{ "best_metric": null, "best_model_checkpoint": null, "epoch": 4.982278481012658, "eval_steps": 500, "global_step": 1230, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.004050632911392405, "grad_norm": 6.415474472185993, "learning_rate": 3.2520325203252037e-07, "loss": 0.8323, "step": 1 }, { "epoch": 0.00810126582278481, "grad_norm": 6.245642634957219, "learning_rate": 6.504065040650407e-07, "loss": 0.8013, "step": 2 }, { "epoch": 0.012151898734177215, "grad_norm": 6.6501385344683905, "learning_rate": 9.75609756097561e-07, "loss": 0.8431, "step": 3 }, { "epoch": 0.01620253164556962, "grad_norm": 6.23140859918603, "learning_rate": 1.3008130081300815e-06, "loss": 0.8169, "step": 4 }, { "epoch": 0.020253164556962026, "grad_norm": 5.788320814490232, "learning_rate": 1.6260162601626018e-06, "loss": 0.796, "step": 5 }, { "epoch": 0.02430379746835443, "grad_norm": 5.815900680268652, "learning_rate": 1.951219512195122e-06, "loss": 0.8137, "step": 6 }, { "epoch": 0.028354430379746835, "grad_norm": 7.809594154071888, "learning_rate": 2.2764227642276426e-06, "loss": 0.9346, "step": 7 }, { "epoch": 0.03240506329113924, "grad_norm": 3.998245022021074, "learning_rate": 2.601626016260163e-06, "loss": 0.7506, "step": 8 }, { "epoch": 0.03645569620253165, "grad_norm": 2.4014241435296526, "learning_rate": 2.926829268292683e-06, "loss": 0.7336, "step": 9 }, { "epoch": 0.04050632911392405, "grad_norm": 2.0963912830344444, "learning_rate": 3.2520325203252037e-06, "loss": 0.731, "step": 10 }, { "epoch": 0.044556962025316456, "grad_norm": 1.9367693719847334, "learning_rate": 3.577235772357724e-06, "loss": 0.7248, "step": 11 }, { "epoch": 0.04860759493670886, "grad_norm": 3.342034035205835, "learning_rate": 3.902439024390244e-06, "loss": 0.6954, "step": 12 }, { "epoch": 0.052658227848101265, "grad_norm": 3.985771424011531, "learning_rate": 4.227642276422765e-06, "loss": 0.7671, "step": 13 }, { "epoch": 0.05670886075949367, "grad_norm": 3.796034843663176, "learning_rate": 4.552845528455285e-06, "loss": 0.6901, "step": 14 }, { "epoch": 0.060759493670886074, "grad_norm": 3.8990301786355035, "learning_rate": 4.8780487804878055e-06, "loss": 0.7703, "step": 15 }, { "epoch": 0.06481012658227848, "grad_norm": 3.345532535186488, "learning_rate": 5.203252032520326e-06, "loss": 0.6767, "step": 16 }, { "epoch": 0.06886075949367089, "grad_norm": 3.076195674387924, "learning_rate": 5.528455284552846e-06, "loss": 0.6674, "step": 17 }, { "epoch": 0.0729113924050633, "grad_norm": 2.3743468146666484, "learning_rate": 5.853658536585366e-06, "loss": 0.6598, "step": 18 }, { "epoch": 0.0769620253164557, "grad_norm": 1.5955109364036133, "learning_rate": 6.178861788617887e-06, "loss": 0.6341, "step": 19 }, { "epoch": 0.0810126582278481, "grad_norm": 1.2513865622140108, "learning_rate": 6.504065040650407e-06, "loss": 0.6256, "step": 20 }, { "epoch": 0.08506329113924051, "grad_norm": 1.4112923507723334, "learning_rate": 6.829268292682928e-06, "loss": 0.6197, "step": 21 }, { "epoch": 0.08911392405063291, "grad_norm": 1.4361555865092683, "learning_rate": 7.154471544715448e-06, "loss": 0.6152, "step": 22 }, { "epoch": 0.09316455696202532, "grad_norm": 1.5826665269610145, "learning_rate": 7.4796747967479676e-06, "loss": 0.6208, "step": 23 }, { "epoch": 0.09721518987341772, "grad_norm": 0.9396578450505865, "learning_rate": 7.804878048780489e-06, "loss": 0.5925, "step": 24 }, { "epoch": 0.10126582278481013, "grad_norm": 0.9997404746658427, "learning_rate": 8.130081300813009e-06, "loss": 0.5866, "step": 25 }, { "epoch": 0.10531645569620253, "grad_norm": 0.8710230572842451, "learning_rate": 8.45528455284553e-06, "loss": 0.5835, "step": 26 }, { "epoch": 0.10936708860759493, "grad_norm": 0.7615555622884265, "learning_rate": 8.78048780487805e-06, "loss": 0.5762, "step": 27 }, { "epoch": 0.11341772151898734, "grad_norm": 0.7478192421939808, "learning_rate": 9.10569105691057e-06, "loss": 0.5768, "step": 28 }, { "epoch": 0.11746835443037974, "grad_norm": 0.8279108335657483, "learning_rate": 9.43089430894309e-06, "loss": 0.5771, "step": 29 }, { "epoch": 0.12151898734177215, "grad_norm": 0.9939770844851752, "learning_rate": 9.756097560975611e-06, "loss": 0.5812, "step": 30 }, { "epoch": 0.12556962025316457, "grad_norm": 0.5795663798615688, "learning_rate": 1.008130081300813e-05, "loss": 0.5558, "step": 31 }, { "epoch": 0.12962025316455697, "grad_norm": 0.6434712563117294, "learning_rate": 1.0406504065040652e-05, "loss": 0.5534, "step": 32 }, { "epoch": 0.13367088607594937, "grad_norm": 0.7611982965183436, "learning_rate": 1.0731707317073172e-05, "loss": 0.5435, "step": 33 }, { "epoch": 0.13772151898734178, "grad_norm": 0.5909571598895514, "learning_rate": 1.1056910569105692e-05, "loss": 0.5548, "step": 34 }, { "epoch": 0.14177215189873418, "grad_norm": 0.5615395493477513, "learning_rate": 1.1382113821138213e-05, "loss": 0.541, "step": 35 }, { "epoch": 0.1458227848101266, "grad_norm": 0.6463318579271167, "learning_rate": 1.1707317073170731e-05, "loss": 0.5177, "step": 36 }, { "epoch": 0.149873417721519, "grad_norm": 0.5698417711305934, "learning_rate": 1.2032520325203254e-05, "loss": 0.5226, "step": 37 }, { "epoch": 0.1539240506329114, "grad_norm": 0.6066148317298183, "learning_rate": 1.2357723577235774e-05, "loss": 0.5243, "step": 38 }, { "epoch": 0.1579746835443038, "grad_norm": 0.6836794028477702, "learning_rate": 1.2682926829268294e-05, "loss": 0.5312, "step": 39 }, { "epoch": 0.1620253164556962, "grad_norm": 0.6012993178451269, "learning_rate": 1.3008130081300815e-05, "loss": 0.5456, "step": 40 }, { "epoch": 0.1660759493670886, "grad_norm": 0.600635675909716, "learning_rate": 1.3333333333333333e-05, "loss": 0.5203, "step": 41 }, { "epoch": 0.17012658227848101, "grad_norm": 0.7396247369745135, "learning_rate": 1.3658536585365855e-05, "loss": 0.5122, "step": 42 }, { "epoch": 0.17417721518987342, "grad_norm": 0.5475562116563479, "learning_rate": 1.3983739837398376e-05, "loss": 0.5342, "step": 43 }, { "epoch": 0.17822784810126582, "grad_norm": 0.4512508336431414, "learning_rate": 1.4308943089430896e-05, "loss": 0.5056, "step": 44 }, { "epoch": 0.18227848101265823, "grad_norm": 0.6068187143976781, "learning_rate": 1.4634146341463415e-05, "loss": 0.5195, "step": 45 }, { "epoch": 0.18632911392405063, "grad_norm": 0.46612194740075846, "learning_rate": 1.4959349593495935e-05, "loss": 0.5276, "step": 46 }, { "epoch": 0.19037974683544304, "grad_norm": 0.5158793223796735, "learning_rate": 1.528455284552846e-05, "loss": 0.5128, "step": 47 }, { "epoch": 0.19443037974683544, "grad_norm": 0.757553136621339, "learning_rate": 1.5609756097560978e-05, "loss": 0.5151, "step": 48 }, { "epoch": 0.19848101265822785, "grad_norm": 0.4364096819109709, "learning_rate": 1.5934959349593496e-05, "loss": 0.5124, "step": 49 }, { "epoch": 0.20253164556962025, "grad_norm": 0.5837721786645184, "learning_rate": 1.6260162601626018e-05, "loss": 0.5149, "step": 50 }, { "epoch": 0.20658227848101265, "grad_norm": 0.3890433822304583, "learning_rate": 1.6585365853658537e-05, "loss": 0.5113, "step": 51 }, { "epoch": 0.21063291139240506, "grad_norm": 0.5724377174421127, "learning_rate": 1.691056910569106e-05, "loss": 0.5104, "step": 52 }, { "epoch": 0.21468354430379746, "grad_norm": 0.4238047477114162, "learning_rate": 1.7235772357723578e-05, "loss": 0.4943, "step": 53 }, { "epoch": 0.21873417721518987, "grad_norm": 0.5038658470560516, "learning_rate": 1.75609756097561e-05, "loss": 0.5166, "step": 54 }, { "epoch": 0.22278481012658227, "grad_norm": 0.44203627895740455, "learning_rate": 1.788617886178862e-05, "loss": 0.5027, "step": 55 }, { "epoch": 0.22683544303797468, "grad_norm": 0.44164280116182425, "learning_rate": 1.821138211382114e-05, "loss": 0.4887, "step": 56 }, { "epoch": 0.23088607594936708, "grad_norm": 0.4310522891052615, "learning_rate": 1.8536585365853663e-05, "loss": 0.4997, "step": 57 }, { "epoch": 0.23493670886075949, "grad_norm": 0.43285730296495945, "learning_rate": 1.886178861788618e-05, "loss": 0.5073, "step": 58 }, { "epoch": 0.2389873417721519, "grad_norm": 0.3712074190878411, "learning_rate": 1.91869918699187e-05, "loss": 0.4871, "step": 59 }, { "epoch": 0.2430379746835443, "grad_norm": 0.4975291168917053, "learning_rate": 1.9512195121951222e-05, "loss": 0.4882, "step": 60 }, { "epoch": 0.2470886075949367, "grad_norm": 0.37338453217735884, "learning_rate": 1.983739837398374e-05, "loss": 0.4904, "step": 61 }, { "epoch": 0.25113924050632913, "grad_norm": 0.72171415044184, "learning_rate": 2.016260162601626e-05, "loss": 0.4989, "step": 62 }, { "epoch": 0.25518987341772154, "grad_norm": 0.4723973732046484, "learning_rate": 2.048780487804878e-05, "loss": 0.4761, "step": 63 }, { "epoch": 0.25924050632911394, "grad_norm": 0.575033328841208, "learning_rate": 2.0813008130081303e-05, "loss": 0.4903, "step": 64 }, { "epoch": 0.26329113924050634, "grad_norm": 0.5678646014261429, "learning_rate": 2.1138211382113822e-05, "loss": 0.4918, "step": 65 }, { "epoch": 0.26734177215189875, "grad_norm": 0.5989163381814802, "learning_rate": 2.1463414634146344e-05, "loss": 0.4927, "step": 66 }, { "epoch": 0.27139240506329115, "grad_norm": 0.5891279338387094, "learning_rate": 2.1788617886178863e-05, "loss": 0.481, "step": 67 }, { "epoch": 0.27544303797468356, "grad_norm": 0.6407721805093948, "learning_rate": 2.2113821138211385e-05, "loss": 0.492, "step": 68 }, { "epoch": 0.27949367088607596, "grad_norm": 0.581393997037744, "learning_rate": 2.2439024390243907e-05, "loss": 0.4871, "step": 69 }, { "epoch": 0.28354430379746837, "grad_norm": 0.5933375742826985, "learning_rate": 2.2764227642276426e-05, "loss": 0.4895, "step": 70 }, { "epoch": 0.28759493670886077, "grad_norm": 0.6869078813243914, "learning_rate": 2.3089430894308948e-05, "loss": 0.492, "step": 71 }, { "epoch": 0.2916455696202532, "grad_norm": 0.5768783887867966, "learning_rate": 2.3414634146341463e-05, "loss": 0.4769, "step": 72 }, { "epoch": 0.2956962025316456, "grad_norm": 0.4739068642911488, "learning_rate": 2.3739837398373985e-05, "loss": 0.4611, "step": 73 }, { "epoch": 0.299746835443038, "grad_norm": 0.5097394930013299, "learning_rate": 2.4065040650406507e-05, "loss": 0.4731, "step": 74 }, { "epoch": 0.3037974683544304, "grad_norm": 0.5985594045698858, "learning_rate": 2.4390243902439026e-05, "loss": 0.4865, "step": 75 }, { "epoch": 0.3078481012658228, "grad_norm": 0.6345103517120135, "learning_rate": 2.4715447154471548e-05, "loss": 0.4864, "step": 76 }, { "epoch": 0.3118987341772152, "grad_norm": 0.5809947349609763, "learning_rate": 2.5040650406504066e-05, "loss": 0.4782, "step": 77 }, { "epoch": 0.3159493670886076, "grad_norm": 0.7353193702335682, "learning_rate": 2.536585365853659e-05, "loss": 0.4703, "step": 78 }, { "epoch": 0.32, "grad_norm": 0.858184226040697, "learning_rate": 2.569105691056911e-05, "loss": 0.482, "step": 79 }, { "epoch": 0.3240506329113924, "grad_norm": 0.8475258288543515, "learning_rate": 2.601626016260163e-05, "loss": 0.4679, "step": 80 }, { "epoch": 0.3281012658227848, "grad_norm": 0.7204106041165006, "learning_rate": 2.634146341463415e-05, "loss": 0.4823, "step": 81 }, { "epoch": 0.3321518987341772, "grad_norm": 0.8017684112149315, "learning_rate": 2.6666666666666667e-05, "loss": 0.4767, "step": 82 }, { "epoch": 0.3362025316455696, "grad_norm": 0.936978381940122, "learning_rate": 2.699186991869919e-05, "loss": 0.4713, "step": 83 }, { "epoch": 0.34025316455696203, "grad_norm": 0.9658075390120598, "learning_rate": 2.731707317073171e-05, "loss": 0.4717, "step": 84 }, { "epoch": 0.34430379746835443, "grad_norm": 0.6419245133954479, "learning_rate": 2.764227642276423e-05, "loss": 0.4624, "step": 85 }, { "epoch": 0.34835443037974684, "grad_norm": 0.7923015374697984, "learning_rate": 2.796747967479675e-05, "loss": 0.4646, "step": 86 }, { "epoch": 0.35240506329113924, "grad_norm": 0.9389622642137307, "learning_rate": 2.829268292682927e-05, "loss": 0.4808, "step": 87 }, { "epoch": 0.35645569620253165, "grad_norm": 1.1180350208373007, "learning_rate": 2.8617886178861792e-05, "loss": 0.4696, "step": 88 }, { "epoch": 0.36050632911392405, "grad_norm": 0.7588876694853695, "learning_rate": 2.8943089430894314e-05, "loss": 0.4816, "step": 89 }, { "epoch": 0.36455696202531646, "grad_norm": 0.727519934751614, "learning_rate": 2.926829268292683e-05, "loss": 0.4658, "step": 90 }, { "epoch": 0.36860759493670886, "grad_norm": 0.8089671656755559, "learning_rate": 2.959349593495935e-05, "loss": 0.4597, "step": 91 }, { "epoch": 0.37265822784810126, "grad_norm": 0.8096694310937108, "learning_rate": 2.991869918699187e-05, "loss": 0.4796, "step": 92 }, { "epoch": 0.37670886075949367, "grad_norm": 0.6478453963740857, "learning_rate": 3.0243902439024392e-05, "loss": 0.4637, "step": 93 }, { "epoch": 0.3807594936708861, "grad_norm": 0.8187918785458496, "learning_rate": 3.056910569105692e-05, "loss": 0.4594, "step": 94 }, { "epoch": 0.3848101265822785, "grad_norm": 0.811878893037055, "learning_rate": 3.089430894308943e-05, "loss": 0.4666, "step": 95 }, { "epoch": 0.3888607594936709, "grad_norm": 0.6157896390078532, "learning_rate": 3.1219512195121955e-05, "loss": 0.4677, "step": 96 }, { "epoch": 0.3929113924050633, "grad_norm": 0.806547424027422, "learning_rate": 3.154471544715447e-05, "loss": 0.4778, "step": 97 }, { "epoch": 0.3969620253164557, "grad_norm": 0.7738447698092992, "learning_rate": 3.186991869918699e-05, "loss": 0.4814, "step": 98 }, { "epoch": 0.4010126582278481, "grad_norm": 1.0154429108509122, "learning_rate": 3.2195121951219514e-05, "loss": 0.4656, "step": 99 }, { "epoch": 0.4050632911392405, "grad_norm": 1.1557861202995499, "learning_rate": 3.2520325203252037e-05, "loss": 0.4557, "step": 100 }, { "epoch": 0.4091139240506329, "grad_norm": 0.8273189243627883, "learning_rate": 3.284552845528456e-05, "loss": 0.4564, "step": 101 }, { "epoch": 0.4131645569620253, "grad_norm": 0.8070437752557867, "learning_rate": 3.3170731707317074e-05, "loss": 0.4694, "step": 102 }, { "epoch": 0.4172151898734177, "grad_norm": 0.9294662209301109, "learning_rate": 3.3495934959349596e-05, "loss": 0.4451, "step": 103 }, { "epoch": 0.4212658227848101, "grad_norm": 1.1970276740800574, "learning_rate": 3.382113821138212e-05, "loss": 0.4722, "step": 104 }, { "epoch": 0.4253164556962025, "grad_norm": 0.7150475198298323, "learning_rate": 3.414634146341463e-05, "loss": 0.4669, "step": 105 }, { "epoch": 0.4293670886075949, "grad_norm": 1.0997218981939283, "learning_rate": 3.4471544715447155e-05, "loss": 0.4677, "step": 106 }, { "epoch": 0.43341772151898733, "grad_norm": 1.2363909564190316, "learning_rate": 3.479674796747968e-05, "loss": 0.4575, "step": 107 }, { "epoch": 0.43746835443037974, "grad_norm": 0.6684217335953629, "learning_rate": 3.51219512195122e-05, "loss": 0.4518, "step": 108 }, { "epoch": 0.44151898734177214, "grad_norm": 1.3121015187213252, "learning_rate": 3.544715447154472e-05, "loss": 0.4629, "step": 109 }, { "epoch": 0.44556962025316454, "grad_norm": 0.7671414188742344, "learning_rate": 3.577235772357724e-05, "loss": 0.4806, "step": 110 }, { "epoch": 0.44962025316455695, "grad_norm": 1.0839321417977639, "learning_rate": 3.609756097560976e-05, "loss": 0.465, "step": 111 }, { "epoch": 0.45367088607594935, "grad_norm": 0.9612479364328397, "learning_rate": 3.642276422764228e-05, "loss": 0.462, "step": 112 }, { "epoch": 0.45772151898734176, "grad_norm": 0.7182337156271724, "learning_rate": 3.67479674796748e-05, "loss": 0.4672, "step": 113 }, { "epoch": 0.46177215189873416, "grad_norm": 0.9148260872894733, "learning_rate": 3.7073170731707325e-05, "loss": 0.4791, "step": 114 }, { "epoch": 0.46582278481012657, "grad_norm": 1.0077137187148508, "learning_rate": 3.739837398373984e-05, "loss": 0.4575, "step": 115 }, { "epoch": 0.46987341772151897, "grad_norm": 1.2799317079219517, "learning_rate": 3.772357723577236e-05, "loss": 0.4771, "step": 116 }, { "epoch": 0.4739240506329114, "grad_norm": 0.9468261309047026, "learning_rate": 3.804878048780488e-05, "loss": 0.4585, "step": 117 }, { "epoch": 0.4779746835443038, "grad_norm": 0.7656721803981215, "learning_rate": 3.83739837398374e-05, "loss": 0.4539, "step": 118 }, { "epoch": 0.4820253164556962, "grad_norm": 0.7890683799391977, "learning_rate": 3.869918699186992e-05, "loss": 0.4544, "step": 119 }, { "epoch": 0.4860759493670886, "grad_norm": 0.9134085499348304, "learning_rate": 3.9024390243902444e-05, "loss": 0.4569, "step": 120 }, { "epoch": 0.490126582278481, "grad_norm": 0.7125797467273723, "learning_rate": 3.9349593495934966e-05, "loss": 0.4734, "step": 121 }, { "epoch": 0.4941772151898734, "grad_norm": 0.6300016475917551, "learning_rate": 3.967479674796748e-05, "loss": 0.4535, "step": 122 }, { "epoch": 0.4982278481012658, "grad_norm": 0.6345208048463399, "learning_rate": 4e-05, "loss": 0.4574, "step": 123 }, { "epoch": 0.5022784810126583, "grad_norm": 0.6609932066175954, "learning_rate": 3.999991946137476e-05, "loss": 0.448, "step": 124 }, { "epoch": 0.5063291139240507, "grad_norm": 0.7275808650113893, "learning_rate": 3.999967784614766e-05, "loss": 0.4706, "step": 125 }, { "epoch": 0.5103797468354431, "grad_norm": 0.661551891998038, "learning_rate": 3.9999275156264656e-05, "loss": 0.4649, "step": 126 }, { "epoch": 0.5144303797468355, "grad_norm": 0.6122172961155627, "learning_rate": 3.999871139496895e-05, "loss": 0.4533, "step": 127 }, { "epoch": 0.5184810126582279, "grad_norm": 0.46209775848932766, "learning_rate": 3.9997986566800995e-05, "loss": 0.4519, "step": 128 }, { "epoch": 0.5225316455696203, "grad_norm": 0.5769037227121283, "learning_rate": 3.999710067759846e-05, "loss": 0.4566, "step": 129 }, { "epoch": 0.5265822784810127, "grad_norm": 0.5379146814067768, "learning_rate": 3.999605373449617e-05, "loss": 0.4472, "step": 130 }, { "epoch": 0.5306329113924051, "grad_norm": 0.530391052325217, "learning_rate": 3.9994845745926075e-05, "loss": 0.4352, "step": 131 }, { "epoch": 0.5346835443037975, "grad_norm": 0.7106750464700411, "learning_rate": 3.999347672161713e-05, "loss": 0.4561, "step": 132 }, { "epoch": 0.5387341772151899, "grad_norm": 0.8178677535448258, "learning_rate": 3.999194667259528e-05, "loss": 0.4606, "step": 133 }, { "epoch": 0.5427848101265823, "grad_norm": 0.8217556398932492, "learning_rate": 3.999025561118334e-05, "loss": 0.4458, "step": 134 }, { "epoch": 0.5468354430379747, "grad_norm": 0.8607520768788017, "learning_rate": 3.998840355100086e-05, "loss": 0.4554, "step": 135 }, { "epoch": 0.5508860759493671, "grad_norm": 0.8639731320401046, "learning_rate": 3.998639050696409e-05, "loss": 0.4316, "step": 136 }, { "epoch": 0.5549367088607595, "grad_norm": 0.7837212633000709, "learning_rate": 3.998421649528582e-05, "loss": 0.4499, "step": 137 }, { "epoch": 0.5589873417721519, "grad_norm": 0.8455238857062118, "learning_rate": 3.9981881533475234e-05, "loss": 0.4568, "step": 138 }, { "epoch": 0.5630379746835443, "grad_norm": 0.8404351704554364, "learning_rate": 3.997938564033779e-05, "loss": 0.4647, "step": 139 }, { "epoch": 0.5670886075949367, "grad_norm": 0.7656910049617103, "learning_rate": 3.9976728835975064e-05, "loss": 0.4472, "step": 140 }, { "epoch": 0.5711392405063291, "grad_norm": 0.8022747533086755, "learning_rate": 3.9973911141784605e-05, "loss": 0.4466, "step": 141 }, { "epoch": 0.5751898734177215, "grad_norm": 0.8590326715355762, "learning_rate": 3.997093258045973e-05, "loss": 0.4561, "step": 142 }, { "epoch": 0.579240506329114, "grad_norm": 0.7915591849752818, "learning_rate": 3.996779317598936e-05, "loss": 0.4494, "step": 143 }, { "epoch": 0.5832911392405064, "grad_norm": 0.6683691186031455, "learning_rate": 3.996449295365782e-05, "loss": 0.4458, "step": 144 }, { "epoch": 0.5873417721518988, "grad_norm": 0.9491778929270845, "learning_rate": 3.996103194004467e-05, "loss": 0.4564, "step": 145 }, { "epoch": 0.5913924050632912, "grad_norm": 0.9942540539683647, "learning_rate": 3.995741016302441e-05, "loss": 0.4547, "step": 146 }, { "epoch": 0.5954430379746836, "grad_norm": 0.8824943809117768, "learning_rate": 3.9953627651766364e-05, "loss": 0.449, "step": 147 }, { "epoch": 0.599493670886076, "grad_norm": 0.9524612133052188, "learning_rate": 3.9949684436734325e-05, "loss": 0.4473, "step": 148 }, { "epoch": 0.6035443037974684, "grad_norm": 0.7873578378269311, "learning_rate": 3.994558054968643e-05, "loss": 0.456, "step": 149 }, { "epoch": 0.6075949367088608, "grad_norm": 0.8662626150655077, "learning_rate": 3.994131602367481e-05, "loss": 0.4489, "step": 150 }, { "epoch": 0.6116455696202532, "grad_norm": 0.8016438395639583, "learning_rate": 3.9936890893045376e-05, "loss": 0.4494, "step": 151 }, { "epoch": 0.6156962025316456, "grad_norm": 0.562976549930401, "learning_rate": 3.993230519343752e-05, "loss": 0.4412, "step": 152 }, { "epoch": 0.619746835443038, "grad_norm": 0.676437775505894, "learning_rate": 3.992755896178383e-05, "loss": 0.4404, "step": 153 }, { "epoch": 0.6237974683544304, "grad_norm": 0.6336115852886224, "learning_rate": 3.992265223630981e-05, "loss": 0.4499, "step": 154 }, { "epoch": 0.6278481012658228, "grad_norm": 0.5676447720447023, "learning_rate": 3.991758505653355e-05, "loss": 0.4389, "step": 155 }, { "epoch": 0.6318987341772152, "grad_norm": 0.5590225438456706, "learning_rate": 3.991235746326543e-05, "loss": 0.4255, "step": 156 }, { "epoch": 0.6359493670886076, "grad_norm": 0.5143432099552642, "learning_rate": 3.9906969498607745e-05, "loss": 0.4432, "step": 157 }, { "epoch": 0.64, "grad_norm": 0.5725567492823503, "learning_rate": 3.990142120595444e-05, "loss": 0.44, "step": 158 }, { "epoch": 0.6440506329113924, "grad_norm": 0.6179859877819363, "learning_rate": 3.98957126299907e-05, "loss": 0.4371, "step": 159 }, { "epoch": 0.6481012658227848, "grad_norm": 0.5121413892529889, "learning_rate": 3.9889843816692596e-05, "loss": 0.4389, "step": 160 }, { "epoch": 0.6521518987341772, "grad_norm": 0.6947846547539233, "learning_rate": 3.9883814813326766e-05, "loss": 0.4519, "step": 161 }, { "epoch": 0.6562025316455696, "grad_norm": 0.5134020151352279, "learning_rate": 3.9877625668449956e-05, "loss": 0.4453, "step": 162 }, { "epoch": 0.660253164556962, "grad_norm": 0.5601034780746725, "learning_rate": 3.98712764319087e-05, "loss": 0.4347, "step": 163 }, { "epoch": 0.6643037974683544, "grad_norm": 0.5960602611647147, "learning_rate": 3.9864767154838864e-05, "loss": 0.458, "step": 164 }, { "epoch": 0.6683544303797468, "grad_norm": 0.4813089607448457, "learning_rate": 3.9858097889665277e-05, "loss": 0.4464, "step": 165 }, { "epoch": 0.6724050632911392, "grad_norm": 0.4884486245925764, "learning_rate": 3.985126869010129e-05, "loss": 0.4341, "step": 166 }, { "epoch": 0.6764556962025317, "grad_norm": 0.40821553951286427, "learning_rate": 3.984427961114833e-05, "loss": 0.4407, "step": 167 }, { "epoch": 0.6805063291139241, "grad_norm": 0.5775182534373128, "learning_rate": 3.9837130709095475e-05, "loss": 0.4355, "step": 168 }, { "epoch": 0.6845569620253165, "grad_norm": 0.6485952830123898, "learning_rate": 3.982982204151901e-05, "loss": 0.4378, "step": 169 }, { "epoch": 0.6886075949367089, "grad_norm": 0.7666748257233252, "learning_rate": 3.982235366728193e-05, "loss": 0.4499, "step": 170 }, { "epoch": 0.6926582278481013, "grad_norm": 0.5540585545557156, "learning_rate": 3.9814725646533505e-05, "loss": 0.4435, "step": 171 }, { "epoch": 0.6967088607594937, "grad_norm": 0.6181619216745663, "learning_rate": 3.9806938040708746e-05, "loss": 0.46, "step": 172 }, { "epoch": 0.7007594936708861, "grad_norm": 0.7631205902320295, "learning_rate": 3.9798990912527976e-05, "loss": 0.4341, "step": 173 }, { "epoch": 0.7048101265822785, "grad_norm": 0.4770057132778238, "learning_rate": 3.979088432599627e-05, "loss": 0.4237, "step": 174 }, { "epoch": 0.7088607594936709, "grad_norm": 0.54721096927718, "learning_rate": 3.9782618346402964e-05, "loss": 0.4356, "step": 175 }, { "epoch": 0.7129113924050633, "grad_norm": 0.49850679877116766, "learning_rate": 3.977419304032111e-05, "loss": 0.4455, "step": 176 }, { "epoch": 0.7169620253164557, "grad_norm": 0.7628538831353551, "learning_rate": 3.976560847560697e-05, "loss": 0.4323, "step": 177 }, { "epoch": 0.7210126582278481, "grad_norm": 0.7812969073926359, "learning_rate": 3.9756864721399456e-05, "loss": 0.4412, "step": 178 }, { "epoch": 0.7250632911392405, "grad_norm": 0.5328076508351888, "learning_rate": 3.974796184811956e-05, "loss": 0.4333, "step": 179 }, { "epoch": 0.7291139240506329, "grad_norm": 0.596506257744311, "learning_rate": 3.973889992746979e-05, "loss": 0.4379, "step": 180 }, { "epoch": 0.7331645569620253, "grad_norm": 0.6815216319995215, "learning_rate": 3.972967903243361e-05, "loss": 0.4333, "step": 181 }, { "epoch": 0.7372151898734177, "grad_norm": 0.5345316674186186, "learning_rate": 3.972029923727486e-05, "loss": 0.4514, "step": 182 }, { "epoch": 0.7412658227848101, "grad_norm": 0.5355537482937675, "learning_rate": 3.971076061753709e-05, "loss": 0.4411, "step": 183 }, { "epoch": 0.7453164556962025, "grad_norm": 0.6310758902715811, "learning_rate": 3.9701063250043066e-05, "loss": 0.4268, "step": 184 }, { "epoch": 0.7493670886075949, "grad_norm": 0.39948891403176234, "learning_rate": 3.969120721289402e-05, "loss": 0.428, "step": 185 }, { "epoch": 0.7534177215189873, "grad_norm": 0.4697653220608853, "learning_rate": 3.9681192585469146e-05, "loss": 0.4304, "step": 186 }, { "epoch": 0.7574683544303797, "grad_norm": 0.4995874017449129, "learning_rate": 3.9671019448424865e-05, "loss": 0.4242, "step": 187 }, { "epoch": 0.7615189873417721, "grad_norm": 0.6371170226201507, "learning_rate": 3.966068788369422e-05, "loss": 0.4464, "step": 188 }, { "epoch": 0.7655696202531646, "grad_norm": 0.40892788503293787, "learning_rate": 3.965019797448622e-05, "loss": 0.4131, "step": 189 }, { "epoch": 0.769620253164557, "grad_norm": 0.5966681360784408, "learning_rate": 3.963954980528515e-05, "loss": 0.438, "step": 190 }, { "epoch": 0.7736708860759494, "grad_norm": 0.4500753525226133, "learning_rate": 3.9628743461849905e-05, "loss": 0.4439, "step": 191 }, { "epoch": 0.7777215189873418, "grad_norm": 0.43245159944438977, "learning_rate": 3.961777903121329e-05, "loss": 0.4362, "step": 192 }, { "epoch": 0.7817721518987342, "grad_norm": 0.45229927495481886, "learning_rate": 3.960665660168131e-05, "loss": 0.4252, "step": 193 }, { "epoch": 0.7858227848101266, "grad_norm": 0.38267878910808245, "learning_rate": 3.9595376262832485e-05, "loss": 0.4271, "step": 194 }, { "epoch": 0.789873417721519, "grad_norm": 0.4276011431383974, "learning_rate": 3.9583938105517127e-05, "loss": 0.4273, "step": 195 }, { "epoch": 0.7939240506329114, "grad_norm": 0.37152599388692803, "learning_rate": 3.957234222185657e-05, "loss": 0.425, "step": 196 }, { "epoch": 0.7979746835443038, "grad_norm": 0.3826135094881225, "learning_rate": 3.9560588705242474e-05, "loss": 0.4193, "step": 197 }, { "epoch": 0.8020253164556962, "grad_norm": 0.3882611014971821, "learning_rate": 3.954867765033605e-05, "loss": 0.4263, "step": 198 }, { "epoch": 0.8060759493670886, "grad_norm": 0.43612555063048986, "learning_rate": 3.953660915306728e-05, "loss": 0.4338, "step": 199 }, { "epoch": 0.810126582278481, "grad_norm": 0.3902531959133332, "learning_rate": 3.952438331063419e-05, "loss": 0.4313, "step": 200 }, { "epoch": 0.8141772151898734, "grad_norm": 0.3626151041766697, "learning_rate": 3.951200022150205e-05, "loss": 0.4317, "step": 201 }, { "epoch": 0.8182278481012658, "grad_norm": 0.40128037728011356, "learning_rate": 3.949945998540253e-05, "loss": 0.4259, "step": 202 }, { "epoch": 0.8222784810126582, "grad_norm": 0.40248587054502344, "learning_rate": 3.9486762703332993e-05, "loss": 0.4297, "step": 203 }, { "epoch": 0.8263291139240506, "grad_norm": 0.41757614755958244, "learning_rate": 3.947390847755559e-05, "loss": 0.4375, "step": 204 }, { "epoch": 0.830379746835443, "grad_norm": 0.4470814534443328, "learning_rate": 3.946089741159648e-05, "loss": 0.4154, "step": 205 }, { "epoch": 0.8344303797468354, "grad_norm": 0.44966688844515695, "learning_rate": 3.944772961024501e-05, "loss": 0.4259, "step": 206 }, { "epoch": 0.8384810126582278, "grad_norm": 0.36405505077568406, "learning_rate": 3.943440517955285e-05, "loss": 0.4335, "step": 207 }, { "epoch": 0.8425316455696202, "grad_norm": 0.48676984549359714, "learning_rate": 3.9420924226833126e-05, "loss": 0.4243, "step": 208 }, { "epoch": 0.8465822784810126, "grad_norm": 0.45346644573063855, "learning_rate": 3.9407286860659566e-05, "loss": 0.4204, "step": 209 }, { "epoch": 0.850632911392405, "grad_norm": 0.3754987790183888, "learning_rate": 3.9393493190865657e-05, "loss": 0.4343, "step": 210 }, { "epoch": 0.8546835443037974, "grad_norm": 0.402207054599873, "learning_rate": 3.937954332854371e-05, "loss": 0.4389, "step": 211 }, { "epoch": 0.8587341772151899, "grad_norm": 0.4532941817031056, "learning_rate": 3.9365437386044016e-05, "loss": 0.4347, "step": 212 }, { "epoch": 0.8627848101265823, "grad_norm": 0.4881550231627137, "learning_rate": 3.935117547697387e-05, "loss": 0.4338, "step": 213 }, { "epoch": 0.8668354430379747, "grad_norm": 0.40886333007016046, "learning_rate": 3.933675771619675e-05, "loss": 0.4394, "step": 214 }, { "epoch": 0.8708860759493671, "grad_norm": 0.4855307297099102, "learning_rate": 3.932218421983131e-05, "loss": 0.4328, "step": 215 }, { "epoch": 0.8749367088607595, "grad_norm": 0.5651612844109208, "learning_rate": 3.9307455105250484e-05, "loss": 0.4307, "step": 216 }, { "epoch": 0.8789873417721519, "grad_norm": 0.5746022405613146, "learning_rate": 3.929257049108054e-05, "loss": 0.4307, "step": 217 }, { "epoch": 0.8830379746835443, "grad_norm": 0.4703725230972783, "learning_rate": 3.927753049720011e-05, "loss": 0.4202, "step": 218 }, { "epoch": 0.8870886075949367, "grad_norm": 0.3749490537066664, "learning_rate": 3.9262335244739234e-05, "loss": 0.422, "step": 219 }, { "epoch": 0.8911392405063291, "grad_norm": 0.5759957007906142, "learning_rate": 3.92469848560784e-05, "loss": 0.4259, "step": 220 }, { "epoch": 0.8951898734177215, "grad_norm": 0.5859580346771722, "learning_rate": 3.923147945484751e-05, "loss": 0.423, "step": 221 }, { "epoch": 0.8992405063291139, "grad_norm": 0.4646174825270583, "learning_rate": 3.9215819165924956e-05, "loss": 0.4223, "step": 222 }, { "epoch": 0.9032911392405063, "grad_norm": 0.42729493640642496, "learning_rate": 3.920000411543654e-05, "loss": 0.4288, "step": 223 }, { "epoch": 0.9073417721518987, "grad_norm": 0.464896001887884, "learning_rate": 3.9184034430754495e-05, "loss": 0.4244, "step": 224 }, { "epoch": 0.9113924050632911, "grad_norm": 0.4747690643088608, "learning_rate": 3.916791024049648e-05, "loss": 0.4392, "step": 225 }, { "epoch": 0.9154430379746835, "grad_norm": 0.44159408516302284, "learning_rate": 3.91516316745245e-05, "loss": 0.4144, "step": 226 }, { "epoch": 0.9194936708860759, "grad_norm": 0.3730754856674497, "learning_rate": 3.913519886394389e-05, "loss": 0.4013, "step": 227 }, { "epoch": 0.9235443037974683, "grad_norm": 0.405486425574033, "learning_rate": 3.911861194110225e-05, "loss": 0.4297, "step": 228 }, { "epoch": 0.9275949367088607, "grad_norm": 0.4223225333456756, "learning_rate": 3.910187103958837e-05, "loss": 0.4297, "step": 229 }, { "epoch": 0.9316455696202531, "grad_norm": 0.5264485351002911, "learning_rate": 3.908497629423117e-05, "loss": 0.4267, "step": 230 }, { "epoch": 0.9356962025316455, "grad_norm": 0.4605064095768363, "learning_rate": 3.9067927841098614e-05, "loss": 0.4217, "step": 231 }, { "epoch": 0.9397468354430379, "grad_norm": 0.5123400395153517, "learning_rate": 3.9050725817496594e-05, "loss": 0.4256, "step": 232 }, { "epoch": 0.9437974683544303, "grad_norm": 0.5312434499214616, "learning_rate": 3.9033370361967844e-05, "loss": 0.4253, "step": 233 }, { "epoch": 0.9478481012658228, "grad_norm": 0.4933664755605908, "learning_rate": 3.901586161429081e-05, "loss": 0.4148, "step": 234 }, { "epoch": 0.9518987341772152, "grad_norm": 0.5980949807431477, "learning_rate": 3.8998199715478545e-05, "loss": 0.4139, "step": 235 }, { "epoch": 0.9559493670886076, "grad_norm": 0.33143280656051644, "learning_rate": 3.8980384807777564e-05, "loss": 0.4257, "step": 236 }, { "epoch": 0.96, "grad_norm": 0.6067299965428729, "learning_rate": 3.896241703466667e-05, "loss": 0.4375, "step": 237 }, { "epoch": 0.9640506329113924, "grad_norm": 0.7586074406121046, "learning_rate": 3.894429654085585e-05, "loss": 0.4221, "step": 238 }, { "epoch": 0.9681012658227848, "grad_norm": 0.6660584176698722, "learning_rate": 3.892602347228505e-05, "loss": 0.415, "step": 239 }, { "epoch": 0.9721518987341772, "grad_norm": 0.6290247453709245, "learning_rate": 3.890759797612307e-05, "loss": 0.42, "step": 240 }, { "epoch": 0.9762025316455696, "grad_norm": 0.5233147878792372, "learning_rate": 3.888902020076632e-05, "loss": 0.4187, "step": 241 }, { "epoch": 0.980253164556962, "grad_norm": 0.5469068565573236, "learning_rate": 3.887029029583764e-05, "loss": 0.4199, "step": 242 }, { "epoch": 0.9843037974683544, "grad_norm": 0.6173325017844778, "learning_rate": 3.8851408412185125e-05, "loss": 0.416, "step": 243 }, { "epoch": 0.9883544303797468, "grad_norm": 0.48978409438824244, "learning_rate": 3.8832374701880855e-05, "loss": 0.4235, "step": 244 }, { "epoch": 0.9924050632911392, "grad_norm": 0.4875522712652264, "learning_rate": 3.881318931821972e-05, "loss": 0.4362, "step": 245 }, { "epoch": 0.9964556962025316, "grad_norm": 0.44599542796660135, "learning_rate": 3.879385241571817e-05, "loss": 0.4178, "step": 246 }, { "epoch": 1.000506329113924, "grad_norm": 0.4491377522648436, "learning_rate": 3.8774364150112955e-05, "loss": 0.4174, "step": 247 }, { "epoch": 1.0045569620253165, "grad_norm": 0.5355296012886486, "learning_rate": 3.8754724678359884e-05, "loss": 0.3884, "step": 248 }, { "epoch": 1.0086075949367088, "grad_norm": 0.4767653014466542, "learning_rate": 3.873493415863256e-05, "loss": 0.3909, "step": 249 }, { "epoch": 1.0126582278481013, "grad_norm": 0.7419751881773777, "learning_rate": 3.871499275032111e-05, "loss": 0.3936, "step": 250 }, { "epoch": 1.0167088607594936, "grad_norm": 0.9139803636724941, "learning_rate": 3.869490061403091e-05, "loss": 0.3997, "step": 251 }, { "epoch": 1.0207594936708861, "grad_norm": 0.6744743151991983, "learning_rate": 3.867465791158124e-05, "loss": 0.3768, "step": 252 }, { "epoch": 1.0248101265822784, "grad_norm": 0.33131906202262507, "learning_rate": 3.865426480600407e-05, "loss": 0.3815, "step": 253 }, { "epoch": 1.028860759493671, "grad_norm": 0.5981280922489554, "learning_rate": 3.863372146154264e-05, "loss": 0.3988, "step": 254 }, { "epoch": 1.0329113924050632, "grad_norm": 0.8519086907492914, "learning_rate": 3.861302804365024e-05, "loss": 0.3944, "step": 255 }, { "epoch": 1.0369620253164558, "grad_norm": 0.6833515861558302, "learning_rate": 3.85921847189888e-05, "loss": 0.3856, "step": 256 }, { "epoch": 1.041012658227848, "grad_norm": 0.39770412708545544, "learning_rate": 3.85711916554276e-05, "loss": 0.3798, "step": 257 }, { "epoch": 1.0450632911392406, "grad_norm": 0.7461357927856809, "learning_rate": 3.85500490220419e-05, "loss": 0.4004, "step": 258 }, { "epoch": 1.0491139240506329, "grad_norm": 0.7452396869592713, "learning_rate": 3.852875698911154e-05, "loss": 0.3944, "step": 259 }, { "epoch": 1.0531645569620254, "grad_norm": 0.4030427052887022, "learning_rate": 3.850731572811963e-05, "loss": 0.3867, "step": 260 }, { "epoch": 1.0572151898734177, "grad_norm": 0.6460724513460864, "learning_rate": 3.848572541175116e-05, "loss": 0.3984, "step": 261 }, { "epoch": 1.0612658227848102, "grad_norm": 0.5751965962931727, "learning_rate": 3.846398621389154e-05, "loss": 0.3878, "step": 262 }, { "epoch": 1.0653164556962025, "grad_norm": 0.5308677870305429, "learning_rate": 3.84420983096253e-05, "loss": 0.3893, "step": 263 }, { "epoch": 1.069367088607595, "grad_norm": 0.46417898136656616, "learning_rate": 3.8420061875234606e-05, "loss": 0.3777, "step": 264 }, { "epoch": 1.0734177215189873, "grad_norm": 0.41153279051589103, "learning_rate": 3.839787708819787e-05, "loss": 0.3838, "step": 265 }, { "epoch": 1.0774683544303798, "grad_norm": 0.4603807014860417, "learning_rate": 3.8375544127188325e-05, "loss": 0.3934, "step": 266 }, { "epoch": 1.081518987341772, "grad_norm": 0.3746230997528963, "learning_rate": 3.8353063172072564e-05, "loss": 0.3757, "step": 267 }, { "epoch": 1.0855696202531646, "grad_norm": 0.44452589474487353, "learning_rate": 3.8330434403909105e-05, "loss": 0.38, "step": 268 }, { "epoch": 1.089620253164557, "grad_norm": 0.4056857588825282, "learning_rate": 3.8307658004946934e-05, "loss": 0.3841, "step": 269 }, { "epoch": 1.0936708860759494, "grad_norm": 0.5180595135457624, "learning_rate": 3.8284734158624046e-05, "loss": 0.3942, "step": 270 }, { "epoch": 1.0977215189873417, "grad_norm": 0.5077944496559453, "learning_rate": 3.826166304956594e-05, "loss": 0.3788, "step": 271 }, { "epoch": 1.1017721518987342, "grad_norm": 0.5129320804461502, "learning_rate": 3.8238444863584164e-05, "loss": 0.3807, "step": 272 }, { "epoch": 1.1058227848101265, "grad_norm": 0.5623096105329815, "learning_rate": 3.821507978767479e-05, "loss": 0.3881, "step": 273 }, { "epoch": 1.109873417721519, "grad_norm": 0.3623822901562958, "learning_rate": 3.819156801001693e-05, "loss": 0.3891, "step": 274 }, { "epoch": 1.1139240506329113, "grad_norm": 0.5594688789341512, "learning_rate": 3.816790971997121e-05, "loss": 0.4055, "step": 275 }, { "epoch": 1.1179746835443038, "grad_norm": 0.5523550492027967, "learning_rate": 3.8144105108078246e-05, "loss": 0.3879, "step": 276 }, { "epoch": 1.1220253164556961, "grad_norm": 0.3755045174080149, "learning_rate": 3.81201543660571e-05, "loss": 0.3798, "step": 277 }, { "epoch": 1.1260759493670887, "grad_norm": 0.557542039169369, "learning_rate": 3.809605768680377e-05, "loss": 0.3852, "step": 278 }, { "epoch": 1.130126582278481, "grad_norm": 0.4755511972528799, "learning_rate": 3.807181526438958e-05, "loss": 0.3816, "step": 279 }, { "epoch": 1.1341772151898735, "grad_norm": 0.49670219073995214, "learning_rate": 3.8047427294059697e-05, "loss": 0.3879, "step": 280 }, { "epoch": 1.1382278481012658, "grad_norm": 0.4285795307225914, "learning_rate": 3.802289397223145e-05, "loss": 0.3866, "step": 281 }, { "epoch": 1.1422784810126583, "grad_norm": 0.3753602920451446, "learning_rate": 3.7998215496492854e-05, "loss": 0.3828, "step": 282 }, { "epoch": 1.1463291139240506, "grad_norm": 0.408197123108917, "learning_rate": 3.797339206560096e-05, "loss": 0.3859, "step": 283 }, { "epoch": 1.150379746835443, "grad_norm": 0.47771043770818933, "learning_rate": 3.794842387948027e-05, "loss": 0.3884, "step": 284 }, { "epoch": 1.1544303797468354, "grad_norm": 0.49396644485651503, "learning_rate": 3.7923311139221114e-05, "loss": 0.3814, "step": 285 }, { "epoch": 1.158481012658228, "grad_norm": 0.44647645799575386, "learning_rate": 3.7898054047078054e-05, "loss": 0.3924, "step": 286 }, { "epoch": 1.1625316455696202, "grad_norm": 0.36940069070342946, "learning_rate": 3.787265280646825e-05, "loss": 0.3855, "step": 287 }, { "epoch": 1.1665822784810127, "grad_norm": 0.4340255682333905, "learning_rate": 3.7847107621969786e-05, "loss": 0.3863, "step": 288 }, { "epoch": 1.170632911392405, "grad_norm": 0.39003162545492664, "learning_rate": 3.7821418699320064e-05, "loss": 0.3977, "step": 289 }, { "epoch": 1.1746835443037975, "grad_norm": 0.36972130134962194, "learning_rate": 3.7795586245414145e-05, "loss": 0.3961, "step": 290 }, { "epoch": 1.1787341772151898, "grad_norm": 0.4540991769583579, "learning_rate": 3.776961046830306e-05, "loss": 0.3988, "step": 291 }, { "epoch": 1.1827848101265823, "grad_norm": 0.45146330656475947, "learning_rate": 3.774349157719215e-05, "loss": 0.3974, "step": 292 }, { "epoch": 1.1868354430379746, "grad_norm": 0.4651657357367075, "learning_rate": 3.7717229782439365e-05, "loss": 0.3938, "step": 293 }, { "epoch": 1.1908860759493671, "grad_norm": 0.49224494952992603, "learning_rate": 3.769082529555359e-05, "loss": 0.3813, "step": 294 }, { "epoch": 1.1949367088607594, "grad_norm": 0.5476265666804807, "learning_rate": 3.766427832919294e-05, "loss": 0.4007, "step": 295 }, { "epoch": 1.198987341772152, "grad_norm": 0.5188965697371972, "learning_rate": 3.7637589097163024e-05, "loss": 0.3861, "step": 296 }, { "epoch": 1.2030379746835442, "grad_norm": 0.42271483192091913, "learning_rate": 3.761075781441526e-05, "loss": 0.3812, "step": 297 }, { "epoch": 1.2070886075949367, "grad_norm": 0.5378047278928432, "learning_rate": 3.75837846970451e-05, "loss": 0.3888, "step": 298 }, { "epoch": 1.211139240506329, "grad_norm": 0.42949059238385817, "learning_rate": 3.755666996229032e-05, "loss": 0.3921, "step": 299 }, { "epoch": 1.2151898734177216, "grad_norm": 0.644230987979411, "learning_rate": 3.752941382852927e-05, "loss": 0.3916, "step": 300 }, { "epoch": 1.2192405063291138, "grad_norm": 0.4308998768127078, "learning_rate": 3.7502016515279115e-05, "loss": 0.3954, "step": 301 }, { "epoch": 1.2232911392405064, "grad_norm": 0.5457219342792031, "learning_rate": 3.7474478243194043e-05, "loss": 0.3889, "step": 302 }, { "epoch": 1.2273417721518987, "grad_norm": 0.35641744549891624, "learning_rate": 3.744679923406351e-05, "loss": 0.3823, "step": 303 }, { "epoch": 1.2313924050632912, "grad_norm": 0.4119861083380852, "learning_rate": 3.741897971081043e-05, "loss": 0.3893, "step": 304 }, { "epoch": 1.2354430379746835, "grad_norm": 0.4288209287244731, "learning_rate": 3.739101989748946e-05, "loss": 0.3999, "step": 305 }, { "epoch": 1.239493670886076, "grad_norm": 0.3287572399053779, "learning_rate": 3.7362920019285066e-05, "loss": 0.3957, "step": 306 }, { "epoch": 1.2435443037974683, "grad_norm": 0.41056115526390513, "learning_rate": 3.73346803025098e-05, "loss": 0.385, "step": 307 }, { "epoch": 1.2475949367088608, "grad_norm": 0.43555009087335306, "learning_rate": 3.730630097460247e-05, "loss": 0.3895, "step": 308 }, { "epoch": 1.251645569620253, "grad_norm": 0.4788946420452696, "learning_rate": 3.727778226412628e-05, "loss": 0.3733, "step": 309 }, { "epoch": 1.2556962025316456, "grad_norm": 0.35356559897587836, "learning_rate": 3.7249124400767006e-05, "loss": 0.3845, "step": 310 }, { "epoch": 1.259746835443038, "grad_norm": 0.449219205472053, "learning_rate": 3.722032761533114e-05, "loss": 0.3988, "step": 311 }, { "epoch": 1.2637974683544304, "grad_norm": 0.46156019731284625, "learning_rate": 3.719139213974403e-05, "loss": 0.3803, "step": 312 }, { "epoch": 1.2678481012658227, "grad_norm": 0.37997546792487924, "learning_rate": 3.7162318207048006e-05, "loss": 0.3813, "step": 313 }, { "epoch": 1.2718987341772152, "grad_norm": 0.37949883700173404, "learning_rate": 3.713310605140055e-05, "loss": 0.387, "step": 314 }, { "epoch": 1.2759493670886077, "grad_norm": 0.47358182664857695, "learning_rate": 3.710375590807233e-05, "loss": 0.3838, "step": 315 }, { "epoch": 1.28, "grad_norm": 0.47143386338161564, "learning_rate": 3.7074268013445365e-05, "loss": 0.3915, "step": 316 }, { "epoch": 1.2840506329113923, "grad_norm": 0.38085659420536866, "learning_rate": 3.7044642605011114e-05, "loss": 0.3766, "step": 317 }, { "epoch": 1.2881012658227848, "grad_norm": 0.3430476492227787, "learning_rate": 3.701487992136854e-05, "loss": 0.3841, "step": 318 }, { "epoch": 1.2921518987341774, "grad_norm": 0.5207648419709944, "learning_rate": 3.69849802022222e-05, "loss": 0.3998, "step": 319 }, { "epoch": 1.2962025316455696, "grad_norm": 0.4973254637712968, "learning_rate": 3.6954943688380334e-05, "loss": 0.3931, "step": 320 }, { "epoch": 1.300253164556962, "grad_norm": 0.3653611623642678, "learning_rate": 3.692477062175289e-05, "loss": 0.384, "step": 321 }, { "epoch": 1.3043037974683545, "grad_norm": 0.47542782498278063, "learning_rate": 3.689446124534958e-05, "loss": 0.3856, "step": 322 }, { "epoch": 1.308354430379747, "grad_norm": 0.4371934138512554, "learning_rate": 3.686401580327799e-05, "loss": 0.3831, "step": 323 }, { "epoch": 1.3124050632911393, "grad_norm": 0.5135720362892234, "learning_rate": 3.683343454074149e-05, "loss": 0.3841, "step": 324 }, { "epoch": 1.3164556962025316, "grad_norm": 0.39884217116185106, "learning_rate": 3.6802717704037386e-05, "loss": 0.3935, "step": 325 }, { "epoch": 1.320506329113924, "grad_norm": 0.5305304971836373, "learning_rate": 3.6771865540554855e-05, "loss": 0.3815, "step": 326 }, { "epoch": 1.3245569620253166, "grad_norm": 0.558076214186387, "learning_rate": 3.674087829877297e-05, "loss": 0.3802, "step": 327 }, { "epoch": 1.3286075949367089, "grad_norm": 0.5129866145236747, "learning_rate": 3.6709756228258735e-05, "loss": 0.3882, "step": 328 }, { "epoch": 1.3326582278481012, "grad_norm": 0.40564328624327883, "learning_rate": 3.667849957966501e-05, "loss": 0.3812, "step": 329 }, { "epoch": 1.3367088607594937, "grad_norm": 0.48270116193212076, "learning_rate": 3.6647108604728546e-05, "loss": 0.3832, "step": 330 }, { "epoch": 1.3407594936708862, "grad_norm": 0.34810813002068225, "learning_rate": 3.661558355626795e-05, "loss": 0.3864, "step": 331 }, { "epoch": 1.3448101265822785, "grad_norm": 0.3975473912319302, "learning_rate": 3.658392468818163e-05, "loss": 0.3851, "step": 332 }, { "epoch": 1.3488607594936708, "grad_norm": 0.35164599510320077, "learning_rate": 3.655213225544574e-05, "loss": 0.3966, "step": 333 }, { "epoch": 1.3529113924050633, "grad_norm": 0.39403550008094174, "learning_rate": 3.652020651411218e-05, "loss": 0.4047, "step": 334 }, { "epoch": 1.3569620253164558, "grad_norm": 0.34348470156419325, "learning_rate": 3.6488147721306474e-05, "loss": 0.3863, "step": 335 }, { "epoch": 1.3610126582278481, "grad_norm": 0.38125827760451214, "learning_rate": 3.645595613522574e-05, "loss": 0.3937, "step": 336 }, { "epoch": 1.3650632911392404, "grad_norm": 0.37455792502858143, "learning_rate": 3.642363201513657e-05, "loss": 0.3811, "step": 337 }, { "epoch": 1.369113924050633, "grad_norm": 0.3724594117226474, "learning_rate": 3.6391175621373006e-05, "loss": 0.4021, "step": 338 }, { "epoch": 1.3731645569620254, "grad_norm": 0.4448892721398664, "learning_rate": 3.6358587215334355e-05, "loss": 0.387, "step": 339 }, { "epoch": 1.3772151898734177, "grad_norm": 0.3296928493023301, "learning_rate": 3.632586705948318e-05, "loss": 0.3906, "step": 340 }, { "epoch": 1.38126582278481, "grad_norm": 0.40864993032451696, "learning_rate": 3.629301541734311e-05, "loss": 0.3914, "step": 341 }, { "epoch": 1.3853164556962025, "grad_norm": 0.5106578345534354, "learning_rate": 3.626003255349676e-05, "loss": 0.3887, "step": 342 }, { "epoch": 1.389367088607595, "grad_norm": 0.3579067782690814, "learning_rate": 3.622691873358357e-05, "loss": 0.3811, "step": 343 }, { "epoch": 1.3934177215189874, "grad_norm": 0.43150012623474937, "learning_rate": 3.61936742242977e-05, "loss": 0.3895, "step": 344 }, { "epoch": 1.3974683544303796, "grad_norm": 0.4220529362256864, "learning_rate": 3.6160299293385864e-05, "loss": 0.3813, "step": 345 }, { "epoch": 1.4015189873417722, "grad_norm": 0.40935806160923444, "learning_rate": 3.612679420964516e-05, "loss": 0.3901, "step": 346 }, { "epoch": 1.4055696202531647, "grad_norm": 0.4555944757022585, "learning_rate": 3.609315924292092e-05, "loss": 0.3895, "step": 347 }, { "epoch": 1.409620253164557, "grad_norm": 0.3703838626697657, "learning_rate": 3.6059394664104554e-05, "loss": 0.3768, "step": 348 }, { "epoch": 1.4136708860759493, "grad_norm": 0.47646098163379164, "learning_rate": 3.602550074513133e-05, "loss": 0.385, "step": 349 }, { "epoch": 1.4177215189873418, "grad_norm": 0.41743410117235674, "learning_rate": 3.599147775897822e-05, "loss": 0.3855, "step": 350 }, { "epoch": 1.4217721518987343, "grad_norm": 0.4881583770003518, "learning_rate": 3.595732597966167e-05, "loss": 0.3976, "step": 351 }, { "epoch": 1.4258227848101266, "grad_norm": 0.350522727089356, "learning_rate": 3.592304568223542e-05, "loss": 0.3947, "step": 352 }, { "epoch": 1.4298734177215189, "grad_norm": 0.43374405737955507, "learning_rate": 3.588863714278826e-05, "loss": 0.3838, "step": 353 }, { "epoch": 1.4339240506329114, "grad_norm": 0.37411793841768315, "learning_rate": 3.585410063844186e-05, "loss": 0.3697, "step": 354 }, { "epoch": 1.437974683544304, "grad_norm": 0.34093369128556505, "learning_rate": 3.581943644734846e-05, "loss": 0.3766, "step": 355 }, { "epoch": 1.4420253164556962, "grad_norm": 0.45812905696141143, "learning_rate": 3.578464484868869e-05, "loss": 0.3876, "step": 356 }, { "epoch": 1.4460759493670885, "grad_norm": 0.4073541259939323, "learning_rate": 3.5749726122669316e-05, "loss": 0.3948, "step": 357 }, { "epoch": 1.450126582278481, "grad_norm": 0.34948730385330445, "learning_rate": 3.5714680550520943e-05, "loss": 0.3845, "step": 358 }, { "epoch": 1.4541772151898735, "grad_norm": 0.4365757259168689, "learning_rate": 3.5679508414495794e-05, "loss": 0.3834, "step": 359 }, { "epoch": 1.4582278481012658, "grad_norm": 0.3767035397633555, "learning_rate": 3.564420999786543e-05, "loss": 0.3923, "step": 360 }, { "epoch": 1.4622784810126581, "grad_norm": 0.41670676839239307, "learning_rate": 3.560878558491842e-05, "loss": 0.3813, "step": 361 }, { "epoch": 1.4663291139240506, "grad_norm": 0.41544401199987, "learning_rate": 3.5573235460958145e-05, "loss": 0.3894, "step": 362 }, { "epoch": 1.4703797468354431, "grad_norm": 0.3836484430109285, "learning_rate": 3.553755991230039e-05, "loss": 0.3857, "step": 363 }, { "epoch": 1.4744303797468354, "grad_norm": 0.341774545752962, "learning_rate": 3.5501759226271144e-05, "loss": 0.3756, "step": 364 }, { "epoch": 1.4784810126582277, "grad_norm": 0.3918957445995156, "learning_rate": 3.546583369120419e-05, "loss": 0.3805, "step": 365 }, { "epoch": 1.4825316455696202, "grad_norm": 0.44283177536687096, "learning_rate": 3.5429783596438864e-05, "loss": 0.3784, "step": 366 }, { "epoch": 1.4865822784810128, "grad_norm": 0.325324591509609, "learning_rate": 3.539360923231766e-05, "loss": 0.3872, "step": 367 }, { "epoch": 1.490632911392405, "grad_norm": 0.3897584859009208, "learning_rate": 3.535731089018394e-05, "loss": 0.3831, "step": 368 }, { "epoch": 1.4946835443037974, "grad_norm": 0.3365984516566389, "learning_rate": 3.532088886237956e-05, "loss": 0.3795, "step": 369 }, { "epoch": 1.4987341772151899, "grad_norm": 0.34828582733504476, "learning_rate": 3.528434344224253e-05, "loss": 0.385, "step": 370 }, { "epoch": 1.5027848101265824, "grad_norm": 0.2963664166645709, "learning_rate": 3.524767492410464e-05, "loss": 0.3914, "step": 371 }, { "epoch": 1.5068354430379747, "grad_norm": 0.3360645169721895, "learning_rate": 3.521088360328908e-05, "loss": 0.3803, "step": 372 }, { "epoch": 1.510886075949367, "grad_norm": 0.31487890178774436, "learning_rate": 3.517396977610811e-05, "loss": 0.398, "step": 373 }, { "epoch": 1.5149367088607595, "grad_norm": 0.33862048751082036, "learning_rate": 3.5136933739860595e-05, "loss": 0.3856, "step": 374 }, { "epoch": 1.518987341772152, "grad_norm": 0.34477918008199077, "learning_rate": 3.509977579282971e-05, "loss": 0.3855, "step": 375 }, { "epoch": 1.5230379746835443, "grad_norm": 0.35246896760560836, "learning_rate": 3.5062496234280424e-05, "loss": 0.3737, "step": 376 }, { "epoch": 1.5270886075949366, "grad_norm": 0.41859233719462613, "learning_rate": 3.502509536445719e-05, "loss": 0.39, "step": 377 }, { "epoch": 1.531139240506329, "grad_norm": 0.36044389824472317, "learning_rate": 3.498757348458147e-05, "loss": 0.3824, "step": 378 }, { "epoch": 1.5351898734177216, "grad_norm": 0.2835073468264586, "learning_rate": 3.4949930896849324e-05, "loss": 0.3749, "step": 379 }, { "epoch": 1.539240506329114, "grad_norm": 0.3434836855339819, "learning_rate": 3.491216790442899e-05, "loss": 0.38, "step": 380 }, { "epoch": 1.5432911392405062, "grad_norm": 0.36490120986185903, "learning_rate": 3.487428481145839e-05, "loss": 0.3849, "step": 381 }, { "epoch": 1.5473417721518987, "grad_norm": 0.40373223290071275, "learning_rate": 3.483628192304278e-05, "loss": 0.3804, "step": 382 }, { "epoch": 1.5513924050632912, "grad_norm": 0.4376544314504377, "learning_rate": 3.479815954525219e-05, "loss": 0.3861, "step": 383 }, { "epoch": 1.5554430379746835, "grad_norm": 0.3447959702211448, "learning_rate": 3.475991798511899e-05, "loss": 0.3819, "step": 384 }, { "epoch": 1.5594936708860758, "grad_norm": 0.3607352884670206, "learning_rate": 3.4721557550635464e-05, "loss": 0.3806, "step": 385 }, { "epoch": 1.5635443037974683, "grad_norm": 0.35934073443804926, "learning_rate": 3.468307855075128e-05, "loss": 0.3908, "step": 386 }, { "epoch": 1.5675949367088609, "grad_norm": 0.385742661665334, "learning_rate": 3.4644481295371005e-05, "loss": 0.3745, "step": 387 }, { "epoch": 1.5716455696202531, "grad_norm": 0.31347396288493085, "learning_rate": 3.460576609535163e-05, "loss": 0.3894, "step": 388 }, { "epoch": 1.5756962025316454, "grad_norm": 0.3832820492785837, "learning_rate": 3.456693326250006e-05, "loss": 0.4001, "step": 389 }, { "epoch": 1.579746835443038, "grad_norm": 0.30891437214861533, "learning_rate": 3.452798310957058e-05, "loss": 0.3703, "step": 390 }, { "epoch": 1.5837974683544305, "grad_norm": 0.3581490519661148, "learning_rate": 3.4488915950262386e-05, "loss": 0.3787, "step": 391 }, { "epoch": 1.5878481012658228, "grad_norm": 0.31743775247878875, "learning_rate": 3.4449732099216985e-05, "loss": 0.382, "step": 392 }, { "epoch": 1.591898734177215, "grad_norm": 0.3444528794729884, "learning_rate": 3.441043187201574e-05, "loss": 0.385, "step": 393 }, { "epoch": 1.5959493670886076, "grad_norm": 0.375573857557467, "learning_rate": 3.437101558517728e-05, "loss": 0.3812, "step": 394 }, { "epoch": 1.6, "grad_norm": 0.2855493756347293, "learning_rate": 3.433148355615496e-05, "loss": 0.3871, "step": 395 }, { "epoch": 1.6040506329113924, "grad_norm": 0.4145372794024573, "learning_rate": 3.4291836103334294e-05, "loss": 0.3859, "step": 396 }, { "epoch": 1.6081012658227847, "grad_norm": 0.35110053014846776, "learning_rate": 3.425207354603043e-05, "loss": 0.3808, "step": 397 }, { "epoch": 1.6121518987341772, "grad_norm": 0.36720821277631593, "learning_rate": 3.421219620448553e-05, "loss": 0.3766, "step": 398 }, { "epoch": 1.6162025316455697, "grad_norm": 0.3859966868005008, "learning_rate": 3.417220439986623e-05, "loss": 0.3807, "step": 399 }, { "epoch": 1.620253164556962, "grad_norm": 0.319952294932407, "learning_rate": 3.4132098454261024e-05, "loss": 0.3789, "step": 400 }, { "epoch": 1.6243037974683543, "grad_norm": 0.3649049613210092, "learning_rate": 3.4091878690677676e-05, "loss": 0.3915, "step": 401 }, { "epoch": 1.6283544303797468, "grad_norm": 0.36678505736652284, "learning_rate": 3.405154543304065e-05, "loss": 0.398, "step": 402 }, { "epoch": 1.6324050632911393, "grad_norm": 0.38737048137230506, "learning_rate": 3.401109900618843e-05, "loss": 0.3945, "step": 403 }, { "epoch": 1.6364556962025316, "grad_norm": 0.32115784530770203, "learning_rate": 3.3970539735870996e-05, "loss": 0.3835, "step": 404 }, { "epoch": 1.640506329113924, "grad_norm": 0.36416119794399626, "learning_rate": 3.392986794874714e-05, "loss": 0.3755, "step": 405 }, { "epoch": 1.6445569620253164, "grad_norm": 0.4082225617145904, "learning_rate": 3.388908397238184e-05, "loss": 0.3737, "step": 406 }, { "epoch": 1.648607594936709, "grad_norm": 0.3369198205190254, "learning_rate": 3.384818813524362e-05, "loss": 0.3843, "step": 407 }, { "epoch": 1.6526582278481012, "grad_norm": 0.4201578501812729, "learning_rate": 3.380718076670195e-05, "loss": 0.3695, "step": 408 }, { "epoch": 1.6567088607594935, "grad_norm": 0.3542001350605442, "learning_rate": 3.376606219702454e-05, "loss": 0.3782, "step": 409 }, { "epoch": 1.660759493670886, "grad_norm": 0.349515649963615, "learning_rate": 3.372483275737468e-05, "loss": 0.3756, "step": 410 }, { "epoch": 1.6648101265822786, "grad_norm": 0.33282122431500144, "learning_rate": 3.368349277980861e-05, "loss": 0.3799, "step": 411 }, { "epoch": 1.6688607594936709, "grad_norm": 0.3950403877271369, "learning_rate": 3.3642042597272844e-05, "loss": 0.3816, "step": 412 }, { "epoch": 1.6729113924050631, "grad_norm": 0.30487427450645455, "learning_rate": 3.360048254360144e-05, "loss": 0.378, "step": 413 }, { "epoch": 1.6769620253164557, "grad_norm": 0.38816425726167464, "learning_rate": 3.355881295351336e-05, "loss": 0.3792, "step": 414 }, { "epoch": 1.6810126582278482, "grad_norm": 0.36841876112144617, "learning_rate": 3.351703416260975e-05, "loss": 0.3685, "step": 415 }, { "epoch": 1.6850632911392405, "grad_norm": 0.3177924094547399, "learning_rate": 3.347514650737126e-05, "loss": 0.3934, "step": 416 }, { "epoch": 1.6891139240506328, "grad_norm": 0.3934558703705316, "learning_rate": 3.3433150325155295e-05, "loss": 0.381, "step": 417 }, { "epoch": 1.6931645569620253, "grad_norm": 0.33814456236604934, "learning_rate": 3.339104595419334e-05, "loss": 0.3781, "step": 418 }, { "epoch": 1.6972151898734178, "grad_norm": 0.30977700182253604, "learning_rate": 3.3348833733588204e-05, "loss": 0.3876, "step": 419 }, { "epoch": 1.70126582278481, "grad_norm": 0.3414023034933318, "learning_rate": 3.3306514003311305e-05, "loss": 0.3688, "step": 420 }, { "epoch": 1.7053164556962024, "grad_norm": 0.35103130670071453, "learning_rate": 3.326408710419996e-05, "loss": 0.3803, "step": 421 }, { "epoch": 1.709367088607595, "grad_norm": 0.34904483945301706, "learning_rate": 3.322155337795454e-05, "loss": 0.3861, "step": 422 }, { "epoch": 1.7134177215189874, "grad_norm": 0.33979237907947274, "learning_rate": 3.317891316713587e-05, "loss": 0.3827, "step": 423 }, { "epoch": 1.7174683544303797, "grad_norm": 0.3449097134547686, "learning_rate": 3.313616681516231e-05, "loss": 0.3799, "step": 424 }, { "epoch": 1.721518987341772, "grad_norm": 0.3354020672856758, "learning_rate": 3.309331466630713e-05, "loss": 0.3618, "step": 425 }, { "epoch": 1.7255696202531645, "grad_norm": 0.3400801256194868, "learning_rate": 3.305035706569563e-05, "loss": 0.3685, "step": 426 }, { "epoch": 1.729620253164557, "grad_norm": 0.3136476182368487, "learning_rate": 3.3007294359302433e-05, "loss": 0.3783, "step": 427 }, { "epoch": 1.7336708860759493, "grad_norm": 0.38071704374745535, "learning_rate": 3.296412689394864e-05, "loss": 0.3846, "step": 428 }, { "epoch": 1.7377215189873416, "grad_norm": 0.40144984428031916, "learning_rate": 3.292085501729909e-05, "loss": 0.3716, "step": 429 }, { "epoch": 1.7417721518987341, "grad_norm": 0.3074171509807652, "learning_rate": 3.2877479077859534e-05, "loss": 0.3705, "step": 430 }, { "epoch": 1.7458227848101266, "grad_norm": 0.47863587618809506, "learning_rate": 3.283399942497381e-05, "loss": 0.3938, "step": 431 }, { "epoch": 1.749873417721519, "grad_norm": 0.3278916512635529, "learning_rate": 3.279041640882108e-05, "loss": 0.3736, "step": 432 }, { "epoch": 1.7539240506329112, "grad_norm": 0.393125999481624, "learning_rate": 3.2746730380412964e-05, "loss": 0.3628, "step": 433 }, { "epoch": 1.7579746835443038, "grad_norm": 0.37974767078319166, "learning_rate": 3.2702941691590726e-05, "loss": 0.3727, "step": 434 }, { "epoch": 1.7620253164556963, "grad_norm": 0.3989574681210475, "learning_rate": 3.265905069502244e-05, "loss": 0.3842, "step": 435 }, { "epoch": 1.7660759493670886, "grad_norm": 0.3829837327826986, "learning_rate": 3.261505774420016e-05, "loss": 0.3848, "step": 436 }, { "epoch": 1.7701265822784809, "grad_norm": 0.47892143509160956, "learning_rate": 3.257096319343707e-05, "loss": 0.3808, "step": 437 }, { "epoch": 1.7741772151898734, "grad_norm": 0.32715282092768, "learning_rate": 3.2526767397864614e-05, "loss": 0.392, "step": 438 }, { "epoch": 1.7782278481012659, "grad_norm": 0.5009057772881422, "learning_rate": 3.248247071342966e-05, "loss": 0.3763, "step": 439 }, { "epoch": 1.7822784810126582, "grad_norm": 0.338905904431926, "learning_rate": 3.243807349689161e-05, "loss": 0.382, "step": 440 }, { "epoch": 1.7863291139240505, "grad_norm": 0.4415792150111884, "learning_rate": 3.2393576105819544e-05, "loss": 0.3813, "step": 441 }, { "epoch": 1.790379746835443, "grad_norm": 0.3348604449565611, "learning_rate": 3.2348978898589333e-05, "loss": 0.385, "step": 442 }, { "epoch": 1.7944303797468355, "grad_norm": 0.3454475612959799, "learning_rate": 3.230428223438075e-05, "loss": 0.3778, "step": 443 }, { "epoch": 1.7984810126582278, "grad_norm": 0.30372719421651795, "learning_rate": 3.225948647317459e-05, "loss": 0.374, "step": 444 }, { "epoch": 1.80253164556962, "grad_norm": 0.3649312397780138, "learning_rate": 3.2214591975749745e-05, "loss": 0.3747, "step": 445 }, { "epoch": 1.8065822784810126, "grad_norm": 0.3186309486964232, "learning_rate": 3.216959910368034e-05, "loss": 0.3921, "step": 446 }, { "epoch": 1.8106329113924051, "grad_norm": 0.3213497065837176, "learning_rate": 3.212450821933277e-05, "loss": 0.3866, "step": 447 }, { "epoch": 1.8146835443037974, "grad_norm": 0.32497704152490003, "learning_rate": 3.207931968586281e-05, "loss": 0.3845, "step": 448 }, { "epoch": 1.81873417721519, "grad_norm": 0.3669099051515152, "learning_rate": 3.203403386721272e-05, "loss": 0.3843, "step": 449 }, { "epoch": 1.8227848101265822, "grad_norm": 0.2759432070619428, "learning_rate": 3.1988651128108245e-05, "loss": 0.3849, "step": 450 }, { "epoch": 1.8268354430379747, "grad_norm": 0.3703439991493252, "learning_rate": 3.194317183405573e-05, "loss": 0.3898, "step": 451 }, { "epoch": 1.8308860759493673, "grad_norm": 0.29746035899196005, "learning_rate": 3.189759635133914e-05, "loss": 0.3717, "step": 452 }, { "epoch": 1.8349367088607595, "grad_norm": 0.2883229460943358, "learning_rate": 3.185192504701718e-05, "loss": 0.3841, "step": 453 }, { "epoch": 1.8389873417721518, "grad_norm": 0.331184284822426, "learning_rate": 3.1806158288920234e-05, "loss": 0.3922, "step": 454 }, { "epoch": 1.8430379746835444, "grad_norm": 0.28240892793288963, "learning_rate": 3.1760296445647477e-05, "loss": 0.387, "step": 455 }, { "epoch": 1.8470886075949369, "grad_norm": 0.29857964674145077, "learning_rate": 3.1714339886563896e-05, "loss": 0.3827, "step": 456 }, { "epoch": 1.8511392405063292, "grad_norm": 0.2822583214529235, "learning_rate": 3.166828898179731e-05, "loss": 0.3728, "step": 457 }, { "epoch": 1.8551898734177215, "grad_norm": 0.33223758210240467, "learning_rate": 3.162214410223536e-05, "loss": 0.375, "step": 458 }, { "epoch": 1.859240506329114, "grad_norm": 0.2843601053758237, "learning_rate": 3.157590561952257e-05, "loss": 0.3776, "step": 459 }, { "epoch": 1.8632911392405065, "grad_norm": 0.3195810857675839, "learning_rate": 3.152957390605732e-05, "loss": 0.3682, "step": 460 }, { "epoch": 1.8673417721518988, "grad_norm": 0.29637973776673787, "learning_rate": 3.148314933498886e-05, "loss": 0.3793, "step": 461 }, { "epoch": 1.871392405063291, "grad_norm": 0.32803722447316613, "learning_rate": 3.143663228021431e-05, "loss": 0.3759, "step": 462 }, { "epoch": 1.8754430379746836, "grad_norm": 0.3125968737082299, "learning_rate": 3.1390023116375624e-05, "loss": 0.3821, "step": 463 }, { "epoch": 1.879493670886076, "grad_norm": 0.3352725905202437, "learning_rate": 3.134332221885661e-05, "loss": 0.3864, "step": 464 }, { "epoch": 1.8835443037974684, "grad_norm": 0.28428383335015184, "learning_rate": 3.129652996377987e-05, "loss": 0.3779, "step": 465 }, { "epoch": 1.8875949367088607, "grad_norm": 0.3464235693926773, "learning_rate": 3.12496467280038e-05, "loss": 0.3734, "step": 466 }, { "epoch": 1.8916455696202532, "grad_norm": 0.3277228540538373, "learning_rate": 3.120267288911952e-05, "loss": 0.3955, "step": 467 }, { "epoch": 1.8956962025316457, "grad_norm": 0.2975124078763355, "learning_rate": 3.11556088254479e-05, "loss": 0.3821, "step": 468 }, { "epoch": 1.899746835443038, "grad_norm": 0.3126545146992582, "learning_rate": 3.11084549160364e-05, "loss": 0.3749, "step": 469 }, { "epoch": 1.9037974683544303, "grad_norm": 0.3115297960255967, "learning_rate": 3.106121154065615e-05, "loss": 0.3741, "step": 470 }, { "epoch": 1.9078481012658228, "grad_norm": 0.32143937749251894, "learning_rate": 3.1013879079798805e-05, "loss": 0.3801, "step": 471 }, { "epoch": 1.9118987341772153, "grad_norm": 0.35055125701341255, "learning_rate": 3.096645791467348e-05, "loss": 0.3784, "step": 472 }, { "epoch": 1.9159493670886076, "grad_norm": 0.4517635701465294, "learning_rate": 3.091894842720373e-05, "loss": 0.3699, "step": 473 }, { "epoch": 1.92, "grad_norm": 0.3321790354093538, "learning_rate": 3.0871351000024425e-05, "loss": 0.3796, "step": 474 }, { "epoch": 1.9240506329113924, "grad_norm": 0.40672437189565214, "learning_rate": 3.0823666016478716e-05, "loss": 0.373, "step": 475 }, { "epoch": 1.928101265822785, "grad_norm": 0.2695914648303373, "learning_rate": 3.0775893860614896e-05, "loss": 0.3708, "step": 476 }, { "epoch": 1.9321518987341773, "grad_norm": 0.41070070304308376, "learning_rate": 3.0728034917183336e-05, "loss": 0.3829, "step": 477 }, { "epoch": 1.9362025316455695, "grad_norm": 0.2913876405563037, "learning_rate": 3.06800895716334e-05, "loss": 0.3746, "step": 478 }, { "epoch": 1.940253164556962, "grad_norm": 0.3814049159184067, "learning_rate": 3.063205821011029e-05, "loss": 0.3702, "step": 479 }, { "epoch": 1.9443037974683546, "grad_norm": 0.26754545883469244, "learning_rate": 3.0583941219452016e-05, "loss": 0.3666, "step": 480 }, { "epoch": 1.9483544303797469, "grad_norm": 0.37434505996330286, "learning_rate": 3.053573898718618e-05, "loss": 0.3781, "step": 481 }, { "epoch": 1.9524050632911392, "grad_norm": 0.33659482534608626, "learning_rate": 3.0487451901526956e-05, "loss": 0.3855, "step": 482 }, { "epoch": 1.9564556962025317, "grad_norm": 0.3814609545669933, "learning_rate": 3.0439080351371875e-05, "loss": 0.3835, "step": 483 }, { "epoch": 1.9605063291139242, "grad_norm": 0.33010718626206204, "learning_rate": 3.0390624726298764e-05, "loss": 0.3807, "step": 484 }, { "epoch": 1.9645569620253165, "grad_norm": 0.491066705532208, "learning_rate": 3.034208541656255e-05, "loss": 0.3796, "step": 485 }, { "epoch": 1.9686075949367088, "grad_norm": 0.3031589042990034, "learning_rate": 3.029346281309218e-05, "loss": 0.3817, "step": 486 }, { "epoch": 1.9726582278481013, "grad_norm": 0.33772235183019367, "learning_rate": 3.0244757307487415e-05, "loss": 0.388, "step": 487 }, { "epoch": 1.9767088607594938, "grad_norm": 0.3207048292632546, "learning_rate": 3.019596929201569e-05, "loss": 0.3741, "step": 488 }, { "epoch": 1.980759493670886, "grad_norm": 0.3045109127366365, "learning_rate": 3.0147099159608985e-05, "loss": 0.3812, "step": 489 }, { "epoch": 1.9848101265822784, "grad_norm": 0.310078772785292, "learning_rate": 3.0098147303860616e-05, "loss": 0.3809, "step": 490 }, { "epoch": 1.988860759493671, "grad_norm": 0.27712872394580873, "learning_rate": 3.0049114119022117e-05, "loss": 0.3769, "step": 491 }, { "epoch": 1.9929113924050634, "grad_norm": 0.2933552702042419, "learning_rate": 3.0000000000000004e-05, "loss": 0.3778, "step": 492 }, { "epoch": 1.9969620253164557, "grad_norm": 0.2843542089325465, "learning_rate": 2.995080534235264e-05, "loss": 0.3734, "step": 493 }, { "epoch": 2.001012658227848, "grad_norm": 0.2892159704634128, "learning_rate": 2.9901530542287044e-05, "loss": 0.3662, "step": 494 }, { "epoch": 2.0050632911392405, "grad_norm": 0.3424981732323711, "learning_rate": 2.9852175996655676e-05, "loss": 0.3426, "step": 495 }, { "epoch": 2.009113924050633, "grad_norm": 0.4117948748214774, "learning_rate": 2.980274210295326e-05, "loss": 0.3269, "step": 496 }, { "epoch": 2.013164556962025, "grad_norm": 0.3651412484426669, "learning_rate": 2.9753229259313578e-05, "loss": 0.3257, "step": 497 }, { "epoch": 2.0172151898734176, "grad_norm": 0.342538280553685, "learning_rate": 2.9703637864506274e-05, "loss": 0.3343, "step": 498 }, { "epoch": 2.02126582278481, "grad_norm": 0.3554763832957155, "learning_rate": 2.965396831793362e-05, "loss": 0.315, "step": 499 }, { "epoch": 2.0253164556962027, "grad_norm": 0.30598846504567967, "learning_rate": 2.9604221019627316e-05, "loss": 0.325, "step": 500 }, { "epoch": 2.0293670886075947, "grad_norm": 0.3962526336460689, "learning_rate": 2.955439637024526e-05, "loss": 0.3249, "step": 501 }, { "epoch": 2.0334177215189873, "grad_norm": 0.3175247925405912, "learning_rate": 2.9504494771068334e-05, "loss": 0.3416, "step": 502 }, { "epoch": 2.0374683544303798, "grad_norm": 0.3331320815029603, "learning_rate": 2.9454516623997156e-05, "loss": 0.3312, "step": 503 }, { "epoch": 2.0415189873417723, "grad_norm": 0.2988153598618544, "learning_rate": 2.9404462331548847e-05, "loss": 0.3207, "step": 504 }, { "epoch": 2.0455696202531644, "grad_norm": 0.30245065502363516, "learning_rate": 2.93543322968538e-05, "loss": 0.3296, "step": 505 }, { "epoch": 2.049620253164557, "grad_norm": 0.29004446883927015, "learning_rate": 2.9304126923652428e-05, "loss": 0.3212, "step": 506 }, { "epoch": 2.0536708860759494, "grad_norm": 0.31256862251177797, "learning_rate": 2.9253846616291896e-05, "loss": 0.3307, "step": 507 }, { "epoch": 2.057721518987342, "grad_norm": 0.33042356786685195, "learning_rate": 2.9203491779722896e-05, "loss": 0.3233, "step": 508 }, { "epoch": 2.061772151898734, "grad_norm": 0.31761413649182735, "learning_rate": 2.9153062819496357e-05, "loss": 0.3295, "step": 509 }, { "epoch": 2.0658227848101265, "grad_norm": 0.3640838043408147, "learning_rate": 2.9102560141760178e-05, "loss": 0.3295, "step": 510 }, { "epoch": 2.069873417721519, "grad_norm": 0.4198501581106694, "learning_rate": 2.9051984153256004e-05, "loss": 0.3329, "step": 511 }, { "epoch": 2.0739240506329115, "grad_norm": 0.2820174995673319, "learning_rate": 2.900133526131588e-05, "loss": 0.3359, "step": 512 }, { "epoch": 2.0779746835443036, "grad_norm": 0.40922055577653627, "learning_rate": 2.8950613873859025e-05, "loss": 0.3385, "step": 513 }, { "epoch": 2.082025316455696, "grad_norm": 0.282037917642925, "learning_rate": 2.8899820399388515e-05, "loss": 0.3218, "step": 514 }, { "epoch": 2.0860759493670886, "grad_norm": 0.2999616133979687, "learning_rate": 2.8848955246988012e-05, "loss": 0.3294, "step": 515 }, { "epoch": 2.090126582278481, "grad_norm": 0.30217208618732316, "learning_rate": 2.879801882631847e-05, "loss": 0.3196, "step": 516 }, { "epoch": 2.094177215189873, "grad_norm": 0.2718131789216686, "learning_rate": 2.8747011547614808e-05, "loss": 0.3297, "step": 517 }, { "epoch": 2.0982278481012657, "grad_norm": 0.35309259158076983, "learning_rate": 2.8695933821682635e-05, "loss": 0.3232, "step": 518 }, { "epoch": 2.1022784810126582, "grad_norm": 0.29550160428797506, "learning_rate": 2.864478605989494e-05, "loss": 0.3257, "step": 519 }, { "epoch": 2.1063291139240508, "grad_norm": 0.39806109825407543, "learning_rate": 2.8593568674188765e-05, "loss": 0.322, "step": 520 }, { "epoch": 2.110379746835443, "grad_norm": 0.3407700951110883, "learning_rate": 2.8542282077061892e-05, "loss": 0.3324, "step": 521 }, { "epoch": 2.1144303797468353, "grad_norm": 0.33249957078948356, "learning_rate": 2.8490926681569523e-05, "loss": 0.3292, "step": 522 }, { "epoch": 2.118481012658228, "grad_norm": 0.33251830475892485, "learning_rate": 2.8439502901320956e-05, "loss": 0.337, "step": 523 }, { "epoch": 2.1225316455696204, "grad_norm": 0.3674822441196616, "learning_rate": 2.8388011150476237e-05, "loss": 0.3372, "step": 524 }, { "epoch": 2.1265822784810124, "grad_norm": 0.4037927845767834, "learning_rate": 2.8336451843742866e-05, "loss": 0.3352, "step": 525 }, { "epoch": 2.130632911392405, "grad_norm": 0.33069077949420245, "learning_rate": 2.8284825396372387e-05, "loss": 0.3249, "step": 526 }, { "epoch": 2.1346835443037975, "grad_norm": 0.3337225840645772, "learning_rate": 2.8233132224157132e-05, "loss": 0.3281, "step": 527 }, { "epoch": 2.13873417721519, "grad_norm": 0.288662636885591, "learning_rate": 2.8181372743426805e-05, "loss": 0.3403, "step": 528 }, { "epoch": 2.1427848101265825, "grad_norm": 0.31955001494250035, "learning_rate": 2.8129547371045128e-05, "loss": 0.331, "step": 529 }, { "epoch": 2.1468354430379746, "grad_norm": 0.31548680162696935, "learning_rate": 2.8077656524406534e-05, "loss": 0.3373, "step": 530 }, { "epoch": 2.150886075949367, "grad_norm": 0.3056851695380509, "learning_rate": 2.802570062143278e-05, "loss": 0.3306, "step": 531 }, { "epoch": 2.1549367088607596, "grad_norm": 0.3220897582611139, "learning_rate": 2.7973680080569555e-05, "loss": 0.3236, "step": 532 }, { "epoch": 2.1589873417721517, "grad_norm": 0.28615022900390585, "learning_rate": 2.792159532078314e-05, "loss": 0.3378, "step": 533 }, { "epoch": 2.163037974683544, "grad_norm": 0.25710558990853427, "learning_rate": 2.7869446761557033e-05, "loss": 0.3304, "step": 534 }, { "epoch": 2.1670886075949367, "grad_norm": 0.3241648830754623, "learning_rate": 2.781723482288857e-05, "loss": 0.3303, "step": 535 }, { "epoch": 2.1711392405063292, "grad_norm": 0.2843606199312862, "learning_rate": 2.7764959925285517e-05, "loss": 0.3285, "step": 536 }, { "epoch": 2.1751898734177217, "grad_norm": 0.28731651294240557, "learning_rate": 2.771262248976272e-05, "loss": 0.3196, "step": 537 }, { "epoch": 2.179240506329114, "grad_norm": 0.29111774494393017, "learning_rate": 2.7660222937838677e-05, "loss": 0.3257, "step": 538 }, { "epoch": 2.1832911392405063, "grad_norm": 0.305608211433527, "learning_rate": 2.7607761691532186e-05, "loss": 0.3242, "step": 539 }, { "epoch": 2.187341772151899, "grad_norm": 0.25680825112924205, "learning_rate": 2.7555239173358916e-05, "loss": 0.3393, "step": 540 }, { "epoch": 2.191392405063291, "grad_norm": 0.2953100039937019, "learning_rate": 2.7502655806328e-05, "loss": 0.3249, "step": 541 }, { "epoch": 2.1954430379746834, "grad_norm": 0.2633644758855575, "learning_rate": 2.7450012013938648e-05, "loss": 0.3201, "step": 542 }, { "epoch": 2.199493670886076, "grad_norm": 0.31557050980893936, "learning_rate": 2.739730822017673e-05, "loss": 0.3363, "step": 543 }, { "epoch": 2.2035443037974685, "grad_norm": 0.2962925024801538, "learning_rate": 2.7344544849511355e-05, "loss": 0.3321, "step": 544 }, { "epoch": 2.207594936708861, "grad_norm": 0.34138763640141323, "learning_rate": 2.7291722326891456e-05, "loss": 0.3323, "step": 545 }, { "epoch": 2.211645569620253, "grad_norm": 0.3694751759911679, "learning_rate": 2.723884107774236e-05, "loss": 0.3292, "step": 546 }, { "epoch": 2.2156962025316456, "grad_norm": 0.29521962871589863, "learning_rate": 2.718590152796239e-05, "loss": 0.3262, "step": 547 }, { "epoch": 2.219746835443038, "grad_norm": 0.34953298414013767, "learning_rate": 2.71329041039194e-05, "loss": 0.3214, "step": 548 }, { "epoch": 2.22379746835443, "grad_norm": 0.31582040752559454, "learning_rate": 2.7079849232447357e-05, "loss": 0.3375, "step": 549 }, { "epoch": 2.2278481012658227, "grad_norm": 0.30706103329052864, "learning_rate": 2.7026737340842895e-05, "loss": 0.3268, "step": 550 }, { "epoch": 2.231898734177215, "grad_norm": 0.2800692083872076, "learning_rate": 2.697356885686189e-05, "loss": 0.3204, "step": 551 }, { "epoch": 2.2359493670886077, "grad_norm": 0.32022238467017505, "learning_rate": 2.6920344208716014e-05, "loss": 0.3367, "step": 552 }, { "epoch": 2.24, "grad_norm": 0.32793979841645, "learning_rate": 2.6867063825069252e-05, "loss": 0.3305, "step": 553 }, { "epoch": 2.2440506329113923, "grad_norm": 0.3363047966507216, "learning_rate": 2.6813728135034494e-05, "loss": 0.3423, "step": 554 }, { "epoch": 2.248101265822785, "grad_norm": 0.2936967471799107, "learning_rate": 2.6760337568170056e-05, "loss": 0.3307, "step": 555 }, { "epoch": 2.2521518987341773, "grad_norm": 0.365642804255868, "learning_rate": 2.6706892554476226e-05, "loss": 0.332, "step": 556 }, { "epoch": 2.2562025316455694, "grad_norm": 0.2702667175098322, "learning_rate": 2.6653393524391795e-05, "loss": 0.3229, "step": 557 }, { "epoch": 2.260253164556962, "grad_norm": 0.37673955239582635, "learning_rate": 2.6599840908790592e-05, "loss": 0.3339, "step": 558 }, { "epoch": 2.2643037974683544, "grad_norm": 0.33590570753148113, "learning_rate": 2.6546235138978028e-05, "loss": 0.335, "step": 559 }, { "epoch": 2.268354430379747, "grad_norm": 0.3481836528369392, "learning_rate": 2.6492576646687597e-05, "loss": 0.3228, "step": 560 }, { "epoch": 2.2724050632911394, "grad_norm": 0.3805196035425885, "learning_rate": 2.6438865864077425e-05, "loss": 0.3287, "step": 561 }, { "epoch": 2.2764556962025315, "grad_norm": 0.3432290723824388, "learning_rate": 2.6385103223726766e-05, "loss": 0.335, "step": 562 }, { "epoch": 2.280506329113924, "grad_norm": 0.360444792093578, "learning_rate": 2.6331289158632537e-05, "loss": 0.3311, "step": 563 }, { "epoch": 2.2845569620253166, "grad_norm": 0.29592824115104943, "learning_rate": 2.6277424102205817e-05, "loss": 0.3523, "step": 564 }, { "epoch": 2.2886075949367086, "grad_norm": 0.3512868009138631, "learning_rate": 2.6223508488268374e-05, "loss": 0.3261, "step": 565 }, { "epoch": 2.292658227848101, "grad_norm": 0.2589453761370934, "learning_rate": 2.6169542751049148e-05, "loss": 0.3254, "step": 566 }, { "epoch": 2.2967088607594937, "grad_norm": 0.32738738514723104, "learning_rate": 2.6115527325180754e-05, "loss": 0.3361, "step": 567 }, { "epoch": 2.300759493670886, "grad_norm": 0.29144446634190196, "learning_rate": 2.606146264569603e-05, "loss": 0.331, "step": 568 }, { "epoch": 2.3048101265822787, "grad_norm": 0.26770691139906255, "learning_rate": 2.6007349148024447e-05, "loss": 0.3361, "step": 569 }, { "epoch": 2.3088607594936708, "grad_norm": 0.3052548012250612, "learning_rate": 2.5953187267988694e-05, "loss": 0.3291, "step": 570 }, { "epoch": 2.3129113924050633, "grad_norm": 0.3120749659517483, "learning_rate": 2.5898977441801097e-05, "loss": 0.3379, "step": 571 }, { "epoch": 2.316962025316456, "grad_norm": 0.3290171363361761, "learning_rate": 2.584472010606015e-05, "loss": 0.3267, "step": 572 }, { "epoch": 2.321012658227848, "grad_norm": 0.3147171186398466, "learning_rate": 2.5790415697746976e-05, "loss": 0.3276, "step": 573 }, { "epoch": 2.3250632911392404, "grad_norm": 0.3058349324230757, "learning_rate": 2.5736064654221808e-05, "loss": 0.3266, "step": 574 }, { "epoch": 2.329113924050633, "grad_norm": 0.3163883752323457, "learning_rate": 2.568166741322048e-05, "loss": 0.328, "step": 575 }, { "epoch": 2.3331645569620254, "grad_norm": 0.2662669297400431, "learning_rate": 2.56272244128509e-05, "loss": 0.3289, "step": 576 }, { "epoch": 2.337215189873418, "grad_norm": 0.2906324953874168, "learning_rate": 2.55727360915895e-05, "loss": 0.3246, "step": 577 }, { "epoch": 2.34126582278481, "grad_norm": 0.29784652321644056, "learning_rate": 2.5518202888277734e-05, "loss": 0.3262, "step": 578 }, { "epoch": 2.3453164556962025, "grad_norm": 0.28311930554445436, "learning_rate": 2.5463625242118523e-05, "loss": 0.3446, "step": 579 }, { "epoch": 2.349367088607595, "grad_norm": 0.31059437904319687, "learning_rate": 2.5409003592672723e-05, "loss": 0.3252, "step": 580 }, { "epoch": 2.353417721518987, "grad_norm": 0.28277811142542364, "learning_rate": 2.535433837985559e-05, "loss": 0.3289, "step": 581 }, { "epoch": 2.3574683544303796, "grad_norm": 0.31490336013064507, "learning_rate": 2.529963004393324e-05, "loss": 0.3354, "step": 582 }, { "epoch": 2.361518987341772, "grad_norm": 0.32537401935729404, "learning_rate": 2.524487902551908e-05, "loss": 0.3337, "step": 583 }, { "epoch": 2.3655696202531646, "grad_norm": 0.28045048115691684, "learning_rate": 2.519008576557029e-05, "loss": 0.3337, "step": 584 }, { "epoch": 2.369620253164557, "grad_norm": 0.3292762153468928, "learning_rate": 2.5135250705384254e-05, "loss": 0.332, "step": 585 }, { "epoch": 2.3736708860759492, "grad_norm": 0.3001696499523172, "learning_rate": 2.5080374286595007e-05, "loss": 0.3316, "step": 586 }, { "epoch": 2.3777215189873417, "grad_norm": 0.3366767363581091, "learning_rate": 2.5025456951169677e-05, "loss": 0.3291, "step": 587 }, { "epoch": 2.3817721518987343, "grad_norm": 0.29421662153356104, "learning_rate": 2.4970499141404942e-05, "loss": 0.3307, "step": 588 }, { "epoch": 2.3858227848101268, "grad_norm": 0.36250435236353695, "learning_rate": 2.491550129992345e-05, "loss": 0.3325, "step": 589 }, { "epoch": 2.389873417721519, "grad_norm": 0.27633217464229615, "learning_rate": 2.486046386967024e-05, "loss": 0.3294, "step": 590 }, { "epoch": 2.3939240506329114, "grad_norm": 0.3219252945256618, "learning_rate": 2.4805387293909214e-05, "loss": 0.3308, "step": 591 }, { "epoch": 2.397974683544304, "grad_norm": 0.2866386405956498, "learning_rate": 2.4750272016219552e-05, "loss": 0.3342, "step": 592 }, { "epoch": 2.4020253164556964, "grad_norm": 0.28819015902064626, "learning_rate": 2.4695118480492114e-05, "loss": 0.3335, "step": 593 }, { "epoch": 2.4060759493670885, "grad_norm": 0.28256310217403885, "learning_rate": 2.4639927130925898e-05, "loss": 0.326, "step": 594 }, { "epoch": 2.410126582278481, "grad_norm": 0.357437540657156, "learning_rate": 2.458469841202444e-05, "loss": 0.3311, "step": 595 }, { "epoch": 2.4141772151898735, "grad_norm": 0.2811157079096098, "learning_rate": 2.452943276859226e-05, "loss": 0.3356, "step": 596 }, { "epoch": 2.418227848101266, "grad_norm": 0.3159045024662614, "learning_rate": 2.447413064573125e-05, "loss": 0.3285, "step": 597 }, { "epoch": 2.422278481012658, "grad_norm": 0.29264679212783756, "learning_rate": 2.4418792488837095e-05, "loss": 0.3262, "step": 598 }, { "epoch": 2.4263291139240506, "grad_norm": 0.26597630967250424, "learning_rate": 2.4363418743595713e-05, "loss": 0.3327, "step": 599 }, { "epoch": 2.430379746835443, "grad_norm": 0.3093830627640994, "learning_rate": 2.430800985597963e-05, "loss": 0.3361, "step": 600 }, { "epoch": 2.4344303797468356, "grad_norm": 0.24788345921168198, "learning_rate": 2.4252566272244415e-05, "loss": 0.3275, "step": 601 }, { "epoch": 2.4384810126582277, "grad_norm": 0.2706719321661926, "learning_rate": 2.4197088438925063e-05, "loss": 0.3397, "step": 602 }, { "epoch": 2.44253164556962, "grad_norm": 0.274747795562337, "learning_rate": 2.4141576802832417e-05, "loss": 0.3298, "step": 603 }, { "epoch": 2.4465822784810127, "grad_norm": 0.25978679998672755, "learning_rate": 2.408603181104957e-05, "loss": 0.3364, "step": 604 }, { "epoch": 2.4506329113924052, "grad_norm": 0.27779088612443664, "learning_rate": 2.4030453910928245e-05, "loss": 0.3374, "step": 605 }, { "epoch": 2.4546835443037973, "grad_norm": 0.2776235401604121, "learning_rate": 2.397484355008521e-05, "loss": 0.3245, "step": 606 }, { "epoch": 2.45873417721519, "grad_norm": 0.26108171164280053, "learning_rate": 2.3919201176398662e-05, "loss": 0.3303, "step": 607 }, { "epoch": 2.4627848101265823, "grad_norm": 0.26298139681357235, "learning_rate": 2.3863527238004633e-05, "loss": 0.3329, "step": 608 }, { "epoch": 2.466835443037975, "grad_norm": 0.27732858415571987, "learning_rate": 2.380782218329337e-05, "loss": 0.3365, "step": 609 }, { "epoch": 2.470886075949367, "grad_norm": 0.26176112731458423, "learning_rate": 2.3752086460905725e-05, "loss": 0.3251, "step": 610 }, { "epoch": 2.4749367088607594, "grad_norm": 0.28581543019032074, "learning_rate": 2.3696320519729544e-05, "loss": 0.3397, "step": 611 }, { "epoch": 2.478987341772152, "grad_norm": 0.24586083745956164, "learning_rate": 2.3640524808896045e-05, "loss": 0.325, "step": 612 }, { "epoch": 2.4830379746835445, "grad_norm": 0.2580079830560591, "learning_rate": 2.3584699777776222e-05, "loss": 0.3328, "step": 613 }, { "epoch": 2.4870886075949366, "grad_norm": 0.2696754878488623, "learning_rate": 2.3528845875977195e-05, "loss": 0.3422, "step": 614 }, { "epoch": 2.491139240506329, "grad_norm": 0.26067682704564016, "learning_rate": 2.3472963553338614e-05, "loss": 0.3347, "step": 615 }, { "epoch": 2.4951898734177216, "grad_norm": 0.28025974755862215, "learning_rate": 2.341705325992901e-05, "loss": 0.3408, "step": 616 }, { "epoch": 2.499240506329114, "grad_norm": 0.26062536298960776, "learning_rate": 2.336111544604222e-05, "loss": 0.3292, "step": 617 }, { "epoch": 2.503291139240506, "grad_norm": 0.2411206080711834, "learning_rate": 2.33051505621937e-05, "loss": 0.3273, "step": 618 }, { "epoch": 2.5073417721518987, "grad_norm": 0.2706645232810319, "learning_rate": 2.324915905911693e-05, "loss": 0.3338, "step": 619 }, { "epoch": 2.511392405063291, "grad_norm": 0.28389393325418055, "learning_rate": 2.319314138775977e-05, "loss": 0.3357, "step": 620 }, { "epoch": 2.5154430379746833, "grad_norm": 0.2992193302214626, "learning_rate": 2.3137097999280856e-05, "loss": 0.3298, "step": 621 }, { "epoch": 2.519493670886076, "grad_norm": 0.2898257731717818, "learning_rate": 2.308102934504593e-05, "loss": 0.3326, "step": 622 }, { "epoch": 2.5235443037974683, "grad_norm": 0.27044840039555673, "learning_rate": 2.3024935876624222e-05, "loss": 0.3198, "step": 623 }, { "epoch": 2.527594936708861, "grad_norm": 0.28710479643231773, "learning_rate": 2.2968818045784813e-05, "loss": 0.3212, "step": 624 }, { "epoch": 2.5316455696202533, "grad_norm": 0.2866929764190186, "learning_rate": 2.2912676304493006e-05, "loss": 0.3291, "step": 625 }, { "epoch": 2.5356962025316454, "grad_norm": 0.2923754907967331, "learning_rate": 2.2856511104906668e-05, "loss": 0.3297, "step": 626 }, { "epoch": 2.539746835443038, "grad_norm": 0.3260031538391965, "learning_rate": 2.2800322899372586e-05, "loss": 0.3265, "step": 627 }, { "epoch": 2.5437974683544304, "grad_norm": 0.30895840492192955, "learning_rate": 2.2744112140422844e-05, "loss": 0.3249, "step": 628 }, { "epoch": 2.547848101265823, "grad_norm": 0.26048632370296165, "learning_rate": 2.2687879280771177e-05, "loss": 0.3288, "step": 629 }, { "epoch": 2.5518987341772155, "grad_norm": 0.32432730076814, "learning_rate": 2.26316247733093e-05, "loss": 0.3297, "step": 630 }, { "epoch": 2.5559493670886075, "grad_norm": 0.28449945044341907, "learning_rate": 2.257534907110328e-05, "loss": 0.3283, "step": 631 }, { "epoch": 2.56, "grad_norm": 0.3217497721083847, "learning_rate": 2.2519052627389882e-05, "loss": 0.3404, "step": 632 }, { "epoch": 2.5640506329113926, "grad_norm": 0.27087670481824067, "learning_rate": 2.246273589557294e-05, "loss": 0.3348, "step": 633 }, { "epoch": 2.5681012658227846, "grad_norm": 0.31954764505770955, "learning_rate": 2.240639932921966e-05, "loss": 0.3291, "step": 634 }, { "epoch": 2.572151898734177, "grad_norm": 0.24165845133473535, "learning_rate": 2.2350043382056995e-05, "loss": 0.3228, "step": 635 }, { "epoch": 2.5762025316455697, "grad_norm": 0.32547897940904286, "learning_rate": 2.2293668507968015e-05, "loss": 0.3357, "step": 636 }, { "epoch": 2.580253164556962, "grad_norm": 0.26317718797296596, "learning_rate": 2.2237275160988186e-05, "loss": 0.3304, "step": 637 }, { "epoch": 2.5843037974683547, "grad_norm": 0.3175524786557426, "learning_rate": 2.2180863795301787e-05, "loss": 0.327, "step": 638 }, { "epoch": 2.5883544303797468, "grad_norm": 0.25662662664496844, "learning_rate": 2.212443486523819e-05, "loss": 0.3324, "step": 639 }, { "epoch": 2.5924050632911393, "grad_norm": 0.35535562147584554, "learning_rate": 2.2067988825268243e-05, "loss": 0.339, "step": 640 }, { "epoch": 2.596455696202532, "grad_norm": 0.2635035875356435, "learning_rate": 2.2011526130000596e-05, "loss": 0.3402, "step": 641 }, { "epoch": 2.600506329113924, "grad_norm": 0.2883374883674006, "learning_rate": 2.1955047234178038e-05, "loss": 0.3289, "step": 642 }, { "epoch": 2.6045569620253164, "grad_norm": 0.29132636127468103, "learning_rate": 2.1898552592673825e-05, "loss": 0.332, "step": 643 }, { "epoch": 2.608607594936709, "grad_norm": 0.2798140566837739, "learning_rate": 2.184204266048803e-05, "loss": 0.322, "step": 644 }, { "epoch": 2.6126582278481014, "grad_norm": 0.2890760476109324, "learning_rate": 2.1785517892743887e-05, "loss": 0.3374, "step": 645 }, { "epoch": 2.616708860759494, "grad_norm": 0.27081567122464173, "learning_rate": 2.17289787446841e-05, "loss": 0.3373, "step": 646 }, { "epoch": 2.620759493670886, "grad_norm": 0.2953918149397897, "learning_rate": 2.1672425671667198e-05, "loss": 0.3359, "step": 647 }, { "epoch": 2.6248101265822785, "grad_norm": 0.25517959365150045, "learning_rate": 2.161585912916385e-05, "loss": 0.3228, "step": 648 }, { "epoch": 2.628860759493671, "grad_norm": 0.2801028137719771, "learning_rate": 2.1559279572753214e-05, "loss": 0.3305, "step": 649 }, { "epoch": 2.632911392405063, "grad_norm": 0.24670480335299305, "learning_rate": 2.1502687458119268e-05, "loss": 0.3229, "step": 650 }, { "epoch": 2.6369620253164556, "grad_norm": 0.2675817990691352, "learning_rate": 2.1446083241047116e-05, "loss": 0.3408, "step": 651 }, { "epoch": 2.641012658227848, "grad_norm": 0.2665811298786067, "learning_rate": 2.1389467377419333e-05, "loss": 0.333, "step": 652 }, { "epoch": 2.6450632911392407, "grad_norm": 0.2593269853196098, "learning_rate": 2.133284032321232e-05, "loss": 0.3294, "step": 653 }, { "epoch": 2.649113924050633, "grad_norm": 0.276399001752783, "learning_rate": 2.1276202534492566e-05, "loss": 0.3379, "step": 654 }, { "epoch": 2.6531645569620252, "grad_norm": 0.264398689066663, "learning_rate": 2.121955446741306e-05, "loss": 0.3244, "step": 655 }, { "epoch": 2.6572151898734178, "grad_norm": 0.2829820864027538, "learning_rate": 2.1162896578209517e-05, "loss": 0.3314, "step": 656 }, { "epoch": 2.6612658227848103, "grad_norm": 0.2792057203264399, "learning_rate": 2.1106229323196813e-05, "loss": 0.3274, "step": 657 }, { "epoch": 2.6653164556962023, "grad_norm": 0.27109024267837295, "learning_rate": 2.1049553158765214e-05, "loss": 0.3228, "step": 658 }, { "epoch": 2.669367088607595, "grad_norm": 0.2767769353561929, "learning_rate": 2.0992868541376764e-05, "loss": 0.3265, "step": 659 }, { "epoch": 2.6734177215189874, "grad_norm": 0.2938367666574841, "learning_rate": 2.093617592756158e-05, "loss": 0.3275, "step": 660 }, { "epoch": 2.67746835443038, "grad_norm": 0.30159873536999365, "learning_rate": 2.0879475773914167e-05, "loss": 0.3301, "step": 661 }, { "epoch": 2.6815189873417724, "grad_norm": 0.27141425894706184, "learning_rate": 2.082276853708978e-05, "loss": 0.3326, "step": 662 }, { "epoch": 2.6855696202531645, "grad_norm": 0.29974178719389627, "learning_rate": 2.076605467380071e-05, "loss": 0.3287, "step": 663 }, { "epoch": 2.689620253164557, "grad_norm": 0.29434250624307945, "learning_rate": 2.0709334640812613e-05, "loss": 0.3401, "step": 664 }, { "epoch": 2.6936708860759495, "grad_norm": 0.2954405039234713, "learning_rate": 2.0652608894940824e-05, "loss": 0.3368, "step": 665 }, { "epoch": 2.6977215189873416, "grad_norm": 0.296254895353691, "learning_rate": 2.0595877893046722e-05, "loss": 0.3216, "step": 666 }, { "epoch": 2.701772151898734, "grad_norm": 0.2971697907569677, "learning_rate": 2.0539142092033985e-05, "loss": 0.3327, "step": 667 }, { "epoch": 2.7058227848101266, "grad_norm": 0.3433416895323225, "learning_rate": 2.048240194884496e-05, "loss": 0.3344, "step": 668 }, { "epoch": 2.709873417721519, "grad_norm": 0.28633900902443615, "learning_rate": 2.042565792045695e-05, "loss": 0.3368, "step": 669 }, { "epoch": 2.7139240506329116, "grad_norm": 0.33836322218257064, "learning_rate": 2.036891046387857e-05, "loss": 0.3268, "step": 670 }, { "epoch": 2.7179746835443037, "grad_norm": 0.32261352210090666, "learning_rate": 2.0312160036146036e-05, "loss": 0.3455, "step": 671 }, { "epoch": 2.7220253164556962, "grad_norm": 0.41688665778197426, "learning_rate": 2.025540709431948e-05, "loss": 0.3332, "step": 672 }, { "epoch": 2.7260759493670887, "grad_norm": 0.3590967710257875, "learning_rate": 2.0198652095479298e-05, "loss": 0.3227, "step": 673 }, { "epoch": 2.730126582278481, "grad_norm": 0.2691079877643053, "learning_rate": 2.014189549672245e-05, "loss": 0.3266, "step": 674 }, { "epoch": 2.7341772151898733, "grad_norm": 0.36911125860651467, "learning_rate": 2.0085137755158776e-05, "loss": 0.3295, "step": 675 }, { "epoch": 2.738227848101266, "grad_norm": 0.2600717477647792, "learning_rate": 2.0028379327907327e-05, "loss": 0.3321, "step": 676 }, { "epoch": 2.7422784810126584, "grad_norm": 0.3219039891581626, "learning_rate": 1.9971620672092676e-05, "loss": 0.3288, "step": 677 }, { "epoch": 2.746329113924051, "grad_norm": 0.282979500893615, "learning_rate": 1.991486224484123e-05, "loss": 0.3215, "step": 678 }, { "epoch": 2.750379746835443, "grad_norm": 0.31360878137702797, "learning_rate": 1.985810450327756e-05, "loss": 0.3327, "step": 679 }, { "epoch": 2.7544303797468355, "grad_norm": 0.2723044110672177, "learning_rate": 1.9801347904520706e-05, "loss": 0.3336, "step": 680 }, { "epoch": 2.758481012658228, "grad_norm": 0.2919583723346383, "learning_rate": 1.974459290568053e-05, "loss": 0.3301, "step": 681 }, { "epoch": 2.76253164556962, "grad_norm": 0.26923994403331125, "learning_rate": 1.968783996385397e-05, "loss": 0.3285, "step": 682 }, { "epoch": 2.7665822784810126, "grad_norm": 0.2717407634619507, "learning_rate": 1.963108953612143e-05, "loss": 0.3204, "step": 683 }, { "epoch": 2.770632911392405, "grad_norm": 0.2745736793564748, "learning_rate": 1.9574342079543056e-05, "loss": 0.3296, "step": 684 }, { "epoch": 2.7746835443037976, "grad_norm": 0.2880212952115748, "learning_rate": 1.9517598051155046e-05, "loss": 0.326, "step": 685 }, { "epoch": 2.77873417721519, "grad_norm": 0.2648610311113754, "learning_rate": 1.9460857907966025e-05, "loss": 0.3306, "step": 686 }, { "epoch": 2.782784810126582, "grad_norm": 0.35454450017588596, "learning_rate": 1.9404122106953285e-05, "loss": 0.3326, "step": 687 }, { "epoch": 2.7868354430379747, "grad_norm": 0.2649448965077903, "learning_rate": 1.9347391105059176e-05, "loss": 0.3221, "step": 688 }, { "epoch": 2.790886075949367, "grad_norm": 0.2614487777160385, "learning_rate": 1.92906653591874e-05, "loss": 0.3329, "step": 689 }, { "epoch": 2.7949367088607593, "grad_norm": 0.28130191197895366, "learning_rate": 1.9233945326199295e-05, "loss": 0.3411, "step": 690 }, { "epoch": 2.798987341772152, "grad_norm": 0.25461726577169475, "learning_rate": 1.917723146291022e-05, "loss": 0.3299, "step": 691 }, { "epoch": 2.8030379746835443, "grad_norm": 0.2749163302027442, "learning_rate": 1.912052422608584e-05, "loss": 0.3361, "step": 692 }, { "epoch": 2.807088607594937, "grad_norm": 0.26110475153010004, "learning_rate": 1.9063824072438428e-05, "loss": 0.3328, "step": 693 }, { "epoch": 2.8111392405063294, "grad_norm": 0.2672339082669794, "learning_rate": 1.9007131458623246e-05, "loss": 0.3355, "step": 694 }, { "epoch": 2.8151898734177214, "grad_norm": 0.29684288642933704, "learning_rate": 1.895044684123479e-05, "loss": 0.3388, "step": 695 }, { "epoch": 2.819240506329114, "grad_norm": 0.26357468365027525, "learning_rate": 1.8893770676803194e-05, "loss": 0.3299, "step": 696 }, { "epoch": 2.8232911392405065, "grad_norm": 0.28450280408290873, "learning_rate": 1.8837103421790486e-05, "loss": 0.3228, "step": 697 }, { "epoch": 2.8273417721518985, "grad_norm": 0.2756279605460319, "learning_rate": 1.8780445532586952e-05, "loss": 0.3347, "step": 698 }, { "epoch": 2.831392405063291, "grad_norm": 0.28727294309310475, "learning_rate": 1.872379746550743e-05, "loss": 0.3276, "step": 699 }, { "epoch": 2.8354430379746836, "grad_norm": 0.262665719019157, "learning_rate": 1.866715967678769e-05, "loss": 0.3263, "step": 700 }, { "epoch": 2.839493670886076, "grad_norm": 0.25679671920250785, "learning_rate": 1.861053262258067e-05, "loss": 0.3254, "step": 701 }, { "epoch": 2.8435443037974686, "grad_norm": 0.25262297959462005, "learning_rate": 1.8553916758952897e-05, "loss": 0.3409, "step": 702 }, { "epoch": 2.8475949367088607, "grad_norm": 0.26484223809758395, "learning_rate": 1.8497312541880735e-05, "loss": 0.3387, "step": 703 }, { "epoch": 2.851645569620253, "grad_norm": 0.24669419080595006, "learning_rate": 1.8440720427246786e-05, "loss": 0.3417, "step": 704 }, { "epoch": 2.8556962025316457, "grad_norm": 0.27348107541598693, "learning_rate": 1.8384140870836157e-05, "loss": 0.3248, "step": 705 }, { "epoch": 2.8597468354430378, "grad_norm": 0.2304324723051282, "learning_rate": 1.8327574328332806e-05, "loss": 0.3238, "step": 706 }, { "epoch": 2.8637974683544303, "grad_norm": 0.2520767433159376, "learning_rate": 1.8271021255315906e-05, "loss": 0.3221, "step": 707 }, { "epoch": 2.867848101265823, "grad_norm": 0.2524194789180567, "learning_rate": 1.8214482107256117e-05, "loss": 0.3336, "step": 708 }, { "epoch": 2.8718987341772153, "grad_norm": 0.25774565116683784, "learning_rate": 1.8157957339511968e-05, "loss": 0.3302, "step": 709 }, { "epoch": 2.875949367088608, "grad_norm": 0.2882719061303316, "learning_rate": 1.8101447407326182e-05, "loss": 0.3463, "step": 710 }, { "epoch": 2.88, "grad_norm": 0.23793339313862766, "learning_rate": 1.8044952765821966e-05, "loss": 0.3324, "step": 711 }, { "epoch": 2.8840506329113924, "grad_norm": 0.25976021993159015, "learning_rate": 1.7988473869999407e-05, "loss": 0.3262, "step": 712 }, { "epoch": 2.888101265822785, "grad_norm": 0.2481666224307932, "learning_rate": 1.7932011174731764e-05, "loss": 0.3314, "step": 713 }, { "epoch": 2.892151898734177, "grad_norm": 0.27865411768669535, "learning_rate": 1.7875565134761817e-05, "loss": 0.3245, "step": 714 }, { "epoch": 2.8962025316455695, "grad_norm": 0.24208352183741302, "learning_rate": 1.7819136204698226e-05, "loss": 0.3355, "step": 715 }, { "epoch": 2.900253164556962, "grad_norm": 0.2698812892457925, "learning_rate": 1.776272483901182e-05, "loss": 0.3301, "step": 716 }, { "epoch": 2.9043037974683545, "grad_norm": 0.26418952008281893, "learning_rate": 1.7706331492031995e-05, "loss": 0.3285, "step": 717 }, { "epoch": 2.908354430379747, "grad_norm": 0.23138639419504592, "learning_rate": 1.764995661794301e-05, "loss": 0.3216, "step": 718 }, { "epoch": 2.912405063291139, "grad_norm": 0.26823526491082816, "learning_rate": 1.759360067078035e-05, "loss": 0.3292, "step": 719 }, { "epoch": 2.9164556962025316, "grad_norm": 0.2699781699086686, "learning_rate": 1.7537264104427064e-05, "loss": 0.3293, "step": 720 }, { "epoch": 2.920506329113924, "grad_norm": 0.3022491155835724, "learning_rate": 1.748094737261012e-05, "loss": 0.3255, "step": 721 }, { "epoch": 2.9245569620253162, "grad_norm": 0.27028146359986216, "learning_rate": 1.7424650928896726e-05, "loss": 0.3294, "step": 722 }, { "epoch": 2.9286075949367087, "grad_norm": 0.24986325459381997, "learning_rate": 1.7368375226690712e-05, "loss": 0.3383, "step": 723 }, { "epoch": 2.9326582278481013, "grad_norm": 0.270025870706655, "learning_rate": 1.731212071922883e-05, "loss": 0.3224, "step": 724 }, { "epoch": 2.9367088607594938, "grad_norm": 0.22832924396223206, "learning_rate": 1.7255887859577156e-05, "loss": 0.329, "step": 725 }, { "epoch": 2.9407594936708863, "grad_norm": 0.22575151052944425, "learning_rate": 1.7199677100627427e-05, "loss": 0.3228, "step": 726 }, { "epoch": 2.9448101265822784, "grad_norm": 0.2496443162807631, "learning_rate": 1.7143488895093343e-05, "loss": 0.3316, "step": 727 }, { "epoch": 2.948860759493671, "grad_norm": 0.22206185177185303, "learning_rate": 1.7087323695506994e-05, "loss": 0.3375, "step": 728 }, { "epoch": 2.9529113924050634, "grad_norm": 0.2340645878138451, "learning_rate": 1.7031181954215194e-05, "loss": 0.3164, "step": 729 }, { "epoch": 2.9569620253164555, "grad_norm": 0.2315280718801412, "learning_rate": 1.6975064123375788e-05, "loss": 0.3265, "step": 730 }, { "epoch": 2.961012658227848, "grad_norm": 0.23118339203307142, "learning_rate": 1.6918970654954084e-05, "loss": 0.3326, "step": 731 }, { "epoch": 2.9650632911392405, "grad_norm": 0.22107925624112848, "learning_rate": 1.686290200071915e-05, "loss": 0.3238, "step": 732 }, { "epoch": 2.969113924050633, "grad_norm": 0.21279339471363562, "learning_rate": 1.6806858612240234e-05, "loss": 0.328, "step": 733 }, { "epoch": 2.9731645569620255, "grad_norm": 0.2415312971288115, "learning_rate": 1.6750840940883078e-05, "loss": 0.3182, "step": 734 }, { "epoch": 2.9772151898734176, "grad_norm": 0.23967873451769908, "learning_rate": 1.6694849437806305e-05, "loss": 0.3301, "step": 735 }, { "epoch": 2.98126582278481, "grad_norm": 0.23895667300292725, "learning_rate": 1.663888455395778e-05, "loss": 0.3292, "step": 736 }, { "epoch": 2.9853164556962026, "grad_norm": 0.20970778483376715, "learning_rate": 1.6582946740070995e-05, "loss": 0.3156, "step": 737 }, { "epoch": 2.9893670886075947, "grad_norm": 0.22156802974682652, "learning_rate": 1.6527036446661396e-05, "loss": 0.3123, "step": 738 }, { "epoch": 2.993417721518987, "grad_norm": 0.30496018504632705, "learning_rate": 1.6471154124022818e-05, "loss": 0.3288, "step": 739 }, { "epoch": 2.9974683544303797, "grad_norm": 0.21694665942993954, "learning_rate": 1.6415300222223788e-05, "loss": 0.3132, "step": 740 }, { "epoch": 3.0015189873417722, "grad_norm": 0.25020531987426925, "learning_rate": 1.6359475191103958e-05, "loss": 0.3112, "step": 741 }, { "epoch": 3.0055696202531648, "grad_norm": 0.34623663448750974, "learning_rate": 1.6303679480270466e-05, "loss": 0.2808, "step": 742 }, { "epoch": 3.009620253164557, "grad_norm": 0.5991017905213688, "learning_rate": 1.624791353909428e-05, "loss": 0.284, "step": 743 }, { "epoch": 3.0136708860759494, "grad_norm": 0.35363220218607344, "learning_rate": 1.619217781670663e-05, "loss": 0.2861, "step": 744 }, { "epoch": 3.017721518987342, "grad_norm": 0.39063655003268, "learning_rate": 1.6136472761995373e-05, "loss": 0.2845, "step": 745 }, { "epoch": 3.0217721518987344, "grad_norm": 0.3045497878581031, "learning_rate": 1.608079882360134e-05, "loss": 0.2712, "step": 746 }, { "epoch": 3.0258227848101265, "grad_norm": 0.37456484732254736, "learning_rate": 1.60251564499148e-05, "loss": 0.2847, "step": 747 }, { "epoch": 3.029873417721519, "grad_norm": 0.33129559156065114, "learning_rate": 1.596954608907176e-05, "loss": 0.2814, "step": 748 }, { "epoch": 3.0339240506329115, "grad_norm": 0.3441321902552517, "learning_rate": 1.591396818895043e-05, "loss": 0.2733, "step": 749 }, { "epoch": 3.037974683544304, "grad_norm": 0.3250503520462677, "learning_rate": 1.585842319716759e-05, "loss": 0.2836, "step": 750 }, { "epoch": 3.042025316455696, "grad_norm": 0.33111783575811754, "learning_rate": 1.5802911561074944e-05, "loss": 0.2831, "step": 751 }, { "epoch": 3.0460759493670886, "grad_norm": 0.27469747547328643, "learning_rate": 1.5747433727755595e-05, "loss": 0.2854, "step": 752 }, { "epoch": 3.050126582278481, "grad_norm": 0.31148006698367614, "learning_rate": 1.5691990144020376e-05, "loss": 0.273, "step": 753 }, { "epoch": 3.0541772151898736, "grad_norm": 0.280906755550277, "learning_rate": 1.5636581256404297e-05, "loss": 0.2877, "step": 754 }, { "epoch": 3.0582278481012657, "grad_norm": 0.2841351091657476, "learning_rate": 1.558120751116291e-05, "loss": 0.2727, "step": 755 }, { "epoch": 3.062278481012658, "grad_norm": 0.297425479016787, "learning_rate": 1.552586935426876e-05, "loss": 0.2684, "step": 756 }, { "epoch": 3.0663291139240507, "grad_norm": 0.29563007148378784, "learning_rate": 1.547056723140774e-05, "loss": 0.2775, "step": 757 }, { "epoch": 3.0703797468354432, "grad_norm": 0.2778709561337934, "learning_rate": 1.5415301587975565e-05, "loss": 0.2805, "step": 758 }, { "epoch": 3.0744303797468353, "grad_norm": 0.25096984976788667, "learning_rate": 1.536007286907411e-05, "loss": 0.2782, "step": 759 }, { "epoch": 3.078481012658228, "grad_norm": 0.3037424978891564, "learning_rate": 1.5304881519507896e-05, "loss": 0.2794, "step": 760 }, { "epoch": 3.0825316455696203, "grad_norm": 0.2625056024423413, "learning_rate": 1.5249727983780453e-05, "loss": 0.2699, "step": 761 }, { "epoch": 3.086582278481013, "grad_norm": 0.2928812406060297, "learning_rate": 1.5194612706090786e-05, "loss": 0.2806, "step": 762 }, { "epoch": 3.090632911392405, "grad_norm": 0.28278662847788827, "learning_rate": 1.5139536130329771e-05, "loss": 0.2832, "step": 763 }, { "epoch": 3.0946835443037974, "grad_norm": 0.2774619670848259, "learning_rate": 1.508449870007656e-05, "loss": 0.2786, "step": 764 }, { "epoch": 3.09873417721519, "grad_norm": 0.3146415190735293, "learning_rate": 1.5029500858595056e-05, "loss": 0.2815, "step": 765 }, { "epoch": 3.1027848101265825, "grad_norm": 0.24695874971150703, "learning_rate": 1.4974543048830328e-05, "loss": 0.2775, "step": 766 }, { "epoch": 3.1068354430379745, "grad_norm": 0.313363256252527, "learning_rate": 1.4919625713405e-05, "loss": 0.2856, "step": 767 }, { "epoch": 3.110886075949367, "grad_norm": 0.26860318167174824, "learning_rate": 1.4864749294615756e-05, "loss": 0.2812, "step": 768 }, { "epoch": 3.1149367088607596, "grad_norm": 0.2746500118812425, "learning_rate": 1.4809914234429716e-05, "loss": 0.2797, "step": 769 }, { "epoch": 3.118987341772152, "grad_norm": 0.28370960321021954, "learning_rate": 1.4755120974480923e-05, "loss": 0.2773, "step": 770 }, { "epoch": 3.123037974683544, "grad_norm": 0.26113768661350545, "learning_rate": 1.4700369956066771e-05, "loss": 0.2791, "step": 771 }, { "epoch": 3.1270886075949367, "grad_norm": 0.2571290557074788, "learning_rate": 1.4645661620144413e-05, "loss": 0.2839, "step": 772 }, { "epoch": 3.131139240506329, "grad_norm": 0.2514995169604917, "learning_rate": 1.4590996407327284e-05, "loss": 0.2818, "step": 773 }, { "epoch": 3.1351898734177217, "grad_norm": 0.24023765927636767, "learning_rate": 1.4536374757881487e-05, "loss": 0.2846, "step": 774 }, { "epoch": 3.1392405063291138, "grad_norm": 0.25897196207325723, "learning_rate": 1.4481797111722271e-05, "loss": 0.2936, "step": 775 }, { "epoch": 3.1432911392405063, "grad_norm": 0.2298827806131259, "learning_rate": 1.4427263908410507e-05, "loss": 0.2749, "step": 776 }, { "epoch": 3.147341772151899, "grad_norm": 0.24839067137643653, "learning_rate": 1.4372775587149108e-05, "loss": 0.2758, "step": 777 }, { "epoch": 3.1513924050632913, "grad_norm": 0.20781706945559958, "learning_rate": 1.4318332586779522e-05, "loss": 0.2643, "step": 778 }, { "epoch": 3.1554430379746834, "grad_norm": 0.23105932151852587, "learning_rate": 1.4263935345778202e-05, "loss": 0.273, "step": 779 }, { "epoch": 3.159493670886076, "grad_norm": 0.20484275635623228, "learning_rate": 1.420958430225303e-05, "loss": 0.2728, "step": 780 }, { "epoch": 3.1635443037974684, "grad_norm": 0.2216538130955399, "learning_rate": 1.415527989393985e-05, "loss": 0.2883, "step": 781 }, { "epoch": 3.167594936708861, "grad_norm": 0.2217034804160841, "learning_rate": 1.410102255819891e-05, "loss": 0.2778, "step": 782 }, { "epoch": 3.171645569620253, "grad_norm": 0.21841701524173282, "learning_rate": 1.404681273201131e-05, "loss": 0.2806, "step": 783 }, { "epoch": 3.1756962025316455, "grad_norm": 0.21784074884574933, "learning_rate": 1.399265085197556e-05, "loss": 0.2808, "step": 784 }, { "epoch": 3.179746835443038, "grad_norm": 0.8030181575953341, "learning_rate": 1.393853735430398e-05, "loss": 0.2802, "step": 785 }, { "epoch": 3.1837974683544306, "grad_norm": 0.21468647974664054, "learning_rate": 1.3884472674819246e-05, "loss": 0.2695, "step": 786 }, { "epoch": 3.1878481012658226, "grad_norm": 0.27507676334470205, "learning_rate": 1.3830457248950864e-05, "loss": 0.267, "step": 787 }, { "epoch": 3.191898734177215, "grad_norm": 0.24008429512003412, "learning_rate": 1.377649151173163e-05, "loss": 0.2662, "step": 788 }, { "epoch": 3.1959493670886077, "grad_norm": 0.2578017685383876, "learning_rate": 1.3722575897794181e-05, "loss": 0.273, "step": 789 }, { "epoch": 3.2, "grad_norm": 0.24013283612547917, "learning_rate": 1.3668710841367472e-05, "loss": 0.2796, "step": 790 }, { "epoch": 3.2040506329113922, "grad_norm": 0.23785422145319832, "learning_rate": 1.361489677627324e-05, "loss": 0.2868, "step": 791 }, { "epoch": 3.2081012658227848, "grad_norm": 0.22680809569620566, "learning_rate": 1.3561134135922585e-05, "loss": 0.28, "step": 792 }, { "epoch": 3.2121518987341773, "grad_norm": 0.2323795290709833, "learning_rate": 1.350742335331241e-05, "loss": 0.2726, "step": 793 }, { "epoch": 3.21620253164557, "grad_norm": 0.22776998433792428, "learning_rate": 1.345376486102198e-05, "loss": 0.2845, "step": 794 }, { "epoch": 3.220253164556962, "grad_norm": 0.2438976091820014, "learning_rate": 1.3400159091209414e-05, "loss": 0.276, "step": 795 }, { "epoch": 3.2243037974683544, "grad_norm": 0.21942712096883152, "learning_rate": 1.3346606475608216e-05, "loss": 0.287, "step": 796 }, { "epoch": 3.228354430379747, "grad_norm": 0.33033539191594125, "learning_rate": 1.3293107445523781e-05, "loss": 0.2713, "step": 797 }, { "epoch": 3.2324050632911394, "grad_norm": 0.22117224821892703, "learning_rate": 1.3239662431829949e-05, "loss": 0.2825, "step": 798 }, { "epoch": 3.2364556962025315, "grad_norm": 0.23187645159814993, "learning_rate": 1.3186271864965509e-05, "loss": 0.2779, "step": 799 }, { "epoch": 3.240506329113924, "grad_norm": 0.22904881619079176, "learning_rate": 1.3132936174930756e-05, "loss": 0.2772, "step": 800 }, { "epoch": 3.2445569620253165, "grad_norm": 0.2310091268205741, "learning_rate": 1.3079655791283995e-05, "loss": 0.2774, "step": 801 }, { "epoch": 3.248607594936709, "grad_norm": 0.23185232231057232, "learning_rate": 1.3026431143138108e-05, "loss": 0.29, "step": 802 }, { "epoch": 3.252658227848101, "grad_norm": 0.2479966688927299, "learning_rate": 1.2973262659157114e-05, "loss": 0.2726, "step": 803 }, { "epoch": 3.2567088607594936, "grad_norm": 0.25785829642944, "learning_rate": 1.2920150767552651e-05, "loss": 0.298, "step": 804 }, { "epoch": 3.260759493670886, "grad_norm": 0.2356846105966214, "learning_rate": 1.2867095896080607e-05, "loss": 0.2817, "step": 805 }, { "epoch": 3.2648101265822786, "grad_norm": 0.23047339170238892, "learning_rate": 1.2814098472037612e-05, "loss": 0.2718, "step": 806 }, { "epoch": 3.2688607594936707, "grad_norm": 0.2509913485794074, "learning_rate": 1.276115892225764e-05, "loss": 0.2846, "step": 807 }, { "epoch": 3.2729113924050632, "grad_norm": 0.24876646859293666, "learning_rate": 1.2708277673108555e-05, "loss": 0.2863, "step": 808 }, { "epoch": 3.2769620253164558, "grad_norm": 0.21939068488728927, "learning_rate": 1.2655455150488649e-05, "loss": 0.2735, "step": 809 }, { "epoch": 3.2810126582278483, "grad_norm": 0.2574820324122498, "learning_rate": 1.2602691779823272e-05, "loss": 0.2832, "step": 810 }, { "epoch": 3.2850632911392403, "grad_norm": 0.23399418543212633, "learning_rate": 1.2549987986061355e-05, "loss": 0.2861, "step": 811 }, { "epoch": 3.289113924050633, "grad_norm": 0.24528408502268756, "learning_rate": 1.2497344193672005e-05, "loss": 0.2866, "step": 812 }, { "epoch": 3.2931645569620254, "grad_norm": 0.2693211924353079, "learning_rate": 1.2444760826641092e-05, "loss": 0.2849, "step": 813 }, { "epoch": 3.297215189873418, "grad_norm": 0.2309441689950126, "learning_rate": 1.2392238308467817e-05, "loss": 0.2812, "step": 814 }, { "epoch": 3.30126582278481, "grad_norm": 0.2599830099353368, "learning_rate": 1.2339777062161326e-05, "loss": 0.2834, "step": 815 }, { "epoch": 3.3053164556962025, "grad_norm": 0.21722254471552002, "learning_rate": 1.2287377510237293e-05, "loss": 0.2787, "step": 816 }, { "epoch": 3.309367088607595, "grad_norm": 0.20304472137008447, "learning_rate": 1.2235040074714488e-05, "loss": 0.2774, "step": 817 }, { "epoch": 3.3134177215189875, "grad_norm": 0.2569724034422125, "learning_rate": 1.2182765177111434e-05, "loss": 0.2782, "step": 818 }, { "epoch": 3.3174683544303796, "grad_norm": 0.21758812170560193, "learning_rate": 1.213055323844297e-05, "loss": 0.2932, "step": 819 }, { "epoch": 3.321518987341772, "grad_norm": 0.24366807301434973, "learning_rate": 1.2078404679216864e-05, "loss": 0.2814, "step": 820 }, { "epoch": 3.3255696202531646, "grad_norm": 0.6210532934336018, "learning_rate": 1.2026319919430458e-05, "loss": 0.2885, "step": 821 }, { "epoch": 3.329620253164557, "grad_norm": 0.21510674537740332, "learning_rate": 1.1974299378567227e-05, "loss": 0.2843, "step": 822 }, { "epoch": 3.333670886075949, "grad_norm": 0.219662007526545, "learning_rate": 1.1922343475593462e-05, "loss": 0.2777, "step": 823 }, { "epoch": 3.3377215189873417, "grad_norm": 0.22250630538704455, "learning_rate": 1.187045262895488e-05, "loss": 0.2832, "step": 824 }, { "epoch": 3.3417721518987342, "grad_norm": 0.2290625276228848, "learning_rate": 1.1818627256573203e-05, "loss": 0.2824, "step": 825 }, { "epoch": 3.3458227848101267, "grad_norm": 0.2714641446297896, "learning_rate": 1.1766867775842864e-05, "loss": 0.2853, "step": 826 }, { "epoch": 3.349873417721519, "grad_norm": 0.21545582194490445, "learning_rate": 1.1715174603627615e-05, "loss": 0.2758, "step": 827 }, { "epoch": 3.3539240506329113, "grad_norm": 0.24717828278458895, "learning_rate": 1.1663548156257147e-05, "loss": 0.2842, "step": 828 }, { "epoch": 3.357974683544304, "grad_norm": 0.20609129578439525, "learning_rate": 1.161198884952377e-05, "loss": 0.2832, "step": 829 }, { "epoch": 3.3620253164556964, "grad_norm": 0.22413641040949572, "learning_rate": 1.1560497098679056e-05, "loss": 0.2761, "step": 830 }, { "epoch": 3.3660759493670884, "grad_norm": 0.23071756875672916, "learning_rate": 1.1509073318430479e-05, "loss": 0.2881, "step": 831 }, { "epoch": 3.370126582278481, "grad_norm": 0.21935720421842325, "learning_rate": 1.1457717922938116e-05, "loss": 0.2808, "step": 832 }, { "epoch": 3.3741772151898735, "grad_norm": 0.21445462867266452, "learning_rate": 1.1406431325811233e-05, "loss": 0.2745, "step": 833 }, { "epoch": 3.378227848101266, "grad_norm": 0.24010799075003048, "learning_rate": 1.135521394010506e-05, "loss": 0.2839, "step": 834 }, { "epoch": 3.382278481012658, "grad_norm": 0.2066502831281872, "learning_rate": 1.1304066178317367e-05, "loss": 0.2653, "step": 835 }, { "epoch": 3.3863291139240506, "grad_norm": 0.2428553301067903, "learning_rate": 1.1252988452385199e-05, "loss": 0.2847, "step": 836 }, { "epoch": 3.390379746835443, "grad_norm": 0.21027566506998357, "learning_rate": 1.1201981173681536e-05, "loss": 0.2801, "step": 837 }, { "epoch": 3.3944303797468356, "grad_norm": 0.23340451895005304, "learning_rate": 1.1151044753011991e-05, "loss": 0.2788, "step": 838 }, { "epoch": 3.3984810126582277, "grad_norm": 0.20538903082378446, "learning_rate": 1.1100179600611491e-05, "loss": 0.2691, "step": 839 }, { "epoch": 3.40253164556962, "grad_norm": 0.2179855159084755, "learning_rate": 1.1049386126140985e-05, "loss": 0.2688, "step": 840 }, { "epoch": 3.4065822784810127, "grad_norm": 0.22436490780485, "learning_rate": 1.0998664738684128e-05, "loss": 0.2821, "step": 841 }, { "epoch": 3.410632911392405, "grad_norm": 0.22899336509609322, "learning_rate": 1.0948015846744e-05, "loss": 0.2822, "step": 842 }, { "epoch": 3.4146835443037973, "grad_norm": 0.23722183175817038, "learning_rate": 1.0897439858239832e-05, "loss": 0.2946, "step": 843 }, { "epoch": 3.41873417721519, "grad_norm": 0.23742016976974528, "learning_rate": 1.0846937180503652e-05, "loss": 0.2756, "step": 844 }, { "epoch": 3.4227848101265823, "grad_norm": 0.20956416922507096, "learning_rate": 1.0796508220277117e-05, "loss": 0.2839, "step": 845 }, { "epoch": 3.426835443037975, "grad_norm": 0.23406350759064465, "learning_rate": 1.0746153383708107e-05, "loss": 0.2658, "step": 846 }, { "epoch": 3.430886075949367, "grad_norm": 0.21807185602377124, "learning_rate": 1.0695873076347579e-05, "loss": 0.2846, "step": 847 }, { "epoch": 3.4349367088607594, "grad_norm": 0.22161382163450977, "learning_rate": 1.0645667703146205e-05, "loss": 0.2842, "step": 848 }, { "epoch": 3.438987341772152, "grad_norm": 0.21806245258224127, "learning_rate": 1.0595537668451161e-05, "loss": 0.2815, "step": 849 }, { "epoch": 3.4430379746835444, "grad_norm": 0.20955364913671898, "learning_rate": 1.0545483376002854e-05, "loss": 0.2747, "step": 850 }, { "epoch": 3.4470886075949365, "grad_norm": 0.20152970626786296, "learning_rate": 1.0495505228931676e-05, "loss": 0.2819, "step": 851 }, { "epoch": 3.451139240506329, "grad_norm": 0.2153361194817364, "learning_rate": 1.044560362975474e-05, "loss": 0.2808, "step": 852 }, { "epoch": 3.4551898734177215, "grad_norm": 0.20274929803279257, "learning_rate": 1.0395778980372695e-05, "loss": 0.2874, "step": 853 }, { "epoch": 3.459240506329114, "grad_norm": 0.19798198752496748, "learning_rate": 1.0346031682066381e-05, "loss": 0.2823, "step": 854 }, { "epoch": 3.463291139240506, "grad_norm": 0.2121658069515071, "learning_rate": 1.0296362135493724e-05, "loss": 0.2819, "step": 855 }, { "epoch": 3.4673417721518986, "grad_norm": 0.2181585021380401, "learning_rate": 1.0246770740686422e-05, "loss": 0.2849, "step": 856 }, { "epoch": 3.471392405063291, "grad_norm": 0.20814626863960395, "learning_rate": 1.0197257897046743e-05, "loss": 0.2822, "step": 857 }, { "epoch": 3.4754430379746837, "grad_norm": 0.20927241507271546, "learning_rate": 1.014782400334433e-05, "loss": 0.2784, "step": 858 }, { "epoch": 3.479493670886076, "grad_norm": 0.20752806022861106, "learning_rate": 1.009846945771296e-05, "loss": 0.287, "step": 859 }, { "epoch": 3.4835443037974683, "grad_norm": 0.19886455404814965, "learning_rate": 1.0049194657647363e-05, "loss": 0.2752, "step": 860 }, { "epoch": 3.487594936708861, "grad_norm": 0.1984462313478483, "learning_rate": 1.0000000000000006e-05, "loss": 0.2871, "step": 861 }, { "epoch": 3.4916455696202533, "grad_norm": 0.20797556209313556, "learning_rate": 9.950885880977891e-06, "loss": 0.2767, "step": 862 }, { "epoch": 3.4956962025316454, "grad_norm": 0.21477248615250175, "learning_rate": 9.901852696139382e-06, "loss": 0.2902, "step": 863 }, { "epoch": 3.499746835443038, "grad_norm": 0.21019029795604546, "learning_rate": 9.852900840391027e-06, "loss": 0.2729, "step": 864 }, { "epoch": 3.5037974683544304, "grad_norm": 0.20591324110484044, "learning_rate": 9.804030707984313e-06, "loss": 0.2772, "step": 865 }, { "epoch": 3.507848101265823, "grad_norm": 0.23181814730836295, "learning_rate": 9.755242692512599e-06, "loss": 0.2948, "step": 866 }, { "epoch": 3.5118987341772154, "grad_norm": 0.20849795352650768, "learning_rate": 9.70653718690782e-06, "loss": 0.279, "step": 867 }, { "epoch": 3.5159493670886075, "grad_norm": 0.20569585419914313, "learning_rate": 9.657914583437454e-06, "loss": 0.2665, "step": 868 }, { "epoch": 3.52, "grad_norm": 0.2331149085668245, "learning_rate": 9.609375273701246e-06, "loss": 0.2823, "step": 869 }, { "epoch": 3.5240506329113925, "grad_norm": 0.20521282360955126, "learning_rate": 9.560919648628133e-06, "loss": 0.2776, "step": 870 }, { "epoch": 3.5281012658227846, "grad_norm": 0.20732685580288548, "learning_rate": 9.512548098473047e-06, "loss": 0.279, "step": 871 }, { "epoch": 3.532151898734177, "grad_norm": 0.21526808302657238, "learning_rate": 9.464261012813825e-06, "loss": 0.2676, "step": 872 }, { "epoch": 3.5362025316455696, "grad_norm": 0.21743212111654706, "learning_rate": 9.416058780547987e-06, "loss": 0.2812, "step": 873 }, { "epoch": 3.540253164556962, "grad_norm": 0.2557497837598477, "learning_rate": 9.367941789889714e-06, "loss": 0.2761, "step": 874 }, { "epoch": 3.5443037974683547, "grad_norm": 0.21533230591705574, "learning_rate": 9.319910428366607e-06, "loss": 0.2849, "step": 875 }, { "epoch": 3.5483544303797467, "grad_norm": 0.23032404006112758, "learning_rate": 9.271965082816667e-06, "loss": 0.2748, "step": 876 }, { "epoch": 3.5524050632911393, "grad_norm": 0.22650432040372223, "learning_rate": 9.224106139385111e-06, "loss": 0.2777, "step": 877 }, { "epoch": 3.5564556962025318, "grad_norm": 0.21599386871419943, "learning_rate": 9.176333983521291e-06, "loss": 0.284, "step": 878 }, { "epoch": 3.560506329113924, "grad_norm": 0.21962375172935417, "learning_rate": 9.12864899997558e-06, "loss": 0.2855, "step": 879 }, { "epoch": 3.5645569620253164, "grad_norm": 0.2167111591177128, "learning_rate": 9.08105157279628e-06, "loss": 0.2775, "step": 880 }, { "epoch": 3.568607594936709, "grad_norm": 0.20224097863502055, "learning_rate": 9.03354208532653e-06, "loss": 0.2849, "step": 881 }, { "epoch": 3.5726582278481014, "grad_norm": 0.20140332517841053, "learning_rate": 8.986120920201205e-06, "loss": 0.2806, "step": 882 }, { "epoch": 3.576708860759494, "grad_norm": 0.20852212701839992, "learning_rate": 8.938788459343852e-06, "loss": 0.2819, "step": 883 }, { "epoch": 3.580759493670886, "grad_norm": 0.22054777414291135, "learning_rate": 8.8915450839636e-06, "loss": 0.2772, "step": 884 }, { "epoch": 3.5848101265822785, "grad_norm": 0.24408590454175388, "learning_rate": 8.844391174552116e-06, "loss": 0.282, "step": 885 }, { "epoch": 3.588860759493671, "grad_norm": 0.2025414279108654, "learning_rate": 8.797327110880479e-06, "loss": 0.2751, "step": 886 }, { "epoch": 3.592911392405063, "grad_norm": 0.20237300917574153, "learning_rate": 8.750353271996206e-06, "loss": 0.2716, "step": 887 }, { "epoch": 3.5969620253164556, "grad_norm": 0.22060111254063744, "learning_rate": 8.703470036220132e-06, "loss": 0.2898, "step": 888 }, { "epoch": 3.601012658227848, "grad_norm": 0.20390766293305565, "learning_rate": 8.656677781143394e-06, "loss": 0.287, "step": 889 }, { "epoch": 3.6050632911392406, "grad_norm": 0.19565132563805046, "learning_rate": 8.609976883624377e-06, "loss": 0.2864, "step": 890 }, { "epoch": 3.609113924050633, "grad_norm": 0.21364129960485237, "learning_rate": 8.563367719785698e-06, "loss": 0.2828, "step": 891 }, { "epoch": 3.613164556962025, "grad_norm": 0.2101567060335429, "learning_rate": 8.516850665011138e-06, "loss": 0.2701, "step": 892 }, { "epoch": 3.6172151898734177, "grad_norm": 0.20149746964872067, "learning_rate": 8.47042609394269e-06, "loss": 0.2816, "step": 893 }, { "epoch": 3.6212658227848102, "grad_norm": 0.21645826894266043, "learning_rate": 8.424094380477432e-06, "loss": 0.2841, "step": 894 }, { "epoch": 3.6253164556962023, "grad_norm": 0.22475713811942938, "learning_rate": 8.37785589776465e-06, "loss": 0.2777, "step": 895 }, { "epoch": 3.629367088607595, "grad_norm": 0.2061574554836814, "learning_rate": 8.331711018202694e-06, "loss": 0.2816, "step": 896 }, { "epoch": 3.6334177215189873, "grad_norm": 0.2093126826253773, "learning_rate": 8.285660113436104e-06, "loss": 0.2904, "step": 897 }, { "epoch": 3.63746835443038, "grad_norm": 0.19091351169525062, "learning_rate": 8.239703554352527e-06, "loss": 0.287, "step": 898 }, { "epoch": 3.6415189873417724, "grad_norm": 0.2012164534022884, "learning_rate": 8.193841711079775e-06, "loss": 0.2722, "step": 899 }, { "epoch": 3.6455696202531644, "grad_norm": 0.24711644744179737, "learning_rate": 8.148074952982828e-06, "loss": 0.2739, "step": 900 }, { "epoch": 3.649620253164557, "grad_norm": 0.17894317984832533, "learning_rate": 8.102403648660859e-06, "loss": 0.2786, "step": 901 }, { "epoch": 3.6536708860759495, "grad_norm": 0.21030744405098956, "learning_rate": 8.056828165944282e-06, "loss": 0.2753, "step": 902 }, { "epoch": 3.6577215189873415, "grad_norm": 0.19628748074038482, "learning_rate": 8.011348871891762e-06, "loss": 0.2834, "step": 903 }, { "epoch": 3.661772151898734, "grad_norm": 0.20263067796832013, "learning_rate": 7.965966132787287e-06, "loss": 0.2786, "step": 904 }, { "epoch": 3.6658227848101266, "grad_norm": 0.20862439909689337, "learning_rate": 7.920680314137189e-06, "loss": 0.2839, "step": 905 }, { "epoch": 3.669873417721519, "grad_norm": 0.1998569422537313, "learning_rate": 7.875491780667246e-06, "loss": 0.2833, "step": 906 }, { "epoch": 3.6739240506329116, "grad_norm": 0.20471806518399324, "learning_rate": 7.830400896319667e-06, "loss": 0.2865, "step": 907 }, { "epoch": 3.6779746835443037, "grad_norm": 0.19870378379429707, "learning_rate": 7.785408024250259e-06, "loss": 0.2747, "step": 908 }, { "epoch": 3.682025316455696, "grad_norm": 0.21382012170664727, "learning_rate": 7.74051352682542e-06, "loss": 0.2736, "step": 909 }, { "epoch": 3.6860759493670887, "grad_norm": 0.20809995820083355, "learning_rate": 7.695717765619257e-06, "loss": 0.2738, "step": 910 }, { "epoch": 3.690126582278481, "grad_norm": 0.1929117470795191, "learning_rate": 7.651021101410673e-06, "loss": 0.2786, "step": 911 }, { "epoch": 3.6941772151898733, "grad_norm": 0.19819844220467653, "learning_rate": 7.606423894180464e-06, "loss": 0.2787, "step": 912 }, { "epoch": 3.698227848101266, "grad_norm": 0.20716190873707743, "learning_rate": 7.56192650310839e-06, "loss": 0.2767, "step": 913 }, { "epoch": 3.7022784810126583, "grad_norm": 0.20076547225181574, "learning_rate": 7.517529286570349e-06, "loss": 0.2767, "step": 914 }, { "epoch": 3.706329113924051, "grad_norm": 0.21950288736073262, "learning_rate": 7.473232602135387e-06, "loss": 0.281, "step": 915 }, { "epoch": 3.710379746835443, "grad_norm": 0.19741967055910806, "learning_rate": 7.429036806562935e-06, "loss": 0.2777, "step": 916 }, { "epoch": 3.7144303797468354, "grad_norm": 0.18693307047894414, "learning_rate": 7.3849422557998455e-06, "loss": 0.2834, "step": 917 }, { "epoch": 3.718481012658228, "grad_norm": 0.20507839210574294, "learning_rate": 7.340949304977567e-06, "loss": 0.2864, "step": 918 }, { "epoch": 3.72253164556962, "grad_norm": 0.20875131646954664, "learning_rate": 7.297058308409282e-06, "loss": 0.2733, "step": 919 }, { "epoch": 3.7265822784810125, "grad_norm": 0.19298566897813818, "learning_rate": 7.25326961958704e-06, "loss": 0.264, "step": 920 }, { "epoch": 3.730632911392405, "grad_norm": 0.2066156014534137, "learning_rate": 7.209583591178921e-06, "loss": 0.2772, "step": 921 }, { "epoch": 3.7346835443037976, "grad_norm": 0.20903127232838198, "learning_rate": 7.1660005750261925e-06, "loss": 0.2753, "step": 922 }, { "epoch": 3.73873417721519, "grad_norm": 0.19557547432640326, "learning_rate": 7.1225209221404765e-06, "loss": 0.2889, "step": 923 }, { "epoch": 3.742784810126582, "grad_norm": 0.19304524034928558, "learning_rate": 7.079144982700909e-06, "loss": 0.2828, "step": 924 }, { "epoch": 3.7468354430379747, "grad_norm": 0.19992295547218517, "learning_rate": 7.0358731060513695e-06, "loss": 0.2843, "step": 925 }, { "epoch": 3.750886075949367, "grad_norm": 0.20202110550535052, "learning_rate": 6.99270564069757e-06, "loss": 0.2733, "step": 926 }, { "epoch": 3.7549367088607593, "grad_norm": 0.2025941469467876, "learning_rate": 6.949642934304375e-06, "loss": 0.2696, "step": 927 }, { "epoch": 3.7589873417721518, "grad_norm": 0.20313884406580657, "learning_rate": 6.906685333692871e-06, "loss": 0.2854, "step": 928 }, { "epoch": 3.7630379746835443, "grad_norm": 0.19788295717695495, "learning_rate": 6.86383318483769e-06, "loss": 0.2888, "step": 929 }, { "epoch": 3.767088607594937, "grad_norm": 0.19372295138036003, "learning_rate": 6.821086832864139e-06, "loss": 0.2828, "step": 930 }, { "epoch": 3.7711392405063293, "grad_norm": 0.2196520284256622, "learning_rate": 6.77844662204546e-06, "loss": 0.2795, "step": 931 }, { "epoch": 3.7751898734177214, "grad_norm": 0.19769885074065532, "learning_rate": 6.7359128958000455e-06, "loss": 0.2715, "step": 932 }, { "epoch": 3.779240506329114, "grad_norm": 0.19209234821682725, "learning_rate": 6.693485996688695e-06, "loss": 0.2839, "step": 933 }, { "epoch": 3.7832911392405064, "grad_norm": 0.193230563247039, "learning_rate": 6.651166266411801e-06, "loss": 0.2685, "step": 934 }, { "epoch": 3.7873417721518985, "grad_norm": 0.2305776062753974, "learning_rate": 6.6089540458066725e-06, "loss": 0.2766, "step": 935 }, { "epoch": 3.791392405063291, "grad_norm": 0.19180536252772262, "learning_rate": 6.566849674844711e-06, "loss": 0.2794, "step": 936 }, { "epoch": 3.7954430379746835, "grad_norm": 0.19678709917398005, "learning_rate": 6.524853492628747e-06, "loss": 0.2792, "step": 937 }, { "epoch": 3.799493670886076, "grad_norm": 0.20431693127840256, "learning_rate": 6.4829658373902536e-06, "loss": 0.2807, "step": 938 }, { "epoch": 3.8035443037974686, "grad_norm": 0.20473689056287275, "learning_rate": 6.441187046486648e-06, "loss": 0.2782, "step": 939 }, { "epoch": 3.8075949367088606, "grad_norm": 0.20965588499968188, "learning_rate": 6.399517456398567e-06, "loss": 0.2802, "step": 940 }, { "epoch": 3.811645569620253, "grad_norm": 0.2187153530497492, "learning_rate": 6.357957402727164e-06, "loss": 0.278, "step": 941 }, { "epoch": 3.8156962025316457, "grad_norm": 0.20596526431412093, "learning_rate": 6.316507220191395e-06, "loss": 0.282, "step": 942 }, { "epoch": 3.8197468354430377, "grad_norm": 0.2010317648618034, "learning_rate": 6.275167242625331e-06, "loss": 0.2875, "step": 943 }, { "epoch": 3.8237974683544302, "grad_norm": 0.19149000906257907, "learning_rate": 6.233937802975471e-06, "loss": 0.2679, "step": 944 }, { "epoch": 3.8278481012658228, "grad_norm": 0.20927508022624924, "learning_rate": 6.192819233298046e-06, "loss": 0.2807, "step": 945 }, { "epoch": 3.8318987341772153, "grad_norm": 0.23020200253961035, "learning_rate": 6.151811864756383e-06, "loss": 0.2762, "step": 946 }, { "epoch": 3.835949367088608, "grad_norm": 0.20079525454402508, "learning_rate": 6.1109160276181655e-06, "loss": 0.2771, "step": 947 }, { "epoch": 3.84, "grad_norm": 0.19549329783802222, "learning_rate": 6.070132051252868e-06, "loss": 0.2851, "step": 948 }, { "epoch": 3.8440506329113924, "grad_norm": 0.21515017986013485, "learning_rate": 6.0294602641290034e-06, "loss": 0.2803, "step": 949 }, { "epoch": 3.848101265822785, "grad_norm": 0.1989246593455719, "learning_rate": 5.988900993811575e-06, "loss": 0.2777, "step": 950 }, { "epoch": 3.852151898734177, "grad_norm": 0.209200875825263, "learning_rate": 5.948454566959363e-06, "loss": 0.2744, "step": 951 }, { "epoch": 3.8562025316455695, "grad_norm": 0.20463385206075316, "learning_rate": 5.908121309322328e-06, "loss": 0.2703, "step": 952 }, { "epoch": 3.860253164556962, "grad_norm": 0.20430321638127266, "learning_rate": 5.867901545738976e-06, "loss": 0.2796, "step": 953 }, { "epoch": 3.8643037974683545, "grad_norm": 0.19226872654602634, "learning_rate": 5.827795600133774e-06, "loss": 0.2909, "step": 954 }, { "epoch": 3.868354430379747, "grad_norm": 0.20517122286709968, "learning_rate": 5.787803795514466e-06, "loss": 0.2805, "step": 955 }, { "epoch": 3.872405063291139, "grad_norm": 0.19386002616150222, "learning_rate": 5.747926453969576e-06, "loss": 0.284, "step": 956 }, { "epoch": 3.8764556962025316, "grad_norm": 0.2103078548228791, "learning_rate": 5.708163896665708e-06, "loss": 0.2828, "step": 957 }, { "epoch": 3.880506329113924, "grad_norm": 0.2157042812080511, "learning_rate": 5.668516443845047e-06, "loss": 0.2856, "step": 958 }, { "epoch": 3.884556962025316, "grad_norm": 0.18651677042597797, "learning_rate": 5.6289844148227225e-06, "loss": 0.2866, "step": 959 }, { "epoch": 3.8886075949367087, "grad_norm": 0.1956346071720028, "learning_rate": 5.5895681279842615e-06, "loss": 0.2817, "step": 960 }, { "epoch": 3.8926582278481012, "grad_norm": 0.21630635613332375, "learning_rate": 5.550267900783019e-06, "loss": 0.2846, "step": 961 }, { "epoch": 3.8967088607594937, "grad_norm": 0.19058752988329603, "learning_rate": 5.511084049737623e-06, "loss": 0.2743, "step": 962 }, { "epoch": 3.9007594936708863, "grad_norm": 0.1950031262319906, "learning_rate": 5.4720168904294215e-06, "loss": 0.2768, "step": 963 }, { "epoch": 3.9048101265822783, "grad_norm": 0.2030209645428474, "learning_rate": 5.433066737499948e-06, "loss": 0.2823, "step": 964 }, { "epoch": 3.908860759493671, "grad_norm": 0.21266400956376602, "learning_rate": 5.394233904648376e-06, "loss": 0.2845, "step": 965 }, { "epoch": 3.9129113924050634, "grad_norm": 0.1819243550174548, "learning_rate": 5.355518704628997e-06, "loss": 0.2811, "step": 966 }, { "epoch": 3.9169620253164554, "grad_norm": 0.18698693235586455, "learning_rate": 5.316921449248731e-06, "loss": 0.2663, "step": 967 }, { "epoch": 3.921012658227848, "grad_norm": 0.21293834695848157, "learning_rate": 5.278442449364538e-06, "loss": 0.2866, "step": 968 }, { "epoch": 3.9250632911392405, "grad_norm": 0.19256984780019168, "learning_rate": 5.240082014881016e-06, "loss": 0.2884, "step": 969 }, { "epoch": 3.929113924050633, "grad_norm": 0.18803725297106622, "learning_rate": 5.201840454747822e-06, "loss": 0.2777, "step": 970 }, { "epoch": 3.9331645569620255, "grad_norm": 0.2043798313179755, "learning_rate": 5.163718076957223e-06, "loss": 0.2888, "step": 971 }, { "epoch": 3.9372151898734176, "grad_norm": 0.19766721411441818, "learning_rate": 5.125715188541609e-06, "loss": 0.2715, "step": 972 }, { "epoch": 3.94126582278481, "grad_norm": 0.17662886764595137, "learning_rate": 5.087832095571021e-06, "loss": 0.2793, "step": 973 }, { "epoch": 3.9453164556962026, "grad_norm": 0.18770153117113855, "learning_rate": 5.0500691031506766e-06, "loss": 0.2864, "step": 974 }, { "epoch": 3.9493670886075947, "grad_norm": 0.20737479591224847, "learning_rate": 5.01242651541854e-06, "loss": 0.2791, "step": 975 }, { "epoch": 3.953417721518987, "grad_norm": 0.1880497337922562, "learning_rate": 4.974904635542815e-06, "loss": 0.2715, "step": 976 }, { "epoch": 3.9574683544303797, "grad_norm": 0.18111747927237415, "learning_rate": 4.937503765719582e-06, "loss": 0.2788, "step": 977 }, { "epoch": 3.961518987341772, "grad_norm": 0.20652138244581872, "learning_rate": 4.900224207170299e-06, "loss": 0.2777, "step": 978 }, { "epoch": 3.9655696202531647, "grad_norm": 0.19461137649764065, "learning_rate": 4.8630662601394065e-06, "loss": 0.2815, "step": 979 }, { "epoch": 3.969620253164557, "grad_norm": 0.19719107829902663, "learning_rate": 4.8260302238918995e-06, "loss": 0.2754, "step": 980 }, { "epoch": 3.9736708860759493, "grad_norm": 0.19295481460369865, "learning_rate": 4.789116396710924e-06, "loss": 0.2739, "step": 981 }, { "epoch": 3.977721518987342, "grad_norm": 0.19920231488249582, "learning_rate": 4.752325075895368e-06, "loss": 0.2812, "step": 982 }, { "epoch": 3.981772151898734, "grad_norm": 0.20722233812548183, "learning_rate": 4.715656557757473e-06, "loss": 0.28, "step": 983 }, { "epoch": 3.9858227848101264, "grad_norm": 0.19585092891965264, "learning_rate": 4.679111137620442e-06, "loss": 0.2787, "step": 984 }, { "epoch": 3.989873417721519, "grad_norm": 0.20327881958660118, "learning_rate": 4.6426891098160585e-06, "loss": 0.2786, "step": 985 }, { "epoch": 3.9939240506329114, "grad_norm": 0.19816452437593624, "learning_rate": 4.6063907676823474e-06, "loss": 0.2804, "step": 986 }, { "epoch": 3.997974683544304, "grad_norm": 0.1898052516274343, "learning_rate": 4.570216403561141e-06, "loss": 0.2789, "step": 987 }, { "epoch": 4.002025316455696, "grad_norm": 0.23355462524752996, "learning_rate": 4.534166308795815e-06, "loss": 0.264, "step": 988 }, { "epoch": 4.006075949367089, "grad_norm": 0.2790306649777152, "learning_rate": 4.498240773728859e-06, "loss": 0.2409, "step": 989 }, { "epoch": 4.010126582278481, "grad_norm": 0.20933402671911225, "learning_rate": 4.462440087699609e-06, "loss": 0.2375, "step": 990 }, { "epoch": 4.014177215189873, "grad_norm": 0.37250331715155854, "learning_rate": 4.426764539041861e-06, "loss": 0.2473, "step": 991 }, { "epoch": 4.018227848101266, "grad_norm": 0.358154394304893, "learning_rate": 4.391214415081582e-06, "loss": 0.2396, "step": 992 }, { "epoch": 4.022278481012658, "grad_norm": 0.20229257078183216, "learning_rate": 4.355790002134579e-06, "loss": 0.2446, "step": 993 }, { "epoch": 4.02632911392405, "grad_norm": 0.3132094462288831, "learning_rate": 4.320491585504207e-06, "loss": 0.2393, "step": 994 }, { "epoch": 4.030379746835443, "grad_norm": 0.3343071128621538, "learning_rate": 4.2853194494790615e-06, "loss": 0.2361, "step": 995 }, { "epoch": 4.034430379746835, "grad_norm": 0.24103322315622314, "learning_rate": 4.250273877330691e-06, "loss": 0.2492, "step": 996 }, { "epoch": 4.038481012658228, "grad_norm": 0.20625474962828566, "learning_rate": 4.215355151311313e-06, "loss": 0.2495, "step": 997 }, { "epoch": 4.04253164556962, "grad_norm": 0.2583201947086298, "learning_rate": 4.180563552651542e-06, "loss": 0.2375, "step": 998 }, { "epoch": 4.046582278481012, "grad_norm": 0.29172707339474213, "learning_rate": 4.145899361558147e-06, "loss": 0.2497, "step": 999 }, { "epoch": 4.050632911392405, "grad_norm": 0.2234106743643072, "learning_rate": 4.111362857211738e-06, "loss": 0.2355, "step": 1000 }, { "epoch": 4.054683544303797, "grad_norm": 0.20427598761415977, "learning_rate": 4.076954317764592e-06, "loss": 0.2483, "step": 1001 }, { "epoch": 4.0587341772151895, "grad_norm": 0.2420869417449406, "learning_rate": 4.042674020338335e-06, "loss": 0.2424, "step": 1002 }, { "epoch": 4.062784810126582, "grad_norm": 0.23131296612056068, "learning_rate": 4.0085222410217835e-06, "loss": 0.2488, "step": 1003 }, { "epoch": 4.0668354430379745, "grad_norm": 0.307878416288998, "learning_rate": 3.974499254868674e-06, "loss": 0.2468, "step": 1004 }, { "epoch": 4.0708860759493675, "grad_norm": 0.20657793929309462, "learning_rate": 3.940605335895451e-06, "loss": 0.2394, "step": 1005 }, { "epoch": 4.0749367088607595, "grad_norm": 0.23573597365124846, "learning_rate": 3.90684075707908e-06, "loss": 0.2537, "step": 1006 }, { "epoch": 4.078987341772152, "grad_norm": 0.20940477572468658, "learning_rate": 3.8732057903548505e-06, "loss": 0.2534, "step": 1007 }, { "epoch": 4.083037974683545, "grad_norm": 0.1937094611241562, "learning_rate": 3.8397007066141375e-06, "loss": 0.2481, "step": 1008 }, { "epoch": 4.087088607594937, "grad_norm": 0.20142476409146776, "learning_rate": 3.806325775702304e-06, "loss": 0.2372, "step": 1009 }, { "epoch": 4.091139240506329, "grad_norm": 0.1968866359377713, "learning_rate": 3.773081266416434e-06, "loss": 0.2454, "step": 1010 }, { "epoch": 4.095189873417722, "grad_norm": 0.18436688847404226, "learning_rate": 3.739967446503245e-06, "loss": 0.2448, "step": 1011 }, { "epoch": 4.099240506329114, "grad_norm": 0.2597030146791785, "learning_rate": 3.706984582656894e-06, "loss": 0.2311, "step": 1012 }, { "epoch": 4.103291139240507, "grad_norm": 0.19057643519843517, "learning_rate": 3.6741329405168237e-06, "loss": 0.2344, "step": 1013 }, { "epoch": 4.107341772151899, "grad_norm": 0.20789367325686448, "learning_rate": 3.641412784665648e-06, "loss": 0.2325, "step": 1014 }, { "epoch": 4.111392405063291, "grad_norm": 0.21770893964930535, "learning_rate": 3.608824378627005e-06, "loss": 0.2432, "step": 1015 }, { "epoch": 4.115443037974684, "grad_norm": 0.19733832423922215, "learning_rate": 3.5763679848634337e-06, "loss": 0.2468, "step": 1016 }, { "epoch": 4.119493670886076, "grad_norm": 0.1831801888241367, "learning_rate": 3.544043864774269e-06, "loss": 0.2408, "step": 1017 }, { "epoch": 4.123544303797468, "grad_norm": 0.1905073745715315, "learning_rate": 3.5118522786935282e-06, "loss": 0.2519, "step": 1018 }, { "epoch": 4.127594936708861, "grad_norm": 0.18531270843314146, "learning_rate": 3.479793485887819e-06, "loss": 0.2428, "step": 1019 }, { "epoch": 4.131645569620253, "grad_norm": 0.19077288870131162, "learning_rate": 3.4478677445542653e-06, "loss": 0.2436, "step": 1020 }, { "epoch": 4.135696202531646, "grad_norm": 0.18113587914604956, "learning_rate": 3.4160753118183767e-06, "loss": 0.2552, "step": 1021 }, { "epoch": 4.139746835443038, "grad_norm": 0.196175221868894, "learning_rate": 3.3844164437320527e-06, "loss": 0.2416, "step": 1022 }, { "epoch": 4.14379746835443, "grad_norm": 0.19353262809761726, "learning_rate": 3.3528913952714558e-06, "loss": 0.2399, "step": 1023 }, { "epoch": 4.147848101265823, "grad_norm": 0.1888770182907619, "learning_rate": 3.321500420335e-06, "loss": 0.2527, "step": 1024 }, { "epoch": 4.151898734177215, "grad_norm": 0.17922729175167854, "learning_rate": 3.290243771741275e-06, "loss": 0.2408, "step": 1025 }, { "epoch": 4.155949367088607, "grad_norm": 0.18102181594895012, "learning_rate": 3.2591217012270325e-06, "loss": 0.2497, "step": 1026 }, { "epoch": 4.16, "grad_norm": 0.17548469868019573, "learning_rate": 3.228134459445149e-06, "loss": 0.2429, "step": 1027 }, { "epoch": 4.164050632911392, "grad_norm": 0.18475870327726912, "learning_rate": 3.1972822959626205e-06, "loss": 0.2457, "step": 1028 }, { "epoch": 4.168101265822785, "grad_norm": 0.18754820159018898, "learning_rate": 3.166565459258513e-06, "loss": 0.2558, "step": 1029 }, { "epoch": 4.172151898734177, "grad_norm": 0.18397927805435688, "learning_rate": 3.1359841967220193e-06, "loss": 0.2429, "step": 1030 }, { "epoch": 4.176202531645569, "grad_norm": 0.1790693088949137, "learning_rate": 3.105538754650419e-06, "loss": 0.2383, "step": 1031 }, { "epoch": 4.180253164556962, "grad_norm": 0.1775001671599968, "learning_rate": 3.07522937824712e-06, "loss": 0.2358, "step": 1032 }, { "epoch": 4.184303797468354, "grad_norm": 0.17992062283276178, "learning_rate": 3.0450563116196697e-06, "loss": 0.2433, "step": 1033 }, { "epoch": 4.188354430379746, "grad_norm": 0.19618839829396903, "learning_rate": 3.0150197977778008e-06, "loss": 0.2507, "step": 1034 }, { "epoch": 4.192405063291139, "grad_norm": 0.19502823182792706, "learning_rate": 2.985120078631465e-06, "loss": 0.245, "step": 1035 }, { "epoch": 4.1964556962025314, "grad_norm": 0.17644704794052674, "learning_rate": 2.9553573949888893e-06, "loss": 0.247, "step": 1036 }, { "epoch": 4.200506329113924, "grad_norm": 0.16853720159965604, "learning_rate": 2.9257319865546384e-06, "loss": 0.2527, "step": 1037 }, { "epoch": 4.2045569620253165, "grad_norm": 0.1791047440995991, "learning_rate": 2.896244091927678e-06, "loss": 0.2387, "step": 1038 }, { "epoch": 4.2086075949367086, "grad_norm": 0.1865169730337142, "learning_rate": 2.8668939485994584e-06, "loss": 0.2355, "step": 1039 }, { "epoch": 4.2126582278481015, "grad_norm": 0.17725998046861396, "learning_rate": 2.837681792951994e-06, "loss": 0.2426, "step": 1040 }, { "epoch": 4.216708860759494, "grad_norm": 0.18271785019680883, "learning_rate": 2.808607860255981e-06, "loss": 0.2436, "step": 1041 }, { "epoch": 4.220759493670886, "grad_norm": 0.17720628230058685, "learning_rate": 2.7796723846688634e-06, "loss": 0.2403, "step": 1042 }, { "epoch": 4.224810126582279, "grad_norm": 0.17935712707663076, "learning_rate": 2.7508755992329937e-06, "loss": 0.2472, "step": 1043 }, { "epoch": 4.228860759493671, "grad_norm": 0.17758497660952421, "learning_rate": 2.722217735873718e-06, "loss": 0.2431, "step": 1044 }, { "epoch": 4.232911392405064, "grad_norm": 0.17890648629798478, "learning_rate": 2.6936990253975315e-06, "loss": 0.2375, "step": 1045 }, { "epoch": 4.236962025316456, "grad_norm": 0.1853242991212006, "learning_rate": 2.665319697490205e-06, "loss": 0.2474, "step": 1046 }, { "epoch": 4.241012658227848, "grad_norm": 0.1777094938497731, "learning_rate": 2.637079980714945e-06, "loss": 0.2542, "step": 1047 }, { "epoch": 4.245063291139241, "grad_norm": 0.17550439275539934, "learning_rate": 2.6089801025105453e-06, "loss": 0.2495, "step": 1048 }, { "epoch": 4.249113924050633, "grad_norm": 0.17613782813524356, "learning_rate": 2.581020289189571e-06, "loss": 0.2437, "step": 1049 }, { "epoch": 4.253164556962025, "grad_norm": 0.1750139693209958, "learning_rate": 2.553200765936501e-06, "loss": 0.2413, "step": 1050 }, { "epoch": 4.257215189873418, "grad_norm": 0.19199185064829669, "learning_rate": 2.525521756805962e-06, "loss": 0.2394, "step": 1051 }, { "epoch": 4.26126582278481, "grad_norm": 0.18403617575200518, "learning_rate": 2.497983484720885e-06, "loss": 0.2415, "step": 1052 }, { "epoch": 4.265316455696203, "grad_norm": 0.17895791443729786, "learning_rate": 2.470586171470728e-06, "loss": 0.2369, "step": 1053 }, { "epoch": 4.269367088607595, "grad_norm": 0.18084642635501685, "learning_rate": 2.4433300377096836e-06, "loss": 0.2343, "step": 1054 }, { "epoch": 4.273417721518987, "grad_norm": 0.18002837738827554, "learning_rate": 2.4162153029549073e-06, "loss": 0.2515, "step": 1055 }, { "epoch": 4.27746835443038, "grad_norm": 0.18258168466728333, "learning_rate": 2.3892421855847458e-06, "loss": 0.2466, "step": 1056 }, { "epoch": 4.281518987341772, "grad_norm": 0.17334871424375783, "learning_rate": 2.362410902836978e-06, "loss": 0.245, "step": 1057 }, { "epoch": 4.285569620253165, "grad_norm": 0.18258081053043015, "learning_rate": 2.3357216708070653e-06, "loss": 0.2419, "step": 1058 }, { "epoch": 4.289620253164557, "grad_norm": 0.17103437379198216, "learning_rate": 2.309174704446411e-06, "loss": 0.2399, "step": 1059 }, { "epoch": 4.293670886075949, "grad_norm": 0.1753240333888945, "learning_rate": 2.2827702175606437e-06, "loss": 0.2534, "step": 1060 }, { "epoch": 4.297721518987342, "grad_norm": 0.1799545061591973, "learning_rate": 2.256508422807855e-06, "loss": 0.2396, "step": 1061 }, { "epoch": 4.301772151898734, "grad_norm": 0.17587033044976064, "learning_rate": 2.230389531696946e-06, "loss": 0.234, "step": 1062 }, { "epoch": 4.305822784810126, "grad_norm": 0.17769845650232238, "learning_rate": 2.204413754585857e-06, "loss": 0.2382, "step": 1063 }, { "epoch": 4.309873417721519, "grad_norm": 0.184409869979378, "learning_rate": 2.1785813006799406e-06, "loss": 0.2435, "step": 1064 }, { "epoch": 4.313924050632911, "grad_norm": 0.17676326339802423, "learning_rate": 2.1528923780302224e-06, "loss": 0.2462, "step": 1065 }, { "epoch": 4.317974683544303, "grad_norm": 0.17394740779321216, "learning_rate": 2.127347193531757e-06, "loss": 0.2447, "step": 1066 }, { "epoch": 4.322025316455696, "grad_norm": 0.1804814896582061, "learning_rate": 2.101945952921942e-06, "loss": 0.254, "step": 1067 }, { "epoch": 4.326075949367088, "grad_norm": 0.1798528506907941, "learning_rate": 2.0766888607788906e-06, "loss": 0.2489, "step": 1068 }, { "epoch": 4.330126582278481, "grad_norm": 0.17950907118741974, "learning_rate": 2.0515761205197337e-06, "loss": 0.241, "step": 1069 }, { "epoch": 4.334177215189873, "grad_norm": 0.17403537121290885, "learning_rate": 2.0266079343990453e-06, "loss": 0.2578, "step": 1070 }, { "epoch": 4.3382278481012655, "grad_norm": 0.1771946718111046, "learning_rate": 2.0017845035071494e-06, "loss": 0.2567, "step": 1071 }, { "epoch": 4.3422784810126585, "grad_norm": 0.18275575688119866, "learning_rate": 1.9771060277685537e-06, "loss": 0.2318, "step": 1072 }, { "epoch": 4.3463291139240505, "grad_norm": 0.17569132247947317, "learning_rate": 1.95257270594031e-06, "loss": 0.2578, "step": 1073 }, { "epoch": 4.3503797468354435, "grad_norm": 0.21744289763150232, "learning_rate": 1.9281847356104188e-06, "loss": 0.2502, "step": 1074 }, { "epoch": 4.3544303797468356, "grad_norm": 0.17866566591475738, "learning_rate": 1.9039423131962365e-06, "loss": 0.2362, "step": 1075 }, { "epoch": 4.358481012658228, "grad_norm": 0.17511583430528235, "learning_rate": 1.8798456339429027e-06, "loss": 0.2494, "step": 1076 }, { "epoch": 4.362531645569621, "grad_norm": 0.1766900395230482, "learning_rate": 1.8558948919217612e-06, "loss": 0.2439, "step": 1077 }, { "epoch": 4.366582278481013, "grad_norm": 0.18050434350686403, "learning_rate": 1.8320902800287954e-06, "loss": 0.2551, "step": 1078 }, { "epoch": 4.370632911392405, "grad_norm": 0.17329710963149328, "learning_rate": 1.8084319899830726e-06, "loss": 0.2476, "step": 1079 }, { "epoch": 4.374683544303798, "grad_norm": 0.1814843841784593, "learning_rate": 1.7849202123252097e-06, "loss": 0.2482, "step": 1080 }, { "epoch": 4.37873417721519, "grad_norm": 6.118578992743657, "learning_rate": 1.7615551364158401e-06, "loss": 0.2783, "step": 1081 }, { "epoch": 4.382784810126582, "grad_norm": 0.18282113691061838, "learning_rate": 1.738336950434061e-06, "loss": 0.2429, "step": 1082 }, { "epoch": 4.386835443037975, "grad_norm": 0.1759845785612773, "learning_rate": 1.715265841375957e-06, "loss": 0.2376, "step": 1083 }, { "epoch": 4.390886075949367, "grad_norm": 0.19021550336440782, "learning_rate": 1.6923419950530684e-06, "loss": 0.2395, "step": 1084 }, { "epoch": 4.39493670886076, "grad_norm": 0.17878719629482004, "learning_rate": 1.6695655960909008e-06, "loss": 0.252, "step": 1085 }, { "epoch": 4.398987341772152, "grad_norm": 0.17716393669601055, "learning_rate": 1.646936827927441e-06, "loss": 0.235, "step": 1086 }, { "epoch": 4.403037974683544, "grad_norm": 0.17889069454416356, "learning_rate": 1.6244558728116766e-06, "loss": 0.2432, "step": 1087 }, { "epoch": 4.407088607594937, "grad_norm": 0.16984236283365617, "learning_rate": 1.6021229118021265e-06, "loss": 0.2443, "step": 1088 }, { "epoch": 4.411139240506329, "grad_norm": 0.16921505874242684, "learning_rate": 1.5799381247653967e-06, "loss": 0.2505, "step": 1089 }, { "epoch": 4.415189873417722, "grad_norm": 0.17598724982859082, "learning_rate": 1.5579016903747013e-06, "loss": 0.2381, "step": 1090 }, { "epoch": 4.419240506329114, "grad_norm": 0.16896544771775407, "learning_rate": 1.5360137861084656e-06, "loss": 0.2468, "step": 1091 }, { "epoch": 4.423291139240506, "grad_norm": 0.16995320899687974, "learning_rate": 1.5142745882488475e-06, "loss": 0.2407, "step": 1092 }, { "epoch": 4.427341772151899, "grad_norm": 0.17565506053423366, "learning_rate": 1.4926842718803691e-06, "loss": 0.2465, "step": 1093 }, { "epoch": 4.431392405063291, "grad_norm": 0.18005621994113985, "learning_rate": 1.4712430108884657e-06, "loss": 0.2528, "step": 1094 }, { "epoch": 4.435443037974683, "grad_norm": 0.17459979000213144, "learning_rate": 1.4499509779581078e-06, "loss": 0.2521, "step": 1095 }, { "epoch": 4.439493670886076, "grad_norm": 0.1715053668972662, "learning_rate": 1.4288083445723988e-06, "loss": 0.2484, "step": 1096 }, { "epoch": 4.443544303797468, "grad_norm": 0.17593220890020092, "learning_rate": 1.4078152810112045e-06, "loss": 0.2501, "step": 1097 }, { "epoch": 4.44759493670886, "grad_norm": 0.17247621764398816, "learning_rate": 1.3869719563497697e-06, "loss": 0.2497, "step": 1098 }, { "epoch": 4.451645569620253, "grad_norm": 0.17071334673747712, "learning_rate": 1.3662785384573663e-06, "loss": 0.2455, "step": 1099 }, { "epoch": 4.455696202531645, "grad_norm": 0.20002065060862598, "learning_rate": 1.3457351939959383e-06, "loss": 0.2456, "step": 1100 }, { "epoch": 4.459746835443038, "grad_norm": 0.16563623219253426, "learning_rate": 1.3253420884187551e-06, "loss": 0.2437, "step": 1101 }, { "epoch": 4.46379746835443, "grad_norm": 0.17239883431632597, "learning_rate": 1.3050993859690953e-06, "loss": 0.2449, "step": 1102 }, { "epoch": 4.467848101265822, "grad_norm": 0.16965670707710442, "learning_rate": 1.2850072496788869e-06, "loss": 0.2517, "step": 1103 }, { "epoch": 4.471898734177215, "grad_norm": 0.19018348489696119, "learning_rate": 1.2650658413674434e-06, "loss": 0.2433, "step": 1104 }, { "epoch": 4.4759493670886075, "grad_norm": 0.16702350457576257, "learning_rate": 1.2452753216401226e-06, "loss": 0.2381, "step": 1105 }, { "epoch": 4.48, "grad_norm": 0.1697159426790234, "learning_rate": 1.2256358498870503e-06, "loss": 0.2393, "step": 1106 }, { "epoch": 4.4840506329113925, "grad_norm": 0.1702470706145786, "learning_rate": 1.2061475842818337e-06, "loss": 0.2383, "step": 1107 }, { "epoch": 4.488101265822785, "grad_norm": 0.172233653895894, "learning_rate": 1.1868106817802816e-06, "loss": 0.2411, "step": 1108 }, { "epoch": 4.4921518987341775, "grad_norm": 0.1816825783859516, "learning_rate": 1.1676252981191482e-06, "loss": 0.2423, "step": 1109 }, { "epoch": 4.49620253164557, "grad_norm": 0.16634220257285656, "learning_rate": 1.1485915878148823e-06, "loss": 0.2442, "step": 1110 }, { "epoch": 4.500253164556962, "grad_norm": 0.16528791145666188, "learning_rate": 1.1297097041623584e-06, "loss": 0.2457, "step": 1111 }, { "epoch": 4.504303797468355, "grad_norm": 0.17130268018043265, "learning_rate": 1.1109797992336847e-06, "loss": 0.2462, "step": 1112 }, { "epoch": 4.508354430379747, "grad_norm": 0.1845402070776009, "learning_rate": 1.092402023876933e-06, "loss": 0.2437, "step": 1113 }, { "epoch": 4.512405063291139, "grad_norm": 0.16696358953113452, "learning_rate": 1.0739765277149527e-06, "loss": 0.2334, "step": 1114 }, { "epoch": 4.516455696202532, "grad_norm": 0.16558663979202068, "learning_rate": 1.0557034591441596e-06, "loss": 0.2431, "step": 1115 }, { "epoch": 4.520506329113924, "grad_norm": 0.17098919697377654, "learning_rate": 1.0375829653333324e-06, "loss": 0.2425, "step": 1116 }, { "epoch": 4.524556962025317, "grad_norm": 0.22574402759229867, "learning_rate": 1.0196151922224385e-06, "loss": 0.2487, "step": 1117 }, { "epoch": 4.528607594936709, "grad_norm": 0.17732465113480544, "learning_rate": 1.0018002845214526e-06, "loss": 0.2423, "step": 1118 }, { "epoch": 4.532658227848101, "grad_norm": 0.16646837966318526, "learning_rate": 9.841383857091947e-07, "loss": 0.2484, "step": 1119 }, { "epoch": 4.536708860759494, "grad_norm": 0.19611265350557733, "learning_rate": 9.666296380321616e-07, "loss": 0.2519, "step": 1120 }, { "epoch": 4.540759493670886, "grad_norm": 0.16615435190504219, "learning_rate": 9.492741825034124e-07, "loss": 0.245, "step": 1121 }, { "epoch": 4.544810126582279, "grad_norm": 0.17164750408314838, "learning_rate": 9.320721589013892e-07, "loss": 0.2484, "step": 1122 }, { "epoch": 4.548860759493671, "grad_norm": 0.16843474445949974, "learning_rate": 9.150237057688339e-07, "loss": 0.2507, "step": 1123 }, { "epoch": 4.552911392405063, "grad_norm": 0.16836417168337095, "learning_rate": 8.981289604116328e-07, "loss": 0.2438, "step": 1124 }, { "epoch": 4.556962025316456, "grad_norm": 0.1860308495679002, "learning_rate": 8.813880588977542e-07, "loss": 0.2488, "step": 1125 }, { "epoch": 4.561012658227848, "grad_norm": 0.17023919320146264, "learning_rate": 8.648011360561126e-07, "loss": 0.2513, "step": 1126 }, { "epoch": 4.56506329113924, "grad_norm": 0.17559898960624393, "learning_rate": 8.483683254755037e-07, "loss": 0.2443, "step": 1127 }, { "epoch": 4.569113924050633, "grad_norm": 0.17507090402145986, "learning_rate": 8.320897595035227e-07, "loss": 0.2353, "step": 1128 }, { "epoch": 4.573164556962025, "grad_norm": 0.1703269648925976, "learning_rate": 8.159655692455093e-07, "loss": 0.2476, "step": 1129 }, { "epoch": 4.577215189873417, "grad_norm": 0.16472930148726642, "learning_rate": 7.999958845634648e-07, "loss": 0.2363, "step": 1130 }, { "epoch": 4.58126582278481, "grad_norm": 0.17083746715719353, "learning_rate": 7.841808340750478e-07, "loss": 0.2394, "step": 1131 }, { "epoch": 4.585316455696202, "grad_norm": 0.16777258865645492, "learning_rate": 7.685205451524869e-07, "loss": 0.234, "step": 1132 }, { "epoch": 4.589367088607595, "grad_norm": 0.17273347473957282, "learning_rate": 7.530151439216027e-07, "loss": 0.2532, "step": 1133 }, { "epoch": 4.593417721518987, "grad_norm": 0.1709174358216556, "learning_rate": 7.376647552607675e-07, "loss": 0.253, "step": 1134 }, { "epoch": 4.597468354430379, "grad_norm": 0.1713892110730535, "learning_rate": 7.224695027998963e-07, "loss": 0.245, "step": 1135 }, { "epoch": 4.601518987341772, "grad_norm": 0.22002517885462536, "learning_rate": 7.07429508919466e-07, "loss": 0.2358, "step": 1136 }, { "epoch": 4.605569620253164, "grad_norm": 0.1688980793364616, "learning_rate": 6.925448947495206e-07, "loss": 0.233, "step": 1137 }, { "epoch": 4.609620253164557, "grad_norm": 0.1772403587015237, "learning_rate": 6.778157801686936e-07, "loss": 0.2478, "step": 1138 }, { "epoch": 4.613670886075949, "grad_norm": 0.16576517954238562, "learning_rate": 6.632422838032515e-07, "loss": 0.2509, "step": 1139 }, { "epoch": 4.6177215189873415, "grad_norm": 0.16523345603498596, "learning_rate": 6.488245230261281e-07, "loss": 0.2459, "step": 1140 }, { "epoch": 4.6217721518987345, "grad_norm": 0.16886817189483222, "learning_rate": 6.345626139559868e-07, "loss": 0.2442, "step": 1141 }, { "epoch": 4.6258227848101265, "grad_norm": 0.1666855124757119, "learning_rate": 6.204566714562866e-07, "loss": 0.2449, "step": 1142 }, { "epoch": 4.629873417721519, "grad_norm": 0.17680945747097404, "learning_rate": 6.06506809134344e-07, "loss": 0.2485, "step": 1143 }, { "epoch": 4.633924050632912, "grad_norm": 0.17350783046255053, "learning_rate": 5.927131393404373e-07, "loss": 0.2447, "step": 1144 }, { "epoch": 4.637974683544304, "grad_norm": 0.16692366122960894, "learning_rate": 5.790757731668817e-07, "loss": 0.2381, "step": 1145 }, { "epoch": 4.642025316455696, "grad_norm": 0.1661946766186289, "learning_rate": 5.655948204471507e-07, "loss": 0.2503, "step": 1146 }, { "epoch": 4.646075949367089, "grad_norm": 0.16644292573214306, "learning_rate": 5.522703897549875e-07, "loss": 0.2485, "step": 1147 }, { "epoch": 4.650126582278481, "grad_norm": 0.16049106614368286, "learning_rate": 5.391025884035239e-07, "loss": 0.2461, "step": 1148 }, { "epoch": 4.654177215189874, "grad_norm": 0.166448739866559, "learning_rate": 5.260915224444207e-07, "loss": 0.2488, "step": 1149 }, { "epoch": 4.658227848101266, "grad_norm": 0.1674792160513929, "learning_rate": 5.132372966670129e-07, "loss": 0.2431, "step": 1150 }, { "epoch": 4.662278481012658, "grad_norm": 0.16508514356494475, "learning_rate": 5.005400145974704e-07, "loss": 0.2422, "step": 1151 }, { "epoch": 4.666329113924051, "grad_norm": 0.1739163676828167, "learning_rate": 4.879997784979562e-07, "loss": 0.2372, "step": 1152 }, { "epoch": 4.670379746835443, "grad_norm": 0.16919717966851922, "learning_rate": 4.7561668936580984e-07, "loss": 0.236, "step": 1153 }, { "epoch": 4.674430379746836, "grad_norm": 0.16695318860623665, "learning_rate": 4.6339084693272306e-07, "loss": 0.2441, "step": 1154 }, { "epoch": 4.678481012658228, "grad_norm": 0.16763487050342316, "learning_rate": 4.5132234966395847e-07, "loss": 0.245, "step": 1155 }, { "epoch": 4.68253164556962, "grad_norm": 0.1684360284617399, "learning_rate": 4.3941129475752795e-07, "loss": 0.2511, "step": 1156 }, { "epoch": 4.686582278481013, "grad_norm": 0.1688494994919624, "learning_rate": 4.27657778143431e-07, "loss": 0.252, "step": 1157 }, { "epoch": 4.690632911392405, "grad_norm": 0.17221066371887098, "learning_rate": 4.1606189448287757e-07, "loss": 0.2465, "step": 1158 }, { "epoch": 4.694683544303797, "grad_norm": 0.16738262912775823, "learning_rate": 4.046237371675177e-07, "loss": 0.2445, "step": 1159 }, { "epoch": 4.69873417721519, "grad_norm": 0.16677645020868626, "learning_rate": 3.9334339831869963e-07, "loss": 0.2508, "step": 1160 }, { "epoch": 4.702784810126582, "grad_norm": 0.16407347377086234, "learning_rate": 3.8222096878671955e-07, "loss": 0.2412, "step": 1161 }, { "epoch": 4.706835443037974, "grad_norm": 0.17107397206919692, "learning_rate": 3.7125653815009545e-07, "loss": 0.2426, "step": 1162 }, { "epoch": 4.710886075949367, "grad_norm": 0.1674752356887656, "learning_rate": 3.6045019471484974e-07, "loss": 0.237, "step": 1163 }, { "epoch": 4.714936708860759, "grad_norm": 0.18066813340947335, "learning_rate": 3.498020255137813e-07, "loss": 0.2365, "step": 1164 }, { "epoch": 4.718987341772152, "grad_norm": 0.17015921718833615, "learning_rate": 3.393121163057811e-07, "loss": 0.2502, "step": 1165 }, { "epoch": 4.723037974683544, "grad_norm": 0.16706009430614988, "learning_rate": 3.289805515751399e-07, "loss": 0.2482, "step": 1166 }, { "epoch": 4.727088607594936, "grad_norm": 0.1680146620338249, "learning_rate": 3.188074145308573e-07, "loss": 0.2356, "step": 1167 }, { "epoch": 4.731139240506329, "grad_norm": 0.17493510763645806, "learning_rate": 3.087927871059804e-07, "loss": 0.2357, "step": 1168 }, { "epoch": 4.735189873417721, "grad_norm": 0.17211766171174137, "learning_rate": 2.989367499569418e-07, "loss": 0.241, "step": 1169 }, { "epoch": 4.739240506329114, "grad_norm": 0.16799307899344137, "learning_rate": 2.8923938246290917e-07, "loss": 0.244, "step": 1170 }, { "epoch": 4.743291139240506, "grad_norm": 0.16921841230097362, "learning_rate": 2.7970076272514804e-07, "loss": 0.2396, "step": 1171 }, { "epoch": 4.7473417721518985, "grad_norm": 0.17242896601435334, "learning_rate": 2.703209675663887e-07, "loss": 0.2409, "step": 1172 }, { "epoch": 4.751392405063291, "grad_norm": 0.168761024069582, "learning_rate": 2.6110007253021374e-07, "loss": 0.2375, "step": 1173 }, { "epoch": 4.7554430379746835, "grad_norm": 0.16980044492397323, "learning_rate": 2.520381518804471e-07, "loss": 0.2515, "step": 1174 }, { "epoch": 4.759493670886076, "grad_norm": 0.1662515639699747, "learning_rate": 2.4313527860054585e-07, "loss": 0.2424, "step": 1175 }, { "epoch": 4.7635443037974685, "grad_norm": 0.1659859289814607, "learning_rate": 2.343915243930317e-07, "loss": 0.2485, "step": 1176 }, { "epoch": 4.767594936708861, "grad_norm": 0.1682949194244476, "learning_rate": 2.2580695967889367e-07, "loss": 0.2306, "step": 1177 }, { "epoch": 4.7716455696202535, "grad_norm": 0.16995523975326382, "learning_rate": 2.1738165359704189e-07, "loss": 0.2401, "step": 1178 }, { "epoch": 4.775696202531646, "grad_norm": 0.16555556742185518, "learning_rate": 2.0911567400373257e-07, "loss": 0.2493, "step": 1179 }, { "epoch": 4.779746835443038, "grad_norm": 0.16537585400684335, "learning_rate": 2.0100908747202607e-07, "loss": 0.2437, "step": 1180 }, { "epoch": 4.783797468354431, "grad_norm": 0.17477743055989348, "learning_rate": 1.9306195929125638e-07, "loss": 0.2381, "step": 1181 }, { "epoch": 4.787848101265823, "grad_norm": 0.16668634406250898, "learning_rate": 1.8527435346650247e-07, "loss": 0.2454, "step": 1182 }, { "epoch": 4.791898734177215, "grad_norm": 0.1657215551042827, "learning_rate": 1.7764633271807108e-07, "loss": 0.2451, "step": 1183 }, { "epoch": 4.795949367088608, "grad_norm": 0.16874977659465937, "learning_rate": 1.7017795848099262e-07, "loss": 0.2425, "step": 1184 }, { "epoch": 4.8, "grad_norm": 0.16497437498551298, "learning_rate": 1.6286929090452596e-07, "loss": 0.2501, "step": 1185 }, { "epoch": 4.804050632911393, "grad_norm": 0.16405802113846413, "learning_rate": 1.557203888516745e-07, "loss": 0.243, "step": 1186 }, { "epoch": 4.808101265822785, "grad_norm": 0.16308218610386832, "learning_rate": 1.487313098987131e-07, "loss": 0.2439, "step": 1187 }, { "epoch": 4.812151898734177, "grad_norm": 0.16502035995872993, "learning_rate": 1.4190211033472402e-07, "loss": 0.2349, "step": 1188 }, { "epoch": 4.81620253164557, "grad_norm": 0.16200575251675672, "learning_rate": 1.3523284516113955e-07, "loss": 0.2435, "step": 1189 }, { "epoch": 4.820253164556962, "grad_norm": 0.17089468742034356, "learning_rate": 1.2872356809130682e-07, "loss": 0.2433, "step": 1190 }, { "epoch": 4.824303797468355, "grad_norm": 0.16597280116624805, "learning_rate": 1.2237433155004807e-07, "loss": 0.2456, "step": 1191 }, { "epoch": 4.828354430379747, "grad_norm": 0.1607341468297265, "learning_rate": 1.1618518667323886e-07, "loss": 0.2527, "step": 1192 }, { "epoch": 4.832405063291139, "grad_norm": 0.18057881321220304, "learning_rate": 1.1015618330740385e-07, "loss": 0.2494, "step": 1193 }, { "epoch": 4.836455696202532, "grad_norm": 0.1667764913523464, "learning_rate": 1.042873700093061e-07, "loss": 0.2456, "step": 1194 }, { "epoch": 4.840506329113924, "grad_norm": 0.1742284309051867, "learning_rate": 9.857879404556291e-08, "loss": 0.2358, "step": 1195 }, { "epoch": 4.844556962025316, "grad_norm": 0.16874460941832994, "learning_rate": 9.303050139225722e-08, "loss": 0.2463, "step": 1196 }, { "epoch": 4.848607594936709, "grad_norm": 0.16966623572482792, "learning_rate": 8.76425367345779e-08, "loss": 0.2427, "step": 1197 }, { "epoch": 4.852658227848101, "grad_norm": 0.16801404358570843, "learning_rate": 8.241494346644897e-08, "loss": 0.2376, "step": 1198 }, { "epoch": 4.856708860759493, "grad_norm": 0.16750067285573214, "learning_rate": 7.734776369019204e-08, "loss": 0.241, "step": 1199 }, { "epoch": 4.860759493670886, "grad_norm": 0.16654841250182853, "learning_rate": 7.244103821617332e-08, "loss": 0.2493, "step": 1200 }, { "epoch": 4.864810126582278, "grad_norm": 0.16395193921084233, "learning_rate": 6.769480656248606e-08, "loss": 0.2371, "step": 1201 }, { "epoch": 4.868860759493671, "grad_norm": 0.16710375088591273, "learning_rate": 6.310910695462635e-08, "loss": 0.2514, "step": 1202 }, { "epoch": 4.872911392405063, "grad_norm": 0.17668930692975512, "learning_rate": 5.8683976325191185e-08, "loss": 0.2496, "step": 1203 }, { "epoch": 4.876962025316455, "grad_norm": 0.16418307719728398, "learning_rate": 5.4419450313571984e-08, "loss": 0.2482, "step": 1204 }, { "epoch": 4.881012658227848, "grad_norm": 0.17189623878755106, "learning_rate": 5.031556326567488e-08, "loss": 0.2504, "step": 1205 }, { "epoch": 4.88506329113924, "grad_norm": 0.1655196413661385, "learning_rate": 4.637234823364312e-08, "loss": 0.2449, "step": 1206 }, { "epoch": 4.889113924050633, "grad_norm": 0.16920369892755294, "learning_rate": 4.258983697558838e-08, "loss": 0.2311, "step": 1207 }, { "epoch": 4.8931645569620255, "grad_norm": 0.1699053434209725, "learning_rate": 3.896805995533548e-08, "loss": 0.2366, "step": 1208 }, { "epoch": 4.8972151898734175, "grad_norm": 0.16661177997911022, "learning_rate": 3.550704634218028e-08, "loss": 0.2379, "step": 1209 }, { "epoch": 4.9012658227848105, "grad_norm": 0.16387786549532132, "learning_rate": 3.2206824010647676e-08, "loss": 0.2343, "step": 1210 }, { "epoch": 4.905316455696203, "grad_norm": 0.16726328492509993, "learning_rate": 2.9067419540278476e-08, "loss": 0.2345, "step": 1211 }, { "epoch": 4.909367088607595, "grad_norm": 0.17123244024933554, "learning_rate": 2.6088858215400638e-08, "loss": 0.2437, "step": 1212 }, { "epoch": 4.913417721518988, "grad_norm": 0.16365470138611837, "learning_rate": 2.3271164024940564e-08, "loss": 0.2502, "step": 1213 }, { "epoch": 4.91746835443038, "grad_norm": 0.17552437095274773, "learning_rate": 2.061435966221881e-08, "loss": 0.242, "step": 1214 }, { "epoch": 4.921518987341772, "grad_norm": 0.1659274768136939, "learning_rate": 1.811846652477245e-08, "loss": 0.2594, "step": 1215 }, { "epoch": 4.925569620253165, "grad_norm": 0.16493018087307326, "learning_rate": 1.5783504714184106e-08, "loss": 0.242, "step": 1216 }, { "epoch": 4.929620253164557, "grad_norm": 0.17005417483148064, "learning_rate": 1.360949303591097e-08, "loss": 0.2494, "step": 1217 }, { "epoch": 4.93367088607595, "grad_norm": 0.171154150843911, "learning_rate": 1.1596448999144916e-08, "loss": 0.2439, "step": 1218 }, { "epoch": 4.937721518987342, "grad_norm": 0.1702527272598993, "learning_rate": 9.744388816668172e-09, "loss": 0.2336, "step": 1219 }, { "epoch": 4.941772151898734, "grad_norm": 0.1721590725348306, "learning_rate": 8.05332740472009e-09, "loss": 0.2469, "step": 1220 }, { "epoch": 4.945822784810127, "grad_norm": 0.1667217065583009, "learning_rate": 6.523278382872811e-09, "loss": 0.2342, "step": 1221 }, { "epoch": 4.949873417721519, "grad_norm": 0.17014884119319537, "learning_rate": 5.15425407393133e-09, "loss": 0.2517, "step": 1222 }, { "epoch": 4.953924050632912, "grad_norm": 0.16470118521756763, "learning_rate": 3.94626550383137e-09, "loss": 0.2454, "step": 1223 }, { "epoch": 4.957974683544304, "grad_norm": 0.16376480677034333, "learning_rate": 2.899322401546112e-09, "loss": 0.2454, "step": 1224 }, { "epoch": 4.962025316455696, "grad_norm": 0.16491643997491326, "learning_rate": 2.013433199010706e-09, "loss": 0.2452, "step": 1225 }, { "epoch": 4.966075949367089, "grad_norm": 0.16337631939206737, "learning_rate": 1.2886050310556563e-09, "loss": 0.241, "step": 1226 }, { "epoch": 4.970126582278481, "grad_norm": 0.17236105849562752, "learning_rate": 7.248437353468695e-10, "loss": 0.2268, "step": 1227 }, { "epoch": 4.974177215189873, "grad_norm": 0.1669782603931199, "learning_rate": 3.221538523412449e-10, "loss": 0.2439, "step": 1228 }, { "epoch": 4.978227848101266, "grad_norm": 0.17423467895329772, "learning_rate": 8.053862524670663e-11, "loss": 0.2465, "step": 1229 }, { "epoch": 4.982278481012658, "grad_norm": 0.16538206453496285, "learning_rate": 0.0, "loss": 0.2419, "step": 1230 }, { "epoch": 4.982278481012658, "step": 1230, "total_flos": 5.834624696138629e+18, "train_loss": 0.34537784527472365, "train_runtime": 54472.2755, "train_samples_per_second": 2.901, "train_steps_per_second": 0.023 } ], "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": 5.834624696138629e+18, "train_batch_size": 1, "trial_name": null, "trial_params": null }