{ "best_metric": null, "best_model_checkpoint": null, "epoch": 4.994430379746835, "eval_steps": 500, "global_step": 1230, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.004050632911392405, "grad_norm": 6.571106709583184, "learning_rate": 3.2520325203252037e-07, "loss": 1.1659, "step": 1 }, { "epoch": 0.00810126582278481, "grad_norm": 6.3468557934774665, "learning_rate": 6.504065040650407e-07, "loss": 1.0967, "step": 2 }, { "epoch": 0.012151898734177215, "grad_norm": 6.44040915768219, "learning_rate": 9.75609756097561e-07, "loss": 1.1312, "step": 3 }, { "epoch": 0.01620253164556962, "grad_norm": 6.227197402815415, "learning_rate": 1.3008130081300815e-06, "loss": 1.127, "step": 4 }, { "epoch": 0.020253164556962026, "grad_norm": 5.74689287207507, "learning_rate": 1.6260162601626018e-06, "loss": 1.0958, "step": 5 }, { "epoch": 0.02430379746835443, "grad_norm": 5.751406558233956, "learning_rate": 1.951219512195122e-06, "loss": 1.1033, "step": 6 }, { "epoch": 0.028354430379746835, "grad_norm": 4.914165119947113, "learning_rate": 2.2764227642276426e-06, "loss": 1.0912, "step": 7 }, { "epoch": 0.03240506329113924, "grad_norm": 4.29838565694995, "learning_rate": 2.601626016260163e-06, "loss": 1.0245, "step": 8 }, { "epoch": 0.03645569620253165, "grad_norm": 2.463531745127488, "learning_rate": 2.926829268292683e-06, "loss": 1.0189, "step": 9 }, { "epoch": 0.04050632911392405, "grad_norm": 2.33926345414119, "learning_rate": 3.2520325203252037e-06, "loss": 1.0331, "step": 10 }, { "epoch": 0.044556962025316456, "grad_norm": 2.097453711821296, "learning_rate": 3.577235772357724e-06, "loss": 0.9965, "step": 11 }, { "epoch": 0.04860759493670886, "grad_norm": 4.215671667037415, "learning_rate": 3.902439024390244e-06, "loss": 0.982, "step": 12 }, { "epoch": 0.052658227848101265, "grad_norm": 4.712335427027248, "learning_rate": 4.227642276422765e-06, "loss": 1.0103, "step": 13 }, { "epoch": 0.05670886075949367, "grad_norm": 4.228783921959283, "learning_rate": 4.552845528455285e-06, "loss": 0.9485, "step": 14 }, { "epoch": 0.060759493670886074, "grad_norm": 4.040523833555338, "learning_rate": 4.8780487804878055e-06, "loss": 0.9595, "step": 15 }, { "epoch": 0.06481012658227848, "grad_norm": 3.0073717231533155, "learning_rate": 5.203252032520326e-06, "loss": 0.926, "step": 16 }, { "epoch": 0.06886075949367089, "grad_norm": 2.8848153422136154, "learning_rate": 5.528455284552846e-06, "loss": 0.9171, "step": 17 }, { "epoch": 0.0729113924050633, "grad_norm": 2.7149651263083836, "learning_rate": 5.853658536585366e-06, "loss": 0.906, "step": 18 }, { "epoch": 0.0769620253164557, "grad_norm": 2.196559960471889, "learning_rate": 6.178861788617887e-06, "loss": 0.892, "step": 19 }, { "epoch": 0.0810126582278481, "grad_norm": 1.8229021576317639, "learning_rate": 6.504065040650407e-06, "loss": 0.8662, "step": 20 }, { "epoch": 0.08506329113924051, "grad_norm": 1.5203551837406186, "learning_rate": 6.829268292682928e-06, "loss": 0.8607, "step": 21 }, { "epoch": 0.08911392405063291, "grad_norm": 1.7368577497315756, "learning_rate": 7.154471544715448e-06, "loss": 0.8716, "step": 22 }, { "epoch": 0.09316455696202532, "grad_norm": 1.5763893771070034, "learning_rate": 7.4796747967479676e-06, "loss": 0.8434, "step": 23 }, { "epoch": 0.09721518987341772, "grad_norm": 1.589665931246622, "learning_rate": 7.804878048780489e-06, "loss": 0.8613, "step": 24 }, { "epoch": 0.10126582278481013, "grad_norm": 1.2239925857235083, "learning_rate": 8.130081300813009e-06, "loss": 0.8594, "step": 25 }, { "epoch": 0.10531645569620253, "grad_norm": 1.3317411369453123, "learning_rate": 8.45528455284553e-06, "loss": 0.8369, "step": 26 }, { "epoch": 0.10936708860759493, "grad_norm": 1.3752663094039768, "learning_rate": 8.78048780487805e-06, "loss": 0.8423, "step": 27 }, { "epoch": 0.11341772151898734, "grad_norm": 1.1737865033817851, "learning_rate": 9.10569105691057e-06, "loss": 0.8172, "step": 28 }, { "epoch": 0.11746835443037974, "grad_norm": 1.1377354790776824, "learning_rate": 9.43089430894309e-06, "loss": 0.8052, "step": 29 }, { "epoch": 0.12151898734177215, "grad_norm": 0.9673220909678029, "learning_rate": 9.756097560975611e-06, "loss": 0.8301, "step": 30 }, { "epoch": 0.12556962025316457, "grad_norm": 1.1113635937256188, "learning_rate": 1.008130081300813e-05, "loss": 0.8122, "step": 31 }, { "epoch": 0.12962025316455697, "grad_norm": 1.1485639105986043, "learning_rate": 1.0406504065040652e-05, "loss": 0.816, "step": 32 }, { "epoch": 0.13367088607594937, "grad_norm": 0.9062703201997527, "learning_rate": 1.0731707317073172e-05, "loss": 0.825, "step": 33 }, { "epoch": 0.13772151898734178, "grad_norm": 0.922246936697616, "learning_rate": 1.1056910569105692e-05, "loss": 0.8045, "step": 34 }, { "epoch": 0.14177215189873418, "grad_norm": 0.8877538394651039, "learning_rate": 1.1382113821138213e-05, "loss": 0.8087, "step": 35 }, { "epoch": 0.1458227848101266, "grad_norm": 0.8321710208761663, "learning_rate": 1.1707317073170731e-05, "loss": 0.8404, "step": 36 }, { "epoch": 0.149873417721519, "grad_norm": 0.7649056008165184, "learning_rate": 1.2032520325203254e-05, "loss": 0.808, "step": 37 }, { "epoch": 0.1539240506329114, "grad_norm": 0.7290821690646506, "learning_rate": 1.2357723577235774e-05, "loss": 0.8218, "step": 38 }, { "epoch": 0.1579746835443038, "grad_norm": 0.8088081528471152, "learning_rate": 1.2682926829268294e-05, "loss": 0.7976, "step": 39 }, { "epoch": 0.1620253164556962, "grad_norm": 0.6675877487506543, "learning_rate": 1.3008130081300815e-05, "loss": 0.7707, "step": 40 }, { "epoch": 0.1660759493670886, "grad_norm": 0.7121066772909572, "learning_rate": 1.3333333333333333e-05, "loss": 0.7689, "step": 41 }, { "epoch": 0.17012658227848101, "grad_norm": 0.8559732882938762, "learning_rate": 1.3658536585365855e-05, "loss": 0.7506, "step": 42 }, { "epoch": 0.17417721518987342, "grad_norm": 0.6180086658887367, "learning_rate": 1.3983739837398376e-05, "loss": 0.7829, "step": 43 }, { "epoch": 0.17822784810126582, "grad_norm": 0.7050956238176304, "learning_rate": 1.4308943089430896e-05, "loss": 0.7429, "step": 44 }, { "epoch": 0.18227848101265823, "grad_norm": 0.7718861840735263, "learning_rate": 1.4634146341463415e-05, "loss": 0.8053, "step": 45 }, { "epoch": 0.18632911392405063, "grad_norm": 0.6266716366636997, "learning_rate": 1.4959349593495935e-05, "loss": 0.7911, "step": 46 }, { "epoch": 0.19037974683544304, "grad_norm": 0.6242508818185738, "learning_rate": 1.528455284552846e-05, "loss": 0.7665, "step": 47 }, { "epoch": 0.19443037974683544, "grad_norm": 0.6758275851917089, "learning_rate": 1.5609756097560978e-05, "loss": 0.7702, "step": 48 }, { "epoch": 0.19848101265822785, "grad_norm": 0.6867302687497145, "learning_rate": 1.5934959349593496e-05, "loss": 0.7555, "step": 49 }, { "epoch": 0.20253164556962025, "grad_norm": 0.7123305896223188, "learning_rate": 1.6260162601626018e-05, "loss": 0.7958, "step": 50 }, { "epoch": 0.20658227848101265, "grad_norm": 0.8247685189632834, "learning_rate": 1.6585365853658537e-05, "loss": 0.7925, "step": 51 }, { "epoch": 0.21063291139240506, "grad_norm": 0.6213089743175803, "learning_rate": 1.691056910569106e-05, "loss": 0.768, "step": 52 }, { "epoch": 0.21468354430379746, "grad_norm": 0.8355347913960276, "learning_rate": 1.7235772357723578e-05, "loss": 0.8276, "step": 53 }, { "epoch": 0.21873417721518987, "grad_norm": 0.601811337262317, "learning_rate": 1.75609756097561e-05, "loss": 0.7538, "step": 54 }, { "epoch": 0.22278481012658227, "grad_norm": 0.7439405863467042, "learning_rate": 1.788617886178862e-05, "loss": 0.7659, "step": 55 }, { "epoch": 0.22683544303797468, "grad_norm": 0.6831920757098024, "learning_rate": 1.821138211382114e-05, "loss": 0.7736, "step": 56 }, { "epoch": 0.23088607594936708, "grad_norm": 0.7413698335138743, "learning_rate": 1.8536585365853663e-05, "loss": 0.7607, "step": 57 }, { "epoch": 0.23493670886075949, "grad_norm": 0.8248730514299659, "learning_rate": 1.886178861788618e-05, "loss": 0.7786, "step": 58 }, { "epoch": 0.2389873417721519, "grad_norm": 0.6942569647147538, "learning_rate": 1.91869918699187e-05, "loss": 0.7524, "step": 59 }, { "epoch": 0.2430379746835443, "grad_norm": 0.7158468460363526, "learning_rate": 1.9512195121951222e-05, "loss": 0.7797, "step": 60 }, { "epoch": 0.2470886075949367, "grad_norm": 0.6976681517720579, "learning_rate": 1.983739837398374e-05, "loss": 0.7481, "step": 61 }, { "epoch": 0.25113924050632913, "grad_norm": 0.6165443856493703, "learning_rate": 2.016260162601626e-05, "loss": 0.7603, "step": 62 }, { "epoch": 0.25518987341772154, "grad_norm": 0.6605236797933135, "learning_rate": 2.048780487804878e-05, "loss": 0.7397, "step": 63 }, { "epoch": 0.25924050632911394, "grad_norm": 0.6780388806149242, "learning_rate": 2.0813008130081303e-05, "loss": 0.7809, "step": 64 }, { "epoch": 0.26329113924050634, "grad_norm": 0.7605056255175247, "learning_rate": 2.1138211382113822e-05, "loss": 0.785, "step": 65 }, { "epoch": 0.26734177215189875, "grad_norm": 0.6031041827973667, "learning_rate": 2.1463414634146344e-05, "loss": 0.7725, "step": 66 }, { "epoch": 0.27139240506329115, "grad_norm": 0.7690978745525988, "learning_rate": 2.1788617886178863e-05, "loss": 0.7914, "step": 67 }, { "epoch": 0.27544303797468356, "grad_norm": 0.6415507052617376, "learning_rate": 2.2113821138211385e-05, "loss": 0.7653, "step": 68 }, { "epoch": 0.27949367088607596, "grad_norm": 0.7087978191728024, "learning_rate": 2.2439024390243907e-05, "loss": 0.7569, "step": 69 }, { "epoch": 0.28354430379746837, "grad_norm": 0.606281597816895, "learning_rate": 2.2764227642276426e-05, "loss": 0.7664, "step": 70 }, { "epoch": 0.28759493670886077, "grad_norm": 0.8135176206320839, "learning_rate": 2.3089430894308948e-05, "loss": 0.752, "step": 71 }, { "epoch": 0.2916455696202532, "grad_norm": 0.686099263470665, "learning_rate": 2.3414634146341463e-05, "loss": 0.7572, "step": 72 }, { "epoch": 0.2956962025316456, "grad_norm": 0.6308590544413757, "learning_rate": 2.3739837398373985e-05, "loss": 0.724, "step": 73 }, { "epoch": 0.299746835443038, "grad_norm": 0.6892643765523921, "learning_rate": 2.4065040650406507e-05, "loss": 0.7547, "step": 74 }, { "epoch": 0.3037974683544304, "grad_norm": 0.7838739591056918, "learning_rate": 2.4390243902439026e-05, "loss": 0.7522, "step": 75 }, { "epoch": 0.3078481012658228, "grad_norm": 0.6625064897254714, "learning_rate": 2.4715447154471548e-05, "loss": 0.7583, "step": 76 }, { "epoch": 0.3118987341772152, "grad_norm": 0.8441688361171769, "learning_rate": 2.5040650406504066e-05, "loss": 0.7452, "step": 77 }, { "epoch": 0.3159493670886076, "grad_norm": 0.818701835899373, "learning_rate": 2.536585365853659e-05, "loss": 0.7516, "step": 78 }, { "epoch": 0.32, "grad_norm": 0.6421669592542906, "learning_rate": 2.569105691056911e-05, "loss": 0.7353, "step": 79 }, { "epoch": 0.3240506329113924, "grad_norm": 0.8329781858867071, "learning_rate": 2.601626016260163e-05, "loss": 0.7898, "step": 80 }, { "epoch": 0.3281012658227848, "grad_norm": 0.7971709348645427, "learning_rate": 2.634146341463415e-05, "loss": 0.7533, "step": 81 }, { "epoch": 0.3321518987341772, "grad_norm": 0.67875480211316, "learning_rate": 2.6666666666666667e-05, "loss": 0.7533, "step": 82 }, { "epoch": 0.3362025316455696, "grad_norm": 0.7740745147535988, "learning_rate": 2.699186991869919e-05, "loss": 0.7292, "step": 83 }, { "epoch": 0.34025316455696203, "grad_norm": 0.7194789044309872, "learning_rate": 2.731707317073171e-05, "loss": 0.7486, "step": 84 }, { "epoch": 0.34430379746835443, "grad_norm": 0.7111157683726461, "learning_rate": 2.764227642276423e-05, "loss": 0.7598, "step": 85 }, { "epoch": 0.34835443037974684, "grad_norm": 0.8990752751141734, "learning_rate": 2.796747967479675e-05, "loss": 0.7448, "step": 86 }, { "epoch": 0.35240506329113924, "grad_norm": 0.6777191935628711, "learning_rate": 2.829268292682927e-05, "loss": 0.7248, "step": 87 }, { "epoch": 0.35645569620253165, "grad_norm": 0.7057377867541059, "learning_rate": 2.8617886178861792e-05, "loss": 0.7233, "step": 88 }, { "epoch": 0.36050632911392405, "grad_norm": 0.8842681736083787, "learning_rate": 2.8943089430894314e-05, "loss": 0.7598, "step": 89 }, { "epoch": 0.36455696202531646, "grad_norm": 0.7251222388111451, "learning_rate": 2.926829268292683e-05, "loss": 0.7911, "step": 90 }, { "epoch": 0.36860759493670886, "grad_norm": 0.6651589159416929, "learning_rate": 2.959349593495935e-05, "loss": 0.748, "step": 91 }, { "epoch": 0.37265822784810126, "grad_norm": 0.648963273615908, "learning_rate": 2.991869918699187e-05, "loss": 0.7483, "step": 92 }, { "epoch": 0.37670886075949367, "grad_norm": 0.7576486039876569, "learning_rate": 3.0243902439024392e-05, "loss": 0.7328, "step": 93 }, { "epoch": 0.3807594936708861, "grad_norm": 0.7861865983200981, "learning_rate": 3.056910569105692e-05, "loss": 0.7283, "step": 94 }, { "epoch": 0.3848101265822785, "grad_norm": 0.7078058622781911, "learning_rate": 3.089430894308943e-05, "loss": 0.709, "step": 95 }, { "epoch": 0.3888607594936709, "grad_norm": 0.8836049610961035, "learning_rate": 3.1219512195121955e-05, "loss": 0.729, "step": 96 }, { "epoch": 0.3929113924050633, "grad_norm": 0.8711150591114366, "learning_rate": 3.154471544715447e-05, "loss": 0.7598, "step": 97 }, { "epoch": 0.3969620253164557, "grad_norm": 0.6876416295978148, "learning_rate": 3.186991869918699e-05, "loss": 0.7213, "step": 98 }, { "epoch": 0.4010126582278481, "grad_norm": 0.6951590123135744, "learning_rate": 3.2195121951219514e-05, "loss": 0.7312, "step": 99 }, { "epoch": 0.4050632911392405, "grad_norm": 0.8853578971830324, "learning_rate": 3.2520325203252037e-05, "loss": 0.7413, "step": 100 }, { "epoch": 0.4091139240506329, "grad_norm": 0.7759960698582434, "learning_rate": 3.284552845528456e-05, "loss": 0.7584, "step": 101 }, { "epoch": 0.4131645569620253, "grad_norm": 0.7153527326208493, "learning_rate": 3.3170731707317074e-05, "loss": 0.7564, "step": 102 }, { "epoch": 0.4172151898734177, "grad_norm": 0.7739411329870899, "learning_rate": 3.3495934959349596e-05, "loss": 0.7776, "step": 103 }, { "epoch": 0.4212658227848101, "grad_norm": 0.9376884160187618, "learning_rate": 3.382113821138212e-05, "loss": 0.746, "step": 104 }, { "epoch": 0.4253164556962025, "grad_norm": 0.7771599280121653, "learning_rate": 3.414634146341463e-05, "loss": 0.7436, "step": 105 }, { "epoch": 0.4293670886075949, "grad_norm": 0.7416073339611879, "learning_rate": 3.4471544715447155e-05, "loss": 0.7691, "step": 106 }, { "epoch": 0.43341772151898733, "grad_norm": 0.937592341721884, "learning_rate": 3.479674796747968e-05, "loss": 0.7533, "step": 107 }, { "epoch": 0.43746835443037974, "grad_norm": 1.0133512988388362, "learning_rate": 3.51219512195122e-05, "loss": 0.7374, "step": 108 }, { "epoch": 0.44151898734177214, "grad_norm": 1.1165203919869917, "learning_rate": 3.544715447154472e-05, "loss": 0.7656, "step": 109 }, { "epoch": 0.44556962025316454, "grad_norm": 0.8138613299717883, "learning_rate": 3.577235772357724e-05, "loss": 0.7658, "step": 110 }, { "epoch": 0.44962025316455695, "grad_norm": 0.9708679457726505, "learning_rate": 3.609756097560976e-05, "loss": 0.7525, "step": 111 }, { "epoch": 0.45367088607594935, "grad_norm": 0.8965571008905113, "learning_rate": 3.642276422764228e-05, "loss": 0.7721, "step": 112 }, { "epoch": 0.45772151898734176, "grad_norm": 0.7878623167114912, "learning_rate": 3.67479674796748e-05, "loss": 0.7308, "step": 113 }, { "epoch": 0.46177215189873416, "grad_norm": 0.7782109575088253, "learning_rate": 3.7073170731707325e-05, "loss": 0.7433, "step": 114 }, { "epoch": 0.46582278481012657, "grad_norm": 0.8022090751821231, "learning_rate": 3.739837398373984e-05, "loss": 0.7094, "step": 115 }, { "epoch": 0.46987341772151897, "grad_norm": 0.8534061193595474, "learning_rate": 3.772357723577236e-05, "loss": 0.7664, "step": 116 }, { "epoch": 0.4739240506329114, "grad_norm": 0.6777133550559788, "learning_rate": 3.804878048780488e-05, "loss": 0.7606, "step": 117 }, { "epoch": 0.4779746835443038, "grad_norm": 0.9061450554519673, "learning_rate": 3.83739837398374e-05, "loss": 0.7176, "step": 118 }, { "epoch": 0.4820253164556962, "grad_norm": 0.7612137510443675, "learning_rate": 3.869918699186992e-05, "loss": 0.7579, "step": 119 }, { "epoch": 0.4860759493670886, "grad_norm": 0.7212369090572933, "learning_rate": 3.9024390243902444e-05, "loss": 0.7321, "step": 120 }, { "epoch": 0.490126582278481, "grad_norm": 0.6930852863068933, "learning_rate": 3.9349593495934966e-05, "loss": 0.7383, "step": 121 }, { "epoch": 0.4941772151898734, "grad_norm": 0.9185333768448346, "learning_rate": 3.967479674796748e-05, "loss": 0.6979, "step": 122 }, { "epoch": 0.4982278481012658, "grad_norm": 0.9458246191784033, "learning_rate": 4e-05, "loss": 0.7376, "step": 123 }, { "epoch": 0.5022784810126583, "grad_norm": 0.9940075440020821, "learning_rate": 3.999991946137476e-05, "loss": 0.7445, "step": 124 }, { "epoch": 0.5063291139240507, "grad_norm": 0.8991890705712159, "learning_rate": 3.999967784614766e-05, "loss": 0.7201, "step": 125 }, { "epoch": 0.5103797468354431, "grad_norm": 0.873716889662941, "learning_rate": 3.9999275156264656e-05, "loss": 0.724, "step": 126 }, { "epoch": 0.5144303797468355, "grad_norm": 0.9399119388344116, "learning_rate": 3.999871139496895e-05, "loss": 0.7493, "step": 127 }, { "epoch": 0.5184810126582279, "grad_norm": 0.7664615058592825, "learning_rate": 3.9997986566800995e-05, "loss": 0.7797, "step": 128 }, { "epoch": 0.5225316455696203, "grad_norm": 0.6684950217488235, "learning_rate": 3.999710067759846e-05, "loss": 0.7379, "step": 129 }, { "epoch": 0.5265822784810127, "grad_norm": 0.5932258685559337, "learning_rate": 3.999605373449617e-05, "loss": 0.7358, "step": 130 }, { "epoch": 0.5306329113924051, "grad_norm": 0.6616167248972982, "learning_rate": 3.9994845745926075e-05, "loss": 0.7498, "step": 131 }, { "epoch": 0.5346835443037975, "grad_norm": 0.6799884867087881, "learning_rate": 3.999347672161713e-05, "loss": 0.7697, "step": 132 }, { "epoch": 0.5387341772151899, "grad_norm": 0.7090093015642288, "learning_rate": 3.999194667259528e-05, "loss": 0.7698, "step": 133 }, { "epoch": 0.5427848101265823, "grad_norm": 0.6417255037349836, "learning_rate": 3.999025561118334e-05, "loss": 0.7289, "step": 134 }, { "epoch": 0.5468354430379747, "grad_norm": 0.767484171094409, "learning_rate": 3.998840355100086e-05, "loss": 0.7641, "step": 135 }, { "epoch": 0.5508860759493671, "grad_norm": 0.6192530889614214, "learning_rate": 3.998639050696409e-05, "loss": 0.6943, "step": 136 }, { "epoch": 0.5549367088607595, "grad_norm": 0.7150167152610103, "learning_rate": 3.998421649528582e-05, "loss": 0.7278, "step": 137 }, { "epoch": 0.5589873417721519, "grad_norm": 0.7043765042343055, "learning_rate": 3.9981881533475234e-05, "loss": 0.7499, "step": 138 }, { "epoch": 0.5630379746835443, "grad_norm": 0.6545238348201198, "learning_rate": 3.997938564033779e-05, "loss": 0.7656, "step": 139 }, { "epoch": 0.5670886075949367, "grad_norm": 0.744206564664996, "learning_rate": 3.9976728835975064e-05, "loss": 0.7402, "step": 140 }, { "epoch": 0.5711392405063291, "grad_norm": 0.7640371659884408, "learning_rate": 3.9973911141784605e-05, "loss": 0.7672, "step": 141 }, { "epoch": 0.5751898734177215, "grad_norm": 0.5758676219089434, "learning_rate": 3.997093258045973e-05, "loss": 0.7421, "step": 142 }, { "epoch": 0.579240506329114, "grad_norm": 0.6687260586332134, "learning_rate": 3.996779317598936e-05, "loss": 0.7457, "step": 143 }, { "epoch": 0.5832911392405064, "grad_norm": 0.597936471753947, "learning_rate": 3.996449295365782e-05, "loss": 0.7117, "step": 144 }, { "epoch": 0.5873417721518988, "grad_norm": 0.6929210648397748, "learning_rate": 3.996103194004467e-05, "loss": 0.7255, "step": 145 }, { "epoch": 0.5913924050632912, "grad_norm": 0.5798551149992234, "learning_rate": 3.995741016302441e-05, "loss": 0.747, "step": 146 }, { "epoch": 0.5954430379746836, "grad_norm": 0.7202738110312024, "learning_rate": 3.9953627651766364e-05, "loss": 0.7383, "step": 147 }, { "epoch": 0.599493670886076, "grad_norm": 0.6597264913698653, "learning_rate": 3.9949684436734325e-05, "loss": 0.7753, "step": 148 }, { "epoch": 0.6035443037974684, "grad_norm": 0.7498489294061434, "learning_rate": 3.994558054968643e-05, "loss": 0.754, "step": 149 }, { "epoch": 0.6075949367088608, "grad_norm": 0.8535133636302471, "learning_rate": 3.994131602367481e-05, "loss": 0.7766, "step": 150 }, { "epoch": 0.6116455696202532, "grad_norm": 0.9300721538551066, "learning_rate": 3.9936890893045376e-05, "loss": 0.7317, "step": 151 }, { "epoch": 0.6156962025316456, "grad_norm": 0.914312047455553, "learning_rate": 3.993230519343752e-05, "loss": 0.7595, "step": 152 }, { "epoch": 0.619746835443038, "grad_norm": 0.6087539378246375, "learning_rate": 3.992755896178383e-05, "loss": 0.7465, "step": 153 }, { "epoch": 0.6237974683544304, "grad_norm": 0.960792786581662, "learning_rate": 3.992265223630981e-05, "loss": 0.7475, "step": 154 }, { "epoch": 0.6278481012658228, "grad_norm": 0.7708689456021359, "learning_rate": 3.991758505653355e-05, "loss": 0.7393, "step": 155 }, { "epoch": 0.6318987341772152, "grad_norm": 0.7073792001207944, "learning_rate": 3.991235746326543e-05, "loss": 0.7354, "step": 156 }, { "epoch": 0.6359493670886076, "grad_norm": 0.6628655657156053, "learning_rate": 3.9906969498607745e-05, "loss": 0.7481, "step": 157 }, { "epoch": 0.64, "grad_norm": 0.7462132302879445, "learning_rate": 3.990142120595444e-05, "loss": 0.735, "step": 158 }, { "epoch": 0.6440506329113924, "grad_norm": 0.9934906918472963, "learning_rate": 3.98957126299907e-05, "loss": 0.7178, "step": 159 }, { "epoch": 0.6481012658227848, "grad_norm": 0.5920882333795232, "learning_rate": 3.9889843816692596e-05, "loss": 0.7206, "step": 160 }, { "epoch": 0.6521518987341772, "grad_norm": 0.8976831579229084, "learning_rate": 3.9883814813326766e-05, "loss": 0.7333, "step": 161 }, { "epoch": 0.6562025316455696, "grad_norm": 0.6081491288950616, "learning_rate": 3.9877625668449956e-05, "loss": 0.7581, "step": 162 }, { "epoch": 0.660253164556962, "grad_norm": 0.6973125730386065, "learning_rate": 3.98712764319087e-05, "loss": 0.7472, "step": 163 }, { "epoch": 0.6643037974683544, "grad_norm": 0.5561853556342977, "learning_rate": 3.9864767154838864e-05, "loss": 0.7452, "step": 164 }, { "epoch": 0.6683544303797468, "grad_norm": 0.5984071104954163, "learning_rate": 3.9858097889665277e-05, "loss": 0.7392, "step": 165 }, { "epoch": 0.6724050632911392, "grad_norm": 0.6444414112644465, "learning_rate": 3.985126869010129e-05, "loss": 0.7447, "step": 166 }, { "epoch": 0.6764556962025317, "grad_norm": 0.6853455947413788, "learning_rate": 3.984427961114833e-05, "loss": 0.7294, "step": 167 }, { "epoch": 0.6805063291139241, "grad_norm": 0.5944146652539893, "learning_rate": 3.9837130709095475e-05, "loss": 0.7512, "step": 168 }, { "epoch": 0.6845569620253165, "grad_norm": 0.8301138165731975, "learning_rate": 3.982982204151901e-05, "loss": 0.7336, "step": 169 }, { "epoch": 0.6886075949367089, "grad_norm": 0.7712992388774709, "learning_rate": 3.982235366728193e-05, "loss": 0.7377, "step": 170 }, { "epoch": 0.6926582278481013, "grad_norm": 0.6021892841088475, "learning_rate": 3.9814725646533505e-05, "loss": 0.7432, "step": 171 }, { "epoch": 0.6967088607594937, "grad_norm": 0.7777538104350252, "learning_rate": 3.9806938040708746e-05, "loss": 0.6903, "step": 172 }, { "epoch": 0.7007594936708861, "grad_norm": 0.6870522327266188, "learning_rate": 3.9798990912527976e-05, "loss": 0.7171, "step": 173 }, { "epoch": 0.7048101265822785, "grad_norm": 0.5462555870425292, "learning_rate": 3.979088432599627e-05, "loss": 0.7497, "step": 174 }, { "epoch": 0.7088607594936709, "grad_norm": 0.6601026537220172, "learning_rate": 3.9782618346402964e-05, "loss": 0.7503, "step": 175 }, { "epoch": 0.7129113924050633, "grad_norm": 0.6616460712188492, "learning_rate": 3.977419304032111e-05, "loss": 0.7723, "step": 176 }, { "epoch": 0.7169620253164557, "grad_norm": 0.5738006578797245, "learning_rate": 3.976560847560697e-05, "loss": 0.7176, "step": 177 }, { "epoch": 0.7210126582278481, "grad_norm": 0.6662895137881383, "learning_rate": 3.9756864721399456e-05, "loss": 0.7482, "step": 178 }, { "epoch": 0.7250632911392405, "grad_norm": 0.6533422575622215, "learning_rate": 3.974796184811956e-05, "loss": 0.7308, "step": 179 }, { "epoch": 0.7291139240506329, "grad_norm": 0.592482932995099, "learning_rate": 3.973889992746979e-05, "loss": 0.7589, "step": 180 }, { "epoch": 0.7331645569620253, "grad_norm": 0.5807297191646881, "learning_rate": 3.972967903243361e-05, "loss": 0.7434, "step": 181 }, { "epoch": 0.7372151898734177, "grad_norm": 0.6656096949786168, "learning_rate": 3.972029923727486e-05, "loss": 0.7345, "step": 182 }, { "epoch": 0.7412658227848101, "grad_norm": 0.5769403319821189, "learning_rate": 3.971076061753709e-05, "loss": 0.7149, "step": 183 }, { "epoch": 0.7453164556962025, "grad_norm": 0.6205839059846194, "learning_rate": 3.9701063250043066e-05, "loss": 0.7583, "step": 184 }, { "epoch": 0.7493670886075949, "grad_norm": 0.5789504980431497, "learning_rate": 3.969120721289402e-05, "loss": 0.7289, "step": 185 }, { "epoch": 0.7534177215189873, "grad_norm": 0.5196131277095205, "learning_rate": 3.9681192585469146e-05, "loss": 0.7364, "step": 186 }, { "epoch": 0.7574683544303797, "grad_norm": 0.6393610191128531, "learning_rate": 3.9671019448424865e-05, "loss": 0.7103, "step": 187 }, { "epoch": 0.7615189873417721, "grad_norm": 0.5518490574347373, "learning_rate": 3.966068788369422e-05, "loss": 0.7547, "step": 188 }, { "epoch": 0.7655696202531646, "grad_norm": 0.6884357689483943, "learning_rate": 3.965019797448622e-05, "loss": 0.7158, "step": 189 }, { "epoch": 0.769620253164557, "grad_norm": 0.5800172530800768, "learning_rate": 3.963954980528515e-05, "loss": 0.7274, "step": 190 }, { "epoch": 0.7736708860759494, "grad_norm": 0.7508961563940924, "learning_rate": 3.9628743461849905e-05, "loss": 0.7207, "step": 191 }, { "epoch": 0.7777215189873418, "grad_norm": 0.6618572451663217, "learning_rate": 3.961777903121329e-05, "loss": 0.7164, "step": 192 }, { "epoch": 0.7817721518987342, "grad_norm": 0.6314066440278383, "learning_rate": 3.960665660168131e-05, "loss": 0.7332, "step": 193 }, { "epoch": 0.7858227848101266, "grad_norm": 0.6866171674348558, "learning_rate": 3.9595376262832485e-05, "loss": 0.7657, "step": 194 }, { "epoch": 0.789873417721519, "grad_norm": 0.6075617629344732, "learning_rate": 3.9583938105517127e-05, "loss": 0.7328, "step": 195 }, { "epoch": 0.7939240506329114, "grad_norm": 0.5818610180931061, "learning_rate": 3.957234222185657e-05, "loss": 0.7176, "step": 196 }, { "epoch": 0.7979746835443038, "grad_norm": 0.7046740263610167, "learning_rate": 3.9560588705242474e-05, "loss": 0.7206, "step": 197 }, { "epoch": 0.8020253164556962, "grad_norm": 0.5470943745284134, "learning_rate": 3.954867765033605e-05, "loss": 0.7182, "step": 198 }, { "epoch": 0.8060759493670886, "grad_norm": 0.5931717106833055, "learning_rate": 3.953660915306728e-05, "loss": 0.7602, "step": 199 }, { "epoch": 0.810126582278481, "grad_norm": 0.6403789810772467, "learning_rate": 3.952438331063419e-05, "loss": 0.7164, "step": 200 }, { "epoch": 0.8141772151898734, "grad_norm": 0.7134347554999481, "learning_rate": 3.951200022150205e-05, "loss": 0.7213, "step": 201 }, { "epoch": 0.8182278481012658, "grad_norm": 0.5650996890368802, "learning_rate": 3.949945998540253e-05, "loss": 0.7363, "step": 202 }, { "epoch": 0.8222784810126582, "grad_norm": 0.7686066933689085, "learning_rate": 3.9486762703332993e-05, "loss": 0.7205, "step": 203 }, { "epoch": 0.8263291139240506, "grad_norm": 0.6239097556137108, "learning_rate": 3.947390847755559e-05, "loss": 0.6968, "step": 204 }, { "epoch": 0.830379746835443, "grad_norm": 0.7076119884633175, "learning_rate": 3.946089741159648e-05, "loss": 0.7355, "step": 205 }, { "epoch": 0.8344303797468354, "grad_norm": 0.800778500998784, "learning_rate": 3.944772961024501e-05, "loss": 0.7468, "step": 206 }, { "epoch": 0.8384810126582278, "grad_norm": 0.6386465865619962, "learning_rate": 3.943440517955285e-05, "loss": 0.7081, "step": 207 }, { "epoch": 0.8425316455696202, "grad_norm": 0.7267712485811015, "learning_rate": 3.9420924226833126e-05, "loss": 0.7089, "step": 208 }, { "epoch": 0.8465822784810126, "grad_norm": 0.7204073917956011, "learning_rate": 3.9407286860659566e-05, "loss": 0.7164, "step": 209 }, { "epoch": 0.850632911392405, "grad_norm": 0.6967915063359004, "learning_rate": 3.9393493190865657e-05, "loss": 0.7197, "step": 210 }, { "epoch": 0.8546835443037974, "grad_norm": 0.5604598898173442, "learning_rate": 3.937954332854371e-05, "loss": 0.7342, "step": 211 }, { "epoch": 0.8587341772151899, "grad_norm": 0.6917350580092844, "learning_rate": 3.9365437386044016e-05, "loss": 0.7225, "step": 212 }, { "epoch": 0.8627848101265823, "grad_norm": 0.610108602973472, "learning_rate": 3.935117547697387e-05, "loss": 0.7228, "step": 213 }, { "epoch": 0.8668354430379747, "grad_norm": 0.6346331524091475, "learning_rate": 3.933675771619675e-05, "loss": 0.7369, "step": 214 }, { "epoch": 0.8708860759493671, "grad_norm": 0.6377756487444797, "learning_rate": 3.932218421983131e-05, "loss": 0.7247, "step": 215 }, { "epoch": 0.8749367088607595, "grad_norm": 0.5498045556386334, "learning_rate": 3.9307455105250484e-05, "loss": 0.7189, "step": 216 }, { "epoch": 0.8789873417721519, "grad_norm": 0.6432813556027215, "learning_rate": 3.929257049108054e-05, "loss": 0.6953, "step": 217 }, { "epoch": 0.8830379746835443, "grad_norm": 0.622393756047167, "learning_rate": 3.927753049720011e-05, "loss": 0.687, "step": 218 }, { "epoch": 0.8870886075949367, "grad_norm": 0.7040927223029406, "learning_rate": 3.9262335244739234e-05, "loss": 0.7202, "step": 219 }, { "epoch": 0.8911392405063291, "grad_norm": 0.612745343242423, "learning_rate": 3.92469848560784e-05, "loss": 0.6974, "step": 220 }, { "epoch": 0.8951898734177215, "grad_norm": 0.9133269412572617, "learning_rate": 3.923147945484751e-05, "loss": 0.7319, "step": 221 }, { "epoch": 0.8992405063291139, "grad_norm": 0.8042659651732839, "learning_rate": 3.9215819165924956e-05, "loss": 0.716, "step": 222 }, { "epoch": 0.9032911392405063, "grad_norm": 0.6551201569233529, "learning_rate": 3.920000411543654e-05, "loss": 0.7295, "step": 223 }, { "epoch": 0.9073417721518987, "grad_norm": 0.6653083166687069, "learning_rate": 3.9184034430754495e-05, "loss": 0.7113, "step": 224 }, { "epoch": 0.9113924050632911, "grad_norm": 0.6232210179029516, "learning_rate": 3.916791024049648e-05, "loss": 0.7168, "step": 225 }, { "epoch": 0.9154430379746835, "grad_norm": 0.5621184300944095, "learning_rate": 3.91516316745245e-05, "loss": 0.6887, "step": 226 }, { "epoch": 0.9194936708860759, "grad_norm": 0.727106581758039, "learning_rate": 3.913519886394389e-05, "loss": 0.7457, "step": 227 }, { "epoch": 0.9235443037974683, "grad_norm": 0.5119750727468806, "learning_rate": 3.911861194110225e-05, "loss": 0.7257, "step": 228 }, { "epoch": 0.9275949367088607, "grad_norm": 0.8307030460111904, "learning_rate": 3.910187103958837e-05, "loss": 0.7039, "step": 229 }, { "epoch": 0.9316455696202531, "grad_norm": 0.6315071084292455, "learning_rate": 3.908497629423117e-05, "loss": 0.7037, "step": 230 }, { "epoch": 0.9356962025316455, "grad_norm": 0.6822123256406369, "learning_rate": 3.9067927841098614e-05, "loss": 0.706, "step": 231 }, { "epoch": 0.9397468354430379, "grad_norm": 0.8412263659187679, "learning_rate": 3.9050725817496594e-05, "loss": 0.6882, "step": 232 }, { "epoch": 0.9437974683544303, "grad_norm": 0.5078983958932715, "learning_rate": 3.9033370361967844e-05, "loss": 0.7139, "step": 233 }, { "epoch": 0.9478481012658228, "grad_norm": 0.9323828619251081, "learning_rate": 3.901586161429081e-05, "loss": 0.7232, "step": 234 }, { "epoch": 0.9518987341772152, "grad_norm": 0.6751634864233157, "learning_rate": 3.8998199715478545e-05, "loss": 0.7029, "step": 235 }, { "epoch": 0.9559493670886076, "grad_norm": 0.6054475312283332, "learning_rate": 3.8980384807777564e-05, "loss": 0.7253, "step": 236 }, { "epoch": 0.96, "grad_norm": 0.719102820823043, "learning_rate": 3.896241703466667e-05, "loss": 0.7069, "step": 237 }, { "epoch": 0.9640506329113924, "grad_norm": 0.5122119075681233, "learning_rate": 3.894429654085585e-05, "loss": 0.7051, "step": 238 }, { "epoch": 0.9681012658227848, "grad_norm": 0.7684709465274283, "learning_rate": 3.892602347228505e-05, "loss": 0.6988, "step": 239 }, { "epoch": 0.9721518987341772, "grad_norm": 0.5877524926996377, "learning_rate": 3.890759797612307e-05, "loss": 0.7299, "step": 240 }, { "epoch": 0.9762025316455696, "grad_norm": 0.5716701868602969, "learning_rate": 3.888902020076632e-05, "loss": 0.7371, "step": 241 }, { "epoch": 0.980253164556962, "grad_norm": 0.5891136390524694, "learning_rate": 3.887029029583764e-05, "loss": 0.6945, "step": 242 }, { "epoch": 0.9843037974683544, "grad_norm": 0.6611228754472508, "learning_rate": 3.8851408412185125e-05, "loss": 0.7123, "step": 243 }, { "epoch": 0.9883544303797468, "grad_norm": 0.5900788938987879, "learning_rate": 3.8832374701880855e-05, "loss": 0.6985, "step": 244 }, { "epoch": 0.9924050632911392, "grad_norm": 0.7233320216477909, "learning_rate": 3.881318931821972e-05, "loss": 0.7011, "step": 245 }, { "epoch": 0.9964556962025316, "grad_norm": 0.5602002034733525, "learning_rate": 3.879385241571817e-05, "loss": 0.7258, "step": 246 }, { "epoch": 1.0035443037974683, "grad_norm": 0.7014699125216525, "learning_rate": 3.8774364150112955e-05, "loss": 0.58, "step": 247 }, { "epoch": 1.0075949367088608, "grad_norm": 0.5134664020785975, "learning_rate": 3.8754724678359884e-05, "loss": 0.5471, "step": 248 }, { "epoch": 1.011645569620253, "grad_norm": 0.7644830357961151, "learning_rate": 3.873493415863256e-05, "loss": 0.5822, "step": 249 }, { "epoch": 1.0156962025316456, "grad_norm": 0.7987852768219524, "learning_rate": 3.871499275032111e-05, "loss": 0.5646, "step": 250 }, { "epoch": 1.019746835443038, "grad_norm": 0.6743252971405668, "learning_rate": 3.869490061403091e-05, "loss": 0.5701, "step": 251 }, { "epoch": 1.0237974683544304, "grad_norm": 0.7303006779394623, "learning_rate": 3.867465791158124e-05, "loss": 0.5376, "step": 252 }, { "epoch": 1.0278481012658227, "grad_norm": 0.6757891665981549, "learning_rate": 3.865426480600407e-05, "loss": 0.5718, "step": 253 }, { "epoch": 1.0318987341772152, "grad_norm": 0.6666322156810555, "learning_rate": 3.863372146154264e-05, "loss": 0.5471, "step": 254 }, { "epoch": 1.0359493670886075, "grad_norm": 0.6458782297025127, "learning_rate": 3.861302804365024e-05, "loss": 0.5366, "step": 255 }, { "epoch": 1.04, "grad_norm": 0.6286623153189377, "learning_rate": 3.85921847189888e-05, "loss": 0.5832, "step": 256 }, { "epoch": 1.0440506329113923, "grad_norm": 0.5913223596064575, "learning_rate": 3.85711916554276e-05, "loss": 0.5557, "step": 257 }, { "epoch": 1.0481012658227848, "grad_norm": 0.6386635997005276, "learning_rate": 3.85500490220419e-05, "loss": 0.5819, "step": 258 }, { "epoch": 1.0521518987341771, "grad_norm": 0.724066350833484, "learning_rate": 3.852875698911154e-05, "loss": 0.5839, "step": 259 }, { "epoch": 1.0562025316455697, "grad_norm": 0.5976403432991646, "learning_rate": 3.850731572811963e-05, "loss": 0.5594, "step": 260 }, { "epoch": 1.060253164556962, "grad_norm": 0.6598395900183405, "learning_rate": 3.848572541175116e-05, "loss": 0.5764, "step": 261 }, { "epoch": 1.0643037974683545, "grad_norm": 0.6158519833647585, "learning_rate": 3.846398621389154e-05, "loss": 0.5697, "step": 262 }, { "epoch": 1.0683544303797468, "grad_norm": 0.7090100891273579, "learning_rate": 3.84420983096253e-05, "loss": 0.5445, "step": 263 }, { "epoch": 1.0724050632911393, "grad_norm": 0.6175266019763572, "learning_rate": 3.8420061875234606e-05, "loss": 0.5781, "step": 264 }, { "epoch": 1.0764556962025316, "grad_norm": 0.584782760862572, "learning_rate": 3.839787708819787e-05, "loss": 0.5429, "step": 265 }, { "epoch": 1.080506329113924, "grad_norm": 0.731163485474329, "learning_rate": 3.8375544127188325e-05, "loss": 0.5373, "step": 266 }, { "epoch": 1.0845569620253164, "grad_norm": 0.6728855433459935, "learning_rate": 3.8353063172072564e-05, "loss": 0.5503, "step": 267 }, { "epoch": 1.0886075949367089, "grad_norm": 0.6746251920086807, "learning_rate": 3.8330434403909105e-05, "loss": 0.5629, "step": 268 }, { "epoch": 1.0926582278481012, "grad_norm": 0.6634905320980594, "learning_rate": 3.8307658004946934e-05, "loss": 0.564, "step": 269 }, { "epoch": 1.0967088607594937, "grad_norm": 0.6439500257294353, "learning_rate": 3.8284734158624046e-05, "loss": 0.5679, "step": 270 }, { "epoch": 1.100759493670886, "grad_norm": 0.6294021393877629, "learning_rate": 3.826166304956594e-05, "loss": 0.5591, "step": 271 }, { "epoch": 1.1048101265822785, "grad_norm": 0.6824563062224214, "learning_rate": 3.8238444863584164e-05, "loss": 0.545, "step": 272 }, { "epoch": 1.1088607594936708, "grad_norm": 0.6374961698187569, "learning_rate": 3.821507978767479e-05, "loss": 0.5436, "step": 273 }, { "epoch": 1.1129113924050633, "grad_norm": 0.6525230180970678, "learning_rate": 3.819156801001693e-05, "loss": 0.5554, "step": 274 }, { "epoch": 1.1169620253164556, "grad_norm": 0.5666479146921168, "learning_rate": 3.816790971997121e-05, "loss": 0.5642, "step": 275 }, { "epoch": 1.1210126582278481, "grad_norm": 0.6708010290047222, "learning_rate": 3.8144105108078246e-05, "loss": 0.5629, "step": 276 }, { "epoch": 1.1250632911392404, "grad_norm": 0.6319073307208358, "learning_rate": 3.81201543660571e-05, "loss": 0.5661, "step": 277 }, { "epoch": 1.129113924050633, "grad_norm": 0.6288750340727314, "learning_rate": 3.809605768680377e-05, "loss": 0.5645, "step": 278 }, { "epoch": 1.1331645569620252, "grad_norm": 0.6788573344595952, "learning_rate": 3.807181526438958e-05, "loss": 0.5643, "step": 279 }, { "epoch": 1.1372151898734177, "grad_norm": 0.563921043211934, "learning_rate": 3.8047427294059697e-05, "loss": 0.5567, "step": 280 }, { "epoch": 1.14126582278481, "grad_norm": 0.7034973409510822, "learning_rate": 3.802289397223145e-05, "loss": 0.5512, "step": 281 }, { "epoch": 1.1453164556962026, "grad_norm": 0.6491264024550745, "learning_rate": 3.7998215496492854e-05, "loss": 0.5417, "step": 282 }, { "epoch": 1.1493670886075948, "grad_norm": 0.5815918300599945, "learning_rate": 3.797339206560096e-05, "loss": 0.5586, "step": 283 }, { "epoch": 1.1534177215189874, "grad_norm": 0.6017015016494089, "learning_rate": 3.794842387948027e-05, "loss": 0.5509, "step": 284 }, { "epoch": 1.1574683544303797, "grad_norm": 0.5680194485456105, "learning_rate": 3.7923311139221114e-05, "loss": 0.5423, "step": 285 }, { "epoch": 1.1615189873417722, "grad_norm": 0.4803497525155686, "learning_rate": 3.7898054047078054e-05, "loss": 0.543, "step": 286 }, { "epoch": 1.1655696202531645, "grad_norm": 0.6309619052584903, "learning_rate": 3.787265280646825e-05, "loss": 0.5804, "step": 287 }, { "epoch": 1.169620253164557, "grad_norm": 0.5267721079590533, "learning_rate": 3.7847107621969786e-05, "loss": 0.5512, "step": 288 }, { "epoch": 1.1736708860759493, "grad_norm": 0.5988631109380446, "learning_rate": 3.7821418699320064e-05, "loss": 0.5447, "step": 289 }, { "epoch": 1.1777215189873418, "grad_norm": 0.6079978710741833, "learning_rate": 3.7795586245414145e-05, "loss": 0.564, "step": 290 }, { "epoch": 1.181772151898734, "grad_norm": 0.5454901160971208, "learning_rate": 3.776961046830306e-05, "loss": 0.5946, "step": 291 }, { "epoch": 1.1858227848101266, "grad_norm": 0.574123929220275, "learning_rate": 3.774349157719215e-05, "loss": 0.5308, "step": 292 }, { "epoch": 1.189873417721519, "grad_norm": 0.5425924858347201, "learning_rate": 3.7717229782439365e-05, "loss": 0.5752, "step": 293 }, { "epoch": 1.1939240506329114, "grad_norm": 0.6000927271190132, "learning_rate": 3.769082529555359e-05, "loss": 0.5576, "step": 294 }, { "epoch": 1.1979746835443037, "grad_norm": 0.5215513102764391, "learning_rate": 3.766427832919294e-05, "loss": 0.581, "step": 295 }, { "epoch": 1.2020253164556962, "grad_norm": 0.6260667055964407, "learning_rate": 3.7637589097163024e-05, "loss": 0.5665, "step": 296 }, { "epoch": 1.2060759493670887, "grad_norm": 0.5766802321021245, "learning_rate": 3.761075781441526e-05, "loss": 0.561, "step": 297 }, { "epoch": 1.210126582278481, "grad_norm": 0.518625383686056, "learning_rate": 3.75837846970451e-05, "loss": 0.5475, "step": 298 }, { "epoch": 1.2141772151898733, "grad_norm": 0.6388295340036321, "learning_rate": 3.755666996229032e-05, "loss": 0.5383, "step": 299 }, { "epoch": 1.2182278481012658, "grad_norm": 0.5162231306101828, "learning_rate": 3.752941382852927e-05, "loss": 0.5747, "step": 300 }, { "epoch": 1.2222784810126583, "grad_norm": 0.6815653584549144, "learning_rate": 3.7502016515279115e-05, "loss": 0.563, "step": 301 }, { "epoch": 1.2263291139240506, "grad_norm": 0.5580077791561577, "learning_rate": 3.7474478243194043e-05, "loss": 0.5687, "step": 302 }, { "epoch": 1.230379746835443, "grad_norm": 0.610250990342235, "learning_rate": 3.744679923406351e-05, "loss": 0.5682, "step": 303 }, { "epoch": 1.2344303797468354, "grad_norm": 0.5496592162511872, "learning_rate": 3.741897971081043e-05, "loss": 0.5589, "step": 304 }, { "epoch": 1.238481012658228, "grad_norm": 0.6259914291676074, "learning_rate": 3.739101989748946e-05, "loss": 0.553, "step": 305 }, { "epoch": 1.2425316455696203, "grad_norm": 0.7197800986719136, "learning_rate": 3.7362920019285066e-05, "loss": 0.5796, "step": 306 }, { "epoch": 1.2465822784810126, "grad_norm": 0.5381743848604148, "learning_rate": 3.73346803025098e-05, "loss": 0.5563, "step": 307 }, { "epoch": 1.250632911392405, "grad_norm": 0.7286548355318839, "learning_rate": 3.730630097460247e-05, "loss": 0.5736, "step": 308 }, { "epoch": 1.2546835443037976, "grad_norm": 0.6837117261889876, "learning_rate": 3.727778226412628e-05, "loss": 0.5479, "step": 309 }, { "epoch": 1.2587341772151899, "grad_norm": 0.519025364717673, "learning_rate": 3.7249124400767006e-05, "loss": 0.5399, "step": 310 }, { "epoch": 1.2627848101265822, "grad_norm": 0.7871516135329399, "learning_rate": 3.722032761533114e-05, "loss": 0.537, "step": 311 }, { "epoch": 1.2668354430379747, "grad_norm": 0.5555319667262646, "learning_rate": 3.719139213974403e-05, "loss": 0.5385, "step": 312 }, { "epoch": 1.2708860759493672, "grad_norm": 0.7683792249634375, "learning_rate": 3.7162318207048006e-05, "loss": 0.5653, "step": 313 }, { "epoch": 1.2749367088607595, "grad_norm": 0.5983652598035072, "learning_rate": 3.713310605140055e-05, "loss": 0.585, "step": 314 }, { "epoch": 1.2789873417721518, "grad_norm": 0.5700659104820841, "learning_rate": 3.710375590807233e-05, "loss": 0.5756, "step": 315 }, { "epoch": 1.2830379746835443, "grad_norm": 0.5346829718638582, "learning_rate": 3.7074268013445365e-05, "loss": 0.5574, "step": 316 }, { "epoch": 1.2870886075949368, "grad_norm": 0.5461623781618027, "learning_rate": 3.7044642605011114e-05, "loss": 0.579, "step": 317 }, { "epoch": 1.2911392405063291, "grad_norm": 0.5361672066210256, "learning_rate": 3.701487992136854e-05, "loss": 0.5709, "step": 318 }, { "epoch": 1.2951898734177214, "grad_norm": 0.49547049511178315, "learning_rate": 3.69849802022222e-05, "loss": 0.5378, "step": 319 }, { "epoch": 1.299240506329114, "grad_norm": 0.5249425185145739, "learning_rate": 3.6954943688380334e-05, "loss": 0.5577, "step": 320 }, { "epoch": 1.3032911392405064, "grad_norm": 0.5063879384796005, "learning_rate": 3.692477062175289e-05, "loss": 0.5551, "step": 321 }, { "epoch": 1.3073417721518987, "grad_norm": 0.5370821298592654, "learning_rate": 3.689446124534958e-05, "loss": 0.5731, "step": 322 }, { "epoch": 1.311392405063291, "grad_norm": 0.5544168018644121, "learning_rate": 3.686401580327799e-05, "loss": 0.567, "step": 323 }, { "epoch": 1.3154430379746835, "grad_norm": 0.4838934761089717, "learning_rate": 3.683343454074149e-05, "loss": 0.5656, "step": 324 }, { "epoch": 1.319493670886076, "grad_norm": 0.6441064115712677, "learning_rate": 3.6802717704037386e-05, "loss": 0.5468, "step": 325 }, { "epoch": 1.3235443037974683, "grad_norm": 0.5003082842981311, "learning_rate": 3.6771865540554855e-05, "loss": 0.5747, "step": 326 }, { "epoch": 1.3275949367088606, "grad_norm": 0.5179662719824416, "learning_rate": 3.674087829877297e-05, "loss": 0.5559, "step": 327 }, { "epoch": 1.3316455696202532, "grad_norm": 0.49169184853130965, "learning_rate": 3.6709756228258735e-05, "loss": 0.5651, "step": 328 }, { "epoch": 1.3356962025316457, "grad_norm": 0.5083818366133815, "learning_rate": 3.667849957966501e-05, "loss": 0.5568, "step": 329 }, { "epoch": 1.339746835443038, "grad_norm": 0.5671061803863471, "learning_rate": 3.6647108604728546e-05, "loss": 0.5542, "step": 330 }, { "epoch": 1.3437974683544303, "grad_norm": 0.5633747934581307, "learning_rate": 3.661558355626795e-05, "loss": 0.5623, "step": 331 }, { "epoch": 1.3478481012658228, "grad_norm": 0.6023132798766525, "learning_rate": 3.658392468818163e-05, "loss": 0.571, "step": 332 }, { "epoch": 1.3518987341772153, "grad_norm": 0.5508644616343382, "learning_rate": 3.655213225544574e-05, "loss": 0.5594, "step": 333 }, { "epoch": 1.3559493670886076, "grad_norm": 0.5795133757579268, "learning_rate": 3.652020651411218e-05, "loss": 0.5551, "step": 334 }, { "epoch": 1.3599999999999999, "grad_norm": 0.560710605259107, "learning_rate": 3.6488147721306474e-05, "loss": 0.5266, "step": 335 }, { "epoch": 1.3640506329113924, "grad_norm": 0.5766223943257023, "learning_rate": 3.645595613522574e-05, "loss": 0.5391, "step": 336 }, { "epoch": 1.368101265822785, "grad_norm": 0.6091343094156372, "learning_rate": 3.642363201513657e-05, "loss": 0.5601, "step": 337 }, { "epoch": 1.3721518987341772, "grad_norm": 0.6247393075010931, "learning_rate": 3.6391175621373006e-05, "loss": 0.5897, "step": 338 }, { "epoch": 1.3762025316455695, "grad_norm": 0.5868635781551573, "learning_rate": 3.6358587215334355e-05, "loss": 0.5548, "step": 339 }, { "epoch": 1.380253164556962, "grad_norm": 0.6777975537322507, "learning_rate": 3.632586705948318e-05, "loss": 0.5488, "step": 340 }, { "epoch": 1.3843037974683545, "grad_norm": 0.5367436651387679, "learning_rate": 3.629301541734311e-05, "loss": 0.5532, "step": 341 }, { "epoch": 1.3883544303797468, "grad_norm": 0.6340411328276255, "learning_rate": 3.626003255349676e-05, "loss": 0.5849, "step": 342 }, { "epoch": 1.3924050632911391, "grad_norm": 0.5697244390706054, "learning_rate": 3.622691873358357e-05, "loss": 0.5823, "step": 343 }, { "epoch": 1.3964556962025316, "grad_norm": 0.5360891924299327, "learning_rate": 3.61936742242977e-05, "loss": 0.5457, "step": 344 }, { "epoch": 1.4005063291139241, "grad_norm": 0.5477971442165089, "learning_rate": 3.6160299293385864e-05, "loss": 0.5618, "step": 345 }, { "epoch": 1.4045569620253164, "grad_norm": 0.5676838786792199, "learning_rate": 3.612679420964516e-05, "loss": 0.5828, "step": 346 }, { "epoch": 1.4086075949367087, "grad_norm": 0.5434940370205507, "learning_rate": 3.609315924292092e-05, "loss": 0.577, "step": 347 }, { "epoch": 1.4126582278481012, "grad_norm": 0.5894339597201111, "learning_rate": 3.6059394664104554e-05, "loss": 0.5608, "step": 348 }, { "epoch": 1.4167088607594938, "grad_norm": 0.4908453447047969, "learning_rate": 3.602550074513133e-05, "loss": 0.5714, "step": 349 }, { "epoch": 1.420759493670886, "grad_norm": 0.5980373932845037, "learning_rate": 3.599147775897822e-05, "loss": 0.5627, "step": 350 }, { "epoch": 1.4248101265822783, "grad_norm": 0.5185428994640007, "learning_rate": 3.595732597966167e-05, "loss": 0.5541, "step": 351 }, { "epoch": 1.4288607594936709, "grad_norm": 0.5889266400658042, "learning_rate": 3.592304568223542e-05, "loss": 0.5599, "step": 352 }, { "epoch": 1.4329113924050634, "grad_norm": 0.5161032596463916, "learning_rate": 3.588863714278826e-05, "loss": 0.5584, "step": 353 }, { "epoch": 1.4369620253164557, "grad_norm": 0.5471646346206313, "learning_rate": 3.585410063844186e-05, "loss": 0.5669, "step": 354 }, { "epoch": 1.441012658227848, "grad_norm": 0.5228874384772896, "learning_rate": 3.581943644734846e-05, "loss": 0.5739, "step": 355 }, { "epoch": 1.4450632911392405, "grad_norm": 0.48987410163966416, "learning_rate": 3.578464484868869e-05, "loss": 0.5508, "step": 356 }, { "epoch": 1.449113924050633, "grad_norm": 0.5119619382772498, "learning_rate": 3.5749726122669316e-05, "loss": 0.5513, "step": 357 }, { "epoch": 1.4531645569620253, "grad_norm": 0.5430192172168714, "learning_rate": 3.5714680550520943e-05, "loss": 0.5976, "step": 358 }, { "epoch": 1.4572151898734178, "grad_norm": 0.48143146946478854, "learning_rate": 3.5679508414495794e-05, "loss": 0.572, "step": 359 }, { "epoch": 1.46126582278481, "grad_norm": 0.5239989845331281, "learning_rate": 3.564420999786543e-05, "loss": 0.5839, "step": 360 }, { "epoch": 1.4653164556962026, "grad_norm": 0.5384514521907741, "learning_rate": 3.560878558491842e-05, "loss": 0.5658, "step": 361 }, { "epoch": 1.469367088607595, "grad_norm": 0.5223186935786868, "learning_rate": 3.5573235460958145e-05, "loss": 0.5508, "step": 362 }, { "epoch": 1.4734177215189874, "grad_norm": 0.5569471546301898, "learning_rate": 3.553755991230039e-05, "loss": 0.5772, "step": 363 }, { "epoch": 1.4774683544303797, "grad_norm": 0.5594319056035232, "learning_rate": 3.5501759226271144e-05, "loss": 0.5669, "step": 364 }, { "epoch": 1.4815189873417722, "grad_norm": 0.5938170250672647, "learning_rate": 3.546583369120419e-05, "loss": 0.5628, "step": 365 }, { "epoch": 1.4855696202531645, "grad_norm": 0.5134420590165855, "learning_rate": 3.5429783596438864e-05, "loss": 0.5649, "step": 366 }, { "epoch": 1.489620253164557, "grad_norm": 0.5576961067749329, "learning_rate": 3.539360923231766e-05, "loss": 0.5736, "step": 367 }, { "epoch": 1.4936708860759493, "grad_norm": 0.5417349510954129, "learning_rate": 3.535731089018394e-05, "loss": 0.5848, "step": 368 }, { "epoch": 1.4977215189873418, "grad_norm": 0.5176225353369023, "learning_rate": 3.532088886237956e-05, "loss": 0.5462, "step": 369 }, { "epoch": 1.5017721518987341, "grad_norm": 0.6054797208523894, "learning_rate": 3.528434344224253e-05, "loss": 0.5778, "step": 370 }, { "epoch": 1.5058227848101264, "grad_norm": 0.5322359966341991, "learning_rate": 3.524767492410464e-05, "loss": 0.5655, "step": 371 }, { "epoch": 1.509873417721519, "grad_norm": 0.586770179721397, "learning_rate": 3.521088360328908e-05, "loss": 0.5764, "step": 372 }, { "epoch": 1.5139240506329115, "grad_norm": 0.5389764979308144, "learning_rate": 3.517396977610811e-05, "loss": 0.5479, "step": 373 }, { "epoch": 1.5179746835443038, "grad_norm": 0.6096411193679818, "learning_rate": 3.5136933739860595e-05, "loss": 0.5684, "step": 374 }, { "epoch": 1.522025316455696, "grad_norm": 0.5925702549500166, "learning_rate": 3.509977579282971e-05, "loss": 0.5407, "step": 375 }, { "epoch": 1.5260759493670886, "grad_norm": 0.5695892670488125, "learning_rate": 3.5062496234280424e-05, "loss": 0.5602, "step": 376 }, { "epoch": 1.530126582278481, "grad_norm": 0.6155187984863116, "learning_rate": 3.502509536445719e-05, "loss": 0.5649, "step": 377 }, { "epoch": 1.5341772151898734, "grad_norm": 0.599375666853206, "learning_rate": 3.498757348458147e-05, "loss": 0.5452, "step": 378 }, { "epoch": 1.5382278481012657, "grad_norm": 0.6424039536808906, "learning_rate": 3.4949930896849324e-05, "loss": 0.5805, "step": 379 }, { "epoch": 1.5422784810126582, "grad_norm": 0.5260204519883275, "learning_rate": 3.491216790442899e-05, "loss": 0.5666, "step": 380 }, { "epoch": 1.5463291139240507, "grad_norm": 0.5536933600365466, "learning_rate": 3.487428481145839e-05, "loss": 0.5973, "step": 381 }, { "epoch": 1.550379746835443, "grad_norm": 0.528298530384041, "learning_rate": 3.483628192304278e-05, "loss": 0.542, "step": 382 }, { "epoch": 1.5544303797468353, "grad_norm": 0.4982479315073803, "learning_rate": 3.479815954525219e-05, "loss": 0.5834, "step": 383 }, { "epoch": 1.5584810126582278, "grad_norm": 0.5503970875962653, "learning_rate": 3.475991798511899e-05, "loss": 0.548, "step": 384 }, { "epoch": 1.5625316455696203, "grad_norm": 0.5528578546134313, "learning_rate": 3.4721557550635464e-05, "loss": 0.5705, "step": 385 }, { "epoch": 1.5665822784810126, "grad_norm": 0.5117583326648169, "learning_rate": 3.468307855075128e-05, "loss": 0.5523, "step": 386 }, { "epoch": 1.570632911392405, "grad_norm": 0.5606428614014143, "learning_rate": 3.4644481295371005e-05, "loss": 0.5444, "step": 387 }, { "epoch": 1.5746835443037974, "grad_norm": 0.5284641782180975, "learning_rate": 3.460576609535163e-05, "loss": 0.5422, "step": 388 }, { "epoch": 1.57873417721519, "grad_norm": 0.5276719774731623, "learning_rate": 3.456693326250006e-05, "loss": 0.576, "step": 389 }, { "epoch": 1.5827848101265822, "grad_norm": 0.5932805860193057, "learning_rate": 3.452798310957058e-05, "loss": 0.5646, "step": 390 }, { "epoch": 1.5868354430379745, "grad_norm": 0.48945256322931074, "learning_rate": 3.4488915950262386e-05, "loss": 0.5486, "step": 391 }, { "epoch": 1.590886075949367, "grad_norm": 0.5785235894348286, "learning_rate": 3.4449732099216985e-05, "loss": 0.5828, "step": 392 }, { "epoch": 1.5949367088607596, "grad_norm": 0.5060243816210529, "learning_rate": 3.441043187201574e-05, "loss": 0.5756, "step": 393 }, { "epoch": 1.5989873417721518, "grad_norm": 0.6027357508236273, "learning_rate": 3.437101558517728e-05, "loss": 0.5843, "step": 394 }, { "epoch": 1.6030379746835441, "grad_norm": 0.5409219010036468, "learning_rate": 3.433148355615496e-05, "loss": 0.5872, "step": 395 }, { "epoch": 1.6070886075949367, "grad_norm": 0.5515424556627629, "learning_rate": 3.4291836103334294e-05, "loss": 0.574, "step": 396 }, { "epoch": 1.6111392405063292, "grad_norm": 0.5911671106532894, "learning_rate": 3.425207354603043e-05, "loss": 0.5779, "step": 397 }, { "epoch": 1.6151898734177215, "grad_norm": 0.49736413358637854, "learning_rate": 3.421219620448553e-05, "loss": 0.5477, "step": 398 }, { "epoch": 1.6192405063291138, "grad_norm": 0.6153083366514016, "learning_rate": 3.417220439986623e-05, "loss": 0.5854, "step": 399 }, { "epoch": 1.6232911392405063, "grad_norm": 0.48191141581212044, "learning_rate": 3.4132098454261024e-05, "loss": 0.5725, "step": 400 }, { "epoch": 1.6273417721518988, "grad_norm": 0.5739701203052112, "learning_rate": 3.4091878690677676e-05, "loss": 0.5884, "step": 401 }, { "epoch": 1.631392405063291, "grad_norm": 0.4809503743606984, "learning_rate": 3.405154543304065e-05, "loss": 0.534, "step": 402 }, { "epoch": 1.6354430379746834, "grad_norm": 0.5633115662164564, "learning_rate": 3.401109900618843e-05, "loss": 0.5522, "step": 403 }, { "epoch": 1.639493670886076, "grad_norm": 0.5085676072639307, "learning_rate": 3.3970539735870996e-05, "loss": 0.5884, "step": 404 }, { "epoch": 1.6435443037974684, "grad_norm": 0.5403398182362823, "learning_rate": 3.392986794874714e-05, "loss": 0.5585, "step": 405 }, { "epoch": 1.647594936708861, "grad_norm": 0.482345208791048, "learning_rate": 3.388908397238184e-05, "loss": 0.5682, "step": 406 }, { "epoch": 1.6516455696202532, "grad_norm": 0.5110066377425396, "learning_rate": 3.384818813524362e-05, "loss": 0.577, "step": 407 }, { "epoch": 1.6556962025316455, "grad_norm": 0.49041157748808434, "learning_rate": 3.380718076670195e-05, "loss": 0.5484, "step": 408 }, { "epoch": 1.659746835443038, "grad_norm": 0.4727326625399599, "learning_rate": 3.376606219702454e-05, "loss": 0.5401, "step": 409 }, { "epoch": 1.6637974683544305, "grad_norm": 0.528430983089335, "learning_rate": 3.372483275737468e-05, "loss": 0.5814, "step": 410 }, { "epoch": 1.6678481012658228, "grad_norm": 0.4684575972860589, "learning_rate": 3.368349277980861e-05, "loss": 0.5324, "step": 411 }, { "epoch": 1.6718987341772151, "grad_norm": 0.5273496749104801, "learning_rate": 3.3642042597272844e-05, "loss": 0.5665, "step": 412 }, { "epoch": 1.6759493670886076, "grad_norm": 0.548939846310305, "learning_rate": 3.360048254360144e-05, "loss": 0.5557, "step": 413 }, { "epoch": 1.6800000000000002, "grad_norm": 0.5414636516920021, "learning_rate": 3.355881295351336e-05, "loss": 0.5551, "step": 414 }, { "epoch": 1.6840506329113925, "grad_norm": 0.5253209101564564, "learning_rate": 3.351703416260975e-05, "loss": 0.5706, "step": 415 }, { "epoch": 1.6881012658227847, "grad_norm": 0.5146276667368331, "learning_rate": 3.347514650737126e-05, "loss": 0.5451, "step": 416 }, { "epoch": 1.6921518987341773, "grad_norm": 0.5224035318112739, "learning_rate": 3.3433150325155295e-05, "loss": 0.5683, "step": 417 }, { "epoch": 1.6962025316455698, "grad_norm": 0.46045943510312765, "learning_rate": 3.339104595419334e-05, "loss": 0.5528, "step": 418 }, { "epoch": 1.700253164556962, "grad_norm": 0.4868558856794719, "learning_rate": 3.3348833733588204e-05, "loss": 0.5674, "step": 419 }, { "epoch": 1.7043037974683544, "grad_norm": 0.5897538080392842, "learning_rate": 3.3306514003311305e-05, "loss": 0.572, "step": 420 }, { "epoch": 1.7083544303797469, "grad_norm": 0.50652754666224, "learning_rate": 3.326408710419996e-05, "loss": 0.5789, "step": 421 }, { "epoch": 1.7124050632911394, "grad_norm": 0.554979621464964, "learning_rate": 3.322155337795454e-05, "loss": 0.547, "step": 422 }, { "epoch": 1.7164556962025317, "grad_norm": 0.5913055470076131, "learning_rate": 3.317891316713587e-05, "loss": 0.5666, "step": 423 }, { "epoch": 1.720506329113924, "grad_norm": 0.5542419599763871, "learning_rate": 3.313616681516231e-05, "loss": 0.5717, "step": 424 }, { "epoch": 1.7245569620253165, "grad_norm": 0.6230025814693243, "learning_rate": 3.309331466630713e-05, "loss": 0.5481, "step": 425 }, { "epoch": 1.728607594936709, "grad_norm": 0.5495037326953882, "learning_rate": 3.305035706569563e-05, "loss": 0.5715, "step": 426 }, { "epoch": 1.7326582278481013, "grad_norm": 0.5484577827690081, "learning_rate": 3.3007294359302433e-05, "loss": 0.5633, "step": 427 }, { "epoch": 1.7367088607594936, "grad_norm": 0.6520957198009941, "learning_rate": 3.296412689394864e-05, "loss": 0.5738, "step": 428 }, { "epoch": 1.7407594936708861, "grad_norm": 0.5088210404628032, "learning_rate": 3.292085501729909e-05, "loss": 0.5881, "step": 429 }, { "epoch": 1.7448101265822786, "grad_norm": 0.6107756919794443, "learning_rate": 3.2877479077859534e-05, "loss": 0.5854, "step": 430 }, { "epoch": 1.748860759493671, "grad_norm": 0.5248259113551257, "learning_rate": 3.283399942497381e-05, "loss": 0.5843, "step": 431 }, { "epoch": 1.7529113924050632, "grad_norm": 0.5109102333649633, "learning_rate": 3.279041640882108e-05, "loss": 0.5729, "step": 432 }, { "epoch": 1.7569620253164557, "grad_norm": 0.5137223434432225, "learning_rate": 3.2746730380412964e-05, "loss": 0.5629, "step": 433 }, { "epoch": 1.7610126582278482, "grad_norm": 0.5319924535136257, "learning_rate": 3.2702941691590726e-05, "loss": 0.5476, "step": 434 }, { "epoch": 1.7650632911392405, "grad_norm": 0.4990013838341748, "learning_rate": 3.265905069502244e-05, "loss": 0.5637, "step": 435 }, { "epoch": 1.7691139240506328, "grad_norm": 0.5330183162332347, "learning_rate": 3.261505774420016e-05, "loss": 0.5644, "step": 436 }, { "epoch": 1.7731645569620254, "grad_norm": 0.4964696771200049, "learning_rate": 3.257096319343707e-05, "loss": 0.5546, "step": 437 }, { "epoch": 1.7772151898734179, "grad_norm": 0.5028366447287627, "learning_rate": 3.2526767397864614e-05, "loss": 0.564, "step": 438 }, { "epoch": 1.7812658227848102, "grad_norm": 0.5609238603642052, "learning_rate": 3.248247071342966e-05, "loss": 0.5657, "step": 439 }, { "epoch": 1.7853164556962025, "grad_norm": 0.4897477762048635, "learning_rate": 3.243807349689161e-05, "loss": 0.5565, "step": 440 }, { "epoch": 1.789367088607595, "grad_norm": 0.4982353789886119, "learning_rate": 3.2393576105819544e-05, "loss": 0.5528, "step": 441 }, { "epoch": 1.7934177215189875, "grad_norm": 0.5383501204444497, "learning_rate": 3.2348978898589333e-05, "loss": 0.5663, "step": 442 }, { "epoch": 1.7974683544303798, "grad_norm": 0.5040956454364913, "learning_rate": 3.230428223438075e-05, "loss": 0.5419, "step": 443 }, { "epoch": 1.801518987341772, "grad_norm": 0.4854006149372596, "learning_rate": 3.225948647317459e-05, "loss": 0.5636, "step": 444 }, { "epoch": 1.8055696202531646, "grad_norm": 0.5352728914442535, "learning_rate": 3.2214591975749745e-05, "loss": 0.5683, "step": 445 }, { "epoch": 1.809620253164557, "grad_norm": 0.4757432909149723, "learning_rate": 3.216959910368034e-05, "loss": 0.5807, "step": 446 }, { "epoch": 1.8136708860759494, "grad_norm": 0.502421859103026, "learning_rate": 3.212450821933277e-05, "loss": 0.5641, "step": 447 }, { "epoch": 1.8177215189873417, "grad_norm": 0.496848184584464, "learning_rate": 3.207931968586281e-05, "loss": 0.5672, "step": 448 }, { "epoch": 1.8217721518987342, "grad_norm": 0.4804120071097033, "learning_rate": 3.203403386721272e-05, "loss": 0.5736, "step": 449 }, { "epoch": 1.8258227848101267, "grad_norm": 0.5219493936086234, "learning_rate": 3.1988651128108245e-05, "loss": 0.5701, "step": 450 }, { "epoch": 1.829873417721519, "grad_norm": 0.5017468802177412, "learning_rate": 3.194317183405573e-05, "loss": 0.555, "step": 451 }, { "epoch": 1.8339240506329113, "grad_norm": 0.5347098350640922, "learning_rate": 3.189759635133914e-05, "loss": 0.5855, "step": 452 }, { "epoch": 1.8379746835443038, "grad_norm": 0.5074949038901487, "learning_rate": 3.185192504701718e-05, "loss": 0.5605, "step": 453 }, { "epoch": 1.8420253164556963, "grad_norm": 0.5384912010841159, "learning_rate": 3.1806158288920234e-05, "loss": 0.5715, "step": 454 }, { "epoch": 1.8460759493670886, "grad_norm": 0.5368471270852025, "learning_rate": 3.1760296445647477e-05, "loss": 0.568, "step": 455 }, { "epoch": 1.850126582278481, "grad_norm": 0.5295469813079198, "learning_rate": 3.1714339886563896e-05, "loss": 0.5765, "step": 456 }, { "epoch": 1.8541772151898734, "grad_norm": 0.5424760590904544, "learning_rate": 3.166828898179731e-05, "loss": 0.5733, "step": 457 }, { "epoch": 1.858227848101266, "grad_norm": 0.6000047503702053, "learning_rate": 3.162214410223536e-05, "loss": 0.5458, "step": 458 }, { "epoch": 1.8622784810126582, "grad_norm": 0.5084058360746005, "learning_rate": 3.157590561952257e-05, "loss": 0.5575, "step": 459 }, { "epoch": 1.8663291139240505, "grad_norm": 0.5538167596465183, "learning_rate": 3.152957390605732e-05, "loss": 0.5603, "step": 460 }, { "epoch": 1.870379746835443, "grad_norm": 0.45699984176200614, "learning_rate": 3.148314933498886e-05, "loss": 0.5546, "step": 461 }, { "epoch": 1.8744303797468356, "grad_norm": 0.5118807931029944, "learning_rate": 3.143663228021431e-05, "loss": 0.5446, "step": 462 }, { "epoch": 1.8784810126582279, "grad_norm": 0.4627072615773375, "learning_rate": 3.1390023116375624e-05, "loss": 0.5698, "step": 463 }, { "epoch": 1.8825316455696202, "grad_norm": 0.5169146528667826, "learning_rate": 3.134332221885661e-05, "loss": 0.5736, "step": 464 }, { "epoch": 1.8865822784810127, "grad_norm": 0.5068841460221797, "learning_rate": 3.129652996377987e-05, "loss": 0.5759, "step": 465 }, { "epoch": 1.8906329113924052, "grad_norm": 0.48244289335507545, "learning_rate": 3.12496467280038e-05, "loss": 0.558, "step": 466 }, { "epoch": 1.8946835443037975, "grad_norm": 0.49764823827033805, "learning_rate": 3.120267288911952e-05, "loss": 0.5348, "step": 467 }, { "epoch": 1.8987341772151898, "grad_norm": 0.49530672137142184, "learning_rate": 3.11556088254479e-05, "loss": 0.5444, "step": 468 }, { "epoch": 1.9027848101265823, "grad_norm": 0.5269361560689466, "learning_rate": 3.11084549160364e-05, "loss": 0.5466, "step": 469 }, { "epoch": 1.9068354430379748, "grad_norm": 0.5407487362808873, "learning_rate": 3.106121154065615e-05, "loss": 0.5515, "step": 470 }, { "epoch": 1.910886075949367, "grad_norm": 0.5485096296362173, "learning_rate": 3.1013879079798805e-05, "loss": 0.5667, "step": 471 }, { "epoch": 1.9149367088607594, "grad_norm": 0.5340023488829639, "learning_rate": 3.096645791467348e-05, "loss": 0.5508, "step": 472 }, { "epoch": 1.918987341772152, "grad_norm": 0.516119961678959, "learning_rate": 3.091894842720373e-05, "loss": 0.5416, "step": 473 }, { "epoch": 1.9230379746835444, "grad_norm": 0.5539615793822608, "learning_rate": 3.0871351000024425e-05, "loss": 0.5388, "step": 474 }, { "epoch": 1.9270886075949367, "grad_norm": 0.4781457483090117, "learning_rate": 3.0823666016478716e-05, "loss": 0.5674, "step": 475 }, { "epoch": 1.931139240506329, "grad_norm": 0.5332480336899131, "learning_rate": 3.0775893860614896e-05, "loss": 0.5684, "step": 476 }, { "epoch": 1.9351898734177215, "grad_norm": 0.49850551522166087, "learning_rate": 3.0728034917183336e-05, "loss": 0.5772, "step": 477 }, { "epoch": 1.939240506329114, "grad_norm": 0.46291711309695754, "learning_rate": 3.06800895716334e-05, "loss": 0.5589, "step": 478 }, { "epoch": 1.9432911392405063, "grad_norm": 0.506169061702032, "learning_rate": 3.063205821011029e-05, "loss": 0.5561, "step": 479 }, { "epoch": 1.9473417721518986, "grad_norm": 0.4806762786878444, "learning_rate": 3.0583941219452016e-05, "loss": 0.5724, "step": 480 }, { "epoch": 1.9513924050632911, "grad_norm": 0.5116909129935454, "learning_rate": 3.053573898718618e-05, "loss": 0.5679, "step": 481 }, { "epoch": 1.9554430379746837, "grad_norm": 0.5557287487077617, "learning_rate": 3.0487451901526956e-05, "loss": 0.5614, "step": 482 }, { "epoch": 1.959493670886076, "grad_norm": 0.49001082321819533, "learning_rate": 3.0439080351371875e-05, "loss": 0.5565, "step": 483 }, { "epoch": 1.9635443037974682, "grad_norm": 0.5223808566284769, "learning_rate": 3.0390624726298764e-05, "loss": 0.5558, "step": 484 }, { "epoch": 1.9675949367088608, "grad_norm": 0.4813766487870517, "learning_rate": 3.034208541656255e-05, "loss": 0.5423, "step": 485 }, { "epoch": 1.9716455696202533, "grad_norm": 0.4946608741858035, "learning_rate": 3.029346281309218e-05, "loss": 0.5692, "step": 486 }, { "epoch": 1.9756962025316456, "grad_norm": 0.49889513638752436, "learning_rate": 3.0244757307487415e-05, "loss": 0.582, "step": 487 }, { "epoch": 1.9797468354430379, "grad_norm": 0.5772925887959205, "learning_rate": 3.019596929201569e-05, "loss": 0.5584, "step": 488 }, { "epoch": 1.9837974683544304, "grad_norm": 0.5188238917298715, "learning_rate": 3.0147099159608985e-05, "loss": 0.5608, "step": 489 }, { "epoch": 1.987848101265823, "grad_norm": 0.5065955534993433, "learning_rate": 3.0098147303860616e-05, "loss": 0.5518, "step": 490 }, { "epoch": 1.9918987341772152, "grad_norm": 0.44423827074209193, "learning_rate": 3.0049114119022117e-05, "loss": 0.5698, "step": 491 }, { "epoch": 1.9959493670886075, "grad_norm": 0.5607131242410512, "learning_rate": 3.0000000000000004e-05, "loss": 0.5715, "step": 492 }, { "epoch": 2.0030379746835445, "grad_norm": 0.8039482910202507, "learning_rate": 2.995080534235264e-05, "loss": 0.4314, "step": 493 }, { "epoch": 2.0070886075949366, "grad_norm": 0.48135821288052116, "learning_rate": 2.9901530542287044e-05, "loss": 0.3855, "step": 494 }, { "epoch": 2.011139240506329, "grad_norm": 1.6501463373176999, "learning_rate": 2.9852175996655676e-05, "loss": 0.407, "step": 495 }, { "epoch": 2.0151898734177216, "grad_norm": 0.6559134106030392, "learning_rate": 2.980274210295326e-05, "loss": 0.3925, "step": 496 }, { "epoch": 2.019240506329114, "grad_norm": 0.6175190741262774, "learning_rate": 2.9753229259313578e-05, "loss": 0.4053, "step": 497 }, { "epoch": 2.023291139240506, "grad_norm": 0.6188151329909006, "learning_rate": 2.9703637864506274e-05, "loss": 0.3862, "step": 498 }, { "epoch": 2.0273417721518987, "grad_norm": 0.5973322669440845, "learning_rate": 2.965396831793362e-05, "loss": 0.3578, "step": 499 }, { "epoch": 2.031392405063291, "grad_norm": 0.5077802096073215, "learning_rate": 2.9604221019627316e-05, "loss": 0.3788, "step": 500 }, { "epoch": 2.0354430379746837, "grad_norm": 0.5442327820771462, "learning_rate": 2.955439637024526e-05, "loss": 0.3758, "step": 501 }, { "epoch": 2.039493670886076, "grad_norm": 0.592602059631016, "learning_rate": 2.9504494771068334e-05, "loss": 0.3815, "step": 502 }, { "epoch": 2.0435443037974683, "grad_norm": 0.5201723313582375, "learning_rate": 2.9454516623997156e-05, "loss": 0.3848, "step": 503 }, { "epoch": 2.047594936708861, "grad_norm": 0.5243852907891441, "learning_rate": 2.9404462331548847e-05, "loss": 0.3893, "step": 504 }, { "epoch": 2.0516455696202534, "grad_norm": 0.5414502175921986, "learning_rate": 2.93543322968538e-05, "loss": 0.3663, "step": 505 }, { "epoch": 2.0556962025316454, "grad_norm": 0.5144266993087999, "learning_rate": 2.9304126923652428e-05, "loss": 0.3724, "step": 506 }, { "epoch": 2.059746835443038, "grad_norm": 0.6073198483294441, "learning_rate": 2.9253846616291896e-05, "loss": 0.3777, "step": 507 }, { "epoch": 2.0637974683544305, "grad_norm": 0.5033445556382764, "learning_rate": 2.9203491779722896e-05, "loss": 0.3913, "step": 508 }, { "epoch": 2.067848101265823, "grad_norm": 0.5486805462961536, "learning_rate": 2.9153062819496357e-05, "loss": 0.3806, "step": 509 }, { "epoch": 2.071898734177215, "grad_norm": 0.5135001795500149, "learning_rate": 2.9102560141760178e-05, "loss": 0.3803, "step": 510 }, { "epoch": 2.0759493670886076, "grad_norm": 0.4953205716278028, "learning_rate": 2.9051984153256004e-05, "loss": 0.3654, "step": 511 }, { "epoch": 2.08, "grad_norm": 0.5369551698314505, "learning_rate": 2.900133526131588e-05, "loss": 0.3638, "step": 512 }, { "epoch": 2.0840506329113926, "grad_norm": 0.5315609261014522, "learning_rate": 2.8950613873859025e-05, "loss": 0.3928, "step": 513 }, { "epoch": 2.0881012658227847, "grad_norm": 0.5163672488467712, "learning_rate": 2.8899820399388515e-05, "loss": 0.3847, "step": 514 }, { "epoch": 2.092151898734177, "grad_norm": 0.5616948933738274, "learning_rate": 2.8848955246988012e-05, "loss": 0.3596, "step": 515 }, { "epoch": 2.0962025316455697, "grad_norm": 0.5182551521467705, "learning_rate": 2.879801882631847e-05, "loss": 0.3566, "step": 516 }, { "epoch": 2.100253164556962, "grad_norm": 0.5118179690767852, "learning_rate": 2.8747011547614808e-05, "loss": 0.3837, "step": 517 }, { "epoch": 2.1043037974683543, "grad_norm": 0.5351108153287164, "learning_rate": 2.8695933821682635e-05, "loss": 0.3522, "step": 518 }, { "epoch": 2.108354430379747, "grad_norm": 0.5045247911135647, "learning_rate": 2.864478605989494e-05, "loss": 0.3602, "step": 519 }, { "epoch": 2.1124050632911393, "grad_norm": 0.5316756529779746, "learning_rate": 2.8593568674188765e-05, "loss": 0.3602, "step": 520 }, { "epoch": 2.116455696202532, "grad_norm": 0.4960196582324591, "learning_rate": 2.8542282077061892e-05, "loss": 0.3877, "step": 521 }, { "epoch": 2.120506329113924, "grad_norm": 0.5456188773758686, "learning_rate": 2.8490926681569523e-05, "loss": 0.3536, "step": 522 }, { "epoch": 2.1245569620253164, "grad_norm": 0.49369933852188636, "learning_rate": 2.8439502901320956e-05, "loss": 0.3616, "step": 523 }, { "epoch": 2.128607594936709, "grad_norm": 0.5023102561123892, "learning_rate": 2.8388011150476237e-05, "loss": 0.3708, "step": 524 }, { "epoch": 2.1326582278481014, "grad_norm": 0.47164855512478004, "learning_rate": 2.8336451843742866e-05, "loss": 0.3649, "step": 525 }, { "epoch": 2.1367088607594935, "grad_norm": 0.4732683097272677, "learning_rate": 2.8284825396372387e-05, "loss": 0.373, "step": 526 }, { "epoch": 2.140759493670886, "grad_norm": 0.47315239668914566, "learning_rate": 2.8233132224157132e-05, "loss": 0.3725, "step": 527 }, { "epoch": 2.1448101265822785, "grad_norm": 0.4229355622648268, "learning_rate": 2.8181372743426805e-05, "loss": 0.3672, "step": 528 }, { "epoch": 2.148860759493671, "grad_norm": 0.5201122614709339, "learning_rate": 2.8129547371045128e-05, "loss": 0.3785, "step": 529 }, { "epoch": 2.152911392405063, "grad_norm": 0.4458075483399817, "learning_rate": 2.8077656524406534e-05, "loss": 0.3853, "step": 530 }, { "epoch": 2.1569620253164556, "grad_norm": 0.5022864068644323, "learning_rate": 2.802570062143278e-05, "loss": 0.3704, "step": 531 }, { "epoch": 2.161012658227848, "grad_norm": 0.45990551634579696, "learning_rate": 2.7973680080569555e-05, "loss": 0.3845, "step": 532 }, { "epoch": 2.1650632911392407, "grad_norm": 0.5015792757411652, "learning_rate": 2.792159532078314e-05, "loss": 0.363, "step": 533 }, { "epoch": 2.1691139240506327, "grad_norm": 0.5094566432769163, "learning_rate": 2.7869446761557033e-05, "loss": 0.3996, "step": 534 }, { "epoch": 2.1731645569620253, "grad_norm": 0.4679206973070292, "learning_rate": 2.781723482288857e-05, "loss": 0.3757, "step": 535 }, { "epoch": 2.1772151898734178, "grad_norm": 0.5173848732175925, "learning_rate": 2.7764959925285517e-05, "loss": 0.3756, "step": 536 }, { "epoch": 2.1812658227848103, "grad_norm": 0.46351826180268074, "learning_rate": 2.771262248976272e-05, "loss": 0.3645, "step": 537 }, { "epoch": 2.1853164556962024, "grad_norm": 0.4997426955688324, "learning_rate": 2.7660222937838677e-05, "loss": 0.3774, "step": 538 }, { "epoch": 2.189367088607595, "grad_norm": 0.5379883661726919, "learning_rate": 2.7607761691532186e-05, "loss": 0.3761, "step": 539 }, { "epoch": 2.1934177215189874, "grad_norm": 0.4534626985988713, "learning_rate": 2.7555239173358916e-05, "loss": 0.3771, "step": 540 }, { "epoch": 2.19746835443038, "grad_norm": 0.5071999621443951, "learning_rate": 2.7502655806328e-05, "loss": 0.3543, "step": 541 }, { "epoch": 2.201518987341772, "grad_norm": 0.4661833043599401, "learning_rate": 2.7450012013938648e-05, "loss": 0.3921, "step": 542 }, { "epoch": 2.2055696202531645, "grad_norm": 0.5008362670137287, "learning_rate": 2.739730822017673e-05, "loss": 0.3892, "step": 543 }, { "epoch": 2.209620253164557, "grad_norm": 0.4752436666759684, "learning_rate": 2.7344544849511355e-05, "loss": 0.3612, "step": 544 }, { "epoch": 2.2136708860759495, "grad_norm": 0.4675194095665916, "learning_rate": 2.7291722326891456e-05, "loss": 0.3481, "step": 545 }, { "epoch": 2.2177215189873416, "grad_norm": 0.5182619498901669, "learning_rate": 2.723884107774236e-05, "loss": 0.3811, "step": 546 }, { "epoch": 2.221772151898734, "grad_norm": 0.4969388349194409, "learning_rate": 2.718590152796239e-05, "loss": 0.3667, "step": 547 }, { "epoch": 2.2258227848101266, "grad_norm": 0.4678836887250709, "learning_rate": 2.71329041039194e-05, "loss": 0.3602, "step": 548 }, { "epoch": 2.229873417721519, "grad_norm": 0.5203453681354989, "learning_rate": 2.7079849232447357e-05, "loss": 0.3694, "step": 549 }, { "epoch": 2.233924050632911, "grad_norm": 0.4604775281016262, "learning_rate": 2.7026737340842895e-05, "loss": 0.3806, "step": 550 }, { "epoch": 2.2379746835443037, "grad_norm": 0.4984622560034051, "learning_rate": 2.697356885686189e-05, "loss": 0.3813, "step": 551 }, { "epoch": 2.2420253164556962, "grad_norm": 0.4735723504675428, "learning_rate": 2.6920344208716014e-05, "loss": 0.3746, "step": 552 }, { "epoch": 2.2460759493670888, "grad_norm": 0.47143926428879807, "learning_rate": 2.6867063825069252e-05, "loss": 0.3706, "step": 553 }, { "epoch": 2.250126582278481, "grad_norm": 0.5115485848578856, "learning_rate": 2.6813728135034494e-05, "loss": 0.3741, "step": 554 }, { "epoch": 2.2541772151898734, "grad_norm": 0.45269744026552305, "learning_rate": 2.6760337568170056e-05, "loss": 0.3701, "step": 555 }, { "epoch": 2.258227848101266, "grad_norm": 0.49259937535007975, "learning_rate": 2.6706892554476226e-05, "loss": 0.3845, "step": 556 }, { "epoch": 2.2622784810126584, "grad_norm": 0.487474727778432, "learning_rate": 2.6653393524391795e-05, "loss": 0.3714, "step": 557 }, { "epoch": 2.2663291139240505, "grad_norm": 0.50330295241095, "learning_rate": 2.6599840908790592e-05, "loss": 0.3669, "step": 558 }, { "epoch": 2.270379746835443, "grad_norm": 0.4802322998224495, "learning_rate": 2.6546235138978028e-05, "loss": 0.3603, "step": 559 }, { "epoch": 2.2744303797468355, "grad_norm": 0.44842972295721173, "learning_rate": 2.6492576646687597e-05, "loss": 0.3888, "step": 560 }, { "epoch": 2.278481012658228, "grad_norm": 0.48079210575591297, "learning_rate": 2.6438865864077425e-05, "loss": 0.358, "step": 561 }, { "epoch": 2.28253164556962, "grad_norm": 0.4193241634607048, "learning_rate": 2.6385103223726766e-05, "loss": 0.3549, "step": 562 }, { "epoch": 2.2865822784810126, "grad_norm": 0.4599401882477522, "learning_rate": 2.6331289158632537e-05, "loss": 0.3815, "step": 563 }, { "epoch": 2.290632911392405, "grad_norm": 0.45597634521773084, "learning_rate": 2.6277424102205817e-05, "loss": 0.4029, "step": 564 }, { "epoch": 2.2946835443037976, "grad_norm": 0.4902080947898592, "learning_rate": 2.6223508488268374e-05, "loss": 0.3803, "step": 565 }, { "epoch": 2.2987341772151897, "grad_norm": 0.4491045606631554, "learning_rate": 2.6169542751049148e-05, "loss": 0.3558, "step": 566 }, { "epoch": 2.302784810126582, "grad_norm": 0.4881693727772947, "learning_rate": 2.6115527325180754e-05, "loss": 0.3771, "step": 567 }, { "epoch": 2.3068354430379747, "grad_norm": 0.443618316180222, "learning_rate": 2.606146264569603e-05, "loss": 0.3582, "step": 568 }, { "epoch": 2.3108860759493672, "grad_norm": 0.46030326410981726, "learning_rate": 2.6007349148024447e-05, "loss": 0.3892, "step": 569 }, { "epoch": 2.3149367088607593, "grad_norm": 0.4426535410348674, "learning_rate": 2.5953187267988694e-05, "loss": 0.3655, "step": 570 }, { "epoch": 2.318987341772152, "grad_norm": 0.43100487340255994, "learning_rate": 2.5898977441801097e-05, "loss": 0.3875, "step": 571 }, { "epoch": 2.3230379746835443, "grad_norm": 0.44832977428344106, "learning_rate": 2.584472010606015e-05, "loss": 0.3589, "step": 572 }, { "epoch": 2.327088607594937, "grad_norm": 0.42953994783913746, "learning_rate": 2.5790415697746976e-05, "loss": 0.3739, "step": 573 }, { "epoch": 2.331139240506329, "grad_norm": 0.4902982716520749, "learning_rate": 2.5736064654221808e-05, "loss": 0.3444, "step": 574 }, { "epoch": 2.3351898734177214, "grad_norm": 0.4330249068227588, "learning_rate": 2.568166741322048e-05, "loss": 0.3768, "step": 575 }, { "epoch": 2.339240506329114, "grad_norm": 0.4327416224423393, "learning_rate": 2.56272244128509e-05, "loss": 0.3813, "step": 576 }, { "epoch": 2.3432911392405065, "grad_norm": 0.44915877124285275, "learning_rate": 2.55727360915895e-05, "loss": 0.383, "step": 577 }, { "epoch": 2.3473417721518985, "grad_norm": 0.44585830464301024, "learning_rate": 2.5518202888277734e-05, "loss": 0.3772, "step": 578 }, { "epoch": 2.351392405063291, "grad_norm": 0.4682008002360376, "learning_rate": 2.5463625242118523e-05, "loss": 0.3667, "step": 579 }, { "epoch": 2.3554430379746836, "grad_norm": 0.4434080939614173, "learning_rate": 2.5409003592672723e-05, "loss": 0.3698, "step": 580 }, { "epoch": 2.359493670886076, "grad_norm": 0.4839304256806482, "learning_rate": 2.535433837985559e-05, "loss": 0.3794, "step": 581 }, { "epoch": 2.363544303797468, "grad_norm": 0.4679488998773356, "learning_rate": 2.529963004393324e-05, "loss": 0.3818, "step": 582 }, { "epoch": 2.3675949367088607, "grad_norm": 0.46111821831516053, "learning_rate": 2.524487902551908e-05, "loss": 0.3751, "step": 583 }, { "epoch": 2.371645569620253, "grad_norm": 0.4400387500529656, "learning_rate": 2.519008576557029e-05, "loss": 0.3703, "step": 584 }, { "epoch": 2.3756962025316457, "grad_norm": 0.46218951455704177, "learning_rate": 2.5135250705384254e-05, "loss": 0.3833, "step": 585 }, { "epoch": 2.379746835443038, "grad_norm": 0.420779954974148, "learning_rate": 2.5080374286595007e-05, "loss": 0.3793, "step": 586 }, { "epoch": 2.3837974683544303, "grad_norm": 0.4876949568112334, "learning_rate": 2.5025456951169677e-05, "loss": 0.387, "step": 587 }, { "epoch": 2.387848101265823, "grad_norm": 0.44476883690646696, "learning_rate": 2.4970499141404942e-05, "loss": 0.3685, "step": 588 }, { "epoch": 2.3918987341772153, "grad_norm": 0.48505359321928876, "learning_rate": 2.491550129992345e-05, "loss": 0.3886, "step": 589 }, { "epoch": 2.3959493670886074, "grad_norm": 0.41240382154959004, "learning_rate": 2.486046386967024e-05, "loss": 0.3714, "step": 590 }, { "epoch": 2.4, "grad_norm": 0.5396064516158852, "learning_rate": 2.4805387293909214e-05, "loss": 0.3629, "step": 591 }, { "epoch": 2.4040506329113924, "grad_norm": 0.4585573614195714, "learning_rate": 2.4750272016219552e-05, "loss": 0.3684, "step": 592 }, { "epoch": 2.408101265822785, "grad_norm": 0.47240981277957017, "learning_rate": 2.4695118480492114e-05, "loss": 0.3628, "step": 593 }, { "epoch": 2.4121518987341775, "grad_norm": 0.4800488189045284, "learning_rate": 2.4639927130925898e-05, "loss": 0.3906, "step": 594 }, { "epoch": 2.4162025316455695, "grad_norm": 0.4382524630241705, "learning_rate": 2.458469841202444e-05, "loss": 0.3847, "step": 595 }, { "epoch": 2.420253164556962, "grad_norm": 0.4964525915077789, "learning_rate": 2.452943276859226e-05, "loss": 0.368, "step": 596 }, { "epoch": 2.4243037974683546, "grad_norm": 0.47075644135947325, "learning_rate": 2.447413064573125e-05, "loss": 0.368, "step": 597 }, { "epoch": 2.4283544303797466, "grad_norm": 0.4830126549165447, "learning_rate": 2.4418792488837095e-05, "loss": 0.3581, "step": 598 }, { "epoch": 2.432405063291139, "grad_norm": 0.478612193067899, "learning_rate": 2.4363418743595713e-05, "loss": 0.373, "step": 599 }, { "epoch": 2.4364556962025317, "grad_norm": 0.46858334716433037, "learning_rate": 2.430800985597963e-05, "loss": 0.3715, "step": 600 }, { "epoch": 2.440506329113924, "grad_norm": 0.44271859817465, "learning_rate": 2.4252566272244415e-05, "loss": 0.3573, "step": 601 }, { "epoch": 2.4445569620253167, "grad_norm": 0.40915876884739055, "learning_rate": 2.4197088438925063e-05, "loss": 0.3597, "step": 602 }, { "epoch": 2.4486075949367088, "grad_norm": 0.4804755289092679, "learning_rate": 2.4141576802832417e-05, "loss": 0.391, "step": 603 }, { "epoch": 2.4526582278481013, "grad_norm": 0.4172482479862191, "learning_rate": 2.408603181104957e-05, "loss": 0.3817, "step": 604 }, { "epoch": 2.456708860759494, "grad_norm": 0.4385939683662679, "learning_rate": 2.4030453910928245e-05, "loss": 0.3541, "step": 605 }, { "epoch": 2.460759493670886, "grad_norm": 0.4577421871853593, "learning_rate": 2.397484355008521e-05, "loss": 0.3515, "step": 606 }, { "epoch": 2.4648101265822784, "grad_norm": 0.4237011643726849, "learning_rate": 2.3919201176398662e-05, "loss": 0.3814, "step": 607 }, { "epoch": 2.468860759493671, "grad_norm": 0.4553963627662781, "learning_rate": 2.3863527238004633e-05, "loss": 0.3847, "step": 608 }, { "epoch": 2.4729113924050634, "grad_norm": 0.4288062135481685, "learning_rate": 2.380782218329337e-05, "loss": 0.3576, "step": 609 }, { "epoch": 2.476962025316456, "grad_norm": 0.4370640534449743, "learning_rate": 2.3752086460905725e-05, "loss": 0.3714, "step": 610 }, { "epoch": 2.481012658227848, "grad_norm": 0.45012713124804205, "learning_rate": 2.3696320519729544e-05, "loss": 0.371, "step": 611 }, { "epoch": 2.4850632911392405, "grad_norm": 0.481057228305272, "learning_rate": 2.3640524808896045e-05, "loss": 0.3645, "step": 612 }, { "epoch": 2.489113924050633, "grad_norm": 0.41495702987472305, "learning_rate": 2.3584699777776222e-05, "loss": 0.3822, "step": 613 }, { "epoch": 2.493164556962025, "grad_norm": 0.4465792422012659, "learning_rate": 2.3528845875977195e-05, "loss": 0.3852, "step": 614 }, { "epoch": 2.4972151898734176, "grad_norm": 0.4409643540162559, "learning_rate": 2.3472963553338614e-05, "loss": 0.3996, "step": 615 }, { "epoch": 2.50126582278481, "grad_norm": 0.43393343396084844, "learning_rate": 2.341705325992901e-05, "loss": 0.3851, "step": 616 }, { "epoch": 2.5053164556962026, "grad_norm": 0.4631709982009208, "learning_rate": 2.336111544604222e-05, "loss": 0.3694, "step": 617 }, { "epoch": 2.509367088607595, "grad_norm": 0.4646600236010894, "learning_rate": 2.33051505621937e-05, "loss": 0.3641, "step": 618 }, { "epoch": 2.5134177215189872, "grad_norm": 0.4032763951037155, "learning_rate": 2.324915905911693e-05, "loss": 0.3695, "step": 619 }, { "epoch": 2.5174683544303798, "grad_norm": 0.5011985771092315, "learning_rate": 2.319314138775977e-05, "loss": 0.387, "step": 620 }, { "epoch": 2.5215189873417723, "grad_norm": 0.46131873648052574, "learning_rate": 2.3137097999280856e-05, "loss": 0.3924, "step": 621 }, { "epoch": 2.5255696202531643, "grad_norm": 0.45758282551060225, "learning_rate": 2.308102934504593e-05, "loss": 0.3597, "step": 622 }, { "epoch": 2.529620253164557, "grad_norm": 0.44928242641878513, "learning_rate": 2.3024935876624222e-05, "loss": 0.3636, "step": 623 }, { "epoch": 2.5336708860759494, "grad_norm": 0.427204181349178, "learning_rate": 2.2968818045784813e-05, "loss": 0.3792, "step": 624 }, { "epoch": 2.537721518987342, "grad_norm": 0.42101583161199185, "learning_rate": 2.2912676304493006e-05, "loss": 0.3615, "step": 625 }, { "epoch": 2.5417721518987344, "grad_norm": 0.45253815045852247, "learning_rate": 2.2856511104906668e-05, "loss": 0.374, "step": 626 }, { "epoch": 2.5458227848101265, "grad_norm": 0.4269476117590302, "learning_rate": 2.2800322899372586e-05, "loss": 0.377, "step": 627 }, { "epoch": 2.549873417721519, "grad_norm": 0.4372173926983107, "learning_rate": 2.2744112140422844e-05, "loss": 0.3963, "step": 628 }, { "epoch": 2.5539240506329115, "grad_norm": 0.4634661912210469, "learning_rate": 2.2687879280771177e-05, "loss": 0.3699, "step": 629 }, { "epoch": 2.5579746835443036, "grad_norm": 0.43473340937819255, "learning_rate": 2.26316247733093e-05, "loss": 0.373, "step": 630 }, { "epoch": 2.562025316455696, "grad_norm": 0.46378257498726166, "learning_rate": 2.257534907110328e-05, "loss": 0.3939, "step": 631 }, { "epoch": 2.5660759493670886, "grad_norm": 0.45127259886446697, "learning_rate": 2.2519052627389882e-05, "loss": 0.4074, "step": 632 }, { "epoch": 2.570126582278481, "grad_norm": 0.39769696018006995, "learning_rate": 2.246273589557294e-05, "loss": 0.4016, "step": 633 }, { "epoch": 2.5741772151898736, "grad_norm": 0.4349460554891752, "learning_rate": 2.240639932921966e-05, "loss": 0.3764, "step": 634 }, { "epoch": 2.5782278481012657, "grad_norm": 0.44441518270595837, "learning_rate": 2.2350043382056995e-05, "loss": 0.3732, "step": 635 }, { "epoch": 2.5822784810126582, "grad_norm": 0.44754773152200383, "learning_rate": 2.2293668507968015e-05, "loss": 0.3989, "step": 636 }, { "epoch": 2.5863291139240507, "grad_norm": 0.41607373293676997, "learning_rate": 2.2237275160988186e-05, "loss": 0.3778, "step": 637 }, { "epoch": 2.590379746835443, "grad_norm": 0.4618204650249146, "learning_rate": 2.2180863795301787e-05, "loss": 0.3897, "step": 638 }, { "epoch": 2.5944303797468353, "grad_norm": 0.4424675217275974, "learning_rate": 2.212443486523819e-05, "loss": 0.3625, "step": 639 }, { "epoch": 2.598481012658228, "grad_norm": 0.46864622731825456, "learning_rate": 2.2067988825268243e-05, "loss": 0.3659, "step": 640 }, { "epoch": 2.6025316455696204, "grad_norm": 0.4692364473521115, "learning_rate": 2.2011526130000596e-05, "loss": 0.345, "step": 641 }, { "epoch": 2.606582278481013, "grad_norm": 0.4417083916283979, "learning_rate": 2.1955047234178038e-05, "loss": 0.3611, "step": 642 }, { "epoch": 2.610632911392405, "grad_norm": 0.4436348273587249, "learning_rate": 2.1898552592673825e-05, "loss": 0.3832, "step": 643 }, { "epoch": 2.6146835443037975, "grad_norm": 0.46957798012846536, "learning_rate": 2.184204266048803e-05, "loss": 0.3813, "step": 644 }, { "epoch": 2.61873417721519, "grad_norm": 0.4420142639518003, "learning_rate": 2.1785517892743887e-05, "loss": 0.3665, "step": 645 }, { "epoch": 2.622784810126582, "grad_norm": 0.4263699509955564, "learning_rate": 2.17289787446841e-05, "loss": 0.3653, "step": 646 }, { "epoch": 2.6268354430379746, "grad_norm": 0.4634892323311741, "learning_rate": 2.1672425671667198e-05, "loss": 0.3638, "step": 647 }, { "epoch": 2.630886075949367, "grad_norm": 0.4462940160759474, "learning_rate": 2.161585912916385e-05, "loss": 0.3684, "step": 648 }, { "epoch": 2.6349367088607596, "grad_norm": 0.41111412959962634, "learning_rate": 2.1559279572753214e-05, "loss": 0.3778, "step": 649 }, { "epoch": 2.638987341772152, "grad_norm": 0.43734369788470545, "learning_rate": 2.1502687458119268e-05, "loss": 0.3707, "step": 650 }, { "epoch": 2.643037974683544, "grad_norm": 0.43641237278648193, "learning_rate": 2.1446083241047116e-05, "loss": 0.3751, "step": 651 }, { "epoch": 2.6470886075949367, "grad_norm": 0.4283855583896673, "learning_rate": 2.1389467377419333e-05, "loss": 0.3842, "step": 652 }, { "epoch": 2.651139240506329, "grad_norm": 0.41322886991837127, "learning_rate": 2.133284032321232e-05, "loss": 0.3824, "step": 653 }, { "epoch": 2.6551898734177213, "grad_norm": 0.45072855088652236, "learning_rate": 2.1276202534492566e-05, "loss": 0.3746, "step": 654 }, { "epoch": 2.659240506329114, "grad_norm": 0.43413161286718827, "learning_rate": 2.121955446741306e-05, "loss": 0.3759, "step": 655 }, { "epoch": 2.6632911392405063, "grad_norm": 0.4172417284109809, "learning_rate": 2.1162896578209517e-05, "loss": 0.3843, "step": 656 }, { "epoch": 2.667341772151899, "grad_norm": 0.423859303671067, "learning_rate": 2.1106229323196813e-05, "loss": 0.3625, "step": 657 }, { "epoch": 2.6713924050632913, "grad_norm": 0.46176197485741244, "learning_rate": 2.1049553158765214e-05, "loss": 0.3963, "step": 658 }, { "epoch": 2.6754430379746834, "grad_norm": 0.42641220916067774, "learning_rate": 2.0992868541376764e-05, "loss": 0.3869, "step": 659 }, { "epoch": 2.679493670886076, "grad_norm": 0.448814219138786, "learning_rate": 2.093617592756158e-05, "loss": 0.3806, "step": 660 }, { "epoch": 2.6835443037974684, "grad_norm": 0.43295628115236884, "learning_rate": 2.0879475773914167e-05, "loss": 0.3652, "step": 661 }, { "epoch": 2.6875949367088605, "grad_norm": 0.4526356236749273, "learning_rate": 2.082276853708978e-05, "loss": 0.3778, "step": 662 }, { "epoch": 2.691645569620253, "grad_norm": 0.4379180665331507, "learning_rate": 2.076605467380071e-05, "loss": 0.3795, "step": 663 }, { "epoch": 2.6956962025316455, "grad_norm": 0.4495933639124367, "learning_rate": 2.0709334640812613e-05, "loss": 0.368, "step": 664 }, { "epoch": 2.699746835443038, "grad_norm": 0.460812917269553, "learning_rate": 2.0652608894940824e-05, "loss": 0.3657, "step": 665 }, { "epoch": 2.7037974683544306, "grad_norm": 0.43207286049516197, "learning_rate": 2.0595877893046722e-05, "loss": 0.3656, "step": 666 }, { "epoch": 2.7078481012658226, "grad_norm": 0.4846938239337839, "learning_rate": 2.0539142092033985e-05, "loss": 0.3911, "step": 667 }, { "epoch": 2.711898734177215, "grad_norm": 0.4553522622649134, "learning_rate": 2.048240194884496e-05, "loss": 0.3684, "step": 668 }, { "epoch": 2.7159493670886077, "grad_norm": 0.43095738696053726, "learning_rate": 2.042565792045695e-05, "loss": 0.3769, "step": 669 }, { "epoch": 2.7199999999999998, "grad_norm": 0.4457352767372932, "learning_rate": 2.036891046387857e-05, "loss": 0.3661, "step": 670 }, { "epoch": 2.7240506329113923, "grad_norm": 0.43272564999227103, "learning_rate": 2.0312160036146036e-05, "loss": 0.357, "step": 671 }, { "epoch": 2.728101265822785, "grad_norm": 0.4488667941793339, "learning_rate": 2.025540709431948e-05, "loss": 0.3513, "step": 672 }, { "epoch": 2.7321518987341773, "grad_norm": 0.4590032500455558, "learning_rate": 2.0198652095479298e-05, "loss": 0.392, "step": 673 }, { "epoch": 2.73620253164557, "grad_norm": 0.4143689274427009, "learning_rate": 2.014189549672245e-05, "loss": 0.3927, "step": 674 }, { "epoch": 2.740253164556962, "grad_norm": 0.42643845591246643, "learning_rate": 2.0085137755158776e-05, "loss": 0.3612, "step": 675 }, { "epoch": 2.7443037974683544, "grad_norm": 0.4133923310250834, "learning_rate": 2.0028379327907327e-05, "loss": 0.3843, "step": 676 }, { "epoch": 2.748354430379747, "grad_norm": 0.441347116364697, "learning_rate": 1.9971620672092676e-05, "loss": 0.3814, "step": 677 }, { "epoch": 2.752405063291139, "grad_norm": 0.42738393956942444, "learning_rate": 1.991486224484123e-05, "loss": 0.3479, "step": 678 }, { "epoch": 2.7564556962025315, "grad_norm": 0.43921828580276145, "learning_rate": 1.985810450327756e-05, "loss": 0.3614, "step": 679 }, { "epoch": 2.760506329113924, "grad_norm": 0.44324989768924977, "learning_rate": 1.9801347904520706e-05, "loss": 0.3728, "step": 680 }, { "epoch": 2.7645569620253165, "grad_norm": 0.4146991127835996, "learning_rate": 1.974459290568053e-05, "loss": 0.3813, "step": 681 }, { "epoch": 2.768607594936709, "grad_norm": 0.4062948031517351, "learning_rate": 1.968783996385397e-05, "loss": 0.3739, "step": 682 }, { "epoch": 2.772658227848101, "grad_norm": 0.41403610183472905, "learning_rate": 1.963108953612143e-05, "loss": 0.3978, "step": 683 }, { "epoch": 2.7767088607594936, "grad_norm": 0.41942598470911646, "learning_rate": 1.9574342079543056e-05, "loss": 0.3678, "step": 684 }, { "epoch": 2.780759493670886, "grad_norm": 0.4161885512717915, "learning_rate": 1.9517598051155046e-05, "loss": 0.3638, "step": 685 }, { "epoch": 2.7848101265822782, "grad_norm": 0.434482265895329, "learning_rate": 1.9460857907966025e-05, "loss": 0.3654, "step": 686 }, { "epoch": 2.7888607594936707, "grad_norm": 0.40819400205500495, "learning_rate": 1.9404122106953285e-05, "loss": 0.3747, "step": 687 }, { "epoch": 2.7929113924050633, "grad_norm": 0.430312718237646, "learning_rate": 1.9347391105059176e-05, "loss": 0.4076, "step": 688 }, { "epoch": 2.7969620253164558, "grad_norm": 0.4088541637533606, "learning_rate": 1.92906653591874e-05, "loss": 0.3867, "step": 689 }, { "epoch": 2.8010126582278483, "grad_norm": 0.4128969808831837, "learning_rate": 1.9233945326199295e-05, "loss": 0.3913, "step": 690 }, { "epoch": 2.8050632911392404, "grad_norm": 0.3945498065073721, "learning_rate": 1.917723146291022e-05, "loss": 0.3765, "step": 691 }, { "epoch": 2.809113924050633, "grad_norm": 0.4188101118272999, "learning_rate": 1.912052422608584e-05, "loss": 0.371, "step": 692 }, { "epoch": 2.8131645569620254, "grad_norm": 0.41704507587550804, "learning_rate": 1.9063824072438428e-05, "loss": 0.3592, "step": 693 }, { "epoch": 2.8172151898734175, "grad_norm": 0.39736219244592047, "learning_rate": 1.9007131458623246e-05, "loss": 0.3793, "step": 694 }, { "epoch": 2.82126582278481, "grad_norm": 0.43606100554416144, "learning_rate": 1.895044684123479e-05, "loss": 0.3678, "step": 695 }, { "epoch": 2.8253164556962025, "grad_norm": 0.4436174413534869, "learning_rate": 1.8893770676803194e-05, "loss": 0.4033, "step": 696 }, { "epoch": 2.829367088607595, "grad_norm": 0.4388142231927746, "learning_rate": 1.8837103421790486e-05, "loss": 0.3654, "step": 697 }, { "epoch": 2.8334177215189875, "grad_norm": 0.42309354189221865, "learning_rate": 1.8780445532586952e-05, "loss": 0.3689, "step": 698 }, { "epoch": 2.8374683544303796, "grad_norm": 0.4323331196170173, "learning_rate": 1.872379746550743e-05, "loss": 0.3879, "step": 699 }, { "epoch": 2.841518987341772, "grad_norm": 0.41872347469671856, "learning_rate": 1.866715967678769e-05, "loss": 0.3664, "step": 700 }, { "epoch": 2.8455696202531646, "grad_norm": 0.4758176019250291, "learning_rate": 1.861053262258067e-05, "loss": 0.3954, "step": 701 }, { "epoch": 2.8496202531645567, "grad_norm": 0.4394535757320233, "learning_rate": 1.8553916758952897e-05, "loss": 0.38, "step": 702 }, { "epoch": 2.853670886075949, "grad_norm": 0.41082343016735334, "learning_rate": 1.8497312541880735e-05, "loss": 0.3846, "step": 703 }, { "epoch": 2.8577215189873417, "grad_norm": 0.4266476178533797, "learning_rate": 1.8440720427246786e-05, "loss": 0.3506, "step": 704 }, { "epoch": 2.8617721518987342, "grad_norm": 0.42748429267692634, "learning_rate": 1.8384140870836157e-05, "loss": 0.3668, "step": 705 }, { "epoch": 2.8658227848101268, "grad_norm": 0.4144812358684469, "learning_rate": 1.8327574328332806e-05, "loss": 0.3831, "step": 706 }, { "epoch": 2.869873417721519, "grad_norm": 0.43629632107083516, "learning_rate": 1.8271021255315906e-05, "loss": 0.3764, "step": 707 }, { "epoch": 2.8739240506329113, "grad_norm": 0.4250597399223823, "learning_rate": 1.8214482107256117e-05, "loss": 0.3738, "step": 708 }, { "epoch": 2.877974683544304, "grad_norm": 0.4434073794604137, "learning_rate": 1.8157957339511968e-05, "loss": 0.3641, "step": 709 }, { "epoch": 2.882025316455696, "grad_norm": 0.3990573076638595, "learning_rate": 1.8101447407326182e-05, "loss": 0.3967, "step": 710 }, { "epoch": 2.8860759493670884, "grad_norm": 0.42093841411499977, "learning_rate": 1.8044952765821966e-05, "loss": 0.3607, "step": 711 }, { "epoch": 2.890126582278481, "grad_norm": 0.39825836021817707, "learning_rate": 1.7988473869999407e-05, "loss": 0.3697, "step": 712 }, { "epoch": 2.8941772151898735, "grad_norm": 0.40645889562570753, "learning_rate": 1.7932011174731764e-05, "loss": 0.3711, "step": 713 }, { "epoch": 2.898227848101266, "grad_norm": 0.42243516124815306, "learning_rate": 1.7875565134761817e-05, "loss": 0.397, "step": 714 }, { "epoch": 2.902278481012658, "grad_norm": 0.4244078255004454, "learning_rate": 1.7819136204698226e-05, "loss": 0.355, "step": 715 }, { "epoch": 2.9063291139240506, "grad_norm": 0.41682215076443735, "learning_rate": 1.776272483901182e-05, "loss": 0.3815, "step": 716 }, { "epoch": 2.910379746835443, "grad_norm": 0.40518859099433613, "learning_rate": 1.7706331492031995e-05, "loss": 0.3759, "step": 717 }, { "epoch": 2.9144303797468356, "grad_norm": 0.41124119549375576, "learning_rate": 1.764995661794301e-05, "loss": 0.3811, "step": 718 }, { "epoch": 2.918481012658228, "grad_norm": 0.4223414816123737, "learning_rate": 1.759360067078035e-05, "loss": 0.39, "step": 719 }, { "epoch": 2.92253164556962, "grad_norm": 0.39660000361793873, "learning_rate": 1.7537264104427064e-05, "loss": 0.3535, "step": 720 }, { "epoch": 2.9265822784810127, "grad_norm": 0.40747751650966446, "learning_rate": 1.748094737261012e-05, "loss": 0.3838, "step": 721 }, { "epoch": 2.9306329113924052, "grad_norm": 0.42252672765287136, "learning_rate": 1.7424650928896726e-05, "loss": 0.3831, "step": 722 }, { "epoch": 2.9346835443037973, "grad_norm": 0.43994285879521566, "learning_rate": 1.7368375226690712e-05, "loss": 0.3817, "step": 723 }, { "epoch": 2.93873417721519, "grad_norm": 0.3887776988805925, "learning_rate": 1.731212071922883e-05, "loss": 0.3677, "step": 724 }, { "epoch": 2.9427848101265823, "grad_norm": 0.4469525650517993, "learning_rate": 1.7255887859577156e-05, "loss": 0.3664, "step": 725 }, { "epoch": 2.946835443037975, "grad_norm": 0.41004907530717444, "learning_rate": 1.7199677100627427e-05, "loss": 0.3672, "step": 726 }, { "epoch": 2.9508860759493674, "grad_norm": 0.407657077639719, "learning_rate": 1.7143488895093343e-05, "loss": 0.3272, "step": 727 }, { "epoch": 2.9549367088607594, "grad_norm": 0.43593100180204347, "learning_rate": 1.7087323695506994e-05, "loss": 0.3652, "step": 728 }, { "epoch": 2.958987341772152, "grad_norm": 0.42461494836768093, "learning_rate": 1.7031181954215194e-05, "loss": 0.3611, "step": 729 }, { "epoch": 2.9630379746835445, "grad_norm": 0.4136530102943701, "learning_rate": 1.6975064123375788e-05, "loss": 0.3714, "step": 730 }, { "epoch": 2.9670886075949365, "grad_norm": 0.4441740359264723, "learning_rate": 1.6918970654954084e-05, "loss": 0.3827, "step": 731 }, { "epoch": 2.971139240506329, "grad_norm": 0.41901382284184213, "learning_rate": 1.686290200071915e-05, "loss": 0.3593, "step": 732 }, { "epoch": 2.9751898734177216, "grad_norm": 0.43137568767494855, "learning_rate": 1.6806858612240234e-05, "loss": 0.3704, "step": 733 }, { "epoch": 2.979240506329114, "grad_norm": 0.4029979019760187, "learning_rate": 1.6750840940883078e-05, "loss": 0.359, "step": 734 }, { "epoch": 2.9832911392405066, "grad_norm": 0.3878546820299257, "learning_rate": 1.6694849437806305e-05, "loss": 0.3728, "step": 735 }, { "epoch": 2.9873417721518987, "grad_norm": 0.41422025405219437, "learning_rate": 1.663888455395778e-05, "loss": 0.39, "step": 736 }, { "epoch": 2.991392405063291, "grad_norm": 0.42023816285752136, "learning_rate": 1.6582946740070995e-05, "loss": 0.3461, "step": 737 }, { "epoch": 2.9954430379746837, "grad_norm": 0.409654378403547, "learning_rate": 1.6527036446661396e-05, "loss": 0.3566, "step": 738 }, { "epoch": 3.0025316455696203, "grad_norm": 0.5167164146858377, "learning_rate": 1.6471154124022818e-05, "loss": 0.3063, "step": 739 }, { "epoch": 3.006582278481013, "grad_norm": 0.4907556703672617, "learning_rate": 1.6415300222223788e-05, "loss": 0.2557, "step": 740 }, { "epoch": 3.010632911392405, "grad_norm": 0.4017497376987807, "learning_rate": 1.6359475191103958e-05, "loss": 0.238, "step": 741 }, { "epoch": 3.0146835443037974, "grad_norm": 0.5999873861652245, "learning_rate": 1.6303679480270466e-05, "loss": 0.2355, "step": 742 }, { "epoch": 3.01873417721519, "grad_norm": 0.676161021008555, "learning_rate": 1.624791353909428e-05, "loss": 0.249, "step": 743 }, { "epoch": 3.0227848101265824, "grad_norm": 0.4840482917685907, "learning_rate": 1.619217781670663e-05, "loss": 0.2349, "step": 744 }, { "epoch": 3.0268354430379745, "grad_norm": 0.47312868636844874, "learning_rate": 1.6136472761995373e-05, "loss": 0.2642, "step": 745 }, { "epoch": 3.030886075949367, "grad_norm": 0.5169793904634343, "learning_rate": 1.608079882360134e-05, "loss": 0.2412, "step": 746 }, { "epoch": 3.0349367088607595, "grad_norm": 0.4670024991177737, "learning_rate": 1.60251564499148e-05, "loss": 0.2349, "step": 747 }, { "epoch": 3.038987341772152, "grad_norm": 0.3864573104094983, "learning_rate": 1.596954608907176e-05, "loss": 0.2097, "step": 748 }, { "epoch": 3.043037974683544, "grad_norm": 0.4057428300173331, "learning_rate": 1.591396818895043e-05, "loss": 0.2365, "step": 749 }, { "epoch": 3.0470886075949366, "grad_norm": 0.503237050543072, "learning_rate": 1.585842319716759e-05, "loss": 0.2559, "step": 750 }, { "epoch": 3.051139240506329, "grad_norm": 0.4836586089897356, "learning_rate": 1.5802911561074944e-05, "loss": 0.2593, "step": 751 }, { "epoch": 3.0551898734177216, "grad_norm": 0.4060515456791972, "learning_rate": 1.5747433727755595e-05, "loss": 0.226, "step": 752 }, { "epoch": 3.0592405063291137, "grad_norm": 0.3806982206703087, "learning_rate": 1.5691990144020376e-05, "loss": 0.2387, "step": 753 }, { "epoch": 3.0632911392405062, "grad_norm": 0.45204980293443897, "learning_rate": 1.5636581256404297e-05, "loss": 0.2584, "step": 754 }, { "epoch": 3.0673417721518987, "grad_norm": 0.4424044733926564, "learning_rate": 1.558120751116291e-05, "loss": 0.2511, "step": 755 }, { "epoch": 3.0713924050632913, "grad_norm": 0.3982733560938897, "learning_rate": 1.552586935426876e-05, "loss": 0.2445, "step": 756 }, { "epoch": 3.0754430379746838, "grad_norm": 0.3988926585424081, "learning_rate": 1.547056723140774e-05, "loss": 0.2408, "step": 757 }, { "epoch": 3.079493670886076, "grad_norm": 0.40547711784723633, "learning_rate": 1.5415301587975565e-05, "loss": 0.244, "step": 758 }, { "epoch": 3.0835443037974684, "grad_norm": 0.41817232693590944, "learning_rate": 1.536007286907411e-05, "loss": 0.2326, "step": 759 }, { "epoch": 3.087594936708861, "grad_norm": 0.3828296588696409, "learning_rate": 1.5304881519507896e-05, "loss": 0.2287, "step": 760 }, { "epoch": 3.091645569620253, "grad_norm": 0.3620774257184526, "learning_rate": 1.5249727983780453e-05, "loss": 0.2404, "step": 761 }, { "epoch": 3.0956962025316455, "grad_norm": 0.3956705135245601, "learning_rate": 1.5194612706090786e-05, "loss": 0.2127, "step": 762 }, { "epoch": 3.099746835443038, "grad_norm": 0.3768940440087776, "learning_rate": 1.5139536130329771e-05, "loss": 0.2218, "step": 763 }, { "epoch": 3.1037974683544305, "grad_norm": 0.3858979740659536, "learning_rate": 1.508449870007656e-05, "loss": 0.251, "step": 764 }, { "epoch": 3.107848101265823, "grad_norm": 0.36703560238000776, "learning_rate": 1.5029500858595056e-05, "loss": 0.23, "step": 765 }, { "epoch": 3.111898734177215, "grad_norm": 0.3732439342341833, "learning_rate": 1.4974543048830328e-05, "loss": 0.2333, "step": 766 }, { "epoch": 3.1159493670886076, "grad_norm": 0.37871645640815105, "learning_rate": 1.4919625713405e-05, "loss": 0.2331, "step": 767 }, { "epoch": 3.12, "grad_norm": 0.38330069500390546, "learning_rate": 1.4864749294615756e-05, "loss": 0.23, "step": 768 }, { "epoch": 3.124050632911392, "grad_norm": 0.40294464394404284, "learning_rate": 1.4809914234429716e-05, "loss": 0.225, "step": 769 }, { "epoch": 3.1281012658227847, "grad_norm": 0.37168319757997886, "learning_rate": 1.4755120974480923e-05, "loss": 0.2533, "step": 770 }, { "epoch": 3.132151898734177, "grad_norm": 0.3653506531789912, "learning_rate": 1.4700369956066771e-05, "loss": 0.2536, "step": 771 }, { "epoch": 3.1362025316455697, "grad_norm": 0.38109010215610906, "learning_rate": 1.4645661620144413e-05, "loss": 0.2558, "step": 772 }, { "epoch": 3.1402531645569622, "grad_norm": 0.37162475643619164, "learning_rate": 1.4590996407327284e-05, "loss": 0.2399, "step": 773 }, { "epoch": 3.1443037974683543, "grad_norm": 0.355870123808396, "learning_rate": 1.4536374757881487e-05, "loss": 0.2234, "step": 774 }, { "epoch": 3.148354430379747, "grad_norm": 0.3959038615561451, "learning_rate": 1.4481797111722271e-05, "loss": 0.2166, "step": 775 }, { "epoch": 3.1524050632911393, "grad_norm": 0.3753556347127664, "learning_rate": 1.4427263908410507e-05, "loss": 0.2369, "step": 776 }, { "epoch": 3.1564556962025314, "grad_norm": 0.39339850359053413, "learning_rate": 1.4372775587149108e-05, "loss": 0.2221, "step": 777 }, { "epoch": 3.160506329113924, "grad_norm": 0.3661495195752543, "learning_rate": 1.4318332586779522e-05, "loss": 0.2427, "step": 778 }, { "epoch": 3.1645569620253164, "grad_norm": 0.33801615622757464, "learning_rate": 1.4263935345778202e-05, "loss": 0.2284, "step": 779 }, { "epoch": 3.168607594936709, "grad_norm": 0.3624074601275801, "learning_rate": 1.420958430225303e-05, "loss": 0.2187, "step": 780 }, { "epoch": 3.1726582278481015, "grad_norm": 0.37171834826243677, "learning_rate": 1.415527989393985e-05, "loss": 0.2166, "step": 781 }, { "epoch": 3.1767088607594935, "grad_norm": 0.35632625409388224, "learning_rate": 1.410102255819891e-05, "loss": 0.234, "step": 782 }, { "epoch": 3.180759493670886, "grad_norm": 0.35777198389184817, "learning_rate": 1.404681273201131e-05, "loss": 0.2195, "step": 783 }, { "epoch": 3.1848101265822786, "grad_norm": 0.3557627887347514, "learning_rate": 1.399265085197556e-05, "loss": 0.2333, "step": 784 }, { "epoch": 3.188860759493671, "grad_norm": 0.36597761689431335, "learning_rate": 1.393853735430398e-05, "loss": 0.2375, "step": 785 }, { "epoch": 3.192911392405063, "grad_norm": 0.359040770836753, "learning_rate": 1.3884472674819246e-05, "loss": 0.2263, "step": 786 }, { "epoch": 3.1969620253164557, "grad_norm": 0.3829457852264788, "learning_rate": 1.3830457248950864e-05, "loss": 0.2544, "step": 787 }, { "epoch": 3.201012658227848, "grad_norm": 0.36705600546389616, "learning_rate": 1.377649151173163e-05, "loss": 0.2379, "step": 788 }, { "epoch": 3.2050632911392407, "grad_norm": 0.37168610436887267, "learning_rate": 1.3722575897794181e-05, "loss": 0.2498, "step": 789 }, { "epoch": 3.209113924050633, "grad_norm": 0.36797750489031017, "learning_rate": 1.3668710841367472e-05, "loss": 0.2197, "step": 790 }, { "epoch": 3.2131645569620253, "grad_norm": 0.35263226464131003, "learning_rate": 1.361489677627324e-05, "loss": 0.2422, "step": 791 }, { "epoch": 3.217215189873418, "grad_norm": 0.37845302529026054, "learning_rate": 1.3561134135922585e-05, "loss": 0.2409, "step": 792 }, { "epoch": 3.2212658227848103, "grad_norm": 0.3492338494114785, "learning_rate": 1.350742335331241e-05, "loss": 0.2534, "step": 793 }, { "epoch": 3.2253164556962024, "grad_norm": 0.36932968261249227, "learning_rate": 1.345376486102198e-05, "loss": 0.2319, "step": 794 }, { "epoch": 3.229367088607595, "grad_norm": 0.367629417312925, "learning_rate": 1.3400159091209414e-05, "loss": 0.244, "step": 795 }, { "epoch": 3.2334177215189874, "grad_norm": 0.3654811386334439, "learning_rate": 1.3346606475608216e-05, "loss": 0.2267, "step": 796 }, { "epoch": 3.23746835443038, "grad_norm": 0.363331412258136, "learning_rate": 1.3293107445523781e-05, "loss": 0.2389, "step": 797 }, { "epoch": 3.241518987341772, "grad_norm": 0.36144175814365953, "learning_rate": 1.3239662431829949e-05, "loss": 0.2122, "step": 798 }, { "epoch": 3.2455696202531645, "grad_norm": 0.3770540442267185, "learning_rate": 1.3186271864965509e-05, "loss": 0.2464, "step": 799 }, { "epoch": 3.249620253164557, "grad_norm": 0.346786645821284, "learning_rate": 1.3132936174930756e-05, "loss": 0.2397, "step": 800 }, { "epoch": 3.253670886075949, "grad_norm": 0.366528274082439, "learning_rate": 1.3079655791283995e-05, "loss": 0.2193, "step": 801 }, { "epoch": 3.2577215189873416, "grad_norm": 0.3800959184504509, "learning_rate": 1.3026431143138108e-05, "loss": 0.2557, "step": 802 }, { "epoch": 3.261772151898734, "grad_norm": 0.3784125498018413, "learning_rate": 1.2973262659157114e-05, "loss": 0.2159, "step": 803 }, { "epoch": 3.2658227848101267, "grad_norm": 0.36613737641311206, "learning_rate": 1.2920150767552651e-05, "loss": 0.2244, "step": 804 }, { "epoch": 3.269873417721519, "grad_norm": 0.3639428304608687, "learning_rate": 1.2867095896080607e-05, "loss": 0.2344, "step": 805 }, { "epoch": 3.2739240506329113, "grad_norm": 0.35219363601092346, "learning_rate": 1.2814098472037612e-05, "loss": 0.2452, "step": 806 }, { "epoch": 3.2779746835443038, "grad_norm": 0.368249230655614, "learning_rate": 1.276115892225764e-05, "loss": 0.2339, "step": 807 }, { "epoch": 3.2820253164556963, "grad_norm": 0.34058301076089803, "learning_rate": 1.2708277673108555e-05, "loss": 0.2324, "step": 808 }, { "epoch": 3.286075949367089, "grad_norm": 0.3582359658622368, "learning_rate": 1.2655455150488649e-05, "loss": 0.2367, "step": 809 }, { "epoch": 3.290126582278481, "grad_norm": 0.364071411063922, "learning_rate": 1.2602691779823272e-05, "loss": 0.2464, "step": 810 }, { "epoch": 3.2941772151898734, "grad_norm": 0.3560760684290192, "learning_rate": 1.2549987986061355e-05, "loss": 0.2504, "step": 811 }, { "epoch": 3.298227848101266, "grad_norm": 0.36277970169240975, "learning_rate": 1.2497344193672005e-05, "loss": 0.2096, "step": 812 }, { "epoch": 3.3022784810126584, "grad_norm": 0.35184271842365494, "learning_rate": 1.2444760826641092e-05, "loss": 0.2378, "step": 813 }, { "epoch": 3.3063291139240505, "grad_norm": 0.35136516497482373, "learning_rate": 1.2392238308467817e-05, "loss": 0.2456, "step": 814 }, { "epoch": 3.310379746835443, "grad_norm": 0.354997239085317, "learning_rate": 1.2339777062161326e-05, "loss": 0.2714, "step": 815 }, { "epoch": 3.3144303797468355, "grad_norm": 0.3470237656794374, "learning_rate": 1.2287377510237293e-05, "loss": 0.226, "step": 816 }, { "epoch": 3.318481012658228, "grad_norm": 0.35270081749251386, "learning_rate": 1.2235040074714488e-05, "loss": 0.2197, "step": 817 }, { "epoch": 3.32253164556962, "grad_norm": 0.3535008682946173, "learning_rate": 1.2182765177111434e-05, "loss": 0.219, "step": 818 }, { "epoch": 3.3265822784810126, "grad_norm": 0.34616495820507975, "learning_rate": 1.213055323844297e-05, "loss": 0.2323, "step": 819 }, { "epoch": 3.330632911392405, "grad_norm": 0.3612158489144064, "learning_rate": 1.2078404679216864e-05, "loss": 0.2348, "step": 820 }, { "epoch": 3.3346835443037977, "grad_norm": 0.3425886361028408, "learning_rate": 1.2026319919430458e-05, "loss": 0.2356, "step": 821 }, { "epoch": 3.3387341772151897, "grad_norm": 0.3416242509236953, "learning_rate": 1.1974299378567227e-05, "loss": 0.2459, "step": 822 }, { "epoch": 3.3427848101265822, "grad_norm": 0.33756698142753544, "learning_rate": 1.1922343475593462e-05, "loss": 0.2437, "step": 823 }, { "epoch": 3.3468354430379748, "grad_norm": 0.3392517669231428, "learning_rate": 1.187045262895488e-05, "loss": 0.2287, "step": 824 }, { "epoch": 3.3508860759493673, "grad_norm": 0.37236671319808856, "learning_rate": 1.1818627256573203e-05, "loss": 0.2352, "step": 825 }, { "epoch": 3.3549367088607593, "grad_norm": 0.35259699406226813, "learning_rate": 1.1766867775842864e-05, "loss": 0.2358, "step": 826 }, { "epoch": 3.358987341772152, "grad_norm": 0.3584125144910017, "learning_rate": 1.1715174603627615e-05, "loss": 0.2211, "step": 827 }, { "epoch": 3.3630379746835444, "grad_norm": 0.3605484330996744, "learning_rate": 1.1663548156257147e-05, "loss": 0.2408, "step": 828 }, { "epoch": 3.367088607594937, "grad_norm": 0.36485140797179744, "learning_rate": 1.161198884952377e-05, "loss": 0.2538, "step": 829 }, { "epoch": 3.371139240506329, "grad_norm": 0.35640506769103003, "learning_rate": 1.1560497098679056e-05, "loss": 0.2202, "step": 830 }, { "epoch": 3.3751898734177215, "grad_norm": 0.36160148328922087, "learning_rate": 1.1509073318430479e-05, "loss": 0.2461, "step": 831 }, { "epoch": 3.379240506329114, "grad_norm": 0.3465237214864515, "learning_rate": 1.1457717922938116e-05, "loss": 0.2127, "step": 832 }, { "epoch": 3.3832911392405065, "grad_norm": 0.34289588491835044, "learning_rate": 1.1406431325811233e-05, "loss": 0.2446, "step": 833 }, { "epoch": 3.3873417721518986, "grad_norm": 0.3377049621840907, "learning_rate": 1.135521394010506e-05, "loss": 0.2329, "step": 834 }, { "epoch": 3.391392405063291, "grad_norm": 0.35235355251116784, "learning_rate": 1.1304066178317367e-05, "loss": 0.2346, "step": 835 }, { "epoch": 3.3954430379746836, "grad_norm": 0.3428831143515493, "learning_rate": 1.1252988452385199e-05, "loss": 0.2243, "step": 836 }, { "epoch": 3.399493670886076, "grad_norm": 0.3322097544436109, "learning_rate": 1.1201981173681536e-05, "loss": 0.2278, "step": 837 }, { "epoch": 3.403544303797468, "grad_norm": 0.36719543268344496, "learning_rate": 1.1151044753011991e-05, "loss": 0.2527, "step": 838 }, { "epoch": 3.4075949367088607, "grad_norm": 0.33616128766695386, "learning_rate": 1.1100179600611491e-05, "loss": 0.2274, "step": 839 }, { "epoch": 3.4116455696202532, "grad_norm": 0.3304965018053031, "learning_rate": 1.1049386126140985e-05, "loss": 0.2564, "step": 840 }, { "epoch": 3.4156962025316457, "grad_norm": 0.34217823442903755, "learning_rate": 1.0998664738684128e-05, "loss": 0.2509, "step": 841 }, { "epoch": 3.419746835443038, "grad_norm": 0.3551998626012895, "learning_rate": 1.0948015846744e-05, "loss": 0.2188, "step": 842 }, { "epoch": 3.4237974683544303, "grad_norm": 0.36204529912371985, "learning_rate": 1.0897439858239832e-05, "loss": 0.2212, "step": 843 }, { "epoch": 3.427848101265823, "grad_norm": 0.33524884906304625, "learning_rate": 1.0846937180503652e-05, "loss": 0.252, "step": 844 }, { "epoch": 3.4318987341772154, "grad_norm": 0.3475390180037774, "learning_rate": 1.0796508220277117e-05, "loss": 0.2479, "step": 845 }, { "epoch": 3.4359493670886074, "grad_norm": 0.3702535275459518, "learning_rate": 1.0746153383708107e-05, "loss": 0.2556, "step": 846 }, { "epoch": 3.44, "grad_norm": 0.36169819209096565, "learning_rate": 1.0695873076347579e-05, "loss": 0.2176, "step": 847 }, { "epoch": 3.4440506329113925, "grad_norm": 0.36170037352386597, "learning_rate": 1.0645667703146205e-05, "loss": 0.235, "step": 848 }, { "epoch": 3.448101265822785, "grad_norm": 0.36396941459653526, "learning_rate": 1.0595537668451161e-05, "loss": 0.2119, "step": 849 }, { "epoch": 3.452151898734177, "grad_norm": 0.34657205375063904, "learning_rate": 1.0545483376002854e-05, "loss": 0.2447, "step": 850 }, { "epoch": 3.4562025316455696, "grad_norm": 0.34764424390609977, "learning_rate": 1.0495505228931676e-05, "loss": 0.2261, "step": 851 }, { "epoch": 3.460253164556962, "grad_norm": 0.3540203000920219, "learning_rate": 1.044560362975474e-05, "loss": 0.225, "step": 852 }, { "epoch": 3.4643037974683546, "grad_norm": 0.33246265501626876, "learning_rate": 1.0395778980372695e-05, "loss": 0.2189, "step": 853 }, { "epoch": 3.4683544303797467, "grad_norm": 0.34906634732507646, "learning_rate": 1.0346031682066381e-05, "loss": 0.2184, "step": 854 }, { "epoch": 3.472405063291139, "grad_norm": 0.35635962906206714, "learning_rate": 1.0296362135493724e-05, "loss": 0.2288, "step": 855 }, { "epoch": 3.4764556962025317, "grad_norm": 0.36576166133727517, "learning_rate": 1.0246770740686422e-05, "loss": 0.2496, "step": 856 }, { "epoch": 3.480506329113924, "grad_norm": 0.3417114170301459, "learning_rate": 1.0197257897046743e-05, "loss": 0.2308, "step": 857 }, { "epoch": 3.4845569620253163, "grad_norm": 0.3449966490636293, "learning_rate": 1.014782400334433e-05, "loss": 0.212, "step": 858 }, { "epoch": 3.488607594936709, "grad_norm": 0.3718839471837771, "learning_rate": 1.009846945771296e-05, "loss": 0.2374, "step": 859 }, { "epoch": 3.4926582278481013, "grad_norm": 0.3418752399103022, "learning_rate": 1.0049194657647363e-05, "loss": 0.2416, "step": 860 }, { "epoch": 3.496708860759494, "grad_norm": 0.3561230693059429, "learning_rate": 1.0000000000000006e-05, "loss": 0.2247, "step": 861 }, { "epoch": 3.500759493670886, "grad_norm": 0.34485654417522094, "learning_rate": 9.950885880977891e-06, "loss": 0.2482, "step": 862 }, { "epoch": 3.5048101265822784, "grad_norm": 0.351924494718063, "learning_rate": 9.901852696139382e-06, "loss": 0.2205, "step": 863 }, { "epoch": 3.508860759493671, "grad_norm": 0.36321790911102725, "learning_rate": 9.852900840391027e-06, "loss": 0.2221, "step": 864 }, { "epoch": 3.5129113924050634, "grad_norm": 0.3694019373909633, "learning_rate": 9.804030707984313e-06, "loss": 0.2305, "step": 865 }, { "epoch": 3.516962025316456, "grad_norm": 0.3510122953259695, "learning_rate": 9.755242692512599e-06, "loss": 0.2348, "step": 866 }, { "epoch": 3.521012658227848, "grad_norm": 0.36009472272766474, "learning_rate": 9.70653718690782e-06, "loss": 0.2256, "step": 867 }, { "epoch": 3.5250632911392406, "grad_norm": 0.326129629745237, "learning_rate": 9.657914583437454e-06, "loss": 0.2344, "step": 868 }, { "epoch": 3.529113924050633, "grad_norm": 0.34724216397346724, "learning_rate": 9.609375273701246e-06, "loss": 0.2175, "step": 869 }, { "epoch": 3.533164556962025, "grad_norm": 0.36224527437022286, "learning_rate": 9.560919648628133e-06, "loss": 0.2637, "step": 870 }, { "epoch": 3.5372151898734177, "grad_norm": 0.35377723398750827, "learning_rate": 9.512548098473047e-06, "loss": 0.2364, "step": 871 }, { "epoch": 3.54126582278481, "grad_norm": 0.3477954918318301, "learning_rate": 9.464261012813825e-06, "loss": 0.2308, "step": 872 }, { "epoch": 3.5453164556962027, "grad_norm": 0.338278257303889, "learning_rate": 9.416058780547987e-06, "loss": 0.2549, "step": 873 }, { "epoch": 3.549367088607595, "grad_norm": 0.3376152903976817, "learning_rate": 9.367941789889714e-06, "loss": 0.2369, "step": 874 }, { "epoch": 3.5534177215189873, "grad_norm": 0.3524873134334011, "learning_rate": 9.319910428366607e-06, "loss": 0.2359, "step": 875 }, { "epoch": 3.55746835443038, "grad_norm": 0.3533505706983089, "learning_rate": 9.271965082816667e-06, "loss": 0.2654, "step": 876 }, { "epoch": 3.5615189873417723, "grad_norm": 0.35227662352006434, "learning_rate": 9.224106139385111e-06, "loss": 0.2148, "step": 877 }, { "epoch": 3.5655696202531644, "grad_norm": 0.35300508403619046, "learning_rate": 9.176333983521291e-06, "loss": 0.2456, "step": 878 }, { "epoch": 3.569620253164557, "grad_norm": 0.3492488175978394, "learning_rate": 9.12864899997558e-06, "loss": 0.2078, "step": 879 }, { "epoch": 3.5736708860759494, "grad_norm": 0.35481569552845293, "learning_rate": 9.08105157279628e-06, "loss": 0.2466, "step": 880 }, { "epoch": 3.577721518987342, "grad_norm": 0.36112810187935535, "learning_rate": 9.03354208532653e-06, "loss": 0.2379, "step": 881 }, { "epoch": 3.5817721518987344, "grad_norm": 0.3549606297518305, "learning_rate": 8.986120920201205e-06, "loss": 0.2267, "step": 882 }, { "epoch": 3.5858227848101265, "grad_norm": 0.33421157575187477, "learning_rate": 8.938788459343852e-06, "loss": 0.2523, "step": 883 }, { "epoch": 3.589873417721519, "grad_norm": 0.3460310573040692, "learning_rate": 8.8915450839636e-06, "loss": 0.2327, "step": 884 }, { "epoch": 3.5939240506329115, "grad_norm": 0.3526726483548, "learning_rate": 8.844391174552116e-06, "loss": 0.2317, "step": 885 }, { "epoch": 3.5979746835443036, "grad_norm": 0.3290269054414998, "learning_rate": 8.797327110880479e-06, "loss": 0.2503, "step": 886 }, { "epoch": 3.602025316455696, "grad_norm": 0.3420397340709768, "learning_rate": 8.750353271996206e-06, "loss": 0.2301, "step": 887 }, { "epoch": 3.6060759493670886, "grad_norm": 0.35564434194356814, "learning_rate": 8.703470036220132e-06, "loss": 0.2254, "step": 888 }, { "epoch": 3.610126582278481, "grad_norm": 0.3418222553142868, "learning_rate": 8.656677781143394e-06, "loss": 0.2349, "step": 889 }, { "epoch": 3.6141772151898737, "grad_norm": 0.3515312318627329, "learning_rate": 8.609976883624377e-06, "loss": 0.2345, "step": 890 }, { "epoch": 3.6182278481012657, "grad_norm": 0.33059395981197054, "learning_rate": 8.563367719785698e-06, "loss": 0.2336, "step": 891 }, { "epoch": 3.6222784810126583, "grad_norm": 0.33597437554075765, "learning_rate": 8.516850665011138e-06, "loss": 0.242, "step": 892 }, { "epoch": 3.6263291139240508, "grad_norm": 0.3440738370837871, "learning_rate": 8.47042609394269e-06, "loss": 0.2292, "step": 893 }, { "epoch": 3.630379746835443, "grad_norm": 0.3299343751671095, "learning_rate": 8.424094380477432e-06, "loss": 0.2406, "step": 894 }, { "epoch": 3.6344303797468354, "grad_norm": 0.34484404975249705, "learning_rate": 8.37785589776465e-06, "loss": 0.2319, "step": 895 }, { "epoch": 3.638481012658228, "grad_norm": 0.333666707615351, "learning_rate": 8.331711018202694e-06, "loss": 0.2352, "step": 896 }, { "epoch": 3.6425316455696204, "grad_norm": 0.33849928626713477, "learning_rate": 8.285660113436104e-06, "loss": 0.2364, "step": 897 }, { "epoch": 3.646582278481013, "grad_norm": 0.31880829704205704, "learning_rate": 8.239703554352527e-06, "loss": 0.2408, "step": 898 }, { "epoch": 3.650632911392405, "grad_norm": 0.3384207854803479, "learning_rate": 8.193841711079775e-06, "loss": 0.215, "step": 899 }, { "epoch": 3.6546835443037975, "grad_norm": 0.3592409593952134, "learning_rate": 8.148074952982828e-06, "loss": 0.2395, "step": 900 }, { "epoch": 3.65873417721519, "grad_norm": 0.33129201011412707, "learning_rate": 8.102403648660859e-06, "loss": 0.2449, "step": 901 }, { "epoch": 3.662784810126582, "grad_norm": 0.34165479543491223, "learning_rate": 8.056828165944282e-06, "loss": 0.2244, "step": 902 }, { "epoch": 3.6668354430379746, "grad_norm": 0.34816387455902914, "learning_rate": 8.011348871891762e-06, "loss": 0.207, "step": 903 }, { "epoch": 3.670886075949367, "grad_norm": 0.33671740750808526, "learning_rate": 7.965966132787287e-06, "loss": 0.2574, "step": 904 }, { "epoch": 3.6749367088607596, "grad_norm": 0.34770099858580455, "learning_rate": 7.920680314137189e-06, "loss": 0.2491, "step": 905 }, { "epoch": 3.678987341772152, "grad_norm": 0.3603663712914182, "learning_rate": 7.875491780667246e-06, "loss": 0.2316, "step": 906 }, { "epoch": 3.683037974683544, "grad_norm": 0.3326744006681135, "learning_rate": 7.830400896319667e-06, "loss": 0.2363, "step": 907 }, { "epoch": 3.6870886075949367, "grad_norm": 0.3388133848415356, "learning_rate": 7.785408024250259e-06, "loss": 0.2267, "step": 908 }, { "epoch": 3.6911392405063292, "grad_norm": 0.34811314427146234, "learning_rate": 7.74051352682542e-06, "loss": 0.2393, "step": 909 }, { "epoch": 3.6951898734177213, "grad_norm": 0.32924802623520716, "learning_rate": 7.695717765619257e-06, "loss": 0.2429, "step": 910 }, { "epoch": 3.699240506329114, "grad_norm": 0.34402817587017587, "learning_rate": 7.651021101410673e-06, "loss": 0.2379, "step": 911 }, { "epoch": 3.7032911392405063, "grad_norm": 0.34029970848448704, "learning_rate": 7.606423894180464e-06, "loss": 0.2292, "step": 912 }, { "epoch": 3.707341772151899, "grad_norm": 0.3337070887544698, "learning_rate": 7.56192650310839e-06, "loss": 0.2364, "step": 913 }, { "epoch": 3.7113924050632914, "grad_norm": 0.33809921084125716, "learning_rate": 7.517529286570349e-06, "loss": 0.2473, "step": 914 }, { "epoch": 3.7154430379746834, "grad_norm": 0.32897127533974213, "learning_rate": 7.473232602135387e-06, "loss": 0.2472, "step": 915 }, { "epoch": 3.719493670886076, "grad_norm": 0.342175089515354, "learning_rate": 7.429036806562935e-06, "loss": 0.2412, "step": 916 }, { "epoch": 3.7235443037974685, "grad_norm": 0.3448541400275619, "learning_rate": 7.3849422557998455e-06, "loss": 0.2088, "step": 917 }, { "epoch": 3.7275949367088606, "grad_norm": 0.3398647976136947, "learning_rate": 7.340949304977567e-06, "loss": 0.2433, "step": 918 }, { "epoch": 3.731645569620253, "grad_norm": 0.3439727655961364, "learning_rate": 7.297058308409282e-06, "loss": 0.2244, "step": 919 }, { "epoch": 3.7356962025316456, "grad_norm": 0.33457040418643136, "learning_rate": 7.25326961958704e-06, "loss": 0.2261, "step": 920 }, { "epoch": 3.739746835443038, "grad_norm": 0.35453966988052726, "learning_rate": 7.209583591178921e-06, "loss": 0.232, "step": 921 }, { "epoch": 3.7437974683544306, "grad_norm": 0.3459860873957885, "learning_rate": 7.1660005750261925e-06, "loss": 0.2013, "step": 922 }, { "epoch": 3.7478481012658227, "grad_norm": 0.3493251602599132, "learning_rate": 7.1225209221404765e-06, "loss": 0.2128, "step": 923 }, { "epoch": 3.751898734177215, "grad_norm": 0.3284560967538705, "learning_rate": 7.079144982700909e-06, "loss": 0.2313, "step": 924 }, { "epoch": 3.7559493670886077, "grad_norm": 0.33724709746820125, "learning_rate": 7.0358731060513695e-06, "loss": 0.2304, "step": 925 }, { "epoch": 3.76, "grad_norm": 0.3377941865080476, "learning_rate": 6.99270564069757e-06, "loss": 0.2518, "step": 926 }, { "epoch": 3.7640506329113923, "grad_norm": 0.3294862119659185, "learning_rate": 6.949642934304375e-06, "loss": 0.2261, "step": 927 }, { "epoch": 3.768101265822785, "grad_norm": 0.3401198471934571, "learning_rate": 6.906685333692871e-06, "loss": 0.2441, "step": 928 }, { "epoch": 3.7721518987341773, "grad_norm": 0.36256814301204215, "learning_rate": 6.86383318483769e-06, "loss": 0.2483, "step": 929 }, { "epoch": 3.77620253164557, "grad_norm": 0.3386630637436573, "learning_rate": 6.821086832864139e-06, "loss": 0.235, "step": 930 }, { "epoch": 3.780253164556962, "grad_norm": 0.335249127842362, "learning_rate": 6.77844662204546e-06, "loss": 0.2213, "step": 931 }, { "epoch": 3.7843037974683544, "grad_norm": 0.3349045982473355, "learning_rate": 6.7359128958000455e-06, "loss": 0.228, "step": 932 }, { "epoch": 3.788354430379747, "grad_norm": 0.34872602370540773, "learning_rate": 6.693485996688695e-06, "loss": 0.2165, "step": 933 }, { "epoch": 3.792405063291139, "grad_norm": 0.3331010961685088, "learning_rate": 6.651166266411801e-06, "loss": 0.2588, "step": 934 }, { "epoch": 3.7964556962025315, "grad_norm": 0.3319885890243186, "learning_rate": 6.6089540458066725e-06, "loss": 0.2431, "step": 935 }, { "epoch": 3.800506329113924, "grad_norm": 0.33110088698812584, "learning_rate": 6.566849674844711e-06, "loss": 0.2454, "step": 936 }, { "epoch": 3.8045569620253166, "grad_norm": 0.35739053318988107, "learning_rate": 6.524853492628747e-06, "loss": 0.2284, "step": 937 }, { "epoch": 3.808607594936709, "grad_norm": 0.3198630433901025, "learning_rate": 6.4829658373902536e-06, "loss": 0.2375, "step": 938 }, { "epoch": 3.812658227848101, "grad_norm": 0.3323138401051713, "learning_rate": 6.441187046486648e-06, "loss": 0.2298, "step": 939 }, { "epoch": 3.8167088607594937, "grad_norm": 0.34558108192354026, "learning_rate": 6.399517456398567e-06, "loss": 0.2316, "step": 940 }, { "epoch": 3.820759493670886, "grad_norm": 0.33434951663099044, "learning_rate": 6.357957402727164e-06, "loss": 0.2359, "step": 941 }, { "epoch": 3.8248101265822783, "grad_norm": 0.33163183185385847, "learning_rate": 6.316507220191395e-06, "loss": 0.2357, "step": 942 }, { "epoch": 3.8288607594936708, "grad_norm": 0.34814830015403, "learning_rate": 6.275167242625331e-06, "loss": 0.2098, "step": 943 }, { "epoch": 3.8329113924050633, "grad_norm": 0.32193017506260063, "learning_rate": 6.233937802975471e-06, "loss": 0.2214, "step": 944 }, { "epoch": 3.836962025316456, "grad_norm": 0.3240287116882871, "learning_rate": 6.192819233298046e-06, "loss": 0.2223, "step": 945 }, { "epoch": 3.8410126582278483, "grad_norm": 0.32522332928020936, "learning_rate": 6.151811864756383e-06, "loss": 0.2108, "step": 946 }, { "epoch": 3.8450632911392404, "grad_norm": 0.33828837405405515, "learning_rate": 6.1109160276181655e-06, "loss": 0.2212, "step": 947 }, { "epoch": 3.849113924050633, "grad_norm": 0.33611084223678317, "learning_rate": 6.070132051252868e-06, "loss": 0.2305, "step": 948 }, { "epoch": 3.8531645569620254, "grad_norm": 0.3460677947232825, "learning_rate": 6.0294602641290034e-06, "loss": 0.2434, "step": 949 }, { "epoch": 3.8572151898734175, "grad_norm": 0.3354582759166687, "learning_rate": 5.988900993811575e-06, "loss": 0.2279, "step": 950 }, { "epoch": 3.86126582278481, "grad_norm": 0.338609054853971, "learning_rate": 5.948454566959363e-06, "loss": 0.2246, "step": 951 }, { "epoch": 3.8653164556962025, "grad_norm": 0.33587533011445797, "learning_rate": 5.908121309322328e-06, "loss": 0.2383, "step": 952 }, { "epoch": 3.869367088607595, "grad_norm": 0.3363482050519141, "learning_rate": 5.867901545738976e-06, "loss": 0.2298, "step": 953 }, { "epoch": 3.8734177215189876, "grad_norm": 0.3228524142592659, "learning_rate": 5.827795600133774e-06, "loss": 0.2362, "step": 954 }, { "epoch": 3.8774683544303796, "grad_norm": 0.36176020386249985, "learning_rate": 5.787803795514466e-06, "loss": 0.2366, "step": 955 }, { "epoch": 3.881518987341772, "grad_norm": 0.340729426199364, "learning_rate": 5.747926453969576e-06, "loss": 0.2152, "step": 956 }, { "epoch": 3.8855696202531647, "grad_norm": 0.35613582667396154, "learning_rate": 5.708163896665708e-06, "loss": 0.2406, "step": 957 }, { "epoch": 3.8896202531645567, "grad_norm": 0.32967324069851894, "learning_rate": 5.668516443845047e-06, "loss": 0.2277, "step": 958 }, { "epoch": 3.8936708860759492, "grad_norm": 0.32759807911838473, "learning_rate": 5.6289844148227225e-06, "loss": 0.2433, "step": 959 }, { "epoch": 3.8977215189873418, "grad_norm": 0.3359689864039365, "learning_rate": 5.5895681279842615e-06, "loss": 0.2249, "step": 960 }, { "epoch": 3.9017721518987343, "grad_norm": 0.3275592775437982, "learning_rate": 5.550267900783019e-06, "loss": 0.2467, "step": 961 }, { "epoch": 3.905822784810127, "grad_norm": 0.34464018078619024, "learning_rate": 5.511084049737623e-06, "loss": 0.2398, "step": 962 }, { "epoch": 3.909873417721519, "grad_norm": 0.3481595426665233, "learning_rate": 5.4720168904294215e-06, "loss": 0.2286, "step": 963 }, { "epoch": 3.9139240506329114, "grad_norm": 0.34152000289356915, "learning_rate": 5.433066737499948e-06, "loss": 0.2284, "step": 964 }, { "epoch": 3.917974683544304, "grad_norm": 0.3242936855657622, "learning_rate": 5.394233904648376e-06, "loss": 0.235, "step": 965 }, { "epoch": 3.922025316455696, "grad_norm": 0.3299743461986252, "learning_rate": 5.355518704628997e-06, "loss": 0.2311, "step": 966 }, { "epoch": 3.9260759493670885, "grad_norm": 0.3324088341130083, "learning_rate": 5.316921449248731e-06, "loss": 0.209, "step": 967 }, { "epoch": 3.930126582278481, "grad_norm": 0.33802238342969715, "learning_rate": 5.278442449364538e-06, "loss": 0.2363, "step": 968 }, { "epoch": 3.9341772151898735, "grad_norm": 0.3335857285716498, "learning_rate": 5.240082014881016e-06, "loss": 0.2358, "step": 969 }, { "epoch": 3.938227848101266, "grad_norm": 0.3238612117623106, "learning_rate": 5.201840454747822e-06, "loss": 0.2392, "step": 970 }, { "epoch": 3.942278481012658, "grad_norm": 0.3354706585459416, "learning_rate": 5.163718076957223e-06, "loss": 0.2398, "step": 971 }, { "epoch": 3.9463291139240506, "grad_norm": 0.33993177662762897, "learning_rate": 5.125715188541609e-06, "loss": 0.241, "step": 972 }, { "epoch": 3.950379746835443, "grad_norm": 0.3281926184197516, "learning_rate": 5.087832095571021e-06, "loss": 0.2492, "step": 973 }, { "epoch": 3.954430379746835, "grad_norm": 0.34946219360584935, "learning_rate": 5.0500691031506766e-06, "loss": 0.2309, "step": 974 }, { "epoch": 3.9584810126582277, "grad_norm": 0.3551456729491995, "learning_rate": 5.01242651541854e-06, "loss": 0.2269, "step": 975 }, { "epoch": 3.9625316455696202, "grad_norm": 0.33765798917233697, "learning_rate": 4.974904635542815e-06, "loss": 0.244, "step": 976 }, { "epoch": 3.9665822784810127, "grad_norm": 0.31853219347677997, "learning_rate": 4.937503765719582e-06, "loss": 0.2418, "step": 977 }, { "epoch": 3.9706329113924053, "grad_norm": 0.34340385606265994, "learning_rate": 4.900224207170299e-06, "loss": 0.2235, "step": 978 }, { "epoch": 3.9746835443037973, "grad_norm": 0.32769745769415326, "learning_rate": 4.8630662601394065e-06, "loss": 0.2518, "step": 979 }, { "epoch": 3.97873417721519, "grad_norm": 0.3488615604789946, "learning_rate": 4.8260302238918995e-06, "loss": 0.2276, "step": 980 }, { "epoch": 3.9827848101265824, "grad_norm": 0.32514365051981725, "learning_rate": 4.789116396710924e-06, "loss": 0.2233, "step": 981 }, { "epoch": 3.9868354430379744, "grad_norm": 0.32581636162744076, "learning_rate": 4.752325075895368e-06, "loss": 0.2386, "step": 982 }, { "epoch": 3.990886075949367, "grad_norm": 0.3348320870594431, "learning_rate": 4.715656557757473e-06, "loss": 0.2348, "step": 983 }, { "epoch": 3.9949367088607595, "grad_norm": 0.34121526065474916, "learning_rate": 4.679111137620442e-06, "loss": 0.2399, "step": 984 }, { "epoch": 4.002025316455696, "grad_norm": 0.34996902230025756, "learning_rate": 4.6426891098160585e-06, "loss": 0.2086, "step": 985 }, { "epoch": 4.006075949367089, "grad_norm": 0.4737869870293495, "learning_rate": 4.6063907676823474e-06, "loss": 0.1603, "step": 986 }, { "epoch": 4.010126582278481, "grad_norm": 0.36152744729913056, "learning_rate": 4.570216403561141e-06, "loss": 0.1824, "step": 987 }, { "epoch": 4.014177215189873, "grad_norm": 0.316622703607989, "learning_rate": 4.534166308795815e-06, "loss": 0.1608, "step": 988 }, { "epoch": 4.018227848101266, "grad_norm": 0.27058138376213486, "learning_rate": 4.498240773728859e-06, "loss": 0.1671, "step": 989 }, { "epoch": 4.022278481012658, "grad_norm": 0.32582983507634555, "learning_rate": 4.462440087699609e-06, "loss": 0.1585, "step": 990 }, { "epoch": 4.02632911392405, "grad_norm": 0.4134267539179803, "learning_rate": 4.426764539041861e-06, "loss": 0.1653, "step": 991 }, { "epoch": 4.030379746835443, "grad_norm": 0.4176672040628537, "learning_rate": 4.391214415081582e-06, "loss": 0.1645, "step": 992 }, { "epoch": 4.034430379746835, "grad_norm": 0.39073185015537004, "learning_rate": 4.355790002134579e-06, "loss": 0.151, "step": 993 }, { "epoch": 4.038481012658228, "grad_norm": 0.37478088773730694, "learning_rate": 4.320491585504207e-06, "loss": 0.1929, "step": 994 }, { "epoch": 4.04253164556962, "grad_norm": 0.32326916945371015, "learning_rate": 4.2853194494790615e-06, "loss": 0.1767, "step": 995 }, { "epoch": 4.046582278481012, "grad_norm": 0.31175716646947377, "learning_rate": 4.250273877330691e-06, "loss": 0.1774, "step": 996 }, { "epoch": 4.050632911392405, "grad_norm": 0.3518887581431788, "learning_rate": 4.215355151311313e-06, "loss": 0.1871, "step": 997 }, { "epoch": 4.054683544303797, "grad_norm": 0.3333296558443136, "learning_rate": 4.180563552651542e-06, "loss": 0.1587, "step": 998 }, { "epoch": 4.0587341772151895, "grad_norm": 0.3077461004425516, "learning_rate": 4.145899361558147e-06, "loss": 0.164, "step": 999 }, { "epoch": 4.062784810126582, "grad_norm": 0.29375061124297847, "learning_rate": 4.111362857211738e-06, "loss": 0.1653, "step": 1000 }, { "epoch": 4.0668354430379745, "grad_norm": 0.29650450982176696, "learning_rate": 4.076954317764592e-06, "loss": 0.1968, "step": 1001 }, { "epoch": 4.0708860759493675, "grad_norm": 0.2942621226899737, "learning_rate": 4.042674020338335e-06, "loss": 0.1693, "step": 1002 }, { "epoch": 4.0749367088607595, "grad_norm": 0.28589635792458207, "learning_rate": 4.0085222410217835e-06, "loss": 0.1884, "step": 1003 }, { "epoch": 4.078987341772152, "grad_norm": 0.2973522242457559, "learning_rate": 3.974499254868674e-06, "loss": 0.1662, "step": 1004 }, { "epoch": 4.083037974683545, "grad_norm": 0.28651031878577, "learning_rate": 3.940605335895451e-06, "loss": 0.1579, "step": 1005 }, { "epoch": 4.087088607594937, "grad_norm": 0.30287099703783055, "learning_rate": 3.90684075707908e-06, "loss": 0.168, "step": 1006 }, { "epoch": 4.091139240506329, "grad_norm": 0.28206027399092215, "learning_rate": 3.8732057903548505e-06, "loss": 0.1557, "step": 1007 }, { "epoch": 4.095189873417722, "grad_norm": 0.2644439079473084, "learning_rate": 3.8397007066141375e-06, "loss": 0.1755, "step": 1008 }, { "epoch": 4.099240506329114, "grad_norm": 0.2723290576618775, "learning_rate": 3.806325775702304e-06, "loss": 0.1594, "step": 1009 }, { "epoch": 4.103291139240507, "grad_norm": 0.27058488742836734, "learning_rate": 3.773081266416434e-06, "loss": 0.1673, "step": 1010 }, { "epoch": 4.107341772151899, "grad_norm": 0.2682829332483415, "learning_rate": 3.739967446503245e-06, "loss": 0.1693, "step": 1011 }, { "epoch": 4.111392405063291, "grad_norm": 0.2707077320238447, "learning_rate": 3.706984582656894e-06, "loss": 0.1576, "step": 1012 }, { "epoch": 4.115443037974684, "grad_norm": 0.27843376401317466, "learning_rate": 3.6741329405168237e-06, "loss": 0.179, "step": 1013 }, { "epoch": 4.119493670886076, "grad_norm": 0.2771202619242917, "learning_rate": 3.641412784665648e-06, "loss": 0.1823, "step": 1014 }, { "epoch": 4.123544303797468, "grad_norm": 0.2542862097909013, "learning_rate": 3.608824378627005e-06, "loss": 0.1778, "step": 1015 }, { "epoch": 4.127594936708861, "grad_norm": 0.28014790405363216, "learning_rate": 3.5763679848634337e-06, "loss": 0.1674, "step": 1016 }, { "epoch": 4.131645569620253, "grad_norm": 0.2617816380121261, "learning_rate": 3.544043864774269e-06, "loss": 0.1888, "step": 1017 }, { "epoch": 4.135696202531646, "grad_norm": 0.2612085628219579, "learning_rate": 3.5118522786935282e-06, "loss": 0.1506, "step": 1018 }, { "epoch": 4.139746835443038, "grad_norm": 0.26185941190150575, "learning_rate": 3.479793485887819e-06, "loss": 0.1403, "step": 1019 }, { "epoch": 4.14379746835443, "grad_norm": 0.27571067983658687, "learning_rate": 3.4478677445542653e-06, "loss": 0.1758, "step": 1020 }, { "epoch": 4.147848101265823, "grad_norm": 0.258309020481671, "learning_rate": 3.4160753118183767e-06, "loss": 0.1753, "step": 1021 }, { "epoch": 4.151898734177215, "grad_norm": 0.2524781960141809, "learning_rate": 3.3844164437320527e-06, "loss": 0.1713, "step": 1022 }, { "epoch": 4.155949367088607, "grad_norm": 0.2531188035138554, "learning_rate": 3.3528913952714558e-06, "loss": 0.1472, "step": 1023 }, { "epoch": 4.16, "grad_norm": 0.26498796052135615, "learning_rate": 3.321500420335e-06, "loss": 0.1797, "step": 1024 }, { "epoch": 4.164050632911392, "grad_norm": 0.24756751406164812, "learning_rate": 3.290243771741275e-06, "loss": 0.1368, "step": 1025 }, { "epoch": 4.168101265822785, "grad_norm": 0.2681097323326484, "learning_rate": 3.2591217012270325e-06, "loss": 0.1653, "step": 1026 }, { "epoch": 4.172151898734177, "grad_norm": 0.25552308083539244, "learning_rate": 3.228134459445149e-06, "loss": 0.1611, "step": 1027 }, { "epoch": 4.176202531645569, "grad_norm": 0.25784442985139006, "learning_rate": 3.1972822959626205e-06, "loss": 0.1425, "step": 1028 }, { "epoch": 4.180253164556962, "grad_norm": 0.2627572318639515, "learning_rate": 3.166565459258513e-06, "loss": 0.1572, "step": 1029 }, { "epoch": 4.184303797468354, "grad_norm": 0.26473136136725045, "learning_rate": 3.1359841967220193e-06, "loss": 0.179, "step": 1030 }, { "epoch": 4.188354430379746, "grad_norm": 0.2522182330002006, "learning_rate": 3.105538754650419e-06, "loss": 0.1627, "step": 1031 }, { "epoch": 4.192405063291139, "grad_norm": 0.2691730416393301, "learning_rate": 3.07522937824712e-06, "loss": 0.156, "step": 1032 }, { "epoch": 4.1964556962025314, "grad_norm": 0.2583032193326536, "learning_rate": 3.0450563116196697e-06, "loss": 0.1721, "step": 1033 }, { "epoch": 4.200506329113924, "grad_norm": 0.25666751780269986, "learning_rate": 3.0150197977778008e-06, "loss": 0.1701, "step": 1034 }, { "epoch": 4.2045569620253165, "grad_norm": 0.25850837074512206, "learning_rate": 2.985120078631465e-06, "loss": 0.1765, "step": 1035 }, { "epoch": 4.2086075949367086, "grad_norm": 0.245904333553056, "learning_rate": 2.9553573949888893e-06, "loss": 0.1786, "step": 1036 }, { "epoch": 4.2126582278481015, "grad_norm": 0.26491624661409396, "learning_rate": 2.9257319865546384e-06, "loss": 0.1524, "step": 1037 }, { "epoch": 4.216708860759494, "grad_norm": 0.26296542538711953, "learning_rate": 2.896244091927678e-06, "loss": 0.1924, "step": 1038 }, { "epoch": 4.220759493670886, "grad_norm": 0.2570411761412734, "learning_rate": 2.8668939485994584e-06, "loss": 0.1605, "step": 1039 }, { "epoch": 4.224810126582279, "grad_norm": 0.2643215954185178, "learning_rate": 2.837681792951994e-06, "loss": 0.1761, "step": 1040 }, { "epoch": 4.228860759493671, "grad_norm": 0.25434195418095445, "learning_rate": 2.808607860255981e-06, "loss": 0.147, "step": 1041 }, { "epoch": 4.232911392405064, "grad_norm": 0.25513521979915943, "learning_rate": 2.7796723846688634e-06, "loss": 0.173, "step": 1042 }, { "epoch": 4.236962025316456, "grad_norm": 0.2622254235805702, "learning_rate": 2.7508755992329937e-06, "loss": 0.1657, "step": 1043 }, { "epoch": 4.241012658227848, "grad_norm": 0.25110807644944844, "learning_rate": 2.722217735873718e-06, "loss": 0.1504, "step": 1044 }, { "epoch": 4.245063291139241, "grad_norm": 0.25374268217539275, "learning_rate": 2.6936990253975315e-06, "loss": 0.1452, "step": 1045 }, { "epoch": 4.249113924050633, "grad_norm": 0.2677109683286116, "learning_rate": 2.665319697490205e-06, "loss": 0.1621, "step": 1046 }, { "epoch": 4.253164556962025, "grad_norm": 0.26009409811464435, "learning_rate": 2.637079980714945e-06, "loss": 0.1929, "step": 1047 }, { "epoch": 4.257215189873418, "grad_norm": 0.25733213505382574, "learning_rate": 2.6089801025105453e-06, "loss": 0.1589, "step": 1048 }, { "epoch": 4.26126582278481, "grad_norm": 0.25152840083717665, "learning_rate": 2.581020289189571e-06, "loss": 0.1637, "step": 1049 }, { "epoch": 4.265316455696203, "grad_norm": 0.2526944758303743, "learning_rate": 2.553200765936501e-06, "loss": 0.1493, "step": 1050 }, { "epoch": 4.269367088607595, "grad_norm": 0.27008639561876024, "learning_rate": 2.525521756805962e-06, "loss": 0.1464, "step": 1051 }, { "epoch": 4.273417721518987, "grad_norm": 0.26031766252069, "learning_rate": 2.497983484720885e-06, "loss": 0.1502, "step": 1052 }, { "epoch": 4.27746835443038, "grad_norm": 0.25830626175395205, "learning_rate": 2.470586171470728e-06, "loss": 0.1629, "step": 1053 }, { "epoch": 4.281518987341772, "grad_norm": 0.26236527563697476, "learning_rate": 2.4433300377096836e-06, "loss": 0.1714, "step": 1054 }, { "epoch": 4.285569620253165, "grad_norm": 0.25776756076245133, "learning_rate": 2.4162153029549073e-06, "loss": 0.1738, "step": 1055 }, { "epoch": 4.289620253164557, "grad_norm": 0.26447761839466766, "learning_rate": 2.3892421855847458e-06, "loss": 0.1719, "step": 1056 }, { "epoch": 4.293670886075949, "grad_norm": 0.26326076296800016, "learning_rate": 2.362410902836978e-06, "loss": 0.1539, "step": 1057 }, { "epoch": 4.297721518987342, "grad_norm": 0.25824158755276816, "learning_rate": 2.3357216708070653e-06, "loss": 0.1755, "step": 1058 }, { "epoch": 4.301772151898734, "grad_norm": 0.25688401943993044, "learning_rate": 2.309174704446411e-06, "loss": 0.176, "step": 1059 }, { "epoch": 4.305822784810126, "grad_norm": 0.2575956658687494, "learning_rate": 2.2827702175606437e-06, "loss": 0.1867, "step": 1060 }, { "epoch": 4.309873417721519, "grad_norm": 0.2575126466052107, "learning_rate": 2.256508422807855e-06, "loss": 0.1775, "step": 1061 }, { "epoch": 4.313924050632911, "grad_norm": 0.26404160105914953, "learning_rate": 2.230389531696946e-06, "loss": 0.1531, "step": 1062 }, { "epoch": 4.317974683544303, "grad_norm": 0.2596959097744285, "learning_rate": 2.204413754585857e-06, "loss": 0.1802, "step": 1063 }, { "epoch": 4.322025316455696, "grad_norm": 0.25834437480331857, "learning_rate": 2.1785813006799406e-06, "loss": 0.169, "step": 1064 }, { "epoch": 4.326075949367088, "grad_norm": 0.25340473839493866, "learning_rate": 2.1528923780302224e-06, "loss": 0.1788, "step": 1065 }, { "epoch": 4.330126582278481, "grad_norm": 0.25471374165628147, "learning_rate": 2.127347193531757e-06, "loss": 0.1643, "step": 1066 }, { "epoch": 4.334177215189873, "grad_norm": 0.26717971227178694, "learning_rate": 2.101945952921942e-06, "loss": 0.1681, "step": 1067 }, { "epoch": 4.3382278481012655, "grad_norm": 0.26917773240435733, "learning_rate": 2.0766888607788906e-06, "loss": 0.1923, "step": 1068 }, { "epoch": 4.3422784810126585, "grad_norm": 0.2654629484094334, "learning_rate": 2.0515761205197337e-06, "loss": 0.1623, "step": 1069 }, { "epoch": 4.3463291139240505, "grad_norm": 0.25110658886072396, "learning_rate": 2.0266079343990453e-06, "loss": 0.1738, "step": 1070 }, { "epoch": 4.3503797468354435, "grad_norm": 0.2622088306552103, "learning_rate": 2.0017845035071494e-06, "loss": 0.1639, "step": 1071 }, { "epoch": 4.3544303797468356, "grad_norm": 0.2525407451716544, "learning_rate": 1.9771060277685537e-06, "loss": 0.1812, "step": 1072 }, { "epoch": 4.358481012658228, "grad_norm": 0.25631251994953247, "learning_rate": 1.95257270594031e-06, "loss": 0.201, "step": 1073 }, { "epoch": 4.362531645569621, "grad_norm": 0.2742337713672874, "learning_rate": 1.9281847356104188e-06, "loss": 0.1696, "step": 1074 }, { "epoch": 4.366582278481013, "grad_norm": 0.2566267476149487, "learning_rate": 1.9039423131962365e-06, "loss": 0.1658, "step": 1075 }, { "epoch": 4.370632911392405, "grad_norm": 0.2616137213774888, "learning_rate": 1.8798456339429027e-06, "loss": 0.1521, "step": 1076 }, { "epoch": 4.374683544303798, "grad_norm": 0.2547835417919082, "learning_rate": 1.8558948919217612e-06, "loss": 0.1982, "step": 1077 }, { "epoch": 4.37873417721519, "grad_norm": 0.2528155626080724, "learning_rate": 1.8320902800287954e-06, "loss": 0.1401, "step": 1078 }, { "epoch": 4.382784810126582, "grad_norm": 0.25386749107070117, "learning_rate": 1.8084319899830726e-06, "loss": 0.1706, "step": 1079 }, { "epoch": 4.386835443037975, "grad_norm": 0.26023567568812805, "learning_rate": 1.7849202123252097e-06, "loss": 0.1951, "step": 1080 }, { "epoch": 4.390886075949367, "grad_norm": 0.2636930729923864, "learning_rate": 1.7615551364158401e-06, "loss": 0.1668, "step": 1081 }, { "epoch": 4.39493670886076, "grad_norm": 0.25793073521056353, "learning_rate": 1.738336950434061e-06, "loss": 0.1532, "step": 1082 }, { "epoch": 4.398987341772152, "grad_norm": 0.25574169059607216, "learning_rate": 1.715265841375957e-06, "loss": 0.1544, "step": 1083 }, { "epoch": 4.403037974683544, "grad_norm": 0.25109692832310326, "learning_rate": 1.6923419950530684e-06, "loss": 0.1831, "step": 1084 }, { "epoch": 4.407088607594937, "grad_norm": 0.268541563066392, "learning_rate": 1.6695655960909008e-06, "loss": 0.1767, "step": 1085 }, { "epoch": 4.411139240506329, "grad_norm": 0.26624707010794607, "learning_rate": 1.646936827927441e-06, "loss": 0.1562, "step": 1086 }, { "epoch": 4.415189873417722, "grad_norm": 0.2566208206306818, "learning_rate": 1.6244558728116766e-06, "loss": 0.1786, "step": 1087 }, { "epoch": 4.419240506329114, "grad_norm": 0.25604227254993983, "learning_rate": 1.6021229118021265e-06, "loss": 0.1632, "step": 1088 }, { "epoch": 4.423291139240506, "grad_norm": 0.2510197874936753, "learning_rate": 1.5799381247653967e-06, "loss": 0.1669, "step": 1089 }, { "epoch": 4.427341772151899, "grad_norm": 0.2508705721776268, "learning_rate": 1.5579016903747013e-06, "loss": 0.1869, "step": 1090 }, { "epoch": 4.431392405063291, "grad_norm": 0.3080079061524469, "learning_rate": 1.5360137861084656e-06, "loss": 0.1996, "step": 1091 }, { "epoch": 4.435443037974683, "grad_norm": 0.2601983088097165, "learning_rate": 1.5142745882488475e-06, "loss": 0.1547, "step": 1092 }, { "epoch": 4.439493670886076, "grad_norm": 0.2501870278706163, "learning_rate": 1.4926842718803691e-06, "loss": 0.133, "step": 1093 }, { "epoch": 4.443544303797468, "grad_norm": 0.253995889535697, "learning_rate": 1.4712430108884657e-06, "loss": 0.1528, "step": 1094 }, { "epoch": 4.44759493670886, "grad_norm": 0.2439698782248293, "learning_rate": 1.4499509779581078e-06, "loss": 0.1416, "step": 1095 }, { "epoch": 4.451645569620253, "grad_norm": 0.2540014114650161, "learning_rate": 1.4288083445723988e-06, "loss": 0.1849, "step": 1096 }, { "epoch": 4.455696202531645, "grad_norm": 0.24861965458576113, "learning_rate": 1.4078152810112045e-06, "loss": 0.1571, "step": 1097 }, { "epoch": 4.459746835443038, "grad_norm": 0.25068555615202215, "learning_rate": 1.3869719563497697e-06, "loss": 0.1548, "step": 1098 }, { "epoch": 4.46379746835443, "grad_norm": 0.25960363501017597, "learning_rate": 1.3662785384573663e-06, "loss": 0.1744, "step": 1099 }, { "epoch": 4.467848101265822, "grad_norm": 0.2630205931097545, "learning_rate": 1.3457351939959383e-06, "loss": 0.1886, "step": 1100 }, { "epoch": 4.471898734177215, "grad_norm": 0.2508523893217522, "learning_rate": 1.3253420884187551e-06, "loss": 0.164, "step": 1101 }, { "epoch": 4.4759493670886075, "grad_norm": 0.2661742363160169, "learning_rate": 1.3050993859690953e-06, "loss": 0.1857, "step": 1102 }, { "epoch": 4.48, "grad_norm": 0.24874228108263366, "learning_rate": 1.2850072496788869e-06, "loss": 0.1519, "step": 1103 }, { "epoch": 4.4840506329113925, "grad_norm": 0.2608780637544093, "learning_rate": 1.2650658413674434e-06, "loss": 0.1566, "step": 1104 }, { "epoch": 4.488101265822785, "grad_norm": 0.2491062903042122, "learning_rate": 1.2452753216401226e-06, "loss": 0.1832, "step": 1105 }, { "epoch": 4.4921518987341775, "grad_norm": 0.25610789643850446, "learning_rate": 1.2256358498870503e-06, "loss": 0.1677, "step": 1106 }, { "epoch": 4.49620253164557, "grad_norm": 0.25898768185354926, "learning_rate": 1.2061475842818337e-06, "loss": 0.173, "step": 1107 }, { "epoch": 4.500253164556962, "grad_norm": 0.27601579015327254, "learning_rate": 1.1868106817802816e-06, "loss": 0.1762, "step": 1108 }, { "epoch": 4.504303797468355, "grad_norm": 0.2634303872261086, "learning_rate": 1.1676252981191482e-06, "loss": 0.1658, "step": 1109 }, { "epoch": 4.508354430379747, "grad_norm": 0.23979582150916046, "learning_rate": 1.1485915878148823e-06, "loss": 0.1541, "step": 1110 }, { "epoch": 4.512405063291139, "grad_norm": 0.258578814263585, "learning_rate": 1.1297097041623584e-06, "loss": 0.1641, "step": 1111 }, { "epoch": 4.516455696202532, "grad_norm": 0.25876536406360545, "learning_rate": 1.1109797992336847e-06, "loss": 0.1677, "step": 1112 }, { "epoch": 4.520506329113924, "grad_norm": 0.24267036687172688, "learning_rate": 1.092402023876933e-06, "loss": 0.1566, "step": 1113 }, { "epoch": 4.524556962025317, "grad_norm": 0.267613234854693, "learning_rate": 1.0739765277149527e-06, "loss": 0.1416, "step": 1114 }, { "epoch": 4.528607594936709, "grad_norm": 0.26399979726283057, "learning_rate": 1.0557034591441596e-06, "loss": 0.1721, "step": 1115 }, { "epoch": 4.532658227848101, "grad_norm": 0.2620625497079886, "learning_rate": 1.0375829653333324e-06, "loss": 0.1711, "step": 1116 }, { "epoch": 4.536708860759494, "grad_norm": 0.2653166593715694, "learning_rate": 1.0196151922224385e-06, "loss": 0.1653, "step": 1117 }, { "epoch": 4.540759493670886, "grad_norm": 0.24530173959555296, "learning_rate": 1.0018002845214526e-06, "loss": 0.1306, "step": 1118 }, { "epoch": 4.544810126582279, "grad_norm": 0.25935526272306314, "learning_rate": 9.841383857091947e-07, "loss": 0.1688, "step": 1119 }, { "epoch": 4.548860759493671, "grad_norm": 0.2600174549021805, "learning_rate": 9.666296380321616e-07, "loss": 0.1545, "step": 1120 }, { "epoch": 4.552911392405063, "grad_norm": 0.253761197454437, "learning_rate": 9.492741825034124e-07, "loss": 0.1975, "step": 1121 }, { "epoch": 4.556962025316456, "grad_norm": 0.25821685173726533, "learning_rate": 9.320721589013892e-07, "loss": 0.1788, "step": 1122 }, { "epoch": 4.561012658227848, "grad_norm": 0.25177646558628425, "learning_rate": 9.150237057688339e-07, "loss": 0.1714, "step": 1123 }, { "epoch": 4.56506329113924, "grad_norm": 0.2700947562911429, "learning_rate": 8.981289604116328e-07, "loss": 0.1673, "step": 1124 }, { "epoch": 4.569113924050633, "grad_norm": 0.25990249015023537, "learning_rate": 8.813880588977542e-07, "loss": 0.1738, "step": 1125 }, { "epoch": 4.573164556962025, "grad_norm": 0.25075211172164924, "learning_rate": 8.648011360561126e-07, "loss": 0.1605, "step": 1126 }, { "epoch": 4.577215189873417, "grad_norm": 0.2471025941023696, "learning_rate": 8.483683254755037e-07, "loss": 0.1643, "step": 1127 }, { "epoch": 4.58126582278481, "grad_norm": 0.26160374450048, "learning_rate": 8.320897595035227e-07, "loss": 0.1549, "step": 1128 }, { "epoch": 4.585316455696202, "grad_norm": 0.26246394704745163, "learning_rate": 8.159655692455093e-07, "loss": 0.1772, "step": 1129 }, { "epoch": 4.589367088607595, "grad_norm": 0.2623133420818694, "learning_rate": 7.999958845634648e-07, "loss": 0.1567, "step": 1130 }, { "epoch": 4.593417721518987, "grad_norm": 0.2502657433821083, "learning_rate": 7.841808340750478e-07, "loss": 0.1666, "step": 1131 }, { "epoch": 4.597468354430379, "grad_norm": 0.2541568181228115, "learning_rate": 7.685205451524869e-07, "loss": 0.1669, "step": 1132 }, { "epoch": 4.601518987341772, "grad_norm": 0.2575121477020851, "learning_rate": 7.530151439216027e-07, "loss": 0.1743, "step": 1133 }, { "epoch": 4.605569620253164, "grad_norm": 0.25148146367315843, "learning_rate": 7.376647552607675e-07, "loss": 0.1523, "step": 1134 }, { "epoch": 4.609620253164557, "grad_norm": 0.2584414015557822, "learning_rate": 7.224695027998963e-07, "loss": 0.142, "step": 1135 }, { "epoch": 4.613670886075949, "grad_norm": 0.2702341562909536, "learning_rate": 7.07429508919466e-07, "loss": 0.167, "step": 1136 }, { "epoch": 4.6177215189873415, "grad_norm": 0.2640621469859642, "learning_rate": 6.925448947495206e-07, "loss": 0.171, "step": 1137 }, { "epoch": 4.6217721518987345, "grad_norm": 0.2589064748475543, "learning_rate": 6.778157801686936e-07, "loss": 0.1324, "step": 1138 }, { "epoch": 4.6258227848101265, "grad_norm": 0.25103754105295173, "learning_rate": 6.632422838032515e-07, "loss": 0.1684, "step": 1139 }, { "epoch": 4.629873417721519, "grad_norm": 0.2514087313246364, "learning_rate": 6.488245230261281e-07, "loss": 0.1613, "step": 1140 }, { "epoch": 4.633924050632912, "grad_norm": 0.25659801021677775, "learning_rate": 6.345626139559868e-07, "loss": 0.1756, "step": 1141 }, { "epoch": 4.637974683544304, "grad_norm": 0.26243446442258056, "learning_rate": 6.204566714562866e-07, "loss": 0.1632, "step": 1142 }, { "epoch": 4.642025316455696, "grad_norm": 0.2507937723105254, "learning_rate": 6.06506809134344e-07, "loss": 0.1805, "step": 1143 }, { "epoch": 4.646075949367089, "grad_norm": 0.2599298403693028, "learning_rate": 5.927131393404373e-07, "loss": 0.1849, "step": 1144 }, { "epoch": 4.650126582278481, "grad_norm": 0.2636382171273464, "learning_rate": 5.790757731668817e-07, "loss": 0.1579, "step": 1145 }, { "epoch": 4.654177215189874, "grad_norm": 0.2661826823273988, "learning_rate": 5.655948204471507e-07, "loss": 0.1861, "step": 1146 }, { "epoch": 4.658227848101266, "grad_norm": 0.2601963664788276, "learning_rate": 5.522703897549875e-07, "loss": 0.1642, "step": 1147 }, { "epoch": 4.662278481012658, "grad_norm": 0.2504843076493723, "learning_rate": 5.391025884035239e-07, "loss": 0.1576, "step": 1148 }, { "epoch": 4.666329113924051, "grad_norm": 0.24585153200753565, "learning_rate": 5.260915224444207e-07, "loss": 0.1816, "step": 1149 }, { "epoch": 4.670379746835443, "grad_norm": 0.2516072545658252, "learning_rate": 5.132372966670129e-07, "loss": 0.1782, "step": 1150 }, { "epoch": 4.674430379746836, "grad_norm": 0.257589320962946, "learning_rate": 5.005400145974704e-07, "loss": 0.1571, "step": 1151 }, { "epoch": 4.678481012658228, "grad_norm": 0.25599235021292704, "learning_rate": 4.879997784979562e-07, "loss": 0.1488, "step": 1152 }, { "epoch": 4.68253164556962, "grad_norm": 0.24868370959715178, "learning_rate": 4.7561668936580984e-07, "loss": 0.1621, "step": 1153 }, { "epoch": 4.686582278481013, "grad_norm": 0.2551667874071031, "learning_rate": 4.6339084693272306e-07, "loss": 0.1606, "step": 1154 }, { "epoch": 4.690632911392405, "grad_norm": 0.2539878349217716, "learning_rate": 4.5132234966395847e-07, "loss": 0.1656, "step": 1155 }, { "epoch": 4.694683544303797, "grad_norm": 0.24417848270813322, "learning_rate": 4.3941129475752795e-07, "loss": 0.1423, "step": 1156 }, { "epoch": 4.69873417721519, "grad_norm": 0.2399970452456977, "learning_rate": 4.27657778143431e-07, "loss": 0.1562, "step": 1157 }, { "epoch": 4.702784810126582, "grad_norm": 0.2642946061887672, "learning_rate": 4.1606189448287757e-07, "loss": 0.1744, "step": 1158 }, { "epoch": 4.706835443037974, "grad_norm": 0.27155109894434387, "learning_rate": 4.046237371675177e-07, "loss": 0.1683, "step": 1159 }, { "epoch": 4.710886075949367, "grad_norm": 0.2568977851400568, "learning_rate": 3.9334339831869963e-07, "loss": 0.1777, "step": 1160 }, { "epoch": 4.714936708860759, "grad_norm": 0.25561801133029116, "learning_rate": 3.8222096878671955e-07, "loss": 0.1709, "step": 1161 }, { "epoch": 4.718987341772152, "grad_norm": 0.2724600607088594, "learning_rate": 3.7125653815009545e-07, "loss": 0.1847, "step": 1162 }, { "epoch": 4.723037974683544, "grad_norm": 0.25187744015318914, "learning_rate": 3.6045019471484974e-07, "loss": 0.1482, "step": 1163 }, { "epoch": 4.727088607594936, "grad_norm": 0.25947970419456917, "learning_rate": 3.498020255137813e-07, "loss": 0.1755, "step": 1164 }, { "epoch": 4.731139240506329, "grad_norm": 0.2550362854793139, "learning_rate": 3.393121163057811e-07, "loss": 0.1802, "step": 1165 }, { "epoch": 4.735189873417721, "grad_norm": 0.26409247629524324, "learning_rate": 3.289805515751399e-07, "loss": 0.1657, "step": 1166 }, { "epoch": 4.739240506329114, "grad_norm": 0.2490094785356258, "learning_rate": 3.188074145308573e-07, "loss": 0.1759, "step": 1167 }, { "epoch": 4.743291139240506, "grad_norm": 0.25391913487211987, "learning_rate": 3.087927871059804e-07, "loss": 0.153, "step": 1168 }, { "epoch": 4.7473417721518985, "grad_norm": 0.2440315818138099, "learning_rate": 2.989367499569418e-07, "loss": 0.1786, "step": 1169 }, { "epoch": 4.751392405063291, "grad_norm": 0.2626356007642752, "learning_rate": 2.8923938246290917e-07, "loss": 0.1759, "step": 1170 }, { "epoch": 4.7554430379746835, "grad_norm": 0.2402473411713559, "learning_rate": 2.7970076272514804e-07, "loss": 0.1473, "step": 1171 }, { "epoch": 4.759493670886076, "grad_norm": 0.26883657755112467, "learning_rate": 2.703209675663887e-07, "loss": 0.1821, "step": 1172 }, { "epoch": 4.7635443037974685, "grad_norm": 0.2613383276792892, "learning_rate": 2.6110007253021374e-07, "loss": 0.1692, "step": 1173 }, { "epoch": 4.767594936708861, "grad_norm": 0.2588169417047757, "learning_rate": 2.520381518804471e-07, "loss": 0.1837, "step": 1174 }, { "epoch": 4.7716455696202535, "grad_norm": 0.26441607869421224, "learning_rate": 2.4313527860054585e-07, "loss": 0.1853, "step": 1175 }, { "epoch": 4.775696202531646, "grad_norm": 0.25214188980178615, "learning_rate": 2.343915243930317e-07, "loss": 0.161, "step": 1176 }, { "epoch": 4.779746835443038, "grad_norm": 0.25818357794886476, "learning_rate": 2.2580695967889367e-07, "loss": 0.1834, "step": 1177 }, { "epoch": 4.783797468354431, "grad_norm": 0.24703768249935715, "learning_rate": 2.1738165359704189e-07, "loss": 0.1467, "step": 1178 }, { "epoch": 4.787848101265823, "grad_norm": 0.2601532506774956, "learning_rate": 2.0911567400373257e-07, "loss": 0.188, "step": 1179 }, { "epoch": 4.791898734177215, "grad_norm": 0.2595769136012586, "learning_rate": 2.0100908747202607e-07, "loss": 0.1675, "step": 1180 }, { "epoch": 4.795949367088608, "grad_norm": 0.2676539205653537, "learning_rate": 1.9306195929125638e-07, "loss": 0.1927, "step": 1181 }, { "epoch": 4.8, "grad_norm": 0.2601617206944027, "learning_rate": 1.8527435346650247e-07, "loss": 0.142, "step": 1182 }, { "epoch": 4.804050632911393, "grad_norm": 0.2547794009253227, "learning_rate": 1.7764633271807108e-07, "loss": 0.165, "step": 1183 }, { "epoch": 4.808101265822785, "grad_norm": 0.2588407175942675, "learning_rate": 1.7017795848099262e-07, "loss": 0.1601, "step": 1184 }, { "epoch": 4.812151898734177, "grad_norm": 0.2606817591083784, "learning_rate": 1.6286929090452596e-07, "loss": 0.1824, "step": 1185 }, { "epoch": 4.81620253164557, "grad_norm": 0.25539368610457835, "learning_rate": 1.557203888516745e-07, "loss": 0.1742, "step": 1186 }, { "epoch": 4.820253164556962, "grad_norm": 0.2520552258744651, "learning_rate": 1.487313098987131e-07, "loss": 0.1793, "step": 1187 }, { "epoch": 4.824303797468355, "grad_norm": 0.25448173902215065, "learning_rate": 1.4190211033472402e-07, "loss": 0.1707, "step": 1188 }, { "epoch": 4.828354430379747, "grad_norm": 0.25327592014603867, "learning_rate": 1.3523284516113955e-07, "loss": 0.137, "step": 1189 }, { "epoch": 4.832405063291139, "grad_norm": 0.27222013276667056, "learning_rate": 1.2872356809130682e-07, "loss": 0.1726, "step": 1190 }, { "epoch": 4.836455696202532, "grad_norm": 0.26232401069152594, "learning_rate": 1.2237433155004807e-07, "loss": 0.1814, "step": 1191 }, { "epoch": 4.840506329113924, "grad_norm": 0.24642424426586418, "learning_rate": 1.1618518667323886e-07, "loss": 0.1619, "step": 1192 }, { "epoch": 4.844556962025316, "grad_norm": 0.2572821309211488, "learning_rate": 1.1015618330740385e-07, "loss": 0.179, "step": 1193 }, { "epoch": 4.848607594936709, "grad_norm": 0.2573292431088768, "learning_rate": 1.042873700093061e-07, "loss": 0.1638, "step": 1194 }, { "epoch": 4.852658227848101, "grad_norm": 0.2574503966350399, "learning_rate": 9.857879404556291e-08, "loss": 0.1646, "step": 1195 }, { "epoch": 4.856708860759493, "grad_norm": 0.2599639260824226, "learning_rate": 9.303050139225722e-08, "loss": 0.1551, "step": 1196 }, { "epoch": 4.860759493670886, "grad_norm": 0.25318924184706004, "learning_rate": 8.76425367345779e-08, "loss": 0.1639, "step": 1197 }, { "epoch": 4.864810126582278, "grad_norm": 0.2628160093159906, "learning_rate": 8.241494346644897e-08, "loss": 0.1648, "step": 1198 }, { "epoch": 4.868860759493671, "grad_norm": 0.25696279131150074, "learning_rate": 7.734776369019204e-08, "loss": 0.1828, "step": 1199 }, { "epoch": 4.872911392405063, "grad_norm": 0.2553483829724684, "learning_rate": 7.244103821617332e-08, "loss": 0.16, "step": 1200 }, { "epoch": 4.876962025316455, "grad_norm": 0.25415792698544154, "learning_rate": 6.769480656248606e-08, "loss": 0.1628, "step": 1201 }, { "epoch": 4.881012658227848, "grad_norm": 0.25015412002513937, "learning_rate": 6.310910695462635e-08, "loss": 0.1533, "step": 1202 }, { "epoch": 4.88506329113924, "grad_norm": 0.2521629601472463, "learning_rate": 5.8683976325191185e-08, "loss": 0.1709, "step": 1203 }, { "epoch": 4.889113924050633, "grad_norm": 0.25484102955541615, "learning_rate": 5.4419450313571984e-08, "loss": 0.1531, "step": 1204 }, { "epoch": 4.8931645569620255, "grad_norm": 0.26232753855627183, "learning_rate": 5.031556326567488e-08, "loss": 0.1699, "step": 1205 }, { "epoch": 4.8972151898734175, "grad_norm": 0.2563545659413828, "learning_rate": 4.637234823364312e-08, "loss": 0.1838, "step": 1206 }, { "epoch": 4.9012658227848105, "grad_norm": 0.25532026322959733, "learning_rate": 4.258983697558838e-08, "loss": 0.1735, "step": 1207 }, { "epoch": 4.905316455696203, "grad_norm": 0.2554035657916979, "learning_rate": 3.896805995533548e-08, "loss": 0.1762, "step": 1208 }, { "epoch": 4.909367088607595, "grad_norm": 0.2583312881178822, "learning_rate": 3.550704634218028e-08, "loss": 0.1666, "step": 1209 }, { "epoch": 4.913417721518988, "grad_norm": 0.2665924486815181, "learning_rate": 3.2206824010647676e-08, "loss": 0.1753, "step": 1210 }, { "epoch": 4.91746835443038, "grad_norm": 0.26088499694192013, "learning_rate": 2.9067419540278476e-08, "loss": 0.147, "step": 1211 }, { "epoch": 4.921518987341772, "grad_norm": 0.25742019737962024, "learning_rate": 2.6088858215400638e-08, "loss": 0.1436, "step": 1212 }, { "epoch": 4.925569620253165, "grad_norm": 0.2733677465176962, "learning_rate": 2.3271164024940564e-08, "loss": 0.1626, "step": 1213 }, { "epoch": 4.929620253164557, "grad_norm": 0.2546645878449272, "learning_rate": 2.061435966221881e-08, "loss": 0.1754, "step": 1214 }, { "epoch": 4.93367088607595, "grad_norm": 0.2598551598859045, "learning_rate": 1.811846652477245e-08, "loss": 0.1703, "step": 1215 }, { "epoch": 4.937721518987342, "grad_norm": 0.26779809704883956, "learning_rate": 1.5783504714184106e-08, "loss": 0.1644, "step": 1216 }, { "epoch": 4.941772151898734, "grad_norm": 0.2634033444949338, "learning_rate": 1.360949303591097e-08, "loss": 0.1551, "step": 1217 }, { "epoch": 4.945822784810127, "grad_norm": 0.26168701177399856, "learning_rate": 1.1596448999144916e-08, "loss": 0.1682, "step": 1218 }, { "epoch": 4.949873417721519, "grad_norm": 0.25577774565137174, "learning_rate": 9.744388816668172e-09, "loss": 0.1638, "step": 1219 }, { "epoch": 4.953924050632912, "grad_norm": 0.2517824418291626, "learning_rate": 8.05332740472009e-09, "loss": 0.168, "step": 1220 }, { "epoch": 4.957974683544304, "grad_norm": 0.24533338407371952, "learning_rate": 6.523278382872811e-09, "loss": 0.1919, "step": 1221 }, { "epoch": 4.962025316455696, "grad_norm": 0.25818570107143723, "learning_rate": 5.15425407393133e-09, "loss": 0.1532, "step": 1222 }, { "epoch": 4.966075949367089, "grad_norm": 0.2634102362967196, "learning_rate": 3.94626550383137e-09, "loss": 0.1771, "step": 1223 }, { "epoch": 4.970126582278481, "grad_norm": 0.25980863796384684, "learning_rate": 2.899322401546112e-09, "loss": 0.172, "step": 1224 }, { "epoch": 4.974177215189873, "grad_norm": 0.2591065536654788, "learning_rate": 2.013433199010706e-09, "loss": 0.1667, "step": 1225 }, { "epoch": 4.978227848101266, "grad_norm": 0.26045966028072703, "learning_rate": 1.2886050310556563e-09, "loss": 0.1765, "step": 1226 }, { "epoch": 4.982278481012658, "grad_norm": 0.25380731013443597, "learning_rate": 7.248437353468695e-10, "loss": 0.1477, "step": 1227 }, { "epoch": 4.98632911392405, "grad_norm": 0.24947606542355721, "learning_rate": 3.221538523412449e-10, "loss": 0.1757, "step": 1228 }, { "epoch": 4.990379746835443, "grad_norm": 0.27194667792684396, "learning_rate": 8.053862524670663e-11, "loss": 0.1403, "step": 1229 }, { "epoch": 4.994430379746835, "grad_norm": 0.2519127326457727, "learning_rate": 0.0, "loss": 0.1908, "step": 1230 }, { "epoch": 4.994430379746835, "step": 1230, "total_flos": 2.277289179383595e+18, "train_loss": 0.42184288542929704, "train_runtime": 36544.1625, "train_samples_per_second": 4.323, "train_steps_per_second": 0.034 } ], "logging_steps": 1, "max_steps": 1230, "num_input_tokens_seen": 0, "num_train_epochs": 5, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 2.277289179383595e+18, "train_batch_size": 1, "trial_name": null, "trial_params": null }