{ "best_metric": null, "best_model_checkpoint": null, "epoch": 4.982278481012658, "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": 6.55906753796316, "learning_rate": 3.2520325203252037e-07, "loss": 1.0784, "step": 1 }, { "epoch": 0.00810126582278481, "grad_norm": 8.177127864170789, "learning_rate": 6.504065040650407e-07, "loss": 1.1843, "step": 2 }, { "epoch": 0.012151898734177215, "grad_norm": 6.894239943320399, "learning_rate": 9.75609756097561e-07, "loss": 1.0982, "step": 3 }, { "epoch": 0.01620253164556962, "grad_norm": 6.434380476523288, "learning_rate": 1.3008130081300815e-06, "loss": 1.0468, "step": 4 }, { "epoch": 0.020253164556962026, "grad_norm": 6.420859739935833, "learning_rate": 1.6260162601626018e-06, "loss": 1.068, "step": 5 }, { "epoch": 0.02430379746835443, "grad_norm": 5.8212038461429465, "learning_rate": 1.951219512195122e-06, "loss": 1.0242, "step": 6 }, { "epoch": 0.028354430379746835, "grad_norm": 5.024144763113275, "learning_rate": 2.2764227642276426e-06, "loss": 1.0178, "step": 7 }, { "epoch": 0.03240506329113924, "grad_norm": 4.678792483833032, "learning_rate": 2.601626016260163e-06, "loss": 1.0161, "step": 8 }, { "epoch": 0.03645569620253165, "grad_norm": 2.617194271830562, "learning_rate": 2.926829268292683e-06, "loss": 0.9811, "step": 9 }, { "epoch": 0.04050632911392405, "grad_norm": 2.4022114429530137, "learning_rate": 3.2520325203252037e-06, "loss": 0.9936, "step": 10 }, { "epoch": 0.044556962025316456, "grad_norm": 2.177931700035122, "learning_rate": 3.577235772357724e-06, "loss": 0.9741, "step": 11 }, { "epoch": 0.04860759493670886, "grad_norm": 4.312452591694395, "learning_rate": 3.902439024390244e-06, "loss": 0.9714, "step": 12 }, { "epoch": 0.052658227848101265, "grad_norm": 4.59772277714488, "learning_rate": 4.227642276422765e-06, "loss": 0.9395, "step": 13 }, { "epoch": 0.05670886075949367, "grad_norm": 4.51533103022075, "learning_rate": 4.552845528455285e-06, "loss": 0.9357, "step": 14 }, { "epoch": 0.060759493670886074, "grad_norm": 4.361481521449638, "learning_rate": 4.8780487804878055e-06, "loss": 0.9173, "step": 15 }, { "epoch": 0.06481012658227848, "grad_norm": 3.5313976701818235, "learning_rate": 5.203252032520326e-06, "loss": 0.8976, "step": 16 }, { "epoch": 0.06886075949367089, "grad_norm": 3.2131718695061537, "learning_rate": 5.528455284552846e-06, "loss": 0.8954, "step": 17 }, { "epoch": 0.0729113924050633, "grad_norm": 3.0895092258236296, "learning_rate": 5.853658536585366e-06, "loss": 0.8916, "step": 18 }, { "epoch": 0.0769620253164557, "grad_norm": 2.5724155319920152, "learning_rate": 6.178861788617887e-06, "loss": 0.8993, "step": 19 }, { "epoch": 0.0810126582278481, "grad_norm": 2.228283102456515, "learning_rate": 6.504065040650407e-06, "loss": 0.8862, "step": 20 }, { "epoch": 0.08506329113924051, "grad_norm": 2.09195497924738, "learning_rate": 6.829268292682928e-06, "loss": 0.8797, "step": 21 }, { "epoch": 0.08911392405063291, "grad_norm": 2.2449258494024145, "learning_rate": 7.154471544715448e-06, "loss": 0.8458, "step": 22 }, { "epoch": 0.09316455696202532, "grad_norm": 2.0924619410829712, "learning_rate": 7.4796747967479676e-06, "loss": 0.8283, "step": 23 }, { "epoch": 0.09721518987341772, "grad_norm": 1.9674440675183225, "learning_rate": 7.804878048780489e-06, "loss": 0.7691, "step": 24 }, { "epoch": 0.10126582278481013, "grad_norm": 1.7841387779991345, "learning_rate": 8.130081300813009e-06, "loss": 0.8202, "step": 25 }, { "epoch": 0.10531645569620253, "grad_norm": 1.3593221784486276, "learning_rate": 8.45528455284553e-06, "loss": 0.8362, "step": 26 }, { "epoch": 0.10936708860759493, "grad_norm": 1.543466103115967, "learning_rate": 8.78048780487805e-06, "loss": 0.8064, "step": 27 }, { "epoch": 0.11341772151898734, "grad_norm": 1.7792793129433424, "learning_rate": 9.10569105691057e-06, "loss": 0.8305, "step": 28 }, { "epoch": 0.11746835443037974, "grad_norm": 1.6887168562720756, "learning_rate": 9.43089430894309e-06, "loss": 0.812, "step": 29 }, { "epoch": 0.12151898734177215, "grad_norm": 1.12531213677336, "learning_rate": 9.756097560975611e-06, "loss": 0.768, "step": 30 }, { "epoch": 0.12556962025316457, "grad_norm": 0.9725371557271467, "learning_rate": 1.008130081300813e-05, "loss": 0.7807, "step": 31 }, { "epoch": 0.12962025316455697, "grad_norm": 1.1570393698882193, "learning_rate": 1.0406504065040652e-05, "loss": 0.7495, "step": 32 }, { "epoch": 0.13367088607594937, "grad_norm": 1.2428876033158116, "learning_rate": 1.0731707317073172e-05, "loss": 0.7926, "step": 33 }, { "epoch": 0.13772151898734178, "grad_norm": 0.9540414485597466, "learning_rate": 1.1056910569105692e-05, "loss": 0.7797, "step": 34 }, { "epoch": 0.14177215189873418, "grad_norm": 0.7191075783633027, "learning_rate": 1.1382113821138213e-05, "loss": 0.7498, "step": 35 }, { "epoch": 0.1458227848101266, "grad_norm": 0.9805508915588987, "learning_rate": 1.1707317073170731e-05, "loss": 0.7426, "step": 36 }, { "epoch": 0.149873417721519, "grad_norm": 0.8243971146659146, "learning_rate": 1.2032520325203254e-05, "loss": 0.7304, "step": 37 }, { "epoch": 0.1539240506329114, "grad_norm": 0.6783615243272562, "learning_rate": 1.2357723577235774e-05, "loss": 0.7619, "step": 38 }, { "epoch": 0.1579746835443038, "grad_norm": 0.8042389133574047, "learning_rate": 1.2682926829268294e-05, "loss": 0.739, "step": 39 }, { "epoch": 0.1620253164556962, "grad_norm": 0.8301654253634728, "learning_rate": 1.3008130081300815e-05, "loss": 0.7523, "step": 40 }, { "epoch": 0.1660759493670886, "grad_norm": 0.6676542006777847, "learning_rate": 1.3333333333333333e-05, "loss": 0.74, "step": 41 }, { "epoch": 0.17012658227848101, "grad_norm": 0.7308824701937043, "learning_rate": 1.3658536585365855e-05, "loss": 0.7538, "step": 42 }, { "epoch": 0.17417721518987342, "grad_norm": 0.7014230633122106, "learning_rate": 1.3983739837398376e-05, "loss": 0.7439, "step": 43 }, { "epoch": 0.17822784810126582, "grad_norm": 0.6835472055321833, "learning_rate": 1.4308943089430896e-05, "loss": 0.7638, "step": 44 }, { "epoch": 0.18227848101265823, "grad_norm": 0.6453071646823085, "learning_rate": 1.4634146341463415e-05, "loss": 0.7123, "step": 45 }, { "epoch": 0.18632911392405063, "grad_norm": 0.7267421661572444, "learning_rate": 1.4959349593495935e-05, "loss": 0.7407, "step": 46 }, { "epoch": 0.19037974683544304, "grad_norm": 0.7119959009495763, "learning_rate": 1.528455284552846e-05, "loss": 0.7473, "step": 47 }, { "epoch": 0.19443037974683544, "grad_norm": 0.821397438557946, "learning_rate": 1.5609756097560978e-05, "loss": 0.7353, "step": 48 }, { "epoch": 0.19848101265822785, "grad_norm": 0.6134228257864113, "learning_rate": 1.5934959349593496e-05, "loss": 0.6997, "step": 49 }, { "epoch": 0.20253164556962025, "grad_norm": 0.6680239348994098, "learning_rate": 1.6260162601626018e-05, "loss": 0.7463, "step": 50 }, { "epoch": 0.20658227848101265, "grad_norm": 0.6811939702526176, "learning_rate": 1.6585365853658537e-05, "loss": 0.7376, "step": 51 }, { "epoch": 0.21063291139240506, "grad_norm": 0.6780552015640755, "learning_rate": 1.691056910569106e-05, "loss": 0.7319, "step": 52 }, { "epoch": 0.21468354430379746, "grad_norm": 0.5977650372451817, "learning_rate": 1.7235772357723578e-05, "loss": 0.7178, "step": 53 }, { "epoch": 0.21873417721518987, "grad_norm": 0.6305079528958574, "learning_rate": 1.75609756097561e-05, "loss": 0.7396, "step": 54 }, { "epoch": 0.22278481012658227, "grad_norm": 0.7036838435304729, "learning_rate": 1.788617886178862e-05, "loss": 0.6809, "step": 55 }, { "epoch": 0.22683544303797468, "grad_norm": 0.6300968195869712, "learning_rate": 1.821138211382114e-05, "loss": 0.7469, "step": 56 }, { "epoch": 0.23088607594936708, "grad_norm": 0.6966781457447978, "learning_rate": 1.8536585365853663e-05, "loss": 0.7079, "step": 57 }, { "epoch": 0.23493670886075949, "grad_norm": 0.7330524887619365, "learning_rate": 1.886178861788618e-05, "loss": 0.727, "step": 58 }, { "epoch": 0.2389873417721519, "grad_norm": 0.6129899942255174, "learning_rate": 1.91869918699187e-05, "loss": 0.717, "step": 59 }, { "epoch": 0.2430379746835443, "grad_norm": 0.7429109921309415, "learning_rate": 1.9512195121951222e-05, "loss": 0.729, "step": 60 }, { "epoch": 0.2470886075949367, "grad_norm": 0.8375400597155144, "learning_rate": 1.983739837398374e-05, "loss": 0.7239, "step": 61 }, { "epoch": 0.25113924050632913, "grad_norm": 0.7408215429113356, "learning_rate": 2.016260162601626e-05, "loss": 0.6922, "step": 62 }, { "epoch": 0.25518987341772154, "grad_norm": 0.9302146733036656, "learning_rate": 2.048780487804878e-05, "loss": 0.7015, "step": 63 }, { "epoch": 0.25924050632911394, "grad_norm": 0.7141309345791, "learning_rate": 2.0813008130081303e-05, "loss": 0.6938, "step": 64 }, { "epoch": 0.26329113924050634, "grad_norm": 0.8205592623524216, "learning_rate": 2.1138211382113822e-05, "loss": 0.6902, "step": 65 }, { "epoch": 0.26734177215189875, "grad_norm": 0.7425561887899516, "learning_rate": 2.1463414634146344e-05, "loss": 0.6683, "step": 66 }, { "epoch": 0.27139240506329115, "grad_norm": 0.7735023062334722, "learning_rate": 2.1788617886178863e-05, "loss": 0.726, "step": 67 }, { "epoch": 0.27544303797468356, "grad_norm": 0.8084693644128156, "learning_rate": 2.2113821138211385e-05, "loss": 0.7369, "step": 68 }, { "epoch": 0.27949367088607596, "grad_norm": 0.7553077251831422, "learning_rate": 2.2439024390243907e-05, "loss": 0.731, "step": 69 }, { "epoch": 0.28354430379746837, "grad_norm": 0.717414058988251, "learning_rate": 2.2764227642276426e-05, "loss": 0.7199, "step": 70 }, { "epoch": 0.28759493670886077, "grad_norm": 0.7913547095232868, "learning_rate": 2.3089430894308948e-05, "loss": 0.738, "step": 71 }, { "epoch": 0.2916455696202532, "grad_norm": 0.7682090180634293, "learning_rate": 2.3414634146341463e-05, "loss": 0.7175, "step": 72 }, { "epoch": 0.2956962025316456, "grad_norm": 0.7365537741456074, "learning_rate": 2.3739837398373985e-05, "loss": 0.6968, "step": 73 }, { "epoch": 0.299746835443038, "grad_norm": 0.8118132721477282, "learning_rate": 2.4065040650406507e-05, "loss": 0.6787, "step": 74 }, { "epoch": 0.3037974683544304, "grad_norm": 0.794034759265073, "learning_rate": 2.4390243902439026e-05, "loss": 0.6765, "step": 75 }, { "epoch": 0.3078481012658228, "grad_norm": 0.8607507721852966, "learning_rate": 2.4715447154471548e-05, "loss": 0.7086, "step": 76 }, { "epoch": 0.3118987341772152, "grad_norm": 0.6738707932017615, "learning_rate": 2.5040650406504066e-05, "loss": 0.7231, "step": 77 }, { "epoch": 0.3159493670886076, "grad_norm": 0.8912182199361357, "learning_rate": 2.536585365853659e-05, "loss": 0.7038, "step": 78 }, { "epoch": 0.32, "grad_norm": 0.8200679259658153, "learning_rate": 2.569105691056911e-05, "loss": 0.7074, "step": 79 }, { "epoch": 0.3240506329113924, "grad_norm": 1.048067564919854, "learning_rate": 2.601626016260163e-05, "loss": 0.7183, "step": 80 }, { "epoch": 0.3281012658227848, "grad_norm": 0.7330078723580583, "learning_rate": 2.634146341463415e-05, "loss": 0.7099, "step": 81 }, { "epoch": 0.3321518987341772, "grad_norm": 0.8248507410191741, "learning_rate": 2.6666666666666667e-05, "loss": 0.7203, "step": 82 }, { "epoch": 0.3362025316455696, "grad_norm": 0.793216396252527, "learning_rate": 2.699186991869919e-05, "loss": 0.7148, "step": 83 }, { "epoch": 0.34025316455696203, "grad_norm": 0.7815347387256152, "learning_rate": 2.731707317073171e-05, "loss": 0.6954, "step": 84 }, { "epoch": 0.34430379746835443, "grad_norm": 0.7797872291162511, "learning_rate": 2.764227642276423e-05, "loss": 0.7008, "step": 85 }, { "epoch": 0.34835443037974684, "grad_norm": 0.8070416529126304, "learning_rate": 2.796747967479675e-05, "loss": 0.6943, "step": 86 }, { "epoch": 0.35240506329113924, "grad_norm": 0.7719224496628879, "learning_rate": 2.829268292682927e-05, "loss": 0.6907, "step": 87 }, { "epoch": 0.35645569620253165, "grad_norm": 0.8080977239729854, "learning_rate": 2.8617886178861792e-05, "loss": 0.7247, "step": 88 }, { "epoch": 0.36050632911392405, "grad_norm": 0.903585639890714, "learning_rate": 2.8943089430894314e-05, "loss": 0.671, "step": 89 }, { "epoch": 0.36455696202531646, "grad_norm": 0.6623165837490701, "learning_rate": 2.926829268292683e-05, "loss": 0.7148, "step": 90 }, { "epoch": 0.36860759493670886, "grad_norm": 0.9180139858227524, "learning_rate": 2.959349593495935e-05, "loss": 0.7119, "step": 91 }, { "epoch": 0.37265822784810126, "grad_norm": 0.8069779540236002, "learning_rate": 2.991869918699187e-05, "loss": 0.6942, "step": 92 }, { "epoch": 0.37670886075949367, "grad_norm": 1.0101672422136745, "learning_rate": 3.0243902439024392e-05, "loss": 0.7125, "step": 93 }, { "epoch": 0.3807594936708861, "grad_norm": 0.8863895947923061, "learning_rate": 3.056910569105692e-05, "loss": 0.7115, "step": 94 }, { "epoch": 0.3848101265822785, "grad_norm": 0.8685000313949982, "learning_rate": 3.089430894308943e-05, "loss": 0.724, "step": 95 }, { "epoch": 0.3888607594936709, "grad_norm": 0.8822616325842728, "learning_rate": 3.1219512195121955e-05, "loss": 0.6937, "step": 96 }, { "epoch": 0.3929113924050633, "grad_norm": 0.9842542667969889, "learning_rate": 3.154471544715447e-05, "loss": 0.6889, "step": 97 }, { "epoch": 0.3969620253164557, "grad_norm": 0.8591231955515726, "learning_rate": 3.186991869918699e-05, "loss": 0.7145, "step": 98 }, { "epoch": 0.4010126582278481, "grad_norm": 0.7964642147219994, "learning_rate": 3.2195121951219514e-05, "loss": 0.7091, "step": 99 }, { "epoch": 0.4050632911392405, "grad_norm": 1.017226250268142, "learning_rate": 3.2520325203252037e-05, "loss": 0.702, "step": 100 }, { "epoch": 0.4091139240506329, "grad_norm": 0.9728448910087989, "learning_rate": 3.284552845528456e-05, "loss": 0.705, "step": 101 }, { "epoch": 0.4131645569620253, "grad_norm": 0.9755631243920004, "learning_rate": 3.3170731707317074e-05, "loss": 0.7173, "step": 102 }, { "epoch": 0.4172151898734177, "grad_norm": 0.7850914733509087, "learning_rate": 3.3495934959349596e-05, "loss": 0.7035, "step": 103 }, { "epoch": 0.4212658227848101, "grad_norm": 1.147157201997912, "learning_rate": 3.382113821138212e-05, "loss": 0.684, "step": 104 }, { "epoch": 0.4253164556962025, "grad_norm": 0.8331447024780189, "learning_rate": 3.414634146341463e-05, "loss": 0.6942, "step": 105 }, { "epoch": 0.4293670886075949, "grad_norm": 0.6769518304906164, "learning_rate": 3.4471544715447155e-05, "loss": 0.7413, "step": 106 }, { "epoch": 0.43341772151898733, "grad_norm": 0.8632604516443241, "learning_rate": 3.479674796747968e-05, "loss": 0.702, "step": 107 }, { "epoch": 0.43746835443037974, "grad_norm": 1.2343086750583565, "learning_rate": 3.51219512195122e-05, "loss": 0.6999, "step": 108 }, { "epoch": 0.44151898734177214, "grad_norm": 0.8282431478508638, "learning_rate": 3.544715447154472e-05, "loss": 0.7086, "step": 109 }, { "epoch": 0.44556962025316454, "grad_norm": 1.255253827788659, "learning_rate": 3.577235772357724e-05, "loss": 0.6849, "step": 110 }, { "epoch": 0.44962025316455695, "grad_norm": 0.8141796597960879, "learning_rate": 3.609756097560976e-05, "loss": 0.7037, "step": 111 }, { "epoch": 0.45367088607594935, "grad_norm": 1.0297056117224446, "learning_rate": 3.642276422764228e-05, "loss": 0.7057, "step": 112 }, { "epoch": 0.45772151898734176, "grad_norm": 1.0656138290992434, "learning_rate": 3.67479674796748e-05, "loss": 0.691, "step": 113 }, { "epoch": 0.46177215189873416, "grad_norm": 0.7806424262384258, "learning_rate": 3.7073170731707325e-05, "loss": 0.6798, "step": 114 }, { "epoch": 0.46582278481012657, "grad_norm": 0.9430768613290405, "learning_rate": 3.739837398373984e-05, "loss": 0.677, "step": 115 }, { "epoch": 0.46987341772151897, "grad_norm": 0.8482043875388267, "learning_rate": 3.772357723577236e-05, "loss": 0.7064, "step": 116 }, { "epoch": 0.4739240506329114, "grad_norm": 0.8448634592956497, "learning_rate": 3.804878048780488e-05, "loss": 0.6854, "step": 117 }, { "epoch": 0.4779746835443038, "grad_norm": 0.8928952982909567, "learning_rate": 3.83739837398374e-05, "loss": 0.7101, "step": 118 }, { "epoch": 0.4820253164556962, "grad_norm": 0.9498124398293109, "learning_rate": 3.869918699186992e-05, "loss": 0.7238, "step": 119 }, { "epoch": 0.4860759493670886, "grad_norm": 0.6630898769920707, "learning_rate": 3.9024390243902444e-05, "loss": 0.6821, "step": 120 }, { "epoch": 0.490126582278481, "grad_norm": 0.7821395188219761, "learning_rate": 3.9349593495934966e-05, "loss": 0.6973, "step": 121 }, { "epoch": 0.4941772151898734, "grad_norm": 0.824028720777045, "learning_rate": 3.967479674796748e-05, "loss": 0.6871, "step": 122 }, { "epoch": 0.4982278481012658, "grad_norm": 0.7250690676743418, "learning_rate": 4e-05, "loss": 0.6934, "step": 123 }, { "epoch": 0.5022784810126583, "grad_norm": 0.7499941600233202, "learning_rate": 3.999991946137476e-05, "loss": 0.7024, "step": 124 }, { "epoch": 0.5063291139240507, "grad_norm": 0.8927917989460654, "learning_rate": 3.999967784614766e-05, "loss": 0.7081, "step": 125 }, { "epoch": 0.5103797468354431, "grad_norm": 1.1660924755985085, "learning_rate": 3.9999275156264656e-05, "loss": 0.6684, "step": 126 }, { "epoch": 0.5144303797468355, "grad_norm": 0.6687279260645504, "learning_rate": 3.999871139496895e-05, "loss": 0.6795, "step": 127 }, { "epoch": 0.5184810126582279, "grad_norm": 1.285446589072879, "learning_rate": 3.9997986566800995e-05, "loss": 0.7463, "step": 128 }, { "epoch": 0.5225316455696203, "grad_norm": 0.8871830863006063, "learning_rate": 3.999710067759846e-05, "loss": 0.6976, "step": 129 }, { "epoch": 0.5265822784810127, "grad_norm": 1.0051518366937047, "learning_rate": 3.999605373449617e-05, "loss": 0.7134, "step": 130 }, { "epoch": 0.5306329113924051, "grad_norm": 0.8960073956905854, "learning_rate": 3.9994845745926075e-05, "loss": 0.676, "step": 131 }, { "epoch": 0.5346835443037975, "grad_norm": 0.8447047587494841, "learning_rate": 3.999347672161713e-05, "loss": 0.6801, "step": 132 }, { "epoch": 0.5387341772151899, "grad_norm": 0.7214517127971848, "learning_rate": 3.999194667259528e-05, "loss": 0.686, "step": 133 }, { "epoch": 0.5427848101265823, "grad_norm": 1.0250815230900236, "learning_rate": 3.999025561118334e-05, "loss": 0.6857, "step": 134 }, { "epoch": 0.5468354430379747, "grad_norm": 0.87914880548719, "learning_rate": 3.998840355100086e-05, "loss": 0.7099, "step": 135 }, { "epoch": 0.5508860759493671, "grad_norm": 0.8520086802083101, "learning_rate": 3.998639050696409e-05, "loss": 0.6828, "step": 136 }, { "epoch": 0.5549367088607595, "grad_norm": 0.7508125355512916, "learning_rate": 3.998421649528582e-05, "loss": 0.7133, "step": 137 }, { "epoch": 0.5589873417721519, "grad_norm": 1.1569979326685833, "learning_rate": 3.9981881533475234e-05, "loss": 0.7013, "step": 138 }, { "epoch": 0.5630379746835443, "grad_norm": 0.6225206156910991, "learning_rate": 3.997938564033779e-05, "loss": 0.7131, "step": 139 }, { "epoch": 0.5670886075949367, "grad_norm": 1.0948024179799014, "learning_rate": 3.9976728835975064e-05, "loss": 0.6813, "step": 140 }, { "epoch": 0.5711392405063291, "grad_norm": 0.8867696402003469, "learning_rate": 3.9973911141784605e-05, "loss": 0.6965, "step": 141 }, { "epoch": 0.5751898734177215, "grad_norm": 0.7712989090316954, "learning_rate": 3.997093258045973e-05, "loss": 0.6903, "step": 142 }, { "epoch": 0.579240506329114, "grad_norm": 1.0624208851960832, "learning_rate": 3.996779317598936e-05, "loss": 0.705, "step": 143 }, { "epoch": 0.5832911392405064, "grad_norm": 0.9006377176547724, "learning_rate": 3.996449295365782e-05, "loss": 0.6838, "step": 144 }, { "epoch": 0.5873417721518988, "grad_norm": 0.6289813110760177, "learning_rate": 3.996103194004467e-05, "loss": 0.6984, "step": 145 }, { "epoch": 0.5913924050632912, "grad_norm": 0.8428616647046197, "learning_rate": 3.995741016302441e-05, "loss": 0.7083, "step": 146 }, { "epoch": 0.5954430379746836, "grad_norm": 0.872564544373022, "learning_rate": 3.9953627651766364e-05, "loss": 0.6699, "step": 147 }, { "epoch": 0.599493670886076, "grad_norm": 0.6697252430165167, "learning_rate": 3.9949684436734325e-05, "loss": 0.6969, "step": 148 }, { "epoch": 0.6035443037974684, "grad_norm": 1.0319629532844818, "learning_rate": 3.994558054968643e-05, "loss": 0.7103, "step": 149 }, { "epoch": 0.6075949367088608, "grad_norm": 0.6333097210408777, "learning_rate": 3.994131602367481e-05, "loss": 0.6659, "step": 150 }, { "epoch": 0.6116455696202532, "grad_norm": 0.9215634177234153, "learning_rate": 3.9936890893045376e-05, "loss": 0.7, "step": 151 }, { "epoch": 0.6156962025316456, "grad_norm": 0.8237431684113901, "learning_rate": 3.993230519343752e-05, "loss": 0.6966, "step": 152 }, { "epoch": 0.619746835443038, "grad_norm": 0.5810009641869288, "learning_rate": 3.992755896178383e-05, "loss": 0.6866, "step": 153 }, { "epoch": 0.6237974683544304, "grad_norm": 0.6506018481673321, "learning_rate": 3.992265223630981e-05, "loss": 0.7082, "step": 154 }, { "epoch": 0.6278481012658228, "grad_norm": 0.6347262420569214, "learning_rate": 3.991758505653355e-05, "loss": 0.6958, "step": 155 }, { "epoch": 0.6318987341772152, "grad_norm": 0.551459080594817, "learning_rate": 3.991235746326543e-05, "loss": 0.6951, "step": 156 }, { "epoch": 0.6359493670886076, "grad_norm": 0.6317312398838507, "learning_rate": 3.9906969498607745e-05, "loss": 0.7012, "step": 157 }, { "epoch": 0.64, "grad_norm": 0.5871190583196279, "learning_rate": 3.990142120595444e-05, "loss": 0.6861, "step": 158 }, { "epoch": 0.6440506329113924, "grad_norm": 0.6666005740267396, "learning_rate": 3.98957126299907e-05, "loss": 0.6693, "step": 159 }, { "epoch": 0.6481012658227848, "grad_norm": 0.599233461150876, "learning_rate": 3.9889843816692596e-05, "loss": 0.7087, "step": 160 }, { "epoch": 0.6521518987341772, "grad_norm": 0.6785937011994412, "learning_rate": 3.9883814813326766e-05, "loss": 0.6611, "step": 161 }, { "epoch": 0.6562025316455696, "grad_norm": 0.6929555246056799, "learning_rate": 3.9877625668449956e-05, "loss": 0.6913, "step": 162 }, { "epoch": 0.660253164556962, "grad_norm": 0.5849567768830223, "learning_rate": 3.98712764319087e-05, "loss": 0.6958, "step": 163 }, { "epoch": 0.6643037974683544, "grad_norm": 0.6582397322256488, "learning_rate": 3.9864767154838864e-05, "loss": 0.6835, "step": 164 }, { "epoch": 0.6683544303797468, "grad_norm": 0.6062906701181775, "learning_rate": 3.9858097889665277e-05, "loss": 0.6815, "step": 165 }, { "epoch": 0.6724050632911392, "grad_norm": 0.6198779173603618, "learning_rate": 3.985126869010129e-05, "loss": 0.662, "step": 166 }, { "epoch": 0.6764556962025317, "grad_norm": 0.6876692891986292, "learning_rate": 3.984427961114833e-05, "loss": 0.6948, "step": 167 }, { "epoch": 0.6805063291139241, "grad_norm": 0.5352505946015318, "learning_rate": 3.9837130709095475e-05, "loss": 0.6795, "step": 168 }, { "epoch": 0.6845569620253165, "grad_norm": 0.6573263530943126, "learning_rate": 3.982982204151901e-05, "loss": 0.7174, "step": 169 }, { "epoch": 0.6886075949367089, "grad_norm": 0.5355443801411851, "learning_rate": 3.982235366728193e-05, "loss": 0.6844, "step": 170 }, { "epoch": 0.6926582278481013, "grad_norm": 0.5976448807283863, "learning_rate": 3.9814725646533505e-05, "loss": 0.6871, "step": 171 }, { "epoch": 0.6967088607594937, "grad_norm": 0.5918510113524478, "learning_rate": 3.9806938040708746e-05, "loss": 0.6989, "step": 172 }, { "epoch": 0.7007594936708861, "grad_norm": 0.7510446754376551, "learning_rate": 3.9798990912527976e-05, "loss": 0.6849, "step": 173 }, { "epoch": 0.7048101265822785, "grad_norm": 0.5137261538910898, "learning_rate": 3.979088432599627e-05, "loss": 0.6877, "step": 174 }, { "epoch": 0.7088607594936709, "grad_norm": 0.6674565950190039, "learning_rate": 3.9782618346402964e-05, "loss": 0.672, "step": 175 }, { "epoch": 0.7129113924050633, "grad_norm": 0.5118206528387398, "learning_rate": 3.977419304032111e-05, "loss": 0.6956, "step": 176 }, { "epoch": 0.7169620253164557, "grad_norm": 0.6960433862067021, "learning_rate": 3.976560847560697e-05, "loss": 0.6541, "step": 177 }, { "epoch": 0.7210126582278481, "grad_norm": 0.5285223677433962, "learning_rate": 3.9756864721399456e-05, "loss": 0.6763, "step": 178 }, { "epoch": 0.7250632911392405, "grad_norm": 0.5636911613931772, "learning_rate": 3.974796184811956e-05, "loss": 0.6687, "step": 179 }, { "epoch": 0.7291139240506329, "grad_norm": 0.5372229029513075, "learning_rate": 3.973889992746979e-05, "loss": 0.6806, "step": 180 }, { "epoch": 0.7331645569620253, "grad_norm": 0.5616726547098868, "learning_rate": 3.972967903243361e-05, "loss": 0.6777, "step": 181 }, { "epoch": 0.7372151898734177, "grad_norm": 0.5537665329725407, "learning_rate": 3.972029923727486e-05, "loss": 0.6605, "step": 182 }, { "epoch": 0.7412658227848101, "grad_norm": 0.6155054595939454, "learning_rate": 3.971076061753709e-05, "loss": 0.6651, "step": 183 }, { "epoch": 0.7453164556962025, "grad_norm": 0.5500077681770749, "learning_rate": 3.9701063250043066e-05, "loss": 0.6605, "step": 184 }, { "epoch": 0.7493670886075949, "grad_norm": 0.6658689297478837, "learning_rate": 3.969120721289402e-05, "loss": 0.6948, "step": 185 }, { "epoch": 0.7534177215189873, "grad_norm": 0.6214282733833033, "learning_rate": 3.9681192585469146e-05, "loss": 0.6992, "step": 186 }, { "epoch": 0.7574683544303797, "grad_norm": 0.5798486191203734, "learning_rate": 3.9671019448424865e-05, "loss": 0.6852, "step": 187 }, { "epoch": 0.7615189873417721, "grad_norm": 0.5615231059243821, "learning_rate": 3.966068788369422e-05, "loss": 0.6935, "step": 188 }, { "epoch": 0.7655696202531646, "grad_norm": 0.5923753148051899, "learning_rate": 3.965019797448622e-05, "loss": 0.667, "step": 189 }, { "epoch": 0.769620253164557, "grad_norm": 0.5640068712728243, "learning_rate": 3.963954980528515e-05, "loss": 0.6784, "step": 190 }, { "epoch": 0.7736708860759494, "grad_norm": 0.5741876545177157, "learning_rate": 3.9628743461849905e-05, "loss": 0.6556, "step": 191 }, { "epoch": 0.7777215189873418, "grad_norm": 0.7442361540934168, "learning_rate": 3.961777903121329e-05, "loss": 0.6844, "step": 192 }, { "epoch": 0.7817721518987342, "grad_norm": 0.6397582584596336, "learning_rate": 3.960665660168131e-05, "loss": 0.6727, "step": 193 }, { "epoch": 0.7858227848101266, "grad_norm": 0.6208477063157973, "learning_rate": 3.9595376262832485e-05, "loss": 0.6974, "step": 194 }, { "epoch": 0.789873417721519, "grad_norm": 0.62364726805141, "learning_rate": 3.9583938105517127e-05, "loss": 0.6717, "step": 195 }, { "epoch": 0.7939240506329114, "grad_norm": 1.1665355009440228, "learning_rate": 3.957234222185657e-05, "loss": 0.7041, "step": 196 }, { "epoch": 0.7979746835443038, "grad_norm": 0.7041754815675705, "learning_rate": 3.9560588705242474e-05, "loss": 0.6842, "step": 197 }, { "epoch": 0.8020253164556962, "grad_norm": 0.6664389883605214, "learning_rate": 3.954867765033605e-05, "loss": 0.6391, "step": 198 }, { "epoch": 0.8060759493670886, "grad_norm": 0.6044947064706115, "learning_rate": 3.953660915306728e-05, "loss": 0.7249, "step": 199 }, { "epoch": 0.810126582278481, "grad_norm": 0.5365283956009281, "learning_rate": 3.952438331063419e-05, "loss": 0.6889, "step": 200 }, { "epoch": 0.8141772151898734, "grad_norm": 0.6140781482590886, "learning_rate": 3.951200022150205e-05, "loss": 0.7139, "step": 201 }, { "epoch": 0.8182278481012658, "grad_norm": 0.4939108507586191, "learning_rate": 3.949945998540253e-05, "loss": 0.6905, "step": 202 }, { "epoch": 0.8222784810126582, "grad_norm": 0.5546872212048728, "learning_rate": 3.9486762703332993e-05, "loss": 0.6796, "step": 203 }, { "epoch": 0.8263291139240506, "grad_norm": 0.6221813330781749, "learning_rate": 3.947390847755559e-05, "loss": 0.708, "step": 204 }, { "epoch": 0.830379746835443, "grad_norm": 2.144622876161739, "learning_rate": 3.946089741159648e-05, "loss": 0.6964, "step": 205 }, { "epoch": 0.8344303797468354, "grad_norm": 0.7519654766187243, "learning_rate": 3.944772961024501e-05, "loss": 0.6829, "step": 206 }, { "epoch": 0.8384810126582278, "grad_norm": 2.601874678104312, "learning_rate": 3.943440517955285e-05, "loss": 0.6906, "step": 207 }, { "epoch": 0.8425316455696202, "grad_norm": 1.0299999411355698, "learning_rate": 3.9420924226833126e-05, "loss": 0.7178, "step": 208 }, { "epoch": 0.8465822784810126, "grad_norm": 0.8998736181665027, "learning_rate": 3.9407286860659566e-05, "loss": 0.6932, "step": 209 }, { "epoch": 0.850632911392405, "grad_norm": 0.8882069233053971, "learning_rate": 3.9393493190865657e-05, "loss": 0.6719, "step": 210 }, { "epoch": 0.8546835443037974, "grad_norm": 0.8986956903850762, "learning_rate": 3.937954332854371e-05, "loss": 0.6882, "step": 211 }, { "epoch": 0.8587341772151899, "grad_norm": 0.9890584479228643, "learning_rate": 3.9365437386044016e-05, "loss": 0.6773, "step": 212 }, { "epoch": 0.8627848101265823, "grad_norm": 0.9065552263165191, "learning_rate": 3.935117547697387e-05, "loss": 0.6957, "step": 213 }, { "epoch": 0.8668354430379747, "grad_norm": 0.9354214096001117, "learning_rate": 3.933675771619675e-05, "loss": 0.6665, "step": 214 }, { "epoch": 0.8708860759493671, "grad_norm": 0.8966649701850935, "learning_rate": 3.932218421983131e-05, "loss": 0.6776, "step": 215 }, { "epoch": 0.8749367088607595, "grad_norm": 0.6672732747052644, "learning_rate": 3.9307455105250484e-05, "loss": 0.6715, "step": 216 }, { "epoch": 0.8789873417721519, "grad_norm": 0.6052678967218981, "learning_rate": 3.929257049108054e-05, "loss": 0.6711, "step": 217 }, { "epoch": 0.8830379746835443, "grad_norm": 0.6536016213218108, "learning_rate": 3.927753049720011e-05, "loss": 0.6587, "step": 218 }, { "epoch": 0.8870886075949367, "grad_norm": 0.6072006263082811, "learning_rate": 3.9262335244739234e-05, "loss": 0.6985, "step": 219 }, { "epoch": 0.8911392405063291, "grad_norm": 0.7321040819492437, "learning_rate": 3.92469848560784e-05, "loss": 0.6943, "step": 220 }, { "epoch": 0.8951898734177215, "grad_norm": 0.7339936939476983, "learning_rate": 3.923147945484751e-05, "loss": 0.6439, "step": 221 }, { "epoch": 0.8992405063291139, "grad_norm": 0.7472419205728422, "learning_rate": 3.9215819165924956e-05, "loss": 0.705, "step": 222 }, { "epoch": 0.9032911392405063, "grad_norm": 0.7621822827574508, "learning_rate": 3.920000411543654e-05, "loss": 0.6681, "step": 223 }, { "epoch": 0.9073417721518987, "grad_norm": 0.7088706336642184, "learning_rate": 3.9184034430754495e-05, "loss": 0.7039, "step": 224 }, { "epoch": 0.9113924050632911, "grad_norm": 0.7302897714835913, "learning_rate": 3.916791024049648e-05, "loss": 0.6465, "step": 225 }, { "epoch": 0.9154430379746835, "grad_norm": 2.1078697649330906, "learning_rate": 3.91516316745245e-05, "loss": 0.6791, "step": 226 }, { "epoch": 0.9194936708860759, "grad_norm": 1.091594693747587, "learning_rate": 3.913519886394389e-05, "loss": 0.7042, "step": 227 }, { "epoch": 0.9235443037974683, "grad_norm": 0.988607830335953, "learning_rate": 3.911861194110225e-05, "loss": 0.6906, "step": 228 }, { "epoch": 0.9275949367088607, "grad_norm": 0.7362021785582009, "learning_rate": 3.910187103958837e-05, "loss": 0.6836, "step": 229 }, { "epoch": 0.9316455696202531, "grad_norm": 0.7740360140654434, "learning_rate": 3.908497629423117e-05, "loss": 0.6689, "step": 230 }, { "epoch": 0.9356962025316455, "grad_norm": 0.5583333016799824, "learning_rate": 3.9067927841098614e-05, "loss": 0.6448, "step": 231 }, { "epoch": 0.9397468354430379, "grad_norm": 0.7734922746226754, "learning_rate": 3.9050725817496594e-05, "loss": 0.6966, "step": 232 }, { "epoch": 0.9437974683544303, "grad_norm": 0.6583241088139664, "learning_rate": 3.9033370361967844e-05, "loss": 0.6767, "step": 233 }, { "epoch": 0.9478481012658228, "grad_norm": 0.5079912310716086, "learning_rate": 3.901586161429081e-05, "loss": 0.6497, "step": 234 }, { "epoch": 0.9518987341772152, "grad_norm": 0.6976142399306376, "learning_rate": 3.8998199715478545e-05, "loss": 0.6854, "step": 235 }, { "epoch": 0.9559493670886076, "grad_norm": 0.5414977241649908, "learning_rate": 3.8980384807777564e-05, "loss": 0.6616, "step": 236 }, { "epoch": 0.96, "grad_norm": 0.7400028808592839, "learning_rate": 3.896241703466667e-05, "loss": 0.6686, "step": 237 }, { "epoch": 0.9640506329113924, "grad_norm": 0.492071064391821, "learning_rate": 3.894429654085585e-05, "loss": 0.6775, "step": 238 }, { "epoch": 0.9681012658227848, "grad_norm": 0.6930365063337764, "learning_rate": 3.892602347228505e-05, "loss": 0.6545, "step": 239 }, { "epoch": 0.9721518987341772, "grad_norm": 0.6469732078903274, "learning_rate": 3.890759797612307e-05, "loss": 0.6816, "step": 240 }, { "epoch": 0.9762025316455696, "grad_norm": 0.6093607097465363, "learning_rate": 3.888902020076632e-05, "loss": 0.7136, "step": 241 }, { "epoch": 0.980253164556962, "grad_norm": 0.649320210603065, "learning_rate": 3.887029029583764e-05, "loss": 0.6798, "step": 242 }, { "epoch": 0.9843037974683544, "grad_norm": 0.7032622370603042, "learning_rate": 3.8851408412185125e-05, "loss": 0.6599, "step": 243 }, { "epoch": 0.9883544303797468, "grad_norm": 0.5582772469678045, "learning_rate": 3.8832374701880855e-05, "loss": 0.6522, "step": 244 }, { "epoch": 0.9924050632911392, "grad_norm": 0.6508752564289336, "learning_rate": 3.881318931821972e-05, "loss": 0.6683, "step": 245 }, { "epoch": 0.9964556962025316, "grad_norm": 0.5845375479863627, "learning_rate": 3.879385241571817e-05, "loss": 0.677, "step": 246 }, { "epoch": 1.000506329113924, "grad_norm": 0.5989155269312043, "learning_rate": 3.8774364150112955e-05, "loss": 0.6802, "step": 247 }, { "epoch": 1.0045569620253165, "grad_norm": 0.7836198782411467, "learning_rate": 3.8754724678359884e-05, "loss": 0.5652, "step": 248 }, { "epoch": 1.0086075949367088, "grad_norm": 0.8622604545396052, "learning_rate": 3.873493415863256e-05, "loss": 0.5928, "step": 249 }, { "epoch": 1.0126582278481013, "grad_norm": 0.7014679274508406, "learning_rate": 3.871499275032111e-05, "loss": 0.5544, "step": 250 }, { "epoch": 1.0167088607594936, "grad_norm": 0.6354419867519022, "learning_rate": 3.869490061403091e-05, "loss": 0.5452, "step": 251 }, { "epoch": 1.0207594936708861, "grad_norm": 0.5410605665055107, "learning_rate": 3.867465791158124e-05, "loss": 0.5289, "step": 252 }, { "epoch": 1.0248101265822784, "grad_norm": 0.6322308502210624, "learning_rate": 3.865426480600407e-05, "loss": 0.5616, "step": 253 }, { "epoch": 1.028860759493671, "grad_norm": 0.5612351346444782, "learning_rate": 3.863372146154264e-05, "loss": 0.5316, "step": 254 }, { "epoch": 1.0329113924050632, "grad_norm": 0.6233449217481026, "learning_rate": 3.861302804365024e-05, "loss": 0.5584, "step": 255 }, { "epoch": 1.0369620253164558, "grad_norm": 0.6470664270619828, "learning_rate": 3.85921847189888e-05, "loss": 0.5334, "step": 256 }, { "epoch": 1.041012658227848, "grad_norm": 0.6402351178559815, "learning_rate": 3.85711916554276e-05, "loss": 0.5469, "step": 257 }, { "epoch": 1.0450632911392406, "grad_norm": 1.1232084894177568, "learning_rate": 3.85500490220419e-05, "loss": 0.5476, "step": 258 }, { "epoch": 1.0491139240506329, "grad_norm": 0.652110766682762, "learning_rate": 3.852875698911154e-05, "loss": 0.552, "step": 259 }, { "epoch": 1.0531645569620254, "grad_norm": 0.5836516962707977, "learning_rate": 3.850731572811963e-05, "loss": 0.5379, "step": 260 }, { "epoch": 1.0572151898734177, "grad_norm": 0.6583327848370913, "learning_rate": 3.848572541175116e-05, "loss": 0.545, "step": 261 }, { "epoch": 1.0612658227848102, "grad_norm": 0.9704621887959937, "learning_rate": 3.846398621389154e-05, "loss": 0.527, "step": 262 }, { "epoch": 1.0653164556962025, "grad_norm": 1.1650016326023878, "learning_rate": 3.84420983096253e-05, "loss": 0.5476, "step": 263 }, { "epoch": 1.069367088607595, "grad_norm": 0.9484948897912377, "learning_rate": 3.8420061875234606e-05, "loss": 0.5578, "step": 264 }, { "epoch": 1.0734177215189873, "grad_norm": 0.6590897930965242, "learning_rate": 3.839787708819787e-05, "loss": 0.5316, "step": 265 }, { "epoch": 1.0774683544303798, "grad_norm": 0.5639961690984401, "learning_rate": 3.8375544127188325e-05, "loss": 0.5456, "step": 266 }, { "epoch": 1.081518987341772, "grad_norm": 0.7042869415949355, "learning_rate": 3.8353063172072564e-05, "loss": 0.5574, "step": 267 }, { "epoch": 1.0855696202531646, "grad_norm": 0.5190930339959589, "learning_rate": 3.8330434403909105e-05, "loss": 0.5419, "step": 268 }, { "epoch": 1.089620253164557, "grad_norm": 0.5776407559100417, "learning_rate": 3.8307658004946934e-05, "loss": 0.5352, "step": 269 }, { "epoch": 1.0936708860759494, "grad_norm": 0.516138358292081, "learning_rate": 3.8284734158624046e-05, "loss": 0.556, "step": 270 }, { "epoch": 1.0977215189873417, "grad_norm": 0.6031927334381678, "learning_rate": 3.826166304956594e-05, "loss": 0.5312, "step": 271 }, { "epoch": 1.1017721518987342, "grad_norm": 0.6634081063273057, "learning_rate": 3.8238444863584164e-05, "loss": 0.5583, "step": 272 }, { "epoch": 1.1058227848101265, "grad_norm": 0.5831693580748882, "learning_rate": 3.821507978767479e-05, "loss": 0.5132, "step": 273 }, { "epoch": 1.109873417721519, "grad_norm": 0.5366616891064945, "learning_rate": 3.819156801001693e-05, "loss": 0.5408, "step": 274 }, { "epoch": 1.1139240506329113, "grad_norm": 0.50900380092165, "learning_rate": 3.816790971997121e-05, "loss": 0.5383, "step": 275 }, { "epoch": 1.1179746835443038, "grad_norm": 0.5813769435095557, "learning_rate": 3.8144105108078246e-05, "loss": 0.5376, "step": 276 }, { "epoch": 1.1220253164556961, "grad_norm": 0.5433796209003829, "learning_rate": 3.81201543660571e-05, "loss": 0.5397, "step": 277 }, { "epoch": 1.1260759493670887, "grad_norm": 0.5600243487201734, "learning_rate": 3.809605768680377e-05, "loss": 0.542, "step": 278 }, { "epoch": 1.130126582278481, "grad_norm": 0.5039565184693243, "learning_rate": 3.807181526438958e-05, "loss": 0.5589, "step": 279 }, { "epoch": 1.1341772151898735, "grad_norm": 0.5244574145400217, "learning_rate": 3.8047427294059697e-05, "loss": 0.5261, "step": 280 }, { "epoch": 1.1382278481012658, "grad_norm": 0.5471083537297282, "learning_rate": 3.802289397223145e-05, "loss": 0.5479, "step": 281 }, { "epoch": 1.1422784810126583, "grad_norm": 0.5810768470413527, "learning_rate": 3.7998215496492854e-05, "loss": 0.5453, "step": 282 }, { "epoch": 1.1463291139240506, "grad_norm": 0.5630869526365532, "learning_rate": 3.797339206560096e-05, "loss": 0.5463, "step": 283 }, { "epoch": 1.150379746835443, "grad_norm": 0.5537676184860583, "learning_rate": 3.794842387948027e-05, "loss": 0.5301, "step": 284 }, { "epoch": 1.1544303797468354, "grad_norm": 0.5487031143817596, "learning_rate": 3.7923311139221114e-05, "loss": 0.5278, "step": 285 }, { "epoch": 1.158481012658228, "grad_norm": 0.5708988588572544, "learning_rate": 3.7898054047078054e-05, "loss": 0.527, "step": 286 }, { "epoch": 1.1625316455696202, "grad_norm": 0.5477132159263439, "learning_rate": 3.787265280646825e-05, "loss": 0.5469, "step": 287 }, { "epoch": 1.1665822784810127, "grad_norm": 0.48753776644150476, "learning_rate": 3.7847107621969786e-05, "loss": 0.5601, "step": 288 }, { "epoch": 1.170632911392405, "grad_norm": 0.535404207337649, "learning_rate": 3.7821418699320064e-05, "loss": 0.5361, "step": 289 }, { "epoch": 1.1746835443037975, "grad_norm": 0.5616002788343727, "learning_rate": 3.7795586245414145e-05, "loss": 0.5312, "step": 290 }, { "epoch": 1.1787341772151898, "grad_norm": 0.5302858620100632, "learning_rate": 3.776961046830306e-05, "loss": 0.5512, "step": 291 }, { "epoch": 1.1827848101265823, "grad_norm": 0.5597461878725631, "learning_rate": 3.774349157719215e-05, "loss": 0.5503, "step": 292 }, { "epoch": 1.1868354430379746, "grad_norm": 0.5490231398095535, "learning_rate": 3.7717229782439365e-05, "loss": 0.5527, "step": 293 }, { "epoch": 1.1908860759493671, "grad_norm": 0.4915274727231385, "learning_rate": 3.769082529555359e-05, "loss": 0.5564, "step": 294 }, { "epoch": 1.1949367088607594, "grad_norm": 0.5918845858312128, "learning_rate": 3.766427832919294e-05, "loss": 0.521, "step": 295 }, { "epoch": 1.198987341772152, "grad_norm": 0.4996606137404119, "learning_rate": 3.7637589097163024e-05, "loss": 0.5179, "step": 296 }, { "epoch": 1.2030379746835442, "grad_norm": 0.6209351078754464, "learning_rate": 3.761075781441526e-05, "loss": 0.5314, "step": 297 }, { "epoch": 1.2070886075949367, "grad_norm": 0.503542725392301, "learning_rate": 3.75837846970451e-05, "loss": 0.5361, "step": 298 }, { "epoch": 1.211139240506329, "grad_norm": 0.6199767671220024, "learning_rate": 3.755666996229032e-05, "loss": 0.5376, "step": 299 }, { "epoch": 1.2151898734177216, "grad_norm": 0.5271821131206372, "learning_rate": 3.752941382852927e-05, "loss": 0.5402, "step": 300 }, { "epoch": 1.2192405063291138, "grad_norm": 0.6131161016649626, "learning_rate": 3.7502016515279115e-05, "loss": 0.5608, "step": 301 }, { "epoch": 1.2232911392405064, "grad_norm": 0.5275544281146524, "learning_rate": 3.7474478243194043e-05, "loss": 0.5526, "step": 302 }, { "epoch": 1.2273417721518987, "grad_norm": 0.6099656438853427, "learning_rate": 3.744679923406351e-05, "loss": 0.5674, "step": 303 }, { "epoch": 1.2313924050632912, "grad_norm": 0.757814440496683, "learning_rate": 3.741897971081043e-05, "loss": 0.5279, "step": 304 }, { "epoch": 1.2354430379746835, "grad_norm": 0.7116366244149072, "learning_rate": 3.739101989748946e-05, "loss": 0.5741, "step": 305 }, { "epoch": 1.239493670886076, "grad_norm": 0.6468660418039696, "learning_rate": 3.7362920019285066e-05, "loss": 0.5662, "step": 306 }, { "epoch": 1.2435443037974683, "grad_norm": 0.6431045214688212, "learning_rate": 3.73346803025098e-05, "loss": 0.529, "step": 307 }, { "epoch": 1.2475949367088608, "grad_norm": 0.5621553627616895, "learning_rate": 3.730630097460247e-05, "loss": 0.5423, "step": 308 }, { "epoch": 1.251645569620253, "grad_norm": 0.7611624491551551, "learning_rate": 3.727778226412628e-05, "loss": 0.5477, "step": 309 }, { "epoch": 1.2556962025316456, "grad_norm": 0.4992275302019909, "learning_rate": 3.7249124400767006e-05, "loss": 0.5228, "step": 310 }, { "epoch": 1.259746835443038, "grad_norm": 0.6419437561130223, "learning_rate": 3.722032761533114e-05, "loss": 0.5467, "step": 311 }, { "epoch": 1.2637974683544304, "grad_norm": 0.5235836724222749, "learning_rate": 3.719139213974403e-05, "loss": 0.5517, "step": 312 }, { "epoch": 1.2678481012658227, "grad_norm": 0.5701664609929853, "learning_rate": 3.7162318207048006e-05, "loss": 0.5461, "step": 313 }, { "epoch": 1.2718987341772152, "grad_norm": 0.6902114255871488, "learning_rate": 3.713310605140055e-05, "loss": 0.5634, "step": 314 }, { "epoch": 1.2759493670886077, "grad_norm": 0.5099226033369004, "learning_rate": 3.710375590807233e-05, "loss": 0.5079, "step": 315 }, { "epoch": 1.28, "grad_norm": 0.6335881105459616, "learning_rate": 3.7074268013445365e-05, "loss": 0.5511, "step": 316 }, { "epoch": 1.2840506329113923, "grad_norm": 0.4710016273134292, "learning_rate": 3.7044642605011114e-05, "loss": 0.5329, "step": 317 }, { "epoch": 1.2881012658227848, "grad_norm": 0.5781566878525152, "learning_rate": 3.701487992136854e-05, "loss": 0.5604, "step": 318 }, { "epoch": 1.2921518987341774, "grad_norm": 0.45688173042527974, "learning_rate": 3.69849802022222e-05, "loss": 0.5456, "step": 319 }, { "epoch": 1.2962025316455696, "grad_norm": 0.57771103167355, "learning_rate": 3.6954943688380334e-05, "loss": 0.5219, "step": 320 }, { "epoch": 1.300253164556962, "grad_norm": 0.5186859218560117, "learning_rate": 3.692477062175289e-05, "loss": 0.5587, "step": 321 }, { "epoch": 1.3043037974683545, "grad_norm": 0.49870330450879313, "learning_rate": 3.689446124534958e-05, "loss": 0.548, "step": 322 }, { "epoch": 1.308354430379747, "grad_norm": 0.5251768770539889, "learning_rate": 3.686401580327799e-05, "loss": 0.5477, "step": 323 }, { "epoch": 1.3124050632911393, "grad_norm": 0.5068744335633837, "learning_rate": 3.683343454074149e-05, "loss": 0.5291, "step": 324 }, { "epoch": 1.3164556962025316, "grad_norm": 0.5497862261404528, "learning_rate": 3.6802717704037386e-05, "loss": 0.5225, "step": 325 }, { "epoch": 1.320506329113924, "grad_norm": 0.5567392621336039, "learning_rate": 3.6771865540554855e-05, "loss": 0.5283, "step": 326 }, { "epoch": 1.3245569620253166, "grad_norm": 0.4853168927971562, "learning_rate": 3.674087829877297e-05, "loss": 0.5186, "step": 327 }, { "epoch": 1.3286075949367089, "grad_norm": 0.5341130629416614, "learning_rate": 3.6709756228258735e-05, "loss": 0.5165, "step": 328 }, { "epoch": 1.3326582278481012, "grad_norm": 0.5001392302256459, "learning_rate": 3.667849957966501e-05, "loss": 0.534, "step": 329 }, { "epoch": 1.3367088607594937, "grad_norm": 0.4944966857771026, "learning_rate": 3.6647108604728546e-05, "loss": 0.5426, "step": 330 }, { "epoch": 1.3407594936708862, "grad_norm": 0.5152050078924341, "learning_rate": 3.661558355626795e-05, "loss": 0.5341, "step": 331 }, { "epoch": 1.3448101265822785, "grad_norm": 0.4613527708642925, "learning_rate": 3.658392468818163e-05, "loss": 0.5477, "step": 332 }, { "epoch": 1.3488607594936708, "grad_norm": 0.5661795144632766, "learning_rate": 3.655213225544574e-05, "loss": 0.5691, "step": 333 }, { "epoch": 1.3529113924050633, "grad_norm": 0.5643809289142876, "learning_rate": 3.652020651411218e-05, "loss": 0.5414, "step": 334 }, { "epoch": 1.3569620253164558, "grad_norm": 0.5425828978154763, "learning_rate": 3.6488147721306474e-05, "loss": 0.5633, "step": 335 }, { "epoch": 1.3610126582278481, "grad_norm": 0.497069741424524, "learning_rate": 3.645595613522574e-05, "loss": 0.5621, "step": 336 }, { "epoch": 1.3650632911392404, "grad_norm": 0.6195780057179011, "learning_rate": 3.642363201513657e-05, "loss": 0.5497, "step": 337 }, { "epoch": 1.369113924050633, "grad_norm": 0.4907793857899326, "learning_rate": 3.6391175621373006e-05, "loss": 0.5331, "step": 338 }, { "epoch": 1.3731645569620254, "grad_norm": 0.5073802392668894, "learning_rate": 3.6358587215334355e-05, "loss": 0.5481, "step": 339 }, { "epoch": 1.3772151898734177, "grad_norm": 0.49991809310192475, "learning_rate": 3.632586705948318e-05, "loss": 0.5323, "step": 340 }, { "epoch": 1.38126582278481, "grad_norm": 0.5193664974154735, "learning_rate": 3.629301541734311e-05, "loss": 0.5342, "step": 341 }, { "epoch": 1.3853164556962025, "grad_norm": 0.5688432467757866, "learning_rate": 3.626003255349676e-05, "loss": 0.5438, "step": 342 }, { "epoch": 1.389367088607595, "grad_norm": 0.5841136342558729, "learning_rate": 3.622691873358357e-05, "loss": 0.5528, "step": 343 }, { "epoch": 1.3934177215189874, "grad_norm": 0.5191330121650943, "learning_rate": 3.61936742242977e-05, "loss": 0.5505, "step": 344 }, { "epoch": 1.3974683544303796, "grad_norm": 0.5268417042096062, "learning_rate": 3.6160299293385864e-05, "loss": 0.5182, "step": 345 }, { "epoch": 1.4015189873417722, "grad_norm": 0.5235753801031392, "learning_rate": 3.612679420964516e-05, "loss": 0.5414, "step": 346 }, { "epoch": 1.4055696202531647, "grad_norm": 0.5232505925229447, "learning_rate": 3.609315924292092e-05, "loss": 0.5577, "step": 347 }, { "epoch": 1.409620253164557, "grad_norm": 0.5020949486487991, "learning_rate": 3.6059394664104554e-05, "loss": 0.5535, "step": 348 }, { "epoch": 1.4136708860759493, "grad_norm": 0.5077430652728979, "learning_rate": 3.602550074513133e-05, "loss": 0.5411, "step": 349 }, { "epoch": 1.4177215189873418, "grad_norm": 0.5186073814744656, "learning_rate": 3.599147775897822e-05, "loss": 0.5288, "step": 350 }, { "epoch": 1.4217721518987343, "grad_norm": 0.509171363617426, "learning_rate": 3.595732597966167e-05, "loss": 0.5373, "step": 351 }, { "epoch": 1.4258227848101266, "grad_norm": 0.49839218405421526, "learning_rate": 3.592304568223542e-05, "loss": 0.5411, "step": 352 }, { "epoch": 1.4298734177215189, "grad_norm": 0.5186790854797183, "learning_rate": 3.588863714278826e-05, "loss": 0.5222, "step": 353 }, { "epoch": 1.4339240506329114, "grad_norm": 0.4989052139186336, "learning_rate": 3.585410063844186e-05, "loss": 0.5283, "step": 354 }, { "epoch": 1.437974683544304, "grad_norm": 0.5741366844063225, "learning_rate": 3.581943644734846e-05, "loss": 0.5392, "step": 355 }, { "epoch": 1.4420253164556962, "grad_norm": 0.4881836869203314, "learning_rate": 3.578464484868869e-05, "loss": 0.5527, "step": 356 }, { "epoch": 1.4460759493670885, "grad_norm": 0.49406189524046534, "learning_rate": 3.5749726122669316e-05, "loss": 0.5483, "step": 357 }, { "epoch": 1.450126582278481, "grad_norm": 0.44404906634316876, "learning_rate": 3.5714680550520943e-05, "loss": 0.5539, "step": 358 }, { "epoch": 1.4541772151898735, "grad_norm": 0.5329732752093623, "learning_rate": 3.5679508414495794e-05, "loss": 0.5412, "step": 359 }, { "epoch": 1.4582278481012658, "grad_norm": 0.5416042026635024, "learning_rate": 3.564420999786543e-05, "loss": 0.5602, "step": 360 }, { "epoch": 1.4622784810126581, "grad_norm": 0.5556104431928851, "learning_rate": 3.560878558491842e-05, "loss": 0.5642, "step": 361 }, { "epoch": 1.4663291139240506, "grad_norm": 0.466095003805798, "learning_rate": 3.5573235460958145e-05, "loss": 0.5431, "step": 362 }, { "epoch": 1.4703797468354431, "grad_norm": 0.5761799959771857, "learning_rate": 3.553755991230039e-05, "loss": 0.5499, "step": 363 }, { "epoch": 1.4744303797468354, "grad_norm": 0.4751644963512538, "learning_rate": 3.5501759226271144e-05, "loss": 0.5291, "step": 364 }, { "epoch": 1.4784810126582277, "grad_norm": 0.46340157533738285, "learning_rate": 3.546583369120419e-05, "loss": 0.5526, "step": 365 }, { "epoch": 1.4825316455696202, "grad_norm": 0.46671447223309254, "learning_rate": 3.5429783596438864e-05, "loss": 0.5493, "step": 366 }, { "epoch": 1.4865822784810128, "grad_norm": 0.5097969150975388, "learning_rate": 3.539360923231766e-05, "loss": 0.5681, "step": 367 }, { "epoch": 1.490632911392405, "grad_norm": 0.49032797639006653, "learning_rate": 3.535731089018394e-05, "loss": 0.5667, "step": 368 }, { "epoch": 1.4946835443037974, "grad_norm": 0.5080648177634723, "learning_rate": 3.532088886237956e-05, "loss": 0.5391, "step": 369 }, { "epoch": 1.4987341772151899, "grad_norm": 0.49115931359677734, "learning_rate": 3.528434344224253e-05, "loss": 0.5381, "step": 370 }, { "epoch": 1.5027848101265824, "grad_norm": 0.4973820382270278, "learning_rate": 3.524767492410464e-05, "loss": 0.5186, "step": 371 }, { "epoch": 1.5068354430379747, "grad_norm": 0.4951951473172774, "learning_rate": 3.521088360328908e-05, "loss": 0.5296, "step": 372 }, { "epoch": 1.510886075949367, "grad_norm": 0.577492711824501, "learning_rate": 3.517396977610811e-05, "loss": 0.5441, "step": 373 }, { "epoch": 1.5149367088607595, "grad_norm": 0.6349505806000422, "learning_rate": 3.5136933739860595e-05, "loss": 0.5605, "step": 374 }, { "epoch": 1.518987341772152, "grad_norm": 0.5420119855895787, "learning_rate": 3.509977579282971e-05, "loss": 0.535, "step": 375 }, { "epoch": 1.5230379746835443, "grad_norm": 0.4778745896508831, "learning_rate": 3.5062496234280424e-05, "loss": 0.5242, "step": 376 }, { "epoch": 1.5270886075949366, "grad_norm": 0.5618021028385385, "learning_rate": 3.502509536445719e-05, "loss": 0.5406, "step": 377 }, { "epoch": 1.531139240506329, "grad_norm": 0.5506980495886351, "learning_rate": 3.498757348458147e-05, "loss": 0.5215, "step": 378 }, { "epoch": 1.5351898734177216, "grad_norm": 0.5419184358358237, "learning_rate": 3.4949930896849324e-05, "loss": 0.5351, "step": 379 }, { "epoch": 1.539240506329114, "grad_norm": 0.5895114974311453, "learning_rate": 3.491216790442899e-05, "loss": 0.5467, "step": 380 }, { "epoch": 1.5432911392405062, "grad_norm": 0.5440429115985579, "learning_rate": 3.487428481145839e-05, "loss": 0.5521, "step": 381 }, { "epoch": 1.5473417721518987, "grad_norm": 0.5016697716778628, "learning_rate": 3.483628192304278e-05, "loss": 0.511, "step": 382 }, { "epoch": 1.5513924050632912, "grad_norm": 0.6320720198397687, "learning_rate": 3.479815954525219e-05, "loss": 0.5513, "step": 383 }, { "epoch": 1.5554430379746835, "grad_norm": 0.4964187353199046, "learning_rate": 3.475991798511899e-05, "loss": 0.5419, "step": 384 }, { "epoch": 1.5594936708860758, "grad_norm": 0.5645564401813931, "learning_rate": 3.4721557550635464e-05, "loss": 0.539, "step": 385 }, { "epoch": 1.5635443037974683, "grad_norm": 0.4733294543908813, "learning_rate": 3.468307855075128e-05, "loss": 0.5184, "step": 386 }, { "epoch": 1.5675949367088609, "grad_norm": 0.483170898755529, "learning_rate": 3.4644481295371005e-05, "loss": 0.5489, "step": 387 }, { "epoch": 1.5716455696202531, "grad_norm": 0.5078961493183789, "learning_rate": 3.460576609535163e-05, "loss": 0.5607, "step": 388 }, { "epoch": 1.5756962025316454, "grad_norm": 0.48181115208576425, "learning_rate": 3.456693326250006e-05, "loss": 0.5204, "step": 389 }, { "epoch": 1.579746835443038, "grad_norm": 0.5671407279053711, "learning_rate": 3.452798310957058e-05, "loss": 0.5758, "step": 390 }, { "epoch": 1.5837974683544305, "grad_norm": 0.4647177785224469, "learning_rate": 3.4488915950262386e-05, "loss": 0.5344, "step": 391 }, { "epoch": 1.5878481012658228, "grad_norm": 0.5264240872934318, "learning_rate": 3.4449732099216985e-05, "loss": 0.5499, "step": 392 }, { "epoch": 1.591898734177215, "grad_norm": 0.47127549913649947, "learning_rate": 3.441043187201574e-05, "loss": 0.5578, "step": 393 }, { "epoch": 1.5959493670886076, "grad_norm": 0.479620253239466, "learning_rate": 3.437101558517728e-05, "loss": 0.5447, "step": 394 }, { "epoch": 1.6, "grad_norm": 0.4728255097961695, "learning_rate": 3.433148355615496e-05, "loss": 0.5444, "step": 395 }, { "epoch": 1.6040506329113924, "grad_norm": 0.5433565902816265, "learning_rate": 3.4291836103334294e-05, "loss": 0.5729, "step": 396 }, { "epoch": 1.6081012658227847, "grad_norm": 0.4626289319117912, "learning_rate": 3.425207354603043e-05, "loss": 0.5303, "step": 397 }, { "epoch": 1.6121518987341772, "grad_norm": 0.48926256749459623, "learning_rate": 3.421219620448553e-05, "loss": 0.5321, "step": 398 }, { "epoch": 1.6162025316455697, "grad_norm": 0.5113450731468268, "learning_rate": 3.417220439986623e-05, "loss": 0.5436, "step": 399 }, { "epoch": 1.620253164556962, "grad_norm": 0.4596623431370115, "learning_rate": 3.4132098454261024e-05, "loss": 0.5332, "step": 400 }, { "epoch": 1.6243037974683543, "grad_norm": 0.48780151116267995, "learning_rate": 3.4091878690677676e-05, "loss": 0.5669, "step": 401 }, { "epoch": 1.6283544303797468, "grad_norm": 0.47479612782257274, "learning_rate": 3.405154543304065e-05, "loss": 0.5613, "step": 402 }, { "epoch": 1.6324050632911393, "grad_norm": 0.5423433921899417, "learning_rate": 3.401109900618843e-05, "loss": 0.5296, "step": 403 }, { "epoch": 1.6364556962025316, "grad_norm": 0.44365436039371237, "learning_rate": 3.3970539735870996e-05, "loss": 0.5515, "step": 404 }, { "epoch": 1.640506329113924, "grad_norm": 0.46084709524722484, "learning_rate": 3.392986794874714e-05, "loss": 0.5602, "step": 405 }, { "epoch": 1.6445569620253164, "grad_norm": 0.4425212193219507, "learning_rate": 3.388908397238184e-05, "loss": 0.5358, "step": 406 }, { "epoch": 1.648607594936709, "grad_norm": 0.4512827312080836, "learning_rate": 3.384818813524362e-05, "loss": 0.5769, "step": 407 }, { "epoch": 1.6526582278481012, "grad_norm": 0.49008288595479055, "learning_rate": 3.380718076670195e-05, "loss": 0.5424, "step": 408 }, { "epoch": 1.6567088607594935, "grad_norm": 0.5042921888011049, "learning_rate": 3.376606219702454e-05, "loss": 0.5691, "step": 409 }, { "epoch": 1.660759493670886, "grad_norm": 0.507175669622762, "learning_rate": 3.372483275737468e-05, "loss": 0.5303, "step": 410 }, { "epoch": 1.6648101265822786, "grad_norm": 0.5006751521822018, "learning_rate": 3.368349277980861e-05, "loss": 0.5614, "step": 411 }, { "epoch": 1.6688607594936709, "grad_norm": 0.5102330873361745, "learning_rate": 3.3642042597272844e-05, "loss": 0.5422, "step": 412 }, { "epoch": 1.6729113924050631, "grad_norm": 0.52650324945473, "learning_rate": 3.360048254360144e-05, "loss": 0.5323, "step": 413 }, { "epoch": 1.6769620253164557, "grad_norm": 0.541863399634605, "learning_rate": 3.355881295351336e-05, "loss": 0.567, "step": 414 }, { "epoch": 1.6810126582278482, "grad_norm": 0.5062222652744562, "learning_rate": 3.351703416260975e-05, "loss": 0.5395, "step": 415 }, { "epoch": 1.6850632911392405, "grad_norm": 0.486265163434854, "learning_rate": 3.347514650737126e-05, "loss": 0.5646, "step": 416 }, { "epoch": 1.6891139240506328, "grad_norm": 0.47948448585444575, "learning_rate": 3.3433150325155295e-05, "loss": 0.5376, "step": 417 }, { "epoch": 1.6931645569620253, "grad_norm": 0.45258193325081336, "learning_rate": 3.339104595419334e-05, "loss": 0.5468, "step": 418 }, { "epoch": 1.6972151898734178, "grad_norm": 0.4628772537110854, "learning_rate": 3.3348833733588204e-05, "loss": 0.5632, "step": 419 }, { "epoch": 1.70126582278481, "grad_norm": 0.4446670015539287, "learning_rate": 3.3306514003311305e-05, "loss": 0.5414, "step": 420 }, { "epoch": 1.7053164556962024, "grad_norm": 0.5116530953845003, "learning_rate": 3.326408710419996e-05, "loss": 0.5517, "step": 421 }, { "epoch": 1.709367088607595, "grad_norm": 0.5020306321474873, "learning_rate": 3.322155337795454e-05, "loss": 0.5305, "step": 422 }, { "epoch": 1.7134177215189874, "grad_norm": 0.45753142902797134, "learning_rate": 3.317891316713587e-05, "loss": 0.5223, "step": 423 }, { "epoch": 1.7174683544303797, "grad_norm": 0.46877641360239125, "learning_rate": 3.313616681516231e-05, "loss": 0.5096, "step": 424 }, { "epoch": 1.721518987341772, "grad_norm": 0.4956067781709886, "learning_rate": 3.309331466630713e-05, "loss": 0.5579, "step": 425 }, { "epoch": 1.7255696202531645, "grad_norm": 0.44610617917762657, "learning_rate": 3.305035706569563e-05, "loss": 0.5395, "step": 426 }, { "epoch": 1.729620253164557, "grad_norm": 0.4636063713633591, "learning_rate": 3.3007294359302433e-05, "loss": 0.5581, "step": 427 }, { "epoch": 1.7336708860759493, "grad_norm": 0.4845376413087123, "learning_rate": 3.296412689394864e-05, "loss": 0.5393, "step": 428 }, { "epoch": 1.7377215189873416, "grad_norm": 0.4619617515854198, "learning_rate": 3.292085501729909e-05, "loss": 0.5228, "step": 429 }, { "epoch": 1.7417721518987341, "grad_norm": 0.5013362660777563, "learning_rate": 3.2877479077859534e-05, "loss": 0.5497, "step": 430 }, { "epoch": 1.7458227848101266, "grad_norm": 0.4680994195846364, "learning_rate": 3.283399942497381e-05, "loss": 0.5306, "step": 431 }, { "epoch": 1.749873417721519, "grad_norm": 0.5295853804721057, "learning_rate": 3.279041640882108e-05, "loss": 0.5253, "step": 432 }, { "epoch": 1.7539240506329112, "grad_norm": 0.451414952176813, "learning_rate": 3.2746730380412964e-05, "loss": 0.525, "step": 433 }, { "epoch": 1.7579746835443038, "grad_norm": 0.6372538061384148, "learning_rate": 3.2702941691590726e-05, "loss": 0.5289, "step": 434 }, { "epoch": 1.7620253164556963, "grad_norm": 0.5115322040692416, "learning_rate": 3.265905069502244e-05, "loss": 0.5161, "step": 435 }, { "epoch": 1.7660759493670886, "grad_norm": 0.6062135789269402, "learning_rate": 3.261505774420016e-05, "loss": 0.5326, "step": 436 }, { "epoch": 1.7701265822784809, "grad_norm": 0.48245788163537917, "learning_rate": 3.257096319343707e-05, "loss": 0.5588, "step": 437 }, { "epoch": 1.7741772151898734, "grad_norm": 0.5572637726585523, "learning_rate": 3.2526767397864614e-05, "loss": 0.5361, "step": 438 }, { "epoch": 1.7782278481012659, "grad_norm": 0.518772397738235, "learning_rate": 3.248247071342966e-05, "loss": 0.535, "step": 439 }, { "epoch": 1.7822784810126582, "grad_norm": 0.4807453521772824, "learning_rate": 3.243807349689161e-05, "loss": 0.5434, "step": 440 }, { "epoch": 1.7863291139240505, "grad_norm": 0.5562866674912852, "learning_rate": 3.2393576105819544e-05, "loss": 0.5401, "step": 441 }, { "epoch": 1.790379746835443, "grad_norm": 0.4627932088603239, "learning_rate": 3.2348978898589333e-05, "loss": 0.512, "step": 442 }, { "epoch": 1.7944303797468355, "grad_norm": 0.47622146522123576, "learning_rate": 3.230428223438075e-05, "loss": 0.5157, "step": 443 }, { "epoch": 1.7984810126582278, "grad_norm": 0.531519665647319, "learning_rate": 3.225948647317459e-05, "loss": 0.526, "step": 444 }, { "epoch": 1.80253164556962, "grad_norm": 0.5028845080640747, "learning_rate": 3.2214591975749745e-05, "loss": 0.5467, "step": 445 }, { "epoch": 1.8065822784810126, "grad_norm": 0.5108244146822318, "learning_rate": 3.216959910368034e-05, "loss": 0.5556, "step": 446 }, { "epoch": 1.8106329113924051, "grad_norm": 0.47515443495747023, "learning_rate": 3.212450821933277e-05, "loss": 0.5491, "step": 447 }, { "epoch": 1.8146835443037974, "grad_norm": 0.5011601265136292, "learning_rate": 3.207931968586281e-05, "loss": 0.5537, "step": 448 }, { "epoch": 1.81873417721519, "grad_norm": 0.47041782608842303, "learning_rate": 3.203403386721272e-05, "loss": 0.5366, "step": 449 }, { "epoch": 1.8227848101265822, "grad_norm": 0.49520118598375035, "learning_rate": 3.1988651128108245e-05, "loss": 0.532, "step": 450 }, { "epoch": 1.8268354430379747, "grad_norm": 0.49688970586681486, "learning_rate": 3.194317183405573e-05, "loss": 0.5391, "step": 451 }, { "epoch": 1.8308860759493673, "grad_norm": 0.526628406576501, "learning_rate": 3.189759635133914e-05, "loss": 0.5742, "step": 452 }, { "epoch": 1.8349367088607595, "grad_norm": 0.5584175802875053, "learning_rate": 3.185192504701718e-05, "loss": 0.5403, "step": 453 }, { "epoch": 1.8389873417721518, "grad_norm": 0.6029243080933533, "learning_rate": 3.1806158288920234e-05, "loss": 0.5539, "step": 454 }, { "epoch": 1.8430379746835444, "grad_norm": 0.718044655520827, "learning_rate": 3.1760296445647477e-05, "loss": 0.5636, "step": 455 }, { "epoch": 1.8470886075949369, "grad_norm": 0.5306706827973985, "learning_rate": 3.1714339886563896e-05, "loss": 0.5617, "step": 456 }, { "epoch": 1.8511392405063292, "grad_norm": 0.46809328355341934, "learning_rate": 3.166828898179731e-05, "loss": 0.5592, "step": 457 }, { "epoch": 1.8551898734177215, "grad_norm": 0.4628074439914945, "learning_rate": 3.162214410223536e-05, "loss": 0.5349, "step": 458 }, { "epoch": 1.859240506329114, "grad_norm": 0.4858675630994198, "learning_rate": 3.157590561952257e-05, "loss": 0.5178, "step": 459 }, { "epoch": 1.8632911392405065, "grad_norm": 0.47791704123898865, "learning_rate": 3.152957390605732e-05, "loss": 0.5402, "step": 460 }, { "epoch": 1.8673417721518988, "grad_norm": 0.47229936336324746, "learning_rate": 3.148314933498886e-05, "loss": 0.5202, "step": 461 }, { "epoch": 1.871392405063291, "grad_norm": 0.49326357162377416, "learning_rate": 3.143663228021431e-05, "loss": 0.5146, "step": 462 }, { "epoch": 1.8754430379746836, "grad_norm": 0.5281476738928226, "learning_rate": 3.1390023116375624e-05, "loss": 0.5436, "step": 463 }, { "epoch": 1.879493670886076, "grad_norm": 0.4643650869276768, "learning_rate": 3.134332221885661e-05, "loss": 0.5595, "step": 464 }, { "epoch": 1.8835443037974684, "grad_norm": 0.5242979015849641, "learning_rate": 3.129652996377987e-05, "loss": 0.5575, "step": 465 }, { "epoch": 1.8875949367088607, "grad_norm": 0.4692549027185009, "learning_rate": 3.12496467280038e-05, "loss": 0.5435, "step": 466 }, { "epoch": 1.8916455696202532, "grad_norm": 0.4840757488525271, "learning_rate": 3.120267288911952e-05, "loss": 0.5536, "step": 467 }, { "epoch": 1.8956962025316457, "grad_norm": 0.44020155065435235, "learning_rate": 3.11556088254479e-05, "loss": 0.5557, "step": 468 }, { "epoch": 1.899746835443038, "grad_norm": 0.4714987889749861, "learning_rate": 3.11084549160364e-05, "loss": 0.5216, "step": 469 }, { "epoch": 1.9037974683544303, "grad_norm": 0.4885917535575599, "learning_rate": 3.106121154065615e-05, "loss": 0.5192, "step": 470 }, { "epoch": 1.9078481012658228, "grad_norm": 0.48440170816081185, "learning_rate": 3.1013879079798805e-05, "loss": 0.5368, "step": 471 }, { "epoch": 1.9118987341772153, "grad_norm": 0.5128491742219433, "learning_rate": 3.096645791467348e-05, "loss": 0.5331, "step": 472 }, { "epoch": 1.9159493670886076, "grad_norm": 0.46069438498687126, "learning_rate": 3.091894842720373e-05, "loss": 0.5359, "step": 473 }, { "epoch": 1.92, "grad_norm": 0.430755090105567, "learning_rate": 3.0871351000024425e-05, "loss": 0.5284, "step": 474 }, { "epoch": 1.9240506329113924, "grad_norm": 0.5338527733640303, "learning_rate": 3.0823666016478716e-05, "loss": 0.5396, "step": 475 }, { "epoch": 1.928101265822785, "grad_norm": 0.43160943227429777, "learning_rate": 3.0775893860614896e-05, "loss": 0.5411, "step": 476 }, { "epoch": 1.9321518987341773, "grad_norm": 0.4849653634455554, "learning_rate": 3.0728034917183336e-05, "loss": 0.5783, "step": 477 }, { "epoch": 1.9362025316455695, "grad_norm": 0.4507518491096528, "learning_rate": 3.06800895716334e-05, "loss": 0.5474, "step": 478 }, { "epoch": 1.940253164556962, "grad_norm": 0.4927340193593329, "learning_rate": 3.063205821011029e-05, "loss": 0.5489, "step": 479 }, { "epoch": 1.9443037974683546, "grad_norm": 0.43187496108968576, "learning_rate": 3.0583941219452016e-05, "loss": 0.5445, "step": 480 }, { "epoch": 1.9483544303797469, "grad_norm": 0.46875703659692636, "learning_rate": 3.053573898718618e-05, "loss": 0.537, "step": 481 }, { "epoch": 1.9524050632911392, "grad_norm": 0.4671952779186092, "learning_rate": 3.0487451901526956e-05, "loss": 0.5452, "step": 482 }, { "epoch": 1.9564556962025317, "grad_norm": 0.4727044972415056, "learning_rate": 3.0439080351371875e-05, "loss": 0.5156, "step": 483 }, { "epoch": 1.9605063291139242, "grad_norm": 0.43758969818825855, "learning_rate": 3.0390624726298764e-05, "loss": 0.5436, "step": 484 }, { "epoch": 1.9645569620253165, "grad_norm": 0.4594709124335448, "learning_rate": 3.034208541656255e-05, "loss": 0.5386, "step": 485 }, { "epoch": 1.9686075949367088, "grad_norm": 0.42581979982866275, "learning_rate": 3.029346281309218e-05, "loss": 0.5377, "step": 486 }, { "epoch": 1.9726582278481013, "grad_norm": 0.510240032492523, "learning_rate": 3.0244757307487415e-05, "loss": 0.5631, "step": 487 }, { "epoch": 1.9767088607594938, "grad_norm": 0.4756522451306843, "learning_rate": 3.019596929201569e-05, "loss": 0.5275, "step": 488 }, { "epoch": 1.980759493670886, "grad_norm": 0.448270251453321, "learning_rate": 3.0147099159608985e-05, "loss": 0.5308, "step": 489 }, { "epoch": 1.9848101265822784, "grad_norm": 0.463187842907566, "learning_rate": 3.0098147303860616e-05, "loss": 0.5024, "step": 490 }, { "epoch": 1.988860759493671, "grad_norm": 0.4539741430052393, "learning_rate": 3.0049114119022117e-05, "loss": 0.5315, "step": 491 }, { "epoch": 1.9929113924050634, "grad_norm": 0.45926479109800367, "learning_rate": 3.0000000000000004e-05, "loss": 0.5615, "step": 492 }, { "epoch": 1.9969620253164557, "grad_norm": 0.496002955360578, "learning_rate": 2.995080534235264e-05, "loss": 0.5276, "step": 493 }, { "epoch": 2.001012658227848, "grad_norm": 0.4437429279552783, "learning_rate": 2.9901530542287044e-05, "loss": 0.4944, "step": 494 }, { "epoch": 2.0050632911392405, "grad_norm": 0.6470813301907576, "learning_rate": 2.9852175996655676e-05, "loss": 0.3888, "step": 495 }, { "epoch": 2.009113924050633, "grad_norm": 0.8345504351813003, "learning_rate": 2.980274210295326e-05, "loss": 0.3869, "step": 496 }, { "epoch": 2.013164556962025, "grad_norm": 0.5569214845576423, "learning_rate": 2.9753229259313578e-05, "loss": 0.3877, "step": 497 }, { "epoch": 2.0172151898734176, "grad_norm": 0.49125287335175466, "learning_rate": 2.9703637864506274e-05, "loss": 0.3864, "step": 498 }, { "epoch": 2.02126582278481, "grad_norm": 0.5487517295953359, "learning_rate": 2.965396831793362e-05, "loss": 0.3955, "step": 499 }, { "epoch": 2.0253164556962027, "grad_norm": 0.47548502031855433, "learning_rate": 2.9604221019627316e-05, "loss": 0.3581, "step": 500 }, { "epoch": 2.0293670886075947, "grad_norm": 0.5519698558007704, "learning_rate": 2.955439637024526e-05, "loss": 0.3993, "step": 501 }, { "epoch": 2.0334177215189873, "grad_norm": 0.5768376184070848, "learning_rate": 2.9504494771068334e-05, "loss": 0.386, "step": 502 }, { "epoch": 2.0374683544303798, "grad_norm": 0.5844060604526423, "learning_rate": 2.9454516623997156e-05, "loss": 0.39, "step": 503 }, { "epoch": 2.0415189873417723, "grad_norm": 0.5479677970093806, "learning_rate": 2.9404462331548847e-05, "loss": 0.3668, "step": 504 }, { "epoch": 2.0455696202531644, "grad_norm": 0.530994502589991, "learning_rate": 2.93543322968538e-05, "loss": 0.3757, "step": 505 }, { "epoch": 2.049620253164557, "grad_norm": 0.5462360608924159, "learning_rate": 2.9304126923652428e-05, "loss": 0.3966, "step": 506 }, { "epoch": 2.0536708860759494, "grad_norm": 0.535070080516606, "learning_rate": 2.9253846616291896e-05, "loss": 0.3839, "step": 507 }, { "epoch": 2.057721518987342, "grad_norm": 0.5084010921675458, "learning_rate": 2.9203491779722896e-05, "loss": 0.3707, "step": 508 }, { "epoch": 2.061772151898734, "grad_norm": 0.47197443211354806, "learning_rate": 2.9153062819496357e-05, "loss": 0.3768, "step": 509 }, { "epoch": 2.0658227848101265, "grad_norm": 0.5151927666797854, "learning_rate": 2.9102560141760178e-05, "loss": 0.3949, "step": 510 }, { "epoch": 2.069873417721519, "grad_norm": 0.4268512765856956, "learning_rate": 2.9051984153256004e-05, "loss": 0.363, "step": 511 }, { "epoch": 2.0739240506329115, "grad_norm": 0.4477474959348708, "learning_rate": 2.900133526131588e-05, "loss": 0.371, "step": 512 }, { "epoch": 2.0779746835443036, "grad_norm": 0.4388070353301152, "learning_rate": 2.8950613873859025e-05, "loss": 0.3853, "step": 513 }, { "epoch": 2.082025316455696, "grad_norm": 0.43574578086982585, "learning_rate": 2.8899820399388515e-05, "loss": 0.3818, "step": 514 }, { "epoch": 2.0860759493670886, "grad_norm": 0.4458908677900068, "learning_rate": 2.8848955246988012e-05, "loss": 0.3683, "step": 515 }, { "epoch": 2.090126582278481, "grad_norm": 0.4278787121095434, "learning_rate": 2.879801882631847e-05, "loss": 0.3911, "step": 516 }, { "epoch": 2.094177215189873, "grad_norm": 0.4558593184354533, "learning_rate": 2.8747011547614808e-05, "loss": 0.39, "step": 517 }, { "epoch": 2.0982278481012657, "grad_norm": 0.43110286061129327, "learning_rate": 2.8695933821682635e-05, "loss": 0.3616, "step": 518 }, { "epoch": 2.1022784810126582, "grad_norm": 0.44915162894934907, "learning_rate": 2.864478605989494e-05, "loss": 0.38, "step": 519 }, { "epoch": 2.1063291139240508, "grad_norm": 0.42247216402523013, "learning_rate": 2.8593568674188765e-05, "loss": 0.3789, "step": 520 }, { "epoch": 2.110379746835443, "grad_norm": 0.45159014737359626, "learning_rate": 2.8542282077061892e-05, "loss": 0.3701, "step": 521 }, { "epoch": 2.1144303797468353, "grad_norm": 0.41601847686925325, "learning_rate": 2.8490926681569523e-05, "loss": 0.4041, "step": 522 }, { "epoch": 2.118481012658228, "grad_norm": 0.4475102076011316, "learning_rate": 2.8439502901320956e-05, "loss": 0.4179, "step": 523 }, { "epoch": 2.1225316455696204, "grad_norm": 0.402907171668536, "learning_rate": 2.8388011150476237e-05, "loss": 0.3815, "step": 524 }, { "epoch": 2.1265822784810124, "grad_norm": 0.4872047190036515, "learning_rate": 2.8336451843742866e-05, "loss": 0.3894, "step": 525 }, { "epoch": 2.130632911392405, "grad_norm": 0.4849418559624368, "learning_rate": 2.8284825396372387e-05, "loss": 0.3684, "step": 526 }, { "epoch": 2.1346835443037975, "grad_norm": 0.4163078542930195, "learning_rate": 2.8233132224157132e-05, "loss": 0.3983, "step": 527 }, { "epoch": 2.13873417721519, "grad_norm": 0.45305759962630815, "learning_rate": 2.8181372743426805e-05, "loss": 0.3857, "step": 528 }, { "epoch": 2.1427848101265825, "grad_norm": 0.3946754351662652, "learning_rate": 2.8129547371045128e-05, "loss": 0.3769, "step": 529 }, { "epoch": 2.1468354430379746, "grad_norm": 0.45393462349869146, "learning_rate": 2.8077656524406534e-05, "loss": 0.3614, "step": 530 }, { "epoch": 2.150886075949367, "grad_norm": 0.41268318037305957, "learning_rate": 2.802570062143278e-05, "loss": 0.404, "step": 531 }, { "epoch": 2.1549367088607596, "grad_norm": 0.4722821673002892, "learning_rate": 2.7973680080569555e-05, "loss": 0.3887, "step": 532 }, { "epoch": 2.1589873417721517, "grad_norm": 0.41071761908922666, "learning_rate": 2.792159532078314e-05, "loss": 0.3887, "step": 533 }, { "epoch": 2.163037974683544, "grad_norm": 0.4688547011591317, "learning_rate": 2.7869446761557033e-05, "loss": 0.3595, "step": 534 }, { "epoch": 2.1670886075949367, "grad_norm": 0.45507727447260454, "learning_rate": 2.781723482288857e-05, "loss": 0.3959, "step": 535 }, { "epoch": 2.1711392405063292, "grad_norm": 0.45541735280590834, "learning_rate": 2.7764959925285517e-05, "loss": 0.3903, "step": 536 }, { "epoch": 2.1751898734177217, "grad_norm": 0.4617458190797676, "learning_rate": 2.771262248976272e-05, "loss": 0.3745, "step": 537 }, { "epoch": 2.179240506329114, "grad_norm": 0.46453244619951795, "learning_rate": 2.7660222937838677e-05, "loss": 0.3996, "step": 538 }, { "epoch": 2.1832911392405063, "grad_norm": 0.4582917053524638, "learning_rate": 2.7607761691532186e-05, "loss": 0.3861, "step": 539 }, { "epoch": 2.187341772151899, "grad_norm": 0.4928658399478945, "learning_rate": 2.7555239173358916e-05, "loss": 0.3825, "step": 540 }, { "epoch": 2.191392405063291, "grad_norm": 0.43952462628025657, "learning_rate": 2.7502655806328e-05, "loss": 0.3788, "step": 541 }, { "epoch": 2.1954430379746834, "grad_norm": 0.42057266009544353, "learning_rate": 2.7450012013938648e-05, "loss": 0.3891, "step": 542 }, { "epoch": 2.199493670886076, "grad_norm": 0.4948839054840683, "learning_rate": 2.739730822017673e-05, "loss": 0.3651, "step": 543 }, { "epoch": 2.2035443037974685, "grad_norm": 0.443485004505028, "learning_rate": 2.7344544849511355e-05, "loss": 0.3841, "step": 544 }, { "epoch": 2.207594936708861, "grad_norm": 0.469401171673092, "learning_rate": 2.7291722326891456e-05, "loss": 0.3862, "step": 545 }, { "epoch": 2.211645569620253, "grad_norm": 0.44298507303405543, "learning_rate": 2.723884107774236e-05, "loss": 0.3859, "step": 546 }, { "epoch": 2.2156962025316456, "grad_norm": 0.4579854970432588, "learning_rate": 2.718590152796239e-05, "loss": 0.3713, "step": 547 }, { "epoch": 2.219746835443038, "grad_norm": 0.4015457942765575, "learning_rate": 2.71329041039194e-05, "loss": 0.3717, "step": 548 }, { "epoch": 2.22379746835443, "grad_norm": 0.4072974468079946, "learning_rate": 2.7079849232447357e-05, "loss": 0.3962, "step": 549 }, { "epoch": 2.2278481012658227, "grad_norm": 0.44218303847102597, "learning_rate": 2.7026737340842895e-05, "loss": 0.3974, "step": 550 }, { "epoch": 2.231898734177215, "grad_norm": 0.43106947710778243, "learning_rate": 2.697356885686189e-05, "loss": 0.392, "step": 551 }, { "epoch": 2.2359493670886077, "grad_norm": 0.45805283114864337, "learning_rate": 2.6920344208716014e-05, "loss": 0.388, "step": 552 }, { "epoch": 2.24, "grad_norm": 0.45714597059627704, "learning_rate": 2.6867063825069252e-05, "loss": 0.3664, "step": 553 }, { "epoch": 2.2440506329113923, "grad_norm": 0.4150969094682427, "learning_rate": 2.6813728135034494e-05, "loss": 0.4068, "step": 554 }, { "epoch": 2.248101265822785, "grad_norm": 0.46045613669929286, "learning_rate": 2.6760337568170056e-05, "loss": 0.3815, "step": 555 }, { "epoch": 2.2521518987341773, "grad_norm": 0.4247740644792364, "learning_rate": 2.6706892554476226e-05, "loss": 0.3801, "step": 556 }, { "epoch": 2.2562025316455694, "grad_norm": 0.43862304124518114, "learning_rate": 2.6653393524391795e-05, "loss": 0.3835, "step": 557 }, { "epoch": 2.260253164556962, "grad_norm": 0.4320117972559154, "learning_rate": 2.6599840908790592e-05, "loss": 0.3624, "step": 558 }, { "epoch": 2.2643037974683544, "grad_norm": 0.4550877055928488, "learning_rate": 2.6546235138978028e-05, "loss": 0.389, "step": 559 }, { "epoch": 2.268354430379747, "grad_norm": 0.4120477164956628, "learning_rate": 2.6492576646687597e-05, "loss": 0.3756, "step": 560 }, { "epoch": 2.2724050632911394, "grad_norm": 0.3999477025552762, "learning_rate": 2.6438865864077425e-05, "loss": 0.3852, "step": 561 }, { "epoch": 2.2764556962025315, "grad_norm": 0.4238924127687483, "learning_rate": 2.6385103223726766e-05, "loss": 0.3865, "step": 562 }, { "epoch": 2.280506329113924, "grad_norm": 0.4470833986497391, "learning_rate": 2.6331289158632537e-05, "loss": 0.3735, "step": 563 }, { "epoch": 2.2845569620253166, "grad_norm": 0.42225505952306747, "learning_rate": 2.6277424102205817e-05, "loss": 0.4031, "step": 564 }, { "epoch": 2.2886075949367086, "grad_norm": 0.4538350305511245, "learning_rate": 2.6223508488268374e-05, "loss": 0.408, "step": 565 }, { "epoch": 2.292658227848101, "grad_norm": 0.42032642433834994, "learning_rate": 2.6169542751049148e-05, "loss": 0.3891, "step": 566 }, { "epoch": 2.2967088607594937, "grad_norm": 0.46243518609638473, "learning_rate": 2.6115527325180754e-05, "loss": 0.3745, "step": 567 }, { "epoch": 2.300759493670886, "grad_norm": 0.4171032354877834, "learning_rate": 2.606146264569603e-05, "loss": 0.366, "step": 568 }, { "epoch": 2.3048101265822787, "grad_norm": 0.46901997378855753, "learning_rate": 2.6007349148024447e-05, "loss": 0.3827, "step": 569 }, { "epoch": 2.3088607594936708, "grad_norm": 0.44137382708760725, "learning_rate": 2.5953187267988694e-05, "loss": 0.3854, "step": 570 }, { "epoch": 2.3129113924050633, "grad_norm": 0.46445570861889274, "learning_rate": 2.5898977441801097e-05, "loss": 0.4048, "step": 571 }, { "epoch": 2.316962025316456, "grad_norm": 0.43420700202254314, "learning_rate": 2.584472010606015e-05, "loss": 0.3911, "step": 572 }, { "epoch": 2.321012658227848, "grad_norm": 0.42600980991623966, "learning_rate": 2.5790415697746976e-05, "loss": 0.3987, "step": 573 }, { "epoch": 2.3250632911392404, "grad_norm": 0.43223838229213385, "learning_rate": 2.5736064654221808e-05, "loss": 0.3855, "step": 574 }, { "epoch": 2.329113924050633, "grad_norm": 0.408401291800542, "learning_rate": 2.568166741322048e-05, "loss": 0.3939, "step": 575 }, { "epoch": 2.3331645569620254, "grad_norm": 0.41872667074975256, "learning_rate": 2.56272244128509e-05, "loss": 0.3985, "step": 576 }, { "epoch": 2.337215189873418, "grad_norm": 0.4779494722216298, "learning_rate": 2.55727360915895e-05, "loss": 0.3782, "step": 577 }, { "epoch": 2.34126582278481, "grad_norm": 0.39704466968193436, "learning_rate": 2.5518202888277734e-05, "loss": 0.4022, "step": 578 }, { "epoch": 2.3453164556962025, "grad_norm": 0.41069144432386845, "learning_rate": 2.5463625242118523e-05, "loss": 0.3767, "step": 579 }, { "epoch": 2.349367088607595, "grad_norm": 0.4865926580428488, "learning_rate": 2.5409003592672723e-05, "loss": 0.3897, "step": 580 }, { "epoch": 2.353417721518987, "grad_norm": 0.40787541191299925, "learning_rate": 2.535433837985559e-05, "loss": 0.3929, "step": 581 }, { "epoch": 2.3574683544303796, "grad_norm": 0.54394340579995, "learning_rate": 2.529963004393324e-05, "loss": 0.3723, "step": 582 }, { "epoch": 2.361518987341772, "grad_norm": 0.40919553376116635, "learning_rate": 2.524487902551908e-05, "loss": 0.39, "step": 583 }, { "epoch": 2.3655696202531646, "grad_norm": 0.4564585274536954, "learning_rate": 2.519008576557029e-05, "loss": 0.3836, "step": 584 }, { "epoch": 2.369620253164557, "grad_norm": 0.42887344552803436, "learning_rate": 2.5135250705384254e-05, "loss": 0.3741, "step": 585 }, { "epoch": 2.3736708860759492, "grad_norm": 0.4938311933928425, "learning_rate": 2.5080374286595007e-05, "loss": 0.3815, "step": 586 }, { "epoch": 2.3777215189873417, "grad_norm": 0.39835111850626687, "learning_rate": 2.5025456951169677e-05, "loss": 0.3912, "step": 587 }, { "epoch": 2.3817721518987343, "grad_norm": 0.49987401392113917, "learning_rate": 2.4970499141404942e-05, "loss": 0.3759, "step": 588 }, { "epoch": 2.3858227848101268, "grad_norm": 0.40242314575136207, "learning_rate": 2.491550129992345e-05, "loss": 0.3969, "step": 589 }, { "epoch": 2.389873417721519, "grad_norm": 0.44794596905648093, "learning_rate": 2.486046386967024e-05, "loss": 0.4048, "step": 590 }, { "epoch": 2.3939240506329114, "grad_norm": 0.461318538459364, "learning_rate": 2.4805387293909214e-05, "loss": 0.366, "step": 591 }, { "epoch": 2.397974683544304, "grad_norm": 0.42271834513903134, "learning_rate": 2.4750272016219552e-05, "loss": 0.4026, "step": 592 }, { "epoch": 2.4020253164556964, "grad_norm": 0.4212451975932134, "learning_rate": 2.4695118480492114e-05, "loss": 0.393, "step": 593 }, { "epoch": 2.4060759493670885, "grad_norm": 0.4711635145182656, "learning_rate": 2.4639927130925898e-05, "loss": 0.3914, "step": 594 }, { "epoch": 2.410126582278481, "grad_norm": 0.4340607140544032, "learning_rate": 2.458469841202444e-05, "loss": 0.3979, "step": 595 }, { "epoch": 2.4141772151898735, "grad_norm": 0.3971359972636412, "learning_rate": 2.452943276859226e-05, "loss": 0.3842, "step": 596 }, { "epoch": 2.418227848101266, "grad_norm": 0.425183350958858, "learning_rate": 2.447413064573125e-05, "loss": 0.3884, "step": 597 }, { "epoch": 2.422278481012658, "grad_norm": 0.4194120043831294, "learning_rate": 2.4418792488837095e-05, "loss": 0.3813, "step": 598 }, { "epoch": 2.4263291139240506, "grad_norm": 0.42155721814491126, "learning_rate": 2.4363418743595713e-05, "loss": 0.3747, "step": 599 }, { "epoch": 2.430379746835443, "grad_norm": 0.4303430105761273, "learning_rate": 2.430800985597963e-05, "loss": 0.3869, "step": 600 }, { "epoch": 2.4344303797468356, "grad_norm": 0.46851543377932653, "learning_rate": 2.4252566272244415e-05, "loss": 0.3873, "step": 601 }, { "epoch": 2.4384810126582277, "grad_norm": 0.4125101767502836, "learning_rate": 2.4197088438925063e-05, "loss": 0.4026, "step": 602 }, { "epoch": 2.44253164556962, "grad_norm": 0.4227035930037927, "learning_rate": 2.4141576802832417e-05, "loss": 0.3925, "step": 603 }, { "epoch": 2.4465822784810127, "grad_norm": 0.40392322591057034, "learning_rate": 2.408603181104957e-05, "loss": 0.3889, "step": 604 }, { "epoch": 2.4506329113924052, "grad_norm": 0.41828412197234605, "learning_rate": 2.4030453910928245e-05, "loss": 0.3814, "step": 605 }, { "epoch": 2.4546835443037973, "grad_norm": 0.3947456999810473, "learning_rate": 2.397484355008521e-05, "loss": 0.4109, "step": 606 }, { "epoch": 2.45873417721519, "grad_norm": 0.40750962693010573, "learning_rate": 2.3919201176398662e-05, "loss": 0.4061, "step": 607 }, { "epoch": 2.4627848101265823, "grad_norm": 0.39212287187345457, "learning_rate": 2.3863527238004633e-05, "loss": 0.3782, "step": 608 }, { "epoch": 2.466835443037975, "grad_norm": 0.4295942639698751, "learning_rate": 2.380782218329337e-05, "loss": 0.3871, "step": 609 }, { "epoch": 2.470886075949367, "grad_norm": 0.39951000854479773, "learning_rate": 2.3752086460905725e-05, "loss": 0.3992, "step": 610 }, { "epoch": 2.4749367088607594, "grad_norm": 0.6702884889852437, "learning_rate": 2.3696320519729544e-05, "loss": 0.4084, "step": 611 }, { "epoch": 2.478987341772152, "grad_norm": 0.4072688410642632, "learning_rate": 2.3640524808896045e-05, "loss": 0.3964, "step": 612 }, { "epoch": 2.4830379746835445, "grad_norm": 0.3824721594104524, "learning_rate": 2.3584699777776222e-05, "loss": 0.3892, "step": 613 }, { "epoch": 2.4870886075949366, "grad_norm": 0.41001199898513135, "learning_rate": 2.3528845875977195e-05, "loss": 0.4006, "step": 614 }, { "epoch": 2.491139240506329, "grad_norm": 0.40846077149665, "learning_rate": 2.3472963553338614e-05, "loss": 0.3918, "step": 615 }, { "epoch": 2.4951898734177216, "grad_norm": 0.3855902282190395, "learning_rate": 2.341705325992901e-05, "loss": 0.3859, "step": 616 }, { "epoch": 2.499240506329114, "grad_norm": 0.4166540163293816, "learning_rate": 2.336111544604222e-05, "loss": 0.3846, "step": 617 }, { "epoch": 2.503291139240506, "grad_norm": 0.4058785521980099, "learning_rate": 2.33051505621937e-05, "loss": 0.3834, "step": 618 }, { "epoch": 2.5073417721518987, "grad_norm": 0.41382222207052305, "learning_rate": 2.324915905911693e-05, "loss": 0.3713, "step": 619 }, { "epoch": 2.511392405063291, "grad_norm": 0.4748296075540585, "learning_rate": 2.319314138775977e-05, "loss": 0.3921, "step": 620 }, { "epoch": 2.5154430379746833, "grad_norm": 0.40158627077914383, "learning_rate": 2.3137097999280856e-05, "loss": 0.3844, "step": 621 }, { "epoch": 2.519493670886076, "grad_norm": 0.45246908240082634, "learning_rate": 2.308102934504593e-05, "loss": 0.3963, "step": 622 }, { "epoch": 2.5235443037974683, "grad_norm": 0.44707022237471833, "learning_rate": 2.3024935876624222e-05, "loss": 0.3891, "step": 623 }, { "epoch": 2.527594936708861, "grad_norm": 0.4024164770338796, "learning_rate": 2.2968818045784813e-05, "loss": 0.3914, "step": 624 }, { "epoch": 2.5316455696202533, "grad_norm": 0.4645617289512509, "learning_rate": 2.2912676304493006e-05, "loss": 0.4108, "step": 625 }, { "epoch": 2.5356962025316454, "grad_norm": 0.40460298063385935, "learning_rate": 2.2856511104906668e-05, "loss": 0.3881, "step": 626 }, { "epoch": 2.539746835443038, "grad_norm": 0.41408346425811454, "learning_rate": 2.2800322899372586e-05, "loss": 0.3666, "step": 627 }, { "epoch": 2.5437974683544304, "grad_norm": 0.42060539262576996, "learning_rate": 2.2744112140422844e-05, "loss": 0.3922, "step": 628 }, { "epoch": 2.547848101265823, "grad_norm": 0.4170878251019115, "learning_rate": 2.2687879280771177e-05, "loss": 0.3711, "step": 629 }, { "epoch": 2.5518987341772155, "grad_norm": 0.4098585133040683, "learning_rate": 2.26316247733093e-05, "loss": 0.3763, "step": 630 }, { "epoch": 2.5559493670886075, "grad_norm": 0.3823241401924837, "learning_rate": 2.257534907110328e-05, "loss": 0.3838, "step": 631 }, { "epoch": 2.56, "grad_norm": 0.3879564799082583, "learning_rate": 2.2519052627389882e-05, "loss": 0.4003, "step": 632 }, { "epoch": 2.5640506329113926, "grad_norm": 0.3930410193793213, "learning_rate": 2.246273589557294e-05, "loss": 0.3656, "step": 633 }, { "epoch": 2.5681012658227846, "grad_norm": 0.40409295802490225, "learning_rate": 2.240639932921966e-05, "loss": 0.3943, "step": 634 }, { "epoch": 2.572151898734177, "grad_norm": 0.41456940804929804, "learning_rate": 2.2350043382056995e-05, "loss": 0.3869, "step": 635 }, { "epoch": 2.5762025316455697, "grad_norm": 0.4151062248324495, "learning_rate": 2.2293668507968015e-05, "loss": 0.3764, "step": 636 }, { "epoch": 2.580253164556962, "grad_norm": 0.4102022375791724, "learning_rate": 2.2237275160988186e-05, "loss": 0.375, "step": 637 }, { "epoch": 2.5843037974683547, "grad_norm": 0.45044580124516465, "learning_rate": 2.2180863795301787e-05, "loss": 0.3724, "step": 638 }, { "epoch": 2.5883544303797468, "grad_norm": 0.39319397741147205, "learning_rate": 2.212443486523819e-05, "loss": 0.364, "step": 639 }, { "epoch": 2.5924050632911393, "grad_norm": 0.4301161400728622, "learning_rate": 2.2067988825268243e-05, "loss": 0.4164, "step": 640 }, { "epoch": 2.596455696202532, "grad_norm": 0.4496147081351878, "learning_rate": 2.2011526130000596e-05, "loss": 0.3884, "step": 641 }, { "epoch": 2.600506329113924, "grad_norm": 0.4380598397962131, "learning_rate": 2.1955047234178038e-05, "loss": 0.3769, "step": 642 }, { "epoch": 2.6045569620253164, "grad_norm": 0.41919044703087177, "learning_rate": 2.1898552592673825e-05, "loss": 0.3793, "step": 643 }, { "epoch": 2.608607594936709, "grad_norm": 0.40163929054003245, "learning_rate": 2.184204266048803e-05, "loss": 0.3924, "step": 644 }, { "epoch": 2.6126582278481014, "grad_norm": 0.4254969341674674, "learning_rate": 2.1785517892743887e-05, "loss": 0.3733, "step": 645 }, { "epoch": 2.616708860759494, "grad_norm": 0.41433810725503406, "learning_rate": 2.17289787446841e-05, "loss": 0.3788, "step": 646 }, { "epoch": 2.620759493670886, "grad_norm": 0.39900904131928877, "learning_rate": 2.1672425671667198e-05, "loss": 0.3709, "step": 647 }, { "epoch": 2.6248101265822785, "grad_norm": 0.389549230103763, "learning_rate": 2.161585912916385e-05, "loss": 0.3927, "step": 648 }, { "epoch": 2.628860759493671, "grad_norm": 0.406000623876316, "learning_rate": 2.1559279572753214e-05, "loss": 0.3885, "step": 649 }, { "epoch": 2.632911392405063, "grad_norm": 0.3964281380206775, "learning_rate": 2.1502687458119268e-05, "loss": 0.3804, "step": 650 }, { "epoch": 2.6369620253164556, "grad_norm": 0.39851176692188095, "learning_rate": 2.1446083241047116e-05, "loss": 0.4042, "step": 651 }, { "epoch": 2.641012658227848, "grad_norm": 0.35297578579993916, "learning_rate": 2.1389467377419333e-05, "loss": 0.3847, "step": 652 }, { "epoch": 2.6450632911392407, "grad_norm": 0.4287966284833857, "learning_rate": 2.133284032321232e-05, "loss": 0.3832, "step": 653 }, { "epoch": 2.649113924050633, "grad_norm": 0.40060665277621876, "learning_rate": 2.1276202534492566e-05, "loss": 0.3877, "step": 654 }, { "epoch": 2.6531645569620252, "grad_norm": 0.37963336052095, "learning_rate": 2.121955446741306e-05, "loss": 0.3836, "step": 655 }, { "epoch": 2.6572151898734178, "grad_norm": 0.4176687287200673, "learning_rate": 2.1162896578209517e-05, "loss": 0.3978, "step": 656 }, { "epoch": 2.6612658227848103, "grad_norm": 0.39706813822951287, "learning_rate": 2.1106229323196813e-05, "loss": 0.3975, "step": 657 }, { "epoch": 2.6653164556962023, "grad_norm": 0.38702457383040445, "learning_rate": 2.1049553158765214e-05, "loss": 0.3682, "step": 658 }, { "epoch": 2.669367088607595, "grad_norm": 0.4538595787628643, "learning_rate": 2.0992868541376764e-05, "loss": 0.3838, "step": 659 }, { "epoch": 2.6734177215189874, "grad_norm": 0.3825854561330915, "learning_rate": 2.093617592756158e-05, "loss": 0.4073, "step": 660 }, { "epoch": 2.67746835443038, "grad_norm": 0.43779057611292194, "learning_rate": 2.0879475773914167e-05, "loss": 0.3875, "step": 661 }, { "epoch": 2.6815189873417724, "grad_norm": 0.4764993590732858, "learning_rate": 2.082276853708978e-05, "loss": 0.3975, "step": 662 }, { "epoch": 2.6855696202531645, "grad_norm": 0.3902917169888842, "learning_rate": 2.076605467380071e-05, "loss": 0.3865, "step": 663 }, { "epoch": 2.689620253164557, "grad_norm": 0.4370687498237814, "learning_rate": 2.0709334640812613e-05, "loss": 0.3799, "step": 664 }, { "epoch": 2.6936708860759495, "grad_norm": 0.39870021291748264, "learning_rate": 2.0652608894940824e-05, "loss": 0.3937, "step": 665 }, { "epoch": 2.6977215189873416, "grad_norm": 0.4071636504879817, "learning_rate": 2.0595877893046722e-05, "loss": 0.3875, "step": 666 }, { "epoch": 2.701772151898734, "grad_norm": 0.38979747967369666, "learning_rate": 2.0539142092033985e-05, "loss": 0.374, "step": 667 }, { "epoch": 2.7058227848101266, "grad_norm": 0.4053319043338533, "learning_rate": 2.048240194884496e-05, "loss": 0.3587, "step": 668 }, { "epoch": 2.709873417721519, "grad_norm": 0.4109872288488362, "learning_rate": 2.042565792045695e-05, "loss": 0.3794, "step": 669 }, { "epoch": 2.7139240506329116, "grad_norm": 0.4224032526858377, "learning_rate": 2.036891046387857e-05, "loss": 0.3839, "step": 670 }, { "epoch": 2.7179746835443037, "grad_norm": 0.4146075596852, "learning_rate": 2.0312160036146036e-05, "loss": 0.3881, "step": 671 }, { "epoch": 2.7220253164556962, "grad_norm": 0.39490688876442714, "learning_rate": 2.025540709431948e-05, "loss": 0.3989, "step": 672 }, { "epoch": 2.7260759493670887, "grad_norm": 0.4259477770580668, "learning_rate": 2.0198652095479298e-05, "loss": 0.3763, "step": 673 }, { "epoch": 2.730126582278481, "grad_norm": 0.41644367135111426, "learning_rate": 2.014189549672245e-05, "loss": 0.3953, "step": 674 }, { "epoch": 2.7341772151898733, "grad_norm": 0.413544167666992, "learning_rate": 2.0085137755158776e-05, "loss": 0.397, "step": 675 }, { "epoch": 2.738227848101266, "grad_norm": 0.41671147750438803, "learning_rate": 2.0028379327907327e-05, "loss": 0.3981, "step": 676 }, { "epoch": 2.7422784810126584, "grad_norm": 0.3664869914858462, "learning_rate": 1.9971620672092676e-05, "loss": 0.3918, "step": 677 }, { "epoch": 2.746329113924051, "grad_norm": 0.3902589481444191, "learning_rate": 1.991486224484123e-05, "loss": 0.4224, "step": 678 }, { "epoch": 2.750379746835443, "grad_norm": 0.39373672394712556, "learning_rate": 1.985810450327756e-05, "loss": 0.3874, "step": 679 }, { "epoch": 2.7544303797468355, "grad_norm": 0.3921136283117895, "learning_rate": 1.9801347904520706e-05, "loss": 0.3601, "step": 680 }, { "epoch": 2.758481012658228, "grad_norm": 0.4018228728150242, "learning_rate": 1.974459290568053e-05, "loss": 0.3821, "step": 681 }, { "epoch": 2.76253164556962, "grad_norm": 0.40408280695314575, "learning_rate": 1.968783996385397e-05, "loss": 0.402, "step": 682 }, { "epoch": 2.7665822784810126, "grad_norm": 0.3995340504486028, "learning_rate": 1.963108953612143e-05, "loss": 0.3753, "step": 683 }, { "epoch": 2.770632911392405, "grad_norm": 0.3692011018856559, "learning_rate": 1.9574342079543056e-05, "loss": 0.3965, "step": 684 }, { "epoch": 2.7746835443037976, "grad_norm": 0.42517330345872467, "learning_rate": 1.9517598051155046e-05, "loss": 0.3522, "step": 685 }, { "epoch": 2.77873417721519, "grad_norm": 0.39658475431612455, "learning_rate": 1.9460857907966025e-05, "loss": 0.381, "step": 686 }, { "epoch": 2.782784810126582, "grad_norm": 0.3862850449286376, "learning_rate": 1.9404122106953285e-05, "loss": 0.3718, "step": 687 }, { "epoch": 2.7868354430379747, "grad_norm": 0.3836618318084305, "learning_rate": 1.9347391105059176e-05, "loss": 0.3797, "step": 688 }, { "epoch": 2.790886075949367, "grad_norm": 0.4091632287936817, "learning_rate": 1.92906653591874e-05, "loss": 0.3763, "step": 689 }, { "epoch": 2.7949367088607593, "grad_norm": 0.40736018525332574, "learning_rate": 1.9233945326199295e-05, "loss": 0.3864, "step": 690 }, { "epoch": 2.798987341772152, "grad_norm": 0.39211782274028534, "learning_rate": 1.917723146291022e-05, "loss": 0.3885, "step": 691 }, { "epoch": 2.8030379746835443, "grad_norm": 0.4450414862733952, "learning_rate": 1.912052422608584e-05, "loss": 0.397, "step": 692 }, { "epoch": 2.807088607594937, "grad_norm": 0.42066432788252967, "learning_rate": 1.9063824072438428e-05, "loss": 0.3904, "step": 693 }, { "epoch": 2.8111392405063294, "grad_norm": 0.4191653386882582, "learning_rate": 1.9007131458623246e-05, "loss": 0.3698, "step": 694 }, { "epoch": 2.8151898734177214, "grad_norm": 0.400646956511416, "learning_rate": 1.895044684123479e-05, "loss": 0.4038, "step": 695 }, { "epoch": 2.819240506329114, "grad_norm": 0.3997240943962438, "learning_rate": 1.8893770676803194e-05, "loss": 0.3735, "step": 696 }, { "epoch": 2.8232911392405065, "grad_norm": 0.3911593340041176, "learning_rate": 1.8837103421790486e-05, "loss": 0.3837, "step": 697 }, { "epoch": 2.8273417721518985, "grad_norm": 0.4057241735303669, "learning_rate": 1.8780445532586952e-05, "loss": 0.3941, "step": 698 }, { "epoch": 2.831392405063291, "grad_norm": 0.4119997890684499, "learning_rate": 1.872379746550743e-05, "loss": 0.3774, "step": 699 }, { "epoch": 2.8354430379746836, "grad_norm": 0.38109055856746904, "learning_rate": 1.866715967678769e-05, "loss": 0.3979, "step": 700 }, { "epoch": 2.839493670886076, "grad_norm": 0.40662465337131715, "learning_rate": 1.861053262258067e-05, "loss": 0.394, "step": 701 }, { "epoch": 2.8435443037974686, "grad_norm": 0.4152092831807893, "learning_rate": 1.8553916758952897e-05, "loss": 0.3969, "step": 702 }, { "epoch": 2.8475949367088607, "grad_norm": 0.40708822085486823, "learning_rate": 1.8497312541880735e-05, "loss": 0.3616, "step": 703 }, { "epoch": 2.851645569620253, "grad_norm": 0.38460483822251956, "learning_rate": 1.8440720427246786e-05, "loss": 0.3932, "step": 704 }, { "epoch": 2.8556962025316457, "grad_norm": 0.43240892144540055, "learning_rate": 1.8384140870836157e-05, "loss": 0.3633, "step": 705 }, { "epoch": 2.8597468354430378, "grad_norm": 0.39200482686126914, "learning_rate": 1.8327574328332806e-05, "loss": 0.3663, "step": 706 }, { "epoch": 2.8637974683544303, "grad_norm": 0.42653836997102995, "learning_rate": 1.8271021255315906e-05, "loss": 0.3607, "step": 707 }, { "epoch": 2.867848101265823, "grad_norm": 0.3993930699363668, "learning_rate": 1.8214482107256117e-05, "loss": 0.408, "step": 708 }, { "epoch": 2.8718987341772153, "grad_norm": 0.4029403456601067, "learning_rate": 1.8157957339511968e-05, "loss": 0.3733, "step": 709 }, { "epoch": 2.875949367088608, "grad_norm": 0.42317304385129356, "learning_rate": 1.8101447407326182e-05, "loss": 0.389, "step": 710 }, { "epoch": 2.88, "grad_norm": 0.38940342464252076, "learning_rate": 1.8044952765821966e-05, "loss": 0.3863, "step": 711 }, { "epoch": 2.8840506329113924, "grad_norm": 0.4261189397717305, "learning_rate": 1.7988473869999407e-05, "loss": 0.3519, "step": 712 }, { "epoch": 2.888101265822785, "grad_norm": 0.3713276022665488, "learning_rate": 1.7932011174731764e-05, "loss": 0.399, "step": 713 }, { "epoch": 2.892151898734177, "grad_norm": 0.4291947621140841, "learning_rate": 1.7875565134761817e-05, "loss": 0.3815, "step": 714 }, { "epoch": 2.8962025316455695, "grad_norm": 0.40604330224993795, "learning_rate": 1.7819136204698226e-05, "loss": 0.3793, "step": 715 }, { "epoch": 2.900253164556962, "grad_norm": 0.4090684834854848, "learning_rate": 1.776272483901182e-05, "loss": 0.3909, "step": 716 }, { "epoch": 2.9043037974683545, "grad_norm": 0.458518758725882, "learning_rate": 1.7706331492031995e-05, "loss": 0.3954, "step": 717 }, { "epoch": 2.908354430379747, "grad_norm": 0.3948617627678639, "learning_rate": 1.764995661794301e-05, "loss": 0.388, "step": 718 }, { "epoch": 2.912405063291139, "grad_norm": 0.39991692600126993, "learning_rate": 1.759360067078035e-05, "loss": 0.3884, "step": 719 }, { "epoch": 2.9164556962025316, "grad_norm": 0.44580694188016196, "learning_rate": 1.7537264104427064e-05, "loss": 0.3969, "step": 720 }, { "epoch": 2.920506329113924, "grad_norm": 0.399435962771365, "learning_rate": 1.748094737261012e-05, "loss": 0.3673, "step": 721 }, { "epoch": 2.9245569620253162, "grad_norm": 0.4085491109727255, "learning_rate": 1.7424650928896726e-05, "loss": 0.3881, "step": 722 }, { "epoch": 2.9286075949367087, "grad_norm": 0.427685768886352, "learning_rate": 1.7368375226690712e-05, "loss": 0.3849, "step": 723 }, { "epoch": 2.9326582278481013, "grad_norm": 0.3743929045965576, "learning_rate": 1.731212071922883e-05, "loss": 0.3905, "step": 724 }, { "epoch": 2.9367088607594938, "grad_norm": 0.42708674507006256, "learning_rate": 1.7255887859577156e-05, "loss": 0.3593, "step": 725 }, { "epoch": 2.9407594936708863, "grad_norm": 0.39631679063457603, "learning_rate": 1.7199677100627427e-05, "loss": 0.3595, "step": 726 }, { "epoch": 2.9448101265822784, "grad_norm": 0.38072902899907707, "learning_rate": 1.7143488895093343e-05, "loss": 0.3831, "step": 727 }, { "epoch": 2.948860759493671, "grad_norm": 0.41060926398242714, "learning_rate": 1.7087323695506994e-05, "loss": 0.3494, "step": 728 }, { "epoch": 2.9529113924050634, "grad_norm": 0.4366837897214133, "learning_rate": 1.7031181954215194e-05, "loss": 0.3915, "step": 729 }, { "epoch": 2.9569620253164555, "grad_norm": 0.4304615026067366, "learning_rate": 1.6975064123375788e-05, "loss": 0.3848, "step": 730 }, { "epoch": 2.961012658227848, "grad_norm": 0.42100111240918187, "learning_rate": 1.6918970654954084e-05, "loss": 0.3772, "step": 731 }, { "epoch": 2.9650632911392405, "grad_norm": 0.41152704517795635, "learning_rate": 1.686290200071915e-05, "loss": 0.3883, "step": 732 }, { "epoch": 2.969113924050633, "grad_norm": 0.40947464554489166, "learning_rate": 1.6806858612240234e-05, "loss": 0.3699, "step": 733 }, { "epoch": 2.9731645569620255, "grad_norm": 0.41713673406975, "learning_rate": 1.6750840940883078e-05, "loss": 0.4267, "step": 734 }, { "epoch": 2.9772151898734176, "grad_norm": 0.3924285379785786, "learning_rate": 1.6694849437806305e-05, "loss": 0.4005, "step": 735 }, { "epoch": 2.98126582278481, "grad_norm": 0.41486473003139873, "learning_rate": 1.663888455395778e-05, "loss": 0.3879, "step": 736 }, { "epoch": 2.9853164556962026, "grad_norm": 0.3965813923196384, "learning_rate": 1.6582946740070995e-05, "loss": 0.3813, "step": 737 }, { "epoch": 2.9893670886075947, "grad_norm": 0.4110662482712831, "learning_rate": 1.6527036446661396e-05, "loss": 0.3795, "step": 738 }, { "epoch": 2.993417721518987, "grad_norm": 0.4123576505819131, "learning_rate": 1.6471154124022818e-05, "loss": 0.3885, "step": 739 }, { "epoch": 2.9974683544303797, "grad_norm": 0.4225397757406159, "learning_rate": 1.6415300222223788e-05, "loss": 0.3854, "step": 740 }, { "epoch": 3.0015189873417722, "grad_norm": 0.43191153139404626, "learning_rate": 1.6359475191103958e-05, "loss": 0.3382, "step": 741 }, { "epoch": 3.0055696202531648, "grad_norm": 0.5452527167197785, "learning_rate": 1.6303679480270466e-05, "loss": 0.2663, "step": 742 }, { "epoch": 3.009620253164557, "grad_norm": 0.40327970092746285, "learning_rate": 1.624791353909428e-05, "loss": 0.2818, "step": 743 }, { "epoch": 3.0136708860759494, "grad_norm": 0.6802109853783359, "learning_rate": 1.619217781670663e-05, "loss": 0.2685, "step": 744 }, { "epoch": 3.017721518987342, "grad_norm": 0.5493765488457371, "learning_rate": 1.6136472761995373e-05, "loss": 0.2615, "step": 745 }, { "epoch": 3.0217721518987344, "grad_norm": 0.5495668556134014, "learning_rate": 1.608079882360134e-05, "loss": 0.262, "step": 746 }, { "epoch": 3.0258227848101265, "grad_norm": 0.5692404040708074, "learning_rate": 1.60251564499148e-05, "loss": 0.283, "step": 747 }, { "epoch": 3.029873417721519, "grad_norm": 0.4596237553959502, "learning_rate": 1.596954608907176e-05, "loss": 0.2845, "step": 748 }, { "epoch": 3.0339240506329115, "grad_norm": 0.44183843156862823, "learning_rate": 1.591396818895043e-05, "loss": 0.268, "step": 749 }, { "epoch": 3.037974683544304, "grad_norm": 0.5034823227431466, "learning_rate": 1.585842319716759e-05, "loss": 0.27, "step": 750 }, { "epoch": 3.042025316455696, "grad_norm": 0.5143480226122105, "learning_rate": 1.5802911561074944e-05, "loss": 0.2556, "step": 751 }, { "epoch": 3.0460759493670886, "grad_norm": 0.40753414664004867, "learning_rate": 1.5747433727755595e-05, "loss": 0.2746, "step": 752 }, { "epoch": 3.050126582278481, "grad_norm": 0.44763762202378204, "learning_rate": 1.5691990144020376e-05, "loss": 0.2577, "step": 753 }, { "epoch": 3.0541772151898736, "grad_norm": 0.5033475312502927, "learning_rate": 1.5636581256404297e-05, "loss": 0.2708, "step": 754 }, { "epoch": 3.0582278481012657, "grad_norm": 0.3843960837305884, "learning_rate": 1.558120751116291e-05, "loss": 0.2709, "step": 755 }, { "epoch": 3.062278481012658, "grad_norm": 0.4079441498773003, "learning_rate": 1.552586935426876e-05, "loss": 0.263, "step": 756 }, { "epoch": 3.0663291139240507, "grad_norm": 0.4667001096354879, "learning_rate": 1.547056723140774e-05, "loss": 0.2627, "step": 757 }, { "epoch": 3.0703797468354432, "grad_norm": 0.3922471974433599, "learning_rate": 1.5415301587975565e-05, "loss": 0.2639, "step": 758 }, { "epoch": 3.0744303797468353, "grad_norm": 0.4188769357404668, "learning_rate": 1.536007286907411e-05, "loss": 0.2863, "step": 759 }, { "epoch": 3.078481012658228, "grad_norm": 0.3963635507256582, "learning_rate": 1.5304881519507896e-05, "loss": 0.2599, "step": 760 }, { "epoch": 3.0825316455696203, "grad_norm": 0.37522925042852695, "learning_rate": 1.5249727983780453e-05, "loss": 0.2558, "step": 761 }, { "epoch": 3.086582278481013, "grad_norm": 0.3941784626843747, "learning_rate": 1.5194612706090786e-05, "loss": 0.2717, "step": 762 }, { "epoch": 3.090632911392405, "grad_norm": 0.38803300524405904, "learning_rate": 1.5139536130329771e-05, "loss": 0.2633, "step": 763 }, { "epoch": 3.0946835443037974, "grad_norm": 0.38984502532794574, "learning_rate": 1.508449870007656e-05, "loss": 0.2545, "step": 764 }, { "epoch": 3.09873417721519, "grad_norm": 0.358335403927563, "learning_rate": 1.5029500858595056e-05, "loss": 0.2928, "step": 765 }, { "epoch": 3.1027848101265825, "grad_norm": 0.37390020238556926, "learning_rate": 1.4974543048830328e-05, "loss": 0.2633, "step": 766 }, { "epoch": 3.1068354430379745, "grad_norm": 0.362666039060567, "learning_rate": 1.4919625713405e-05, "loss": 0.2651, "step": 767 }, { "epoch": 3.110886075949367, "grad_norm": 0.3590135876734494, "learning_rate": 1.4864749294615756e-05, "loss": 0.266, "step": 768 }, { "epoch": 3.1149367088607596, "grad_norm": 0.3693890477034798, "learning_rate": 1.4809914234429716e-05, "loss": 0.265, "step": 769 }, { "epoch": 3.118987341772152, "grad_norm": 0.3598693965800597, "learning_rate": 1.4755120974480923e-05, "loss": 0.2583, "step": 770 }, { "epoch": 3.123037974683544, "grad_norm": 0.3585358392770977, "learning_rate": 1.4700369956066771e-05, "loss": 0.2516, "step": 771 }, { "epoch": 3.1270886075949367, "grad_norm": 0.3526960620443326, "learning_rate": 1.4645661620144413e-05, "loss": 0.2679, "step": 772 }, { "epoch": 3.131139240506329, "grad_norm": 0.3603448466638372, "learning_rate": 1.4590996407327284e-05, "loss": 0.2547, "step": 773 }, { "epoch": 3.1351898734177217, "grad_norm": 0.36959173878395296, "learning_rate": 1.4536374757881487e-05, "loss": 0.277, "step": 774 }, { "epoch": 3.1392405063291138, "grad_norm": 0.3326943036249935, "learning_rate": 1.4481797111722271e-05, "loss": 0.2687, "step": 775 }, { "epoch": 3.1432911392405063, "grad_norm": 0.35934125977850423, "learning_rate": 1.4427263908410507e-05, "loss": 0.2747, "step": 776 }, { "epoch": 3.147341772151899, "grad_norm": 0.33402499966968424, "learning_rate": 1.4372775587149108e-05, "loss": 0.2433, "step": 777 }, { "epoch": 3.1513924050632913, "grad_norm": 0.338438229635516, "learning_rate": 1.4318332586779522e-05, "loss": 0.258, "step": 778 }, { "epoch": 3.1554430379746834, "grad_norm": 0.3518870368490762, "learning_rate": 1.4263935345778202e-05, "loss": 0.2844, "step": 779 }, { "epoch": 3.159493670886076, "grad_norm": 0.3378107342268102, "learning_rate": 1.420958430225303e-05, "loss": 0.2694, "step": 780 }, { "epoch": 3.1635443037974684, "grad_norm": 0.343886367401892, "learning_rate": 1.415527989393985e-05, "loss": 0.262, "step": 781 }, { "epoch": 3.167594936708861, "grad_norm": 0.3489646455078497, "learning_rate": 1.410102255819891e-05, "loss": 0.2815, "step": 782 }, { "epoch": 3.171645569620253, "grad_norm": 0.33903002287189316, "learning_rate": 1.404681273201131e-05, "loss": 0.2557, "step": 783 }, { "epoch": 3.1756962025316455, "grad_norm": 0.3557591837575114, "learning_rate": 1.399265085197556e-05, "loss": 0.2667, "step": 784 }, { "epoch": 3.179746835443038, "grad_norm": 0.3430097493120992, "learning_rate": 1.393853735430398e-05, "loss": 0.2653, "step": 785 }, { "epoch": 3.1837974683544306, "grad_norm": 0.3409677755217359, "learning_rate": 1.3884472674819246e-05, "loss": 0.2519, "step": 786 }, { "epoch": 3.1878481012658226, "grad_norm": 0.3535384462358427, "learning_rate": 1.3830457248950864e-05, "loss": 0.2639, "step": 787 }, { "epoch": 3.191898734177215, "grad_norm": 0.35207712332437124, "learning_rate": 1.377649151173163e-05, "loss": 0.2603, "step": 788 }, { "epoch": 3.1959493670886077, "grad_norm": 0.36713855984584404, "learning_rate": 1.3722575897794181e-05, "loss": 0.245, "step": 789 }, { "epoch": 3.2, "grad_norm": 0.34618241969700103, "learning_rate": 1.3668710841367472e-05, "loss": 0.2438, "step": 790 }, { "epoch": 3.2040506329113922, "grad_norm": 0.3739370797525924, "learning_rate": 1.361489677627324e-05, "loss": 0.27, "step": 791 }, { "epoch": 3.2081012658227848, "grad_norm": 0.3313824405218033, "learning_rate": 1.3561134135922585e-05, "loss": 0.2765, "step": 792 }, { "epoch": 3.2121518987341773, "grad_norm": 0.3618089559623846, "learning_rate": 1.350742335331241e-05, "loss": 0.2699, "step": 793 }, { "epoch": 3.21620253164557, "grad_norm": 0.36986645515505284, "learning_rate": 1.345376486102198e-05, "loss": 0.2557, "step": 794 }, { "epoch": 3.220253164556962, "grad_norm": 0.35167770640999096, "learning_rate": 1.3400159091209414e-05, "loss": 0.2581, "step": 795 }, { "epoch": 3.2243037974683544, "grad_norm": 0.3358284299585849, "learning_rate": 1.3346606475608216e-05, "loss": 0.275, "step": 796 }, { "epoch": 3.228354430379747, "grad_norm": 0.3989628003206363, "learning_rate": 1.3293107445523781e-05, "loss": 0.261, "step": 797 }, { "epoch": 3.2324050632911394, "grad_norm": 0.3594532026080628, "learning_rate": 1.3239662431829949e-05, "loss": 0.2518, "step": 798 }, { "epoch": 3.2364556962025315, "grad_norm": 0.34790342597639845, "learning_rate": 1.3186271864965509e-05, "loss": 0.2778, "step": 799 }, { "epoch": 3.240506329113924, "grad_norm": 0.36847004535790434, "learning_rate": 1.3132936174930756e-05, "loss": 0.2542, "step": 800 }, { "epoch": 3.2445569620253165, "grad_norm": 0.3597217205601531, "learning_rate": 1.3079655791283995e-05, "loss": 0.264, "step": 801 }, { "epoch": 3.248607594936709, "grad_norm": 0.3506019978139135, "learning_rate": 1.3026431143138108e-05, "loss": 0.256, "step": 802 }, { "epoch": 3.252658227848101, "grad_norm": 0.36509326976298095, "learning_rate": 1.2973262659157114e-05, "loss": 0.2565, "step": 803 }, { "epoch": 3.2567088607594936, "grad_norm": 0.3489152428619806, "learning_rate": 1.2920150767552651e-05, "loss": 0.2599, "step": 804 }, { "epoch": 3.260759493670886, "grad_norm": 0.3262516751625959, "learning_rate": 1.2867095896080607e-05, "loss": 0.269, "step": 805 }, { "epoch": 3.2648101265822786, "grad_norm": 0.3351710164884565, "learning_rate": 1.2814098472037612e-05, "loss": 0.263, "step": 806 }, { "epoch": 3.2688607594936707, "grad_norm": 0.36862442137300283, "learning_rate": 1.276115892225764e-05, "loss": 0.2721, "step": 807 }, { "epoch": 3.2729113924050632, "grad_norm": 0.3278493234848722, "learning_rate": 1.2708277673108555e-05, "loss": 0.2585, "step": 808 }, { "epoch": 3.2769620253164558, "grad_norm": 0.3348136545460641, "learning_rate": 1.2655455150488649e-05, "loss": 0.2368, "step": 809 }, { "epoch": 3.2810126582278483, "grad_norm": 0.33635084494763795, "learning_rate": 1.2602691779823272e-05, "loss": 0.2739, "step": 810 }, { "epoch": 3.2850632911392403, "grad_norm": 0.33230100110498945, "learning_rate": 1.2549987986061355e-05, "loss": 0.2574, "step": 811 }, { "epoch": 3.289113924050633, "grad_norm": 0.34807928740971933, "learning_rate": 1.2497344193672005e-05, "loss": 0.2635, "step": 812 }, { "epoch": 3.2931645569620254, "grad_norm": 0.35721185020248153, "learning_rate": 1.2444760826641092e-05, "loss": 0.2759, "step": 813 }, { "epoch": 3.297215189873418, "grad_norm": 0.32383582591764176, "learning_rate": 1.2392238308467817e-05, "loss": 0.2538, "step": 814 }, { "epoch": 3.30126582278481, "grad_norm": 0.3422507978481079, "learning_rate": 1.2339777062161326e-05, "loss": 0.2655, "step": 815 }, { "epoch": 3.3053164556962025, "grad_norm": 0.3445837197161966, "learning_rate": 1.2287377510237293e-05, "loss": 0.2729, "step": 816 }, { "epoch": 3.309367088607595, "grad_norm": 0.3325457560219979, "learning_rate": 1.2235040074714488e-05, "loss": 0.2776, "step": 817 }, { "epoch": 3.3134177215189875, "grad_norm": 0.34537651150973603, "learning_rate": 1.2182765177111434e-05, "loss": 0.2797, "step": 818 }, { "epoch": 3.3174683544303796, "grad_norm": 0.3378512296265388, "learning_rate": 1.213055323844297e-05, "loss": 0.2643, "step": 819 }, { "epoch": 3.321518987341772, "grad_norm": 0.3470062998269343, "learning_rate": 1.2078404679216864e-05, "loss": 0.2556, "step": 820 }, { "epoch": 3.3255696202531646, "grad_norm": 0.35203685572300925, "learning_rate": 1.2026319919430458e-05, "loss": 0.2385, "step": 821 }, { "epoch": 3.329620253164557, "grad_norm": 0.3332489881640686, "learning_rate": 1.1974299378567227e-05, "loss": 0.2874, "step": 822 }, { "epoch": 3.333670886075949, "grad_norm": 0.34810156728198954, "learning_rate": 1.1922343475593462e-05, "loss": 0.2541, "step": 823 }, { "epoch": 3.3377215189873417, "grad_norm": 0.34844494497949396, "learning_rate": 1.187045262895488e-05, "loss": 0.2695, "step": 824 }, { "epoch": 3.3417721518987342, "grad_norm": 0.34586607977028616, "learning_rate": 1.1818627256573203e-05, "loss": 0.2615, "step": 825 }, { "epoch": 3.3458227848101267, "grad_norm": 0.33572308612994767, "learning_rate": 1.1766867775842864e-05, "loss": 0.2427, "step": 826 }, { "epoch": 3.349873417721519, "grad_norm": 0.32011661569737987, "learning_rate": 1.1715174603627615e-05, "loss": 0.2427, "step": 827 }, { "epoch": 3.3539240506329113, "grad_norm": 0.35341883976469707, "learning_rate": 1.1663548156257147e-05, "loss": 0.2675, "step": 828 }, { "epoch": 3.357974683544304, "grad_norm": 0.36496826865169557, "learning_rate": 1.161198884952377e-05, "loss": 0.2608, "step": 829 }, { "epoch": 3.3620253164556964, "grad_norm": 0.3203762902317623, "learning_rate": 1.1560497098679056e-05, "loss": 0.2719, "step": 830 }, { "epoch": 3.3660759493670884, "grad_norm": 0.3395433509084218, "learning_rate": 1.1509073318430479e-05, "loss": 0.2662, "step": 831 }, { "epoch": 3.370126582278481, "grad_norm": 0.3261857401522712, "learning_rate": 1.1457717922938116e-05, "loss": 0.2698, "step": 832 }, { "epoch": 3.3741772151898735, "grad_norm": 0.32848375001053504, "learning_rate": 1.1406431325811233e-05, "loss": 0.2606, "step": 833 }, { "epoch": 3.378227848101266, "grad_norm": 0.3429707341183145, "learning_rate": 1.135521394010506e-05, "loss": 0.2481, "step": 834 }, { "epoch": 3.382278481012658, "grad_norm": 0.3441808274597079, "learning_rate": 1.1304066178317367e-05, "loss": 0.2847, "step": 835 }, { "epoch": 3.3863291139240506, "grad_norm": 0.3084428702590627, "learning_rate": 1.1252988452385199e-05, "loss": 0.262, "step": 836 }, { "epoch": 3.390379746835443, "grad_norm": 0.3456723876918039, "learning_rate": 1.1201981173681536e-05, "loss": 0.2715, "step": 837 }, { "epoch": 3.3944303797468356, "grad_norm": 0.3306766983447715, "learning_rate": 1.1151044753011991e-05, "loss": 0.2647, "step": 838 }, { "epoch": 3.3984810126582277, "grad_norm": 0.31960069114820566, "learning_rate": 1.1100179600611491e-05, "loss": 0.2736, "step": 839 }, { "epoch": 3.40253164556962, "grad_norm": 0.3387011088668899, "learning_rate": 1.1049386126140985e-05, "loss": 0.2397, "step": 840 }, { "epoch": 3.4065822784810127, "grad_norm": 0.3255992021245716, "learning_rate": 1.0998664738684128e-05, "loss": 0.2649, "step": 841 }, { "epoch": 3.410632911392405, "grad_norm": 0.32054563080937515, "learning_rate": 1.0948015846744e-05, "loss": 0.2647, "step": 842 }, { "epoch": 3.4146835443037973, "grad_norm": 0.33010197020218424, "learning_rate": 1.0897439858239832e-05, "loss": 0.2466, "step": 843 }, { "epoch": 3.41873417721519, "grad_norm": 0.34076920392900595, "learning_rate": 1.0846937180503652e-05, "loss": 0.2745, "step": 844 }, { "epoch": 3.4227848101265823, "grad_norm": 0.3267942693747088, "learning_rate": 1.0796508220277117e-05, "loss": 0.2665, "step": 845 }, { "epoch": 3.426835443037975, "grad_norm": 0.3263873546351397, "learning_rate": 1.0746153383708107e-05, "loss": 0.2346, "step": 846 }, { "epoch": 3.430886075949367, "grad_norm": 0.31854950290389644, "learning_rate": 1.0695873076347579e-05, "loss": 0.2821, "step": 847 }, { "epoch": 3.4349367088607594, "grad_norm": 0.32921729381811404, "learning_rate": 1.0645667703146205e-05, "loss": 0.2571, "step": 848 }, { "epoch": 3.438987341772152, "grad_norm": 0.32099388775503457, "learning_rate": 1.0595537668451161e-05, "loss": 0.2673, "step": 849 }, { "epoch": 3.4430379746835444, "grad_norm": 0.3514056162612334, "learning_rate": 1.0545483376002854e-05, "loss": 0.2424, "step": 850 }, { "epoch": 3.4470886075949365, "grad_norm": 0.33410177618363895, "learning_rate": 1.0495505228931676e-05, "loss": 0.2642, "step": 851 }, { "epoch": 3.451139240506329, "grad_norm": 0.36199335712958325, "learning_rate": 1.044560362975474e-05, "loss": 0.2576, "step": 852 }, { "epoch": 3.4551898734177215, "grad_norm": 0.3384542020867513, "learning_rate": 1.0395778980372695e-05, "loss": 0.2387, "step": 853 }, { "epoch": 3.459240506329114, "grad_norm": 0.3325894685365072, "learning_rate": 1.0346031682066381e-05, "loss": 0.2665, "step": 854 }, { "epoch": 3.463291139240506, "grad_norm": 0.34641762440920626, "learning_rate": 1.0296362135493724e-05, "loss": 0.2541, "step": 855 }, { "epoch": 3.4673417721518986, "grad_norm": 0.34036853116539445, "learning_rate": 1.0246770740686422e-05, "loss": 0.2646, "step": 856 }, { "epoch": 3.471392405063291, "grad_norm": 0.3316208816732494, "learning_rate": 1.0197257897046743e-05, "loss": 0.2656, "step": 857 }, { "epoch": 3.4754430379746837, "grad_norm": 0.3221564768410517, "learning_rate": 1.014782400334433e-05, "loss": 0.2939, "step": 858 }, { "epoch": 3.479493670886076, "grad_norm": 0.33617885630667055, "learning_rate": 1.009846945771296e-05, "loss": 0.2785, "step": 859 }, { "epoch": 3.4835443037974683, "grad_norm": 0.3185734357300342, "learning_rate": 1.0049194657647363e-05, "loss": 0.255, "step": 860 }, { "epoch": 3.487594936708861, "grad_norm": 0.318980648900219, "learning_rate": 1.0000000000000006e-05, "loss": 0.2555, "step": 861 }, { "epoch": 3.4916455696202533, "grad_norm": 0.32902810117902787, "learning_rate": 9.950885880977891e-06, "loss": 0.2712, "step": 862 }, { "epoch": 3.4956962025316454, "grad_norm": 0.3338166119789578, "learning_rate": 9.901852696139382e-06, "loss": 0.2378, "step": 863 }, { "epoch": 3.499746835443038, "grad_norm": 0.3401254153121683, "learning_rate": 9.852900840391027e-06, "loss": 0.257, "step": 864 }, { "epoch": 3.5037974683544304, "grad_norm": 0.3265383350111184, "learning_rate": 9.804030707984313e-06, "loss": 0.2614, "step": 865 }, { "epoch": 3.507848101265823, "grad_norm": 0.3445486080265418, "learning_rate": 9.755242692512599e-06, "loss": 0.2652, "step": 866 }, { "epoch": 3.5118987341772154, "grad_norm": 0.31720780216887545, "learning_rate": 9.70653718690782e-06, "loss": 0.2562, "step": 867 }, { "epoch": 3.5159493670886075, "grad_norm": 0.33274430942400385, "learning_rate": 9.657914583437454e-06, "loss": 0.2749, "step": 868 }, { "epoch": 3.52, "grad_norm": 0.33169238855608657, "learning_rate": 9.609375273701246e-06, "loss": 0.2839, "step": 869 }, { "epoch": 3.5240506329113925, "grad_norm": 0.3131564884715295, "learning_rate": 9.560919648628133e-06, "loss": 0.2531, "step": 870 }, { "epoch": 3.5281012658227846, "grad_norm": 0.3196828627742117, "learning_rate": 9.512548098473047e-06, "loss": 0.2726, "step": 871 }, { "epoch": 3.532151898734177, "grad_norm": 0.3204619361550153, "learning_rate": 9.464261012813825e-06, "loss": 0.2671, "step": 872 }, { "epoch": 3.5362025316455696, "grad_norm": 0.33094022678107343, "learning_rate": 9.416058780547987e-06, "loss": 0.2877, "step": 873 }, { "epoch": 3.540253164556962, "grad_norm": 0.34498741124557597, "learning_rate": 9.367941789889714e-06, "loss": 0.2301, "step": 874 }, { "epoch": 3.5443037974683547, "grad_norm": 0.3160320342659353, "learning_rate": 9.319910428366607e-06, "loss": 0.2625, "step": 875 }, { "epoch": 3.5483544303797467, "grad_norm": 0.3546663869719849, "learning_rate": 9.271965082816667e-06, "loss": 0.2603, "step": 876 }, { "epoch": 3.5524050632911393, "grad_norm": 0.32362964025307667, "learning_rate": 9.224106139385111e-06, "loss": 0.2653, "step": 877 }, { "epoch": 3.5564556962025318, "grad_norm": 0.3229170350514279, "learning_rate": 9.176333983521291e-06, "loss": 0.2574, "step": 878 }, { "epoch": 3.560506329113924, "grad_norm": 0.3157487235248422, "learning_rate": 9.12864899997558e-06, "loss": 0.2715, "step": 879 }, { "epoch": 3.5645569620253164, "grad_norm": 0.3275058479404392, "learning_rate": 9.08105157279628e-06, "loss": 0.2784, "step": 880 }, { "epoch": 3.568607594936709, "grad_norm": 0.338102405333511, "learning_rate": 9.03354208532653e-06, "loss": 0.2727, "step": 881 }, { "epoch": 3.5726582278481014, "grad_norm": 0.3090710454938609, "learning_rate": 8.986120920201205e-06, "loss": 0.3, "step": 882 }, { "epoch": 3.576708860759494, "grad_norm": 0.33028307390177414, "learning_rate": 8.938788459343852e-06, "loss": 0.2474, "step": 883 }, { "epoch": 3.580759493670886, "grad_norm": 0.32361280387606645, "learning_rate": 8.8915450839636e-06, "loss": 0.2758, "step": 884 }, { "epoch": 3.5848101265822785, "grad_norm": 0.33030083052537057, "learning_rate": 8.844391174552116e-06, "loss": 0.2545, "step": 885 }, { "epoch": 3.588860759493671, "grad_norm": 0.332277591582174, "learning_rate": 8.797327110880479e-06, "loss": 0.2664, "step": 886 }, { "epoch": 3.592911392405063, "grad_norm": 0.3331746148519476, "learning_rate": 8.750353271996206e-06, "loss": 0.2498, "step": 887 }, { "epoch": 3.5969620253164556, "grad_norm": 0.3269873188610072, "learning_rate": 8.703470036220132e-06, "loss": 0.257, "step": 888 }, { "epoch": 3.601012658227848, "grad_norm": 0.3187116692272149, "learning_rate": 8.656677781143394e-06, "loss": 0.265, "step": 889 }, { "epoch": 3.6050632911392406, "grad_norm": 0.32713190677376575, "learning_rate": 8.609976883624377e-06, "loss": 0.2768, "step": 890 }, { "epoch": 3.609113924050633, "grad_norm": 0.33772464428944315, "learning_rate": 8.563367719785698e-06, "loss": 0.271, "step": 891 }, { "epoch": 3.613164556962025, "grad_norm": 0.32479619687312006, "learning_rate": 8.516850665011138e-06, "loss": 0.2748, "step": 892 }, { "epoch": 3.6172151898734177, "grad_norm": 0.33717642608337667, "learning_rate": 8.47042609394269e-06, "loss": 0.2511, "step": 893 }, { "epoch": 3.6212658227848102, "grad_norm": 0.3433900428132607, "learning_rate": 8.424094380477432e-06, "loss": 0.2517, "step": 894 }, { "epoch": 3.6253164556962023, "grad_norm": 0.31467340500526214, "learning_rate": 8.37785589776465e-06, "loss": 0.2561, "step": 895 }, { "epoch": 3.629367088607595, "grad_norm": 0.31713638606334843, "learning_rate": 8.331711018202694e-06, "loss": 0.245, "step": 896 }, { "epoch": 3.6334177215189873, "grad_norm": 0.32697195450998223, "learning_rate": 8.285660113436104e-06, "loss": 0.2745, "step": 897 }, { "epoch": 3.63746835443038, "grad_norm": 0.3223652811248751, "learning_rate": 8.239703554352527e-06, "loss": 0.2791, "step": 898 }, { "epoch": 3.6415189873417724, "grad_norm": 0.312637822400577, "learning_rate": 8.193841711079775e-06, "loss": 0.26, "step": 899 }, { "epoch": 3.6455696202531644, "grad_norm": 0.3144771771122148, "learning_rate": 8.148074952982828e-06, "loss": 0.2594, "step": 900 }, { "epoch": 3.649620253164557, "grad_norm": 0.3288253747730312, "learning_rate": 8.102403648660859e-06, "loss": 0.2431, "step": 901 }, { "epoch": 3.6536708860759495, "grad_norm": 0.3744944016523773, "learning_rate": 8.056828165944282e-06, "loss": 0.2603, "step": 902 }, { "epoch": 3.6577215189873415, "grad_norm": 0.3222576417851976, "learning_rate": 8.011348871891762e-06, "loss": 0.2791, "step": 903 }, { "epoch": 3.661772151898734, "grad_norm": 0.3325574385423051, "learning_rate": 7.965966132787287e-06, "loss": 0.2429, "step": 904 }, { "epoch": 3.6658227848101266, "grad_norm": 0.31655167648442045, "learning_rate": 7.920680314137189e-06, "loss": 0.2844, "step": 905 }, { "epoch": 3.669873417721519, "grad_norm": 0.3079878045572072, "learning_rate": 7.875491780667246e-06, "loss": 0.2722, "step": 906 }, { "epoch": 3.6739240506329116, "grad_norm": 0.3201506447831331, "learning_rate": 7.830400896319667e-06, "loss": 0.2661, "step": 907 }, { "epoch": 3.6779746835443037, "grad_norm": 0.3348387254726911, "learning_rate": 7.785408024250259e-06, "loss": 0.2723, "step": 908 }, { "epoch": 3.682025316455696, "grad_norm": 0.31667698434358627, "learning_rate": 7.74051352682542e-06, "loss": 0.273, "step": 909 }, { "epoch": 3.6860759493670887, "grad_norm": 0.31776977050284777, "learning_rate": 7.695717765619257e-06, "loss": 0.284, "step": 910 }, { "epoch": 3.690126582278481, "grad_norm": 0.3284365872102749, "learning_rate": 7.651021101410673e-06, "loss": 0.262, "step": 911 }, { "epoch": 3.6941772151898733, "grad_norm": 0.3114744275176387, "learning_rate": 7.606423894180464e-06, "loss": 0.2779, "step": 912 }, { "epoch": 3.698227848101266, "grad_norm": 0.3090932925853516, "learning_rate": 7.56192650310839e-06, "loss": 0.2705, "step": 913 }, { "epoch": 3.7022784810126583, "grad_norm": 0.31796658387460897, "learning_rate": 7.517529286570349e-06, "loss": 0.2613, "step": 914 }, { "epoch": 3.706329113924051, "grad_norm": 0.32370739095442297, "learning_rate": 7.473232602135387e-06, "loss": 0.2725, "step": 915 }, { "epoch": 3.710379746835443, "grad_norm": 0.315046321765776, "learning_rate": 7.429036806562935e-06, "loss": 0.2635, "step": 916 }, { "epoch": 3.7144303797468354, "grad_norm": 0.3228087394599951, "learning_rate": 7.3849422557998455e-06, "loss": 0.2511, "step": 917 }, { "epoch": 3.718481012658228, "grad_norm": 0.3281449356086604, "learning_rate": 7.340949304977567e-06, "loss": 0.2832, "step": 918 }, { "epoch": 3.72253164556962, "grad_norm": 0.3157170390395275, "learning_rate": 7.297058308409282e-06, "loss": 0.2728, "step": 919 }, { "epoch": 3.7265822784810125, "grad_norm": 0.31744343566041766, "learning_rate": 7.25326961958704e-06, "loss": 0.2642, "step": 920 }, { "epoch": 3.730632911392405, "grad_norm": 0.3119593135306949, "learning_rate": 7.209583591178921e-06, "loss": 0.2833, "step": 921 }, { "epoch": 3.7346835443037976, "grad_norm": 0.31359424821863835, "learning_rate": 7.1660005750261925e-06, "loss": 0.2664, "step": 922 }, { "epoch": 3.73873417721519, "grad_norm": 0.3258853638176504, "learning_rate": 7.1225209221404765e-06, "loss": 0.2624, "step": 923 }, { "epoch": 3.742784810126582, "grad_norm": 0.32259592435370155, "learning_rate": 7.079144982700909e-06, "loss": 0.2709, "step": 924 }, { "epoch": 3.7468354430379747, "grad_norm": 0.31323950666994593, "learning_rate": 7.0358731060513695e-06, "loss": 0.2542, "step": 925 }, { "epoch": 3.750886075949367, "grad_norm": 0.32817774209951456, "learning_rate": 6.99270564069757e-06, "loss": 0.2718, "step": 926 }, { "epoch": 3.7549367088607593, "grad_norm": 0.31400375503839756, "learning_rate": 6.949642934304375e-06, "loss": 0.2648, "step": 927 }, { "epoch": 3.7589873417721518, "grad_norm": 0.3386139245202975, "learning_rate": 6.906685333692871e-06, "loss": 0.2394, "step": 928 }, { "epoch": 3.7630379746835443, "grad_norm": 0.3187564707760043, "learning_rate": 6.86383318483769e-06, "loss": 0.2836, "step": 929 }, { "epoch": 3.767088607594937, "grad_norm": 0.30569509644835785, "learning_rate": 6.821086832864139e-06, "loss": 0.2897, "step": 930 }, { "epoch": 3.7711392405063293, "grad_norm": 0.3169604009653782, "learning_rate": 6.77844662204546e-06, "loss": 0.2762, "step": 931 }, { "epoch": 3.7751898734177214, "grad_norm": 0.31561160716521064, "learning_rate": 6.7359128958000455e-06, "loss": 0.2632, "step": 932 }, { "epoch": 3.779240506329114, "grad_norm": 0.32043001428279433, "learning_rate": 6.693485996688695e-06, "loss": 0.2846, "step": 933 }, { "epoch": 3.7832911392405064, "grad_norm": 0.3098426253265193, "learning_rate": 6.651166266411801e-06, "loss": 0.2613, "step": 934 }, { "epoch": 3.7873417721518985, "grad_norm": 0.3164470169672765, "learning_rate": 6.6089540458066725e-06, "loss": 0.275, "step": 935 }, { "epoch": 3.791392405063291, "grad_norm": 0.29736062609439207, "learning_rate": 6.566849674844711e-06, "loss": 0.2657, "step": 936 }, { "epoch": 3.7954430379746835, "grad_norm": 0.3176711486723409, "learning_rate": 6.524853492628747e-06, "loss": 0.2687, "step": 937 }, { "epoch": 3.799493670886076, "grad_norm": 0.315897628852583, "learning_rate": 6.4829658373902536e-06, "loss": 0.256, "step": 938 }, { "epoch": 3.8035443037974686, "grad_norm": 0.31686712692135405, "learning_rate": 6.441187046486648e-06, "loss": 0.2608, "step": 939 }, { "epoch": 3.8075949367088606, "grad_norm": 0.3475173091519947, "learning_rate": 6.399517456398567e-06, "loss": 0.2694, "step": 940 }, { "epoch": 3.811645569620253, "grad_norm": 0.3244118128092711, "learning_rate": 6.357957402727164e-06, "loss": 0.2647, "step": 941 }, { "epoch": 3.8156962025316457, "grad_norm": 0.3344481284643848, "learning_rate": 6.316507220191395e-06, "loss": 0.2668, "step": 942 }, { "epoch": 3.8197468354430377, "grad_norm": 0.3195841534026393, "learning_rate": 6.275167242625331e-06, "loss": 0.2707, "step": 943 }, { "epoch": 3.8237974683544302, "grad_norm": 0.3068073947469872, "learning_rate": 6.233937802975471e-06, "loss": 0.2473, "step": 944 }, { "epoch": 3.8278481012658228, "grad_norm": 0.3270603906639929, "learning_rate": 6.192819233298046e-06, "loss": 0.2553, "step": 945 }, { "epoch": 3.8318987341772153, "grad_norm": 0.3172554057122396, "learning_rate": 6.151811864756383e-06, "loss": 0.2916, "step": 946 }, { "epoch": 3.835949367088608, "grad_norm": 0.31376601380998415, "learning_rate": 6.1109160276181655e-06, "loss": 0.253, "step": 947 }, { "epoch": 3.84, "grad_norm": 0.3149336517182424, "learning_rate": 6.070132051252868e-06, "loss": 0.2826, "step": 948 }, { "epoch": 3.8440506329113924, "grad_norm": 0.33439997075685063, "learning_rate": 6.0294602641290034e-06, "loss": 0.256, "step": 949 }, { "epoch": 3.848101265822785, "grad_norm": 0.3139261505239044, "learning_rate": 5.988900993811575e-06, "loss": 0.2729, "step": 950 }, { "epoch": 3.852151898734177, "grad_norm": 0.31660105635241664, "learning_rate": 5.948454566959363e-06, "loss": 0.2544, "step": 951 }, { "epoch": 3.8562025316455695, "grad_norm": 0.3269233772048771, "learning_rate": 5.908121309322328e-06, "loss": 0.2627, "step": 952 }, { "epoch": 3.860253164556962, "grad_norm": 0.3147948622931532, "learning_rate": 5.867901545738976e-06, "loss": 0.2915, "step": 953 }, { "epoch": 3.8643037974683545, "grad_norm": 0.3351509127492675, "learning_rate": 5.827795600133774e-06, "loss": 0.2537, "step": 954 }, { "epoch": 3.868354430379747, "grad_norm": 0.31005460721140116, "learning_rate": 5.787803795514466e-06, "loss": 0.2834, "step": 955 }, { "epoch": 3.872405063291139, "grad_norm": 0.33331858640286377, "learning_rate": 5.747926453969576e-06, "loss": 0.2828, "step": 956 }, { "epoch": 3.8764556962025316, "grad_norm": 0.31759536436651725, "learning_rate": 5.708163896665708e-06, "loss": 0.2448, "step": 957 }, { "epoch": 3.880506329113924, "grad_norm": 0.33779200418503547, "learning_rate": 5.668516443845047e-06, "loss": 0.2294, "step": 958 }, { "epoch": 3.884556962025316, "grad_norm": 0.30169237983052843, "learning_rate": 5.6289844148227225e-06, "loss": 0.2646, "step": 959 }, { "epoch": 3.8886075949367087, "grad_norm": 0.3281540775022162, "learning_rate": 5.5895681279842615e-06, "loss": 0.2569, "step": 960 }, { "epoch": 3.8926582278481012, "grad_norm": 0.32117534562922834, "learning_rate": 5.550267900783019e-06, "loss": 0.2594, "step": 961 }, { "epoch": 3.8967088607594937, "grad_norm": 0.3208770011610911, "learning_rate": 5.511084049737623e-06, "loss": 0.2733, "step": 962 }, { "epoch": 3.9007594936708863, "grad_norm": 0.3158866438488446, "learning_rate": 5.4720168904294215e-06, "loss": 0.2443, "step": 963 }, { "epoch": 3.9048101265822783, "grad_norm": 0.30138477559137833, "learning_rate": 5.433066737499948e-06, "loss": 0.2604, "step": 964 }, { "epoch": 3.908860759493671, "grad_norm": 0.32263994992755884, "learning_rate": 5.394233904648376e-06, "loss": 0.2526, "step": 965 }, { "epoch": 3.9129113924050634, "grad_norm": 0.2992074596191799, "learning_rate": 5.355518704628997e-06, "loss": 0.2713, "step": 966 }, { "epoch": 3.9169620253164554, "grad_norm": 0.3237653375650156, "learning_rate": 5.316921449248731e-06, "loss": 0.2479, "step": 967 }, { "epoch": 3.921012658227848, "grad_norm": 0.3266876639465116, "learning_rate": 5.278442449364538e-06, "loss": 0.2643, "step": 968 }, { "epoch": 3.9250632911392405, "grad_norm": 0.33081664826729956, "learning_rate": 5.240082014881016e-06, "loss": 0.271, "step": 969 }, { "epoch": 3.929113924050633, "grad_norm": 0.32125313255120286, "learning_rate": 5.201840454747822e-06, "loss": 0.2613, "step": 970 }, { "epoch": 3.9331645569620255, "grad_norm": 0.3087655412899437, "learning_rate": 5.163718076957223e-06, "loss": 0.2747, "step": 971 }, { "epoch": 3.9372151898734176, "grad_norm": 0.32996872252122483, "learning_rate": 5.125715188541609e-06, "loss": 0.2759, "step": 972 }, { "epoch": 3.94126582278481, "grad_norm": 0.3187610575300363, "learning_rate": 5.087832095571021e-06, "loss": 0.2427, "step": 973 }, { "epoch": 3.9453164556962026, "grad_norm": 0.330725662307795, "learning_rate": 5.0500691031506766e-06, "loss": 0.2303, "step": 974 }, { "epoch": 3.9493670886075947, "grad_norm": 0.3300269333908474, "learning_rate": 5.01242651541854e-06, "loss": 0.2418, "step": 975 }, { "epoch": 3.953417721518987, "grad_norm": 0.3090656155555407, "learning_rate": 4.974904635542815e-06, "loss": 0.2811, "step": 976 }, { "epoch": 3.9574683544303797, "grad_norm": 0.32162718183457567, "learning_rate": 4.937503765719582e-06, "loss": 0.2531, "step": 977 }, { "epoch": 3.961518987341772, "grad_norm": 0.320753603970091, "learning_rate": 4.900224207170299e-06, "loss": 0.2615, "step": 978 }, { "epoch": 3.9655696202531647, "grad_norm": 0.33231783001083337, "learning_rate": 4.8630662601394065e-06, "loss": 0.2549, "step": 979 }, { "epoch": 3.969620253164557, "grad_norm": 0.32657942900982045, "learning_rate": 4.8260302238918995e-06, "loss": 0.25, "step": 980 }, { "epoch": 3.9736708860759493, "grad_norm": 0.3119273256173969, "learning_rate": 4.789116396710924e-06, "loss": 0.2704, "step": 981 }, { "epoch": 3.977721518987342, "grad_norm": 0.3117142067763989, "learning_rate": 4.752325075895368e-06, "loss": 0.2789, "step": 982 }, { "epoch": 3.981772151898734, "grad_norm": 0.3214445245680965, "learning_rate": 4.715656557757473e-06, "loss": 0.2909, "step": 983 }, { "epoch": 3.9858227848101264, "grad_norm": 0.31025429507511665, "learning_rate": 4.679111137620442e-06, "loss": 0.2808, "step": 984 }, { "epoch": 3.989873417721519, "grad_norm": 0.30412425150505734, "learning_rate": 4.6426891098160585e-06, "loss": 0.2668, "step": 985 }, { "epoch": 3.9939240506329114, "grad_norm": 0.33098529974998, "learning_rate": 4.6063907676823474e-06, "loss": 0.2446, "step": 986 }, { "epoch": 3.997974683544304, "grad_norm": 0.5792634449695248, "learning_rate": 4.570216403561141e-06, "loss": 0.251, "step": 987 }, { "epoch": 4.002025316455696, "grad_norm": 0.3721236604845247, "learning_rate": 4.534166308795815e-06, "loss": 0.2291, "step": 988 }, { "epoch": 4.006075949367089, "grad_norm": 0.39136903983402704, "learning_rate": 4.498240773728859e-06, "loss": 0.2058, "step": 989 }, { "epoch": 4.010126582278481, "grad_norm": 0.30470007712312885, "learning_rate": 4.462440087699609e-06, "loss": 0.2157, "step": 990 }, { "epoch": 4.014177215189873, "grad_norm": 0.27579527660664954, "learning_rate": 4.426764539041861e-06, "loss": 0.1981, "step": 991 }, { "epoch": 4.018227848101266, "grad_norm": 0.30417488834598116, "learning_rate": 4.391214415081582e-06, "loss": 0.1942, "step": 992 }, { "epoch": 4.022278481012658, "grad_norm": 0.3516925546091204, "learning_rate": 4.355790002134579e-06, "loss": 0.1911, "step": 993 }, { "epoch": 4.02632911392405, "grad_norm": 0.44314020190119313, "learning_rate": 4.320491585504207e-06, "loss": 0.2117, "step": 994 }, { "epoch": 4.030379746835443, "grad_norm": 0.3530416964529726, "learning_rate": 4.2853194494790615e-06, "loss": 0.2279, "step": 995 }, { "epoch": 4.034430379746835, "grad_norm": 0.3073323630723491, "learning_rate": 4.250273877330691e-06, "loss": 0.1864, "step": 996 }, { "epoch": 4.038481012658228, "grad_norm": 0.3250379764272706, "learning_rate": 4.215355151311313e-06, "loss": 0.2043, "step": 997 }, { "epoch": 4.04253164556962, "grad_norm": 0.3606884080948156, "learning_rate": 4.180563552651542e-06, "loss": 0.2131, "step": 998 }, { "epoch": 4.046582278481012, "grad_norm": 0.3386873098062385, "learning_rate": 4.145899361558147e-06, "loss": 0.1865, "step": 999 }, { "epoch": 4.050632911392405, "grad_norm": 0.2956590876833359, "learning_rate": 4.111362857211738e-06, "loss": 0.1851, "step": 1000 }, { "epoch": 4.054683544303797, "grad_norm": 0.26230348998509323, "learning_rate": 4.076954317764592e-06, "loss": 0.203, "step": 1001 }, { "epoch": 4.0587341772151895, "grad_norm": 0.2932277442108135, "learning_rate": 4.042674020338335e-06, "loss": 0.2065, "step": 1002 }, { "epoch": 4.062784810126582, "grad_norm": 0.3140118751434953, "learning_rate": 4.0085222410217835e-06, "loss": 0.1928, "step": 1003 }, { "epoch": 4.0668354430379745, "grad_norm": 0.28038469766246527, "learning_rate": 3.974499254868674e-06, "loss": 0.217, "step": 1004 }, { "epoch": 4.0708860759493675, "grad_norm": 0.2804338063956472, "learning_rate": 3.940605335895451e-06, "loss": 0.1861, "step": 1005 }, { "epoch": 4.0749367088607595, "grad_norm": 0.28209454096986325, "learning_rate": 3.90684075707908e-06, "loss": 0.1944, "step": 1006 }, { "epoch": 4.078987341772152, "grad_norm": 0.2689199611218599, "learning_rate": 3.8732057903548505e-06, "loss": 0.2156, "step": 1007 }, { "epoch": 4.083037974683545, "grad_norm": 0.2712775398808852, "learning_rate": 3.8397007066141375e-06, "loss": 0.2135, "step": 1008 }, { "epoch": 4.087088607594937, "grad_norm": 0.27850494233393835, "learning_rate": 3.806325775702304e-06, "loss": 0.1895, "step": 1009 }, { "epoch": 4.091139240506329, "grad_norm": 0.30019099475029837, "learning_rate": 3.773081266416434e-06, "loss": 0.202, "step": 1010 }, { "epoch": 4.095189873417722, "grad_norm": 0.2552449031543262, "learning_rate": 3.739967446503245e-06, "loss": 0.1992, "step": 1011 }, { "epoch": 4.099240506329114, "grad_norm": 0.26688140953556155, "learning_rate": 3.706984582656894e-06, "loss": 0.2164, "step": 1012 }, { "epoch": 4.103291139240507, "grad_norm": 0.25936244545794473, "learning_rate": 3.6741329405168237e-06, "loss": 0.2001, "step": 1013 }, { "epoch": 4.107341772151899, "grad_norm": 0.2596668447138313, "learning_rate": 3.641412784665648e-06, "loss": 0.2107, "step": 1014 }, { "epoch": 4.111392405063291, "grad_norm": 0.26049113635250803, "learning_rate": 3.608824378627005e-06, "loss": 0.1913, "step": 1015 }, { "epoch": 4.115443037974684, "grad_norm": 0.26939584000372474, "learning_rate": 3.5763679848634337e-06, "loss": 0.196, "step": 1016 }, { "epoch": 4.119493670886076, "grad_norm": 0.277007321598147, "learning_rate": 3.544043864774269e-06, "loss": 0.1808, "step": 1017 }, { "epoch": 4.123544303797468, "grad_norm": 0.2681145798856028, "learning_rate": 3.5118522786935282e-06, "loss": 0.2078, "step": 1018 }, { "epoch": 4.127594936708861, "grad_norm": 0.2541228893285848, "learning_rate": 3.479793485887819e-06, "loss": 0.1879, "step": 1019 }, { "epoch": 4.131645569620253, "grad_norm": 0.265433292541998, "learning_rate": 3.4478677445542653e-06, "loss": 0.1829, "step": 1020 }, { "epoch": 4.135696202531646, "grad_norm": 0.26091256570585825, "learning_rate": 3.4160753118183767e-06, "loss": 0.19, "step": 1021 }, { "epoch": 4.139746835443038, "grad_norm": 0.2591023826338954, "learning_rate": 3.3844164437320527e-06, "loss": 0.1878, "step": 1022 }, { "epoch": 4.14379746835443, "grad_norm": 0.2664267527221068, "learning_rate": 3.3528913952714558e-06, "loss": 0.2017, "step": 1023 }, { "epoch": 4.147848101265823, "grad_norm": 0.2603403173587131, "learning_rate": 3.321500420335e-06, "loss": 0.2006, "step": 1024 }, { "epoch": 4.151898734177215, "grad_norm": 0.26630463878715044, "learning_rate": 3.290243771741275e-06, "loss": 0.1766, "step": 1025 }, { "epoch": 4.155949367088607, "grad_norm": 0.26849734154547505, "learning_rate": 3.2591217012270325e-06, "loss": 0.1943, "step": 1026 }, { "epoch": 4.16, "grad_norm": 0.25327109133699743, "learning_rate": 3.228134459445149e-06, "loss": 0.2053, "step": 1027 }, { "epoch": 4.164050632911392, "grad_norm": 0.2920573773116488, "learning_rate": 3.1972822959626205e-06, "loss": 0.2068, "step": 1028 }, { "epoch": 4.168101265822785, "grad_norm": 0.27639435373112786, "learning_rate": 3.166565459258513e-06, "loss": 0.2195, "step": 1029 }, { "epoch": 4.172151898734177, "grad_norm": 0.26767777016550615, "learning_rate": 3.1359841967220193e-06, "loss": 0.2049, "step": 1030 }, { "epoch": 4.176202531645569, "grad_norm": 0.26697907174264557, "learning_rate": 3.105538754650419e-06, "loss": 0.1904, "step": 1031 }, { "epoch": 4.180253164556962, "grad_norm": 0.25998245293462274, "learning_rate": 3.07522937824712e-06, "loss": 0.1867, "step": 1032 }, { "epoch": 4.184303797468354, "grad_norm": 0.26603076204147463, "learning_rate": 3.0450563116196697e-06, "loss": 0.2207, "step": 1033 }, { "epoch": 4.188354430379746, "grad_norm": 0.2600569253168482, "learning_rate": 3.0150197977778008e-06, "loss": 0.2279, "step": 1034 }, { "epoch": 4.192405063291139, "grad_norm": 0.2605433716531618, "learning_rate": 2.985120078631465e-06, "loss": 0.2092, "step": 1035 }, { "epoch": 4.1964556962025314, "grad_norm": 0.24680953788150237, "learning_rate": 2.9553573949888893e-06, "loss": 0.1938, "step": 1036 }, { "epoch": 4.200506329113924, "grad_norm": 0.2572577742930261, "learning_rate": 2.9257319865546384e-06, "loss": 0.208, "step": 1037 }, { "epoch": 4.2045569620253165, "grad_norm": 0.2444109176348975, "learning_rate": 2.896244091927678e-06, "loss": 0.1745, "step": 1038 }, { "epoch": 4.2086075949367086, "grad_norm": 0.2713473562284962, "learning_rate": 2.8668939485994584e-06, "loss": 0.1955, "step": 1039 }, { "epoch": 4.2126582278481015, "grad_norm": 0.2776367184183773, "learning_rate": 2.837681792951994e-06, "loss": 0.1765, "step": 1040 }, { "epoch": 4.216708860759494, "grad_norm": 0.27974242954315337, "learning_rate": 2.808607860255981e-06, "loss": 0.1974, "step": 1041 }, { "epoch": 4.220759493670886, "grad_norm": 0.27073839929857746, "learning_rate": 2.7796723846688634e-06, "loss": 0.1759, "step": 1042 }, { "epoch": 4.224810126582279, "grad_norm": 0.25258616109110776, "learning_rate": 2.7508755992329937e-06, "loss": 0.2107, "step": 1043 }, { "epoch": 4.228860759493671, "grad_norm": 0.2542379644003926, "learning_rate": 2.722217735873718e-06, "loss": 0.1878, "step": 1044 }, { "epoch": 4.232911392405064, "grad_norm": 0.26203167753781714, "learning_rate": 2.6936990253975315e-06, "loss": 0.2214, "step": 1045 }, { "epoch": 4.236962025316456, "grad_norm": 0.2560206588196985, "learning_rate": 2.665319697490205e-06, "loss": 0.1928, "step": 1046 }, { "epoch": 4.241012658227848, "grad_norm": 0.2597726839583381, "learning_rate": 2.637079980714945e-06, "loss": 0.1999, "step": 1047 }, { "epoch": 4.245063291139241, "grad_norm": 0.25389263663470296, "learning_rate": 2.6089801025105453e-06, "loss": 0.1907, "step": 1048 }, { "epoch": 4.249113924050633, "grad_norm": 0.26435356131248655, "learning_rate": 2.581020289189571e-06, "loss": 0.198, "step": 1049 }, { "epoch": 4.253164556962025, "grad_norm": 0.2534170107036218, "learning_rate": 2.553200765936501e-06, "loss": 0.2124, "step": 1050 }, { "epoch": 4.257215189873418, "grad_norm": 0.24688223102313175, "learning_rate": 2.525521756805962e-06, "loss": 0.2163, "step": 1051 }, { "epoch": 4.26126582278481, "grad_norm": 0.25222649531501007, "learning_rate": 2.497983484720885e-06, "loss": 0.2045, "step": 1052 }, { "epoch": 4.265316455696203, "grad_norm": 0.25735449846706737, "learning_rate": 2.470586171470728e-06, "loss": 0.1882, "step": 1053 }, { "epoch": 4.269367088607595, "grad_norm": 0.2729219915104221, "learning_rate": 2.4433300377096836e-06, "loss": 0.1967, "step": 1054 }, { "epoch": 4.273417721518987, "grad_norm": 0.2579055474680333, "learning_rate": 2.4162153029549073e-06, "loss": 0.1968, "step": 1055 }, { "epoch": 4.27746835443038, "grad_norm": 0.2673419387466656, "learning_rate": 2.3892421855847458e-06, "loss": 0.2316, "step": 1056 }, { "epoch": 4.281518987341772, "grad_norm": 0.24500478581196256, "learning_rate": 2.362410902836978e-06, "loss": 0.199, "step": 1057 }, { "epoch": 4.285569620253165, "grad_norm": 0.2574506672269286, "learning_rate": 2.3357216708070653e-06, "loss": 0.1878, "step": 1058 }, { "epoch": 4.289620253164557, "grad_norm": 0.24636404438410153, "learning_rate": 2.309174704446411e-06, "loss": 0.22, "step": 1059 }, { "epoch": 4.293670886075949, "grad_norm": 0.2660328362749937, "learning_rate": 2.2827702175606437e-06, "loss": 0.2212, "step": 1060 }, { "epoch": 4.297721518987342, "grad_norm": 0.25625905277509853, "learning_rate": 2.256508422807855e-06, "loss": 0.2102, "step": 1061 }, { "epoch": 4.301772151898734, "grad_norm": 0.2603940729234846, "learning_rate": 2.230389531696946e-06, "loss": 0.1972, "step": 1062 }, { "epoch": 4.305822784810126, "grad_norm": 0.26040537549228626, "learning_rate": 2.204413754585857e-06, "loss": 0.1898, "step": 1063 }, { "epoch": 4.309873417721519, "grad_norm": 0.26172312397024106, "learning_rate": 2.1785813006799406e-06, "loss": 0.2102, "step": 1064 }, { "epoch": 4.313924050632911, "grad_norm": 0.2516714013760067, "learning_rate": 2.1528923780302224e-06, "loss": 0.2061, "step": 1065 }, { "epoch": 4.317974683544303, "grad_norm": 0.25211051979432547, "learning_rate": 2.127347193531757e-06, "loss": 0.2005, "step": 1066 }, { "epoch": 4.322025316455696, "grad_norm": 0.2669369091752155, "learning_rate": 2.101945952921942e-06, "loss": 0.2175, "step": 1067 }, { "epoch": 4.326075949367088, "grad_norm": 0.2620411155354285, "learning_rate": 2.0766888607788906e-06, "loss": 0.2043, "step": 1068 }, { "epoch": 4.330126582278481, "grad_norm": 0.25473957542555276, "learning_rate": 2.0515761205197337e-06, "loss": 0.2013, "step": 1069 }, { "epoch": 4.334177215189873, "grad_norm": 0.2538878456680882, "learning_rate": 2.0266079343990453e-06, "loss": 0.1877, "step": 1070 }, { "epoch": 4.3382278481012655, "grad_norm": 0.2679828072468956, "learning_rate": 2.0017845035071494e-06, "loss": 0.1977, "step": 1071 }, { "epoch": 4.3422784810126585, "grad_norm": 0.25424102258445963, "learning_rate": 1.9771060277685537e-06, "loss": 0.1864, "step": 1072 }, { "epoch": 4.3463291139240505, "grad_norm": 0.2567495984816703, "learning_rate": 1.95257270594031e-06, "loss": 0.2244, "step": 1073 }, { "epoch": 4.3503797468354435, "grad_norm": 0.25591010454047686, "learning_rate": 1.9281847356104188e-06, "loss": 0.214, "step": 1074 }, { "epoch": 4.3544303797468356, "grad_norm": 0.26007102968782314, "learning_rate": 1.9039423131962365e-06, "loss": 0.2027, "step": 1075 }, { "epoch": 4.358481012658228, "grad_norm": 0.2504724746397086, "learning_rate": 1.8798456339429027e-06, "loss": 0.2175, "step": 1076 }, { "epoch": 4.362531645569621, "grad_norm": 0.25715500215297166, "learning_rate": 1.8558948919217612e-06, "loss": 0.1994, "step": 1077 }, { "epoch": 4.366582278481013, "grad_norm": 0.2693125479345569, "learning_rate": 1.8320902800287954e-06, "loss": 0.1995, "step": 1078 }, { "epoch": 4.370632911392405, "grad_norm": 0.26017805125444016, "learning_rate": 1.8084319899830726e-06, "loss": 0.1819, "step": 1079 }, { "epoch": 4.374683544303798, "grad_norm": 0.2513390801072665, "learning_rate": 1.7849202123252097e-06, "loss": 0.1807, "step": 1080 }, { "epoch": 4.37873417721519, "grad_norm": 0.25489075741020345, "learning_rate": 1.7615551364158401e-06, "loss": 0.228, "step": 1081 }, { "epoch": 4.382784810126582, "grad_norm": 0.26626649380394846, "learning_rate": 1.738336950434061e-06, "loss": 0.1759, "step": 1082 }, { "epoch": 4.386835443037975, "grad_norm": 0.25774472228283635, "learning_rate": 1.715265841375957e-06, "loss": 0.1897, "step": 1083 }, { "epoch": 4.390886075949367, "grad_norm": 0.2871492458480163, "learning_rate": 1.6923419950530684e-06, "loss": 0.2196, "step": 1084 }, { "epoch": 4.39493670886076, "grad_norm": 0.25941329280393755, "learning_rate": 1.6695655960909008e-06, "loss": 0.223, "step": 1085 }, { "epoch": 4.398987341772152, "grad_norm": 0.25914760124287717, "learning_rate": 1.646936827927441e-06, "loss": 0.1951, "step": 1086 }, { "epoch": 4.403037974683544, "grad_norm": 0.26226799156374864, "learning_rate": 1.6244558728116766e-06, "loss": 0.1924, "step": 1087 }, { "epoch": 4.407088607594937, "grad_norm": 0.26353009798775956, "learning_rate": 1.6021229118021265e-06, "loss": 0.199, "step": 1088 }, { "epoch": 4.411139240506329, "grad_norm": 0.25119988440153457, "learning_rate": 1.5799381247653967e-06, "loss": 0.1891, "step": 1089 }, { "epoch": 4.415189873417722, "grad_norm": 0.26217085685319036, "learning_rate": 1.5579016903747013e-06, "loss": 0.189, "step": 1090 }, { "epoch": 4.419240506329114, "grad_norm": 0.24645475730048516, "learning_rate": 1.5360137861084656e-06, "loss": 0.2179, "step": 1091 }, { "epoch": 4.423291139240506, "grad_norm": 0.24695637188839822, "learning_rate": 1.5142745882488475e-06, "loss": 0.1759, "step": 1092 }, { "epoch": 4.427341772151899, "grad_norm": 0.2559573314342137, "learning_rate": 1.4926842718803691e-06, "loss": 0.2153, "step": 1093 }, { "epoch": 4.431392405063291, "grad_norm": 0.2573161995121045, "learning_rate": 1.4712430108884657e-06, "loss": 0.2016, "step": 1094 }, { "epoch": 4.435443037974683, "grad_norm": 0.2586803199702613, "learning_rate": 1.4499509779581078e-06, "loss": 0.2324, "step": 1095 }, { "epoch": 4.439493670886076, "grad_norm": 0.2651622153038958, "learning_rate": 1.4288083445723988e-06, "loss": 0.2164, "step": 1096 }, { "epoch": 4.443544303797468, "grad_norm": 0.2502690213887669, "learning_rate": 1.4078152810112045e-06, "loss": 0.2258, "step": 1097 }, { "epoch": 4.44759493670886, "grad_norm": 0.2599934974649156, "learning_rate": 1.3869719563497697e-06, "loss": 0.1938, "step": 1098 }, { "epoch": 4.451645569620253, "grad_norm": 0.2584474091905813, "learning_rate": 1.3662785384573663e-06, "loss": 0.208, "step": 1099 }, { "epoch": 4.455696202531645, "grad_norm": 0.25768108259988115, "learning_rate": 1.3457351939959383e-06, "loss": 0.2035, "step": 1100 }, { "epoch": 4.459746835443038, "grad_norm": 0.2515438237320309, "learning_rate": 1.3253420884187551e-06, "loss": 0.2159, "step": 1101 }, { "epoch": 4.46379746835443, "grad_norm": 0.2582943941626399, "learning_rate": 1.3050993859690953e-06, "loss": 0.1988, "step": 1102 }, { "epoch": 4.467848101265822, "grad_norm": 0.25803776308646204, "learning_rate": 1.2850072496788869e-06, "loss": 0.1895, "step": 1103 }, { "epoch": 4.471898734177215, "grad_norm": 0.2667497907608444, "learning_rate": 1.2650658413674434e-06, "loss": 0.1797, "step": 1104 }, { "epoch": 4.4759493670886075, "grad_norm": 0.26183066905086944, "learning_rate": 1.2452753216401226e-06, "loss": 0.2017, "step": 1105 }, { "epoch": 4.48, "grad_norm": 0.26287778319205124, "learning_rate": 1.2256358498870503e-06, "loss": 0.1995, "step": 1106 }, { "epoch": 4.4840506329113925, "grad_norm": 0.25629722855732373, "learning_rate": 1.2061475842818337e-06, "loss": 0.1827, "step": 1107 }, { "epoch": 4.488101265822785, "grad_norm": 0.26559805058494484, "learning_rate": 1.1868106817802816e-06, "loss": 0.1904, "step": 1108 }, { "epoch": 4.4921518987341775, "grad_norm": 0.2609879623743967, "learning_rate": 1.1676252981191482e-06, "loss": 0.2058, "step": 1109 }, { "epoch": 4.49620253164557, "grad_norm": 0.261599016675736, "learning_rate": 1.1485915878148823e-06, "loss": 0.2123, "step": 1110 }, { "epoch": 4.500253164556962, "grad_norm": 0.26175433947321614, "learning_rate": 1.1297097041623584e-06, "loss": 0.1908, "step": 1111 }, { "epoch": 4.504303797468355, "grad_norm": 0.2594173158023276, "learning_rate": 1.1109797992336847e-06, "loss": 0.2011, "step": 1112 }, { "epoch": 4.508354430379747, "grad_norm": 0.25402893037079205, "learning_rate": 1.092402023876933e-06, "loss": 0.212, "step": 1113 }, { "epoch": 4.512405063291139, "grad_norm": 0.26277772801270816, "learning_rate": 1.0739765277149527e-06, "loss": 0.2142, "step": 1114 }, { "epoch": 4.516455696202532, "grad_norm": 0.2620580201352199, "learning_rate": 1.0557034591441596e-06, "loss": 0.2098, "step": 1115 }, { "epoch": 4.520506329113924, "grad_norm": 0.2603600139609231, "learning_rate": 1.0375829653333324e-06, "loss": 0.1954, "step": 1116 }, { "epoch": 4.524556962025317, "grad_norm": 0.2661137592612214, "learning_rate": 1.0196151922224385e-06, "loss": 0.2109, "step": 1117 }, { "epoch": 4.528607594936709, "grad_norm": 0.2559249290469737, "learning_rate": 1.0018002845214526e-06, "loss": 0.1909, "step": 1118 }, { "epoch": 4.532658227848101, "grad_norm": 0.25385730057764094, "learning_rate": 9.841383857091947e-07, "loss": 0.2259, "step": 1119 }, { "epoch": 4.536708860759494, "grad_norm": 0.27120740012442074, "learning_rate": 9.666296380321616e-07, "loss": 0.1966, "step": 1120 }, { "epoch": 4.540759493670886, "grad_norm": 0.4674510156934785, "learning_rate": 9.492741825034124e-07, "loss": 0.1911, "step": 1121 }, { "epoch": 4.544810126582279, "grad_norm": 0.2538840568581922, "learning_rate": 9.320721589013892e-07, "loss": 0.2165, "step": 1122 }, { "epoch": 4.548860759493671, "grad_norm": 0.2429833265370068, "learning_rate": 9.150237057688339e-07, "loss": 0.2256, "step": 1123 }, { "epoch": 4.552911392405063, "grad_norm": 0.2610418096693974, "learning_rate": 8.981289604116328e-07, "loss": 0.2013, "step": 1124 }, { "epoch": 4.556962025316456, "grad_norm": 0.26125454018136046, "learning_rate": 8.813880588977542e-07, "loss": 0.1918, "step": 1125 }, { "epoch": 4.561012658227848, "grad_norm": 0.2677154661848974, "learning_rate": 8.648011360561126e-07, "loss": 0.2162, "step": 1126 }, { "epoch": 4.56506329113924, "grad_norm": 0.2688958375759793, "learning_rate": 8.483683254755037e-07, "loss": 0.2108, "step": 1127 }, { "epoch": 4.569113924050633, "grad_norm": 0.2600809163591567, "learning_rate": 8.320897595035227e-07, "loss": 0.1939, "step": 1128 }, { "epoch": 4.573164556962025, "grad_norm": 0.2532753898062609, "learning_rate": 8.159655692455093e-07, "loss": 0.2046, "step": 1129 }, { "epoch": 4.577215189873417, "grad_norm": 0.2629751299573545, "learning_rate": 7.999958845634648e-07, "loss": 0.1966, "step": 1130 }, { "epoch": 4.58126582278481, "grad_norm": 0.2563757443790689, "learning_rate": 7.841808340750478e-07, "loss": 0.2185, "step": 1131 }, { "epoch": 4.585316455696202, "grad_norm": 0.2592995942272794, "learning_rate": 7.685205451524869e-07, "loss": 0.196, "step": 1132 }, { "epoch": 4.589367088607595, "grad_norm": 0.27171705323379486, "learning_rate": 7.530151439216027e-07, "loss": 0.2135, "step": 1133 }, { "epoch": 4.593417721518987, "grad_norm": 0.2751242440938801, "learning_rate": 7.376647552607675e-07, "loss": 0.1834, "step": 1134 }, { "epoch": 4.597468354430379, "grad_norm": 0.2546290199015462, "learning_rate": 7.224695027998963e-07, "loss": 0.234, "step": 1135 }, { "epoch": 4.601518987341772, "grad_norm": 0.2560005061329681, "learning_rate": 7.07429508919466e-07, "loss": 0.2016, "step": 1136 }, { "epoch": 4.605569620253164, "grad_norm": 0.26596872341379246, "learning_rate": 6.925448947495206e-07, "loss": 0.2149, "step": 1137 }, { "epoch": 4.609620253164557, "grad_norm": 0.2535663908538801, "learning_rate": 6.778157801686936e-07, "loss": 0.2077, "step": 1138 }, { "epoch": 4.613670886075949, "grad_norm": 0.25233920575766744, "learning_rate": 6.632422838032515e-07, "loss": 0.2129, "step": 1139 }, { "epoch": 4.6177215189873415, "grad_norm": 0.24299980870599985, "learning_rate": 6.488245230261281e-07, "loss": 0.2182, "step": 1140 }, { "epoch": 4.6217721518987345, "grad_norm": 0.24791097924727792, "learning_rate": 6.345626139559868e-07, "loss": 0.2179, "step": 1141 }, { "epoch": 4.6258227848101265, "grad_norm": 0.2730718445904622, "learning_rate": 6.204566714562866e-07, "loss": 0.1816, "step": 1142 }, { "epoch": 4.629873417721519, "grad_norm": 0.2494814654743771, "learning_rate": 6.06506809134344e-07, "loss": 0.1884, "step": 1143 }, { "epoch": 4.633924050632912, "grad_norm": 0.25968782904862, "learning_rate": 5.927131393404373e-07, "loss": 0.2188, "step": 1144 }, { "epoch": 4.637974683544304, "grad_norm": 0.24873784113715391, "learning_rate": 5.790757731668817e-07, "loss": 0.2109, "step": 1145 }, { "epoch": 4.642025316455696, "grad_norm": 0.24663903671656864, "learning_rate": 5.655948204471507e-07, "loss": 0.2046, "step": 1146 }, { "epoch": 4.646075949367089, "grad_norm": 0.26455901870905174, "learning_rate": 5.522703897549875e-07, "loss": 0.165, "step": 1147 }, { "epoch": 4.650126582278481, "grad_norm": 0.25994147864716793, "learning_rate": 5.391025884035239e-07, "loss": 0.202, "step": 1148 }, { "epoch": 4.654177215189874, "grad_norm": 0.2552130883037689, "learning_rate": 5.260915224444207e-07, "loss": 0.1905, "step": 1149 }, { "epoch": 4.658227848101266, "grad_norm": 0.2520723647899325, "learning_rate": 5.132372966670129e-07, "loss": 0.1897, "step": 1150 }, { "epoch": 4.662278481012658, "grad_norm": 0.25541257682857565, "learning_rate": 5.005400145974704e-07, "loss": 0.1898, "step": 1151 }, { "epoch": 4.666329113924051, "grad_norm": 0.2633965121897966, "learning_rate": 4.879997784979562e-07, "loss": 0.2053, "step": 1152 }, { "epoch": 4.670379746835443, "grad_norm": 0.25155106278030187, "learning_rate": 4.7561668936580984e-07, "loss": 0.19, "step": 1153 }, { "epoch": 4.674430379746836, "grad_norm": 0.2733586599966375, "learning_rate": 4.6339084693272306e-07, "loss": 0.1718, "step": 1154 }, { "epoch": 4.678481012658228, "grad_norm": 0.2552157034368329, "learning_rate": 4.5132234966395847e-07, "loss": 0.2039, "step": 1155 }, { "epoch": 4.68253164556962, "grad_norm": 0.24499654876575175, "learning_rate": 4.3941129475752795e-07, "loss": 0.1967, "step": 1156 }, { "epoch": 4.686582278481013, "grad_norm": 0.2502528049258829, "learning_rate": 4.27657778143431e-07, "loss": 0.199, "step": 1157 }, { "epoch": 4.690632911392405, "grad_norm": 0.2506870405628806, "learning_rate": 4.1606189448287757e-07, "loss": 0.1944, "step": 1158 }, { "epoch": 4.694683544303797, "grad_norm": 0.25975165042784715, "learning_rate": 4.046237371675177e-07, "loss": 0.2017, "step": 1159 }, { "epoch": 4.69873417721519, "grad_norm": 0.25989418230897615, "learning_rate": 3.9334339831869963e-07, "loss": 0.2126, "step": 1160 }, { "epoch": 4.702784810126582, "grad_norm": 0.2659341974303986, "learning_rate": 3.8222096878671955e-07, "loss": 0.2008, "step": 1161 }, { "epoch": 4.706835443037974, "grad_norm": 0.2561937883750807, "learning_rate": 3.7125653815009545e-07, "loss": 0.1972, "step": 1162 }, { "epoch": 4.710886075949367, "grad_norm": 0.2513574699510313, "learning_rate": 3.6045019471484974e-07, "loss": 0.2124, "step": 1163 }, { "epoch": 4.714936708860759, "grad_norm": 0.250594883075141, "learning_rate": 3.498020255137813e-07, "loss": 0.2253, "step": 1164 }, { "epoch": 4.718987341772152, "grad_norm": 0.25733167524895595, "learning_rate": 3.393121163057811e-07, "loss": 0.192, "step": 1165 }, { "epoch": 4.723037974683544, "grad_norm": 0.262820307328474, "learning_rate": 3.289805515751399e-07, "loss": 0.1837, "step": 1166 }, { "epoch": 4.727088607594936, "grad_norm": 0.2593953805731552, "learning_rate": 3.188074145308573e-07, "loss": 0.2071, "step": 1167 }, { "epoch": 4.731139240506329, "grad_norm": 0.2727614628595669, "learning_rate": 3.087927871059804e-07, "loss": 0.1813, "step": 1168 }, { "epoch": 4.735189873417721, "grad_norm": 0.25644710902041545, "learning_rate": 2.989367499569418e-07, "loss": 0.2209, "step": 1169 }, { "epoch": 4.739240506329114, "grad_norm": 0.2599520810449123, "learning_rate": 2.8923938246290917e-07, "loss": 0.1911, "step": 1170 }, { "epoch": 4.743291139240506, "grad_norm": 0.26017748778682365, "learning_rate": 2.7970076272514804e-07, "loss": 0.2275, "step": 1171 }, { "epoch": 4.7473417721518985, "grad_norm": 0.2610670395905398, "learning_rate": 2.703209675663887e-07, "loss": 0.1898, "step": 1172 }, { "epoch": 4.751392405063291, "grad_norm": 0.2555266401171507, "learning_rate": 2.6110007253021374e-07, "loss": 0.1965, "step": 1173 }, { "epoch": 4.7554430379746835, "grad_norm": 0.25042632585807806, "learning_rate": 2.520381518804471e-07, "loss": 0.2075, "step": 1174 }, { "epoch": 4.759493670886076, "grad_norm": 0.2660657459053939, "learning_rate": 2.4313527860054585e-07, "loss": 0.1932, "step": 1175 }, { "epoch": 4.7635443037974685, "grad_norm": 0.2583544935638731, "learning_rate": 2.343915243930317e-07, "loss": 0.196, "step": 1176 }, { "epoch": 4.767594936708861, "grad_norm": 0.2589984230888356, "learning_rate": 2.2580695967889367e-07, "loss": 0.2009, "step": 1177 }, { "epoch": 4.7716455696202535, "grad_norm": 0.24829184066134716, "learning_rate": 2.1738165359704189e-07, "loss": 0.1991, "step": 1178 }, { "epoch": 4.775696202531646, "grad_norm": 0.255388176799681, "learning_rate": 2.0911567400373257e-07, "loss": 0.2032, "step": 1179 }, { "epoch": 4.779746835443038, "grad_norm": 0.261126904992374, "learning_rate": 2.0100908747202607e-07, "loss": 0.1797, "step": 1180 }, { "epoch": 4.783797468354431, "grad_norm": 0.2727703311843937, "learning_rate": 1.9306195929125638e-07, "loss": 0.1932, "step": 1181 }, { "epoch": 4.787848101265823, "grad_norm": 0.25512819137521175, "learning_rate": 1.8527435346650247e-07, "loss": 0.1824, "step": 1182 }, { "epoch": 4.791898734177215, "grad_norm": 0.25685994501467535, "learning_rate": 1.7764633271807108e-07, "loss": 0.1858, "step": 1183 }, { "epoch": 4.795949367088608, "grad_norm": 0.26116843727275263, "learning_rate": 1.7017795848099262e-07, "loss": 0.2037, "step": 1184 }, { "epoch": 4.8, "grad_norm": 0.24261649317112205, "learning_rate": 1.6286929090452596e-07, "loss": 0.1974, "step": 1185 }, { "epoch": 4.804050632911393, "grad_norm": 0.2632508888810747, "learning_rate": 1.557203888516745e-07, "loss": 0.1921, "step": 1186 }, { "epoch": 4.808101265822785, "grad_norm": 0.2526033265860498, "learning_rate": 1.487313098987131e-07, "loss": 0.1872, "step": 1187 }, { "epoch": 4.812151898734177, "grad_norm": 0.25713280328575305, "learning_rate": 1.4190211033472402e-07, "loss": 0.2171, "step": 1188 }, { "epoch": 4.81620253164557, "grad_norm": 0.2531221889466361, "learning_rate": 1.3523284516113955e-07, "loss": 0.2226, "step": 1189 }, { "epoch": 4.820253164556962, "grad_norm": 0.27028921977515946, "learning_rate": 1.2872356809130682e-07, "loss": 0.2086, "step": 1190 }, { "epoch": 4.824303797468355, "grad_norm": 0.26184631258232305, "learning_rate": 1.2237433155004807e-07, "loss": 0.1823, "step": 1191 }, { "epoch": 4.828354430379747, "grad_norm": 0.2557204609831343, "learning_rate": 1.1618518667323886e-07, "loss": 0.1981, "step": 1192 }, { "epoch": 4.832405063291139, "grad_norm": 0.2688487183483729, "learning_rate": 1.1015618330740385e-07, "loss": 0.189, "step": 1193 }, { "epoch": 4.836455696202532, "grad_norm": 0.24407445507673506, "learning_rate": 1.042873700093061e-07, "loss": 0.212, "step": 1194 }, { "epoch": 4.840506329113924, "grad_norm": 0.25168007593479574, "learning_rate": 9.857879404556291e-08, "loss": 0.1842, "step": 1195 }, { "epoch": 4.844556962025316, "grad_norm": 0.24729472746524225, "learning_rate": 9.303050139225722e-08, "loss": 0.2105, "step": 1196 }, { "epoch": 4.848607594936709, "grad_norm": 0.25087842294525586, "learning_rate": 8.76425367345779e-08, "loss": 0.202, "step": 1197 }, { "epoch": 4.852658227848101, "grad_norm": 0.255093151643287, "learning_rate": 8.241494346644897e-08, "loss": 0.1988, "step": 1198 }, { "epoch": 4.856708860759493, "grad_norm": 0.26493440825250186, "learning_rate": 7.734776369019204e-08, "loss": 0.1899, "step": 1199 }, { "epoch": 4.860759493670886, "grad_norm": 0.2509506896831489, "learning_rate": 7.244103821617332e-08, "loss": 0.1991, "step": 1200 }, { "epoch": 4.864810126582278, "grad_norm": 0.24976165575565415, "learning_rate": 6.769480656248606e-08, "loss": 0.1975, "step": 1201 }, { "epoch": 4.868860759493671, "grad_norm": 0.25677453688847107, "learning_rate": 6.310910695462635e-08, "loss": 0.1891, "step": 1202 }, { "epoch": 4.872911392405063, "grad_norm": 0.24960798396536554, "learning_rate": 5.8683976325191185e-08, "loss": 0.1964, "step": 1203 }, { "epoch": 4.876962025316455, "grad_norm": 0.2562673030771883, "learning_rate": 5.4419450313571984e-08, "loss": 0.1952, "step": 1204 }, { "epoch": 4.881012658227848, "grad_norm": 0.25148256604317804, "learning_rate": 5.031556326567488e-08, "loss": 0.2053, "step": 1205 }, { "epoch": 4.88506329113924, "grad_norm": 0.25132293409313355, "learning_rate": 4.637234823364312e-08, "loss": 0.192, "step": 1206 }, { "epoch": 4.889113924050633, "grad_norm": 0.25161290702266537, "learning_rate": 4.258983697558838e-08, "loss": 0.2018, "step": 1207 }, { "epoch": 4.8931645569620255, "grad_norm": 0.2614603720015524, "learning_rate": 3.896805995533548e-08, "loss": 0.199, "step": 1208 }, { "epoch": 4.8972151898734175, "grad_norm": 0.25439785288439415, "learning_rate": 3.550704634218028e-08, "loss": 0.1814, "step": 1209 }, { "epoch": 4.9012658227848105, "grad_norm": 0.2562978210273886, "learning_rate": 3.2206824010647676e-08, "loss": 0.2226, "step": 1210 }, { "epoch": 4.905316455696203, "grad_norm": 0.2562906441919873, "learning_rate": 2.9067419540278476e-08, "loss": 0.1978, "step": 1211 }, { "epoch": 4.909367088607595, "grad_norm": 0.26166661741583147, "learning_rate": 2.6088858215400638e-08, "loss": 0.2073, "step": 1212 }, { "epoch": 4.913417721518988, "grad_norm": 0.2550683316951649, "learning_rate": 2.3271164024940564e-08, "loss": 0.1867, "step": 1213 }, { "epoch": 4.91746835443038, "grad_norm": 0.24370769207392634, "learning_rate": 2.061435966221881e-08, "loss": 0.1921, "step": 1214 }, { "epoch": 4.921518987341772, "grad_norm": 0.26294511697653583, "learning_rate": 1.811846652477245e-08, "loss": 0.1979, "step": 1215 }, { "epoch": 4.925569620253165, "grad_norm": 0.260366888458207, "learning_rate": 1.5783504714184106e-08, "loss": 0.1627, "step": 1216 }, { "epoch": 4.929620253164557, "grad_norm": 0.2577422841424921, "learning_rate": 1.360949303591097e-08, "loss": 0.1941, "step": 1217 }, { "epoch": 4.93367088607595, "grad_norm": 0.25550922183224617, "learning_rate": 1.1596448999144916e-08, "loss": 0.2122, "step": 1218 }, { "epoch": 4.937721518987342, "grad_norm": 0.2570343867327324, "learning_rate": 9.744388816668172e-09, "loss": 0.2049, "step": 1219 }, { "epoch": 4.941772151898734, "grad_norm": 0.24995684680426222, "learning_rate": 8.05332740472009e-09, "loss": 0.1968, "step": 1220 }, { "epoch": 4.945822784810127, "grad_norm": 0.24258178275605372, "learning_rate": 6.523278382872811e-09, "loss": 0.2065, "step": 1221 }, { "epoch": 4.949873417721519, "grad_norm": 0.24767610996219358, "learning_rate": 5.15425407393133e-09, "loss": 0.2223, "step": 1222 }, { "epoch": 4.953924050632912, "grad_norm": 0.26362975951420525, "learning_rate": 3.94626550383137e-09, "loss": 0.212, "step": 1223 }, { "epoch": 4.957974683544304, "grad_norm": 0.2629444180484097, "learning_rate": 2.899322401546112e-09, "loss": 0.202, "step": 1224 }, { "epoch": 4.962025316455696, "grad_norm": 0.2515087426519623, "learning_rate": 2.013433199010706e-09, "loss": 0.2, "step": 1225 }, { "epoch": 4.966075949367089, "grad_norm": 0.2640666157848904, "learning_rate": 1.2886050310556563e-09, "loss": 0.2032, "step": 1226 }, { "epoch": 4.970126582278481, "grad_norm": 0.24909500709443078, "learning_rate": 7.248437353468695e-10, "loss": 0.2001, "step": 1227 }, { "epoch": 4.974177215189873, "grad_norm": 0.2468695280513938, "learning_rate": 3.221538523412449e-10, "loss": 0.1929, "step": 1228 }, { "epoch": 4.978227848101266, "grad_norm": 0.276345255589295, "learning_rate": 8.053862524670663e-11, "loss": 0.212, "step": 1229 }, { "epoch": 4.982278481012658, "grad_norm": 0.2535100196043872, "learning_rate": 0.0, "loss": 0.1996, "step": 1230 }, { "epoch": 4.982278481012658, "step": 1230, "total_flos": 2.622219768794677e+18, "train_loss": 0.4246671596678292, "train_runtime": 41165.0994, "train_samples_per_second": 3.838, "train_steps_per_second": 0.03 } ], "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": 2.622219768794677e+18, "train_batch_size": 1, "trial_name": null, "trial_params": null }