.3050993859690953e-06, "loss": 0.1298, "step": 1102 }, { "epoch": 4.473924050632911, "grad_norm": 0.23396947113950303, "learning_rate": 1.2850072496788869e-06, "loss": 0.1125, "step": 1103 }, { "epoch": 4.4779746835443035, "grad_norm": 0.24064273143152556, "learning_rate": 1.2650658413674434e-06, "loss": 0.1361, "step": 1104 }, { "epoch": 4.4820253164556965, "grad_norm": 0.24972502850261938, "learning_rate": 1.2452753216401226e-06, "loss": 0.1431, "step": 1105 }, { "epoch": 4.4860759493670885, "grad_norm": 0.24800139621814976, "learning_rate": 1.2256358498870503e-06, "loss": 0.1461, "step": 1106 }, { "epoch": 4.490126582278481, "grad_norm": 0.23469256085137338, "learning_rate": 1.2061475842818337e-06, "loss": 0.1429, "step": 1107 }, { "epoch": 4.494177215189874, "grad_norm": 0.22866632856889382, "learning_rate": 1.1868106817802816e-06, "loss": 0.1083, "step": 1108 }, { "epoch": 4.498227848101266, "grad_norm": 0.23322985752929426, "learning_rate": 1.1676252981191482e-06, "loss": 0.1427, "step": 1109 }, { "epoch": 4.502278481012659, "grad_norm": 0.2370895810197135, "learning_rate": 1.1485915878148823e-06, "loss": 0.1338, "step": 1110 }, { "epoch": 4.506329113924051, "grad_norm": 0.23498558661531413, "learning_rate": 1.1297097041623584e-06, "loss": 0.1309, "step": 1111 }, { "epoch": 4.510379746835443, "grad_norm": 0.2358743299742422, "learning_rate": 1.1109797992336847e-06, "loss": 0.138, "step": 1112 }, { "epoch": 4.514430379746836, "grad_norm": 0.23217915075876489, "learning_rate": 1.092402023876933e-06, "loss": 0.1637, "step": 1113 }, { "epoch": 4.518481012658228, "grad_norm": 0.2489455897317282, "learning_rate": 1.0739765277149527e-06, "loss": 0.1253, "step": 1114 }, { "epoch": 4.52253164556962, "grad_norm": 0.22748001374157933, "learning_rate": 1.0557034591441596e-06, "loss": 0.1361, "step": 1115 }, { "epoch": 4.526582278481013, "grad_norm": 0.2452036733903124, "learning_rate": 1.0375829653333324e-06, "loss": 0.1412, "step": 1116 }, { "epoch": 4.530632911392405, "grad_norm": 0.23803578358048752, "learning_rate": 1.0196151922224385e-06, "loss": 0.1256, "step": 1117 }, { "epoch": 4.534683544303798, "grad_norm": 0.2292401768643876, "learning_rate": 1.0018002845214526e-06, "loss": 0.1369, "step": 1118 }, { "epoch": 4.53873417721519, "grad_norm": 0.24093324990677473, "learning_rate": 9.841383857091947e-07, "loss": 0.1393, "step": 1119 }, { "epoch": 4.542784810126582, "grad_norm": 0.2342928944764323, "learning_rate": 9.666296380321616e-07, "loss": 0.1612, "step": 1120 }, { "epoch": 4.546835443037975, "grad_norm": 0.2479902798518943, "learning_rate": 9.492741825034124e-07, "loss": 0.1351, "step": 1121 }, { "epoch": 4.550886075949367, "grad_norm": 0.2320203053752211, "learning_rate": 9.320721589013892e-07, "loss": 0.1442, "step": 1122 }, { "epoch": 4.55493670886076, "grad_norm": 0.23849640593491636, "learning_rate": 9.150237057688339e-07, "loss": 0.1284, "step": 1123 }, { "epoch": 4.558987341772152, "grad_norm": 0.22782130807228998, "learning_rate": 8.981289604116328e-07, "loss": 0.1142, "step": 1124 }, { "epoch": 4.563037974683544, "grad_norm": 0.2416153807030879, "learning_rate": 8.813880588977542e-07, "loss": 0.1546, "step": 1125 }, { "epoch": 4.567088607594937, "grad_norm": 0.23983237851758113, "learning_rate": 8.648011360561126e-07, "loss": 0.144, "step": 1126 }, { "epoch": 4.571139240506329, "grad_norm": 0.24688721549343784, "learning_rate": 8.483683254755037e-07, "loss": 0.1511, "step": 1127 }, { "epoch": 4.575189873417721, "grad_norm": 0.23165945284952505, "learning_rate": 8.320897595035227e-07, "loss": 0.1361, "step": 1128 }, { "epoch": 4.579240506329114, "grad_norm": 0.23904232448252624, "learning_rate": 8.159655692455093e-07, "loss": 0.1499, "step": 1129 }, { "epoch": 4.583291139240506, "grad_norm": 0.24825616489329416, "learning_rate": 7.999958845634648e-07, "loss": 0.1644, "step": 1130 }, { "epoch": 4.587341772151898, "grad_norm": 0.23454016457982207, "learning_rate": 7.841808340750478e-07, "loss": 0.113, "step": 1131 }, { "epoch": 4.591392405063291, "grad_norm": 0.22639651528849505, "learning_rate": 7.685205451524869e-07, "loss": 0.1245, "step": 1132 }, { "epoch": 4.595443037974683, "grad_norm": 0.2427163886010715, "learning_rate": 7.530151439216027e-07, "loss": 0.1679, "step": 1133 }, { "epoch": 4.599493670886076, "grad_norm": 0.23616379173132862, "learning_rate": 7.376647552607675e-07, "loss": 0.1557, "step": 1134 }, { "epoch": 4.603544303797468, "grad_norm": 0.23202442697988554, "learning_rate": 7.224695027998963e-07, "loss": 0.126, "step": 1135 }, { "epoch": 4.6075949367088604, "grad_norm": 0.23059942411870465, "learning_rate": 7.07429508919466e-07, "loss": 0.1664, "step": 1136 }, { "epoch": 4.611645569620253, "grad_norm": 0.24941688636130052, "learning_rate": 6.925448947495206e-07, "loss": 0.1432, "step": 1137 }, { "epoch": 4.6156962025316455, "grad_norm": 0.23143001373682703, "learning_rate": 6.778157801686936e-07, "loss": 0.1369, "step": 1138 }, { "epoch": 4.619746835443038, "grad_norm": 0.24410653758318196, "learning_rate": 6.632422838032515e-07, "loss": 0.1569, "step": 1139 }, { "epoch": 4.6237974683544305, "grad_norm": 0.2251205486329122, "learning_rate": 6.488245230261281e-07, "loss": 0.1345, "step": 1140 }, { "epoch": 4.627848101265823, "grad_norm": 0.23377454756986832, "learning_rate": 6.345626139559868e-07, "loss": 0.1598, "step": 1141 }, { "epoch": 4.6318987341772155, "grad_norm": 0.2361701419997191, "learning_rate": 6.204566714562866e-07, "loss": 0.1242, "step": 1142 }, { "epoch": 4.635949367088608, "grad_norm": 0.2469449217989458, "learning_rate": 6.06506809134344e-07, "loss": 0.1449, "step": 1143 }, { "epoch": 4.64, "grad_norm": 0.2338315360985314, "learning_rate": 5.927131393404373e-07, "loss": 0.1402, "step": 1144 }, { "epoch": 4.644050632911393, "grad_norm": 0.2323581929639781, "learning_rate": 5.790757731668817e-07, "loss": 0.1549, "step": 1145 }, { "epoch": 4.648101265822785, "grad_norm": 0.24772147773179456, "learning_rate": 5.655948204471507e-07, "loss": 0.1408, "step": 1146 }, { "epoch": 4.652151898734177, "grad_norm": 0.23890063068429532, "learning_rate": 5.522703897549875e-07, "loss": 0.1473, "step": 1147 }, { "epoch": 4.65620253164557, "grad_norm": 0.2476840192096612, "learning_rate": 5.391025884035239e-07, "loss": 0.1557, "step": 1148 }, { "epoch": 4.660253164556962, "grad_norm": 0.24016907675370217, "learning_rate": 5.260915224444207e-07, "loss": 0.1559, "step": 1149 }, { "epoch": 4.664303797468355, "grad_norm": 0.23835214487848153, "learning_rate": 5.132372966670129e-07, "loss": 0.1386, "step": 1150 }, { "epoch": 4.668354430379747, "grad_norm": 0.23807159410317136, "learning_rate": 5.005400145974704e-07, "loss": 0.1397, "step": 1151 }, { "epoch": 4.672405063291139, "grad_norm": 0.2344483103253217, "learning_rate": 4.879997784979562e-07, "loss": 0.1485, "step": 1152 }, { "epoch": 4.676455696202532, "grad_norm": 0.2253589131312874, "learning_rate": 4.7561668936580984e-07, "loss": 0.1254, "step": 1153 }, { "epoch": 4.680506329113924, "grad_norm": 0.22692241845715774, "learning_rate": 4.6339084693272306e-07, "loss": 0.1208, "step": 1154 }, { "epoch": 4.684556962025317, "grad_norm": 0.23181887576176557, "learning_rate": 4.5132234966395847e-07, "loss": 0.1448, "step": 1155 }, { "epoch": 4.688607594936709, "grad_norm": 0.24034498960853065, "learning_rate": 4.3941129475752795e-07, "loss": 0.1618, "step": 1156 }, { "epoch": 4.692658227848101, "grad_norm": 0.237528052898905, "learning_rate": 4.27657778143431e-07, "loss": 0.1498, "step": 1157 }, { "epoch": 4.696708860759494, "grad_norm": 0.22597622740520265, "learning_rate": 4.1606189448287757e-07, "loss": 0.1467, "step": 1158 }, { "epoch": 4.700759493670886, "grad_norm": 0.2297701115133076, "learning_rate": 4.046237371675177e-07, "loss": 0.1505, "step": 1159 }, { "epoch": 4.704810126582278, "grad_norm": 0.22510872940162144, "learning_rate": 3.9334339831869963e-07, "loss": 0.1282, "step": 1160 }, { "epoch": 4.708860759493671, "grad_norm": 0.2328172181260304, "learning_rate": 3.8222096878671955e-07, "loss": 0.1224, "step": 1161 }, { "epoch": 4.712911392405063, "grad_norm": 0.22675696270305162, "learning_rate": 3.7125653815009545e-07, "loss": 0.1187, "step": 1162 }, { "epoch": 4.716962025316455, "grad_norm": 0.23214401259279263, "learning_rate": 3.6045019471484974e-07, "loss": 0.1344, "step": 1163 }, { "epoch": 4.721012658227848, "grad_norm": 0.22925962442286085, "learning_rate": 3.498020255137813e-07, "loss": 0.1319, "step": 1164 }, { "epoch": 4.72506329113924, "grad_norm": 0.2401494275547872, "learning_rate": 3.393121163057811e-07, "loss": 0.1354, "step": 1165 }, { "epoch": 4.729113924050633, "grad_norm": 0.22478260765257105, "learning_rate": 3.289805515751399e-07, "loss": 0.1443, "step": 1166 }, { "epoch": 4.733164556962025, "grad_norm": 0.24898525606177904, "learning_rate": 3.188074145308573e-07, "loss": 0.1477, "step": 1167 }, { "epoch": 4.737215189873417, "grad_norm": 0.22220602875951562, "learning_rate": 3.087927871059804e-07, "loss": 0.1403, "step": 1168 }, { "epoch": 4.74126582278481, "grad_norm": 0.24858067544997386, "learning_rate": 2.989367499569418e-07, "loss": 0.1488, "step": 1169 }, { "epoch": 4.745316455696202, "grad_norm": 0.23396487698407403, "learning_rate": 2.8923938246290917e-07, "loss": 0.1277, "step": 1170 }, { "epoch": 4.749367088607595, "grad_norm": 0.24079404730294326, "learning_rate": 2.7970076272514804e-07, "loss": 0.153, "step": 1171 }, { "epoch": 4.7534177215189874, "grad_norm": 0.2192154228764998, "learning_rate": 2.703209675663887e-07, "loss": 0.1252, "step": 1172 }, { "epoch": 4.7574683544303795, "grad_norm": 0.2288480206405283, "learning_rate": 2.6110007253021374e-07, "loss": 0.1601, "step": 1173 }, { "epoch": 4.7615189873417725, "grad_norm": 0.23764811608159905, "learning_rate": 2.520381518804471e-07, "loss": 0.157, "step": 1174 }, { "epoch": 4.7655696202531646, "grad_norm": 0.23641317772132653, "learning_rate": 2.4313527860054585e-07, "loss": 0.1385, "step": 1175 }, { "epoch": 4.769620253164557, "grad_norm": 0.23837229305983426, "learning_rate": 2.343915243930317e-07, "loss": 0.1441, "step": 1176 }, { "epoch": 4.77367088607595, "grad_norm": 0.23441313990620863, "learning_rate": 2.2580695967889367e-07, "loss": 0.1391, "step": 1177 }, { "epoch": 4.777721518987342, "grad_norm": 0.23050277141661826, "learning_rate": 2.1738165359704189e-07, "loss": 0.1328, "step": 1178 }, { "epoch": 4.781772151898734, "grad_norm": 0.22827036523271177, "learning_rate": 2.0911567400373257e-07, "loss": 0.1529, "step": 1179 }, { "epoch": 4.785822784810127, "grad_norm": 0.24378696254448562, "learning_rate": 2.0100908747202607e-07, "loss": 0.1551, "step": 1180 }, { "epoch": 4.789873417721519, "grad_norm": 0.23451018819025415, "learning_rate": 1.9306195929125638e-07, "loss": 0.1268, "step": 1181 }, { "epoch": 4.793924050632912, "grad_norm": 0.2270003315535884, "learning_rate": 1.8527435346650247e-07, "loss": 0.1287, "step": 1182 }, { "epoch": 4.797974683544304, "grad_norm": 0.24613874083125378, "learning_rate": 1.7764633271807108e-07, "loss": 0.1303, "step": 1183 }, { "epoch": 4.802025316455696, "grad_norm": 0.22772463800765677, "learning_rate": 1.7017795848099262e-07, "loss": 0.1528, "step": 1184 }, { "epoch": 4.806075949367089, "grad_norm": 0.23977785053574008, "learning_rate": 1.6286929090452596e-07, "loss": 0.1199, "step": 1185 }, { "epoch": 4.810126582278481, "grad_norm": 0.23380087679828385, "learning_rate": 1.557203888516745e-07, "loss": 0.1352, "step": 1186 }, { "epoch": 4.814177215189874, "grad_norm": 0.2437347484695611, "learning_rate": 1.487313098987131e-07, "loss": 0.146, "step": 1187 }, { "epoch": 4.818227848101266, "grad_norm": 0.23649990925066786, "learning_rate": 1.4190211033472402e-07, "loss": 0.1348, "step": 1188 }, { "epoch": 4.822278481012658, "grad_norm": 0.2340947386389473, "learning_rate": 1.3523284516113955e-07, "loss": 0.1432, "step": 1189 }, { "epoch": 4.826329113924051, "grad_norm": 0.23140158768214397, "learning_rate": 1.2872356809130682e-07, "loss": 0.1326, "step": 1190 }, { "epoch": 4.830379746835443, "grad_norm": 0.24022471517319452, "learning_rate": 1.2237433155004807e-07, "loss": 0.1598, "step": 1191 }, { "epoch": 4.834430379746835, "grad_norm": 0.24558271828672043, "learning_rate": 1.1618518667323886e-07, "loss": 0.1598, "step": 1192 }, { "epoch": 4.838481012658228, "grad_norm": 0.2278752885439251, "learning_rate": 1.1015618330740385e-07, "loss": 0.1169, "step": 1193 }, { "epoch": 4.84253164556962, "grad_norm": 0.22958064406873735, "learning_rate": 1.042873700093061e-07, "loss": 0.1532, "step": 1194 }, { "epoch": 4.846582278481012, "grad_norm": 0.24014371723349107, "learning_rate": 9.857879404556291e-08, "loss": 0.1532, "step": 1195 }, { "epoch": 4.850632911392405, "grad_norm": 0.23183963820071213, "learning_rate": 9.303050139225722e-08, "loss": 0.144, "step": 1196 }, { "epoch": 4.854683544303797, "grad_norm": 0.23438078977863505, "learning_rate": 8.76425367345779e-08, "loss": 0.1411, "step": 1197 }, { "epoch": 4.85873417721519, "grad_norm": 0.24226567800218582, "learning_rate": 8.241494346644897e-08, "loss": 0.1461, "step": 1198 }, { "epoch": 4.862784810126582, "grad_norm": 0.24765547954957412, "learning_rate": 7.734776369019204e-08, "loss": 0.1536, "step": 1199 }, { "epoch": 4.866835443037974, "grad_norm": 0.23919430832131902, "learning_rate": 7.244103821617332e-08, "loss": 0.1311, "step": 1200 }, { "epoch": 4.870886075949367, "grad_norm": 0.23826315889623517, "learning_rate": 6.769480656248606e-08, "loss": 0.1243, "step": 1201 }, { "epoch": 4.874936708860759, "grad_norm": 0.2504955144078034, "learning_rate": 6.310910695462635e-08, "loss": 0.1468, "step": 1202 }, { "epoch": 4.878987341772152, "grad_norm": 0.23403277363189096, "learning_rate": 5.8683976325191185e-08, "loss": 0.1361, "step": 1203 }, { "epoch": 4.883037974683544, "grad_norm": 0.2512315096378766, "learning_rate": 5.4419450313571984e-08, "loss": 0.1351, "step": 1204 }, { "epoch": 4.8870886075949365, "grad_norm": 0.23832097649022294, "learning_rate": 5.031556326567488e-08, "loss": 0.1504, "step": 1205 }, { "epoch": 4.891139240506329, "grad_norm": 0.23577827932240675, "learning_rate": 4.637234823364312e-08, "loss": 0.1325, "step": 1206 }, { "epoch": 4.8951898734177215, "grad_norm": 0.24321503661123633, "learning_rate": 4.258983697558838e-08, "loss": 0.1242, "step": 1207 }, { "epoch": 4.899240506329114, "grad_norm": 0.2275465687088214, "learning_rate": 3.896805995533548e-08, "loss": 0.1334, "step": 1208 }, { "epoch": 4.9032911392405065, "grad_norm": 0.23817313680246693, "learning_rate": 3.550704634218028e-08, "loss": 0.1225, "step": 1209 }, { "epoch": 4.907341772151899, "grad_norm": 0.2377941953762549, "learning_rate": 3.2206824010647676e-08, "loss": 0.1408, "step": 1210 }, { "epoch": 4.911392405063291, "grad_norm": 0.23582720441100335, "learning_rate": 2.9067419540278476e-08, "loss": 0.1492, "step": 1211 }, { "epoch": 4.915443037974684, "grad_norm": 0.23769583249353501, "learning_rate": 2.6088858215400638e-08, "loss": 0.1579, "step": 1212 }, { "epoch": 4.919493670886076, "grad_norm": 0.24473133703979608, "learning_rate": 2.3271164024940564e-08, "loss": 0.1528, "step": 1213 }, { "epoch": 4.923544303797469, "grad_norm": 0.24281832930454497, "learning_rate": 2.061435966221881e-08, "loss": 0.1562, "step": 1214 }, { "epoch": 4.927594936708861, "grad_norm": 0.23144141843319643, "learning_rate": 1.811846652477245e-08, "loss": 0.16, "step": 1215 }, { "epoch": 4.931645569620253, "grad_norm": 0.24447899799630252, "learning_rate": 1.5783504714184106e-08, "loss": 0.1348, "step": 1216 }, { "epoch": 4.935696202531646, "grad_norm": 0.23572242261357207, "learning_rate": 1.360949303591097e-08, "loss": 0.1484, "step": 1217 }, { "epoch": 4.939746835443038, "grad_norm": 0.23229453697490482, "learning_rate": 1.1596448999144916e-08, "loss": 0.1465, "step": 1218 }, { "epoch": 4.943797468354431, "grad_norm": 0.24860356122996013, "learning_rate": 9.744388816668172e-09, "loss": 0.1535, "step": 1219 }, { "epoch": 4.947848101265823, "grad_norm": 0.23795452610222598, "learning_rate": 8.05332740472009e-09, "loss": 0.1658, "step": 1220 }, { "epoch": 4.951898734177215, "grad_norm": 0.2358201303290236, "learning_rate": 6.523278382872811e-09, "loss": 0.1421, "step": 1221 }, { "epoch": 4.955949367088608, "grad_norm": 0.2255004055863859, "learning_rate": 5.15425407393133e-09, "loss": 0.1425, "step": 1222 }, { "epoch": 4.96, "grad_norm": 0.23058326248552638, "learning_rate": 3.94626550383137e-09, "loss": 0.1133, "step": 1223 }, { "epoch": 4.964050632911392, "grad_norm": 0.2368289501688177, "learning_rate": 2.899322401546112e-09, "loss": 0.1792, "step": 1224 }, { "epoch": 4.968101265822785, "grad_norm": 0.2461744734739615, "learning_rate": 2.013433199010706e-09, "loss": 0.1206, "step": 1225 }, { "epoch": 4.972151898734177, "grad_norm": 0.23451528188546278, "learning_rate": 1.2886050310556563e-09, "loss": 0.1301, "step": 1226 }, { "epoch": 4.976202531645569, "grad_norm": 0.22355435215913785, "learning_rate": 7.248437353468695e-10, "loss": 0.1401, "step": 1227 }, { "epoch": 4.980253164556962, "grad_norm": 0.24154848812838428, "learning_rate": 3.221538523412449e-10, "loss": 0.1331, "step": 1228 }, { "epoch": 4.984303797468354, "grad_norm": 0.2272356964215785, "learning_rate": 8.053862524670663e-11, "loss": 0.125, "step": 1229 }, { "epoch": 4.988354430379747, "grad_norm": 0.24580958015212298, "learning_rate": 0.0, "loss": 0.1381, "step": 1230 }, { "epoch": 4.988354430379747, "step": 1230, "total_flos": 2.293885687520297e+18, "train_loss": 0.37534874780633587, "train_runtime": 84608.2663, "train_samples_per_second": 1.867, "train_steps_per_second": 0.015 } ], "logging_steps": 1, "max_steps": 1230, "num_input_tokens_seen": 0, "num_train_epochs": 5, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 2.293885687520297e+18, "train_batch_size": 1, "trial_name": null, "trial_params": null }