{ "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": 7.617837834116492, "learning_rate": 3.2520325203252037e-07, "loss": 1.16, "step": 1 }, { "epoch": 0.00810126582278481, "grad_norm": 7.417931077521923, "learning_rate": 6.504065040650407e-07, "loss": 1.1423, "step": 2 }, { "epoch": 0.012151898734177215, "grad_norm": 7.606860267963496, "learning_rate": 9.75609756097561e-07, "loss": 1.1734, "step": 3 }, { "epoch": 0.01620253164556962, "grad_norm": 7.515965761968464, "learning_rate": 1.3008130081300815e-06, "loss": 1.1754, "step": 4 }, { "epoch": 0.020253164556962026, "grad_norm": 7.504836227756345, "learning_rate": 1.6260162601626018e-06, "loss": 1.1723, "step": 5 }, { "epoch": 0.02430379746835443, "grad_norm": 7.299424243274091, "learning_rate": 1.951219512195122e-06, "loss": 1.1428, "step": 6 }, { "epoch": 0.028354430379746835, "grad_norm": 5.778445365140883, "learning_rate": 2.2764227642276426e-06, "loss": 1.1097, "step": 7 }, { "epoch": 0.03240506329113924, "grad_norm": 5.450445763001378, "learning_rate": 2.601626016260163e-06, "loss": 1.092, "step": 8 }, { "epoch": 0.03645569620253165, "grad_norm": 2.9604833422994634, "learning_rate": 2.926829268292683e-06, "loss": 1.0088, "step": 9 }, { "epoch": 0.04050632911392405, "grad_norm": 2.6489016372318983, "learning_rate": 3.2520325203252037e-06, "loss": 1.0173, "step": 10 }, { "epoch": 0.044556962025316456, "grad_norm": 2.522059935761868, "learning_rate": 3.577235772357724e-06, "loss": 1.0197, "step": 11 }, { "epoch": 0.04860759493670886, "grad_norm": 4.515346650668116, "learning_rate": 3.902439024390244e-06, "loss": 0.9929, "step": 12 }, { "epoch": 0.052658227848101265, "grad_norm": 4.80670169866494, "learning_rate": 4.227642276422765e-06, "loss": 0.991, "step": 13 }, { "epoch": 0.05670886075949367, "grad_norm": 4.727799783269868, "learning_rate": 4.552845528455285e-06, "loss": 0.9932, "step": 14 }, { "epoch": 0.060759493670886074, "grad_norm": 4.260893950833707, "learning_rate": 4.8780487804878055e-06, "loss": 0.9403, "step": 15 }, { "epoch": 0.06481012658227848, "grad_norm": 3.1504838055854165, "learning_rate": 5.203252032520326e-06, "loss": 0.9033, "step": 16 }, { "epoch": 0.06886075949367089, "grad_norm": 3.0838556343365084, "learning_rate": 5.528455284552846e-06, "loss": 0.9157, "step": 17 }, { "epoch": 0.0729113924050633, "grad_norm": 2.6673292595102427, "learning_rate": 5.853658536585366e-06, "loss": 0.9018, "step": 18 }, { "epoch": 0.0769620253164557, "grad_norm": 2.4414909823384296, "learning_rate": 6.178861788617887e-06, "loss": 0.8668, "step": 19 }, { "epoch": 0.0810126582278481, "grad_norm": 2.307983627045584, "learning_rate": 6.504065040650407e-06, "loss": 0.8661, "step": 20 }, { "epoch": 0.08506329113924051, "grad_norm": 1.8685378925294627, "learning_rate": 6.829268292682928e-06, "loss": 0.8833, "step": 21 }, { "epoch": 0.08911392405063291, "grad_norm": 1.6749854917821847, "learning_rate": 7.154471544715448e-06, "loss": 0.8533, "step": 22 }, { "epoch": 0.09316455696202532, "grad_norm": 1.855433138871714, "learning_rate": 7.4796747967479676e-06, "loss": 0.8395, "step": 23 }, { "epoch": 0.09721518987341772, "grad_norm": 1.8263617948735995, "learning_rate": 7.804878048780489e-06, "loss": 0.8508, "step": 24 }, { "epoch": 0.10126582278481013, "grad_norm": 1.5531368939819, "learning_rate": 8.130081300813009e-06, "loss": 0.8504, "step": 25 }, { "epoch": 0.10531645569620253, "grad_norm": 1.2512894603261764, "learning_rate": 8.45528455284553e-06, "loss": 0.8245, "step": 26 }, { "epoch": 0.10936708860759493, "grad_norm": 1.2066141761952367, "learning_rate": 8.78048780487805e-06, "loss": 0.806, "step": 27 }, { "epoch": 0.11341772151898734, "grad_norm": 1.3298840676771275, "learning_rate": 9.10569105691057e-06, "loss": 0.8194, "step": 28 }, { "epoch": 0.11746835443037974, "grad_norm": 1.168822278347949, "learning_rate": 9.43089430894309e-06, "loss": 0.8127, "step": 29 }, { "epoch": 0.12151898734177215, "grad_norm": 1.088777832901239, "learning_rate": 9.756097560975611e-06, "loss": 0.7995, "step": 30 }, { "epoch": 0.12556962025316457, "grad_norm": 1.058396988456167, "learning_rate": 1.008130081300813e-05, "loss": 0.8263, "step": 31 }, { "epoch": 0.12962025316455697, "grad_norm": 1.1274307431191168, "learning_rate": 1.0406504065040652e-05, "loss": 0.7958, "step": 32 }, { "epoch": 0.13367088607594937, "grad_norm": 0.9651136167335175, "learning_rate": 1.0731707317073172e-05, "loss": 0.8053, "step": 33 }, { "epoch": 0.13772151898734178, "grad_norm": 0.9266835743150675, "learning_rate": 1.1056910569105692e-05, "loss": 0.7892, "step": 34 }, { "epoch": 0.14177215189873418, "grad_norm": 0.8125798553421062, "learning_rate": 1.1382113821138213e-05, "loss": 0.7842, "step": 35 }, { "epoch": 0.1458227848101266, "grad_norm": 0.9013352571554477, "learning_rate": 1.1707317073170731e-05, "loss": 0.7924, "step": 36 }, { "epoch": 0.149873417721519, "grad_norm": 0.7947414433363965, "learning_rate": 1.2032520325203254e-05, "loss": 0.7853, "step": 37 }, { "epoch": 0.1539240506329114, "grad_norm": 0.8337772816859146, "learning_rate": 1.2357723577235774e-05, "loss": 0.7691, "step": 38 }, { "epoch": 0.1579746835443038, "grad_norm": 0.778126598934907, "learning_rate": 1.2682926829268294e-05, "loss": 0.7629, "step": 39 }, { "epoch": 0.1620253164556962, "grad_norm": 0.7812155515983142, "learning_rate": 1.3008130081300815e-05, "loss": 0.7745, "step": 40 }, { "epoch": 0.1660759493670886, "grad_norm": 0.7653643610543535, "learning_rate": 1.3333333333333333e-05, "loss": 0.7473, "step": 41 }, { "epoch": 0.17012658227848101, "grad_norm": 0.739067853282636, "learning_rate": 1.3658536585365855e-05, "loss": 0.7453, "step": 42 }, { "epoch": 0.17417721518987342, "grad_norm": 0.749100251547327, "learning_rate": 1.3983739837398376e-05, "loss": 0.7648, "step": 43 }, { "epoch": 0.17822784810126582, "grad_norm": 0.7520704205913245, "learning_rate": 1.4308943089430896e-05, "loss": 0.7751, "step": 44 }, { "epoch": 0.18227848101265823, "grad_norm": 0.7477056834302785, "learning_rate": 1.4634146341463415e-05, "loss": 0.7447, "step": 45 }, { "epoch": 0.18632911392405063, "grad_norm": 0.7525722847598849, "learning_rate": 1.4959349593495935e-05, "loss": 0.7643, "step": 46 }, { "epoch": 0.19037974683544304, "grad_norm": 0.772263309901149, "learning_rate": 1.528455284552846e-05, "loss": 0.7656, "step": 47 }, { "epoch": 0.19443037974683544, "grad_norm": 0.7940700035485274, "learning_rate": 1.5609756097560978e-05, "loss": 0.729, "step": 48 }, { "epoch": 0.19848101265822785, "grad_norm": 0.8366387877570672, "learning_rate": 1.5934959349593496e-05, "loss": 0.7387, "step": 49 }, { "epoch": 0.20253164556962025, "grad_norm": 0.8893513253853156, "learning_rate": 1.6260162601626018e-05, "loss": 0.7726, "step": 50 }, { "epoch": 0.20658227848101265, "grad_norm": 0.8022094990955485, "learning_rate": 1.6585365853658537e-05, "loss": 0.7943, "step": 51 }, { "epoch": 0.21063291139240506, "grad_norm": 0.8704100879488675, "learning_rate": 1.691056910569106e-05, "loss": 0.7616, "step": 52 }, { "epoch": 0.21468354430379746, "grad_norm": 0.872234865152445, "learning_rate": 1.7235772357723578e-05, "loss": 0.7721, "step": 53 }, { "epoch": 0.21873417721518987, "grad_norm": 0.9416090934271246, "learning_rate": 1.75609756097561e-05, "loss": 0.7453, "step": 54 }, { "epoch": 0.22278481012658227, "grad_norm": 0.9416482601863565, "learning_rate": 1.788617886178862e-05, "loss": 0.7557, "step": 55 }, { "epoch": 0.22683544303797468, "grad_norm": 0.8046315109599508, "learning_rate": 1.821138211382114e-05, "loss": 0.752, "step": 56 }, { "epoch": 0.23088607594936708, "grad_norm": 0.9299905221184107, "learning_rate": 1.8536585365853663e-05, "loss": 0.759, "step": 57 }, { "epoch": 0.23493670886075949, "grad_norm": 0.8022311793740524, "learning_rate": 1.886178861788618e-05, "loss": 0.7767, "step": 58 }, { "epoch": 0.2389873417721519, "grad_norm": 0.8711396886954561, "learning_rate": 1.91869918699187e-05, "loss": 0.7516, "step": 59 }, { "epoch": 0.2430379746835443, "grad_norm": 0.8183353148958978, "learning_rate": 1.9512195121951222e-05, "loss": 0.7453, "step": 60 }, { "epoch": 0.2470886075949367, "grad_norm": 0.8115093347934724, "learning_rate": 1.983739837398374e-05, "loss": 0.7656, "step": 61 }, { "epoch": 0.25113924050632913, "grad_norm": 0.8633786980257462, "learning_rate": 2.016260162601626e-05, "loss": 0.757, "step": 62 }, { "epoch": 0.25518987341772154, "grad_norm": 0.8514754940173566, "learning_rate": 2.048780487804878e-05, "loss": 0.7403, "step": 63 }, { "epoch": 0.25924050632911394, "grad_norm": 0.7129303477349457, "learning_rate": 2.0813008130081303e-05, "loss": 0.7466, "step": 64 }, { "epoch": 0.26329113924050634, "grad_norm": 0.8018961631687076, "learning_rate": 2.1138211382113822e-05, "loss": 0.7721, "step": 65 }, { "epoch": 0.26734177215189875, "grad_norm": 0.8104385440332211, "learning_rate": 2.1463414634146344e-05, "loss": 0.7458, "step": 66 }, { "epoch": 0.27139240506329115, "grad_norm": 0.7675494954856981, "learning_rate": 2.1788617886178863e-05, "loss": 0.7652, "step": 67 }, { "epoch": 0.27544303797468356, "grad_norm": 0.9220731993923245, "learning_rate": 2.2113821138211385e-05, "loss": 0.7877, "step": 68 }, { "epoch": 0.27949367088607596, "grad_norm": 0.7383789161415777, "learning_rate": 2.2439024390243907e-05, "loss": 0.7505, "step": 69 }, { "epoch": 0.28354430379746837, "grad_norm": 0.8955290663786842, "learning_rate": 2.2764227642276426e-05, "loss": 0.7216, "step": 70 }, { "epoch": 0.28759493670886077, "grad_norm": 0.8248372255496892, "learning_rate": 2.3089430894308948e-05, "loss": 0.7447, "step": 71 }, { "epoch": 0.2916455696202532, "grad_norm": 0.8408748786038153, "learning_rate": 2.3414634146341463e-05, "loss": 0.7445, "step": 72 }, { "epoch": 0.2956962025316456, "grad_norm": 0.789993242231247, "learning_rate": 2.3739837398373985e-05, "loss": 0.7681, "step": 73 }, { "epoch": 0.299746835443038, "grad_norm": 0.8277876728889325, "learning_rate": 2.4065040650406507e-05, "loss": 0.7301, "step": 74 }, { "epoch": 0.3037974683544304, "grad_norm": 0.7169461455471284, "learning_rate": 2.4390243902439026e-05, "loss": 0.7544, "step": 75 }, { "epoch": 0.3078481012658228, "grad_norm": 0.8027879530003417, "learning_rate": 2.4715447154471548e-05, "loss": 0.7484, "step": 76 }, { "epoch": 0.3118987341772152, "grad_norm": 0.851351501635389, "learning_rate": 2.5040650406504066e-05, "loss": 0.7659, "step": 77 }, { "epoch": 0.3159493670886076, "grad_norm": 0.8687979162707072, "learning_rate": 2.536585365853659e-05, "loss": 0.7717, "step": 78 }, { "epoch": 0.32, "grad_norm": 0.8664173801515614, "learning_rate": 2.569105691056911e-05, "loss": 0.7399, "step": 79 }, { "epoch": 0.3240506329113924, "grad_norm": 0.7910677015025227, "learning_rate": 2.601626016260163e-05, "loss": 0.7553, "step": 80 }, { "epoch": 0.3281012658227848, "grad_norm": 0.9406217995821762, "learning_rate": 2.634146341463415e-05, "loss": 0.7363, "step": 81 }, { "epoch": 0.3321518987341772, "grad_norm": 0.9492761564130546, "learning_rate": 2.6666666666666667e-05, "loss": 0.7229, "step": 82 }, { "epoch": 0.3362025316455696, "grad_norm": 0.8109955138725587, "learning_rate": 2.699186991869919e-05, "loss": 0.7224, "step": 83 }, { "epoch": 0.34025316455696203, "grad_norm": 0.9452321053107655, "learning_rate": 2.731707317073171e-05, "loss": 0.7409, "step": 84 }, { "epoch": 0.34430379746835443, "grad_norm": 0.7764623336175654, "learning_rate": 2.764227642276423e-05, "loss": 0.7531, "step": 85 }, { "epoch": 0.34835443037974684, "grad_norm": 0.8514290447226843, "learning_rate": 2.796747967479675e-05, "loss": 0.7336, "step": 86 }, { "epoch": 0.35240506329113924, "grad_norm": 0.8220602288596803, "learning_rate": 2.829268292682927e-05, "loss": 0.7445, "step": 87 }, { "epoch": 0.35645569620253165, "grad_norm": 0.9129006525140244, "learning_rate": 2.8617886178861792e-05, "loss": 0.7415, "step": 88 }, { "epoch": 0.36050632911392405, "grad_norm": 0.7666673346116649, "learning_rate": 2.8943089430894314e-05, "loss": 0.7468, "step": 89 }, { "epoch": 0.36455696202531646, "grad_norm": 0.9722556473580112, "learning_rate": 2.926829268292683e-05, "loss": 0.7479, "step": 90 }, { "epoch": 0.36860759493670886, "grad_norm": 0.7345631874230992, "learning_rate": 2.959349593495935e-05, "loss": 0.7085, "step": 91 }, { "epoch": 0.37265822784810126, "grad_norm": 0.8780947191729689, "learning_rate": 2.991869918699187e-05, "loss": 0.7378, "step": 92 }, { "epoch": 0.37670886075949367, "grad_norm": 0.9424179266328594, "learning_rate": 3.0243902439024392e-05, "loss": 0.7492, "step": 93 }, { "epoch": 0.3807594936708861, "grad_norm": 0.7572585709207498, "learning_rate": 3.056910569105692e-05, "loss": 0.7335, "step": 94 }, { "epoch": 0.3848101265822785, "grad_norm": 0.8887246913474167, "learning_rate": 3.089430894308943e-05, "loss": 0.7234, "step": 95 }, { "epoch": 0.3888607594936709, "grad_norm": 0.9047376044140383, "learning_rate": 3.1219512195121955e-05, "loss": 0.7357, "step": 96 }, { "epoch": 0.3929113924050633, "grad_norm": 0.7696771855144633, "learning_rate": 3.154471544715447e-05, "loss": 0.7204, "step": 97 }, { "epoch": 0.3969620253164557, "grad_norm": 0.867175722471642, "learning_rate": 3.186991869918699e-05, "loss": 0.7258, "step": 98 }, { "epoch": 0.4010126582278481, "grad_norm": 0.7040541294197078, "learning_rate": 3.2195121951219514e-05, "loss": 0.7135, "step": 99 }, { "epoch": 0.4050632911392405, "grad_norm": 0.9184704702960393, "learning_rate": 3.2520325203252037e-05, "loss": 0.7271, "step": 100 }, { "epoch": 0.4091139240506329, "grad_norm": 0.7929035893414408, "learning_rate": 3.284552845528456e-05, "loss": 0.7066, "step": 101 }, { "epoch": 0.4131645569620253, "grad_norm": 0.7950896971160175, "learning_rate": 3.3170731707317074e-05, "loss": 0.7055, "step": 102 }, { "epoch": 0.4172151898734177, "grad_norm": 0.8965032622282595, "learning_rate": 3.3495934959349596e-05, "loss": 0.7543, "step": 103 }, { "epoch": 0.4212658227848101, "grad_norm": 0.9315180596753461, "learning_rate": 3.382113821138212e-05, "loss": 0.729, "step": 104 }, { "epoch": 0.4253164556962025, "grad_norm": 0.9279893880978063, "learning_rate": 3.414634146341463e-05, "loss": 0.747, "step": 105 }, { "epoch": 0.4293670886075949, "grad_norm": 0.6617918943168188, "learning_rate": 3.4471544715447155e-05, "loss": 0.7249, "step": 106 }, { "epoch": 0.43341772151898733, "grad_norm": 0.9618429083670235, "learning_rate": 3.479674796747968e-05, "loss": 0.7285, "step": 107 }, { "epoch": 0.43746835443037974, "grad_norm": 0.8088754051732185, "learning_rate": 3.51219512195122e-05, "loss": 0.7247, "step": 108 }, { "epoch": 0.44151898734177214, "grad_norm": 1.1365174139683911, "learning_rate": 3.544715447154472e-05, "loss": 0.7566, "step": 109 }, { "epoch": 0.44556962025316454, "grad_norm": 0.7178905036979701, "learning_rate": 3.577235772357724e-05, "loss": 0.6951, "step": 110 }, { "epoch": 0.44962025316455695, "grad_norm": 1.0088517939744934, "learning_rate": 3.609756097560976e-05, "loss": 0.7313, "step": 111 }, { "epoch": 0.45367088607594935, "grad_norm": 0.7673244929215312, "learning_rate": 3.642276422764228e-05, "loss": 0.7477, "step": 112 }, { "epoch": 0.45772151898734176, "grad_norm": 1.2239627794127412, "learning_rate": 3.67479674796748e-05, "loss": 0.7602, "step": 113 }, { "epoch": 0.46177215189873416, "grad_norm": 0.7872479182663926, "learning_rate": 3.7073170731707325e-05, "loss": 0.72, "step": 114 }, { "epoch": 0.46582278481012657, "grad_norm": 1.2891216566726784, "learning_rate": 3.739837398373984e-05, "loss": 0.7409, "step": 115 }, { "epoch": 0.46987341772151897, "grad_norm": 0.8949176111459162, "learning_rate": 3.772357723577236e-05, "loss": 0.7257, "step": 116 }, { "epoch": 0.4739240506329114, "grad_norm": 1.289291749325952, "learning_rate": 3.804878048780488e-05, "loss": 0.6993, "step": 117 }, { "epoch": 0.4779746835443038, "grad_norm": 1.008639565509747, "learning_rate": 3.83739837398374e-05, "loss": 0.7436, "step": 118 }, { "epoch": 0.4820253164556962, "grad_norm": 1.1338011410438353, "learning_rate": 3.869918699186992e-05, "loss": 0.7647, "step": 119 }, { "epoch": 0.4860759493670886, "grad_norm": 1.0748552031683016, "learning_rate": 3.9024390243902444e-05, "loss": 0.7383, "step": 120 }, { "epoch": 0.490126582278481, "grad_norm": 1.1074337141420132, "learning_rate": 3.9349593495934966e-05, "loss": 0.7373, "step": 121 }, { "epoch": 0.4941772151898734, "grad_norm": 1.098106333360525, "learning_rate": 3.967479674796748e-05, "loss": 0.7373, "step": 122 }, { "epoch": 0.4982278481012658, "grad_norm": 0.9963183414002057, "learning_rate": 4e-05, "loss": 0.7585, "step": 123 }, { "epoch": 0.5022784810126583, "grad_norm": 1.0370119354119411, "learning_rate": 3.999991946137476e-05, "loss": 0.7605, "step": 124 }, { "epoch": 0.5063291139240507, "grad_norm": 1.1475572649849635, "learning_rate": 3.999967784614766e-05, "loss": 0.7049, "step": 125 }, { "epoch": 0.5103797468354431, "grad_norm": 0.9276943623171345, "learning_rate": 3.9999275156264656e-05, "loss": 0.7355, "step": 126 }, { "epoch": 0.5144303797468355, "grad_norm": 1.3657754648094234, "learning_rate": 3.999871139496895e-05, "loss": 0.7333, "step": 127 }, { "epoch": 0.5184810126582279, "grad_norm": 1.139645822441082, "learning_rate": 3.9997986566800995e-05, "loss": 0.7442, "step": 128 }, { "epoch": 0.5225316455696203, "grad_norm": 1.1278006160142324, "learning_rate": 3.999710067759846e-05, "loss": 0.7359, "step": 129 }, { "epoch": 0.5265822784810127, "grad_norm": 0.9107027968782215, "learning_rate": 3.999605373449617e-05, "loss": 0.7566, "step": 130 }, { "epoch": 0.5306329113924051, "grad_norm": 0.9250248843713331, "learning_rate": 3.9994845745926075e-05, "loss": 0.7404, "step": 131 }, { "epoch": 0.5346835443037975, "grad_norm": 0.8657453861204257, "learning_rate": 3.999347672161713e-05, "loss": 0.7449, "step": 132 }, { "epoch": 0.5387341772151899, "grad_norm": 0.8004544312607134, "learning_rate": 3.999194667259528e-05, "loss": 0.7459, "step": 133 }, { "epoch": 0.5427848101265823, "grad_norm": 0.7845345787126302, "learning_rate": 3.999025561118334e-05, "loss": 0.7728, "step": 134 }, { "epoch": 0.5468354430379747, "grad_norm": 0.8115141376197885, "learning_rate": 3.998840355100086e-05, "loss": 0.7365, "step": 135 }, { "epoch": 0.5508860759493671, "grad_norm": 0.7900957115017105, "learning_rate": 3.998639050696409e-05, "loss": 0.7112, "step": 136 }, { "epoch": 0.5549367088607595, "grad_norm": 0.9272734389119743, "learning_rate": 3.998421649528582e-05, "loss": 0.7557, "step": 137 }, { "epoch": 0.5589873417721519, "grad_norm": 0.7897595779744797, "learning_rate": 3.9981881533475234e-05, "loss": 0.7208, "step": 138 }, { "epoch": 0.5630379746835443, "grad_norm": 0.9918127964924532, "learning_rate": 3.997938564033779e-05, "loss": 0.7016, "step": 139 }, { "epoch": 0.5670886075949367, "grad_norm": 0.8027764166579886, "learning_rate": 3.9976728835975064e-05, "loss": 0.7145, "step": 140 }, { "epoch": 0.5711392405063291, "grad_norm": 0.9169581174010155, "learning_rate": 3.9973911141784605e-05, "loss": 0.7142, "step": 141 }, { "epoch": 0.5751898734177215, "grad_norm": 0.959957041433855, "learning_rate": 3.997093258045973e-05, "loss": 0.7358, "step": 142 }, { "epoch": 0.579240506329114, "grad_norm": 0.7119752185115049, "learning_rate": 3.996779317598936e-05, "loss": 0.7691, "step": 143 }, { "epoch": 0.5832911392405064, "grad_norm": 1.1634983638378682, "learning_rate": 3.996449295365782e-05, "loss": 0.751, "step": 144 }, { "epoch": 0.5873417721518988, "grad_norm": 0.8193958037340558, "learning_rate": 3.996103194004467e-05, "loss": 0.724, "step": 145 }, { "epoch": 0.5913924050632912, "grad_norm": 0.806628799022185, "learning_rate": 3.995741016302441e-05, "loss": 0.7397, "step": 146 }, { "epoch": 0.5954430379746836, "grad_norm": 0.9300929906170152, "learning_rate": 3.9953627651766364e-05, "loss": 0.7151, "step": 147 }, { "epoch": 0.599493670886076, "grad_norm": 0.798928849850063, "learning_rate": 3.9949684436734325e-05, "loss": 0.7222, "step": 148 }, { "epoch": 0.6035443037974684, "grad_norm": 0.9285120449268384, "learning_rate": 3.994558054968643e-05, "loss": 0.7064, "step": 149 }, { "epoch": 0.6075949367088608, "grad_norm": 0.9029742837464774, "learning_rate": 3.994131602367481e-05, "loss": 0.7184, "step": 150 }, { "epoch": 0.6116455696202532, "grad_norm": 0.840555310062713, "learning_rate": 3.9936890893045376e-05, "loss": 0.7551, "step": 151 }, { "epoch": 0.6156962025316456, "grad_norm": 0.9476973483313873, "learning_rate": 3.993230519343752e-05, "loss": 0.724, "step": 152 }, { "epoch": 0.619746835443038, "grad_norm": 0.7219012084237144, "learning_rate": 3.992755896178383e-05, "loss": 0.7178, "step": 153 }, { "epoch": 0.6237974683544304, "grad_norm": 0.6166282168983201, "learning_rate": 3.992265223630981e-05, "loss": 0.7128, "step": 154 }, { "epoch": 0.6278481012658228, "grad_norm": 0.7282680572675326, "learning_rate": 3.991758505653355e-05, "loss": 0.7232, "step": 155 }, { "epoch": 0.6318987341772152, "grad_norm": 0.672271584817375, "learning_rate": 3.991235746326543e-05, "loss": 0.7547, "step": 156 }, { "epoch": 0.6359493670886076, "grad_norm": 0.7218858535540704, "learning_rate": 3.9906969498607745e-05, "loss": 0.7235, "step": 157 }, { "epoch": 0.64, "grad_norm": 0.6797233288410177, "learning_rate": 3.990142120595444e-05, "loss": 0.7345, "step": 158 }, { "epoch": 0.6440506329113924, "grad_norm": 0.8435194648503243, "learning_rate": 3.98957126299907e-05, "loss": 0.7068, "step": 159 }, { "epoch": 0.6481012658227848, "grad_norm": 0.896394549954892, "learning_rate": 3.9889843816692596e-05, "loss": 0.7496, "step": 160 }, { "epoch": 0.6521518987341772, "grad_norm": 0.6555297805489207, "learning_rate": 3.9883814813326766e-05, "loss": 0.7156, "step": 161 }, { "epoch": 0.6562025316455696, "grad_norm": 0.7000683415574447, "learning_rate": 3.9877625668449956e-05, "loss": 0.7392, "step": 162 }, { "epoch": 0.660253164556962, "grad_norm": 0.7759122842127731, "learning_rate": 3.98712764319087e-05, "loss": 0.7246, "step": 163 }, { "epoch": 0.6643037974683544, "grad_norm": 0.7005703745535381, "learning_rate": 3.9864767154838864e-05, "loss": 0.7281, "step": 164 }, { "epoch": 0.6683544303797468, "grad_norm": 0.6800033416982166, "learning_rate": 3.9858097889665277e-05, "loss": 0.6885, "step": 165 }, { "epoch": 0.6724050632911392, "grad_norm": 0.6430277441291997, "learning_rate": 3.985126869010129e-05, "loss": 0.7182, "step": 166 }, { "epoch": 0.6764556962025317, "grad_norm": 0.6592080471133435, "learning_rate": 3.984427961114833e-05, "loss": 0.7208, "step": 167 }, { "epoch": 0.6805063291139241, "grad_norm": 0.6579426358821475, "learning_rate": 3.9837130709095475e-05, "loss": 0.7194, "step": 168 }, { "epoch": 0.6845569620253165, "grad_norm": 0.6510122560753736, "learning_rate": 3.982982204151901e-05, "loss": 0.7071, "step": 169 }, { "epoch": 0.6886075949367089, "grad_norm": 0.7638335340457971, "learning_rate": 3.982235366728193e-05, "loss": 0.7093, "step": 170 }, { "epoch": 0.6926582278481013, "grad_norm": 0.6889051910655011, "learning_rate": 3.9814725646533505e-05, "loss": 0.7233, "step": 171 }, { "epoch": 0.6967088607594937, "grad_norm": 0.9483118441629994, "learning_rate": 3.9806938040708746e-05, "loss": 0.7192, "step": 172 }, { "epoch": 0.7007594936708861, "grad_norm": 0.7119454445752753, "learning_rate": 3.9798990912527976e-05, "loss": 0.7307, "step": 173 }, { "epoch": 0.7048101265822785, "grad_norm": 0.7809596618430877, "learning_rate": 3.979088432599627e-05, "loss": 0.7358, "step": 174 }, { "epoch": 0.7088607594936709, "grad_norm": 0.8081628589962211, "learning_rate": 3.9782618346402964e-05, "loss": 0.7317, "step": 175 }, { "epoch": 0.7129113924050633, "grad_norm": 0.8172745587485889, "learning_rate": 3.977419304032111e-05, "loss": 0.7179, "step": 176 }, { "epoch": 0.7169620253164557, "grad_norm": 1.0640681247537516, "learning_rate": 3.976560847560697e-05, "loss": 0.7366, "step": 177 }, { "epoch": 0.7210126582278481, "grad_norm": 0.6520693737031721, "learning_rate": 3.9756864721399456e-05, "loss": 0.7292, "step": 178 }, { "epoch": 0.7250632911392405, "grad_norm": 0.7977186478294545, "learning_rate": 3.974796184811956e-05, "loss": 0.6932, "step": 179 }, { "epoch": 0.7291139240506329, "grad_norm": 0.7220695542766716, "learning_rate": 3.973889992746979e-05, "loss": 0.729, "step": 180 }, { "epoch": 0.7331645569620253, "grad_norm": 0.8171143090704082, "learning_rate": 3.972967903243361e-05, "loss": 0.6983, "step": 181 }, { "epoch": 0.7372151898734177, "grad_norm": 0.7334052635295845, "learning_rate": 3.972029923727486e-05, "loss": 0.6985, "step": 182 }, { "epoch": 0.7412658227848101, "grad_norm": 0.8247342762437694, "learning_rate": 3.971076061753709e-05, "loss": 0.7249, "step": 183 }, { "epoch": 0.7453164556962025, "grad_norm": 0.8505340470824432, "learning_rate": 3.9701063250043066e-05, "loss": 0.7254, "step": 184 }, { "epoch": 0.7493670886075949, "grad_norm": 0.7873953229582996, "learning_rate": 3.969120721289402e-05, "loss": 0.7249, "step": 185 }, { "epoch": 0.7534177215189873, "grad_norm": 0.8493778225260805, "learning_rate": 3.9681192585469146e-05, "loss": 0.7462, "step": 186 }, { "epoch": 0.7574683544303797, "grad_norm": 0.7506886127293471, "learning_rate": 3.9671019448424865e-05, "loss": 0.7101, "step": 187 }, { "epoch": 0.7615189873417721, "grad_norm": 0.6569646859593051, "learning_rate": 3.966068788369422e-05, "loss": 0.7178, "step": 188 }, { "epoch": 0.7655696202531646, "grad_norm": 0.8377534989764616, "learning_rate": 3.965019797448622e-05, "loss": 0.734, "step": 189 }, { "epoch": 0.769620253164557, "grad_norm": 0.6212131298902227, "learning_rate": 3.963954980528515e-05, "loss": 0.7249, "step": 190 }, { "epoch": 0.7736708860759494, "grad_norm": 0.8535049047986489, "learning_rate": 3.9628743461849905e-05, "loss": 0.7227, "step": 191 }, { "epoch": 0.7777215189873418, "grad_norm": 0.7234613087563891, "learning_rate": 3.961777903121329e-05, "loss": 0.7122, "step": 192 }, { "epoch": 0.7817721518987342, "grad_norm": 0.8931294028221949, "learning_rate": 3.960665660168131e-05, "loss": 0.7291, "step": 193 }, { "epoch": 0.7858227848101266, "grad_norm": 0.7243428320932357, "learning_rate": 3.9595376262832485e-05, "loss": 0.6869, "step": 194 }, { "epoch": 0.789873417721519, "grad_norm": 0.7467868619111522, "learning_rate": 3.9583938105517127e-05, "loss": 0.73, "step": 195 }, { "epoch": 0.7939240506329114, "grad_norm": 0.8537131295614125, "learning_rate": 3.957234222185657e-05, "loss": 0.7287, "step": 196 }, { "epoch": 0.7979746835443038, "grad_norm": 0.689469611279874, "learning_rate": 3.9560588705242474e-05, "loss": 0.7417, "step": 197 }, { "epoch": 0.8020253164556962, "grad_norm": 0.7682376193484047, "learning_rate": 3.954867765033605e-05, "loss": 0.7269, "step": 198 }, { "epoch": 0.8060759493670886, "grad_norm": 0.7173585690825061, "learning_rate": 3.953660915306728e-05, "loss": 0.7084, "step": 199 }, { "epoch": 0.810126582278481, "grad_norm": 0.6244696866612162, "learning_rate": 3.952438331063419e-05, "loss": 0.7134, "step": 200 }, { "epoch": 0.8141772151898734, "grad_norm": 0.765107841300598, "learning_rate": 3.951200022150205e-05, "loss": 0.7282, "step": 201 }, { "epoch": 0.8182278481012658, "grad_norm": 0.7233665257228408, "learning_rate": 3.949945998540253e-05, "loss": 0.7245, "step": 202 }, { "epoch": 0.8222784810126582, "grad_norm": 0.6587929275266171, "learning_rate": 3.9486762703332993e-05, "loss": 0.7258, "step": 203 }, { "epoch": 0.8263291139240506, "grad_norm": 0.7241507418521594, "learning_rate": 3.947390847755559e-05, "loss": 0.7053, "step": 204 }, { "epoch": 0.830379746835443, "grad_norm": 0.6311551586513956, "learning_rate": 3.946089741159648e-05, "loss": 0.7451, "step": 205 }, { "epoch": 0.8344303797468354, "grad_norm": 0.7003662643046463, "learning_rate": 3.944772961024501e-05, "loss": 0.714, "step": 206 }, { "epoch": 0.8384810126582278, "grad_norm": 0.5862482318373851, "learning_rate": 3.943440517955285e-05, "loss": 0.7219, "step": 207 }, { "epoch": 0.8425316455696202, "grad_norm": 0.6631331141962418, "learning_rate": 3.9420924226833126e-05, "loss": 0.7267, "step": 208 }, { "epoch": 0.8465822784810126, "grad_norm": 0.6247303781550227, "learning_rate": 3.9407286860659566e-05, "loss": 0.748, "step": 209 }, { "epoch": 0.850632911392405, "grad_norm": 0.6552308412715417, "learning_rate": 3.9393493190865657e-05, "loss": 0.7061, "step": 210 }, { "epoch": 0.8546835443037974, "grad_norm": 0.6815336134959604, "learning_rate": 3.937954332854371e-05, "loss": 0.721, "step": 211 }, { "epoch": 0.8587341772151899, "grad_norm": 0.7070338060160224, "learning_rate": 3.9365437386044016e-05, "loss": 0.717, "step": 212 }, { "epoch": 0.8627848101265823, "grad_norm": 0.5835978346383717, "learning_rate": 3.935117547697387e-05, "loss": 0.7325, "step": 213 }, { "epoch": 0.8668354430379747, "grad_norm": 0.6619164536833728, "learning_rate": 3.933675771619675e-05, "loss": 0.7046, "step": 214 }, { "epoch": 0.8708860759493671, "grad_norm": 0.6501848353376092, "learning_rate": 3.932218421983131e-05, "loss": 0.7014, "step": 215 }, { "epoch": 0.8749367088607595, "grad_norm": 0.6756397438052408, "learning_rate": 3.9307455105250484e-05, "loss": 0.7047, "step": 216 }, { "epoch": 0.8789873417721519, "grad_norm": 0.6108369091854617, "learning_rate": 3.929257049108054e-05, "loss": 0.7331, "step": 217 }, { "epoch": 0.8830379746835443, "grad_norm": 0.6270566491442032, "learning_rate": 3.927753049720011e-05, "loss": 0.7364, "step": 218 }, { "epoch": 0.8870886075949367, "grad_norm": 0.5716569280317367, "learning_rate": 3.9262335244739234e-05, "loss": 0.6904, "step": 219 }, { "epoch": 0.8911392405063291, "grad_norm": 0.6438571453702734, "learning_rate": 3.92469848560784e-05, "loss": 0.6893, "step": 220 }, { "epoch": 0.8951898734177215, "grad_norm": 0.5829640599116803, "learning_rate": 3.923147945484751e-05, "loss": 0.691, "step": 221 }, { "epoch": 0.8992405063291139, "grad_norm": 0.5370571350361716, "learning_rate": 3.9215819165924956e-05, "loss": 0.6923, "step": 222 }, { "epoch": 0.9032911392405063, "grad_norm": 0.712167980942259, "learning_rate": 3.920000411543654e-05, "loss": 0.7331, "step": 223 }, { "epoch": 0.9073417721518987, "grad_norm": 0.6487960843227336, "learning_rate": 3.9184034430754495e-05, "loss": 0.7253, "step": 224 }, { "epoch": 0.9113924050632911, "grad_norm": 0.6732358040567376, "learning_rate": 3.916791024049648e-05, "loss": 0.7048, "step": 225 }, { "epoch": 0.9154430379746835, "grad_norm": 0.5834015164467481, "learning_rate": 3.91516316745245e-05, "loss": 0.7225, "step": 226 }, { "epoch": 0.9194936708860759, "grad_norm": 0.6387531535874168, "learning_rate": 3.913519886394389e-05, "loss": 0.6916, "step": 227 }, { "epoch": 0.9235443037974683, "grad_norm": 0.6217177578783734, "learning_rate": 3.911861194110225e-05, "loss": 0.6929, "step": 228 }, { "epoch": 0.9275949367088607, "grad_norm": 0.6010704745739301, "learning_rate": 3.910187103958837e-05, "loss": 0.7047, "step": 229 }, { "epoch": 0.9316455696202531, "grad_norm": 0.6420132768139387, "learning_rate": 3.908497629423117e-05, "loss": 0.7046, "step": 230 }, { "epoch": 0.9356962025316455, "grad_norm": 0.5778548689576104, "learning_rate": 3.9067927841098614e-05, "loss": 0.7262, "step": 231 }, { "epoch": 0.9397468354430379, "grad_norm": 0.649348164948976, "learning_rate": 3.9050725817496594e-05, "loss": 0.6897, "step": 232 }, { "epoch": 0.9437974683544303, "grad_norm": 0.5789423869989285, "learning_rate": 3.9033370361967844e-05, "loss": 0.6989, "step": 233 }, { "epoch": 0.9478481012658228, "grad_norm": 0.6996342225389438, "learning_rate": 3.901586161429081e-05, "loss": 0.6868, "step": 234 }, { "epoch": 0.9518987341772152, "grad_norm": 0.5505417665849154, "learning_rate": 3.8998199715478545e-05, "loss": 0.6918, "step": 235 }, { "epoch": 0.9559493670886076, "grad_norm": 0.6814590938486706, "learning_rate": 3.8980384807777564e-05, "loss": 0.7275, "step": 236 }, { "epoch": 0.96, "grad_norm": 0.6029053661082889, "learning_rate": 3.896241703466667e-05, "loss": 0.7078, "step": 237 }, { "epoch": 0.9640506329113924, "grad_norm": 0.6434438372333053, "learning_rate": 3.894429654085585e-05, "loss": 0.6932, "step": 238 }, { "epoch": 0.9681012658227848, "grad_norm": 0.5538439381048395, "learning_rate": 3.892602347228505e-05, "loss": 0.6785, "step": 239 }, { "epoch": 0.9721518987341772, "grad_norm": 0.6165501303859456, "learning_rate": 3.890759797612307e-05, "loss": 0.6996, "step": 240 }, { "epoch": 0.9762025316455696, "grad_norm": 0.5627073250442403, "learning_rate": 3.888902020076632e-05, "loss": 0.6804, "step": 241 }, { "epoch": 0.980253164556962, "grad_norm": 0.6259995784467591, "learning_rate": 3.887029029583764e-05, "loss": 0.6914, "step": 242 }, { "epoch": 0.9843037974683544, "grad_norm": 0.568897337649215, "learning_rate": 3.8851408412185125e-05, "loss": 0.6819, "step": 243 }, { "epoch": 0.9883544303797468, "grad_norm": 0.6158147387613341, "learning_rate": 3.8832374701880855e-05, "loss": 0.7073, "step": 244 }, { "epoch": 0.9924050632911392, "grad_norm": 0.6507340495640718, "learning_rate": 3.881318931821972e-05, "loss": 0.71, "step": 245 }, { "epoch": 0.9964556962025316, "grad_norm": 0.5775535354169804, "learning_rate": 3.879385241571817e-05, "loss": 0.6897, "step": 246 }, { "epoch": 1.000506329113924, "grad_norm": 0.555305113483285, "learning_rate": 3.8774364150112955e-05, "loss": 0.675, "step": 247 }, { "epoch": 1.0045569620253165, "grad_norm": 0.7832155752383657, "learning_rate": 3.8754724678359884e-05, "loss": 0.5531, "step": 248 }, { "epoch": 1.0086075949367088, "grad_norm": 0.6811510904544219, "learning_rate": 3.873493415863256e-05, "loss": 0.5585, "step": 249 }, { "epoch": 1.0126582278481013, "grad_norm": 0.6973284031354905, "learning_rate": 3.871499275032111e-05, "loss": 0.5513, "step": 250 }, { "epoch": 1.0167088607594936, "grad_norm": 0.7406016851911261, "learning_rate": 3.869490061403091e-05, "loss": 0.5228, "step": 251 }, { "epoch": 1.0207594936708861, "grad_norm": 0.6732473341260875, "learning_rate": 3.867465791158124e-05, "loss": 0.5598, "step": 252 }, { "epoch": 1.0248101265822784, "grad_norm": 0.8097086689185362, "learning_rate": 3.865426480600407e-05, "loss": 0.5484, "step": 253 }, { "epoch": 1.028860759493671, "grad_norm": 0.6352783772342526, "learning_rate": 3.863372146154264e-05, "loss": 0.5161, "step": 254 }, { "epoch": 1.0329113924050632, "grad_norm": 0.6370690589327438, "learning_rate": 3.861302804365024e-05, "loss": 0.5395, "step": 255 }, { "epoch": 1.0369620253164558, "grad_norm": 0.6822941471343973, "learning_rate": 3.85921847189888e-05, "loss": 0.5436, "step": 256 }, { "epoch": 1.041012658227848, "grad_norm": 0.6629129838397727, "learning_rate": 3.85711916554276e-05, "loss": 0.5308, "step": 257 }, { "epoch": 1.0450632911392406, "grad_norm": 0.6878466508638529, "learning_rate": 3.85500490220419e-05, "loss": 0.5287, "step": 258 }, { "epoch": 1.0491139240506329, "grad_norm": 0.6770071484184564, "learning_rate": 3.852875698911154e-05, "loss": 0.5407, "step": 259 }, { "epoch": 1.0531645569620254, "grad_norm": 0.7670291474296155, "learning_rate": 3.850731572811963e-05, "loss": 0.5513, "step": 260 }, { "epoch": 1.0572151898734177, "grad_norm": 0.7168831686802901, "learning_rate": 3.848572541175116e-05, "loss": 0.536, "step": 261 }, { "epoch": 1.0612658227848102, "grad_norm": 0.7616839089484781, "learning_rate": 3.846398621389154e-05, "loss": 0.5257, "step": 262 }, { "epoch": 1.0653164556962025, "grad_norm": 0.6756529902306905, "learning_rate": 3.84420983096253e-05, "loss": 0.5403, "step": 263 }, { "epoch": 1.069367088607595, "grad_norm": 0.7087566196774108, "learning_rate": 3.8420061875234606e-05, "loss": 0.549, "step": 264 }, { "epoch": 1.0734177215189873, "grad_norm": 0.6416978602250606, "learning_rate": 3.839787708819787e-05, "loss": 0.5172, "step": 265 }, { "epoch": 1.0774683544303798, "grad_norm": 0.8599618335217114, "learning_rate": 3.8375544127188325e-05, "loss": 0.5464, "step": 266 }, { "epoch": 1.081518987341772, "grad_norm": 0.7264958226214121, "learning_rate": 3.8353063172072564e-05, "loss": 0.5421, "step": 267 }, { "epoch": 1.0855696202531646, "grad_norm": 0.7272737015214346, "learning_rate": 3.8330434403909105e-05, "loss": 0.561, "step": 268 }, { "epoch": 1.089620253164557, "grad_norm": 0.6890926721191458, "learning_rate": 3.8307658004946934e-05, "loss": 0.519, "step": 269 }, { "epoch": 1.0936708860759494, "grad_norm": 0.8876234063086479, "learning_rate": 3.8284734158624046e-05, "loss": 0.5431, "step": 270 }, { "epoch": 1.0977215189873417, "grad_norm": 0.7018940835654477, "learning_rate": 3.826166304956594e-05, "loss": 0.5344, "step": 271 }, { "epoch": 1.1017721518987342, "grad_norm": 0.6711944688351932, "learning_rate": 3.8238444863584164e-05, "loss": 0.5485, "step": 272 }, { "epoch": 1.1058227848101265, "grad_norm": 0.6762816986658614, "learning_rate": 3.821507978767479e-05, "loss": 0.5218, "step": 273 }, { "epoch": 1.109873417721519, "grad_norm": 0.6325866584332683, "learning_rate": 3.819156801001693e-05, "loss": 0.5674, "step": 274 }, { "epoch": 1.1139240506329113, "grad_norm": 0.6906013962546015, "learning_rate": 3.816790971997121e-05, "loss": 0.5317, "step": 275 }, { "epoch": 1.1179746835443038, "grad_norm": 0.6941861074961534, "learning_rate": 3.8144105108078246e-05, "loss": 0.5273, "step": 276 }, { "epoch": 1.1220253164556961, "grad_norm": 0.7638521232741007, "learning_rate": 3.81201543660571e-05, "loss": 0.5363, "step": 277 }, { "epoch": 1.1260759493670887, "grad_norm": 0.7043794763574502, "learning_rate": 3.809605768680377e-05, "loss": 0.5669, "step": 278 }, { "epoch": 1.130126582278481, "grad_norm": 0.6983133080094177, "learning_rate": 3.807181526438958e-05, "loss": 0.5657, "step": 279 }, { "epoch": 1.1341772151898735, "grad_norm": 0.6938416267987038, "learning_rate": 3.8047427294059697e-05, "loss": 0.5288, "step": 280 }, { "epoch": 1.1382278481012658, "grad_norm": 0.6276078536939335, "learning_rate": 3.802289397223145e-05, "loss": 0.5299, "step": 281 }, { "epoch": 1.1422784810126583, "grad_norm": 0.653806890939892, "learning_rate": 3.7998215496492854e-05, "loss": 0.5466, "step": 282 }, { "epoch": 1.1463291139240506, "grad_norm": 0.6225192765588502, "learning_rate": 3.797339206560096e-05, "loss": 0.5446, "step": 283 }, { "epoch": 1.150379746835443, "grad_norm": 0.6292857483329835, "learning_rate": 3.794842387948027e-05, "loss": 0.5423, "step": 284 }, { "epoch": 1.1544303797468354, "grad_norm": 0.7918888593858274, "learning_rate": 3.7923311139221114e-05, "loss": 0.55, "step": 285 }, { "epoch": 1.158481012658228, "grad_norm": 0.6024544333394691, "learning_rate": 3.7898054047078054e-05, "loss": 0.5424, "step": 286 }, { "epoch": 1.1625316455696202, "grad_norm": 0.8256798694233449, "learning_rate": 3.787265280646825e-05, "loss": 0.5635, "step": 287 }, { "epoch": 1.1665822784810127, "grad_norm": 0.6020414596620741, "learning_rate": 3.7847107621969786e-05, "loss": 0.5546, "step": 288 }, { "epoch": 1.170632911392405, "grad_norm": 0.7161057503615841, "learning_rate": 3.7821418699320064e-05, "loss": 0.5707, "step": 289 }, { "epoch": 1.1746835443037975, "grad_norm": 0.6337257658816712, "learning_rate": 3.7795586245414145e-05, "loss": 0.5642, "step": 290 }, { "epoch": 1.1787341772151898, "grad_norm": 0.6918177316394645, "learning_rate": 3.776961046830306e-05, "loss": 0.5421, "step": 291 }, { "epoch": 1.1827848101265823, "grad_norm": 0.7816925278229739, "learning_rate": 3.774349157719215e-05, "loss": 0.5575, "step": 292 }, { "epoch": 1.1868354430379746, "grad_norm": 0.5999441707731732, "learning_rate": 3.7717229782439365e-05, "loss": 0.5486, "step": 293 }, { "epoch": 1.1908860759493671, "grad_norm": 0.7288677233201711, "learning_rate": 3.769082529555359e-05, "loss": 0.5677, "step": 294 }, { "epoch": 1.1949367088607594, "grad_norm": 0.5921179573138968, "learning_rate": 3.766427832919294e-05, "loss": 0.5349, "step": 295 }, { "epoch": 1.198987341772152, "grad_norm": 0.6943044959411836, "learning_rate": 3.7637589097163024e-05, "loss": 0.5395, "step": 296 }, { "epoch": 1.2030379746835442, "grad_norm": 0.6449313273343611, "learning_rate": 3.761075781441526e-05, "loss": 0.5834, "step": 297 }, { "epoch": 1.2070886075949367, "grad_norm": 0.7163706158490212, "learning_rate": 3.75837846970451e-05, "loss": 0.5145, "step": 298 }, { "epoch": 1.211139240506329, "grad_norm": 0.7722031013245806, "learning_rate": 3.755666996229032e-05, "loss": 0.5327, "step": 299 }, { "epoch": 1.2151898734177216, "grad_norm": 0.6782589998458589, "learning_rate": 3.752941382852927e-05, "loss": 0.5666, "step": 300 }, { "epoch": 1.2192405063291138, "grad_norm": 0.8791585857667596, "learning_rate": 3.7502016515279115e-05, "loss": 0.5593, "step": 301 }, { "epoch": 1.2232911392405064, "grad_norm": 0.6447965250021749, "learning_rate": 3.7474478243194043e-05, "loss": 0.5487, "step": 302 }, { "epoch": 1.2273417721518987, "grad_norm": 0.9764642643356894, "learning_rate": 3.744679923406351e-05, "loss": 0.537, "step": 303 }, { "epoch": 1.2313924050632912, "grad_norm": 0.6158663653740211, "learning_rate": 3.741897971081043e-05, "loss": 0.5499, "step": 304 }, { "epoch": 1.2354430379746835, "grad_norm": 1.0291041422153402, "learning_rate": 3.739101989748946e-05, "loss": 0.5567, "step": 305 }, { "epoch": 1.239493670886076, "grad_norm": 0.6725248079727824, "learning_rate": 3.7362920019285066e-05, "loss": 0.5585, "step": 306 }, { "epoch": 1.2435443037974683, "grad_norm": 0.6561616899446185, "learning_rate": 3.73346803025098e-05, "loss": 0.5071, "step": 307 }, { "epoch": 1.2475949367088608, "grad_norm": 0.6707671433855723, "learning_rate": 3.730630097460247e-05, "loss": 0.5504, "step": 308 }, { "epoch": 1.251645569620253, "grad_norm": 0.5886519935728523, "learning_rate": 3.727778226412628e-05, "loss": 0.5444, "step": 309 }, { "epoch": 1.2556962025316456, "grad_norm": 0.6377584670262159, "learning_rate": 3.7249124400767006e-05, "loss": 0.5607, "step": 310 }, { "epoch": 1.259746835443038, "grad_norm": 0.6027858574809996, "learning_rate": 3.722032761533114e-05, "loss": 0.5075, "step": 311 }, { "epoch": 1.2637974683544304, "grad_norm": 0.6602785865160528, "learning_rate": 3.719139213974403e-05, "loss": 0.5435, "step": 312 }, { "epoch": 1.2678481012658227, "grad_norm": 0.6423138532168488, "learning_rate": 3.7162318207048006e-05, "loss": 0.5431, "step": 313 }, { "epoch": 1.2718987341772152, "grad_norm": 0.6454228472260345, "learning_rate": 3.713310605140055e-05, "loss": 0.5574, "step": 314 }, { "epoch": 1.2759493670886077, "grad_norm": 0.597127159971195, "learning_rate": 3.710375590807233e-05, "loss": 0.53, "step": 315 }, { "epoch": 1.28, "grad_norm": 0.6813246304516908, "learning_rate": 3.7074268013445365e-05, "loss": 0.5547, "step": 316 }, { "epoch": 1.2840506329113923, "grad_norm": 0.6853255777766764, "learning_rate": 3.7044642605011114e-05, "loss": 0.5615, "step": 317 }, { "epoch": 1.2881012658227848, "grad_norm": 0.6991019479390482, "learning_rate": 3.701487992136854e-05, "loss": 0.5442, "step": 318 }, { "epoch": 1.2921518987341774, "grad_norm": 0.6292026011905707, "learning_rate": 3.69849802022222e-05, "loss": 0.5477, "step": 319 }, { "epoch": 1.2962025316455696, "grad_norm": 0.597271541019834, "learning_rate": 3.6954943688380334e-05, "loss": 0.5338, "step": 320 }, { "epoch": 1.300253164556962, "grad_norm": 0.7449301650094223, "learning_rate": 3.692477062175289e-05, "loss": 0.5471, "step": 321 }, { "epoch": 1.3043037974683545, "grad_norm": 0.5833030287439732, "learning_rate": 3.689446124534958e-05, "loss": 0.5642, "step": 322 }, { "epoch": 1.308354430379747, "grad_norm": 0.6703022567444046, "learning_rate": 3.686401580327799e-05, "loss": 0.5337, "step": 323 }, { "epoch": 1.3124050632911393, "grad_norm": 0.6130602461978475, "learning_rate": 3.683343454074149e-05, "loss": 0.53, "step": 324 }, { "epoch": 1.3164556962025316, "grad_norm": 0.7437594084878721, "learning_rate": 3.6802717704037386e-05, "loss": 0.5425, "step": 325 }, { "epoch": 1.320506329113924, "grad_norm": 0.6771440243401585, "learning_rate": 3.6771865540554855e-05, "loss": 0.5408, "step": 326 }, { "epoch": 1.3245569620253166, "grad_norm": 0.6359729266484467, "learning_rate": 3.674087829877297e-05, "loss": 0.5338, "step": 327 }, { "epoch": 1.3286075949367089, "grad_norm": 0.6575182393787502, "learning_rate": 3.6709756228258735e-05, "loss": 0.5649, "step": 328 }, { "epoch": 1.3326582278481012, "grad_norm": 0.7405123141270721, "learning_rate": 3.667849957966501e-05, "loss": 0.5408, "step": 329 }, { "epoch": 1.3367088607594937, "grad_norm": 0.6710619450021389, "learning_rate": 3.6647108604728546e-05, "loss": 0.5235, "step": 330 }, { "epoch": 1.3407594936708862, "grad_norm": 0.6373488951581933, "learning_rate": 3.661558355626795e-05, "loss": 0.5495, "step": 331 }, { "epoch": 1.3448101265822785, "grad_norm": 0.8230975174818288, "learning_rate": 3.658392468818163e-05, "loss": 0.5349, "step": 332 }, { "epoch": 1.3488607594936708, "grad_norm": 0.6322423777898264, "learning_rate": 3.655213225544574e-05, "loss": 0.5513, "step": 333 }, { "epoch": 1.3529113924050633, "grad_norm": 0.6777401529937817, "learning_rate": 3.652020651411218e-05, "loss": 0.5371, "step": 334 }, { "epoch": 1.3569620253164558, "grad_norm": 0.694014846431399, "learning_rate": 3.6488147721306474e-05, "loss": 0.5475, "step": 335 }, { "epoch": 1.3610126582278481, "grad_norm": 0.7614535474244609, "learning_rate": 3.645595613522574e-05, "loss": 0.5608, "step": 336 }, { "epoch": 1.3650632911392404, "grad_norm": 0.6276052214807273, "learning_rate": 3.642363201513657e-05, "loss": 0.5318, "step": 337 }, { "epoch": 1.369113924050633, "grad_norm": 0.7431267181463734, "learning_rate": 3.6391175621373006e-05, "loss": 0.5553, "step": 338 }, { "epoch": 1.3731645569620254, "grad_norm": 0.5868611983250923, "learning_rate": 3.6358587215334355e-05, "loss": 0.5294, "step": 339 }, { "epoch": 1.3772151898734177, "grad_norm": 0.8018527774251623, "learning_rate": 3.632586705948318e-05, "loss": 0.5145, "step": 340 }, { "epoch": 1.38126582278481, "grad_norm": 0.6084385422615354, "learning_rate": 3.629301541734311e-05, "loss": 0.5381, "step": 341 }, { "epoch": 1.3853164556962025, "grad_norm": 0.614250297780794, "learning_rate": 3.626003255349676e-05, "loss": 0.5749, "step": 342 }, { "epoch": 1.389367088607595, "grad_norm": 0.6771057713455705, "learning_rate": 3.622691873358357e-05, "loss": 0.5628, "step": 343 }, { "epoch": 1.3934177215189874, "grad_norm": 0.5704143665202606, "learning_rate": 3.61936742242977e-05, "loss": 0.5733, "step": 344 }, { "epoch": 1.3974683544303796, "grad_norm": 0.5593519923822478, "learning_rate": 3.6160299293385864e-05, "loss": 0.5511, "step": 345 }, { "epoch": 1.4015189873417722, "grad_norm": 0.6100787280146471, "learning_rate": 3.612679420964516e-05, "loss": 0.5713, "step": 346 }, { "epoch": 1.4055696202531647, "grad_norm": 0.6312427884600266, "learning_rate": 3.609315924292092e-05, "loss": 0.5529, "step": 347 }, { "epoch": 1.409620253164557, "grad_norm": 0.5732096315407855, "learning_rate": 3.6059394664104554e-05, "loss": 0.5694, "step": 348 }, { "epoch": 1.4136708860759493, "grad_norm": 0.6544501239860531, "learning_rate": 3.602550074513133e-05, "loss": 0.5189, "step": 349 }, { "epoch": 1.4177215189873418, "grad_norm": 0.5835598748848927, "learning_rate": 3.599147775897822e-05, "loss": 0.5682, "step": 350 }, { "epoch": 1.4217721518987343, "grad_norm": 0.7438512741780238, "learning_rate": 3.595732597966167e-05, "loss": 0.535, "step": 351 }, { "epoch": 1.4258227848101266, "grad_norm": 0.5797162120272035, "learning_rate": 3.592304568223542e-05, "loss": 0.5649, "step": 352 }, { "epoch": 1.4298734177215189, "grad_norm": 0.6126285219435557, "learning_rate": 3.588863714278826e-05, "loss": 0.5383, "step": 353 }, { "epoch": 1.4339240506329114, "grad_norm": 0.574951270507805, "learning_rate": 3.585410063844186e-05, "loss": 0.5387, "step": 354 }, { "epoch": 1.437974683544304, "grad_norm": 0.6385479758170858, "learning_rate": 3.581943644734846e-05, "loss": 0.5401, "step": 355 }, { "epoch": 1.4420253164556962, "grad_norm": 0.5713406257357291, "learning_rate": 3.578464484868869e-05, "loss": 0.5299, "step": 356 }, { "epoch": 1.4460759493670885, "grad_norm": 0.6381869707132825, "learning_rate": 3.5749726122669316e-05, "loss": 0.5681, "step": 357 }, { "epoch": 1.450126582278481, "grad_norm": 0.5948098543360847, "learning_rate": 3.5714680550520943e-05, "loss": 0.5314, "step": 358 }, { "epoch": 1.4541772151898735, "grad_norm": 0.5917825787121088, "learning_rate": 3.5679508414495794e-05, "loss": 0.5386, "step": 359 }, { "epoch": 1.4582278481012658, "grad_norm": 0.6977517610919686, "learning_rate": 3.564420999786543e-05, "loss": 0.5666, "step": 360 }, { "epoch": 1.4622784810126581, "grad_norm": 0.6295232183429044, "learning_rate": 3.560878558491842e-05, "loss": 0.5391, "step": 361 }, { "epoch": 1.4663291139240506, "grad_norm": 0.5778059164164233, "learning_rate": 3.5573235460958145e-05, "loss": 0.5586, "step": 362 }, { "epoch": 1.4703797468354431, "grad_norm": 0.6217794302345817, "learning_rate": 3.553755991230039e-05, "loss": 0.5515, "step": 363 }, { "epoch": 1.4744303797468354, "grad_norm": 0.5656167963078857, "learning_rate": 3.5501759226271144e-05, "loss": 0.5421, "step": 364 }, { "epoch": 1.4784810126582277, "grad_norm": 0.5679233469491899, "learning_rate": 3.546583369120419e-05, "loss": 0.5374, "step": 365 }, { "epoch": 1.4825316455696202, "grad_norm": 0.6250898460202119, "learning_rate": 3.5429783596438864e-05, "loss": 0.5445, "step": 366 }, { "epoch": 1.4865822784810128, "grad_norm": 0.5837777315362416, "learning_rate": 3.539360923231766e-05, "loss": 0.5421, "step": 367 }, { "epoch": 1.490632911392405, "grad_norm": 0.5687290099351461, "learning_rate": 3.535731089018394e-05, "loss": 0.5481, "step": 368 }, { "epoch": 1.4946835443037974, "grad_norm": 0.5469408821111096, "learning_rate": 3.532088886237956e-05, "loss": 0.524, "step": 369 }, { "epoch": 1.4987341772151899, "grad_norm": 0.5413978428193511, "learning_rate": 3.528434344224253e-05, "loss": 0.5289, "step": 370 }, { "epoch": 1.5027848101265824, "grad_norm": 0.5734068860912478, "learning_rate": 3.524767492410464e-05, "loss": 0.5543, "step": 371 }, { "epoch": 1.5068354430379747, "grad_norm": 0.5558717542012712, "learning_rate": 3.521088360328908e-05, "loss": 0.5395, "step": 372 }, { "epoch": 1.510886075949367, "grad_norm": 0.5483436070166579, "learning_rate": 3.517396977610811e-05, "loss": 0.5299, "step": 373 }, { "epoch": 1.5149367088607595, "grad_norm": 0.5689034014921425, "learning_rate": 3.5136933739860595e-05, "loss": 0.5473, "step": 374 }, { "epoch": 1.518987341772152, "grad_norm": 0.6048417094297025, "learning_rate": 3.509977579282971e-05, "loss": 0.5305, "step": 375 }, { "epoch": 1.5230379746835443, "grad_norm": 0.5711439584903703, "learning_rate": 3.5062496234280424e-05, "loss": 0.5276, "step": 376 }, { "epoch": 1.5270886075949366, "grad_norm": 0.5883785554170976, "learning_rate": 3.502509536445719e-05, "loss": 0.5891, "step": 377 }, { "epoch": 1.531139240506329, "grad_norm": 0.5666347220398514, "learning_rate": 3.498757348458147e-05, "loss": 0.5375, "step": 378 }, { "epoch": 1.5351898734177216, "grad_norm": 0.6477970874191944, "learning_rate": 3.4949930896849324e-05, "loss": 0.562, "step": 379 }, { "epoch": 1.539240506329114, "grad_norm": 0.5919257936870856, "learning_rate": 3.491216790442899e-05, "loss": 0.5593, "step": 380 }, { "epoch": 1.5432911392405062, "grad_norm": 0.5989293805109824, "learning_rate": 3.487428481145839e-05, "loss": 0.5433, "step": 381 }, { "epoch": 1.5473417721518987, "grad_norm": 0.5893483491133682, "learning_rate": 3.483628192304278e-05, "loss": 0.5524, "step": 382 }, { "epoch": 1.5513924050632912, "grad_norm": 0.6187216887577751, "learning_rate": 3.479815954525219e-05, "loss": 0.5603, "step": 383 }, { "epoch": 1.5554430379746835, "grad_norm": 0.5503208698889717, "learning_rate": 3.475991798511899e-05, "loss": 0.5478, "step": 384 }, { "epoch": 1.5594936708860758, "grad_norm": 0.5853053458407745, "learning_rate": 3.4721557550635464e-05, "loss": 0.5434, "step": 385 }, { "epoch": 1.5635443037974683, "grad_norm": 0.5299404305646072, "learning_rate": 3.468307855075128e-05, "loss": 0.5606, "step": 386 }, { "epoch": 1.5675949367088609, "grad_norm": 0.5459989566856989, "learning_rate": 3.4644481295371005e-05, "loss": 0.5477, "step": 387 }, { "epoch": 1.5716455696202531, "grad_norm": 0.5762547145586141, "learning_rate": 3.460576609535163e-05, "loss": 0.5382, "step": 388 }, { "epoch": 1.5756962025316454, "grad_norm": 0.6299258990636325, "learning_rate": 3.456693326250006e-05, "loss": 0.5364, "step": 389 }, { "epoch": 1.579746835443038, "grad_norm": 0.5743256043298994, "learning_rate": 3.452798310957058e-05, "loss": 0.5399, "step": 390 }, { "epoch": 1.5837974683544305, "grad_norm": 0.6149769384175793, "learning_rate": 3.4488915950262386e-05, "loss": 0.5096, "step": 391 }, { "epoch": 1.5878481012658228, "grad_norm": 0.5565654249067685, "learning_rate": 3.4449732099216985e-05, "loss": 0.5515, "step": 392 }, { "epoch": 1.591898734177215, "grad_norm": 0.6522989193821184, "learning_rate": 3.441043187201574e-05, "loss": 0.5605, "step": 393 }, { "epoch": 1.5959493670886076, "grad_norm": 0.5453511141415136, "learning_rate": 3.437101558517728e-05, "loss": 0.564, "step": 394 }, { "epoch": 1.6, "grad_norm": 0.625900625584594, "learning_rate": 3.433148355615496e-05, "loss": 0.539, "step": 395 }, { "epoch": 1.6040506329113924, "grad_norm": 0.590093238870863, "learning_rate": 3.4291836103334294e-05, "loss": 0.5618, "step": 396 }, { "epoch": 1.6081012658227847, "grad_norm": 0.5651930953767162, "learning_rate": 3.425207354603043e-05, "loss": 0.5538, "step": 397 }, { "epoch": 1.6121518987341772, "grad_norm": 0.626584862804343, "learning_rate": 3.421219620448553e-05, "loss": 0.5366, "step": 398 }, { "epoch": 1.6162025316455697, "grad_norm": 0.5611782897162598, "learning_rate": 3.417220439986623e-05, "loss": 0.5325, "step": 399 }, { "epoch": 1.620253164556962, "grad_norm": 0.6116608712796263, "learning_rate": 3.4132098454261024e-05, "loss": 0.5316, "step": 400 }, { "epoch": 1.6243037974683543, "grad_norm": 0.7202530341622096, "learning_rate": 3.4091878690677676e-05, "loss": 0.5617, "step": 401 }, { "epoch": 1.6283544303797468, "grad_norm": 0.5846951891400604, "learning_rate": 3.405154543304065e-05, "loss": 0.5551, "step": 402 }, { "epoch": 1.6324050632911393, "grad_norm": 0.616275445216595, "learning_rate": 3.401109900618843e-05, "loss": 0.5674, "step": 403 }, { "epoch": 1.6364556962025316, "grad_norm": 0.569216252960721, "learning_rate": 3.3970539735870996e-05, "loss": 0.5376, "step": 404 }, { "epoch": 1.640506329113924, "grad_norm": 0.5463091730573258, "learning_rate": 3.392986794874714e-05, "loss": 0.5484, "step": 405 }, { "epoch": 1.6445569620253164, "grad_norm": 0.5407897552293796, "learning_rate": 3.388908397238184e-05, "loss": 0.5413, "step": 406 }, { "epoch": 1.648607594936709, "grad_norm": 0.5768444166808991, "learning_rate": 3.384818813524362e-05, "loss": 0.5317, "step": 407 }, { "epoch": 1.6526582278481012, "grad_norm": 0.5355916897656308, "learning_rate": 3.380718076670195e-05, "loss": 0.5224, "step": 408 }, { "epoch": 1.6567088607594935, "grad_norm": 0.5761398245490607, "learning_rate": 3.376606219702454e-05, "loss": 0.5574, "step": 409 }, { "epoch": 1.660759493670886, "grad_norm": 0.5618503490143766, "learning_rate": 3.372483275737468e-05, "loss": 0.5492, "step": 410 }, { "epoch": 1.6648101265822786, "grad_norm": 0.564259781994206, "learning_rate": 3.368349277980861e-05, "loss": 0.5556, "step": 411 }, { "epoch": 1.6688607594936709, "grad_norm": 0.5121954216595368, "learning_rate": 3.3642042597272844e-05, "loss": 0.5531, "step": 412 }, { "epoch": 1.6729113924050631, "grad_norm": 0.6009422167713047, "learning_rate": 3.360048254360144e-05, "loss": 0.562, "step": 413 }, { "epoch": 1.6769620253164557, "grad_norm": 0.5141566867860878, "learning_rate": 3.355881295351336e-05, "loss": 0.5494, "step": 414 }, { "epoch": 1.6810126582278482, "grad_norm": 0.5258027836801278, "learning_rate": 3.351703416260975e-05, "loss": 0.5301, "step": 415 }, { "epoch": 1.6850632911392405, "grad_norm": 0.5647426124740895, "learning_rate": 3.347514650737126e-05, "loss": 0.5295, "step": 416 }, { "epoch": 1.6891139240506328, "grad_norm": 0.548321055145781, "learning_rate": 3.3433150325155295e-05, "loss": 0.5506, "step": 417 }, { "epoch": 1.6931645569620253, "grad_norm": 0.624772830323253, "learning_rate": 3.339104595419334e-05, "loss": 0.5558, "step": 418 }, { "epoch": 1.6972151898734178, "grad_norm": 0.5895990923936193, "learning_rate": 3.3348833733588204e-05, "loss": 0.5605, "step": 419 }, { "epoch": 1.70126582278481, "grad_norm": 0.5422687101802768, "learning_rate": 3.3306514003311305e-05, "loss": 0.542, "step": 420 }, { "epoch": 1.7053164556962024, "grad_norm": 0.6837996453758035, "learning_rate": 3.326408710419996e-05, "loss": 0.5359, "step": 421 }, { "epoch": 1.709367088607595, "grad_norm": 0.6244502654337716, "learning_rate": 3.322155337795454e-05, "loss": 0.5709, "step": 422 }, { "epoch": 1.7134177215189874, "grad_norm": 0.5916469897832282, "learning_rate": 3.317891316713587e-05, "loss": 0.5512, "step": 423 }, { "epoch": 1.7174683544303797, "grad_norm": 0.6530476414921728, "learning_rate": 3.313616681516231e-05, "loss": 0.5404, "step": 424 }, { "epoch": 1.721518987341772, "grad_norm": 0.5899068382882665, "learning_rate": 3.309331466630713e-05, "loss": 0.5498, "step": 425 }, { "epoch": 1.7255696202531645, "grad_norm": 0.6027642979675908, "learning_rate": 3.305035706569563e-05, "loss": 0.5676, "step": 426 }, { "epoch": 1.729620253164557, "grad_norm": 0.7000058813829594, "learning_rate": 3.3007294359302433e-05, "loss": 0.5304, "step": 427 }, { "epoch": 1.7336708860759493, "grad_norm": 0.5990096250144654, "learning_rate": 3.296412689394864e-05, "loss": 0.5342, "step": 428 }, { "epoch": 1.7377215189873416, "grad_norm": 0.6271305204797311, "learning_rate": 3.292085501729909e-05, "loss": 0.5454, "step": 429 }, { "epoch": 1.7417721518987341, "grad_norm": 0.6122558071012204, "learning_rate": 3.2877479077859534e-05, "loss": 0.5319, "step": 430 }, { "epoch": 1.7458227848101266, "grad_norm": 0.5651980478508644, "learning_rate": 3.283399942497381e-05, "loss": 0.5669, "step": 431 }, { "epoch": 1.749873417721519, "grad_norm": 0.6219870342340965, "learning_rate": 3.279041640882108e-05, "loss": 0.5419, "step": 432 }, { "epoch": 1.7539240506329112, "grad_norm": 0.5788354228324006, "learning_rate": 3.2746730380412964e-05, "loss": 0.5493, "step": 433 }, { "epoch": 1.7579746835443038, "grad_norm": 0.5780489953503358, "learning_rate": 3.2702941691590726e-05, "loss": 0.5551, "step": 434 }, { "epoch": 1.7620253164556963, "grad_norm": 0.5861864444264543, "learning_rate": 3.265905069502244e-05, "loss": 0.5576, "step": 435 }, { "epoch": 1.7660759493670886, "grad_norm": 0.6407670285331633, "learning_rate": 3.261505774420016e-05, "loss": 0.5632, "step": 436 }, { "epoch": 1.7701265822784809, "grad_norm": 0.5820712758649353, "learning_rate": 3.257096319343707e-05, "loss": 0.5429, "step": 437 }, { "epoch": 1.7741772151898734, "grad_norm": 0.5317301485325099, "learning_rate": 3.2526767397864614e-05, "loss": 0.5512, "step": 438 }, { "epoch": 1.7782278481012659, "grad_norm": 0.5968171531795912, "learning_rate": 3.248247071342966e-05, "loss": 0.5591, "step": 439 }, { "epoch": 1.7822784810126582, "grad_norm": 0.6382187818366395, "learning_rate": 3.243807349689161e-05, "loss": 0.5667, "step": 440 }, { "epoch": 1.7863291139240505, "grad_norm": 0.5992369132430182, "learning_rate": 3.2393576105819544e-05, "loss": 0.5456, "step": 441 }, { "epoch": 1.790379746835443, "grad_norm": 0.6375695531675323, "learning_rate": 3.2348978898589333e-05, "loss": 0.5476, "step": 442 }, { "epoch": 1.7944303797468355, "grad_norm": 0.5511838738428328, "learning_rate": 3.230428223438075e-05, "loss": 0.5521, "step": 443 }, { "epoch": 1.7984810126582278, "grad_norm": 0.5413312282533523, "learning_rate": 3.225948647317459e-05, "loss": 0.5231, "step": 444 }, { "epoch": 1.80253164556962, "grad_norm": 0.5292046844127042, "learning_rate": 3.2214591975749745e-05, "loss": 0.5497, "step": 445 }, { "epoch": 1.8065822784810126, "grad_norm": 0.5839883542815792, "learning_rate": 3.216959910368034e-05, "loss": 0.5369, "step": 446 }, { "epoch": 1.8106329113924051, "grad_norm": 0.5804113838792775, "learning_rate": 3.212450821933277e-05, "loss": 0.5722, "step": 447 }, { "epoch": 1.8146835443037974, "grad_norm": 0.5844481864652151, "learning_rate": 3.207931968586281e-05, "loss": 0.5559, "step": 448 }, { "epoch": 1.81873417721519, "grad_norm": 0.5169985282133785, "learning_rate": 3.203403386721272e-05, "loss": 0.5463, "step": 449 }, { "epoch": 1.8227848101265822, "grad_norm": 0.53115158699474, "learning_rate": 3.1988651128108245e-05, "loss": 0.5343, "step": 450 }, { "epoch": 1.8268354430379747, "grad_norm": 0.6207082495615589, "learning_rate": 3.194317183405573e-05, "loss": 0.5575, "step": 451 }, { "epoch": 1.8308860759493673, "grad_norm": 0.5563023715885324, "learning_rate": 3.189759635133914e-05, "loss": 0.5475, "step": 452 }, { "epoch": 1.8349367088607595, "grad_norm": 0.665079977296859, "learning_rate": 3.185192504701718e-05, "loss": 0.5498, "step": 453 }, { "epoch": 1.8389873417721518, "grad_norm": 0.525398527166491, "learning_rate": 3.1806158288920234e-05, "loss": 0.5707, "step": 454 }, { "epoch": 1.8430379746835444, "grad_norm": 0.5705595390759757, "learning_rate": 3.1760296445647477e-05, "loss": 0.5347, "step": 455 }, { "epoch": 1.8470886075949369, "grad_norm": 0.5199727621598886, "learning_rate": 3.1714339886563896e-05, "loss": 0.5491, "step": 456 }, { "epoch": 1.8511392405063292, "grad_norm": 0.5358592543546232, "learning_rate": 3.166828898179731e-05, "loss": 0.5293, "step": 457 }, { "epoch": 1.8551898734177215, "grad_norm": 0.5241867024502586, "learning_rate": 3.162214410223536e-05, "loss": 0.5641, "step": 458 }, { "epoch": 1.859240506329114, "grad_norm": 0.595101381832834, "learning_rate": 3.157590561952257e-05, "loss": 0.5547, "step": 459 }, { "epoch": 1.8632911392405065, "grad_norm": 0.532359268232095, "learning_rate": 3.152957390605732e-05, "loss": 0.5633, "step": 460 }, { "epoch": 1.8673417721518988, "grad_norm": 0.5346264366081717, "learning_rate": 3.148314933498886e-05, "loss": 0.5331, "step": 461 }, { "epoch": 1.871392405063291, "grad_norm": 0.5306973770082704, "learning_rate": 3.143663228021431e-05, "loss": 0.544, "step": 462 }, { "epoch": 1.8754430379746836, "grad_norm": 0.5047801642391576, "learning_rate": 3.1390023116375624e-05, "loss": 0.5477, "step": 463 }, { "epoch": 1.879493670886076, "grad_norm": 0.5778743771273076, "learning_rate": 3.134332221885661e-05, "loss": 0.5607, "step": 464 }, { "epoch": 1.8835443037974684, "grad_norm": 0.5167418645933533, "learning_rate": 3.129652996377987e-05, "loss": 0.5371, "step": 465 }, { "epoch": 1.8875949367088607, "grad_norm": 0.5490474099329337, "learning_rate": 3.12496467280038e-05, "loss": 0.581, "step": 466 }, { "epoch": 1.8916455696202532, "grad_norm": 0.5509188796038724, "learning_rate": 3.120267288911952e-05, "loss": 0.5688, "step": 467 }, { "epoch": 1.8956962025316457, "grad_norm": 0.5200580092547212, "learning_rate": 3.11556088254479e-05, "loss": 0.5554, "step": 468 }, { "epoch": 1.899746835443038, "grad_norm": 0.5159466552591311, "learning_rate": 3.11084549160364e-05, "loss": 0.5321, "step": 469 }, { "epoch": 1.9037974683544303, "grad_norm": 0.49893536732900257, "learning_rate": 3.106121154065615e-05, "loss": 0.5167, "step": 470 }, { "epoch": 1.9078481012658228, "grad_norm": 0.49624153596719944, "learning_rate": 3.1013879079798805e-05, "loss": 0.5223, "step": 471 }, { "epoch": 1.9118987341772153, "grad_norm": 0.5441347240862859, "learning_rate": 3.096645791467348e-05, "loss": 0.5512, "step": 472 }, { "epoch": 1.9159493670886076, "grad_norm": 0.5263082942775913, "learning_rate": 3.091894842720373e-05, "loss": 0.5498, "step": 473 }, { "epoch": 1.92, "grad_norm": 0.545663824602585, "learning_rate": 3.0871351000024425e-05, "loss": 0.5592, "step": 474 }, { "epoch": 1.9240506329113924, "grad_norm": 0.5468077834281793, "learning_rate": 3.0823666016478716e-05, "loss": 0.5487, "step": 475 }, { "epoch": 1.928101265822785, "grad_norm": 0.5241111484011857, "learning_rate": 3.0775893860614896e-05, "loss": 0.5369, "step": 476 }, { "epoch": 1.9321518987341773, "grad_norm": 0.5084336265163474, "learning_rate": 3.0728034917183336e-05, "loss": 0.5721, "step": 477 }, { "epoch": 1.9362025316455695, "grad_norm": 0.5215646698819957, "learning_rate": 3.06800895716334e-05, "loss": 0.5324, "step": 478 }, { "epoch": 1.940253164556962, "grad_norm": 0.5407604655652652, "learning_rate": 3.063205821011029e-05, "loss": 0.5509, "step": 479 }, { "epoch": 1.9443037974683546, "grad_norm": 0.5075339567084158, "learning_rate": 3.0583941219452016e-05, "loss": 0.5375, "step": 480 }, { "epoch": 1.9483544303797469, "grad_norm": 0.5000765318249653, "learning_rate": 3.053573898718618e-05, "loss": 0.5447, "step": 481 }, { "epoch": 1.9524050632911392, "grad_norm": 0.5299546108761943, "learning_rate": 3.0487451901526956e-05, "loss": 0.5421, "step": 482 }, { "epoch": 1.9564556962025317, "grad_norm": 0.5619491788250537, "learning_rate": 3.0439080351371875e-05, "loss": 0.5651, "step": 483 }, { "epoch": 1.9605063291139242, "grad_norm": 0.5548614739056885, "learning_rate": 3.0390624726298764e-05, "loss": 0.5539, "step": 484 }, { "epoch": 1.9645569620253165, "grad_norm": 0.5164705692904406, "learning_rate": 3.034208541656255e-05, "loss": 0.5341, "step": 485 }, { "epoch": 1.9686075949367088, "grad_norm": 0.5959012360252335, "learning_rate": 3.029346281309218e-05, "loss": 0.5515, "step": 486 }, { "epoch": 1.9726582278481013, "grad_norm": 0.5846940538413107, "learning_rate": 3.0244757307487415e-05, "loss": 0.5478, "step": 487 }, { "epoch": 1.9767088607594938, "grad_norm": 0.5588405305734488, "learning_rate": 3.019596929201569e-05, "loss": 0.5056, "step": 488 }, { "epoch": 1.980759493670886, "grad_norm": 0.6079139298742237, "learning_rate": 3.0147099159608985e-05, "loss": 0.5749, "step": 489 }, { "epoch": 1.9848101265822784, "grad_norm": 0.5784466850152714, "learning_rate": 3.0098147303860616e-05, "loss": 0.5398, "step": 490 }, { "epoch": 1.988860759493671, "grad_norm": 0.4906539120404494, "learning_rate": 3.0049114119022117e-05, "loss": 0.5437, "step": 491 }, { "epoch": 1.9929113924050634, "grad_norm": 0.5965767993114353, "learning_rate": 3.0000000000000004e-05, "loss": 0.5721, "step": 492 }, { "epoch": 1.9969620253164557, "grad_norm": 0.5416098170621777, "learning_rate": 2.995080534235264e-05, "loss": 0.5162, "step": 493 }, { "epoch": 2.001012658227848, "grad_norm": 0.6145807090395391, "learning_rate": 2.9901530542287044e-05, "loss": 0.5255, "step": 494 }, { "epoch": 2.0050632911392405, "grad_norm": 0.7371605449337364, "learning_rate": 2.9852175996655676e-05, "loss": 0.3898, "step": 495 }, { "epoch": 2.009113924050633, "grad_norm": 1.026159246066735, "learning_rate": 2.980274210295326e-05, "loss": 0.3483, "step": 496 }, { "epoch": 2.013164556962025, "grad_norm": 0.6693555352601105, "learning_rate": 2.9753229259313578e-05, "loss": 0.3561, "step": 497 }, { "epoch": 2.0172151898734176, "grad_norm": 0.6217154393558036, "learning_rate": 2.9703637864506274e-05, "loss": 0.3553, "step": 498 }, { "epoch": 2.02126582278481, "grad_norm": 0.608452201341684, "learning_rate": 2.965396831793362e-05, "loss": 0.3796, "step": 499 }, { "epoch": 2.0253164556962027, "grad_norm": 0.6101729636879298, "learning_rate": 2.9604221019627316e-05, "loss": 0.3589, "step": 500 }, { "epoch": 2.0293670886075947, "grad_norm": 0.5944875305902156, "learning_rate": 2.955439637024526e-05, "loss": 0.3503, "step": 501 }, { "epoch": 2.0334177215189873, "grad_norm": 0.599472136339116, "learning_rate": 2.9504494771068334e-05, "loss": 0.3529, "step": 502 }, { "epoch": 2.0374683544303798, "grad_norm": 0.589362686827065, "learning_rate": 2.9454516623997156e-05, "loss": 0.3754, "step": 503 }, { "epoch": 2.0415189873417723, "grad_norm": 0.5940248257501248, "learning_rate": 2.9404462331548847e-05, "loss": 0.3628, "step": 504 }, { "epoch": 2.0455696202531644, "grad_norm": 0.5485952200169573, "learning_rate": 2.93543322968538e-05, "loss": 0.3706, "step": 505 }, { "epoch": 2.049620253164557, "grad_norm": 0.5754660556385779, "learning_rate": 2.9304126923652428e-05, "loss": 0.3298, "step": 506 }, { "epoch": 2.0536708860759494, "grad_norm": 0.5705018400773723, "learning_rate": 2.9253846616291896e-05, "loss": 0.3482, "step": 507 }, { "epoch": 2.057721518987342, "grad_norm": 0.5295180530528039, "learning_rate": 2.9203491779722896e-05, "loss": 0.3325, "step": 508 }, { "epoch": 2.061772151898734, "grad_norm": 0.5417990585177334, "learning_rate": 2.9153062819496357e-05, "loss": 0.3566, "step": 509 }, { "epoch": 2.0658227848101265, "grad_norm": 0.5433946521278729, "learning_rate": 2.9102560141760178e-05, "loss": 0.3617, "step": 510 }, { "epoch": 2.069873417721519, "grad_norm": 0.503227830270464, "learning_rate": 2.9051984153256004e-05, "loss": 0.3429, "step": 511 }, { "epoch": 2.0739240506329115, "grad_norm": 0.5292428222923923, "learning_rate": 2.900133526131588e-05, "loss": 0.3298, "step": 512 }, { "epoch": 2.0779746835443036, "grad_norm": 0.5459415806912602, "learning_rate": 2.8950613873859025e-05, "loss": 0.3352, "step": 513 }, { "epoch": 2.082025316455696, "grad_norm": 0.514851581264407, "learning_rate": 2.8899820399388515e-05, "loss": 0.3388, "step": 514 }, { "epoch": 2.0860759493670886, "grad_norm": 0.5939972423133854, "learning_rate": 2.8848955246988012e-05, "loss": 0.3687, "step": 515 }, { "epoch": 2.090126582278481, "grad_norm": 0.536220621279482, "learning_rate": 2.879801882631847e-05, "loss": 0.3664, "step": 516 }, { "epoch": 2.094177215189873, "grad_norm": 0.543723576660602, "learning_rate": 2.8747011547614808e-05, "loss": 0.3569, "step": 517 }, { "epoch": 2.0982278481012657, "grad_norm": 0.5863882367951083, "learning_rate": 2.8695933821682635e-05, "loss": 0.3704, "step": 518 }, { "epoch": 2.1022784810126582, "grad_norm": 0.5149293778318187, "learning_rate": 2.864478605989494e-05, "loss": 0.3543, "step": 519 }, { "epoch": 2.1063291139240508, "grad_norm": 0.5684935243933996, "learning_rate": 2.8593568674188765e-05, "loss": 0.3724, "step": 520 }, { "epoch": 2.110379746835443, "grad_norm": 0.5616002026010688, "learning_rate": 2.8542282077061892e-05, "loss": 0.3676, "step": 521 }, { "epoch": 2.1144303797468353, "grad_norm": 0.5586172909254676, "learning_rate": 2.8490926681569523e-05, "loss": 0.3353, "step": 522 }, { "epoch": 2.118481012658228, "grad_norm": 0.5343014341470259, "learning_rate": 2.8439502901320956e-05, "loss": 0.3528, "step": 523 }, { "epoch": 2.1225316455696204, "grad_norm": 0.6027055947075765, "learning_rate": 2.8388011150476237e-05, "loss": 0.3442, "step": 524 }, { "epoch": 2.1265822784810124, "grad_norm": 0.5013086386130247, "learning_rate": 2.8336451843742866e-05, "loss": 0.3187, "step": 525 }, { "epoch": 2.130632911392405, "grad_norm": 0.5584812194243518, "learning_rate": 2.8284825396372387e-05, "loss": 0.3686, "step": 526 }, { "epoch": 2.1346835443037975, "grad_norm": 0.48993017270139627, "learning_rate": 2.8233132224157132e-05, "loss": 0.3529, "step": 527 }, { "epoch": 2.13873417721519, "grad_norm": 0.5951197483363406, "learning_rate": 2.8181372743426805e-05, "loss": 0.3386, "step": 528 }, { "epoch": 2.1427848101265825, "grad_norm": 0.46795598642198527, "learning_rate": 2.8129547371045128e-05, "loss": 0.3436, "step": 529 }, { "epoch": 2.1468354430379746, "grad_norm": 0.584671437859655, "learning_rate": 2.8077656524406534e-05, "loss": 0.3273, "step": 530 }, { "epoch": 2.150886075949367, "grad_norm": 0.5221509756708084, "learning_rate": 2.802570062143278e-05, "loss": 0.3635, "step": 531 }, { "epoch": 2.1549367088607596, "grad_norm": 0.6152300716616181, "learning_rate": 2.7973680080569555e-05, "loss": 0.3675, "step": 532 }, { "epoch": 2.1589873417721517, "grad_norm": 0.4835734081582775, "learning_rate": 2.792159532078314e-05, "loss": 0.3437, "step": 533 }, { "epoch": 2.163037974683544, "grad_norm": 0.5452635161870307, "learning_rate": 2.7869446761557033e-05, "loss": 0.3458, "step": 534 }, { "epoch": 2.1670886075949367, "grad_norm": 0.5280756869187745, "learning_rate": 2.781723482288857e-05, "loss": 0.3516, "step": 535 }, { "epoch": 2.1711392405063292, "grad_norm": 0.576957572565004, "learning_rate": 2.7764959925285517e-05, "loss": 0.3586, "step": 536 }, { "epoch": 2.1751898734177217, "grad_norm": 0.5752601943139669, "learning_rate": 2.771262248976272e-05, "loss": 0.3547, "step": 537 }, { "epoch": 2.179240506329114, "grad_norm": 0.5397658981979709, "learning_rate": 2.7660222937838677e-05, "loss": 0.3401, "step": 538 }, { "epoch": 2.1832911392405063, "grad_norm": 0.5107579558759825, "learning_rate": 2.7607761691532186e-05, "loss": 0.3634, "step": 539 }, { "epoch": 2.187341772151899, "grad_norm": 0.5157138646399128, "learning_rate": 2.7555239173358916e-05, "loss": 0.3383, "step": 540 }, { "epoch": 2.191392405063291, "grad_norm": 0.5349059034538083, "learning_rate": 2.7502655806328e-05, "loss": 0.3431, "step": 541 }, { "epoch": 2.1954430379746834, "grad_norm": 0.5424283696909682, "learning_rate": 2.7450012013938648e-05, "loss": 0.3547, "step": 542 }, { "epoch": 2.199493670886076, "grad_norm": 0.5330073081809307, "learning_rate": 2.739730822017673e-05, "loss": 0.351, "step": 543 }, { "epoch": 2.2035443037974685, "grad_norm": 0.5010691722686016, "learning_rate": 2.7344544849511355e-05, "loss": 0.3372, "step": 544 }, { "epoch": 2.207594936708861, "grad_norm": 0.5987251078346799, "learning_rate": 2.7291722326891456e-05, "loss": 0.3451, "step": 545 }, { "epoch": 2.211645569620253, "grad_norm": 0.4950358498258221, "learning_rate": 2.723884107774236e-05, "loss": 0.3442, "step": 546 }, { "epoch": 2.2156962025316456, "grad_norm": 0.5601474658710336, "learning_rate": 2.718590152796239e-05, "loss": 0.3626, "step": 547 }, { "epoch": 2.219746835443038, "grad_norm": 0.5341848615011767, "learning_rate": 2.71329041039194e-05, "loss": 0.3568, "step": 548 }, { "epoch": 2.22379746835443, "grad_norm": 0.520282048282148, "learning_rate": 2.7079849232447357e-05, "loss": 0.3287, "step": 549 }, { "epoch": 2.2278481012658227, "grad_norm": 0.5267654567820348, "learning_rate": 2.7026737340842895e-05, "loss": 0.3598, "step": 550 }, { "epoch": 2.231898734177215, "grad_norm": 0.5691009550607382, "learning_rate": 2.697356885686189e-05, "loss": 0.3565, "step": 551 }, { "epoch": 2.2359493670886077, "grad_norm": 0.4813495678122059, "learning_rate": 2.6920344208716014e-05, "loss": 0.3573, "step": 552 }, { "epoch": 2.24, "grad_norm": 0.5450681311673041, "learning_rate": 2.6867063825069252e-05, "loss": 0.3302, "step": 553 }, { "epoch": 2.2440506329113923, "grad_norm": 0.4845440196528506, "learning_rate": 2.6813728135034494e-05, "loss": 0.3707, "step": 554 }, { "epoch": 2.248101265822785, "grad_norm": 0.5043533951012208, "learning_rate": 2.6760337568170056e-05, "loss": 0.3472, "step": 555 }, { "epoch": 2.2521518987341773, "grad_norm": 0.4972264715531547, "learning_rate": 2.6706892554476226e-05, "loss": 0.3606, "step": 556 }, { "epoch": 2.2562025316455694, "grad_norm": 0.48057752710604984, "learning_rate": 2.6653393524391795e-05, "loss": 0.3616, "step": 557 }, { "epoch": 2.260253164556962, "grad_norm": 0.5108449548276576, "learning_rate": 2.6599840908790592e-05, "loss": 0.3499, "step": 558 }, { "epoch": 2.2643037974683544, "grad_norm": 0.5004386712416193, "learning_rate": 2.6546235138978028e-05, "loss": 0.3526, "step": 559 }, { "epoch": 2.268354430379747, "grad_norm": 0.5222659860111528, "learning_rate": 2.6492576646687597e-05, "loss": 0.3539, "step": 560 }, { "epoch": 2.2724050632911394, "grad_norm": 0.49823255286590923, "learning_rate": 2.6438865864077425e-05, "loss": 0.3654, "step": 561 }, { "epoch": 2.2764556962025315, "grad_norm": 0.5142821003365293, "learning_rate": 2.6385103223726766e-05, "loss": 0.3438, "step": 562 }, { "epoch": 2.280506329113924, "grad_norm": 0.49980021568164656, "learning_rate": 2.6331289158632537e-05, "loss": 0.3366, "step": 563 }, { "epoch": 2.2845569620253166, "grad_norm": 0.4503343411923907, "learning_rate": 2.6277424102205817e-05, "loss": 0.3718, "step": 564 }, { "epoch": 2.2886075949367086, "grad_norm": 0.5019221775449153, "learning_rate": 2.6223508488268374e-05, "loss": 0.3649, "step": 565 }, { "epoch": 2.292658227848101, "grad_norm": 0.47586671171777334, "learning_rate": 2.6169542751049148e-05, "loss": 0.3537, "step": 566 }, { "epoch": 2.2967088607594937, "grad_norm": 0.4951702993489543, "learning_rate": 2.6115527325180754e-05, "loss": 0.3562, "step": 567 }, { "epoch": 2.300759493670886, "grad_norm": 0.48979395429182776, "learning_rate": 2.606146264569603e-05, "loss": 0.3726, "step": 568 }, { "epoch": 2.3048101265822787, "grad_norm": 0.48590364479588183, "learning_rate": 2.6007349148024447e-05, "loss": 0.3412, "step": 569 }, { "epoch": 2.3088607594936708, "grad_norm": 0.5130042368757649, "learning_rate": 2.5953187267988694e-05, "loss": 0.3533, "step": 570 }, { "epoch": 2.3129113924050633, "grad_norm": 0.4865272150414806, "learning_rate": 2.5898977441801097e-05, "loss": 0.3483, "step": 571 }, { "epoch": 2.316962025316456, "grad_norm": 0.5245718907970914, "learning_rate": 2.584472010606015e-05, "loss": 0.3632, "step": 572 }, { "epoch": 2.321012658227848, "grad_norm": 0.49230741819553964, "learning_rate": 2.5790415697746976e-05, "loss": 0.3661, "step": 573 }, { "epoch": 2.3250632911392404, "grad_norm": 0.5348518706712615, "learning_rate": 2.5736064654221808e-05, "loss": 0.3615, "step": 574 }, { "epoch": 2.329113924050633, "grad_norm": 0.5134075691816518, "learning_rate": 2.568166741322048e-05, "loss": 0.3686, "step": 575 }, { "epoch": 2.3331645569620254, "grad_norm": 0.4914585021321793, "learning_rate": 2.56272244128509e-05, "loss": 0.3847, "step": 576 }, { "epoch": 2.337215189873418, "grad_norm": 0.5306921848495776, "learning_rate": 2.55727360915895e-05, "loss": 0.3629, "step": 577 }, { "epoch": 2.34126582278481, "grad_norm": 0.48788166354519696, "learning_rate": 2.5518202888277734e-05, "loss": 0.3859, "step": 578 }, { "epoch": 2.3453164556962025, "grad_norm": 0.5068541238787084, "learning_rate": 2.5463625242118523e-05, "loss": 0.3737, "step": 579 }, { "epoch": 2.349367088607595, "grad_norm": 0.5599781667575077, "learning_rate": 2.5409003592672723e-05, "loss": 0.3818, "step": 580 }, { "epoch": 2.353417721518987, "grad_norm": 0.47108425193450376, "learning_rate": 2.535433837985559e-05, "loss": 0.366, "step": 581 }, { "epoch": 2.3574683544303796, "grad_norm": 0.5310651828309362, "learning_rate": 2.529963004393324e-05, "loss": 0.361, "step": 582 }, { "epoch": 2.361518987341772, "grad_norm": 0.49287690437035814, "learning_rate": 2.524487902551908e-05, "loss": 0.3433, "step": 583 }, { "epoch": 2.3655696202531646, "grad_norm": 0.5327884043329697, "learning_rate": 2.519008576557029e-05, "loss": 0.3335, "step": 584 }, { "epoch": 2.369620253164557, "grad_norm": 0.5266233493337659, "learning_rate": 2.5135250705384254e-05, "loss": 0.3611, "step": 585 }, { "epoch": 2.3736708860759492, "grad_norm": 0.4812561534469466, "learning_rate": 2.5080374286595007e-05, "loss": 0.3544, "step": 586 }, { "epoch": 2.3777215189873417, "grad_norm": 0.5374109399294358, "learning_rate": 2.5025456951169677e-05, "loss": 0.3737, "step": 587 }, { "epoch": 2.3817721518987343, "grad_norm": 0.48535860337235553, "learning_rate": 2.4970499141404942e-05, "loss": 0.3717, "step": 588 }, { "epoch": 2.3858227848101268, "grad_norm": 0.5147741648635933, "learning_rate": 2.491550129992345e-05, "loss": 0.3746, "step": 589 }, { "epoch": 2.389873417721519, "grad_norm": 0.49552978188585844, "learning_rate": 2.486046386967024e-05, "loss": 0.3616, "step": 590 }, { "epoch": 2.3939240506329114, "grad_norm": 0.5676491517326091, "learning_rate": 2.4805387293909214e-05, "loss": 0.3833, "step": 591 }, { "epoch": 2.397974683544304, "grad_norm": 0.5032444846625178, "learning_rate": 2.4750272016219552e-05, "loss": 0.3219, "step": 592 }, { "epoch": 2.4020253164556964, "grad_norm": 0.48170631114631973, "learning_rate": 2.4695118480492114e-05, "loss": 0.3654, "step": 593 }, { "epoch": 2.4060759493670885, "grad_norm": 0.49968613016722624, "learning_rate": 2.4639927130925898e-05, "loss": 0.3579, "step": 594 }, { "epoch": 2.410126582278481, "grad_norm": 0.49020301497937047, "learning_rate": 2.458469841202444e-05, "loss": 0.3632, "step": 595 }, { "epoch": 2.4141772151898735, "grad_norm": 0.4879680899116057, "learning_rate": 2.452943276859226e-05, "loss": 0.3541, "step": 596 }, { "epoch": 2.418227848101266, "grad_norm": 0.47268412578763774, "learning_rate": 2.447413064573125e-05, "loss": 0.3441, "step": 597 }, { "epoch": 2.422278481012658, "grad_norm": 0.5828200712425684, "learning_rate": 2.4418792488837095e-05, "loss": 0.3778, "step": 598 }, { "epoch": 2.4263291139240506, "grad_norm": 0.4934773568804981, "learning_rate": 2.4363418743595713e-05, "loss": 0.3935, "step": 599 }, { "epoch": 2.430379746835443, "grad_norm": 0.48871752115228595, "learning_rate": 2.430800985597963e-05, "loss": 0.3542, "step": 600 }, { "epoch": 2.4344303797468356, "grad_norm": 0.49788504344412277, "learning_rate": 2.4252566272244415e-05, "loss": 0.3733, "step": 601 }, { "epoch": 2.4384810126582277, "grad_norm": 0.47457200015986817, "learning_rate": 2.4197088438925063e-05, "loss": 0.3417, "step": 602 }, { "epoch": 2.44253164556962, "grad_norm": 0.48057064783906367, "learning_rate": 2.4141576802832417e-05, "loss": 0.3286, "step": 603 }, { "epoch": 2.4465822784810127, "grad_norm": 0.5258394552053389, "learning_rate": 2.408603181104957e-05, "loss": 0.3564, "step": 604 }, { "epoch": 2.4506329113924052, "grad_norm": 0.466431106267755, "learning_rate": 2.4030453910928245e-05, "loss": 0.3799, "step": 605 }, { "epoch": 2.4546835443037973, "grad_norm": 0.48900478627077354, "learning_rate": 2.397484355008521e-05, "loss": 0.3402, "step": 606 }, { "epoch": 2.45873417721519, "grad_norm": 0.500812123657692, "learning_rate": 2.3919201176398662e-05, "loss": 0.3544, "step": 607 }, { "epoch": 2.4627848101265823, "grad_norm": 0.5070734446487384, "learning_rate": 2.3863527238004633e-05, "loss": 0.3483, "step": 608 }, { "epoch": 2.466835443037975, "grad_norm": 0.4802943445503838, "learning_rate": 2.380782218329337e-05, "loss": 0.3757, "step": 609 }, { "epoch": 2.470886075949367, "grad_norm": 0.4750820954168926, "learning_rate": 2.3752086460905725e-05, "loss": 0.3579, "step": 610 }, { "epoch": 2.4749367088607594, "grad_norm": 0.5092752562549945, "learning_rate": 2.3696320519729544e-05, "loss": 0.3573, "step": 611 }, { "epoch": 2.478987341772152, "grad_norm": 0.46758448526929, "learning_rate": 2.3640524808896045e-05, "loss": 0.3351, "step": 612 }, { "epoch": 2.4830379746835445, "grad_norm": 0.5087833975950969, "learning_rate": 2.3584699777776222e-05, "loss": 0.3833, "step": 613 }, { "epoch": 2.4870886075949366, "grad_norm": 0.47593019439099277, "learning_rate": 2.3528845875977195e-05, "loss": 0.3555, "step": 614 }, { "epoch": 2.491139240506329, "grad_norm": 0.5162871494294002, "learning_rate": 2.3472963553338614e-05, "loss": 0.36, "step": 615 }, { "epoch": 2.4951898734177216, "grad_norm": 0.43954834096737144, "learning_rate": 2.341705325992901e-05, "loss": 0.3583, "step": 616 }, { "epoch": 2.499240506329114, "grad_norm": 0.5101420824634776, "learning_rate": 2.336111544604222e-05, "loss": 0.3389, "step": 617 }, { "epoch": 2.503291139240506, "grad_norm": 0.49203717176856965, "learning_rate": 2.33051505621937e-05, "loss": 0.3475, "step": 618 }, { "epoch": 2.5073417721518987, "grad_norm": 0.47273957119899934, "learning_rate": 2.324915905911693e-05, "loss": 0.3619, "step": 619 }, { "epoch": 2.511392405063291, "grad_norm": 0.48275863951596404, "learning_rate": 2.319314138775977e-05, "loss": 0.343, "step": 620 }, { "epoch": 2.5154430379746833, "grad_norm": 0.4692462962386632, "learning_rate": 2.3137097999280856e-05, "loss": 0.3638, "step": 621 }, { "epoch": 2.519493670886076, "grad_norm": 0.47495208026490765, "learning_rate": 2.308102934504593e-05, "loss": 0.356, "step": 622 }, { "epoch": 2.5235443037974683, "grad_norm": 0.4892001231507276, "learning_rate": 2.3024935876624222e-05, "loss": 0.3615, "step": 623 }, { "epoch": 2.527594936708861, "grad_norm": 0.5006628377944033, "learning_rate": 2.2968818045784813e-05, "loss": 0.3717, "step": 624 }, { "epoch": 2.5316455696202533, "grad_norm": 0.49823271147792697, "learning_rate": 2.2912676304493006e-05, "loss": 0.3535, "step": 625 }, { "epoch": 2.5356962025316454, "grad_norm": 0.4895498411785922, "learning_rate": 2.2856511104906668e-05, "loss": 0.3697, "step": 626 }, { "epoch": 2.539746835443038, "grad_norm": 0.5205957524736666, "learning_rate": 2.2800322899372586e-05, "loss": 0.3744, "step": 627 }, { "epoch": 2.5437974683544304, "grad_norm": 0.4615246633803433, "learning_rate": 2.2744112140422844e-05, "loss": 0.3583, "step": 628 }, { "epoch": 2.547848101265823, "grad_norm": 0.507057345680905, "learning_rate": 2.2687879280771177e-05, "loss": 0.3704, "step": 629 }, { "epoch": 2.5518987341772155, "grad_norm": 0.46896356881733475, "learning_rate": 2.26316247733093e-05, "loss": 0.3596, "step": 630 }, { "epoch": 2.5559493670886075, "grad_norm": 0.4552144025342221, "learning_rate": 2.257534907110328e-05, "loss": 0.3376, "step": 631 }, { "epoch": 2.56, "grad_norm": 0.4722500888488154, "learning_rate": 2.2519052627389882e-05, "loss": 0.3687, "step": 632 }, { "epoch": 2.5640506329113926, "grad_norm": 0.4661547770948948, "learning_rate": 2.246273589557294e-05, "loss": 0.3472, "step": 633 }, { "epoch": 2.5681012658227846, "grad_norm": 0.4766757808075662, "learning_rate": 2.240639932921966e-05, "loss": 0.3496, "step": 634 }, { "epoch": 2.572151898734177, "grad_norm": 0.4645897079543252, "learning_rate": 2.2350043382056995e-05, "loss": 0.3587, "step": 635 }, { "epoch": 2.5762025316455697, "grad_norm": 0.4852749013112411, "learning_rate": 2.2293668507968015e-05, "loss": 0.3409, "step": 636 }, { "epoch": 2.580253164556962, "grad_norm": 0.4805132936309502, "learning_rate": 2.2237275160988186e-05, "loss": 0.357, "step": 637 }, { "epoch": 2.5843037974683547, "grad_norm": 0.4656853395630425, "learning_rate": 2.2180863795301787e-05, "loss": 0.3396, "step": 638 }, { "epoch": 2.5883544303797468, "grad_norm": 0.44526223142975385, "learning_rate": 2.212443486523819e-05, "loss": 0.3366, "step": 639 }, { "epoch": 2.5924050632911393, "grad_norm": 0.46672548774940714, "learning_rate": 2.2067988825268243e-05, "loss": 0.352, "step": 640 }, { "epoch": 2.596455696202532, "grad_norm": 0.448848946355186, "learning_rate": 2.2011526130000596e-05, "loss": 0.3636, "step": 641 }, { "epoch": 2.600506329113924, "grad_norm": 0.48743836885547226, "learning_rate": 2.1955047234178038e-05, "loss": 0.3539, "step": 642 }, { "epoch": 2.6045569620253164, "grad_norm": 0.4595668789009914, "learning_rate": 2.1898552592673825e-05, "loss": 0.3661, "step": 643 }, { "epoch": 2.608607594936709, "grad_norm": 0.4563423508457443, "learning_rate": 2.184204266048803e-05, "loss": 0.3692, "step": 644 }, { "epoch": 2.6126582278481014, "grad_norm": 0.490537317352902, "learning_rate": 2.1785517892743887e-05, "loss": 0.3469, "step": 645 }, { "epoch": 2.616708860759494, "grad_norm": 0.48330110912842444, "learning_rate": 2.17289787446841e-05, "loss": 0.3762, "step": 646 }, { "epoch": 2.620759493670886, "grad_norm": 0.5619775424397693, "learning_rate": 2.1672425671667198e-05, "loss": 0.3365, "step": 647 }, { "epoch": 2.6248101265822785, "grad_norm": 0.4594106331072145, "learning_rate": 2.161585912916385e-05, "loss": 0.3472, "step": 648 }, { "epoch": 2.628860759493671, "grad_norm": 0.5169216279852891, "learning_rate": 2.1559279572753214e-05, "loss": 0.3501, "step": 649 }, { "epoch": 2.632911392405063, "grad_norm": 0.5422678376690597, "learning_rate": 2.1502687458119268e-05, "loss": 0.3403, "step": 650 }, { "epoch": 2.6369620253164556, "grad_norm": 0.4587586100034399, "learning_rate": 2.1446083241047116e-05, "loss": 0.3517, "step": 651 }, { "epoch": 2.641012658227848, "grad_norm": 0.5613984290953302, "learning_rate": 2.1389467377419333e-05, "loss": 0.3364, "step": 652 }, { "epoch": 2.6450632911392407, "grad_norm": 0.47082179813729563, "learning_rate": 2.133284032321232e-05, "loss": 0.3649, "step": 653 }, { "epoch": 2.649113924050633, "grad_norm": 0.47357584354979154, "learning_rate": 2.1276202534492566e-05, "loss": 0.3467, "step": 654 }, { "epoch": 2.6531645569620252, "grad_norm": 0.4800573356002243, "learning_rate": 2.121955446741306e-05, "loss": 0.3304, "step": 655 }, { "epoch": 2.6572151898734178, "grad_norm": 0.4906790322084436, "learning_rate": 2.1162896578209517e-05, "loss": 0.3661, "step": 656 }, { "epoch": 2.6612658227848103, "grad_norm": 0.47178419874642874, "learning_rate": 2.1106229323196813e-05, "loss": 0.3709, "step": 657 }, { "epoch": 2.6653164556962023, "grad_norm": 0.4769243351194265, "learning_rate": 2.1049553158765214e-05, "loss": 0.3241, "step": 658 }, { "epoch": 2.669367088607595, "grad_norm": 0.46672083590227187, "learning_rate": 2.0992868541376764e-05, "loss": 0.3573, "step": 659 }, { "epoch": 2.6734177215189874, "grad_norm": 0.4612793181335863, "learning_rate": 2.093617592756158e-05, "loss": 0.3343, "step": 660 }, { "epoch": 2.67746835443038, "grad_norm": 0.47769489998709536, "learning_rate": 2.0879475773914167e-05, "loss": 0.3651, "step": 661 }, { "epoch": 2.6815189873417724, "grad_norm": 0.46169544234118737, "learning_rate": 2.082276853708978e-05, "loss": 0.3484, "step": 662 }, { "epoch": 2.6855696202531645, "grad_norm": 0.5070515889458975, "learning_rate": 2.076605467380071e-05, "loss": 0.331, "step": 663 }, { "epoch": 2.689620253164557, "grad_norm": 0.46090874604677484, "learning_rate": 2.0709334640812613e-05, "loss": 0.3634, "step": 664 }, { "epoch": 2.6936708860759495, "grad_norm": 0.49137686188875396, "learning_rate": 2.0652608894940824e-05, "loss": 0.3619, "step": 665 }, { "epoch": 2.6977215189873416, "grad_norm": 0.4673304231807944, "learning_rate": 2.0595877893046722e-05, "loss": 0.3559, "step": 666 }, { "epoch": 2.701772151898734, "grad_norm": 0.48948016526936894, "learning_rate": 2.0539142092033985e-05, "loss": 0.3651, "step": 667 }, { "epoch": 2.7058227848101266, "grad_norm": 0.44358340554737036, "learning_rate": 2.048240194884496e-05, "loss": 0.3464, "step": 668 }, { "epoch": 2.709873417721519, "grad_norm": 0.46402043450622515, "learning_rate": 2.042565792045695e-05, "loss": 0.3511, "step": 669 }, { "epoch": 2.7139240506329116, "grad_norm": 0.4450216529665482, "learning_rate": 2.036891046387857e-05, "loss": 0.3612, "step": 670 }, { "epoch": 2.7179746835443037, "grad_norm": 0.4571101899389741, "learning_rate": 2.0312160036146036e-05, "loss": 0.3509, "step": 671 }, { "epoch": 2.7220253164556962, "grad_norm": 0.46177036503175384, "learning_rate": 2.025540709431948e-05, "loss": 0.3473, "step": 672 }, { "epoch": 2.7260759493670887, "grad_norm": 0.44690500570880937, "learning_rate": 2.0198652095479298e-05, "loss": 0.3573, "step": 673 }, { "epoch": 2.730126582278481, "grad_norm": 0.46141571434796536, "learning_rate": 2.014189549672245e-05, "loss": 0.3221, "step": 674 }, { "epoch": 2.7341772151898733, "grad_norm": 0.45235634076039477, "learning_rate": 2.0085137755158776e-05, "loss": 0.344, "step": 675 }, { "epoch": 2.738227848101266, "grad_norm": 0.43424485584319567, "learning_rate": 2.0028379327907327e-05, "loss": 0.3567, "step": 676 }, { "epoch": 2.7422784810126584, "grad_norm": 0.43948646918303624, "learning_rate": 1.9971620672092676e-05, "loss": 0.3601, "step": 677 }, { "epoch": 2.746329113924051, "grad_norm": 0.44790464993089063, "learning_rate": 1.991486224484123e-05, "loss": 0.3539, "step": 678 }, { "epoch": 2.750379746835443, "grad_norm": 0.465508137815262, "learning_rate": 1.985810450327756e-05, "loss": 0.369, "step": 679 }, { "epoch": 2.7544303797468355, "grad_norm": 0.46335686917921104, "learning_rate": 1.9801347904520706e-05, "loss": 0.3344, "step": 680 }, { "epoch": 2.758481012658228, "grad_norm": 0.4521116970079556, "learning_rate": 1.974459290568053e-05, "loss": 0.369, "step": 681 }, { "epoch": 2.76253164556962, "grad_norm": 0.4796615043416971, "learning_rate": 1.968783996385397e-05, "loss": 0.3716, "step": 682 }, { "epoch": 2.7665822784810126, "grad_norm": 0.46404569410175633, "learning_rate": 1.963108953612143e-05, "loss": 0.3666, "step": 683 }, { "epoch": 2.770632911392405, "grad_norm": 0.4829133891719137, "learning_rate": 1.9574342079543056e-05, "loss": 0.3209, "step": 684 }, { "epoch": 2.7746835443037976, "grad_norm": 0.48556485378952036, "learning_rate": 1.9517598051155046e-05, "loss": 0.3472, "step": 685 }, { "epoch": 2.77873417721519, "grad_norm": 0.44256040393905655, "learning_rate": 1.9460857907966025e-05, "loss": 0.3651, "step": 686 }, { "epoch": 2.782784810126582, "grad_norm": 0.47517072980808034, "learning_rate": 1.9404122106953285e-05, "loss": 0.3417, "step": 687 }, { "epoch": 2.7868354430379747, "grad_norm": 0.4665237702480731, "learning_rate": 1.9347391105059176e-05, "loss": 0.3445, "step": 688 }, { "epoch": 2.790886075949367, "grad_norm": 0.4265994299519683, "learning_rate": 1.92906653591874e-05, "loss": 0.3883, "step": 689 }, { "epoch": 2.7949367088607593, "grad_norm": 0.4491171569034515, "learning_rate": 1.9233945326199295e-05, "loss": 0.3463, "step": 690 }, { "epoch": 2.798987341772152, "grad_norm": 0.4583550774313177, "learning_rate": 1.917723146291022e-05, "loss": 0.3596, "step": 691 }, { "epoch": 2.8030379746835443, "grad_norm": 0.46371551049141185, "learning_rate": 1.912052422608584e-05, "loss": 0.3351, "step": 692 }, { "epoch": 2.807088607594937, "grad_norm": 0.46944257604481077, "learning_rate": 1.9063824072438428e-05, "loss": 0.3608, "step": 693 }, { "epoch": 2.8111392405063294, "grad_norm": 0.508865387105456, "learning_rate": 1.9007131458623246e-05, "loss": 0.3478, "step": 694 }, { "epoch": 2.8151898734177214, "grad_norm": 0.4819844419508227, "learning_rate": 1.895044684123479e-05, "loss": 0.3499, "step": 695 }, { "epoch": 2.819240506329114, "grad_norm": 0.4676415026049661, "learning_rate": 1.8893770676803194e-05, "loss": 0.3449, "step": 696 }, { "epoch": 2.8232911392405065, "grad_norm": 0.48018354050289364, "learning_rate": 1.8837103421790486e-05, "loss": 0.3567, "step": 697 }, { "epoch": 2.8273417721518985, "grad_norm": 0.47191282113426664, "learning_rate": 1.8780445532586952e-05, "loss": 0.3738, "step": 698 }, { "epoch": 2.831392405063291, "grad_norm": 0.49088682340875606, "learning_rate": 1.872379746550743e-05, "loss": 0.3401, "step": 699 }, { "epoch": 2.8354430379746836, "grad_norm": 0.4932928778270544, "learning_rate": 1.866715967678769e-05, "loss": 0.3408, "step": 700 }, { "epoch": 2.839493670886076, "grad_norm": 0.47416296794645363, "learning_rate": 1.861053262258067e-05, "loss": 0.3538, "step": 701 }, { "epoch": 2.8435443037974686, "grad_norm": 0.5284116572653916, "learning_rate": 1.8553916758952897e-05, "loss": 0.3597, "step": 702 }, { "epoch": 2.8475949367088607, "grad_norm": 0.449733289475327, "learning_rate": 1.8497312541880735e-05, "loss": 0.3717, "step": 703 }, { "epoch": 2.851645569620253, "grad_norm": 0.5161907373867617, "learning_rate": 1.8440720427246786e-05, "loss": 0.3406, "step": 704 }, { "epoch": 2.8556962025316457, "grad_norm": 0.5012167952900446, "learning_rate": 1.8384140870836157e-05, "loss": 0.3695, "step": 705 }, { "epoch": 2.8597468354430378, "grad_norm": 0.44390863714601075, "learning_rate": 1.8327574328332806e-05, "loss": 0.3644, "step": 706 }, { "epoch": 2.8637974683544303, "grad_norm": 0.5090230882729763, "learning_rate": 1.8271021255315906e-05, "loss": 0.3635, "step": 707 }, { "epoch": 2.867848101265823, "grad_norm": 0.5132320078292623, "learning_rate": 1.8214482107256117e-05, "loss": 0.3662, "step": 708 }, { "epoch": 2.8718987341772153, "grad_norm": 0.4772121111500768, "learning_rate": 1.8157957339511968e-05, "loss": 0.3567, "step": 709 }, { "epoch": 2.875949367088608, "grad_norm": 0.45868630630634094, "learning_rate": 1.8101447407326182e-05, "loss": 0.3625, "step": 710 }, { "epoch": 2.88, "grad_norm": 0.484509955554625, "learning_rate": 1.8044952765821966e-05, "loss": 0.365, "step": 711 }, { "epoch": 2.8840506329113924, "grad_norm": 0.4339184882569882, "learning_rate": 1.7988473869999407e-05, "loss": 0.3765, "step": 712 }, { "epoch": 2.888101265822785, "grad_norm": 0.46733471588225206, "learning_rate": 1.7932011174731764e-05, "loss": 0.3456, "step": 713 }, { "epoch": 2.892151898734177, "grad_norm": 0.4947741746450697, "learning_rate": 1.7875565134761817e-05, "loss": 0.3826, "step": 714 }, { "epoch": 2.8962025316455695, "grad_norm": 0.45281078844936856, "learning_rate": 1.7819136204698226e-05, "loss": 0.3716, "step": 715 }, { "epoch": 2.900253164556962, "grad_norm": 0.4784005301065605, "learning_rate": 1.776272483901182e-05, "loss": 0.3376, "step": 716 }, { "epoch": 2.9043037974683545, "grad_norm": 0.44865201607886, "learning_rate": 1.7706331492031995e-05, "loss": 0.3579, "step": 717 }, { "epoch": 2.908354430379747, "grad_norm": 0.4691823892030148, "learning_rate": 1.764995661794301e-05, "loss": 0.3626, "step": 718 }, { "epoch": 2.912405063291139, "grad_norm": 0.47917816722627504, "learning_rate": 1.759360067078035e-05, "loss": 0.3554, "step": 719 }, { "epoch": 2.9164556962025316, "grad_norm": 0.444674807597793, "learning_rate": 1.7537264104427064e-05, "loss": 0.3649, "step": 720 }, { "epoch": 2.920506329113924, "grad_norm": 0.4731625665146926, "learning_rate": 1.748094737261012e-05, "loss": 0.3687, "step": 721 }, { "epoch": 2.9245569620253162, "grad_norm": 0.44778051999352897, "learning_rate": 1.7424650928896726e-05, "loss": 0.3357, "step": 722 }, { "epoch": 2.9286075949367087, "grad_norm": 0.4507507456823704, "learning_rate": 1.7368375226690712e-05, "loss": 0.3654, "step": 723 }, { "epoch": 2.9326582278481013, "grad_norm": 0.4606767235199757, "learning_rate": 1.731212071922883e-05, "loss": 0.3427, "step": 724 }, { "epoch": 2.9367088607594938, "grad_norm": 0.49308233967104986, "learning_rate": 1.7255887859577156e-05, "loss": 0.3631, "step": 725 }, { "epoch": 2.9407594936708863, "grad_norm": 0.4465849603019107, "learning_rate": 1.7199677100627427e-05, "loss": 0.3317, "step": 726 }, { "epoch": 2.9448101265822784, "grad_norm": 0.4872109924214035, "learning_rate": 1.7143488895093343e-05, "loss": 0.3676, "step": 727 }, { "epoch": 2.948860759493671, "grad_norm": 0.458655877379535, "learning_rate": 1.7087323695506994e-05, "loss": 0.3511, "step": 728 }, { "epoch": 2.9529113924050634, "grad_norm": 0.4669570418464671, "learning_rate": 1.7031181954215194e-05, "loss": 0.3389, "step": 729 }, { "epoch": 2.9569620253164555, "grad_norm": 0.49278205683176585, "learning_rate": 1.6975064123375788e-05, "loss": 0.3588, "step": 730 }, { "epoch": 2.961012658227848, "grad_norm": 0.48138792783357426, "learning_rate": 1.6918970654954084e-05, "loss": 0.3246, "step": 731 }, { "epoch": 2.9650632911392405, "grad_norm": 0.4521127635185209, "learning_rate": 1.686290200071915e-05, "loss": 0.3552, "step": 732 }, { "epoch": 2.969113924050633, "grad_norm": 0.48861481600709816, "learning_rate": 1.6806858612240234e-05, "loss": 0.343, "step": 733 }, { "epoch": 2.9731645569620255, "grad_norm": 0.45073203523788624, "learning_rate": 1.6750840940883078e-05, "loss": 0.3603, "step": 734 }, { "epoch": 2.9772151898734176, "grad_norm": 0.48084898566467305, "learning_rate": 1.6694849437806305e-05, "loss": 0.3384, "step": 735 }, { "epoch": 2.98126582278481, "grad_norm": 0.4830076052676503, "learning_rate": 1.663888455395778e-05, "loss": 0.3484, "step": 736 }, { "epoch": 2.9853164556962026, "grad_norm": 0.45829002902752314, "learning_rate": 1.6582946740070995e-05, "loss": 0.3476, "step": 737 }, { "epoch": 2.9893670886075947, "grad_norm": 0.46747610545277923, "learning_rate": 1.6527036446661396e-05, "loss": 0.3507, "step": 738 }, { "epoch": 2.993417721518987, "grad_norm": 0.5108821817494196, "learning_rate": 1.6471154124022818e-05, "loss": 0.3524, "step": 739 }, { "epoch": 2.9974683544303797, "grad_norm": 0.48863952719128845, "learning_rate": 1.6415300222223788e-05, "loss": 0.3514, "step": 740 }, { "epoch": 3.0015189873417722, "grad_norm": 0.4576169174933906, "learning_rate": 1.6359475191103958e-05, "loss": 0.3162, "step": 741 }, { "epoch": 3.0055696202531648, "grad_norm": 0.5558155603275978, "learning_rate": 1.6303679480270466e-05, "loss": 0.2347, "step": 742 }, { "epoch": 3.009620253164557, "grad_norm": 0.4052323010238568, "learning_rate": 1.624791353909428e-05, "loss": 0.2314, "step": 743 }, { "epoch": 3.0136708860759494, "grad_norm": 0.504400479974541, "learning_rate": 1.619217781670663e-05, "loss": 0.2217, "step": 744 }, { "epoch": 3.017721518987342, "grad_norm": 0.712607651898232, "learning_rate": 1.6136472761995373e-05, "loss": 0.2485, "step": 745 }, { "epoch": 3.0217721518987344, "grad_norm": 0.5205385170381861, "learning_rate": 1.608079882360134e-05, "loss": 0.2423, "step": 746 }, { "epoch": 3.0258227848101265, "grad_norm": 0.5129115187245612, "learning_rate": 1.60251564499148e-05, "loss": 0.216, "step": 747 }, { "epoch": 3.029873417721519, "grad_norm": 0.5745268735625805, "learning_rate": 1.596954608907176e-05, "loss": 0.2237, "step": 748 }, { "epoch": 3.0339240506329115, "grad_norm": 0.46745434349035864, "learning_rate": 1.591396818895043e-05, "loss": 0.2295, "step": 749 }, { "epoch": 3.037974683544304, "grad_norm": 0.4470104084797433, "learning_rate": 1.585842319716759e-05, "loss": 0.2321, "step": 750 }, { "epoch": 3.042025316455696, "grad_norm": 0.4432306151372116, "learning_rate": 1.5802911561074944e-05, "loss": 0.2226, "step": 751 }, { "epoch": 3.0460759493670886, "grad_norm": 0.4784441958851918, "learning_rate": 1.5747433727755595e-05, "loss": 0.2335, "step": 752 }, { "epoch": 3.050126582278481, "grad_norm": 0.4616034887823587, "learning_rate": 1.5691990144020376e-05, "loss": 0.2388, "step": 753 }, { "epoch": 3.0541772151898736, "grad_norm": 0.43299003285284543, "learning_rate": 1.5636581256404297e-05, "loss": 0.229, "step": 754 }, { "epoch": 3.0582278481012657, "grad_norm": 0.44364842319348075, "learning_rate": 1.558120751116291e-05, "loss": 0.2233, "step": 755 }, { "epoch": 3.062278481012658, "grad_norm": 0.4497562162535785, "learning_rate": 1.552586935426876e-05, "loss": 0.2142, "step": 756 }, { "epoch": 3.0663291139240507, "grad_norm": 0.41542082686392995, "learning_rate": 1.547056723140774e-05, "loss": 0.2224, "step": 757 }, { "epoch": 3.0703797468354432, "grad_norm": 0.4801992078678777, "learning_rate": 1.5415301587975565e-05, "loss": 0.2331, "step": 758 }, { "epoch": 3.0744303797468353, "grad_norm": 0.42837079862571936, "learning_rate": 1.536007286907411e-05, "loss": 0.2215, "step": 759 }, { "epoch": 3.078481012658228, "grad_norm": 0.3944842142964027, "learning_rate": 1.5304881519507896e-05, "loss": 0.2287, "step": 760 }, { "epoch": 3.0825316455696203, "grad_norm": 0.4251968717559588, "learning_rate": 1.5249727983780453e-05, "loss": 0.2415, "step": 761 }, { "epoch": 3.086582278481013, "grad_norm": 0.3935782641311252, "learning_rate": 1.5194612706090786e-05, "loss": 0.234, "step": 762 }, { "epoch": 3.090632911392405, "grad_norm": 0.3847525938689482, "learning_rate": 1.5139536130329771e-05, "loss": 0.2308, "step": 763 }, { "epoch": 3.0946835443037974, "grad_norm": 0.38453395660022716, "learning_rate": 1.508449870007656e-05, "loss": 0.2209, "step": 764 }, { "epoch": 3.09873417721519, "grad_norm": 0.39100958245081063, "learning_rate": 1.5029500858595056e-05, "loss": 0.1811, "step": 765 }, { "epoch": 3.1027848101265825, "grad_norm": 0.4204118000722288, "learning_rate": 1.4974543048830328e-05, "loss": 0.2342, "step": 766 }, { "epoch": 3.1068354430379745, "grad_norm": 0.3905938636412467, "learning_rate": 1.4919625713405e-05, "loss": 0.2252, "step": 767 }, { "epoch": 3.110886075949367, "grad_norm": 0.41278286723689406, "learning_rate": 1.4864749294615756e-05, "loss": 0.2044, "step": 768 }, { "epoch": 3.1149367088607596, "grad_norm": 0.3689641221363606, "learning_rate": 1.4809914234429716e-05, "loss": 0.2243, "step": 769 }, { "epoch": 3.118987341772152, "grad_norm": 0.42146611942657985, "learning_rate": 1.4755120974480923e-05, "loss": 0.2413, "step": 770 }, { "epoch": 3.123037974683544, "grad_norm": 0.3865389313649817, "learning_rate": 1.4700369956066771e-05, "loss": 0.2335, "step": 771 }, { "epoch": 3.1270886075949367, "grad_norm": 0.3978972250967386, "learning_rate": 1.4645661620144413e-05, "loss": 0.2549, "step": 772 }, { "epoch": 3.131139240506329, "grad_norm": 0.3869134867841158, "learning_rate": 1.4590996407327284e-05, "loss": 0.2098, "step": 773 }, { "epoch": 3.1351898734177217, "grad_norm": 0.39985320253096274, "learning_rate": 1.4536374757881487e-05, "loss": 0.2433, "step": 774 }, { "epoch": 3.1392405063291138, "grad_norm": 0.39576186313935624, "learning_rate": 1.4481797111722271e-05, "loss": 0.2042, "step": 775 }, { "epoch": 3.1432911392405063, "grad_norm": 0.3931700748029026, "learning_rate": 1.4427263908410507e-05, "loss": 0.2383, "step": 776 }, { "epoch": 3.147341772151899, "grad_norm": 0.3800502564051839, "learning_rate": 1.4372775587149108e-05, "loss": 0.2275, "step": 777 }, { "epoch": 3.1513924050632913, "grad_norm": 0.3800184542840794, "learning_rate": 1.4318332586779522e-05, "loss": 0.2251, "step": 778 }, { "epoch": 3.1554430379746834, "grad_norm": 0.3881901365682713, "learning_rate": 1.4263935345778202e-05, "loss": 0.2274, "step": 779 }, { "epoch": 3.159493670886076, "grad_norm": 0.4046494496174754, "learning_rate": 1.420958430225303e-05, "loss": 0.2518, "step": 780 }, { "epoch": 3.1635443037974684, "grad_norm": 0.373115170300213, "learning_rate": 1.415527989393985e-05, "loss": 0.2399, "step": 781 }, { "epoch": 3.167594936708861, "grad_norm": 0.3732540757132007, "learning_rate": 1.410102255819891e-05, "loss": 0.1964, "step": 782 }, { "epoch": 3.171645569620253, "grad_norm": 0.3875722061164957, "learning_rate": 1.404681273201131e-05, "loss": 0.2133, "step": 783 }, { "epoch": 3.1756962025316455, "grad_norm": 0.3908487288844292, "learning_rate": 1.399265085197556e-05, "loss": 0.2432, "step": 784 }, { "epoch": 3.179746835443038, "grad_norm": 0.3691358764854472, "learning_rate": 1.393853735430398e-05, "loss": 0.2105, "step": 785 }, { "epoch": 3.1837974683544306, "grad_norm": 0.3718145464470567, "learning_rate": 1.3884472674819246e-05, "loss": 0.1982, "step": 786 }, { "epoch": 3.1878481012658226, "grad_norm": 0.38502336953407207, "learning_rate": 1.3830457248950864e-05, "loss": 0.2357, "step": 787 }, { "epoch": 3.191898734177215, "grad_norm": 0.3894474004690482, "learning_rate": 1.377649151173163e-05, "loss": 0.2233, "step": 788 }, { "epoch": 3.1959493670886077, "grad_norm": 0.3738143933934285, "learning_rate": 1.3722575897794181e-05, "loss": 0.195, "step": 789 }, { "epoch": 3.2, "grad_norm": 0.37856959370567794, "learning_rate": 1.3668710841367472e-05, "loss": 0.2228, "step": 790 }, { "epoch": 3.2040506329113922, "grad_norm": 0.36548060795590576, "learning_rate": 1.361489677627324e-05, "loss": 0.2031, "step": 791 }, { "epoch": 3.2081012658227848, "grad_norm": 0.3588407935707722, "learning_rate": 1.3561134135922585e-05, "loss": 0.215, "step": 792 }, { "epoch": 3.2121518987341773, "grad_norm": 0.3927477813246824, "learning_rate": 1.350742335331241e-05, "loss": 0.2464, "step": 793 }, { "epoch": 3.21620253164557, "grad_norm": 0.38026098490999866, "learning_rate": 1.345376486102198e-05, "loss": 0.2188, "step": 794 }, { "epoch": 3.220253164556962, "grad_norm": 0.3838833487996605, "learning_rate": 1.3400159091209414e-05, "loss": 0.2127, "step": 795 }, { "epoch": 3.2243037974683544, "grad_norm": 0.3962338675325812, "learning_rate": 1.3346606475608216e-05, "loss": 0.2179, "step": 796 }, { "epoch": 3.228354430379747, "grad_norm": 0.3763469903538635, "learning_rate": 1.3293107445523781e-05, "loss": 0.2165, "step": 797 }, { "epoch": 3.2324050632911394, "grad_norm": 0.38440262834211797, "learning_rate": 1.3239662431829949e-05, "loss": 0.2267, "step": 798 }, { "epoch": 3.2364556962025315, "grad_norm": 0.37077773701601724, "learning_rate": 1.3186271864965509e-05, "loss": 0.2252, "step": 799 }, { "epoch": 3.240506329113924, "grad_norm": 0.3869514412131439, "learning_rate": 1.3132936174930756e-05, "loss": 0.2222, "step": 800 }, { "epoch": 3.2445569620253165, "grad_norm": 0.3727974856754257, "learning_rate": 1.3079655791283995e-05, "loss": 0.2298, "step": 801 }, { "epoch": 3.248607594936709, "grad_norm": 0.3737277951201105, "learning_rate": 1.3026431143138108e-05, "loss": 0.2351, "step": 802 }, { "epoch": 3.252658227848101, "grad_norm": 0.3630685575723726, "learning_rate": 1.2973262659157114e-05, "loss": 0.2201, "step": 803 }, { "epoch": 3.2567088607594936, "grad_norm": 0.3829500990045676, "learning_rate": 1.2920150767552651e-05, "loss": 0.2044, "step": 804 }, { "epoch": 3.260759493670886, "grad_norm": 0.3795850556767077, "learning_rate": 1.2867095896080607e-05, "loss": 0.1997, "step": 805 }, { "epoch": 3.2648101265822786, "grad_norm": 0.38386418180535076, "learning_rate": 1.2814098472037612e-05, "loss": 0.2239, "step": 806 }, { "epoch": 3.2688607594936707, "grad_norm": 0.39888341242415487, "learning_rate": 1.276115892225764e-05, "loss": 0.2116, "step": 807 }, { "epoch": 3.2729113924050632, "grad_norm": 0.3826235148138331, "learning_rate": 1.2708277673108555e-05, "loss": 0.2141, "step": 808 }, { "epoch": 3.2769620253164558, "grad_norm": 0.40923087179490797, "learning_rate": 1.2655455150488649e-05, "loss": 0.2121, "step": 809 }, { "epoch": 3.2810126582278483, "grad_norm": 0.38569435104907174, "learning_rate": 1.2602691779823272e-05, "loss": 0.2278, "step": 810 }, { "epoch": 3.2850632911392403, "grad_norm": 0.3945664142698204, "learning_rate": 1.2549987986061355e-05, "loss": 0.216, "step": 811 }, { "epoch": 3.289113924050633, "grad_norm": 0.40588686113233596, "learning_rate": 1.2497344193672005e-05, "loss": 0.2193, "step": 812 }, { "epoch": 3.2931645569620254, "grad_norm": 0.3925405485888381, "learning_rate": 1.2444760826641092e-05, "loss": 0.2065, "step": 813 }, { "epoch": 3.297215189873418, "grad_norm": 0.3636382543931487, "learning_rate": 1.2392238308467817e-05, "loss": 0.228, "step": 814 }, { "epoch": 3.30126582278481, "grad_norm": 0.388906384215717, "learning_rate": 1.2339777062161326e-05, "loss": 0.2208, "step": 815 }, { "epoch": 3.3053164556962025, "grad_norm": 0.41623432664000826, "learning_rate": 1.2287377510237293e-05, "loss": 0.2185, "step": 816 }, { "epoch": 3.309367088607595, "grad_norm": 0.35797874544025454, "learning_rate": 1.2235040074714488e-05, "loss": 0.2034, "step": 817 }, { "epoch": 3.3134177215189875, "grad_norm": 0.38216339131263644, "learning_rate": 1.2182765177111434e-05, "loss": 0.2667, "step": 818 }, { "epoch": 3.3174683544303796, "grad_norm": 0.3936652621075552, "learning_rate": 1.213055323844297e-05, "loss": 0.2251, "step": 819 }, { "epoch": 3.321518987341772, "grad_norm": 0.37376785442650073, "learning_rate": 1.2078404679216864e-05, "loss": 0.2185, "step": 820 }, { "epoch": 3.3255696202531646, "grad_norm": 0.3773456025241373, "learning_rate": 1.2026319919430458e-05, "loss": 0.1925, "step": 821 }, { "epoch": 3.329620253164557, "grad_norm": 0.37280502468919224, "learning_rate": 1.1974299378567227e-05, "loss": 0.2208, "step": 822 }, { "epoch": 3.333670886075949, "grad_norm": 0.368876349696973, "learning_rate": 1.1922343475593462e-05, "loss": 0.2342, "step": 823 }, { "epoch": 3.3377215189873417, "grad_norm": 0.36645647079975635, "learning_rate": 1.187045262895488e-05, "loss": 0.2279, "step": 824 }, { "epoch": 3.3417721518987342, "grad_norm": 0.3699005572842383, "learning_rate": 1.1818627256573203e-05, "loss": 0.2096, "step": 825 }, { "epoch": 3.3458227848101267, "grad_norm": 0.3703262926218789, "learning_rate": 1.1766867775842864e-05, "loss": 0.2006, "step": 826 }, { "epoch": 3.349873417721519, "grad_norm": 0.37929883618397114, "learning_rate": 1.1715174603627615e-05, "loss": 0.2401, "step": 827 }, { "epoch": 3.3539240506329113, "grad_norm": 0.3606983694338296, "learning_rate": 1.1663548156257147e-05, "loss": 0.2113, "step": 828 }, { "epoch": 3.357974683544304, "grad_norm": 0.36257545988365353, "learning_rate": 1.161198884952377e-05, "loss": 0.1978, "step": 829 }, { "epoch": 3.3620253164556964, "grad_norm": 0.3807351634197303, "learning_rate": 1.1560497098679056e-05, "loss": 0.1976, "step": 830 }, { "epoch": 3.3660759493670884, "grad_norm": 0.37426448039620047, "learning_rate": 1.1509073318430479e-05, "loss": 0.2279, "step": 831 }, { "epoch": 3.370126582278481, "grad_norm": 0.3652494150295617, "learning_rate": 1.1457717922938116e-05, "loss": 0.244, "step": 832 }, { "epoch": 3.3741772151898735, "grad_norm": 0.37821156607703404, "learning_rate": 1.1406431325811233e-05, "loss": 0.2376, "step": 833 }, { "epoch": 3.378227848101266, "grad_norm": 0.37740893021707383, "learning_rate": 1.135521394010506e-05, "loss": 0.2254, "step": 834 }, { "epoch": 3.382278481012658, "grad_norm": 0.38381884314342757, "learning_rate": 1.1304066178317367e-05, "loss": 0.2404, "step": 835 }, { "epoch": 3.3863291139240506, "grad_norm": 0.3727518683799057, "learning_rate": 1.1252988452385199e-05, "loss": 0.2079, "step": 836 }, { "epoch": 3.390379746835443, "grad_norm": 0.36859797532633726, "learning_rate": 1.1201981173681536e-05, "loss": 0.2131, "step": 837 }, { "epoch": 3.3944303797468356, "grad_norm": 0.37269392288648917, "learning_rate": 1.1151044753011991e-05, "loss": 0.2309, "step": 838 }, { "epoch": 3.3984810126582277, "grad_norm": 0.3768421573987143, "learning_rate": 1.1100179600611491e-05, "loss": 0.2235, "step": 839 }, { "epoch": 3.40253164556962, "grad_norm": 0.3813709872916844, "learning_rate": 1.1049386126140985e-05, "loss": 0.2211, "step": 840 }, { "epoch": 3.4065822784810127, "grad_norm": 0.35223029503231235, "learning_rate": 1.0998664738684128e-05, "loss": 0.2244, "step": 841 }, { "epoch": 3.410632911392405, "grad_norm": 0.37362070980475914, "learning_rate": 1.0948015846744e-05, "loss": 0.1971, "step": 842 }, { "epoch": 3.4146835443037973, "grad_norm": 0.37448573473029484, "learning_rate": 1.0897439858239832e-05, "loss": 0.2263, "step": 843 }, { "epoch": 3.41873417721519, "grad_norm": 0.3606355882722779, "learning_rate": 1.0846937180503652e-05, "loss": 0.2225, "step": 844 }, { "epoch": 3.4227848101265823, "grad_norm": 0.3670186305045252, "learning_rate": 1.0796508220277117e-05, "loss": 0.2271, "step": 845 }, { "epoch": 3.426835443037975, "grad_norm": 0.3558420011905422, "learning_rate": 1.0746153383708107e-05, "loss": 0.2059, "step": 846 }, { "epoch": 3.430886075949367, "grad_norm": 0.3763601371531875, "learning_rate": 1.0695873076347579e-05, "loss": 0.2228, "step": 847 }, { "epoch": 3.4349367088607594, "grad_norm": 0.37013532119753784, "learning_rate": 1.0645667703146205e-05, "loss": 0.2139, "step": 848 }, { "epoch": 3.438987341772152, "grad_norm": 0.37164048022661167, "learning_rate": 1.0595537668451161e-05, "loss": 0.1986, "step": 849 }, { "epoch": 3.4430379746835444, "grad_norm": 0.3902975842456337, "learning_rate": 1.0545483376002854e-05, "loss": 0.2062, "step": 850 }, { "epoch": 3.4470886075949365, "grad_norm": 0.38297604055699525, "learning_rate": 1.0495505228931676e-05, "loss": 0.2061, "step": 851 }, { "epoch": 3.451139240506329, "grad_norm": 0.3659977560759588, "learning_rate": 1.044560362975474e-05, "loss": 0.2118, "step": 852 }, { "epoch": 3.4551898734177215, "grad_norm": 0.3731344758920211, "learning_rate": 1.0395778980372695e-05, "loss": 0.2034, "step": 853 }, { "epoch": 3.459240506329114, "grad_norm": 0.3688066837449616, "learning_rate": 1.0346031682066381e-05, "loss": 0.2241, "step": 854 }, { "epoch": 3.463291139240506, "grad_norm": 0.3793778394719784, "learning_rate": 1.0296362135493724e-05, "loss": 0.234, "step": 855 }, { "epoch": 3.4673417721518986, "grad_norm": 0.3670089795245891, "learning_rate": 1.0246770740686422e-05, "loss": 0.2268, "step": 856 }, { "epoch": 3.471392405063291, "grad_norm": 0.3529377272016234, "learning_rate": 1.0197257897046743e-05, "loss": 0.2074, "step": 857 }, { "epoch": 3.4754430379746837, "grad_norm": 0.3732161934431868, "learning_rate": 1.014782400334433e-05, "loss": 0.204, "step": 858 }, { "epoch": 3.479493670886076, "grad_norm": 0.37255979883708945, "learning_rate": 1.009846945771296e-05, "loss": 0.2276, "step": 859 }, { "epoch": 3.4835443037974683, "grad_norm": 0.3861437716869687, "learning_rate": 1.0049194657647363e-05, "loss": 0.2097, "step": 860 }, { "epoch": 3.487594936708861, "grad_norm": 0.3716017527475694, "learning_rate": 1.0000000000000006e-05, "loss": 0.2128, "step": 861 }, { "epoch": 3.4916455696202533, "grad_norm": 0.36822156260190164, "learning_rate": 9.950885880977891e-06, "loss": 0.1958, "step": 862 }, { "epoch": 3.4956962025316454, "grad_norm": 0.37083508705879376, "learning_rate": 9.901852696139382e-06, "loss": 0.2371, "step": 863 }, { "epoch": 3.499746835443038, "grad_norm": 0.3867094866429861, "learning_rate": 9.852900840391027e-06, "loss": 0.2003, "step": 864 }, { "epoch": 3.5037974683544304, "grad_norm": 0.3506288167678988, "learning_rate": 9.804030707984313e-06, "loss": 0.2311, "step": 865 }, { "epoch": 3.507848101265823, "grad_norm": 0.3636858763226978, "learning_rate": 9.755242692512599e-06, "loss": 0.2112, "step": 866 }, { "epoch": 3.5118987341772154, "grad_norm": 0.35702463770886983, "learning_rate": 9.70653718690782e-06, "loss": 0.2455, "step": 867 }, { "epoch": 3.5159493670886075, "grad_norm": 0.36671907442061485, "learning_rate": 9.657914583437454e-06, "loss": 0.2272, "step": 868 }, { "epoch": 3.52, "grad_norm": 0.36487437992074007, "learning_rate": 9.609375273701246e-06, "loss": 0.222, "step": 869 }, { "epoch": 3.5240506329113925, "grad_norm": 0.3548354644106794, "learning_rate": 9.560919648628133e-06, "loss": 0.2408, "step": 870 }, { "epoch": 3.5281012658227846, "grad_norm": 0.3568054682518671, "learning_rate": 9.512548098473047e-06, "loss": 0.2242, "step": 871 }, { "epoch": 3.532151898734177, "grad_norm": 0.371003733145476, "learning_rate": 9.464261012813825e-06, "loss": 0.2252, "step": 872 }, { "epoch": 3.5362025316455696, "grad_norm": 0.38606421284929365, "learning_rate": 9.416058780547987e-06, "loss": 0.2149, "step": 873 }, { "epoch": 3.540253164556962, "grad_norm": 0.362535373449549, "learning_rate": 9.367941789889714e-06, "loss": 0.2466, "step": 874 }, { "epoch": 3.5443037974683547, "grad_norm": 0.37215785173059396, "learning_rate": 9.319910428366607e-06, "loss": 0.2309, "step": 875 }, { "epoch": 3.5483544303797467, "grad_norm": 0.3640966079530545, "learning_rate": 9.271965082816667e-06, "loss": 0.1884, "step": 876 }, { "epoch": 3.5524050632911393, "grad_norm": 0.369285727416333, "learning_rate": 9.224106139385111e-06, "loss": 0.2001, "step": 877 }, { "epoch": 3.5564556962025318, "grad_norm": 0.3804293294460493, "learning_rate": 9.176333983521291e-06, "loss": 0.2377, "step": 878 }, { "epoch": 3.560506329113924, "grad_norm": 0.3764921496614701, "learning_rate": 9.12864899997558e-06, "loss": 0.1907, "step": 879 }, { "epoch": 3.5645569620253164, "grad_norm": 0.3475758221888143, "learning_rate": 9.08105157279628e-06, "loss": 0.2125, "step": 880 }, { "epoch": 3.568607594936709, "grad_norm": 0.37333540547458716, "learning_rate": 9.03354208532653e-06, "loss": 0.2224, "step": 881 }, { "epoch": 3.5726582278481014, "grad_norm": 0.37241295074986336, "learning_rate": 8.986120920201205e-06, "loss": 0.2228, "step": 882 }, { "epoch": 3.576708860759494, "grad_norm": 0.35873826993872965, "learning_rate": 8.938788459343852e-06, "loss": 0.222, "step": 883 }, { "epoch": 3.580759493670886, "grad_norm": 0.3614810831609748, "learning_rate": 8.8915450839636e-06, "loss": 0.2046, "step": 884 }, { "epoch": 3.5848101265822785, "grad_norm": 0.345475690664218, "learning_rate": 8.844391174552116e-06, "loss": 0.2154, "step": 885 }, { "epoch": 3.588860759493671, "grad_norm": 0.360168397544251, "learning_rate": 8.797327110880479e-06, "loss": 0.2206, "step": 886 }, { "epoch": 3.592911392405063, "grad_norm": 0.37233946814837515, "learning_rate": 8.750353271996206e-06, "loss": 0.213, "step": 887 }, { "epoch": 3.5969620253164556, "grad_norm": 0.4293808289297878, "learning_rate": 8.703470036220132e-06, "loss": 0.2211, "step": 888 }, { "epoch": 3.601012658227848, "grad_norm": 0.3669590524477367, "learning_rate": 8.656677781143394e-06, "loss": 0.1957, "step": 889 }, { "epoch": 3.6050632911392406, "grad_norm": 0.36384485187354587, "learning_rate": 8.609976883624377e-06, "loss": 0.2479, "step": 890 }, { "epoch": 3.609113924050633, "grad_norm": 0.3575370159227776, "learning_rate": 8.563367719785698e-06, "loss": 0.2018, "step": 891 }, { "epoch": 3.613164556962025, "grad_norm": 0.3703822931499657, "learning_rate": 8.516850665011138e-06, "loss": 0.2376, "step": 892 }, { "epoch": 3.6172151898734177, "grad_norm": 0.3696520883274806, "learning_rate": 8.47042609394269e-06, "loss": 0.2227, "step": 893 }, { "epoch": 3.6212658227848102, "grad_norm": 0.35875391504890913, "learning_rate": 8.424094380477432e-06, "loss": 0.2015, "step": 894 }, { "epoch": 3.6253164556962023, "grad_norm": 0.36813708929404604, "learning_rate": 8.37785589776465e-06, "loss": 0.2246, "step": 895 }, { "epoch": 3.629367088607595, "grad_norm": 0.3705862526429583, "learning_rate": 8.331711018202694e-06, "loss": 0.2072, "step": 896 }, { "epoch": 3.6334177215189873, "grad_norm": 0.3616041428580799, "learning_rate": 8.285660113436104e-06, "loss": 0.2136, "step": 897 }, { "epoch": 3.63746835443038, "grad_norm": 0.36529520747138494, "learning_rate": 8.239703554352527e-06, "loss": 0.2212, "step": 898 }, { "epoch": 3.6415189873417724, "grad_norm": 0.3728013745423025, "learning_rate": 8.193841711079775e-06, "loss": 0.2317, "step": 899 }, { "epoch": 3.6455696202531644, "grad_norm": 0.34201232476934074, "learning_rate": 8.148074952982828e-06, "loss": 0.2183, "step": 900 }, { "epoch": 3.649620253164557, "grad_norm": 0.3572383879924341, "learning_rate": 8.102403648660859e-06, "loss": 0.2188, "step": 901 }, { "epoch": 3.6536708860759495, "grad_norm": 0.352053940192906, "learning_rate": 8.056828165944282e-06, "loss": 0.2393, "step": 902 }, { "epoch": 3.6577215189873415, "grad_norm": 0.3596698640719156, "learning_rate": 8.011348871891762e-06, "loss": 0.2064, "step": 903 }, { "epoch": 3.661772151898734, "grad_norm": 0.3718015965360058, "learning_rate": 7.965966132787287e-06, "loss": 0.2239, "step": 904 }, { "epoch": 3.6658227848101266, "grad_norm": 0.3873503809392087, "learning_rate": 7.920680314137189e-06, "loss": 0.2375, "step": 905 }, { "epoch": 3.669873417721519, "grad_norm": 0.380665615461963, "learning_rate": 7.875491780667246e-06, "loss": 0.2087, "step": 906 }, { "epoch": 3.6739240506329116, "grad_norm": 0.36106428443263894, "learning_rate": 7.830400896319667e-06, "loss": 0.2107, "step": 907 }, { "epoch": 3.6779746835443037, "grad_norm": 0.36797939950037184, "learning_rate": 7.785408024250259e-06, "loss": 0.211, "step": 908 }, { "epoch": 3.682025316455696, "grad_norm": 0.3505295242055551, "learning_rate": 7.74051352682542e-06, "loss": 0.2119, "step": 909 }, { "epoch": 3.6860759493670887, "grad_norm": 0.37301286439604897, "learning_rate": 7.695717765619257e-06, "loss": 0.2045, "step": 910 }, { "epoch": 3.690126582278481, "grad_norm": 0.36519772681229284, "learning_rate": 7.651021101410673e-06, "loss": 0.218, "step": 911 }, { "epoch": 3.6941772151898733, "grad_norm": 0.35891459647566043, "learning_rate": 7.606423894180464e-06, "loss": 0.2215, "step": 912 }, { "epoch": 3.698227848101266, "grad_norm": 0.38044887311758396, "learning_rate": 7.56192650310839e-06, "loss": 0.219, "step": 913 }, { "epoch": 3.7022784810126583, "grad_norm": 0.36885740007834017, "learning_rate": 7.517529286570349e-06, "loss": 0.2188, "step": 914 }, { "epoch": 3.706329113924051, "grad_norm": 0.3658816745293446, "learning_rate": 7.473232602135387e-06, "loss": 0.2239, "step": 915 }, { "epoch": 3.710379746835443, "grad_norm": 0.37192322059285166, "learning_rate": 7.429036806562935e-06, "loss": 0.2273, "step": 916 }, { "epoch": 3.7144303797468354, "grad_norm": 0.37312428100174266, "learning_rate": 7.3849422557998455e-06, "loss": 0.241, "step": 917 }, { "epoch": 3.718481012658228, "grad_norm": 0.36298765211112294, "learning_rate": 7.340949304977567e-06, "loss": 0.2171, "step": 918 }, { "epoch": 3.72253164556962, "grad_norm": 0.36395953089180383, "learning_rate": 7.297058308409282e-06, "loss": 0.2194, "step": 919 }, { "epoch": 3.7265822784810125, "grad_norm": 0.3547052676780192, "learning_rate": 7.25326961958704e-06, "loss": 0.215, "step": 920 }, { "epoch": 3.730632911392405, "grad_norm": 0.3689503232584222, "learning_rate": 7.209583591178921e-06, "loss": 0.2155, "step": 921 }, { "epoch": 3.7346835443037976, "grad_norm": 0.36748221544657383, "learning_rate": 7.1660005750261925e-06, "loss": 0.2117, "step": 922 }, { "epoch": 3.73873417721519, "grad_norm": 0.36028272936405714, "learning_rate": 7.1225209221404765e-06, "loss": 0.2368, "step": 923 }, { "epoch": 3.742784810126582, "grad_norm": 0.38848997234236277, "learning_rate": 7.079144982700909e-06, "loss": 0.2218, "step": 924 }, { "epoch": 3.7468354430379747, "grad_norm": 0.37155754381598366, "learning_rate": 7.0358731060513695e-06, "loss": 0.1997, "step": 925 }, { "epoch": 3.750886075949367, "grad_norm": 0.3596333521364935, "learning_rate": 6.99270564069757e-06, "loss": 0.2224, "step": 926 }, { "epoch": 3.7549367088607593, "grad_norm": 0.35470441106999834, "learning_rate": 6.949642934304375e-06, "loss": 0.2193, "step": 927 }, { "epoch": 3.7589873417721518, "grad_norm": 0.3700829652693974, "learning_rate": 6.906685333692871e-06, "loss": 0.2121, "step": 928 }, { "epoch": 3.7630379746835443, "grad_norm": 0.36506587294742593, "learning_rate": 6.86383318483769e-06, "loss": 0.1907, "step": 929 }, { "epoch": 3.767088607594937, "grad_norm": 0.35942877199860124, "learning_rate": 6.821086832864139e-06, "loss": 0.2105, "step": 930 }, { "epoch": 3.7711392405063293, "grad_norm": 0.35535098066171755, "learning_rate": 6.77844662204546e-06, "loss": 0.2194, "step": 931 }, { "epoch": 3.7751898734177214, "grad_norm": 0.35883149919636664, "learning_rate": 6.7359128958000455e-06, "loss": 0.2191, "step": 932 }, { "epoch": 3.779240506329114, "grad_norm": 0.35428454661724573, "learning_rate": 6.693485996688695e-06, "loss": 0.2114, "step": 933 }, { "epoch": 3.7832911392405064, "grad_norm": 0.352877509008566, "learning_rate": 6.651166266411801e-06, "loss": 0.1829, "step": 934 }, { "epoch": 3.7873417721518985, "grad_norm": 0.35329852978962534, "learning_rate": 6.6089540458066725e-06, "loss": 0.1994, "step": 935 }, { "epoch": 3.791392405063291, "grad_norm": 0.3691648600422784, "learning_rate": 6.566849674844711e-06, "loss": 0.1685, "step": 936 }, { "epoch": 3.7954430379746835, "grad_norm": 0.354500348568206, "learning_rate": 6.524853492628747e-06, "loss": 0.2161, "step": 937 }, { "epoch": 3.799493670886076, "grad_norm": 0.369880027085605, "learning_rate": 6.4829658373902536e-06, "loss": 0.2144, "step": 938 }, { "epoch": 3.8035443037974686, "grad_norm": 0.37272939471806654, "learning_rate": 6.441187046486648e-06, "loss": 0.2023, "step": 939 }, { "epoch": 3.8075949367088606, "grad_norm": 0.3803847661367527, "learning_rate": 6.399517456398567e-06, "loss": 0.2077, "step": 940 }, { "epoch": 3.811645569620253, "grad_norm": 0.3592364179939384, "learning_rate": 6.357957402727164e-06, "loss": 0.2194, "step": 941 }, { "epoch": 3.8156962025316457, "grad_norm": 0.36146603604462035, "learning_rate": 6.316507220191395e-06, "loss": 0.2147, "step": 942 }, { "epoch": 3.8197468354430377, "grad_norm": 0.3626116398275795, "learning_rate": 6.275167242625331e-06, "loss": 0.2093, "step": 943 }, { "epoch": 3.8237974683544302, "grad_norm": 0.355211100550123, "learning_rate": 6.233937802975471e-06, "loss": 0.2141, "step": 944 }, { "epoch": 3.8278481012658228, "grad_norm": 0.354985839699917, "learning_rate": 6.192819233298046e-06, "loss": 0.2049, "step": 945 }, { "epoch": 3.8318987341772153, "grad_norm": 0.36115953534519624, "learning_rate": 6.151811864756383e-06, "loss": 0.1988, "step": 946 }, { "epoch": 3.835949367088608, "grad_norm": 0.35882381688188514, "learning_rate": 6.1109160276181655e-06, "loss": 0.1913, "step": 947 }, { "epoch": 3.84, "grad_norm": 0.3685520926909103, "learning_rate": 6.070132051252868e-06, "loss": 0.2154, "step": 948 }, { "epoch": 3.8440506329113924, "grad_norm": 0.3761146694422308, "learning_rate": 6.0294602641290034e-06, "loss": 0.1988, "step": 949 }, { "epoch": 3.848101265822785, "grad_norm": 0.3507373773672799, "learning_rate": 5.988900993811575e-06, "loss": 0.2012, "step": 950 }, { "epoch": 3.852151898734177, "grad_norm": 0.3543916267930478, "learning_rate": 5.948454566959363e-06, "loss": 0.2302, "step": 951 }, { "epoch": 3.8562025316455695, "grad_norm": 0.3491239706511343, "learning_rate": 5.908121309322328e-06, "loss": 0.2099, "step": 952 }, { "epoch": 3.860253164556962, "grad_norm": 0.3485527828997989, "learning_rate": 5.867901545738976e-06, "loss": 0.1987, "step": 953 }, { "epoch": 3.8643037974683545, "grad_norm": 0.35730172559449197, "learning_rate": 5.827795600133774e-06, "loss": 0.2194, "step": 954 }, { "epoch": 3.868354430379747, "grad_norm": 0.3536093069882929, "learning_rate": 5.787803795514466e-06, "loss": 0.2207, "step": 955 }, { "epoch": 3.872405063291139, "grad_norm": 0.3615285146688458, "learning_rate": 5.747926453969576e-06, "loss": 0.2329, "step": 956 }, { "epoch": 3.8764556962025316, "grad_norm": 0.34068208701256847, "learning_rate": 5.708163896665708e-06, "loss": 0.2019, "step": 957 }, { "epoch": 3.880506329113924, "grad_norm": 0.3428263634255573, "learning_rate": 5.668516443845047e-06, "loss": 0.2229, "step": 958 }, { "epoch": 3.884556962025316, "grad_norm": 0.33856673851974656, "learning_rate": 5.6289844148227225e-06, "loss": 0.2076, "step": 959 }, { "epoch": 3.8886075949367087, "grad_norm": 0.37104175641852527, "learning_rate": 5.5895681279842615e-06, "loss": 0.217, "step": 960 }, { "epoch": 3.8926582278481012, "grad_norm": 0.3584951315299229, "learning_rate": 5.550267900783019e-06, "loss": 0.235, "step": 961 }, { "epoch": 3.8967088607594937, "grad_norm": 0.34918032184688863, "learning_rate": 5.511084049737623e-06, "loss": 0.1957, "step": 962 }, { "epoch": 3.9007594936708863, "grad_norm": 0.3585970257800184, "learning_rate": 5.4720168904294215e-06, "loss": 0.213, "step": 963 }, { "epoch": 3.9048101265822783, "grad_norm": 0.3676928526831861, "learning_rate": 5.433066737499948e-06, "loss": 0.1864, "step": 964 }, { "epoch": 3.908860759493671, "grad_norm": 0.3626051530282238, "learning_rate": 5.394233904648376e-06, "loss": 0.2173, "step": 965 }, { "epoch": 3.9129113924050634, "grad_norm": 0.3551917929798552, "learning_rate": 5.355518704628997e-06, "loss": 0.2031, "step": 966 }, { "epoch": 3.9169620253164554, "grad_norm": 0.3335565469006917, "learning_rate": 5.316921449248731e-06, "loss": 0.2197, "step": 967 }, { "epoch": 3.921012658227848, "grad_norm": 0.346614996221909, "learning_rate": 5.278442449364538e-06, "loss": 0.2163, "step": 968 }, { "epoch": 3.9250632911392405, "grad_norm": 0.365042035310353, "learning_rate": 5.240082014881016e-06, "loss": 0.1934, "step": 969 }, { "epoch": 3.929113924050633, "grad_norm": 0.3582107739808749, "learning_rate": 5.201840454747822e-06, "loss": 0.1971, "step": 970 }, { "epoch": 3.9331645569620255, "grad_norm": 0.3524436123218363, "learning_rate": 5.163718076957223e-06, "loss": 0.2108, "step": 971 }, { "epoch": 3.9372151898734176, "grad_norm": 0.3614340091631595, "learning_rate": 5.125715188541609e-06, "loss": 0.2221, "step": 972 }, { "epoch": 3.94126582278481, "grad_norm": 0.3606225131164546, "learning_rate": 5.087832095571021e-06, "loss": 0.1902, "step": 973 }, { "epoch": 3.9453164556962026, "grad_norm": 0.3481100998449664, "learning_rate": 5.0500691031506766e-06, "loss": 0.2167, "step": 974 }, { "epoch": 3.9493670886075947, "grad_norm": 0.35525664016375114, "learning_rate": 5.01242651541854e-06, "loss": 0.1891, "step": 975 }, { "epoch": 3.953417721518987, "grad_norm": 0.3574167836618765, "learning_rate": 4.974904635542815e-06, "loss": 0.2008, "step": 976 }, { "epoch": 3.9574683544303797, "grad_norm": 0.35732813340520925, "learning_rate": 4.937503765719582e-06, "loss": 0.1996, "step": 977 }, { "epoch": 3.961518987341772, "grad_norm": 0.369362637716189, "learning_rate": 4.900224207170299e-06, "loss": 0.211, "step": 978 }, { "epoch": 3.9655696202531647, "grad_norm": 0.3570320852237364, "learning_rate": 4.8630662601394065e-06, "loss": 0.2142, "step": 979 }, { "epoch": 3.969620253164557, "grad_norm": 0.3619752981813516, "learning_rate": 4.8260302238918995e-06, "loss": 0.2158, "step": 980 }, { "epoch": 3.9736708860759493, "grad_norm": 0.3671439896874569, "learning_rate": 4.789116396710924e-06, "loss": 0.2276, "step": 981 }, { "epoch": 3.977721518987342, "grad_norm": 0.3625868268376129, "learning_rate": 4.752325075895368e-06, "loss": 0.1976, "step": 982 }, { "epoch": 3.981772151898734, "grad_norm": 0.35920874943823955, "learning_rate": 4.715656557757473e-06, "loss": 0.2126, "step": 983 }, { "epoch": 3.9858227848101264, "grad_norm": 0.3645278920600121, "learning_rate": 4.679111137620442e-06, "loss": 0.2311, "step": 984 }, { "epoch": 3.989873417721519, "grad_norm": 0.36139371451864755, "learning_rate": 4.6426891098160585e-06, "loss": 0.1969, "step": 985 }, { "epoch": 3.9939240506329114, "grad_norm": 0.35970307364584425, "learning_rate": 4.6063907676823474e-06, "loss": 0.204, "step": 986 }, { "epoch": 3.997974683544304, "grad_norm": 0.3423337253791574, "learning_rate": 4.570216403561141e-06, "loss": 0.1989, "step": 987 }, { "epoch": 4.002025316455696, "grad_norm": 0.3460438536037461, "learning_rate": 4.534166308795815e-06, "loss": 0.1934, "step": 988 }, { "epoch": 4.006075949367089, "grad_norm": 0.43502415315357823, "learning_rate": 4.498240773728859e-06, "loss": 0.1722, "step": 989 }, { "epoch": 4.010126582278481, "grad_norm": 0.34755349955622705, "learning_rate": 4.462440087699609e-06, "loss": 0.1704, "step": 990 }, { "epoch": 4.014177215189873, "grad_norm": 0.3003523514337882, "learning_rate": 4.426764539041861e-06, "loss": 0.162, "step": 991 }, { "epoch": 4.018227848101266, "grad_norm": 0.2779994877137451, "learning_rate": 4.391214415081582e-06, "loss": 0.16, "step": 992 }, { "epoch": 4.022278481012658, "grad_norm": 0.3138401570044041, "learning_rate": 4.355790002134579e-06, "loss": 0.1726, "step": 993 }, { "epoch": 4.02632911392405, "grad_norm": 0.36386711384999165, "learning_rate": 4.320491585504207e-06, "loss": 0.1575, "step": 994 }, { "epoch": 4.030379746835443, "grad_norm": 0.40917868071192937, "learning_rate": 4.2853194494790615e-06, "loss": 0.1672, "step": 995 }, { "epoch": 4.034430379746835, "grad_norm": 0.40283710616935264, "learning_rate": 4.250273877330691e-06, "loss": 0.164, "step": 996 }, { "epoch": 4.038481012658228, "grad_norm": 0.3194088389331393, "learning_rate": 4.215355151311313e-06, "loss": 0.1411, "step": 997 }, { "epoch": 4.04253164556962, "grad_norm": 0.311733808094645, "learning_rate": 4.180563552651542e-06, "loss": 0.1557, "step": 998 }, { "epoch": 4.046582278481012, "grad_norm": 0.3199172103150692, "learning_rate": 4.145899361558147e-06, "loss": 0.1492, "step": 999 }, { "epoch": 4.050632911392405, "grad_norm": 0.32137386388363737, "learning_rate": 4.111362857211738e-06, "loss": 0.1416, "step": 1000 }, { "epoch": 4.054683544303797, "grad_norm": 0.33943469771353163, "learning_rate": 4.076954317764592e-06, "loss": 0.173, "step": 1001 }, { "epoch": 4.0587341772151895, "grad_norm": 0.3418571715403082, "learning_rate": 4.042674020338335e-06, "loss": 0.1587, "step": 1002 }, { "epoch": 4.062784810126582, "grad_norm": 0.32056791669425205, "learning_rate": 4.0085222410217835e-06, "loss": 0.1372, "step": 1003 }, { "epoch": 4.0668354430379745, "grad_norm": 0.2805181154666157, "learning_rate": 3.974499254868674e-06, "loss": 0.1326, "step": 1004 }, { "epoch": 4.0708860759493675, "grad_norm": 0.2803675775375474, "learning_rate": 3.940605335895451e-06, "loss": 0.1367, "step": 1005 }, { "epoch": 4.0749367088607595, "grad_norm": 0.27793411218436226, "learning_rate": 3.90684075707908e-06, "loss": 0.1351, "step": 1006 }, { "epoch": 4.078987341772152, "grad_norm": 0.3442474478360219, "learning_rate": 3.8732057903548505e-06, "loss": 0.1495, "step": 1007 }, { "epoch": 4.083037974683545, "grad_norm": 0.30436265924698913, "learning_rate": 3.8397007066141375e-06, "loss": 0.1514, "step": 1008 }, { "epoch": 4.087088607594937, "grad_norm": 0.3184823288208169, "learning_rate": 3.806325775702304e-06, "loss": 0.1478, "step": 1009 }, { "epoch": 4.091139240506329, "grad_norm": 0.3044112593517142, "learning_rate": 3.773081266416434e-06, "loss": 0.1616, "step": 1010 }, { "epoch": 4.095189873417722, "grad_norm": 0.29980068988974323, "learning_rate": 3.739967446503245e-06, "loss": 0.1747, "step": 1011 }, { "epoch": 4.099240506329114, "grad_norm": 0.2726021109501018, "learning_rate": 3.706984582656894e-06, "loss": 0.1686, "step": 1012 }, { "epoch": 4.103291139240507, "grad_norm": 0.2683476365009089, "learning_rate": 3.6741329405168237e-06, "loss": 0.1612, "step": 1013 }, { "epoch": 4.107341772151899, "grad_norm": 0.2873017698115637, "learning_rate": 3.641412784665648e-06, "loss": 0.1514, "step": 1014 }, { "epoch": 4.111392405063291, "grad_norm": 0.28560381258740325, "learning_rate": 3.608824378627005e-06, "loss": 0.1558, "step": 1015 }, { "epoch": 4.115443037974684, "grad_norm": 0.28015817451371045, "learning_rate": 3.5763679848634337e-06, "loss": 0.1642, "step": 1016 }, { "epoch": 4.119493670886076, "grad_norm": 0.287558269390876, "learning_rate": 3.544043864774269e-06, "loss": 0.1463, "step": 1017 }, { "epoch": 4.123544303797468, "grad_norm": 0.27816297333525436, "learning_rate": 3.5118522786935282e-06, "loss": 0.1718, "step": 1018 }, { "epoch": 4.127594936708861, "grad_norm": 0.27596806625733844, "learning_rate": 3.479793485887819e-06, "loss": 0.1596, "step": 1019 }, { "epoch": 4.131645569620253, "grad_norm": 0.28270114985824485, "learning_rate": 3.4478677445542653e-06, "loss": 0.1436, "step": 1020 }, { "epoch": 4.135696202531646, "grad_norm": 0.2764347222016774, "learning_rate": 3.4160753118183767e-06, "loss": 0.1642, "step": 1021 }, { "epoch": 4.139746835443038, "grad_norm": 0.28872376257840326, "learning_rate": 3.3844164437320527e-06, "loss": 0.1581, "step": 1022 }, { "epoch": 4.14379746835443, "grad_norm": 0.27190713212899453, "learning_rate": 3.3528913952714558e-06, "loss": 0.1396, "step": 1023 }, { "epoch": 4.147848101265823, "grad_norm": 0.28055870365785934, "learning_rate": 3.321500420335e-06, "loss": 0.1784, "step": 1024 }, { "epoch": 4.151898734177215, "grad_norm": 0.29054661780893865, "learning_rate": 3.290243771741275e-06, "loss": 0.175, "step": 1025 }, { "epoch": 4.155949367088607, "grad_norm": 0.2942408820119366, "learning_rate": 3.2591217012270325e-06, "loss": 0.1677, "step": 1026 }, { "epoch": 4.16, "grad_norm": 0.2555454226145166, "learning_rate": 3.228134459445149e-06, "loss": 0.1538, "step": 1027 }, { "epoch": 4.164050632911392, "grad_norm": 0.2796643608729421, "learning_rate": 3.1972822959626205e-06, "loss": 0.1704, "step": 1028 }, { "epoch": 4.168101265822785, "grad_norm": 0.268130168890299, "learning_rate": 3.166565459258513e-06, "loss": 0.1613, "step": 1029 }, { "epoch": 4.172151898734177, "grad_norm": 0.2672233857809391, "learning_rate": 3.1359841967220193e-06, "loss": 0.1681, "step": 1030 }, { "epoch": 4.176202531645569, "grad_norm": 0.26547969514966024, "learning_rate": 3.105538754650419e-06, "loss": 0.1475, "step": 1031 }, { "epoch": 4.180253164556962, "grad_norm": 0.26815224014345534, "learning_rate": 3.07522937824712e-06, "loss": 0.1371, "step": 1032 }, { "epoch": 4.184303797468354, "grad_norm": 0.28683802624983207, "learning_rate": 3.0450563116196697e-06, "loss": 0.1743, "step": 1033 }, { "epoch": 4.188354430379746, "grad_norm": 0.27410031722625333, "learning_rate": 3.0150197977778008e-06, "loss": 0.1399, "step": 1034 }, { "epoch": 4.192405063291139, "grad_norm": 0.2668419272159192, "learning_rate": 2.985120078631465e-06, "loss": 0.1553, "step": 1035 }, { "epoch": 4.1964556962025314, "grad_norm": 0.25654266053956154, "learning_rate": 2.9553573949888893e-06, "loss": 0.1274, "step": 1036 }, { "epoch": 4.200506329113924, "grad_norm": 0.27034549769498945, "learning_rate": 2.9257319865546384e-06, "loss": 0.1818, "step": 1037 }, { "epoch": 4.2045569620253165, "grad_norm": 0.26872619796525193, "learning_rate": 2.896244091927678e-06, "loss": 0.152, "step": 1038 }, { "epoch": 4.2086075949367086, "grad_norm": 0.2761753744153625, "learning_rate": 2.8668939485994584e-06, "loss": 0.1387, "step": 1039 }, { "epoch": 4.2126582278481015, "grad_norm": 0.27777322930152193, "learning_rate": 2.837681792951994e-06, "loss": 0.1591, "step": 1040 }, { "epoch": 4.216708860759494, "grad_norm": 0.2562830054434623, "learning_rate": 2.808607860255981e-06, "loss": 0.1613, "step": 1041 }, { "epoch": 4.220759493670886, "grad_norm": 0.2717841009210779, "learning_rate": 2.7796723846688634e-06, "loss": 0.1463, "step": 1042 }, { "epoch": 4.224810126582279, "grad_norm": 0.2612610767672185, "learning_rate": 2.7508755992329937e-06, "loss": 0.1568, "step": 1043 }, { "epoch": 4.228860759493671, "grad_norm": 0.2603112014754713, "learning_rate": 2.722217735873718e-06, "loss": 0.1418, "step": 1044 }, { "epoch": 4.232911392405064, "grad_norm": 0.2660814254872195, "learning_rate": 2.6936990253975315e-06, "loss": 0.1536, "step": 1045 }, { "epoch": 4.236962025316456, "grad_norm": 0.25184939355177555, "learning_rate": 2.665319697490205e-06, "loss": 0.1396, "step": 1046 }, { "epoch": 4.241012658227848, "grad_norm": 0.25232117436161655, "learning_rate": 2.637079980714945e-06, "loss": 0.1423, "step": 1047 }, { "epoch": 4.245063291139241, "grad_norm": 0.26631199689652996, "learning_rate": 2.6089801025105453e-06, "loss": 0.1304, "step": 1048 }, { "epoch": 4.249113924050633, "grad_norm": 0.2733050547439414, "learning_rate": 2.581020289189571e-06, "loss": 0.1469, "step": 1049 }, { "epoch": 4.253164556962025, "grad_norm": 0.2722564778847879, "learning_rate": 2.553200765936501e-06, "loss": 0.173, "step": 1050 }, { "epoch": 4.257215189873418, "grad_norm": 0.26906760365339666, "learning_rate": 2.525521756805962e-06, "loss": 0.1625, "step": 1051 }, { "epoch": 4.26126582278481, "grad_norm": 0.2805658535958119, "learning_rate": 2.497983484720885e-06, "loss": 0.1527, "step": 1052 }, { "epoch": 4.265316455696203, "grad_norm": 0.26538886026499703, "learning_rate": 2.470586171470728e-06, "loss": 0.1304, "step": 1053 }, { "epoch": 4.269367088607595, "grad_norm": 0.26575651258567506, "learning_rate": 2.4433300377096836e-06, "loss": 0.1457, "step": 1054 }, { "epoch": 4.273417721518987, "grad_norm": 0.2626909136438915, "learning_rate": 2.4162153029549073e-06, "loss": 0.1467, "step": 1055 }, { "epoch": 4.27746835443038, "grad_norm": 0.2838858180970347, "learning_rate": 2.3892421855847458e-06, "loss": 0.1429, "step": 1056 }, { "epoch": 4.281518987341772, "grad_norm": 0.2585464150212323, "learning_rate": 2.362410902836978e-06, "loss": 0.1599, "step": 1057 }, { "epoch": 4.285569620253165, "grad_norm": 0.2820485489852442, "learning_rate": 2.3357216708070653e-06, "loss": 0.168, "step": 1058 }, { "epoch": 4.289620253164557, "grad_norm": 0.26867122200397037, "learning_rate": 2.309174704446411e-06, "loss": 0.1518, "step": 1059 }, { "epoch": 4.293670886075949, "grad_norm": 0.2724325981786069, "learning_rate": 2.2827702175606437e-06, "loss": 0.1501, "step": 1060 }, { "epoch": 4.297721518987342, "grad_norm": 0.273900324624766, "learning_rate": 2.256508422807855e-06, "loss": 0.1822, "step": 1061 }, { "epoch": 4.301772151898734, "grad_norm": 0.2696072669349348, "learning_rate": 2.230389531696946e-06, "loss": 0.145, "step": 1062 }, { "epoch": 4.305822784810126, "grad_norm": 0.2706410501988951, "learning_rate": 2.204413754585857e-06, "loss": 0.1343, "step": 1063 }, { "epoch": 4.309873417721519, "grad_norm": 0.2565000655573423, "learning_rate": 2.1785813006799406e-06, "loss": 0.1581, "step": 1064 }, { "epoch": 4.313924050632911, "grad_norm": 0.2610278749120484, "learning_rate": 2.1528923780302224e-06, "loss": 0.1409, "step": 1065 }, { "epoch": 4.317974683544303, "grad_norm": 0.2588386461087395, "learning_rate": 2.127347193531757e-06, "loss": 0.1455, "step": 1066 }, { "epoch": 4.322025316455696, "grad_norm": 0.26511443149005515, "learning_rate": 2.101945952921942e-06, "loss": 0.1615, "step": 1067 }, { "epoch": 4.326075949367088, "grad_norm": 0.2576568450902808, "learning_rate": 2.0766888607788906e-06, "loss": 0.1399, "step": 1068 }, { "epoch": 4.330126582278481, "grad_norm": 0.2697812289405365, "learning_rate": 2.0515761205197337e-06, "loss": 0.1594, "step": 1069 }, { "epoch": 4.334177215189873, "grad_norm": 0.266166070639842, "learning_rate": 2.0266079343990453e-06, "loss": 0.1589, "step": 1070 }, { "epoch": 4.3382278481012655, "grad_norm": 0.2674402766522545, "learning_rate": 2.0017845035071494e-06, "loss": 0.166, "step": 1071 }, { "epoch": 4.3422784810126585, "grad_norm": 0.26560150900925367, "learning_rate": 1.9771060277685537e-06, "loss": 0.1353, "step": 1072 }, { "epoch": 4.3463291139240505, "grad_norm": 0.26029327907106903, "learning_rate": 1.95257270594031e-06, "loss": 0.1498, "step": 1073 }, { "epoch": 4.3503797468354435, "grad_norm": 0.2765441911115528, "learning_rate": 1.9281847356104188e-06, "loss": 0.1391, "step": 1074 }, { "epoch": 4.3544303797468356, "grad_norm": 0.25654102283024954, "learning_rate": 1.9039423131962365e-06, "loss": 0.1286, "step": 1075 }, { "epoch": 4.358481012658228, "grad_norm": 0.2671373171300295, "learning_rate": 1.8798456339429027e-06, "loss": 0.1666, "step": 1076 }, { "epoch": 4.362531645569621, "grad_norm": 0.27152929038243756, "learning_rate": 1.8558948919217612e-06, "loss": 0.1479, "step": 1077 }, { "epoch": 4.366582278481013, "grad_norm": 0.2640781681134849, "learning_rate": 1.8320902800287954e-06, "loss": 0.1421, "step": 1078 }, { "epoch": 4.370632911392405, "grad_norm": 0.26283058622581024, "learning_rate": 1.8084319899830726e-06, "loss": 0.1492, "step": 1079 }, { "epoch": 4.374683544303798, "grad_norm": 0.28550595409827956, "learning_rate": 1.7849202123252097e-06, "loss": 0.1774, "step": 1080 }, { "epoch": 4.37873417721519, "grad_norm": 0.27847557817607527, "learning_rate": 1.7615551364158401e-06, "loss": 0.1392, "step": 1081 }, { "epoch": 4.382784810126582, "grad_norm": 0.2706842205330614, "learning_rate": 1.738336950434061e-06, "loss": 0.1585, "step": 1082 }, { "epoch": 4.386835443037975, "grad_norm": 0.2890512050072188, "learning_rate": 1.715265841375957e-06, "loss": 0.139, "step": 1083 }, { "epoch": 4.390886075949367, "grad_norm": 0.2833353827463198, "learning_rate": 1.6923419950530684e-06, "loss": 0.1558, "step": 1084 }, { "epoch": 4.39493670886076, "grad_norm": 0.2728056176486022, "learning_rate": 1.6695655960909008e-06, "loss": 0.1643, "step": 1085 }, { "epoch": 4.398987341772152, "grad_norm": 0.2669848386053188, "learning_rate": 1.646936827927441e-06, "loss": 0.1494, "step": 1086 }, { "epoch": 4.403037974683544, "grad_norm": 0.26087910336615655, "learning_rate": 1.6244558728116766e-06, "loss": 0.1516, "step": 1087 }, { "epoch": 4.407088607594937, "grad_norm": 0.26949992122262234, "learning_rate": 1.6021229118021265e-06, "loss": 0.1594, "step": 1088 }, { "epoch": 4.411139240506329, "grad_norm": 0.2639917793669414, "learning_rate": 1.5799381247653967e-06, "loss": 0.1697, "step": 1089 }, { "epoch": 4.415189873417722, "grad_norm": 0.2621705654913447, "learning_rate": 1.5579016903747013e-06, "loss": 0.1557, "step": 1090 }, { "epoch": 4.419240506329114, "grad_norm": 0.2637190186271578, "learning_rate": 1.5360137861084656e-06, "loss": 0.1488, "step": 1091 }, { "epoch": 4.423291139240506, "grad_norm": 0.25972243977188764, "learning_rate": 1.5142745882488475e-06, "loss": 0.155, "step": 1092 }, { "epoch": 4.427341772151899, "grad_norm": 0.26928406918264103, "learning_rate": 1.4926842718803691e-06, "loss": 0.1616, "step": 1093 }, { "epoch": 4.431392405063291, "grad_norm": 0.27065083029932097, "learning_rate": 1.4712430108884657e-06, "loss": 0.1578, "step": 1094 }, { "epoch": 4.435443037974683, "grad_norm": 0.26689730470577644, "learning_rate": 1.4499509779581078e-06, "loss": 0.1678, "step": 1095 }, { "epoch": 4.439493670886076, "grad_norm": 0.2611664514403115, "learning_rate": 1.4288083445723988e-06, "loss": 0.1467, "step": 1096 }, { "epoch": 4.443544303797468, "grad_norm": 0.2628496717844133, "learning_rate": 1.4078152810112045e-06, "loss": 0.1313, "step": 1097 }, { "epoch": 4.44759493670886, "grad_norm": 0.28667336811923466, "learning_rate": 1.3869719563497697e-06, "loss": 0.1695, "step": 1098 }, { "epoch": 4.451645569620253, "grad_norm": 0.2787139466854447, "learning_rate": 1.3662785384573663e-06, "loss": 0.1707, "step": 1099 }, { "epoch": 4.455696202531645, "grad_norm": 0.26539360640437903, "learning_rate": 1.3457351939959383e-06, "loss": 0.1377, "step": 1100 }, { "epoch": 4.459746835443038, "grad_norm": 0.2664565488849423, "learning_rate": 1.3253420884187551e-06, "loss": 0.1561, "step": 1101 }, { "epoch": 4.46379746835443, "grad_norm": 0.2743511784044007, "learning_rate": 1.3050993859690953e-06, "loss": 0.162, "step": 1102 }, { "epoch": 4.467848101265822, "grad_norm": 0.26745753182917115, "learning_rate": 1.2850072496788869e-06, "loss": 0.1606, "step": 1103 }, { "epoch": 4.471898734177215, "grad_norm": 0.27804503615336046, "learning_rate": 1.2650658413674434e-06, "loss": 0.1608, "step": 1104 }, { "epoch": 4.4759493670886075, "grad_norm": 0.2654048023670733, "learning_rate": 1.2452753216401226e-06, "loss": 0.1667, "step": 1105 }, { "epoch": 4.48, "grad_norm": 0.2575405972195568, "learning_rate": 1.2256358498870503e-06, "loss": 0.142, "step": 1106 }, { "epoch": 4.4840506329113925, "grad_norm": 0.2636779557153573, "learning_rate": 1.2061475842818337e-06, "loss": 0.1548, "step": 1107 }, { "epoch": 4.488101265822785, "grad_norm": 0.26828520140231493, "learning_rate": 1.1868106817802816e-06, "loss": 0.1497, "step": 1108 }, { "epoch": 4.4921518987341775, "grad_norm": 0.2596087833113723, "learning_rate": 1.1676252981191482e-06, "loss": 0.1845, "step": 1109 }, { "epoch": 4.49620253164557, "grad_norm": 0.2561600776561207, "learning_rate": 1.1485915878148823e-06, "loss": 0.1572, "step": 1110 }, { "epoch": 4.500253164556962, "grad_norm": 0.2655058458313665, "learning_rate": 1.1297097041623584e-06, "loss": 0.1546, "step": 1111 }, { "epoch": 4.504303797468355, "grad_norm": 0.2533898604474188, "learning_rate": 1.1109797992336847e-06, "loss": 0.1283, "step": 1112 }, { "epoch": 4.508354430379747, "grad_norm": 0.2663785417139597, "learning_rate": 1.092402023876933e-06, "loss": 0.1648, "step": 1113 }, { "epoch": 4.512405063291139, "grad_norm": 0.262073011329174, "learning_rate": 1.0739765277149527e-06, "loss": 0.1369, "step": 1114 }, { "epoch": 4.516455696202532, "grad_norm": 0.27594886878855784, "learning_rate": 1.0557034591441596e-06, "loss": 0.1556, "step": 1115 }, { "epoch": 4.520506329113924, "grad_norm": 0.3206397595541424, "learning_rate": 1.0375829653333324e-06, "loss": 0.1301, "step": 1116 }, { "epoch": 4.524556962025317, "grad_norm": 0.2681500386195023, "learning_rate": 1.0196151922224385e-06, "loss": 0.1671, "step": 1117 }, { "epoch": 4.528607594936709, "grad_norm": 0.27901972539962544, "learning_rate": 1.0018002845214526e-06, "loss": 0.1608, "step": 1118 }, { "epoch": 4.532658227848101, "grad_norm": 0.2743136628088833, "learning_rate": 9.841383857091947e-07, "loss": 0.1564, "step": 1119 }, { "epoch": 4.536708860759494, "grad_norm": 0.29383822895011164, "learning_rate": 9.666296380321616e-07, "loss": 0.1551, "step": 1120 }, { "epoch": 4.540759493670886, "grad_norm": 0.24806653717172383, "learning_rate": 9.492741825034124e-07, "loss": 0.1396, "step": 1121 }, { "epoch": 4.544810126582279, "grad_norm": 0.25951960998816176, "learning_rate": 9.320721589013892e-07, "loss": 0.164, "step": 1122 }, { "epoch": 4.548860759493671, "grad_norm": 0.26169976194374256, "learning_rate": 9.150237057688339e-07, "loss": 0.1476, "step": 1123 }, { "epoch": 4.552911392405063, "grad_norm": 0.26114082780035414, "learning_rate": 8.981289604116328e-07, "loss": 0.1613, "step": 1124 }, { "epoch": 4.556962025316456, "grad_norm": 0.27043871792150886, "learning_rate": 8.813880588977542e-07, "loss": 0.1488, "step": 1125 }, { "epoch": 4.561012658227848, "grad_norm": 0.27005460693184713, "learning_rate": 8.648011360561126e-07, "loss": 0.1791, "step": 1126 }, { "epoch": 4.56506329113924, "grad_norm": 0.26821142393259784, "learning_rate": 8.483683254755037e-07, "loss": 0.1507, "step": 1127 }, { "epoch": 4.569113924050633, "grad_norm": 0.26218449038818864, "learning_rate": 8.320897595035227e-07, "loss": 0.1539, "step": 1128 }, { "epoch": 4.573164556962025, "grad_norm": 0.2506349160494743, "learning_rate": 8.159655692455093e-07, "loss": 0.1511, "step": 1129 }, { "epoch": 4.577215189873417, "grad_norm": 0.2558120582103157, "learning_rate": 7.999958845634648e-07, "loss": 0.1303, "step": 1130 }, { "epoch": 4.58126582278481, "grad_norm": 0.2550887897690892, "learning_rate": 7.841808340750478e-07, "loss": 0.1904, "step": 1131 }, { "epoch": 4.585316455696202, "grad_norm": 0.2643877300365898, "learning_rate": 7.685205451524869e-07, "loss": 0.1332, "step": 1132 }, { "epoch": 4.589367088607595, "grad_norm": 0.264055191609623, "learning_rate": 7.530151439216027e-07, "loss": 0.1517, "step": 1133 }, { "epoch": 4.593417721518987, "grad_norm": 0.2731816101648263, "learning_rate": 7.376647552607675e-07, "loss": 0.1555, "step": 1134 }, { "epoch": 4.597468354430379, "grad_norm": 0.2688012463904095, "learning_rate": 7.224695027998963e-07, "loss": 0.1487, "step": 1135 }, { "epoch": 4.601518987341772, "grad_norm": 0.26327789869157237, "learning_rate": 7.07429508919466e-07, "loss": 0.1625, "step": 1136 }, { "epoch": 4.605569620253164, "grad_norm": 0.2719946055409481, "learning_rate": 6.925448947495206e-07, "loss": 0.164, "step": 1137 }, { "epoch": 4.609620253164557, "grad_norm": 0.27063930661861535, "learning_rate": 6.778157801686936e-07, "loss": 0.1365, "step": 1138 }, { "epoch": 4.613670886075949, "grad_norm": 0.2696597369523681, "learning_rate": 6.632422838032515e-07, "loss": 0.1681, "step": 1139 }, { "epoch": 4.6177215189873415, "grad_norm": 0.2602750834259741, "learning_rate": 6.488245230261281e-07, "loss": 0.1503, "step": 1140 }, { "epoch": 4.6217721518987345, "grad_norm": 0.2689229629791167, "learning_rate": 6.345626139559868e-07, "loss": 0.1556, "step": 1141 }, { "epoch": 4.6258227848101265, "grad_norm": 0.2589292281416876, "learning_rate": 6.204566714562866e-07, "loss": 0.153, "step": 1142 }, { "epoch": 4.629873417721519, "grad_norm": 0.29233311408671364, "learning_rate": 6.06506809134344e-07, "loss": 0.1625, "step": 1143 }, { "epoch": 4.633924050632912, "grad_norm": 0.2601893751899515, "learning_rate": 5.927131393404373e-07, "loss": 0.1596, "step": 1144 }, { "epoch": 4.637974683544304, "grad_norm": 0.268945670768301, "learning_rate": 5.790757731668817e-07, "loss": 0.1541, "step": 1145 }, { "epoch": 4.642025316455696, "grad_norm": 0.27160112244689527, "learning_rate": 5.655948204471507e-07, "loss": 0.1844, "step": 1146 }, { "epoch": 4.646075949367089, "grad_norm": 0.26703647458616864, "learning_rate": 5.522703897549875e-07, "loss": 0.1667, "step": 1147 }, { "epoch": 4.650126582278481, "grad_norm": 0.25559137444811164, "learning_rate": 5.391025884035239e-07, "loss": 0.1636, "step": 1148 }, { "epoch": 4.654177215189874, "grad_norm": 0.2610536687307726, "learning_rate": 5.260915224444207e-07, "loss": 0.1534, "step": 1149 }, { "epoch": 4.658227848101266, "grad_norm": 0.266967591493412, "learning_rate": 5.132372966670129e-07, "loss": 0.1709, "step": 1150 }, { "epoch": 4.662278481012658, "grad_norm": 0.27241647209072456, "learning_rate": 5.005400145974704e-07, "loss": 0.1351, "step": 1151 }, { "epoch": 4.666329113924051, "grad_norm": 0.28379296306723995, "learning_rate": 4.879997784979562e-07, "loss": 0.1496, "step": 1152 }, { "epoch": 4.670379746835443, "grad_norm": 0.2871373310167841, "learning_rate": 4.7561668936580984e-07, "loss": 0.1395, "step": 1153 }, { "epoch": 4.674430379746836, "grad_norm": 0.2755682300014426, "learning_rate": 4.6339084693272306e-07, "loss": 0.1666, "step": 1154 }, { "epoch": 4.678481012658228, "grad_norm": 0.2618377072299602, "learning_rate": 4.5132234966395847e-07, "loss": 0.1612, "step": 1155 }, { "epoch": 4.68253164556962, "grad_norm": 0.25665850892469544, "learning_rate": 4.3941129475752795e-07, "loss": 0.1563, "step": 1156 }, { "epoch": 4.686582278481013, "grad_norm": 0.27546770647806523, "learning_rate": 4.27657778143431e-07, "loss": 0.1615, "step": 1157 }, { "epoch": 4.690632911392405, "grad_norm": 0.2620782299715212, "learning_rate": 4.1606189448287757e-07, "loss": 0.1343, "step": 1158 }, { "epoch": 4.694683544303797, "grad_norm": 0.2750232246327414, "learning_rate": 4.046237371675177e-07, "loss": 0.1483, "step": 1159 }, { "epoch": 4.69873417721519, "grad_norm": 0.2560560125140842, "learning_rate": 3.9334339831869963e-07, "loss": 0.1639, "step": 1160 }, { "epoch": 4.702784810126582, "grad_norm": 0.2733548088410282, "learning_rate": 3.8222096878671955e-07, "loss": 0.1411, "step": 1161 }, { "epoch": 4.706835443037974, "grad_norm": 0.27401904827445644, "learning_rate": 3.7125653815009545e-07, "loss": 0.1488, "step": 1162 }, { "epoch": 4.710886075949367, "grad_norm": 0.24791168770904842, "learning_rate": 3.6045019471484974e-07, "loss": 0.1549, "step": 1163 }, { "epoch": 4.714936708860759, "grad_norm": 0.28462239767863523, "learning_rate": 3.498020255137813e-07, "loss": 0.1792, "step": 1164 }, { "epoch": 4.718987341772152, "grad_norm": 0.2518712712450192, "learning_rate": 3.393121163057811e-07, "loss": 0.138, "step": 1165 }, { "epoch": 4.723037974683544, "grad_norm": 0.2558771900798081, "learning_rate": 3.289805515751399e-07, "loss": 0.1428, "step": 1166 }, { "epoch": 4.727088607594936, "grad_norm": 0.2829450126795175, "learning_rate": 3.188074145308573e-07, "loss": 0.1501, "step": 1167 }, { "epoch": 4.731139240506329, "grad_norm": 0.2722064004672672, "learning_rate": 3.087927871059804e-07, "loss": 0.1531, "step": 1168 }, { "epoch": 4.735189873417721, "grad_norm": 0.2673483148859674, "learning_rate": 2.989367499569418e-07, "loss": 0.1235, "step": 1169 }, { "epoch": 4.739240506329114, "grad_norm": 0.255699450696738, "learning_rate": 2.8923938246290917e-07, "loss": 0.1603, "step": 1170 }, { "epoch": 4.743291139240506, "grad_norm": 0.27173768191205755, "learning_rate": 2.7970076272514804e-07, "loss": 0.1325, "step": 1171 }, { "epoch": 4.7473417721518985, "grad_norm": 0.2634557234250493, "learning_rate": 2.703209675663887e-07, "loss": 0.1626, "step": 1172 }, { "epoch": 4.751392405063291, "grad_norm": 0.2773372160219956, "learning_rate": 2.6110007253021374e-07, "loss": 0.1792, "step": 1173 }, { "epoch": 4.7554430379746835, "grad_norm": 0.26548402843118607, "learning_rate": 2.520381518804471e-07, "loss": 0.1444, "step": 1174 }, { "epoch": 4.759493670886076, "grad_norm": 0.253588222154805, "learning_rate": 2.4313527860054585e-07, "loss": 0.1357, "step": 1175 }, { "epoch": 4.7635443037974685, "grad_norm": 0.28170346801495283, "learning_rate": 2.343915243930317e-07, "loss": 0.1504, "step": 1176 }, { "epoch": 4.767594936708861, "grad_norm": 0.2592033602272628, "learning_rate": 2.2580695967889367e-07, "loss": 0.1222, "step": 1177 }, { "epoch": 4.7716455696202535, "grad_norm": 0.2712602956521086, "learning_rate": 2.1738165359704189e-07, "loss": 0.1359, "step": 1178 }, { "epoch": 4.775696202531646, "grad_norm": 0.28061558357498734, "learning_rate": 2.0911567400373257e-07, "loss": 0.1322, "step": 1179 }, { "epoch": 4.779746835443038, "grad_norm": 0.2605148269520422, "learning_rate": 2.0100908747202607e-07, "loss": 0.1347, "step": 1180 }, { "epoch": 4.783797468354431, "grad_norm": 0.26476339702462814, "learning_rate": 1.9306195929125638e-07, "loss": 0.1425, "step": 1181 }, { "epoch": 4.787848101265823, "grad_norm": 0.26407963031284987, "learning_rate": 1.8527435346650247e-07, "loss": 0.1458, "step": 1182 }, { "epoch": 4.791898734177215, "grad_norm": 0.26328910285103885, "learning_rate": 1.7764633271807108e-07, "loss": 0.1396, "step": 1183 }, { "epoch": 4.795949367088608, "grad_norm": 0.2700164516051789, "learning_rate": 1.7017795848099262e-07, "loss": 0.1758, "step": 1184 }, { "epoch": 4.8, "grad_norm": 0.27145161129651335, "learning_rate": 1.6286929090452596e-07, "loss": 0.1364, "step": 1185 }, { "epoch": 4.804050632911393, "grad_norm": 0.27639483974305973, "learning_rate": 1.557203888516745e-07, "loss": 0.1429, "step": 1186 }, { "epoch": 4.808101265822785, "grad_norm": 0.2636941358126914, "learning_rate": 1.487313098987131e-07, "loss": 0.1392, "step": 1187 }, { "epoch": 4.812151898734177, "grad_norm": 0.2678974137641404, "learning_rate": 1.4190211033472402e-07, "loss": 0.1476, "step": 1188 }, { "epoch": 4.81620253164557, "grad_norm": 0.2594701390255011, "learning_rate": 1.3523284516113955e-07, "loss": 0.1697, "step": 1189 }, { "epoch": 4.820253164556962, "grad_norm": 0.27936082925622935, "learning_rate": 1.2872356809130682e-07, "loss": 0.1528, "step": 1190 }, { "epoch": 4.824303797468355, "grad_norm": 0.2622158939844664, "learning_rate": 1.2237433155004807e-07, "loss": 0.1501, "step": 1191 }, { "epoch": 4.828354430379747, "grad_norm": 0.27479983561676347, "learning_rate": 1.1618518667323886e-07, "loss": 0.1703, "step": 1192 }, { "epoch": 4.832405063291139, "grad_norm": 0.2694038827738397, "learning_rate": 1.1015618330740385e-07, "loss": 0.1514, "step": 1193 }, { "epoch": 4.836455696202532, "grad_norm": 0.2740619285133102, "learning_rate": 1.042873700093061e-07, "loss": 0.1515, "step": 1194 }, { "epoch": 4.840506329113924, "grad_norm": 0.25663054702782445, "learning_rate": 9.857879404556291e-08, "loss": 0.1461, "step": 1195 }, { "epoch": 4.844556962025316, "grad_norm": 0.25638672232237475, "learning_rate": 9.303050139225722e-08, "loss": 0.1269, "step": 1196 }, { "epoch": 4.848607594936709, "grad_norm": 0.26042936208737305, "learning_rate": 8.76425367345779e-08, "loss": 0.1469, "step": 1197 }, { "epoch": 4.852658227848101, "grad_norm": 0.25987934243109634, "learning_rate": 8.241494346644897e-08, "loss": 0.1618, "step": 1198 }, { "epoch": 4.856708860759493, "grad_norm": 0.26531712647808287, "learning_rate": 7.734776369019204e-08, "loss": 0.1878, "step": 1199 }, { "epoch": 4.860759493670886, "grad_norm": 0.27339882268483534, "learning_rate": 7.244103821617332e-08, "loss": 0.1695, "step": 1200 }, { "epoch": 4.864810126582278, "grad_norm": 0.26627732882833643, "learning_rate": 6.769480656248606e-08, "loss": 0.1468, "step": 1201 }, { "epoch": 4.868860759493671, "grad_norm": 0.2646091337755445, "learning_rate": 6.310910695462635e-08, "loss": 0.1444, "step": 1202 }, { "epoch": 4.872911392405063, "grad_norm": 0.2751578802369476, "learning_rate": 5.8683976325191185e-08, "loss": 0.1608, "step": 1203 }, { "epoch": 4.876962025316455, "grad_norm": 0.25646677448136224, "learning_rate": 5.4419450313571984e-08, "loss": 0.1373, "step": 1204 }, { "epoch": 4.881012658227848, "grad_norm": 0.26019531786424205, "learning_rate": 5.031556326567488e-08, "loss": 0.1288, "step": 1205 }, { "epoch": 4.88506329113924, "grad_norm": 0.27029110860073857, "learning_rate": 4.637234823364312e-08, "loss": 0.1534, "step": 1206 }, { "epoch": 4.889113924050633, "grad_norm": 0.2727154292614314, "learning_rate": 4.258983697558838e-08, "loss": 0.1537, "step": 1207 }, { "epoch": 4.8931645569620255, "grad_norm": 0.2672538755351328, "learning_rate": 3.896805995533548e-08, "loss": 0.1344, "step": 1208 }, { "epoch": 4.8972151898734175, "grad_norm": 0.2622934697526035, "learning_rate": 3.550704634218028e-08, "loss": 0.1293, "step": 1209 }, { "epoch": 4.9012658227848105, "grad_norm": 0.27805383961090874, "learning_rate": 3.2206824010647676e-08, "loss": 0.1451, "step": 1210 }, { "epoch": 4.905316455696203, "grad_norm": 0.25600327935291745, "learning_rate": 2.9067419540278476e-08, "loss": 0.127, "step": 1211 }, { "epoch": 4.909367088607595, "grad_norm": 0.26269284572191914, "learning_rate": 2.6088858215400638e-08, "loss": 0.1481, "step": 1212 }, { "epoch": 4.913417721518988, "grad_norm": 0.2566221362751083, "learning_rate": 2.3271164024940564e-08, "loss": 0.1156, "step": 1213 }, { "epoch": 4.91746835443038, "grad_norm": 0.25790122171500973, "learning_rate": 2.061435966221881e-08, "loss": 0.1433, "step": 1214 }, { "epoch": 4.921518987341772, "grad_norm": 0.2614683365995269, "learning_rate": 1.811846652477245e-08, "loss": 0.1527, "step": 1215 }, { "epoch": 4.925569620253165, "grad_norm": 0.2582629509562234, "learning_rate": 1.5783504714184106e-08, "loss": 0.15, "step": 1216 }, { "epoch": 4.929620253164557, "grad_norm": 0.26291483401211485, "learning_rate": 1.360949303591097e-08, "loss": 0.1325, "step": 1217 }, { "epoch": 4.93367088607595, "grad_norm": 0.2676097024194672, "learning_rate": 1.1596448999144916e-08, "loss": 0.1528, "step": 1218 }, { "epoch": 4.937721518987342, "grad_norm": 0.24934496385720378, "learning_rate": 9.744388816668172e-09, "loss": 0.1106, "step": 1219 }, { "epoch": 4.941772151898734, "grad_norm": 0.2566888047997743, "learning_rate": 8.05332740472009e-09, "loss": 0.149, "step": 1220 }, { "epoch": 4.945822784810127, "grad_norm": 0.25587086156766237, "learning_rate": 6.523278382872811e-09, "loss": 0.14, "step": 1221 }, { "epoch": 4.949873417721519, "grad_norm": 0.2610074150256156, "learning_rate": 5.15425407393133e-09, "loss": 0.1446, "step": 1222 }, { "epoch": 4.953924050632912, "grad_norm": 0.25619216960927027, "learning_rate": 3.94626550383137e-09, "loss": 0.1561, "step": 1223 }, { "epoch": 4.957974683544304, "grad_norm": 0.26031703518255944, "learning_rate": 2.899322401546112e-09, "loss": 0.1382, "step": 1224 }, { "epoch": 4.962025316455696, "grad_norm": 0.2538421029077102, "learning_rate": 2.013433199010706e-09, "loss": 0.1465, "step": 1225 }, { "epoch": 4.966075949367089, "grad_norm": 0.26678562767222536, "learning_rate": 1.2886050310556563e-09, "loss": 0.1614, "step": 1226 }, { "epoch": 4.970126582278481, "grad_norm": 0.26266248909182754, "learning_rate": 7.248437353468695e-10, "loss": 0.1369, "step": 1227 }, { "epoch": 4.974177215189873, "grad_norm": 0.2477614967376003, "learning_rate": 3.221538523412449e-10, "loss": 0.1498, "step": 1228 }, { "epoch": 4.978227848101266, "grad_norm": 0.26024336197002085, "learning_rate": 8.053862524670663e-11, "loss": 0.1465, "step": 1229 }, { "epoch": 4.982278481012658, "grad_norm": 0.2509110796437732, "learning_rate": 0.0, "loss": 0.1768, "step": 1230 }, { "epoch": 4.982278481012658, "step": 1230, "total_flos": 1.7050706653871473e+18, "train_loss": 0.4073354158399066, "train_runtime": 30876.0115, "train_samples_per_second": 5.117, "train_steps_per_second": 0.04 } ], "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": 1.7050706653871473e+18, "train_batch_size": 1, "trial_name": null, "trial_params": null }