{ "best_metric": null, "best_model_checkpoint": null, "epoch": 4.988354430379747, "eval_steps": 500, "global_step": 1230, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.004050632911392405, "grad_norm": 8.089455058236336, "learning_rate": 3.2520325203252037e-07, "loss": 0.9093, "step": 1 }, { "epoch": 0.00810126582278481, "grad_norm": 8.375665926269741, "learning_rate": 6.504065040650407e-07, "loss": 0.9384, "step": 2 }, { "epoch": 0.012151898734177215, "grad_norm": 8.589122429623925, "learning_rate": 9.75609756097561e-07, "loss": 0.937, "step": 3 }, { "epoch": 0.01620253164556962, "grad_norm": 7.899338146081763, "learning_rate": 1.3008130081300815e-06, "loss": 0.8965, "step": 4 }, { "epoch": 0.020253164556962026, "grad_norm": 7.661863645441067, "learning_rate": 1.6260162601626018e-06, "loss": 0.9003, "step": 5 }, { "epoch": 0.02430379746835443, "grad_norm": 7.654822386484915, "learning_rate": 1.951219512195122e-06, "loss": 0.9084, "step": 6 }, { "epoch": 0.028354430379746835, "grad_norm": 5.8009213596071065, "learning_rate": 2.2764227642276426e-06, "loss": 0.8385, "step": 7 }, { "epoch": 0.03240506329113924, "grad_norm": 5.458112099971182, "learning_rate": 2.601626016260163e-06, "loss": 0.8343, "step": 8 }, { "epoch": 0.03645569620253165, "grad_norm": 3.3965813268753156, "learning_rate": 2.926829268292683e-06, "loss": 0.7775, "step": 9 }, { "epoch": 0.04050632911392405, "grad_norm": 3.0689362731985375, "learning_rate": 3.2520325203252037e-06, "loss": 0.7711, "step": 10 }, { "epoch": 0.044556962025316456, "grad_norm": 2.7827433136756903, "learning_rate": 3.577235772357724e-06, "loss": 0.743, "step": 11 }, { "epoch": 0.04860759493670886, "grad_norm": 3.833476347425904, "learning_rate": 3.902439024390244e-06, "loss": 0.7059, "step": 12 }, { "epoch": 0.052658227848101265, "grad_norm": 3.91685315453582, "learning_rate": 4.227642276422765e-06, "loss": 0.6974, "step": 13 }, { "epoch": 0.05670886075949367, "grad_norm": 3.770408537761192, "learning_rate": 4.552845528455285e-06, "loss": 0.673, "step": 14 }, { "epoch": 0.060759493670886074, "grad_norm": 3.4776896176400194, "learning_rate": 4.8780487804878055e-06, "loss": 0.6587, "step": 15 }, { "epoch": 0.06481012658227848, "grad_norm": 2.772509595695334, "learning_rate": 5.203252032520326e-06, "loss": 0.6091, "step": 16 }, { "epoch": 0.06886075949367089, "grad_norm": 2.3726416828199075, "learning_rate": 5.528455284552846e-06, "loss": 0.5922, "step": 17 }, { "epoch": 0.0729113924050633, "grad_norm": 1.8164552458330736, "learning_rate": 5.853658536585366e-06, "loss": 0.581, "step": 18 }, { "epoch": 0.0769620253164557, "grad_norm": 1.60301536607072, "learning_rate": 6.178861788617887e-06, "loss": 0.5507, "step": 19 }, { "epoch": 0.0810126582278481, "grad_norm": 1.4031963968588765, "learning_rate": 6.504065040650407e-06, "loss": 0.5406, "step": 20 }, { "epoch": 0.08506329113924051, "grad_norm": 1.2484367348838485, "learning_rate": 6.829268292682928e-06, "loss": 0.5165, "step": 21 }, { "epoch": 0.08911392405063291, "grad_norm": 1.3052270786448275, "learning_rate": 7.154471544715448e-06, "loss": 0.504, "step": 22 }, { "epoch": 0.09316455696202532, "grad_norm": 1.2133980593762885, "learning_rate": 7.4796747967479676e-06, "loss": 0.5156, "step": 23 }, { "epoch": 0.09721518987341772, "grad_norm": 1.0027981024064265, "learning_rate": 7.804878048780489e-06, "loss": 0.492, "step": 24 }, { "epoch": 0.10126582278481013, "grad_norm": 1.0262420840915643, "learning_rate": 8.130081300813009e-06, "loss": 0.4682, "step": 25 }, { "epoch": 0.10531645569620253, "grad_norm": 0.9678933807798736, "learning_rate": 8.45528455284553e-06, "loss": 0.4762, "step": 26 }, { "epoch": 0.10936708860759493, "grad_norm": 0.7746539950385759, "learning_rate": 8.78048780487805e-06, "loss": 0.4674, "step": 27 }, { "epoch": 0.11341772151898734, "grad_norm": 0.827734206560828, "learning_rate": 9.10569105691057e-06, "loss": 0.4507, "step": 28 }, { "epoch": 0.11746835443037974, "grad_norm": 0.8819233823437846, "learning_rate": 9.43089430894309e-06, "loss": 0.4485, "step": 29 }, { "epoch": 0.12151898734177215, "grad_norm": 0.8260067457207694, "learning_rate": 9.756097560975611e-06, "loss": 0.4548, "step": 30 }, { "epoch": 0.12556962025316457, "grad_norm": 0.691846096854957, "learning_rate": 1.008130081300813e-05, "loss": 0.4414, "step": 31 }, { "epoch": 0.12962025316455697, "grad_norm": 0.7747141890031944, "learning_rate": 1.0406504065040652e-05, "loss": 0.4367, "step": 32 }, { "epoch": 0.13367088607594937, "grad_norm": 0.6105471174741062, "learning_rate": 1.0731707317073172e-05, "loss": 0.44, "step": 33 }, { "epoch": 0.13772151898734178, "grad_norm": 0.7215760853270964, "learning_rate": 1.1056910569105692e-05, "loss": 0.4362, "step": 34 }, { "epoch": 0.14177215189873418, "grad_norm": 0.7223557811311894, "learning_rate": 1.1382113821138213e-05, "loss": 0.4167, "step": 35 }, { "epoch": 0.1458227848101266, "grad_norm": 0.6622815093218082, "learning_rate": 1.1707317073170731e-05, "loss": 0.4265, "step": 36 }, { "epoch": 0.149873417721519, "grad_norm": 0.6279232222535471, "learning_rate": 1.2032520325203254e-05, "loss": 0.407, "step": 37 }, { "epoch": 0.1539240506329114, "grad_norm": 0.6276313952292206, "learning_rate": 1.2357723577235774e-05, "loss": 0.4304, "step": 38 }, { "epoch": 0.1579746835443038, "grad_norm": 0.6235790864291396, "learning_rate": 1.2682926829268294e-05, "loss": 0.4174, "step": 39 }, { "epoch": 0.1620253164556962, "grad_norm": 0.6465862328212117, "learning_rate": 1.3008130081300815e-05, "loss": 0.4292, "step": 40 }, { "epoch": 0.1660759493670886, "grad_norm": 0.6714748856981292, "learning_rate": 1.3333333333333333e-05, "loss": 0.4132, "step": 41 }, { "epoch": 0.17012658227848101, "grad_norm": 0.5912062969370978, "learning_rate": 1.3658536585365855e-05, "loss": 0.3899, "step": 42 }, { "epoch": 0.17417721518987342, "grad_norm": 0.6058300775853507, "learning_rate": 1.3983739837398376e-05, "loss": 0.4125, "step": 43 }, { "epoch": 0.17822784810126582, "grad_norm": 0.5673990660729435, "learning_rate": 1.4308943089430896e-05, "loss": 0.4019, "step": 44 }, { "epoch": 0.18227848101265823, "grad_norm": 0.6592342937805942, "learning_rate": 1.4634146341463415e-05, "loss": 0.4142, "step": 45 }, { "epoch": 0.18632911392405063, "grad_norm": 0.6149397494367884, "learning_rate": 1.4959349593495935e-05, "loss": 0.4073, "step": 46 }, { "epoch": 0.19037974683544304, "grad_norm": 0.6410789214470322, "learning_rate": 1.528455284552846e-05, "loss": 0.3834, "step": 47 }, { "epoch": 0.19443037974683544, "grad_norm": 0.6091077487079957, "learning_rate": 1.5609756097560978e-05, "loss": 0.3883, "step": 48 }, { "epoch": 0.19848101265822785, "grad_norm": 0.6051105486856936, "learning_rate": 1.5934959349593496e-05, "loss": 0.386, "step": 49 }, { "epoch": 0.20253164556962025, "grad_norm": 0.5132426064197095, "learning_rate": 1.6260162601626018e-05, "loss": 0.3884, "step": 50 }, { "epoch": 0.20658227848101265, "grad_norm": 0.5948630020937037, "learning_rate": 1.6585365853658537e-05, "loss": 0.3687, "step": 51 }, { "epoch": 0.21063291139240506, "grad_norm": 0.6633568229247392, "learning_rate": 1.691056910569106e-05, "loss": 0.3863, "step": 52 }, { "epoch": 0.21468354430379746, "grad_norm": 0.6982404754099033, "learning_rate": 1.7235772357723578e-05, "loss": 0.3868, "step": 53 }, { "epoch": 0.21873417721518987, "grad_norm": 0.6475256587360759, "learning_rate": 1.75609756097561e-05, "loss": 0.3713, "step": 54 }, { "epoch": 0.22278481012658227, "grad_norm": 0.6992057622279685, "learning_rate": 1.788617886178862e-05, "loss": 0.3776, "step": 55 }, { "epoch": 0.22683544303797468, "grad_norm": 0.6058928931284311, "learning_rate": 1.821138211382114e-05, "loss": 0.3858, "step": 56 }, { "epoch": 0.23088607594936708, "grad_norm": 0.7394944903297722, "learning_rate": 1.8536585365853663e-05, "loss": 0.3787, "step": 57 }, { "epoch": 0.23493670886075949, "grad_norm": 0.6420010605337766, "learning_rate": 1.886178861788618e-05, "loss": 0.3582, "step": 58 }, { "epoch": 0.2389873417721519, "grad_norm": 0.6242961926004756, "learning_rate": 1.91869918699187e-05, "loss": 0.3715, "step": 59 }, { "epoch": 0.2430379746835443, "grad_norm": 0.6650027464143872, "learning_rate": 1.9512195121951222e-05, "loss": 0.3732, "step": 60 }, { "epoch": 0.2470886075949367, "grad_norm": 0.7408231265796157, "learning_rate": 1.983739837398374e-05, "loss": 0.3856, "step": 61 }, { "epoch": 0.25113924050632913, "grad_norm": 0.6817720788147983, "learning_rate": 2.016260162601626e-05, "loss": 0.3707, "step": 62 }, { "epoch": 0.25518987341772154, "grad_norm": 0.7859182941144918, "learning_rate": 2.048780487804878e-05, "loss": 0.3687, "step": 63 }, { "epoch": 0.25924050632911394, "grad_norm": 0.8338031856388477, "learning_rate": 2.0813008130081303e-05, "loss": 0.3652, "step": 64 }, { "epoch": 0.26329113924050634, "grad_norm": 0.7311622679991219, "learning_rate": 2.1138211382113822e-05, "loss": 0.3687, "step": 65 }, { "epoch": 0.26734177215189875, "grad_norm": 0.7470405461928926, "learning_rate": 2.1463414634146344e-05, "loss": 0.3554, "step": 66 }, { "epoch": 0.27139240506329115, "grad_norm": 0.8197341257123507, "learning_rate": 2.1788617886178863e-05, "loss": 0.3722, "step": 67 }, { "epoch": 0.27544303797468356, "grad_norm": 0.8672181707619843, "learning_rate": 2.2113821138211385e-05, "loss": 0.3603, "step": 68 }, { "epoch": 0.27949367088607596, "grad_norm": 0.6902267055800838, "learning_rate": 2.2439024390243907e-05, "loss": 0.3614, "step": 69 }, { "epoch": 0.28354430379746837, "grad_norm": 0.8019353279878109, "learning_rate": 2.2764227642276426e-05, "loss": 0.3616, "step": 70 }, { "epoch": 0.28759493670886077, "grad_norm": 0.903669738763232, "learning_rate": 2.3089430894308948e-05, "loss": 0.3768, "step": 71 }, { "epoch": 0.2916455696202532, "grad_norm": 0.7576060744157311, "learning_rate": 2.3414634146341463e-05, "loss": 0.3643, "step": 72 }, { "epoch": 0.2956962025316456, "grad_norm": 0.7605790893811154, "learning_rate": 2.3739837398373985e-05, "loss": 0.359, "step": 73 }, { "epoch": 0.299746835443038, "grad_norm": 0.8205066308846232, "learning_rate": 2.4065040650406507e-05, "loss": 0.3652, "step": 74 }, { "epoch": 0.3037974683544304, "grad_norm": 0.8003899287599199, "learning_rate": 2.4390243902439026e-05, "loss": 0.3517, "step": 75 }, { "epoch": 0.3078481012658228, "grad_norm": 0.7078002797148821, "learning_rate": 2.4715447154471548e-05, "loss": 0.3689, "step": 76 }, { "epoch": 0.3118987341772152, "grad_norm": 0.9051867064305539, "learning_rate": 2.5040650406504066e-05, "loss": 0.3635, "step": 77 }, { "epoch": 0.3159493670886076, "grad_norm": 0.7944448518560457, "learning_rate": 2.536585365853659e-05, "loss": 0.3641, "step": 78 }, { "epoch": 0.32, "grad_norm": 0.7653211003896152, "learning_rate": 2.569105691056911e-05, "loss": 0.3606, "step": 79 }, { "epoch": 0.3240506329113924, "grad_norm": 0.6856940574482244, "learning_rate": 2.601626016260163e-05, "loss": 0.3654, "step": 80 }, { "epoch": 0.3281012658227848, "grad_norm": 0.7279079013993204, "learning_rate": 2.634146341463415e-05, "loss": 0.3595, "step": 81 }, { "epoch": 0.3321518987341772, "grad_norm": 0.598594827621277, "learning_rate": 2.6666666666666667e-05, "loss": 0.3642, "step": 82 }, { "epoch": 0.3362025316455696, "grad_norm": 0.9477421907098008, "learning_rate": 2.699186991869919e-05, "loss": 0.3749, "step": 83 }, { "epoch": 0.34025316455696203, "grad_norm": 0.783851506425357, "learning_rate": 2.731707317073171e-05, "loss": 0.3619, "step": 84 }, { "epoch": 0.34430379746835443, "grad_norm": 0.7728497780687326, "learning_rate": 2.764227642276423e-05, "loss": 0.3683, "step": 85 }, { "epoch": 0.34835443037974684, "grad_norm": 0.9213557426839256, "learning_rate": 2.796747967479675e-05, "loss": 0.3537, "step": 86 }, { "epoch": 0.35240506329113924, "grad_norm": 0.8430639115817118, "learning_rate": 2.829268292682927e-05, "loss": 0.3498, "step": 87 }, { "epoch": 0.35645569620253165, "grad_norm": 0.8132354442334956, "learning_rate": 2.8617886178861792e-05, "loss": 0.3675, "step": 88 }, { "epoch": 0.36050632911392405, "grad_norm": 0.7997459582386907, "learning_rate": 2.8943089430894314e-05, "loss": 0.348, "step": 89 }, { "epoch": 0.36455696202531646, "grad_norm": 0.834414331588682, "learning_rate": 2.926829268292683e-05, "loss": 0.3614, "step": 90 }, { "epoch": 0.36860759493670886, "grad_norm": 0.8006037432448121, "learning_rate": 2.959349593495935e-05, "loss": 0.3597, "step": 91 }, { "epoch": 0.37265822784810126, "grad_norm": 0.7295221106881411, "learning_rate": 2.991869918699187e-05, "loss": 0.3618, "step": 92 }, { "epoch": 0.37670886075949367, "grad_norm": 0.7208476924759981, "learning_rate": 3.0243902439024392e-05, "loss": 0.3404, "step": 93 }, { "epoch": 0.3807594936708861, "grad_norm": 0.74030262588427, "learning_rate": 3.056910569105692e-05, "loss": 0.3628, "step": 94 }, { "epoch": 0.3848101265822785, "grad_norm": 0.7212712753365499, "learning_rate": 3.089430894308943e-05, "loss": 0.3488, "step": 95 }, { "epoch": 0.3888607594936709, "grad_norm": 0.6918855872552983, "learning_rate": 3.1219512195121955e-05, "loss": 0.3634, "step": 96 }, { "epoch": 0.3929113924050633, "grad_norm": 0.6116814804568776, "learning_rate": 3.154471544715447e-05, "loss": 0.3437, "step": 97 }, { "epoch": 0.3969620253164557, "grad_norm": 0.7027026434231884, "learning_rate": 3.186991869918699e-05, "loss": 0.3503, "step": 98 }, { "epoch": 0.4010126582278481, "grad_norm": 0.6394560886572498, "learning_rate": 3.2195121951219514e-05, "loss": 0.3511, "step": 99 }, { "epoch": 0.4050632911392405, "grad_norm": 0.7730875400330355, "learning_rate": 3.2520325203252037e-05, "loss": 0.3435, "step": 100 }, { "epoch": 0.4091139240506329, "grad_norm": 0.7241626313631154, "learning_rate": 3.284552845528456e-05, "loss": 0.3558, "step": 101 }, { "epoch": 0.4131645569620253, "grad_norm": 0.767061832635897, "learning_rate": 3.3170731707317074e-05, "loss": 0.3488, "step": 102 }, { "epoch": 0.4172151898734177, "grad_norm": 0.664929911989611, "learning_rate": 3.3495934959349596e-05, "loss": 0.3368, "step": 103 }, { "epoch": 0.4212658227848101, "grad_norm": 0.6685032480358734, "learning_rate": 3.382113821138212e-05, "loss": 0.3647, "step": 104 }, { "epoch": 0.4253164556962025, "grad_norm": 0.5999787248552033, "learning_rate": 3.414634146341463e-05, "loss": 0.35, "step": 105 }, { "epoch": 0.4293670886075949, "grad_norm": 0.6897852559047605, "learning_rate": 3.4471544715447155e-05, "loss": 0.3488, "step": 106 }, { "epoch": 0.43341772151898733, "grad_norm": 0.6891330491261648, "learning_rate": 3.479674796747968e-05, "loss": 0.3716, "step": 107 }, { "epoch": 0.43746835443037974, "grad_norm": 0.597616197789292, "learning_rate": 3.51219512195122e-05, "loss": 0.3568, "step": 108 }, { "epoch": 0.44151898734177214, "grad_norm": 0.6337653532544358, "learning_rate": 3.544715447154472e-05, "loss": 0.3588, "step": 109 }, { "epoch": 0.44556962025316454, "grad_norm": 0.5778060424153778, "learning_rate": 3.577235772357724e-05, "loss": 0.3416, "step": 110 }, { "epoch": 0.44962025316455695, "grad_norm": 0.5918226068392759, "learning_rate": 3.609756097560976e-05, "loss": 0.3345, "step": 111 }, { "epoch": 0.45367088607594935, "grad_norm": 0.671596537773974, "learning_rate": 3.642276422764228e-05, "loss": 0.3505, "step": 112 }, { "epoch": 0.45772151898734176, "grad_norm": 0.6440498923794135, "learning_rate": 3.67479674796748e-05, "loss": 0.3341, "step": 113 }, { "epoch": 0.46177215189873416, "grad_norm": 0.6169325549969494, "learning_rate": 3.7073170731707325e-05, "loss": 0.3464, "step": 114 }, { "epoch": 0.46582278481012657, "grad_norm": 0.7440102913423496, "learning_rate": 3.739837398373984e-05, "loss": 0.3567, "step": 115 }, { "epoch": 0.46987341772151897, "grad_norm": 0.743784686213993, "learning_rate": 3.772357723577236e-05, "loss": 0.3474, "step": 116 }, { "epoch": 0.4739240506329114, "grad_norm": 0.7423978464605595, "learning_rate": 3.804878048780488e-05, "loss": 0.3448, "step": 117 }, { "epoch": 0.4779746835443038, "grad_norm": 0.6157572504706285, "learning_rate": 3.83739837398374e-05, "loss": 0.3321, "step": 118 }, { "epoch": 0.4820253164556962, "grad_norm": 0.690557702355051, "learning_rate": 3.869918699186992e-05, "loss": 0.3621, "step": 119 }, { "epoch": 0.4860759493670886, "grad_norm": 0.7420920321382808, "learning_rate": 3.9024390243902444e-05, "loss": 0.3426, "step": 120 }, { "epoch": 0.490126582278481, "grad_norm": 0.6549208785355131, "learning_rate": 3.9349593495934966e-05, "loss": 0.362, "step": 121 }, { "epoch": 0.4941772151898734, "grad_norm": 0.7269854559512435, "learning_rate": 3.967479674796748e-05, "loss": 0.3646, "step": 122 }, { "epoch": 0.4982278481012658, "grad_norm": 0.7290511260358372, "learning_rate": 4e-05, "loss": 0.3683, "step": 123 }, { "epoch": 0.5022784810126583, "grad_norm": 0.6508825055942902, "learning_rate": 3.999991946137476e-05, "loss": 0.3524, "step": 124 }, { "epoch": 0.5063291139240507, "grad_norm": 0.6581136780428771, "learning_rate": 3.999967784614766e-05, "loss": 0.3354, "step": 125 }, { "epoch": 0.5103797468354431, "grad_norm": 0.6667261830326043, "learning_rate": 3.9999275156264656e-05, "loss": 0.3512, "step": 126 }, { "epoch": 0.5144303797468355, "grad_norm": 0.6748072935816252, "learning_rate": 3.999871139496895e-05, "loss": 0.3657, "step": 127 }, { "epoch": 0.5184810126582279, "grad_norm": 0.617337847480494, "learning_rate": 3.9997986566800995e-05, "loss": 0.337, "step": 128 }, { "epoch": 0.5225316455696203, "grad_norm": 0.6726517623702486, "learning_rate": 3.999710067759846e-05, "loss": 0.3545, "step": 129 }, { "epoch": 0.5265822784810127, "grad_norm": 0.6203906130484298, "learning_rate": 3.999605373449617e-05, "loss": 0.351, "step": 130 }, { "epoch": 0.5306329113924051, "grad_norm": 0.5285942524666161, "learning_rate": 3.9994845745926075e-05, "loss": 0.3367, "step": 131 }, { "epoch": 0.5346835443037975, "grad_norm": 0.5314266923079615, "learning_rate": 3.999347672161713e-05, "loss": 0.3526, "step": 132 }, { "epoch": 0.5387341772151899, "grad_norm": 0.5255219729713763, "learning_rate": 3.999194667259528e-05, "loss": 0.3388, "step": 133 }, { "epoch": 0.5427848101265823, "grad_norm": 0.5180537273134794, "learning_rate": 3.999025561118334e-05, "loss": 0.3505, "step": 134 }, { "epoch": 0.5468354430379747, "grad_norm": 0.6581238637485025, "learning_rate": 3.998840355100086e-05, "loss": 0.3451, "step": 135 }, { "epoch": 0.5508860759493671, "grad_norm": 0.696924040935584, "learning_rate": 3.998639050696409e-05, "loss": 0.3423, "step": 136 }, { "epoch": 0.5549367088607595, "grad_norm": 0.5884727496378748, "learning_rate": 3.998421649528582e-05, "loss": 0.3394, "step": 137 }, { "epoch": 0.5589873417721519, "grad_norm": 0.6877703705786279, "learning_rate": 3.9981881533475234e-05, "loss": 0.3344, "step": 138 }, { "epoch": 0.5630379746835443, "grad_norm": 0.6424335594474383, "learning_rate": 3.997938564033779e-05, "loss": 0.3463, "step": 139 }, { "epoch": 0.5670886075949367, "grad_norm": 0.5836703291709624, "learning_rate": 3.9976728835975064e-05, "loss": 0.3409, "step": 140 }, { "epoch": 0.5711392405063291, "grad_norm": 0.6151785469740537, "learning_rate": 3.9973911141784605e-05, "loss": 0.3387, "step": 141 }, { "epoch": 0.5751898734177215, "grad_norm": 0.556979624835709, "learning_rate": 3.997093258045973e-05, "loss": 0.3496, "step": 142 }, { "epoch": 0.579240506329114, "grad_norm": 0.5284059798335874, "learning_rate": 3.996779317598936e-05, "loss": 0.341, "step": 143 }, { "epoch": 0.5832911392405064, "grad_norm": 0.5997261965444728, "learning_rate": 3.996449295365782e-05, "loss": 0.3362, "step": 144 }, { "epoch": 0.5873417721518988, "grad_norm": 0.5859512305610277, "learning_rate": 3.996103194004467e-05, "loss": 0.3403, "step": 145 }, { "epoch": 0.5913924050632912, "grad_norm": 0.5836851879585024, "learning_rate": 3.995741016302441e-05, "loss": 0.3375, "step": 146 }, { "epoch": 0.5954430379746836, "grad_norm": 0.53785832632969, "learning_rate": 3.9953627651766364e-05, "loss": 0.339, "step": 147 }, { "epoch": 0.599493670886076, "grad_norm": 0.6013979632172686, "learning_rate": 3.9949684436734325e-05, "loss": 0.3416, "step": 148 }, { "epoch": 0.6035443037974684, "grad_norm": 0.6576873724016494, "learning_rate": 3.994558054968643e-05, "loss": 0.3467, "step": 149 }, { "epoch": 0.6075949367088608, "grad_norm": 0.531718444014578, "learning_rate": 3.994131602367481e-05, "loss": 0.3373, "step": 150 }, { "epoch": 0.6116455696202532, "grad_norm": 0.5748919861990145, "learning_rate": 3.9936890893045376e-05, "loss": 0.3484, "step": 151 }, { "epoch": 0.6156962025316456, "grad_norm": 0.6036185963080564, "learning_rate": 3.993230519343752e-05, "loss": 0.3367, "step": 152 }, { "epoch": 0.619746835443038, "grad_norm": 0.5774311293433187, "learning_rate": 3.992755896178383e-05, "loss": 0.335, "step": 153 }, { "epoch": 0.6237974683544304, "grad_norm": 0.5536813030035657, "learning_rate": 3.992265223630981e-05, "loss": 0.3437, "step": 154 }, { "epoch": 0.6278481012658228, "grad_norm": 0.5461856944536939, "learning_rate": 3.991758505653355e-05, "loss": 0.353, "step": 155 }, { "epoch": 0.6318987341772152, "grad_norm": 0.5917588644022594, "learning_rate": 3.991235746326543e-05, "loss": 0.3521, "step": 156 }, { "epoch": 0.6359493670886076, "grad_norm": 0.53332415970403, "learning_rate": 3.9906969498607745e-05, "loss": 0.3329, "step": 157 }, { "epoch": 0.64, "grad_norm": 0.7212586362940234, "learning_rate": 3.990142120595444e-05, "loss": 0.3354, "step": 158 }, { "epoch": 0.6440506329113924, "grad_norm": 0.5631574897218024, "learning_rate": 3.98957126299907e-05, "loss": 0.3481, "step": 159 }, { "epoch": 0.6481012658227848, "grad_norm": 0.5006705198669466, "learning_rate": 3.9889843816692596e-05, "loss": 0.3294, "step": 160 }, { "epoch": 0.6521518987341772, "grad_norm": 0.5459029515680469, "learning_rate": 3.9883814813326766e-05, "loss": 0.3283, "step": 161 }, { "epoch": 0.6562025316455696, "grad_norm": 0.5148119089962142, "learning_rate": 3.9877625668449956e-05, "loss": 0.323, "step": 162 }, { "epoch": 0.660253164556962, "grad_norm": 0.49078945889810005, "learning_rate": 3.98712764319087e-05, "loss": 0.3384, "step": 163 }, { "epoch": 0.6643037974683544, "grad_norm": 0.6162527534013139, "learning_rate": 3.9864767154838864e-05, "loss": 0.3447, "step": 164 }, { "epoch": 0.6683544303797468, "grad_norm": 0.5335871618671262, "learning_rate": 3.9858097889665277e-05, "loss": 0.3345, "step": 165 }, { "epoch": 0.6724050632911392, "grad_norm": 0.5851532868653434, "learning_rate": 3.985126869010129e-05, "loss": 0.3465, "step": 166 }, { "epoch": 0.6764556962025317, "grad_norm": 0.44967016255514874, "learning_rate": 3.984427961114833e-05, "loss": 0.3341, "step": 167 }, { "epoch": 0.6805063291139241, "grad_norm": 0.5268573455860243, "learning_rate": 3.9837130709095475e-05, "loss": 0.3265, "step": 168 }, { "epoch": 0.6845569620253165, "grad_norm": 0.5487211695517631, "learning_rate": 3.982982204151901e-05, "loss": 0.3268, "step": 169 }, { "epoch": 0.6886075949367089, "grad_norm": 0.44345004185583314, "learning_rate": 3.982235366728193e-05, "loss": 0.3256, "step": 170 }, { "epoch": 0.6926582278481013, "grad_norm": 0.5145216833901087, "learning_rate": 3.9814725646533505e-05, "loss": 0.3337, "step": 171 }, { "epoch": 0.6967088607594937, "grad_norm": 0.4300434005685066, "learning_rate": 3.9806938040708746e-05, "loss": 0.3348, "step": 172 }, { "epoch": 0.7007594936708861, "grad_norm": 0.536269559103447, "learning_rate": 3.9798990912527976e-05, "loss": 0.3308, "step": 173 }, { "epoch": 0.7048101265822785, "grad_norm": 0.47235948453757154, "learning_rate": 3.979088432599627e-05, "loss": 0.33, "step": 174 }, { "epoch": 0.7088607594936709, "grad_norm": 0.4916351157475063, "learning_rate": 3.9782618346402964e-05, "loss": 0.3169, "step": 175 }, { "epoch": 0.7129113924050633, "grad_norm": 0.448380642724122, "learning_rate": 3.977419304032111e-05, "loss": 0.3388, "step": 176 }, { "epoch": 0.7169620253164557, "grad_norm": 0.5018455929116044, "learning_rate": 3.976560847560697e-05, "loss": 0.332, "step": 177 }, { "epoch": 0.7210126582278481, "grad_norm": 0.4401400433532376, "learning_rate": 3.9756864721399456e-05, "loss": 0.3185, "step": 178 }, { "epoch": 0.7250632911392405, "grad_norm": 0.471027913677774, "learning_rate": 3.974796184811956e-05, "loss": 0.3316, "step": 179 }, { "epoch": 0.7291139240506329, "grad_norm": 0.5073475016039629, "learning_rate": 3.973889992746979e-05, "loss": 0.3349, "step": 180 }, { "epoch": 0.7331645569620253, "grad_norm": 0.45950736890970284, "learning_rate": 3.972967903243361e-05, "loss": 0.3426, "step": 181 }, { "epoch": 0.7372151898734177, "grad_norm": 0.44851674526509006, "learning_rate": 3.972029923727486e-05, "loss": 0.3301, "step": 182 }, { "epoch": 0.7412658227848101, "grad_norm": 0.5294969091714065, "learning_rate": 3.971076061753709e-05, "loss": 0.3468, "step": 183 }, { "epoch": 0.7453164556962025, "grad_norm": 0.44377219519429006, "learning_rate": 3.9701063250043066e-05, "loss": 0.354, "step": 184 }, { "epoch": 0.7493670886075949, "grad_norm": 0.5159011769311572, "learning_rate": 3.969120721289402e-05, "loss": 0.3174, "step": 185 }, { "epoch": 0.7534177215189873, "grad_norm": 0.5546236992676333, "learning_rate": 3.9681192585469146e-05, "loss": 0.342, "step": 186 }, { "epoch": 0.7574683544303797, "grad_norm": 0.47176297831573055, "learning_rate": 3.9671019448424865e-05, "loss": 0.3384, "step": 187 }, { "epoch": 0.7615189873417721, "grad_norm": 0.5429086645267254, "learning_rate": 3.966068788369422e-05, "loss": 0.3312, "step": 188 }, { "epoch": 0.7655696202531646, "grad_norm": 0.5290910538818989, "learning_rate": 3.965019797448622e-05, "loss": 0.3205, "step": 189 }, { "epoch": 0.769620253164557, "grad_norm": 0.46484171768634164, "learning_rate": 3.963954980528515e-05, "loss": 0.3319, "step": 190 }, { "epoch": 0.7736708860759494, "grad_norm": 0.5689569717711954, "learning_rate": 3.9628743461849905e-05, "loss": 0.3274, "step": 191 }, { "epoch": 0.7777215189873418, "grad_norm": 0.4360262515950889, "learning_rate": 3.961777903121329e-05, "loss": 0.3205, "step": 192 }, { "epoch": 0.7817721518987342, "grad_norm": 0.5433962524439369, "learning_rate": 3.960665660168131e-05, "loss": 0.3258, "step": 193 }, { "epoch": 0.7858227848101266, "grad_norm": 0.4831282102987305, "learning_rate": 3.9595376262832485e-05, "loss": 0.3366, "step": 194 }, { "epoch": 0.789873417721519, "grad_norm": 0.4789040630741959, "learning_rate": 3.9583938105517127e-05, "loss": 0.3361, "step": 195 }, { "epoch": 0.7939240506329114, "grad_norm": 0.48040373369372424, "learning_rate": 3.957234222185657e-05, "loss": 0.3323, "step": 196 }, { "epoch": 0.7979746835443038, "grad_norm": 0.45674964047471817, "learning_rate": 3.9560588705242474e-05, "loss": 0.3243, "step": 197 }, { "epoch": 0.8020253164556962, "grad_norm": 0.5059484162860639, "learning_rate": 3.954867765033605e-05, "loss": 0.3376, "step": 198 }, { "epoch": 0.8060759493670886, "grad_norm": 0.47892827218190487, "learning_rate": 3.953660915306728e-05, "loss": 0.3204, "step": 199 }, { "epoch": 0.810126582278481, "grad_norm": 0.6902259501781849, "learning_rate": 3.952438331063419e-05, "loss": 0.3316, "step": 200 }, { "epoch": 0.8141772151898734, "grad_norm": 0.4415843187207279, "learning_rate": 3.951200022150205e-05, "loss": 0.3322, "step": 201 }, { "epoch": 0.8182278481012658, "grad_norm": 0.4995642886758986, "learning_rate": 3.949945998540253e-05, "loss": 0.3286, "step": 202 }, { "epoch": 0.8222784810126582, "grad_norm": 0.4893039742175873, "learning_rate": 3.9486762703332993e-05, "loss": 0.3337, "step": 203 }, { "epoch": 0.8263291139240506, "grad_norm": 0.4672617888112675, "learning_rate": 3.947390847755559e-05, "loss": 0.3345, "step": 204 }, { "epoch": 0.830379746835443, "grad_norm": 0.5544034485434493, "learning_rate": 3.946089741159648e-05, "loss": 0.3269, "step": 205 }, { "epoch": 0.8344303797468354, "grad_norm": 0.5544241629102327, "learning_rate": 3.944772961024501e-05, "loss": 0.3325, "step": 206 }, { "epoch": 0.8384810126582278, "grad_norm": 0.5226898576750412, "learning_rate": 3.943440517955285e-05, "loss": 0.3371, "step": 207 }, { "epoch": 0.8425316455696202, "grad_norm": 0.572014555369674, "learning_rate": 3.9420924226833126e-05, "loss": 0.3185, "step": 208 }, { "epoch": 0.8465822784810126, "grad_norm": 0.4945155690238942, "learning_rate": 3.9407286860659566e-05, "loss": 0.3272, "step": 209 }, { "epoch": 0.850632911392405, "grad_norm": 0.5697562374409489, "learning_rate": 3.9393493190865657e-05, "loss": 0.3322, "step": 210 }, { "epoch": 0.8546835443037974, "grad_norm": 0.4471409749162931, "learning_rate": 3.937954332854371e-05, "loss": 0.316, "step": 211 }, { "epoch": 0.8587341772151899, "grad_norm": 0.534776593242497, "learning_rate": 3.9365437386044016e-05, "loss": 0.3266, "step": 212 }, { "epoch": 0.8627848101265823, "grad_norm": 0.5032434943881124, "learning_rate": 3.935117547697387e-05, "loss": 0.3298, "step": 213 }, { "epoch": 0.8668354430379747, "grad_norm": 0.4445767852142823, "learning_rate": 3.933675771619675e-05, "loss": 0.3294, "step": 214 }, { "epoch": 0.8708860759493671, "grad_norm": 0.4973154423817258, "learning_rate": 3.932218421983131e-05, "loss": 0.3211, "step": 215 }, { "epoch": 0.8749367088607595, "grad_norm": 0.4409134895565638, "learning_rate": 3.9307455105250484e-05, "loss": 0.3349, "step": 216 }, { "epoch": 0.8789873417721519, "grad_norm": 0.5298229136896988, "learning_rate": 3.929257049108054e-05, "loss": 0.3386, "step": 217 }, { "epoch": 0.8830379746835443, "grad_norm": 0.40238108239125053, "learning_rate": 3.927753049720011e-05, "loss": 0.3307, "step": 218 }, { "epoch": 0.8870886075949367, "grad_norm": 0.4908350420599685, "learning_rate": 3.9262335244739234e-05, "loss": 0.3332, "step": 219 }, { "epoch": 0.8911392405063291, "grad_norm": 0.46271804041597786, "learning_rate": 3.92469848560784e-05, "loss": 0.3305, "step": 220 }, { "epoch": 0.8951898734177215, "grad_norm": 0.4334139278746186, "learning_rate": 3.923147945484751e-05, "loss": 0.3315, "step": 221 }, { "epoch": 0.8992405063291139, "grad_norm": 0.5210445918705947, "learning_rate": 3.9215819165924956e-05, "loss": 0.3358, "step": 222 }, { "epoch": 0.9032911392405063, "grad_norm": 0.4459529026497199, "learning_rate": 3.920000411543654e-05, "loss": 0.3259, "step": 223 }, { "epoch": 0.9073417721518987, "grad_norm": 0.5130491015125151, "learning_rate": 3.9184034430754495e-05, "loss": 0.3193, "step": 224 }, { "epoch": 0.9113924050632911, "grad_norm": 0.46877149188628386, "learning_rate": 3.916791024049648e-05, "loss": 0.3103, "step": 225 }, { "epoch": 0.9154430379746835, "grad_norm": 0.4956403983580926, "learning_rate": 3.91516316745245e-05, "loss": 0.3292, "step": 226 }, { "epoch": 0.9194936708860759, "grad_norm": 0.43536012711652883, "learning_rate": 3.913519886394389e-05, "loss": 0.3271, "step": 227 }, { "epoch": 0.9235443037974683, "grad_norm": 0.4417096683642713, "learning_rate": 3.911861194110225e-05, "loss": 0.3167, "step": 228 }, { "epoch": 0.9275949367088607, "grad_norm": 0.49243143908123693, "learning_rate": 3.910187103958837e-05, "loss": 0.3397, "step": 229 }, { "epoch": 0.9316455696202531, "grad_norm": 0.4425040714956997, "learning_rate": 3.908497629423117e-05, "loss": 0.3348, "step": 230 }, { "epoch": 0.9356962025316455, "grad_norm": 0.48557222516177106, "learning_rate": 3.9067927841098614e-05, "loss": 0.3155, "step": 231 }, { "epoch": 0.9397468354430379, "grad_norm": 0.4198350007114086, "learning_rate": 3.9050725817496594e-05, "loss": 0.349, "step": 232 }, { "epoch": 0.9437974683544303, "grad_norm": 0.5102048984274443, "learning_rate": 3.9033370361967844e-05, "loss": 0.3189, "step": 233 }, { "epoch": 0.9478481012658228, "grad_norm": 0.4083401396391044, "learning_rate": 3.901586161429081e-05, "loss": 0.3221, "step": 234 }, { "epoch": 0.9518987341772152, "grad_norm": 0.4265296454362207, "learning_rate": 3.8998199715478545e-05, "loss": 0.3248, "step": 235 }, { "epoch": 0.9559493670886076, "grad_norm": 0.44678549252844385, "learning_rate": 3.8980384807777564e-05, "loss": 0.3169, "step": 236 }, { "epoch": 0.96, "grad_norm": 0.4223409730574559, "learning_rate": 3.896241703466667e-05, "loss": 0.3268, "step": 237 }, { "epoch": 0.9640506329113924, "grad_norm": 0.42038002220515447, "learning_rate": 3.894429654085585e-05, "loss": 0.3322, "step": 238 }, { "epoch": 0.9681012658227848, "grad_norm": 0.4312237617122363, "learning_rate": 3.892602347228505e-05, "loss": 0.331, "step": 239 }, { "epoch": 0.9721518987341772, "grad_norm": 0.39533005904125407, "learning_rate": 3.890759797612307e-05, "loss": 0.3276, "step": 240 }, { "epoch": 0.9762025316455696, "grad_norm": 0.4463071449351665, "learning_rate": 3.888902020076632e-05, "loss": 0.3338, "step": 241 }, { "epoch": 0.980253164556962, "grad_norm": 0.3970153048994021, "learning_rate": 3.887029029583764e-05, "loss": 0.3309, "step": 242 }, { "epoch": 0.9843037974683544, "grad_norm": 0.48800768623650354, "learning_rate": 3.8851408412185125e-05, "loss": 0.3234, "step": 243 }, { "epoch": 0.9883544303797468, "grad_norm": 0.36951585599880554, "learning_rate": 3.8832374701880855e-05, "loss": 0.3238, "step": 244 }, { "epoch": 0.9924050632911392, "grad_norm": 0.4390676797988026, "learning_rate": 3.881318931821972e-05, "loss": 0.323, "step": 245 }, { "epoch": 0.9964556962025316, "grad_norm": 0.41248995970903257, "learning_rate": 3.879385241571817e-05, "loss": 0.332, "step": 246 }, { "epoch": 1.0020253164556963, "grad_norm": 0.40813213709277896, "learning_rate": 3.8774364150112955e-05, "loss": 0.3029, "step": 247 }, { "epoch": 1.0060759493670886, "grad_norm": 0.4198090261561659, "learning_rate": 3.8754724678359884e-05, "loss": 0.2986, "step": 248 }, { "epoch": 1.010126582278481, "grad_norm": 0.4791712754899254, "learning_rate": 3.873493415863256e-05, "loss": 0.2906, "step": 249 }, { "epoch": 1.0141772151898734, "grad_norm": 0.4231291530457333, "learning_rate": 3.871499275032111e-05, "loss": 0.2851, "step": 250 }, { "epoch": 1.0182278481012659, "grad_norm": 0.4978227860649792, "learning_rate": 3.869490061403091e-05, "loss": 0.2772, "step": 251 }, { "epoch": 1.0222784810126582, "grad_norm": 0.44279359256674355, "learning_rate": 3.867465791158124e-05, "loss": 0.2792, "step": 252 }, { "epoch": 1.0263291139240507, "grad_norm": 0.42284523043899724, "learning_rate": 3.865426480600407e-05, "loss": 0.2865, "step": 253 }, { "epoch": 1.030379746835443, "grad_norm": 0.436073748561062, "learning_rate": 3.863372146154264e-05, "loss": 0.2938, "step": 254 }, { "epoch": 1.0344303797468355, "grad_norm": 0.41915549047663775, "learning_rate": 3.861302804365024e-05, "loss": 0.2865, "step": 255 }, { "epoch": 1.0384810126582278, "grad_norm": 0.5613789500885332, "learning_rate": 3.85921847189888e-05, "loss": 0.3022, "step": 256 }, { "epoch": 1.0425316455696203, "grad_norm": 0.404423843388825, "learning_rate": 3.85711916554276e-05, "loss": 0.2837, "step": 257 }, { "epoch": 1.0465822784810126, "grad_norm": 0.5300927898110976, "learning_rate": 3.85500490220419e-05, "loss": 0.2862, "step": 258 }, { "epoch": 1.0506329113924051, "grad_norm": 0.413621246224311, "learning_rate": 3.852875698911154e-05, "loss": 0.279, "step": 259 }, { "epoch": 1.0546835443037974, "grad_norm": 0.4873591016024607, "learning_rate": 3.850731572811963e-05, "loss": 0.2938, "step": 260 }, { "epoch": 1.05873417721519, "grad_norm": 0.4293093876989896, "learning_rate": 3.848572541175116e-05, "loss": 0.2846, "step": 261 }, { "epoch": 1.0627848101265822, "grad_norm": 0.46755397914300023, "learning_rate": 3.846398621389154e-05, "loss": 0.2906, "step": 262 }, { "epoch": 1.0668354430379747, "grad_norm": 0.4163746891875974, "learning_rate": 3.84420983096253e-05, "loss": 0.2812, "step": 263 }, { "epoch": 1.070886075949367, "grad_norm": 0.47642652749891545, "learning_rate": 3.8420061875234606e-05, "loss": 0.2846, "step": 264 }, { "epoch": 1.0749367088607595, "grad_norm": 0.4152474050742314, "learning_rate": 3.839787708819787e-05, "loss": 0.2835, "step": 265 }, { "epoch": 1.0789873417721518, "grad_norm": 0.42530664364400844, "learning_rate": 3.8375544127188325e-05, "loss": 0.2784, "step": 266 }, { "epoch": 1.0830379746835443, "grad_norm": 0.46413858641132916, "learning_rate": 3.8353063172072564e-05, "loss": 0.3036, "step": 267 }, { "epoch": 1.0870886075949366, "grad_norm": 0.37041776096544127, "learning_rate": 3.8330434403909105e-05, "loss": 0.2712, "step": 268 }, { "epoch": 1.0911392405063292, "grad_norm": 0.4601051239025973, "learning_rate": 3.8307658004946934e-05, "loss": 0.2993, "step": 269 }, { "epoch": 1.0951898734177214, "grad_norm": 0.3968347355583008, "learning_rate": 3.8284734158624046e-05, "loss": 0.2806, "step": 270 }, { "epoch": 1.099240506329114, "grad_norm": 0.4729665087450276, "learning_rate": 3.826166304956594e-05, "loss": 0.2832, "step": 271 }, { "epoch": 1.1032911392405063, "grad_norm": 0.38698875916804953, "learning_rate": 3.8238444863584164e-05, "loss": 0.2792, "step": 272 }, { "epoch": 1.1073417721518988, "grad_norm": 0.4722743472380661, "learning_rate": 3.821507978767479e-05, "loss": 0.3013, "step": 273 }, { "epoch": 1.111392405063291, "grad_norm": 0.43697229860645653, "learning_rate": 3.819156801001693e-05, "loss": 0.3043, "step": 274 }, { "epoch": 1.1154430379746836, "grad_norm": 0.44652271381521025, "learning_rate": 3.816790971997121e-05, "loss": 0.292, "step": 275 }, { "epoch": 1.1194936708860759, "grad_norm": 0.41552860929774477, "learning_rate": 3.8144105108078246e-05, "loss": 0.2799, "step": 276 }, { "epoch": 1.1235443037974684, "grad_norm": 0.4586631360034, "learning_rate": 3.81201543660571e-05, "loss": 0.2815, "step": 277 }, { "epoch": 1.1275949367088607, "grad_norm": 0.37359305677433036, "learning_rate": 3.809605768680377e-05, "loss": 0.2935, "step": 278 }, { "epoch": 1.1316455696202532, "grad_norm": 0.41417872503223285, "learning_rate": 3.807181526438958e-05, "loss": 0.2847, "step": 279 }, { "epoch": 1.1356962025316455, "grad_norm": 0.41627589065270404, "learning_rate": 3.8047427294059697e-05, "loss": 0.2761, "step": 280 }, { "epoch": 1.139746835443038, "grad_norm": 0.4099218458634838, "learning_rate": 3.802289397223145e-05, "loss": 0.3005, "step": 281 }, { "epoch": 1.1437974683544303, "grad_norm": 0.4224129070011162, "learning_rate": 3.7998215496492854e-05, "loss": 0.2839, "step": 282 }, { "epoch": 1.1478481012658228, "grad_norm": 0.41989835499688644, "learning_rate": 3.797339206560096e-05, "loss": 0.2814, "step": 283 }, { "epoch": 1.1518987341772151, "grad_norm": 0.3842273922949148, "learning_rate": 3.794842387948027e-05, "loss": 0.2882, "step": 284 }, { "epoch": 1.1559493670886076, "grad_norm": 0.4610866359510784, "learning_rate": 3.7923311139221114e-05, "loss": 0.2826, "step": 285 }, { "epoch": 1.16, "grad_norm": 0.4658143778817596, "learning_rate": 3.7898054047078054e-05, "loss": 0.2822, "step": 286 }, { "epoch": 1.1640506329113924, "grad_norm": 0.44246000936049834, "learning_rate": 3.787265280646825e-05, "loss": 0.2866, "step": 287 }, { "epoch": 1.1681012658227847, "grad_norm": 0.48484701072954556, "learning_rate": 3.7847107621969786e-05, "loss": 0.2822, "step": 288 }, { "epoch": 1.1721518987341772, "grad_norm": 0.5476630544279082, "learning_rate": 3.7821418699320064e-05, "loss": 0.2937, "step": 289 }, { "epoch": 1.1762025316455695, "grad_norm": 0.426380575924502, "learning_rate": 3.7795586245414145e-05, "loss": 0.2788, "step": 290 }, { "epoch": 1.180253164556962, "grad_norm": 0.5168856086051592, "learning_rate": 3.776961046830306e-05, "loss": 0.28, "step": 291 }, { "epoch": 1.1843037974683543, "grad_norm": 0.4174272069889726, "learning_rate": 3.774349157719215e-05, "loss": 0.2838, "step": 292 }, { "epoch": 1.1883544303797469, "grad_norm": 0.4360881094610555, "learning_rate": 3.7717229782439365e-05, "loss": 0.283, "step": 293 }, { "epoch": 1.1924050632911392, "grad_norm": 0.3994910510109684, "learning_rate": 3.769082529555359e-05, "loss": 0.2838, "step": 294 }, { "epoch": 1.1964556962025317, "grad_norm": 0.4184341331731547, "learning_rate": 3.766427832919294e-05, "loss": 0.2921, "step": 295 }, { "epoch": 1.200506329113924, "grad_norm": 0.4108530825174392, "learning_rate": 3.7637589097163024e-05, "loss": 0.3006, "step": 296 }, { "epoch": 1.2045569620253165, "grad_norm": 0.4648838015594172, "learning_rate": 3.761075781441526e-05, "loss": 0.2992, "step": 297 }, { "epoch": 1.2086075949367088, "grad_norm": 0.3930692730914696, "learning_rate": 3.75837846970451e-05, "loss": 0.2905, "step": 298 }, { "epoch": 1.2126582278481013, "grad_norm": 0.4145078438297483, "learning_rate": 3.755666996229032e-05, "loss": 0.2932, "step": 299 }, { "epoch": 1.2167088607594936, "grad_norm": 0.39182298997235687, "learning_rate": 3.752941382852927e-05, "loss": 0.2931, "step": 300 }, { "epoch": 1.220759493670886, "grad_norm": 0.37933578123221, "learning_rate": 3.7502016515279115e-05, "loss": 0.2861, "step": 301 }, { "epoch": 1.2248101265822784, "grad_norm": 0.371955918612292, "learning_rate": 3.7474478243194043e-05, "loss": 0.2844, "step": 302 }, { "epoch": 1.228860759493671, "grad_norm": 0.39281668030241634, "learning_rate": 3.744679923406351e-05, "loss": 0.2944, "step": 303 }, { "epoch": 1.2329113924050632, "grad_norm": 0.3992291315252381, "learning_rate": 3.741897971081043e-05, "loss": 0.2974, "step": 304 }, { "epoch": 1.2369620253164557, "grad_norm": 0.43374702854925457, "learning_rate": 3.739101989748946e-05, "loss": 0.2872, "step": 305 }, { "epoch": 1.241012658227848, "grad_norm": 0.43176583209698005, "learning_rate": 3.7362920019285066e-05, "loss": 0.2999, "step": 306 }, { "epoch": 1.2450632911392405, "grad_norm": 0.4169548198742266, "learning_rate": 3.73346803025098e-05, "loss": 0.2967, "step": 307 }, { "epoch": 1.2491139240506328, "grad_norm": 0.3853249462932398, "learning_rate": 3.730630097460247e-05, "loss": 0.2925, "step": 308 }, { "epoch": 1.2531645569620253, "grad_norm": 0.3763541096943806, "learning_rate": 3.727778226412628e-05, "loss": 0.2909, "step": 309 }, { "epoch": 1.2572151898734178, "grad_norm": 0.3855451173712659, "learning_rate": 3.7249124400767006e-05, "loss": 0.29, "step": 310 }, { "epoch": 1.2612658227848101, "grad_norm": 0.39264847396443836, "learning_rate": 3.722032761533114e-05, "loss": 0.2844, "step": 311 }, { "epoch": 1.2653164556962024, "grad_norm": 0.3495309537733776, "learning_rate": 3.719139213974403e-05, "loss": 0.292, "step": 312 }, { "epoch": 1.269367088607595, "grad_norm": 0.39591085048805447, "learning_rate": 3.7162318207048006e-05, "loss": 0.283, "step": 313 }, { "epoch": 1.2734177215189875, "grad_norm": 0.3637541915069588, "learning_rate": 3.713310605140055e-05, "loss": 0.2909, "step": 314 }, { "epoch": 1.2774683544303798, "grad_norm": 0.3759748188108481, "learning_rate": 3.710375590807233e-05, "loss": 0.2872, "step": 315 }, { "epoch": 1.281518987341772, "grad_norm": 0.41426086219208824, "learning_rate": 3.7074268013445365e-05, "loss": 0.2908, "step": 316 }, { "epoch": 1.2855696202531646, "grad_norm": 0.35838518415115944, "learning_rate": 3.7044642605011114e-05, "loss": 0.287, "step": 317 }, { "epoch": 1.289620253164557, "grad_norm": 0.3970770776289624, "learning_rate": 3.701487992136854e-05, "loss": 0.3006, "step": 318 }, { "epoch": 1.2936708860759494, "grad_norm": 0.3996555547468859, "learning_rate": 3.69849802022222e-05, "loss": 0.2971, "step": 319 }, { "epoch": 1.2977215189873417, "grad_norm": 0.41819982466545574, "learning_rate": 3.6954943688380334e-05, "loss": 0.2957, "step": 320 }, { "epoch": 1.3017721518987342, "grad_norm": 0.36984713699699273, "learning_rate": 3.692477062175289e-05, "loss": 0.2773, "step": 321 }, { "epoch": 1.3058227848101267, "grad_norm": 0.4261864141616112, "learning_rate": 3.689446124534958e-05, "loss": 0.2909, "step": 322 }, { "epoch": 1.309873417721519, "grad_norm": 0.3833505238171726, "learning_rate": 3.686401580327799e-05, "loss": 0.2794, "step": 323 }, { "epoch": 1.3139240506329113, "grad_norm": 0.4437176558388381, "learning_rate": 3.683343454074149e-05, "loss": 0.2941, "step": 324 }, { "epoch": 1.3179746835443038, "grad_norm": 0.4149127803572897, "learning_rate": 3.6802717704037386e-05, "loss": 0.2715, "step": 325 }, { "epoch": 1.3220253164556963, "grad_norm": 0.4854972792771002, "learning_rate": 3.6771865540554855e-05, "loss": 0.2922, "step": 326 }, { "epoch": 1.3260759493670886, "grad_norm": 0.3976267170623021, "learning_rate": 3.674087829877297e-05, "loss": 0.289, "step": 327 }, { "epoch": 1.330126582278481, "grad_norm": 0.4906334622837946, "learning_rate": 3.6709756228258735e-05, "loss": 0.2903, "step": 328 }, { "epoch": 1.3341772151898734, "grad_norm": 0.36306070615368835, "learning_rate": 3.667849957966501e-05, "loss": 0.2891, "step": 329 }, { "epoch": 1.338227848101266, "grad_norm": 0.4311014851098733, "learning_rate": 3.6647108604728546e-05, "loss": 0.2875, "step": 330 }, { "epoch": 1.3422784810126582, "grad_norm": 0.35644664535607457, "learning_rate": 3.661558355626795e-05, "loss": 0.2828, "step": 331 }, { "epoch": 1.3463291139240505, "grad_norm": 0.4094919107349934, "learning_rate": 3.658392468818163e-05, "loss": 0.276, "step": 332 }, { "epoch": 1.350379746835443, "grad_norm": 0.33805829262575077, "learning_rate": 3.655213225544574e-05, "loss": 0.2977, "step": 333 }, { "epoch": 1.3544303797468356, "grad_norm": 0.4306799462630922, "learning_rate": 3.652020651411218e-05, "loss": 0.285, "step": 334 }, { "epoch": 1.3584810126582278, "grad_norm": 0.3411012249491007, "learning_rate": 3.6488147721306474e-05, "loss": 0.2804, "step": 335 }, { "epoch": 1.3625316455696201, "grad_norm": 0.4153935619674362, "learning_rate": 3.645595613522574e-05, "loss": 0.2921, "step": 336 }, { "epoch": 1.3665822784810127, "grad_norm": 0.36408582389721855, "learning_rate": 3.642363201513657e-05, "loss": 0.2921, "step": 337 }, { "epoch": 1.3706329113924052, "grad_norm": 0.3880261212470533, "learning_rate": 3.6391175621373006e-05, "loss": 0.2751, "step": 338 }, { "epoch": 1.3746835443037975, "grad_norm": 0.404667795342007, "learning_rate": 3.6358587215334355e-05, "loss": 0.2668, "step": 339 }, { "epoch": 1.3787341772151898, "grad_norm": 0.33843565388008706, "learning_rate": 3.632586705948318e-05, "loss": 0.291, "step": 340 }, { "epoch": 1.3827848101265823, "grad_norm": 0.36802427403825755, "learning_rate": 3.629301541734311e-05, "loss": 0.2898, "step": 341 }, { "epoch": 1.3868354430379748, "grad_norm": 0.3717335529509393, "learning_rate": 3.626003255349676e-05, "loss": 0.2881, "step": 342 }, { "epoch": 1.390886075949367, "grad_norm": 0.38517632759878845, "learning_rate": 3.622691873358357e-05, "loss": 0.2768, "step": 343 }, { "epoch": 1.3949367088607594, "grad_norm": 0.34677205308800507, "learning_rate": 3.61936742242977e-05, "loss": 0.286, "step": 344 }, { "epoch": 1.398987341772152, "grad_norm": 0.38360498897037465, "learning_rate": 3.6160299293385864e-05, "loss": 0.2865, "step": 345 }, { "epoch": 1.4030379746835444, "grad_norm": 0.35886906188557516, "learning_rate": 3.612679420964516e-05, "loss": 0.2788, "step": 346 }, { "epoch": 1.4070886075949367, "grad_norm": 0.3570769724479581, "learning_rate": 3.609315924292092e-05, "loss": 0.2867, "step": 347 }, { "epoch": 1.411139240506329, "grad_norm": 0.33064904222362146, "learning_rate": 3.6059394664104554e-05, "loss": 0.2922, "step": 348 }, { "epoch": 1.4151898734177215, "grad_norm": 0.37872007586859, "learning_rate": 3.602550074513133e-05, "loss": 0.285, "step": 349 }, { "epoch": 1.419240506329114, "grad_norm": 0.3712977303904389, "learning_rate": 3.599147775897822e-05, "loss": 0.2863, "step": 350 }, { "epoch": 1.4232911392405063, "grad_norm": 0.3674223189125509, "learning_rate": 3.595732597966167e-05, "loss": 0.2968, "step": 351 }, { "epoch": 1.4273417721518986, "grad_norm": 0.38253371617978144, "learning_rate": 3.592304568223542e-05, "loss": 0.2779, "step": 352 }, { "epoch": 1.4313924050632911, "grad_norm": 0.3703673759495799, "learning_rate": 3.588863714278826e-05, "loss": 0.2974, "step": 353 }, { "epoch": 1.4354430379746836, "grad_norm": 0.3555578792469796, "learning_rate": 3.585410063844186e-05, "loss": 0.2859, "step": 354 }, { "epoch": 1.439493670886076, "grad_norm": 0.3974285116556952, "learning_rate": 3.581943644734846e-05, "loss": 0.2981, "step": 355 }, { "epoch": 1.4435443037974682, "grad_norm": 0.3571641898699622, "learning_rate": 3.578464484868869e-05, "loss": 0.2791, "step": 356 }, { "epoch": 1.4475949367088607, "grad_norm": 0.40183749042900896, "learning_rate": 3.5749726122669316e-05, "loss": 0.2869, "step": 357 }, { "epoch": 1.4516455696202533, "grad_norm": 0.36867346627942915, "learning_rate": 3.5714680550520943e-05, "loss": 0.2747, "step": 358 }, { "epoch": 1.4556962025316456, "grad_norm": 0.39877957763627786, "learning_rate": 3.5679508414495794e-05, "loss": 0.2895, "step": 359 }, { "epoch": 1.4597468354430378, "grad_norm": 0.3533618295648068, "learning_rate": 3.564420999786543e-05, "loss": 0.2898, "step": 360 }, { "epoch": 1.4637974683544304, "grad_norm": 0.3863706626297576, "learning_rate": 3.560878558491842e-05, "loss": 0.2897, "step": 361 }, { "epoch": 1.4678481012658229, "grad_norm": 0.34110953104077757, "learning_rate": 3.5573235460958145e-05, "loss": 0.2918, "step": 362 }, { "epoch": 1.4718987341772152, "grad_norm": 0.3761622276868551, "learning_rate": 3.553755991230039e-05, "loss": 0.2957, "step": 363 }, { "epoch": 1.4759493670886075, "grad_norm": 0.39504731001427085, "learning_rate": 3.5501759226271144e-05, "loss": 0.2926, "step": 364 }, { "epoch": 1.48, "grad_norm": 0.3608048319704179, "learning_rate": 3.546583369120419e-05, "loss": 0.2797, "step": 365 }, { "epoch": 1.4840506329113925, "grad_norm": 0.37352361578413373, "learning_rate": 3.5429783596438864e-05, "loss": 0.2878, "step": 366 }, { "epoch": 1.4881012658227848, "grad_norm": 0.39918407979609033, "learning_rate": 3.539360923231766e-05, "loss": 0.2868, "step": 367 }, { "epoch": 1.492151898734177, "grad_norm": 0.3497967067617052, "learning_rate": 3.535731089018394e-05, "loss": 0.2849, "step": 368 }, { "epoch": 1.4962025316455696, "grad_norm": 0.4194502248977205, "learning_rate": 3.532088886237956e-05, "loss": 0.288, "step": 369 }, { "epoch": 1.5002531645569621, "grad_norm": 0.3601916936401368, "learning_rate": 3.528434344224253e-05, "loss": 0.2835, "step": 370 }, { "epoch": 1.5043037974683544, "grad_norm": 0.36928395040371254, "learning_rate": 3.524767492410464e-05, "loss": 0.2884, "step": 371 }, { "epoch": 1.5083544303797467, "grad_norm": 0.33411543342584527, "learning_rate": 3.521088360328908e-05, "loss": 0.2939, "step": 372 }, { "epoch": 1.5124050632911392, "grad_norm": 0.4088039125680305, "learning_rate": 3.517396977610811e-05, "loss": 0.3008, "step": 373 }, { "epoch": 1.5164556962025317, "grad_norm": 0.36162451661688344, "learning_rate": 3.5136933739860595e-05, "loss": 0.2894, "step": 374 }, { "epoch": 1.520506329113924, "grad_norm": 0.3539434229611253, "learning_rate": 3.509977579282971e-05, "loss": 0.2954, "step": 375 }, { "epoch": 1.5245569620253163, "grad_norm": 0.39211146966136934, "learning_rate": 3.5062496234280424e-05, "loss": 0.2865, "step": 376 }, { "epoch": 1.5286075949367088, "grad_norm": 0.38136650309692005, "learning_rate": 3.502509536445719e-05, "loss": 0.2856, "step": 377 }, { "epoch": 1.5326582278481014, "grad_norm": 0.40386423236497476, "learning_rate": 3.498757348458147e-05, "loss": 0.2835, "step": 378 }, { "epoch": 1.5367088607594936, "grad_norm": 0.39041064989490126, "learning_rate": 3.4949930896849324e-05, "loss": 0.2942, "step": 379 }, { "epoch": 1.540759493670886, "grad_norm": 0.34880918681283024, "learning_rate": 3.491216790442899e-05, "loss": 0.273, "step": 380 }, { "epoch": 1.5448101265822785, "grad_norm": 0.3863401871828532, "learning_rate": 3.487428481145839e-05, "loss": 0.2846, "step": 381 }, { "epoch": 1.548860759493671, "grad_norm": 0.36929313632205485, "learning_rate": 3.483628192304278e-05, "loss": 0.2804, "step": 382 }, { "epoch": 1.5529113924050633, "grad_norm": 0.35416844611412596, "learning_rate": 3.479815954525219e-05, "loss": 0.2756, "step": 383 }, { "epoch": 1.5569620253164556, "grad_norm": 0.40239511714442794, "learning_rate": 3.475991798511899e-05, "loss": 0.2793, "step": 384 }, { "epoch": 1.561012658227848, "grad_norm": 0.4127809164324532, "learning_rate": 3.4721557550635464e-05, "loss": 0.2984, "step": 385 }, { "epoch": 1.5650632911392406, "grad_norm": 0.37706439588549734, "learning_rate": 3.468307855075128e-05, "loss": 0.2866, "step": 386 }, { "epoch": 1.5691139240506329, "grad_norm": 0.34533588998888504, "learning_rate": 3.4644481295371005e-05, "loss": 0.2666, "step": 387 }, { "epoch": 1.5731645569620252, "grad_norm": 0.3765903206850051, "learning_rate": 3.460576609535163e-05, "loss": 0.2954, "step": 388 }, { "epoch": 1.5772151898734177, "grad_norm": 0.3796007419939592, "learning_rate": 3.456693326250006e-05, "loss": 0.2848, "step": 389 }, { "epoch": 1.5812658227848102, "grad_norm": 0.3856721420813229, "learning_rate": 3.452798310957058e-05, "loss": 0.2984, "step": 390 }, { "epoch": 1.5853164556962025, "grad_norm": 0.3559955692309453, "learning_rate": 3.4488915950262386e-05, "loss": 0.2841, "step": 391 }, { "epoch": 1.5893670886075948, "grad_norm": 0.36828317128584037, "learning_rate": 3.4449732099216985e-05, "loss": 0.2915, "step": 392 }, { "epoch": 1.5934177215189873, "grad_norm": 0.3588827982365104, "learning_rate": 3.441043187201574e-05, "loss": 0.282, "step": 393 }, { "epoch": 1.5974683544303798, "grad_norm": 0.3330001486575166, "learning_rate": 3.437101558517728e-05, "loss": 0.2927, "step": 394 }, { "epoch": 1.6015189873417721, "grad_norm": 0.38607685483724047, "learning_rate": 3.433148355615496e-05, "loss": 0.2924, "step": 395 }, { "epoch": 1.6055696202531644, "grad_norm": 0.3159620746828716, "learning_rate": 3.4291836103334294e-05, "loss": 0.2765, "step": 396 }, { "epoch": 1.609620253164557, "grad_norm": 0.3711631404379386, "learning_rate": 3.425207354603043e-05, "loss": 0.2935, "step": 397 }, { "epoch": 1.6136708860759494, "grad_norm": 0.41268107098759177, "learning_rate": 3.421219620448553e-05, "loss": 0.2776, "step": 398 }, { "epoch": 1.6177215189873417, "grad_norm": 0.35893485856578344, "learning_rate": 3.417220439986623e-05, "loss": 0.293, "step": 399 }, { "epoch": 1.621772151898734, "grad_norm": 0.3969603960057248, "learning_rate": 3.4132098454261024e-05, "loss": 0.2876, "step": 400 }, { "epoch": 1.6258227848101265, "grad_norm": 0.35602257360617107, "learning_rate": 3.4091878690677676e-05, "loss": 0.2832, "step": 401 }, { "epoch": 1.629873417721519, "grad_norm": 0.38210001592613474, "learning_rate": 3.405154543304065e-05, "loss": 0.2872, "step": 402 }, { "epoch": 1.6339240506329114, "grad_norm": 0.37747324959195644, "learning_rate": 3.401109900618843e-05, "loss": 0.2821, "step": 403 }, { "epoch": 1.6379746835443036, "grad_norm": 0.364982326082847, "learning_rate": 3.3970539735870996e-05, "loss": 0.2802, "step": 404 }, { "epoch": 1.6420253164556962, "grad_norm": 0.46016612054237654, "learning_rate": 3.392986794874714e-05, "loss": 0.2907, "step": 405 }, { "epoch": 1.6460759493670887, "grad_norm": 0.38023345195557035, "learning_rate": 3.388908397238184e-05, "loss": 0.2788, "step": 406 }, { "epoch": 1.650126582278481, "grad_norm": 0.40175074272796657, "learning_rate": 3.384818813524362e-05, "loss": 0.293, "step": 407 }, { "epoch": 1.6541772151898733, "grad_norm": 0.4025943931071708, "learning_rate": 3.380718076670195e-05, "loss": 0.2837, "step": 408 }, { "epoch": 1.6582278481012658, "grad_norm": 0.3822624339119545, "learning_rate": 3.376606219702454e-05, "loss": 0.2819, "step": 409 }, { "epoch": 1.6622784810126583, "grad_norm": 0.39561206636129814, "learning_rate": 3.372483275737468e-05, "loss": 0.282, "step": 410 }, { "epoch": 1.6663291139240506, "grad_norm": 0.358422345916927, "learning_rate": 3.368349277980861e-05, "loss": 0.278, "step": 411 }, { "epoch": 1.6703797468354429, "grad_norm": 0.47387893724410357, "learning_rate": 3.3642042597272844e-05, "loss": 0.2933, "step": 412 }, { "epoch": 1.6744303797468354, "grad_norm": 0.3547598072661075, "learning_rate": 3.360048254360144e-05, "loss": 0.2896, "step": 413 }, { "epoch": 1.678481012658228, "grad_norm": 0.4043430846334564, "learning_rate": 3.355881295351336e-05, "loss": 0.2749, "step": 414 }, { "epoch": 1.6825316455696202, "grad_norm": 0.41747576794953445, "learning_rate": 3.351703416260975e-05, "loss": 0.2973, "step": 415 }, { "epoch": 1.6865822784810125, "grad_norm": 0.3817401826062703, "learning_rate": 3.347514650737126e-05, "loss": 0.3004, "step": 416 }, { "epoch": 1.690632911392405, "grad_norm": 0.38924751408545244, "learning_rate": 3.3433150325155295e-05, "loss": 0.2793, "step": 417 }, { "epoch": 1.6946835443037975, "grad_norm": 0.35713562636790575, "learning_rate": 3.339104595419334e-05, "loss": 0.2838, "step": 418 }, { "epoch": 1.6987341772151898, "grad_norm": 0.368871390383488, "learning_rate": 3.3348833733588204e-05, "loss": 0.2812, "step": 419 }, { "epoch": 1.7027848101265821, "grad_norm": 0.3553852734401772, "learning_rate": 3.3306514003311305e-05, "loss": 0.2811, "step": 420 }, { "epoch": 1.7068354430379746, "grad_norm": 0.4004171042884104, "learning_rate": 3.326408710419996e-05, "loss": 0.2967, "step": 421 }, { "epoch": 1.7108860759493671, "grad_norm": 0.339358656254935, "learning_rate": 3.322155337795454e-05, "loss": 0.2848, "step": 422 }, { "epoch": 1.7149367088607594, "grad_norm": 0.4137849488129059, "learning_rate": 3.317891316713587e-05, "loss": 0.2896, "step": 423 }, { "epoch": 1.7189873417721517, "grad_norm": 0.3186130848475963, "learning_rate": 3.313616681516231e-05, "loss": 0.2935, "step": 424 }, { "epoch": 1.7230379746835442, "grad_norm": 0.39088047740521525, "learning_rate": 3.309331466630713e-05, "loss": 0.2764, "step": 425 }, { "epoch": 1.7270886075949368, "grad_norm": 0.3540035962585536, "learning_rate": 3.305035706569563e-05, "loss": 0.288, "step": 426 }, { "epoch": 1.7311392405063293, "grad_norm": 0.48640022440158565, "learning_rate": 3.3007294359302433e-05, "loss": 0.2887, "step": 427 }, { "epoch": 1.7351898734177216, "grad_norm": 0.33334626663968364, "learning_rate": 3.296412689394864e-05, "loss": 0.2935, "step": 428 }, { "epoch": 1.7392405063291139, "grad_norm": 0.4693619152273012, "learning_rate": 3.292085501729909e-05, "loss": 0.2827, "step": 429 }, { "epoch": 1.7432911392405064, "grad_norm": 0.3318646418879354, "learning_rate": 3.2877479077859534e-05, "loss": 0.286, "step": 430 }, { "epoch": 1.747341772151899, "grad_norm": 0.45956055311988786, "learning_rate": 3.283399942497381e-05, "loss": 0.2858, "step": 431 }, { "epoch": 1.7513924050632912, "grad_norm": 0.4081187912489, "learning_rate": 3.279041640882108e-05, "loss": 0.279, "step": 432 }, { "epoch": 1.7554430379746835, "grad_norm": 0.4032549342120343, "learning_rate": 3.2746730380412964e-05, "loss": 0.29, "step": 433 }, { "epoch": 1.759493670886076, "grad_norm": 0.36803699495942754, "learning_rate": 3.2702941691590726e-05, "loss": 0.2745, "step": 434 }, { "epoch": 1.7635443037974685, "grad_norm": 0.42145022502183876, "learning_rate": 3.265905069502244e-05, "loss": 0.2923, "step": 435 }, { "epoch": 1.7675949367088608, "grad_norm": 0.35747589036994487, "learning_rate": 3.261505774420016e-05, "loss": 0.2904, "step": 436 }, { "epoch": 1.771645569620253, "grad_norm": 0.4130631553051332, "learning_rate": 3.257096319343707e-05, "loss": 0.2967, "step": 437 }, { "epoch": 1.7756962025316456, "grad_norm": 0.33595608549343603, "learning_rate": 3.2526767397864614e-05, "loss": 0.2818, "step": 438 }, { "epoch": 1.7797468354430381, "grad_norm": 0.42230795302371715, "learning_rate": 3.248247071342966e-05, "loss": 0.2829, "step": 439 }, { "epoch": 1.7837974683544304, "grad_norm": 0.32959622846805015, "learning_rate": 3.243807349689161e-05, "loss": 0.275, "step": 440 }, { "epoch": 1.7878481012658227, "grad_norm": 0.4282128882361803, "learning_rate": 3.2393576105819544e-05, "loss": 0.2951, "step": 441 }, { "epoch": 1.7918987341772152, "grad_norm": 0.36652928347092606, "learning_rate": 3.2348978898589333e-05, "loss": 0.2916, "step": 442 }, { "epoch": 1.7959493670886078, "grad_norm": 0.3788439750029412, "learning_rate": 3.230428223438075e-05, "loss": 0.2881, "step": 443 }, { "epoch": 1.8, "grad_norm": 0.38807542988721777, "learning_rate": 3.225948647317459e-05, "loss": 0.2792, "step": 444 }, { "epoch": 1.8040506329113923, "grad_norm": 0.36362420613303553, "learning_rate": 3.2214591975749745e-05, "loss": 0.2894, "step": 445 }, { "epoch": 1.8081012658227849, "grad_norm": 0.39030357276215394, "learning_rate": 3.216959910368034e-05, "loss": 0.295, "step": 446 }, { "epoch": 1.8121518987341774, "grad_norm": 0.34448294388425077, "learning_rate": 3.212450821933277e-05, "loss": 0.2852, "step": 447 }, { "epoch": 1.8162025316455697, "grad_norm": 0.3793322434309718, "learning_rate": 3.207931968586281e-05, "loss": 0.2714, "step": 448 }, { "epoch": 1.820253164556962, "grad_norm": 0.36194102203716005, "learning_rate": 3.203403386721272e-05, "loss": 0.2884, "step": 449 }, { "epoch": 1.8243037974683545, "grad_norm": 0.39678754805564315, "learning_rate": 3.1988651128108245e-05, "loss": 0.2752, "step": 450 }, { "epoch": 1.828354430379747, "grad_norm": 0.35878724860369965, "learning_rate": 3.194317183405573e-05, "loss": 0.2875, "step": 451 }, { "epoch": 1.8324050632911393, "grad_norm": 0.3627976718454411, "learning_rate": 3.189759635133914e-05, "loss": 0.2688, "step": 452 }, { "epoch": 1.8364556962025316, "grad_norm": 0.36426379955800336, "learning_rate": 3.185192504701718e-05, "loss": 0.2812, "step": 453 }, { "epoch": 1.840506329113924, "grad_norm": 0.3850140541931581, "learning_rate": 3.1806158288920234e-05, "loss": 0.2862, "step": 454 }, { "epoch": 1.8445569620253166, "grad_norm": 0.3379549913785118, "learning_rate": 3.1760296445647477e-05, "loss": 0.2779, "step": 455 }, { "epoch": 1.848607594936709, "grad_norm": 0.36687680052653127, "learning_rate": 3.1714339886563896e-05, "loss": 0.2854, "step": 456 }, { "epoch": 1.8526582278481012, "grad_norm": 0.3703334463104137, "learning_rate": 3.166828898179731e-05, "loss": 0.2884, "step": 457 }, { "epoch": 1.8567088607594937, "grad_norm": 0.37374297463435263, "learning_rate": 3.162214410223536e-05, "loss": 0.2807, "step": 458 }, { "epoch": 1.8607594936708862, "grad_norm": 0.33461746970783063, "learning_rate": 3.157590561952257e-05, "loss": 0.2771, "step": 459 }, { "epoch": 1.8648101265822785, "grad_norm": 0.3584657290667073, "learning_rate": 3.152957390605732e-05, "loss": 0.281, "step": 460 }, { "epoch": 1.8688607594936708, "grad_norm": 0.3377893529722125, "learning_rate": 3.148314933498886e-05, "loss": 0.2857, "step": 461 }, { "epoch": 1.8729113924050633, "grad_norm": 0.39648130201994286, "learning_rate": 3.143663228021431e-05, "loss": 0.283, "step": 462 }, { "epoch": 1.8769620253164558, "grad_norm": 0.345437254685188, "learning_rate": 3.1390023116375624e-05, "loss": 0.2871, "step": 463 }, { "epoch": 1.8810126582278481, "grad_norm": 0.3491428685995151, "learning_rate": 3.134332221885661e-05, "loss": 0.2769, "step": 464 }, { "epoch": 1.8850632911392404, "grad_norm": 0.36860677484309096, "learning_rate": 3.129652996377987e-05, "loss": 0.29, "step": 465 }, { "epoch": 1.889113924050633, "grad_norm": 0.36820490121413557, "learning_rate": 3.12496467280038e-05, "loss": 0.2824, "step": 466 }, { "epoch": 1.8931645569620255, "grad_norm": 0.37488219400133554, "learning_rate": 3.120267288911952e-05, "loss": 0.3014, "step": 467 }, { "epoch": 1.8972151898734178, "grad_norm": 0.3388423969914111, "learning_rate": 3.11556088254479e-05, "loss": 0.2875, "step": 468 }, { "epoch": 1.90126582278481, "grad_norm": 0.3595137078528882, "learning_rate": 3.11084549160364e-05, "loss": 0.2934, "step": 469 }, { "epoch": 1.9053164556962026, "grad_norm": 0.32674174137971373, "learning_rate": 3.106121154065615e-05, "loss": 0.272, "step": 470 }, { "epoch": 1.909367088607595, "grad_norm": 0.4298050739441802, "learning_rate": 3.1013879079798805e-05, "loss": 0.2935, "step": 471 }, { "epoch": 1.9134177215189874, "grad_norm": 0.39009783463202835, "learning_rate": 3.096645791467348e-05, "loss": 0.2883, "step": 472 }, { "epoch": 1.9174683544303797, "grad_norm": 0.35489213667550057, "learning_rate": 3.091894842720373e-05, "loss": 0.2846, "step": 473 }, { "epoch": 1.9215189873417722, "grad_norm": 0.35419758276599533, "learning_rate": 3.0871351000024425e-05, "loss": 0.2876, "step": 474 }, { "epoch": 1.9255696202531647, "grad_norm": 0.3356840590195632, "learning_rate": 3.0823666016478716e-05, "loss": 0.2914, "step": 475 }, { "epoch": 1.929620253164557, "grad_norm": 0.3709132191986837, "learning_rate": 3.0775893860614896e-05, "loss": 0.2795, "step": 476 }, { "epoch": 1.9336708860759493, "grad_norm": 0.3516005063859416, "learning_rate": 3.0728034917183336e-05, "loss": 0.2798, "step": 477 }, { "epoch": 1.9377215189873418, "grad_norm": 0.32033993996875554, "learning_rate": 3.06800895716334e-05, "loss": 0.2877, "step": 478 }, { "epoch": 1.9417721518987343, "grad_norm": 0.3486757259482924, "learning_rate": 3.063205821011029e-05, "loss": 0.2879, "step": 479 }, { "epoch": 1.9458227848101266, "grad_norm": 0.32559604660219804, "learning_rate": 3.0583941219452016e-05, "loss": 0.2838, "step": 480 }, { "epoch": 1.949873417721519, "grad_norm": 0.3393192076619708, "learning_rate": 3.053573898718618e-05, "loss": 0.2956, "step": 481 }, { "epoch": 1.9539240506329114, "grad_norm": 0.3389000153518252, "learning_rate": 3.0487451901526956e-05, "loss": 0.2806, "step": 482 }, { "epoch": 1.957974683544304, "grad_norm": 0.3452673148390943, "learning_rate": 3.0439080351371875e-05, "loss": 0.2912, "step": 483 }, { "epoch": 1.9620253164556962, "grad_norm": 0.32560900630919687, "learning_rate": 3.0390624726298764e-05, "loss": 0.2903, "step": 484 }, { "epoch": 1.9660759493670885, "grad_norm": 0.3534696920263292, "learning_rate": 3.034208541656255e-05, "loss": 0.2806, "step": 485 }, { "epoch": 1.970126582278481, "grad_norm": 0.3685334162685568, "learning_rate": 3.029346281309218e-05, "loss": 0.2891, "step": 486 }, { "epoch": 1.9741772151898735, "grad_norm": 0.32681496652432596, "learning_rate": 3.0244757307487415e-05, "loss": 0.287, "step": 487 }, { "epoch": 1.9782278481012658, "grad_norm": 0.36133665925971514, "learning_rate": 3.019596929201569e-05, "loss": 0.287, "step": 488 }, { "epoch": 1.9822784810126581, "grad_norm": 0.3703279486192102, "learning_rate": 3.0147099159608985e-05, "loss": 0.2834, "step": 489 }, { "epoch": 1.9863291139240506, "grad_norm": 0.3182108445492053, "learning_rate": 3.0098147303860616e-05, "loss": 0.2787, "step": 490 }, { "epoch": 1.9903797468354432, "grad_norm": 0.353921133422431, "learning_rate": 3.0049114119022117e-05, "loss": 0.287, "step": 491 }, { "epoch": 1.9944303797468355, "grad_norm": 0.3136328480790407, "learning_rate": 3.0000000000000004e-05, "loss": 0.289, "step": 492 }, { "epoch": 1.9984810126582278, "grad_norm": 0.311898144047653, "learning_rate": 2.995080534235264e-05, "loss": 0.2673, "step": 493 }, { "epoch": 2.0040506329113925, "grad_norm": 0.386284867752039, "learning_rate": 2.9901530542287044e-05, "loss": 0.2348, "step": 494 }, { "epoch": 2.008101265822785, "grad_norm": 0.3340386696495949, "learning_rate": 2.9852175996655676e-05, "loss": 0.23, "step": 495 }, { "epoch": 2.012151898734177, "grad_norm": 0.351371118183595, "learning_rate": 2.980274210295326e-05, "loss": 0.2249, "step": 496 }, { "epoch": 2.0162025316455696, "grad_norm": 0.4558632477135829, "learning_rate": 2.9753229259313578e-05, "loss": 0.237, "step": 497 }, { "epoch": 2.020253164556962, "grad_norm": 0.33661584578757753, "learning_rate": 2.9703637864506274e-05, "loss": 0.2215, "step": 498 }, { "epoch": 2.0243037974683546, "grad_norm": 0.3613891078870842, "learning_rate": 2.965396831793362e-05, "loss": 0.2304, "step": 499 }, { "epoch": 2.0283544303797467, "grad_norm": 0.33926317269529854, "learning_rate": 2.9604221019627316e-05, "loss": 0.2288, "step": 500 }, { "epoch": 2.0324050632911392, "grad_norm": 0.3690887356862079, "learning_rate": 2.955439637024526e-05, "loss": 0.2364, "step": 501 }, { "epoch": 2.0364556962025318, "grad_norm": 0.34606557409822486, "learning_rate": 2.9504494771068334e-05, "loss": 0.2228, "step": 502 }, { "epoch": 2.0405063291139243, "grad_norm": 0.3793008311766855, "learning_rate": 2.9454516623997156e-05, "loss": 0.2279, "step": 503 }, { "epoch": 2.0445569620253163, "grad_norm": 0.35407639303344285, "learning_rate": 2.9404462331548847e-05, "loss": 0.2203, "step": 504 }, { "epoch": 2.048607594936709, "grad_norm": 0.3576596777457015, "learning_rate": 2.93543322968538e-05, "loss": 0.2309, "step": 505 }, { "epoch": 2.0526582278481014, "grad_norm": 0.35378429336832623, "learning_rate": 2.9304126923652428e-05, "loss": 0.2287, "step": 506 }, { "epoch": 2.056708860759494, "grad_norm": 0.3411118994778694, "learning_rate": 2.9253846616291896e-05, "loss": 0.2184, "step": 507 }, { "epoch": 2.060759493670886, "grad_norm": 0.32724885510323515, "learning_rate": 2.9203491779722896e-05, "loss": 0.2322, "step": 508 }, { "epoch": 2.0648101265822785, "grad_norm": 0.34553490202549053, "learning_rate": 2.9153062819496357e-05, "loss": 0.2314, "step": 509 }, { "epoch": 2.068860759493671, "grad_norm": 0.3340336450913032, "learning_rate": 2.9102560141760178e-05, "loss": 0.2272, "step": 510 }, { "epoch": 2.0729113924050635, "grad_norm": 0.2996885741478258, "learning_rate": 2.9051984153256004e-05, "loss": 0.2267, "step": 511 }, { "epoch": 2.0769620253164556, "grad_norm": 0.3735780995744048, "learning_rate": 2.900133526131588e-05, "loss": 0.2228, "step": 512 }, { "epoch": 2.081012658227848, "grad_norm": 0.3196169917277184, "learning_rate": 2.8950613873859025e-05, "loss": 0.2166, "step": 513 }, { "epoch": 2.0850632911392406, "grad_norm": 0.342340265273401, "learning_rate": 2.8899820399388515e-05, "loss": 0.2222, "step": 514 }, { "epoch": 2.089113924050633, "grad_norm": 0.34321038507226254, "learning_rate": 2.8848955246988012e-05, "loss": 0.222, "step": 515 }, { "epoch": 2.093164556962025, "grad_norm": 0.36991051373922135, "learning_rate": 2.879801882631847e-05, "loss": 0.225, "step": 516 }, { "epoch": 2.0972151898734177, "grad_norm": 0.3720544230922529, "learning_rate": 2.8747011547614808e-05, "loss": 0.2291, "step": 517 }, { "epoch": 2.1012658227848102, "grad_norm": 0.37989137333516076, "learning_rate": 2.8695933821682635e-05, "loss": 0.2198, "step": 518 }, { "epoch": 2.1053164556962027, "grad_norm": 0.34791051418537794, "learning_rate": 2.864478605989494e-05, "loss": 0.2183, "step": 519 }, { "epoch": 2.109367088607595, "grad_norm": 0.33489255465230405, "learning_rate": 2.8593568674188765e-05, "loss": 0.2211, "step": 520 }, { "epoch": 2.1134177215189873, "grad_norm": 0.3231270755966945, "learning_rate": 2.8542282077061892e-05, "loss": 0.2281, "step": 521 }, { "epoch": 2.11746835443038, "grad_norm": 0.34303768720119016, "learning_rate": 2.8490926681569523e-05, "loss": 0.2264, "step": 522 }, { "epoch": 2.1215189873417724, "grad_norm": 0.3426347324224885, "learning_rate": 2.8439502901320956e-05, "loss": 0.2282, "step": 523 }, { "epoch": 2.1255696202531644, "grad_norm": 0.34724093682642954, "learning_rate": 2.8388011150476237e-05, "loss": 0.2316, "step": 524 }, { "epoch": 2.129620253164557, "grad_norm": 0.3155460284000724, "learning_rate": 2.8336451843742866e-05, "loss": 0.2173, "step": 525 }, { "epoch": 2.1336708860759495, "grad_norm": 0.3234693620740511, "learning_rate": 2.8284825396372387e-05, "loss": 0.2174, "step": 526 }, { "epoch": 2.137721518987342, "grad_norm": 0.3108926257192208, "learning_rate": 2.8233132224157132e-05, "loss": 0.2145, "step": 527 }, { "epoch": 2.141772151898734, "grad_norm": 0.32396709597725487, "learning_rate": 2.8181372743426805e-05, "loss": 0.2275, "step": 528 }, { "epoch": 2.1458227848101266, "grad_norm": 0.35131301218116806, "learning_rate": 2.8129547371045128e-05, "loss": 0.2246, "step": 529 }, { "epoch": 2.149873417721519, "grad_norm": 0.3424390618225487, "learning_rate": 2.8077656524406534e-05, "loss": 0.2297, "step": 530 }, { "epoch": 2.1539240506329116, "grad_norm": 0.307179677565078, "learning_rate": 2.802570062143278e-05, "loss": 0.2267, "step": 531 }, { "epoch": 2.1579746835443037, "grad_norm": 0.338975930368688, "learning_rate": 2.7973680080569555e-05, "loss": 0.2302, "step": 532 }, { "epoch": 2.162025316455696, "grad_norm": 0.35699826781385663, "learning_rate": 2.792159532078314e-05, "loss": 0.245, "step": 533 }, { "epoch": 2.1660759493670887, "grad_norm": 0.3530424458345945, "learning_rate": 2.7869446761557033e-05, "loss": 0.2336, "step": 534 }, { "epoch": 2.170126582278481, "grad_norm": 0.3335515831542766, "learning_rate": 2.781723482288857e-05, "loss": 0.223, "step": 535 }, { "epoch": 2.1741772151898733, "grad_norm": 0.3469160978434825, "learning_rate": 2.7764959925285517e-05, "loss": 0.2265, "step": 536 }, { "epoch": 2.178227848101266, "grad_norm": 0.36117155710013943, "learning_rate": 2.771262248976272e-05, "loss": 0.2272, "step": 537 }, { "epoch": 2.1822784810126583, "grad_norm": 0.36599939712327495, "learning_rate": 2.7660222937838677e-05, "loss": 0.236, "step": 538 }, { "epoch": 2.186329113924051, "grad_norm": 0.32080598371745456, "learning_rate": 2.7607761691532186e-05, "loss": 0.2299, "step": 539 }, { "epoch": 2.190379746835443, "grad_norm": 0.3670412807626775, "learning_rate": 2.7555239173358916e-05, "loss": 0.2199, "step": 540 }, { "epoch": 2.1944303797468354, "grad_norm": 0.3771213935300867, "learning_rate": 2.7502655806328e-05, "loss": 0.2231, "step": 541 }, { "epoch": 2.198481012658228, "grad_norm": 0.31691640192613657, "learning_rate": 2.7450012013938648e-05, "loss": 0.2193, "step": 542 }, { "epoch": 2.2025316455696204, "grad_norm": 0.35187043113708244, "learning_rate": 2.739730822017673e-05, "loss": 0.2201, "step": 543 }, { "epoch": 2.2065822784810125, "grad_norm": 0.3217441454481017, "learning_rate": 2.7344544849511355e-05, "loss": 0.2356, "step": 544 }, { "epoch": 2.210632911392405, "grad_norm": 0.3490013334343527, "learning_rate": 2.7291722326891456e-05, "loss": 0.2264, "step": 545 }, { "epoch": 2.2146835443037975, "grad_norm": 0.29915883669201304, "learning_rate": 2.723884107774236e-05, "loss": 0.2295, "step": 546 }, { "epoch": 2.21873417721519, "grad_norm": 0.3758899075159843, "learning_rate": 2.718590152796239e-05, "loss": 0.2274, "step": 547 }, { "epoch": 2.222784810126582, "grad_norm": 0.33524487461046226, "learning_rate": 2.71329041039194e-05, "loss": 0.2329, "step": 548 }, { "epoch": 2.2268354430379746, "grad_norm": 0.40293735211370474, "learning_rate": 2.7079849232447357e-05, "loss": 0.2388, "step": 549 }, { "epoch": 2.230886075949367, "grad_norm": 0.3068816002911051, "learning_rate": 2.7026737340842895e-05, "loss": 0.2332, "step": 550 }, { "epoch": 2.2349367088607597, "grad_norm": 0.3710671211959028, "learning_rate": 2.697356885686189e-05, "loss": 0.2372, "step": 551 }, { "epoch": 2.2389873417721518, "grad_norm": 0.32502388891042727, "learning_rate": 2.6920344208716014e-05, "loss": 0.2384, "step": 552 }, { "epoch": 2.2430379746835443, "grad_norm": 0.33713338891771805, "learning_rate": 2.6867063825069252e-05, "loss": 0.2407, "step": 553 }, { "epoch": 2.247088607594937, "grad_norm": 0.35204390632977156, "learning_rate": 2.6813728135034494e-05, "loss": 0.2309, "step": 554 }, { "epoch": 2.2511392405063293, "grad_norm": 0.3233734524879218, "learning_rate": 2.6760337568170056e-05, "loss": 0.2326, "step": 555 }, { "epoch": 2.2551898734177214, "grad_norm": 0.3679996360594078, "learning_rate": 2.6706892554476226e-05, "loss": 0.2361, "step": 556 }, { "epoch": 2.259240506329114, "grad_norm": 0.31981652393839066, "learning_rate": 2.6653393524391795e-05, "loss": 0.2191, "step": 557 }, { "epoch": 2.2632911392405064, "grad_norm": 0.3020390508736238, "learning_rate": 2.6599840908790592e-05, "loss": 0.2317, "step": 558 }, { "epoch": 2.267341772151899, "grad_norm": 0.33513972393878955, "learning_rate": 2.6546235138978028e-05, "loss": 0.2358, "step": 559 }, { "epoch": 2.271392405063291, "grad_norm": 0.3040050175421357, "learning_rate": 2.6492576646687597e-05, "loss": 0.2341, "step": 560 }, { "epoch": 2.2754430379746835, "grad_norm": 0.3077910624280179, "learning_rate": 2.6438865864077425e-05, "loss": 0.2305, "step": 561 }, { "epoch": 2.279493670886076, "grad_norm": 0.3183909605192464, "learning_rate": 2.6385103223726766e-05, "loss": 0.2307, "step": 562 }, { "epoch": 2.2835443037974685, "grad_norm": 0.31870205811677926, "learning_rate": 2.6331289158632537e-05, "loss": 0.2297, "step": 563 }, { "epoch": 2.2875949367088606, "grad_norm": 0.32085500601974853, "learning_rate": 2.6277424102205817e-05, "loss": 0.2263, "step": 564 }, { "epoch": 2.291645569620253, "grad_norm": 0.3246307198759553, "learning_rate": 2.6223508488268374e-05, "loss": 0.215, "step": 565 }, { "epoch": 2.2956962025316456, "grad_norm": 0.3057137292844907, "learning_rate": 2.6169542751049148e-05, "loss": 0.223, "step": 566 }, { "epoch": 2.299746835443038, "grad_norm": 0.33059668321650737, "learning_rate": 2.6115527325180754e-05, "loss": 0.2308, "step": 567 }, { "epoch": 2.3037974683544302, "grad_norm": 0.3172600663486833, "learning_rate": 2.606146264569603e-05, "loss": 0.2244, "step": 568 }, { "epoch": 2.3078481012658227, "grad_norm": 0.3052383563918037, "learning_rate": 2.6007349148024447e-05, "loss": 0.229, "step": 569 }, { "epoch": 2.3118987341772153, "grad_norm": 0.3334218876065349, "learning_rate": 2.5953187267988694e-05, "loss": 0.2355, "step": 570 }, { "epoch": 2.3159493670886078, "grad_norm": 0.3291836201656969, "learning_rate": 2.5898977441801097e-05, "loss": 0.2255, "step": 571 }, { "epoch": 2.32, "grad_norm": 0.3217624049845604, "learning_rate": 2.584472010606015e-05, "loss": 0.2232, "step": 572 }, { "epoch": 2.3240506329113924, "grad_norm": 0.33752920226440447, "learning_rate": 2.5790415697746976e-05, "loss": 0.2262, "step": 573 }, { "epoch": 2.328101265822785, "grad_norm": 0.3138798646590419, "learning_rate": 2.5736064654221808e-05, "loss": 0.2344, "step": 574 }, { "epoch": 2.3321518987341774, "grad_norm": 0.3530844812523061, "learning_rate": 2.568166741322048e-05, "loss": 0.2479, "step": 575 }, { "epoch": 2.3362025316455695, "grad_norm": 0.3207330997013087, "learning_rate": 2.56272244128509e-05, "loss": 0.2284, "step": 576 }, { "epoch": 2.340253164556962, "grad_norm": 0.3545302030323795, "learning_rate": 2.55727360915895e-05, "loss": 0.223, "step": 577 }, { "epoch": 2.3443037974683545, "grad_norm": 0.3508917274373573, "learning_rate": 2.5518202888277734e-05, "loss": 0.2289, "step": 578 }, { "epoch": 2.348354430379747, "grad_norm": 0.35256888003218706, "learning_rate": 2.5463625242118523e-05, "loss": 0.2239, "step": 579 }, { "epoch": 2.352405063291139, "grad_norm": 0.33706842591877445, "learning_rate": 2.5409003592672723e-05, "loss": 0.238, "step": 580 }, { "epoch": 2.3564556962025316, "grad_norm": 0.3127796027174602, "learning_rate": 2.535433837985559e-05, "loss": 0.2261, "step": 581 }, { "epoch": 2.360506329113924, "grad_norm": 0.3178050928210413, "learning_rate": 2.529963004393324e-05, "loss": 0.2361, "step": 582 }, { "epoch": 2.3645569620253166, "grad_norm": 0.3273109252304113, "learning_rate": 2.524487902551908e-05, "loss": 0.2162, "step": 583 }, { "epoch": 2.3686075949367087, "grad_norm": 0.28487931044109094, "learning_rate": 2.519008576557029e-05, "loss": 0.2251, "step": 584 }, { "epoch": 2.372658227848101, "grad_norm": 0.3256294033964462, "learning_rate": 2.5135250705384254e-05, "loss": 0.2361, "step": 585 }, { "epoch": 2.3767088607594937, "grad_norm": 0.3159547528316452, "learning_rate": 2.5080374286595007e-05, "loss": 0.2307, "step": 586 }, { "epoch": 2.3807594936708862, "grad_norm": 0.3262745501538403, "learning_rate": 2.5025456951169677e-05, "loss": 0.2291, "step": 587 }, { "epoch": 2.3848101265822783, "grad_norm": 0.32267695318009926, "learning_rate": 2.4970499141404942e-05, "loss": 0.2172, "step": 588 }, { "epoch": 2.388860759493671, "grad_norm": 0.3349234088386378, "learning_rate": 2.491550129992345e-05, "loss": 0.237, "step": 589 }, { "epoch": 2.3929113924050633, "grad_norm": 0.31366914213531083, "learning_rate": 2.486046386967024e-05, "loss": 0.229, "step": 590 }, { "epoch": 2.396962025316456, "grad_norm": 0.31918269411832284, "learning_rate": 2.4805387293909214e-05, "loss": 0.2272, "step": 591 }, { "epoch": 2.401012658227848, "grad_norm": 0.319853166211096, "learning_rate": 2.4750272016219552e-05, "loss": 0.2281, "step": 592 }, { "epoch": 2.4050632911392404, "grad_norm": 0.35014147674914076, "learning_rate": 2.4695118480492114e-05, "loss": 0.2299, "step": 593 }, { "epoch": 2.409113924050633, "grad_norm": 0.33344859794086296, "learning_rate": 2.4639927130925898e-05, "loss": 0.2316, "step": 594 }, { "epoch": 2.4131645569620255, "grad_norm": 0.3307424748773881, "learning_rate": 2.458469841202444e-05, "loss": 0.2199, "step": 595 }, { "epoch": 2.4172151898734175, "grad_norm": 0.40421910904308095, "learning_rate": 2.452943276859226e-05, "loss": 0.2318, "step": 596 }, { "epoch": 2.42126582278481, "grad_norm": 0.325111590336323, "learning_rate": 2.447413064573125e-05, "loss": 0.2291, "step": 597 }, { "epoch": 2.4253164556962026, "grad_norm": 0.34688608594103965, "learning_rate": 2.4418792488837095e-05, "loss": 0.2207, "step": 598 }, { "epoch": 2.429367088607595, "grad_norm": 0.34240013430086497, "learning_rate": 2.4363418743595713e-05, "loss": 0.2315, "step": 599 }, { "epoch": 2.433417721518987, "grad_norm": 0.32833267027961877, "learning_rate": 2.430800985597963e-05, "loss": 0.2349, "step": 600 }, { "epoch": 2.4374683544303797, "grad_norm": 0.33045162343695134, "learning_rate": 2.4252566272244415e-05, "loss": 0.2287, "step": 601 }, { "epoch": 2.441518987341772, "grad_norm": 0.3379393717466279, "learning_rate": 2.4197088438925063e-05, "loss": 0.2243, "step": 602 }, { "epoch": 2.4455696202531647, "grad_norm": 0.33066064270480044, "learning_rate": 2.4141576802832417e-05, "loss": 0.2299, "step": 603 }, { "epoch": 2.449620253164557, "grad_norm": 0.3187575816153345, "learning_rate": 2.408603181104957e-05, "loss": 0.2327, "step": 604 }, { "epoch": 2.4536708860759493, "grad_norm": 0.3336170726930501, "learning_rate": 2.4030453910928245e-05, "loss": 0.2272, "step": 605 }, { "epoch": 2.457721518987342, "grad_norm": 0.3191820524636175, "learning_rate": 2.397484355008521e-05, "loss": 0.2229, "step": 606 }, { "epoch": 2.4617721518987343, "grad_norm": 0.30915433402269127, "learning_rate": 2.3919201176398662e-05, "loss": 0.2203, "step": 607 }, { "epoch": 2.4658227848101264, "grad_norm": 0.32600422936271606, "learning_rate": 2.3863527238004633e-05, "loss": 0.2334, "step": 608 }, { "epoch": 2.469873417721519, "grad_norm": 0.3469122714745186, "learning_rate": 2.380782218329337e-05, "loss": 0.2413, "step": 609 }, { "epoch": 2.4739240506329114, "grad_norm": 0.31124085666934653, "learning_rate": 2.3752086460905725e-05, "loss": 0.2243, "step": 610 }, { "epoch": 2.477974683544304, "grad_norm": 0.3196263806202107, "learning_rate": 2.3696320519729544e-05, "loss": 0.2354, "step": 611 }, { "epoch": 2.482025316455696, "grad_norm": 0.3359437940900918, "learning_rate": 2.3640524808896045e-05, "loss": 0.23, "step": 612 }, { "epoch": 2.4860759493670885, "grad_norm": 0.33327395605716564, "learning_rate": 2.3584699777776222e-05, "loss": 0.24, "step": 613 }, { "epoch": 2.490126582278481, "grad_norm": 0.33441250276179435, "learning_rate": 2.3528845875977195e-05, "loss": 0.2209, "step": 614 }, { "epoch": 2.4941772151898736, "grad_norm": 0.32046355433414114, "learning_rate": 2.3472963553338614e-05, "loss": 0.2339, "step": 615 }, { "epoch": 2.4982278481012656, "grad_norm": 0.2974436717594666, "learning_rate": 2.341705325992901e-05, "loss": 0.2337, "step": 616 }, { "epoch": 2.502278481012658, "grad_norm": 0.3053925905865147, "learning_rate": 2.336111544604222e-05, "loss": 0.233, "step": 617 }, { "epoch": 2.5063291139240507, "grad_norm": 0.3109408047054944, "learning_rate": 2.33051505621937e-05, "loss": 0.2254, "step": 618 }, { "epoch": 2.510379746835443, "grad_norm": 0.32478242223191206, "learning_rate": 2.324915905911693e-05, "loss": 0.229, "step": 619 }, { "epoch": 2.5144303797468357, "grad_norm": 0.3085018883343355, "learning_rate": 2.319314138775977e-05, "loss": 0.2051, "step": 620 }, { "epoch": 2.5184810126582278, "grad_norm": 0.329032469662047, "learning_rate": 2.3137097999280856e-05, "loss": 0.2294, "step": 621 }, { "epoch": 2.5225316455696203, "grad_norm": 0.3184119263317959, "learning_rate": 2.308102934504593e-05, "loss": 0.2391, "step": 622 }, { "epoch": 2.526582278481013, "grad_norm": 0.3034676386543481, "learning_rate": 2.3024935876624222e-05, "loss": 0.2298, "step": 623 }, { "epoch": 2.530632911392405, "grad_norm": 0.3335957197522153, "learning_rate": 2.2968818045784813e-05, "loss": 0.2229, "step": 624 }, { "epoch": 2.5346835443037974, "grad_norm": 0.31904898196036724, "learning_rate": 2.2912676304493006e-05, "loss": 0.2267, "step": 625 }, { "epoch": 2.53873417721519, "grad_norm": 0.3154489363302233, "learning_rate": 2.2856511104906668e-05, "loss": 0.2246, "step": 626 }, { "epoch": 2.5427848101265824, "grad_norm": 0.33054741307794216, "learning_rate": 2.2800322899372586e-05, "loss": 0.2298, "step": 627 }, { "epoch": 2.546835443037975, "grad_norm": 0.3163263670417468, "learning_rate": 2.2744112140422844e-05, "loss": 0.2444, "step": 628 }, { "epoch": 2.550886075949367, "grad_norm": 0.3225978218285014, "learning_rate": 2.2687879280771177e-05, "loss": 0.219, "step": 629 }, { "epoch": 2.5549367088607595, "grad_norm": 0.2985894175027459, "learning_rate": 2.26316247733093e-05, "loss": 0.2324, "step": 630 }, { "epoch": 2.558987341772152, "grad_norm": 0.29934392473134414, "learning_rate": 2.257534907110328e-05, "loss": 0.2333, "step": 631 }, { "epoch": 2.563037974683544, "grad_norm": 0.3090196852296368, "learning_rate": 2.2519052627389882e-05, "loss": 0.2327, "step": 632 }, { "epoch": 2.5670886075949366, "grad_norm": 0.31690059464579773, "learning_rate": 2.246273589557294e-05, "loss": 0.2344, "step": 633 }, { "epoch": 2.571139240506329, "grad_norm": 0.29947160064506284, "learning_rate": 2.240639932921966e-05, "loss": 0.2283, "step": 634 }, { "epoch": 2.5751898734177217, "grad_norm": 0.3274835866431638, "learning_rate": 2.2350043382056995e-05, "loss": 0.2303, "step": 635 }, { "epoch": 2.579240506329114, "grad_norm": 0.30391376026563466, "learning_rate": 2.2293668507968015e-05, "loss": 0.2211, "step": 636 }, { "epoch": 2.5832911392405062, "grad_norm": 0.3153493821015811, "learning_rate": 2.2237275160988186e-05, "loss": 0.228, "step": 637 }, { "epoch": 2.5873417721518988, "grad_norm": 0.3098201684538456, "learning_rate": 2.2180863795301787e-05, "loss": 0.2241, "step": 638 }, { "epoch": 2.5913924050632913, "grad_norm": 0.31244691450807865, "learning_rate": 2.212443486523819e-05, "loss": 0.2279, "step": 639 }, { "epoch": 2.5954430379746833, "grad_norm": 0.33642723894601784, "learning_rate": 2.2067988825268243e-05, "loss": 0.241, "step": 640 }, { "epoch": 2.599493670886076, "grad_norm": 0.3285379150365912, "learning_rate": 2.2011526130000596e-05, "loss": 0.2223, "step": 641 }, { "epoch": 2.6035443037974684, "grad_norm": 0.33316772544462125, "learning_rate": 2.1955047234178038e-05, "loss": 0.2255, "step": 642 }, { "epoch": 2.607594936708861, "grad_norm": 0.38243069968932275, "learning_rate": 2.1898552592673825e-05, "loss": 0.2295, "step": 643 }, { "epoch": 2.6116455696202534, "grad_norm": 0.32785865056681535, "learning_rate": 2.184204266048803e-05, "loss": 0.2303, "step": 644 }, { "epoch": 2.6156962025316455, "grad_norm": 0.35458168291317116, "learning_rate": 2.1785517892743887e-05, "loss": 0.2335, "step": 645 }, { "epoch": 2.619746835443038, "grad_norm": 0.3681796411526633, "learning_rate": 2.17289787446841e-05, "loss": 0.2248, "step": 646 }, { "epoch": 2.6237974683544305, "grad_norm": 0.32822564957697903, "learning_rate": 2.1672425671667198e-05, "loss": 0.2122, "step": 647 }, { "epoch": 2.6278481012658226, "grad_norm": 0.3292624539010464, "learning_rate": 2.161585912916385e-05, "loss": 0.232, "step": 648 }, { "epoch": 2.631898734177215, "grad_norm": 0.3133078886958593, "learning_rate": 2.1559279572753214e-05, "loss": 0.2293, "step": 649 }, { "epoch": 2.6359493670886076, "grad_norm": 0.3208031574233622, "learning_rate": 2.1502687458119268e-05, "loss": 0.2183, "step": 650 }, { "epoch": 2.64, "grad_norm": 0.31230470024071744, "learning_rate": 2.1446083241047116e-05, "loss": 0.2172, "step": 651 }, { "epoch": 2.6440506329113926, "grad_norm": 0.32515482032019444, "learning_rate": 2.1389467377419333e-05, "loss": 0.2478, "step": 652 }, { "epoch": 2.6481012658227847, "grad_norm": 0.30890767595294294, "learning_rate": 2.133284032321232e-05, "loss": 0.2215, "step": 653 }, { "epoch": 2.6521518987341772, "grad_norm": 0.29833606354088055, "learning_rate": 2.1276202534492566e-05, "loss": 0.2322, "step": 654 }, { "epoch": 2.6562025316455697, "grad_norm": 0.3074976851441407, "learning_rate": 2.121955446741306e-05, "loss": 0.2227, "step": 655 }, { "epoch": 2.660253164556962, "grad_norm": 0.3248324826003024, "learning_rate": 2.1162896578209517e-05, "loss": 0.2184, "step": 656 }, { "epoch": 2.6643037974683543, "grad_norm": 0.31287300093299275, "learning_rate": 2.1106229323196813e-05, "loss": 0.2284, "step": 657 }, { "epoch": 2.668354430379747, "grad_norm": 0.3186873326086335, "learning_rate": 2.1049553158765214e-05, "loss": 0.2314, "step": 658 }, { "epoch": 2.6724050632911394, "grad_norm": 0.294359966051873, "learning_rate": 2.0992868541376764e-05, "loss": 0.2231, "step": 659 }, { "epoch": 2.676455696202532, "grad_norm": 0.29729028260180923, "learning_rate": 2.093617592756158e-05, "loss": 0.2293, "step": 660 }, { "epoch": 2.680506329113924, "grad_norm": 0.30151014664944564, "learning_rate": 2.0879475773914167e-05, "loss": 0.2332, "step": 661 }, { "epoch": 2.6845569620253165, "grad_norm": 0.2999987449784973, "learning_rate": 2.082276853708978e-05, "loss": 0.2369, "step": 662 }, { "epoch": 2.688607594936709, "grad_norm": 0.3023274507070841, "learning_rate": 2.076605467380071e-05, "loss": 0.2353, "step": 663 }, { "epoch": 2.692658227848101, "grad_norm": 0.2985951080819497, "learning_rate": 2.0709334640812613e-05, "loss": 0.2383, "step": 664 }, { "epoch": 2.6967088607594936, "grad_norm": 0.3055601723897411, "learning_rate": 2.0652608894940824e-05, "loss": 0.2311, "step": 665 }, { "epoch": 2.700759493670886, "grad_norm": 0.32521750581219794, "learning_rate": 2.0595877893046722e-05, "loss": 0.2286, "step": 666 }, { "epoch": 2.7048101265822786, "grad_norm": 0.3191256234955041, "learning_rate": 2.0539142092033985e-05, "loss": 0.2253, "step": 667 }, { "epoch": 2.708860759493671, "grad_norm": 0.29596402237936853, "learning_rate": 2.048240194884496e-05, "loss": 0.2234, "step": 668 }, { "epoch": 2.712911392405063, "grad_norm": 0.29959827808810474, "learning_rate": 2.042565792045695e-05, "loss": 0.2255, "step": 669 }, { "epoch": 2.7169620253164557, "grad_norm": 0.31782402469140353, "learning_rate": 2.036891046387857e-05, "loss": 0.2394, "step": 670 }, { "epoch": 2.721012658227848, "grad_norm": 0.3009336455684078, "learning_rate": 2.0312160036146036e-05, "loss": 0.2307, "step": 671 }, { "epoch": 2.7250632911392403, "grad_norm": 0.31650140296283413, "learning_rate": 2.025540709431948e-05, "loss": 0.2254, "step": 672 }, { "epoch": 2.729113924050633, "grad_norm": 0.31504556693079927, "learning_rate": 2.0198652095479298e-05, "loss": 0.2271, "step": 673 }, { "epoch": 2.7331645569620253, "grad_norm": 0.3376726019782482, "learning_rate": 2.014189549672245e-05, "loss": 0.2229, "step": 674 }, { "epoch": 2.737215189873418, "grad_norm": 0.30468819879345516, "learning_rate": 2.0085137755158776e-05, "loss": 0.229, "step": 675 }, { "epoch": 2.7412658227848103, "grad_norm": 0.35086334085585247, "learning_rate": 2.0028379327907327e-05, "loss": 0.2272, "step": 676 }, { "epoch": 2.7453164556962024, "grad_norm": 0.3197962696632555, "learning_rate": 1.9971620672092676e-05, "loss": 0.2318, "step": 677 }, { "epoch": 2.749367088607595, "grad_norm": 0.28576453202887786, "learning_rate": 1.991486224484123e-05, "loss": 0.2261, "step": 678 }, { "epoch": 2.7534177215189874, "grad_norm": 0.313272957306259, "learning_rate": 1.985810450327756e-05, "loss": 0.2209, "step": 679 }, { "epoch": 2.7574683544303795, "grad_norm": 0.29430486204042394, "learning_rate": 1.9801347904520706e-05, "loss": 0.2263, "step": 680 }, { "epoch": 2.761518987341772, "grad_norm": 0.3177741345550705, "learning_rate": 1.974459290568053e-05, "loss": 0.2225, "step": 681 }, { "epoch": 2.7655696202531646, "grad_norm": 0.31112893133915936, "learning_rate": 1.968783996385397e-05, "loss": 0.2314, "step": 682 }, { "epoch": 2.769620253164557, "grad_norm": 0.2845439673741226, "learning_rate": 1.963108953612143e-05, "loss": 0.2335, "step": 683 }, { "epoch": 2.7736708860759496, "grad_norm": 0.30287989022068423, "learning_rate": 1.9574342079543056e-05, "loss": 0.2189, "step": 684 }, { "epoch": 2.7777215189873417, "grad_norm": 0.29925855432303694, "learning_rate": 1.9517598051155046e-05, "loss": 0.2185, "step": 685 }, { "epoch": 2.781772151898734, "grad_norm": 0.2807647200917759, "learning_rate": 1.9460857907966025e-05, "loss": 0.2213, "step": 686 }, { "epoch": 2.7858227848101267, "grad_norm": 0.33042456457991565, "learning_rate": 1.9404122106953285e-05, "loss": 0.2239, "step": 687 }, { "epoch": 2.7898734177215188, "grad_norm": 0.3490568986431759, "learning_rate": 1.9347391105059176e-05, "loss": 0.221, "step": 688 }, { "epoch": 2.7939240506329113, "grad_norm": 0.2837227312673863, "learning_rate": 1.92906653591874e-05, "loss": 0.2146, "step": 689 }, { "epoch": 2.797974683544304, "grad_norm": 0.3392734325982745, "learning_rate": 1.9233945326199295e-05, "loss": 0.2329, "step": 690 }, { "epoch": 2.8020253164556963, "grad_norm": 0.3278835077490305, "learning_rate": 1.917723146291022e-05, "loss": 0.2212, "step": 691 }, { "epoch": 2.806075949367089, "grad_norm": 0.30436536554604743, "learning_rate": 1.912052422608584e-05, "loss": 0.2321, "step": 692 }, { "epoch": 2.810126582278481, "grad_norm": 0.32719804246477485, "learning_rate": 1.9063824072438428e-05, "loss": 0.2256, "step": 693 }, { "epoch": 2.8141772151898734, "grad_norm": 0.3241485373241186, "learning_rate": 1.9007131458623246e-05, "loss": 0.2301, "step": 694 }, { "epoch": 2.818227848101266, "grad_norm": 0.3117007281515005, "learning_rate": 1.895044684123479e-05, "loss": 0.2368, "step": 695 }, { "epoch": 2.822278481012658, "grad_norm": 0.3096068410265423, "learning_rate": 1.8893770676803194e-05, "loss": 0.2262, "step": 696 }, { "epoch": 2.8263291139240505, "grad_norm": 0.3097539124445047, "learning_rate": 1.8837103421790486e-05, "loss": 0.2403, "step": 697 }, { "epoch": 2.830379746835443, "grad_norm": 0.2953831801204104, "learning_rate": 1.8780445532586952e-05, "loss": 0.2336, "step": 698 }, { "epoch": 2.8344303797468355, "grad_norm": 0.30211463075146344, "learning_rate": 1.872379746550743e-05, "loss": 0.2355, "step": 699 }, { "epoch": 2.838481012658228, "grad_norm": 0.30038074569647966, "learning_rate": 1.866715967678769e-05, "loss": 0.2276, "step": 700 }, { "epoch": 2.84253164556962, "grad_norm": 0.27325955762943327, "learning_rate": 1.861053262258067e-05, "loss": 0.2126, "step": 701 }, { "epoch": 2.8465822784810126, "grad_norm": 0.3237507285940527, "learning_rate": 1.8553916758952897e-05, "loss": 0.2298, "step": 702 }, { "epoch": 2.850632911392405, "grad_norm": 0.30142543836676555, "learning_rate": 1.8497312541880735e-05, "loss": 0.2237, "step": 703 }, { "epoch": 2.8546835443037972, "grad_norm": 0.30681397438612046, "learning_rate": 1.8440720427246786e-05, "loss": 0.2376, "step": 704 }, { "epoch": 2.8587341772151897, "grad_norm": 0.29990128699649615, "learning_rate": 1.8384140870836157e-05, "loss": 0.2272, "step": 705 }, { "epoch": 2.8627848101265823, "grad_norm": 0.3391741706838783, "learning_rate": 1.8327574328332806e-05, "loss": 0.2297, "step": 706 }, { "epoch": 2.8668354430379748, "grad_norm": 0.30228715752739127, "learning_rate": 1.8271021255315906e-05, "loss": 0.2192, "step": 707 }, { "epoch": 2.8708860759493673, "grad_norm": 0.28204244320912364, "learning_rate": 1.8214482107256117e-05, "loss": 0.2165, "step": 708 }, { "epoch": 2.8749367088607594, "grad_norm": 0.30649728881301247, "learning_rate": 1.8157957339511968e-05, "loss": 0.2356, "step": 709 }, { "epoch": 2.878987341772152, "grad_norm": 0.33711027265297716, "learning_rate": 1.8101447407326182e-05, "loss": 0.2344, "step": 710 }, { "epoch": 2.8830379746835444, "grad_norm": 0.29965263768215367, "learning_rate": 1.8044952765821966e-05, "loss": 0.2199, "step": 711 }, { "epoch": 2.8870886075949365, "grad_norm": 0.3067677996246315, "learning_rate": 1.7988473869999407e-05, "loss": 0.2214, "step": 712 }, { "epoch": 2.891139240506329, "grad_norm": 0.32381066576442075, "learning_rate": 1.7932011174731764e-05, "loss": 0.2311, "step": 713 }, { "epoch": 2.8951898734177215, "grad_norm": 0.2955331927433309, "learning_rate": 1.7875565134761817e-05, "loss": 0.2282, "step": 714 }, { "epoch": 2.899240506329114, "grad_norm": 0.31606134521638674, "learning_rate": 1.7819136204698226e-05, "loss": 0.2236, "step": 715 }, { "epoch": 2.9032911392405065, "grad_norm": 0.33693414443070546, "learning_rate": 1.776272483901182e-05, "loss": 0.2284, "step": 716 }, { "epoch": 2.9073417721518986, "grad_norm": 0.31075330529866607, "learning_rate": 1.7706331492031995e-05, "loss": 0.2263, "step": 717 }, { "epoch": 2.911392405063291, "grad_norm": 0.29025269864265074, "learning_rate": 1.764995661794301e-05, "loss": 0.2307, "step": 718 }, { "epoch": 2.9154430379746836, "grad_norm": 0.3576265417864713, "learning_rate": 1.759360067078035e-05, "loss": 0.2202, "step": 719 }, { "epoch": 2.9194936708860757, "grad_norm": 0.32213234711134736, "learning_rate": 1.7537264104427064e-05, "loss": 0.2235, "step": 720 }, { "epoch": 2.923544303797468, "grad_norm": 0.3327233179429874, "learning_rate": 1.748094737261012e-05, "loss": 0.2273, "step": 721 }, { "epoch": 2.9275949367088607, "grad_norm": 0.2965056575199383, "learning_rate": 1.7424650928896726e-05, "loss": 0.2307, "step": 722 }, { "epoch": 2.9316455696202532, "grad_norm": 0.3555823632879672, "learning_rate": 1.7368375226690712e-05, "loss": 0.2367, "step": 723 }, { "epoch": 2.9356962025316458, "grad_norm": 0.3620602217006019, "learning_rate": 1.731212071922883e-05, "loss": 0.2221, "step": 724 }, { "epoch": 2.939746835443038, "grad_norm": 0.30230233081928903, "learning_rate": 1.7255887859577156e-05, "loss": 0.2228, "step": 725 }, { "epoch": 2.9437974683544303, "grad_norm": 0.3507526331774556, "learning_rate": 1.7199677100627427e-05, "loss": 0.2264, "step": 726 }, { "epoch": 2.947848101265823, "grad_norm": 0.3411839384698184, "learning_rate": 1.7143488895093343e-05, "loss": 0.2373, "step": 727 }, { "epoch": 2.951898734177215, "grad_norm": 0.3007795874175203, "learning_rate": 1.7087323695506994e-05, "loss": 0.2234, "step": 728 }, { "epoch": 2.9559493670886074, "grad_norm": 0.3027997970396035, "learning_rate": 1.7031181954215194e-05, "loss": 0.2167, "step": 729 }, { "epoch": 2.96, "grad_norm": 0.34489464075194065, "learning_rate": 1.6975064123375788e-05, "loss": 0.2196, "step": 730 }, { "epoch": 2.9640506329113925, "grad_norm": 0.33005492695970756, "learning_rate": 1.6918970654954084e-05, "loss": 0.2331, "step": 731 }, { "epoch": 2.968101265822785, "grad_norm": 0.3020204067531584, "learning_rate": 1.686290200071915e-05, "loss": 0.2345, "step": 732 }, { "epoch": 2.972151898734177, "grad_norm": 0.3518120129103537, "learning_rate": 1.6806858612240234e-05, "loss": 0.2343, "step": 733 }, { "epoch": 2.9762025316455696, "grad_norm": 0.295744544290977, "learning_rate": 1.6750840940883078e-05, "loss": 0.2326, "step": 734 }, { "epoch": 2.980253164556962, "grad_norm": 0.3289899180649419, "learning_rate": 1.6694849437806305e-05, "loss": 0.2338, "step": 735 }, { "epoch": 2.984303797468354, "grad_norm": 0.3114433085594379, "learning_rate": 1.663888455395778e-05, "loss": 0.2255, "step": 736 }, { "epoch": 2.9883544303797467, "grad_norm": 0.2876630168510911, "learning_rate": 1.6582946740070995e-05, "loss": 0.2234, "step": 737 }, { "epoch": 2.992405063291139, "grad_norm": 0.31475431138160365, "learning_rate": 1.6527036446661396e-05, "loss": 0.2267, "step": 738 }, { "epoch": 2.9964556962025317, "grad_norm": 0.29153316832672305, "learning_rate": 1.6471154124022818e-05, "loss": 0.2244, "step": 739 }, { "epoch": 3.002025316455696, "grad_norm": 0.3336838529818124, "learning_rate": 1.6415300222223788e-05, "loss": 0.1896, "step": 740 }, { "epoch": 3.0060759493670886, "grad_norm": 0.37403911913938087, "learning_rate": 1.6359475191103958e-05, "loss": 0.1681, "step": 741 }, { "epoch": 3.010126582278481, "grad_norm": 0.3815368986442555, "learning_rate": 1.6303679480270466e-05, "loss": 0.1698, "step": 742 }, { "epoch": 3.0141772151898736, "grad_norm": 0.5238811457979302, "learning_rate": 1.624791353909428e-05, "loss": 0.1684, "step": 743 }, { "epoch": 3.0182278481012657, "grad_norm": 0.343585479895364, "learning_rate": 1.619217781670663e-05, "loss": 0.1621, "step": 744 }, { "epoch": 3.022278481012658, "grad_norm": 0.4291762636782264, "learning_rate": 1.6136472761995373e-05, "loss": 0.1679, "step": 745 }, { "epoch": 3.0263291139240507, "grad_norm": 0.3351592390921522, "learning_rate": 1.608079882360134e-05, "loss": 0.1546, "step": 746 }, { "epoch": 3.030379746835443, "grad_norm": 0.3713125603399009, "learning_rate": 1.60251564499148e-05, "loss": 0.1682, "step": 747 }, { "epoch": 3.0344303797468353, "grad_norm": 0.35433211306608775, "learning_rate": 1.596954608907176e-05, "loss": 0.1589, "step": 748 }, { "epoch": 3.038481012658228, "grad_norm": 0.35625931410287864, "learning_rate": 1.591396818895043e-05, "loss": 0.1641, "step": 749 }, { "epoch": 3.0425316455696203, "grad_norm": 0.3370564714303177, "learning_rate": 1.585842319716759e-05, "loss": 0.1579, "step": 750 }, { "epoch": 3.046582278481013, "grad_norm": 0.35433662496610563, "learning_rate": 1.5802911561074944e-05, "loss": 0.164, "step": 751 }, { "epoch": 3.050632911392405, "grad_norm": 0.32086270677962386, "learning_rate": 1.5747433727755595e-05, "loss": 0.1609, "step": 752 }, { "epoch": 3.0546835443037974, "grad_norm": 0.3521404111470219, "learning_rate": 1.5691990144020376e-05, "loss": 0.168, "step": 753 }, { "epoch": 3.05873417721519, "grad_norm": 0.3702391546240525, "learning_rate": 1.5636581256404297e-05, "loss": 0.1576, "step": 754 }, { "epoch": 3.0627848101265824, "grad_norm": 0.34729533487442976, "learning_rate": 1.558120751116291e-05, "loss": 0.1591, "step": 755 }, { "epoch": 3.0668354430379745, "grad_norm": 0.3358535771091228, "learning_rate": 1.552586935426876e-05, "loss": 0.1618, "step": 756 }, { "epoch": 3.070886075949367, "grad_norm": 0.3660998618279771, "learning_rate": 1.547056723140774e-05, "loss": 0.1647, "step": 757 }, { "epoch": 3.0749367088607595, "grad_norm": 0.34768769314890985, "learning_rate": 1.5415301587975565e-05, "loss": 0.1649, "step": 758 }, { "epoch": 3.078987341772152, "grad_norm": 0.33690765908655146, "learning_rate": 1.536007286907411e-05, "loss": 0.1596, "step": 759 }, { "epoch": 3.083037974683544, "grad_norm": 0.34740897053688985, "learning_rate": 1.5304881519507896e-05, "loss": 0.167, "step": 760 }, { "epoch": 3.0870886075949366, "grad_norm": 0.33093191815829415, "learning_rate": 1.5249727983780453e-05, "loss": 0.1682, "step": 761 }, { "epoch": 3.091139240506329, "grad_norm": 0.343676678307107, "learning_rate": 1.5194612706090786e-05, "loss": 0.1582, "step": 762 }, { "epoch": 3.0951898734177217, "grad_norm": 0.3378399055547801, "learning_rate": 1.5139536130329771e-05, "loss": 0.1591, "step": 763 }, { "epoch": 3.0992405063291137, "grad_norm": 0.3428422547347823, "learning_rate": 1.508449870007656e-05, "loss": 0.1579, "step": 764 }, { "epoch": 3.1032911392405063, "grad_norm": 0.3143850890818085, "learning_rate": 1.5029500858595056e-05, "loss": 0.1537, "step": 765 }, { "epoch": 3.1073417721518988, "grad_norm": 0.335551171305608, "learning_rate": 1.4974543048830328e-05, "loss": 0.161, "step": 766 }, { "epoch": 3.1113924050632913, "grad_norm": 0.3147849796948702, "learning_rate": 1.4919625713405e-05, "loss": 0.158, "step": 767 }, { "epoch": 3.1154430379746834, "grad_norm": 0.3088132773372078, "learning_rate": 1.4864749294615756e-05, "loss": 0.1626, "step": 768 }, { "epoch": 3.119493670886076, "grad_norm": 0.3177175469320239, "learning_rate": 1.4809914234429716e-05, "loss": 0.1598, "step": 769 }, { "epoch": 3.1235443037974684, "grad_norm": 0.3121444262918483, "learning_rate": 1.4755120974480923e-05, "loss": 0.1627, "step": 770 }, { "epoch": 3.127594936708861, "grad_norm": 0.32229138155849607, "learning_rate": 1.4700369956066771e-05, "loss": 0.1588, "step": 771 }, { "epoch": 3.131645569620253, "grad_norm": 0.35068078939208297, "learning_rate": 1.4645661620144413e-05, "loss": 0.1626, "step": 772 }, { "epoch": 3.1356962025316455, "grad_norm": 0.31393977375763277, "learning_rate": 1.4590996407327284e-05, "loss": 0.1606, "step": 773 }, { "epoch": 3.139746835443038, "grad_norm": 0.31862253485057945, "learning_rate": 1.4536374757881487e-05, "loss": 0.1547, "step": 774 }, { "epoch": 3.1437974683544305, "grad_norm": 0.3218733325499347, "learning_rate": 1.4481797111722271e-05, "loss": 0.1566, "step": 775 }, { "epoch": 3.1478481012658226, "grad_norm": 0.34014660222825727, "learning_rate": 1.4427263908410507e-05, "loss": 0.1651, "step": 776 }, { "epoch": 3.151898734177215, "grad_norm": 0.31607392280516405, "learning_rate": 1.4372775587149108e-05, "loss": 0.1683, "step": 777 }, { "epoch": 3.1559493670886076, "grad_norm": 0.32824407292041574, "learning_rate": 1.4318332586779522e-05, "loss": 0.1583, "step": 778 }, { "epoch": 3.16, "grad_norm": 0.31741136233438244, "learning_rate": 1.4263935345778202e-05, "loss": 0.1682, "step": 779 }, { "epoch": 3.164050632911392, "grad_norm": 0.2983012503784583, "learning_rate": 1.420958430225303e-05, "loss": 0.1693, "step": 780 }, { "epoch": 3.1681012658227847, "grad_norm": 0.3197003040202798, "learning_rate": 1.415527989393985e-05, "loss": 0.1504, "step": 781 }, { "epoch": 3.1721518987341772, "grad_norm": 0.33860642379128375, "learning_rate": 1.410102255819891e-05, "loss": 0.1589, "step": 782 }, { "epoch": 3.1762025316455698, "grad_norm": 0.33464341147822335, "learning_rate": 1.404681273201131e-05, "loss": 0.1665, "step": 783 }, { "epoch": 3.180253164556962, "grad_norm": 0.3322758262688437, "learning_rate": 1.399265085197556e-05, "loss": 0.1615, "step": 784 }, { "epoch": 3.1843037974683543, "grad_norm": 0.3477816075652091, "learning_rate": 1.393853735430398e-05, "loss": 0.1637, "step": 785 }, { "epoch": 3.188354430379747, "grad_norm": 0.3210025438157679, "learning_rate": 1.3884472674819246e-05, "loss": 0.1551, "step": 786 }, { "epoch": 3.1924050632911394, "grad_norm": 0.36489406176825245, "learning_rate": 1.3830457248950864e-05, "loss": 0.1588, "step": 787 }, { "epoch": 3.1964556962025314, "grad_norm": 0.35167448169157234, "learning_rate": 1.377649151173163e-05, "loss": 0.1696, "step": 788 }, { "epoch": 3.200506329113924, "grad_norm": 0.3377002451357465, "learning_rate": 1.3722575897794181e-05, "loss": 0.1583, "step": 789 }, { "epoch": 3.2045569620253165, "grad_norm": 0.33816038608584464, "learning_rate": 1.3668710841367472e-05, "loss": 0.1583, "step": 790 }, { "epoch": 3.208607594936709, "grad_norm": 0.33699296692128156, "learning_rate": 1.361489677627324e-05, "loss": 0.1556, "step": 791 }, { "epoch": 3.212658227848101, "grad_norm": 0.33663988331028627, "learning_rate": 1.3561134135922585e-05, "loss": 0.1624, "step": 792 }, { "epoch": 3.2167088607594936, "grad_norm": 0.3155822834034656, "learning_rate": 1.350742335331241e-05, "loss": 0.1676, "step": 793 }, { "epoch": 3.220759493670886, "grad_norm": 0.343702196522854, "learning_rate": 1.345376486102198e-05, "loss": 0.1555, "step": 794 }, { "epoch": 3.2248101265822786, "grad_norm": 0.30715674064025605, "learning_rate": 1.3400159091209414e-05, "loss": 0.1645, "step": 795 }, { "epoch": 3.2288607594936707, "grad_norm": 0.309307845130646, "learning_rate": 1.3346606475608216e-05, "loss": 0.1577, "step": 796 }, { "epoch": 3.232911392405063, "grad_norm": 0.3244784397352814, "learning_rate": 1.3293107445523781e-05, "loss": 0.1628, "step": 797 }, { "epoch": 3.2369620253164557, "grad_norm": 0.31897933155104946, "learning_rate": 1.3239662431829949e-05, "loss": 0.1579, "step": 798 }, { "epoch": 3.2410126582278482, "grad_norm": 0.3105430466920123, "learning_rate": 1.3186271864965509e-05, "loss": 0.1742, "step": 799 }, { "epoch": 3.2450632911392403, "grad_norm": 0.3111913244391673, "learning_rate": 1.3132936174930756e-05, "loss": 0.1636, "step": 800 }, { "epoch": 3.249113924050633, "grad_norm": 0.34902735983703825, "learning_rate": 1.3079655791283995e-05, "loss": 0.1658, "step": 801 }, { "epoch": 3.2531645569620253, "grad_norm": 0.3045007220320991, "learning_rate": 1.3026431143138108e-05, "loss": 0.154, "step": 802 }, { "epoch": 3.257215189873418, "grad_norm": 0.29959360944104163, "learning_rate": 1.2973262659157114e-05, "loss": 0.1623, "step": 803 }, { "epoch": 3.26126582278481, "grad_norm": 0.3802360146747788, "learning_rate": 1.2920150767552651e-05, "loss": 0.1632, "step": 804 }, { "epoch": 3.2653164556962024, "grad_norm": 0.3272076198303392, "learning_rate": 1.2867095896080607e-05, "loss": 0.1624, "step": 805 }, { "epoch": 3.269367088607595, "grad_norm": 0.3082729867281307, "learning_rate": 1.2814098472037612e-05, "loss": 0.1692, "step": 806 }, { "epoch": 3.2734177215189875, "grad_norm": 0.3388523491973715, "learning_rate": 1.276115892225764e-05, "loss": 0.1559, "step": 807 }, { "epoch": 3.27746835443038, "grad_norm": 0.32588429626861326, "learning_rate": 1.2708277673108555e-05, "loss": 0.1516, "step": 808 }, { "epoch": 3.281518987341772, "grad_norm": 0.29210238682083095, "learning_rate": 1.2655455150488649e-05, "loss": 0.1574, "step": 809 }, { "epoch": 3.2855696202531646, "grad_norm": 0.3240391540206831, "learning_rate": 1.2602691779823272e-05, "loss": 0.1589, "step": 810 }, { "epoch": 3.289620253164557, "grad_norm": 0.3240161735943306, "learning_rate": 1.2549987986061355e-05, "loss": 0.169, "step": 811 }, { "epoch": 3.293670886075949, "grad_norm": 0.2927975412848078, "learning_rate": 1.2497344193672005e-05, "loss": 0.1687, "step": 812 }, { "epoch": 3.2977215189873417, "grad_norm": 0.2871726311958699, "learning_rate": 1.2444760826641092e-05, "loss": 0.1499, "step": 813 }, { "epoch": 3.301772151898734, "grad_norm": 0.30786732647310155, "learning_rate": 1.2392238308467817e-05, "loss": 0.1549, "step": 814 }, { "epoch": 3.3058227848101267, "grad_norm": 0.30427165276768925, "learning_rate": 1.2339777062161326e-05, "loss": 0.1594, "step": 815 }, { "epoch": 3.309873417721519, "grad_norm": 0.2807878093797431, "learning_rate": 1.2287377510237293e-05, "loss": 0.1658, "step": 816 }, { "epoch": 3.3139240506329113, "grad_norm": 0.30172568216808493, "learning_rate": 1.2235040074714488e-05, "loss": 0.1468, "step": 817 }, { "epoch": 3.317974683544304, "grad_norm": 0.31292767764345053, "learning_rate": 1.2182765177111434e-05, "loss": 0.1658, "step": 818 }, { "epoch": 3.3220253164556963, "grad_norm": 0.302518697828019, "learning_rate": 1.213055323844297e-05, "loss": 0.1651, "step": 819 }, { "epoch": 3.3260759493670884, "grad_norm": 0.29514869063035937, "learning_rate": 1.2078404679216864e-05, "loss": 0.1663, "step": 820 }, { "epoch": 3.330126582278481, "grad_norm": 0.2837879185015284, "learning_rate": 1.2026319919430458e-05, "loss": 0.1632, "step": 821 }, { "epoch": 3.3341772151898734, "grad_norm": 0.29579640302001653, "learning_rate": 1.1974299378567227e-05, "loss": 0.1644, "step": 822 }, { "epoch": 3.338227848101266, "grad_norm": 0.3092411941150059, "learning_rate": 1.1922343475593462e-05, "loss": 0.1599, "step": 823 }, { "epoch": 3.3422784810126585, "grad_norm": 0.3055405437318074, "learning_rate": 1.187045262895488e-05, "loss": 0.1654, "step": 824 }, { "epoch": 3.3463291139240505, "grad_norm": 0.31741030461806213, "learning_rate": 1.1818627256573203e-05, "loss": 0.1661, "step": 825 }, { "epoch": 3.350379746835443, "grad_norm": 0.3054890696921869, "learning_rate": 1.1766867775842864e-05, "loss": 0.1717, "step": 826 }, { "epoch": 3.3544303797468356, "grad_norm": 0.2997207882822613, "learning_rate": 1.1715174603627615e-05, "loss": 0.1539, "step": 827 }, { "epoch": 3.3584810126582276, "grad_norm": 0.3093438042357472, "learning_rate": 1.1663548156257147e-05, "loss": 0.1638, "step": 828 }, { "epoch": 3.36253164556962, "grad_norm": 0.30694487590484093, "learning_rate": 1.161198884952377e-05, "loss": 0.1627, "step": 829 }, { "epoch": 3.3665822784810127, "grad_norm": 0.3129144483969426, "learning_rate": 1.1560497098679056e-05, "loss": 0.1562, "step": 830 }, { "epoch": 3.370632911392405, "grad_norm": 0.29633902121945876, "learning_rate": 1.1509073318430479e-05, "loss": 0.1653, "step": 831 }, { "epoch": 3.3746835443037977, "grad_norm": 0.30696453825919334, "learning_rate": 1.1457717922938116e-05, "loss": 0.1541, "step": 832 }, { "epoch": 3.3787341772151898, "grad_norm": 0.31944250183992695, "learning_rate": 1.1406431325811233e-05, "loss": 0.1674, "step": 833 }, { "epoch": 3.3827848101265823, "grad_norm": 0.30400128209574995, "learning_rate": 1.135521394010506e-05, "loss": 0.16, "step": 834 }, { "epoch": 3.386835443037975, "grad_norm": 0.2963130052616333, "learning_rate": 1.1304066178317367e-05, "loss": 0.1573, "step": 835 }, { "epoch": 3.390886075949367, "grad_norm": 0.3071286079234481, "learning_rate": 1.1252988452385199e-05, "loss": 0.1668, "step": 836 }, { "epoch": 3.3949367088607594, "grad_norm": 0.29975229793250335, "learning_rate": 1.1201981173681536e-05, "loss": 0.1512, "step": 837 }, { "epoch": 3.398987341772152, "grad_norm": 0.3059158323800646, "learning_rate": 1.1151044753011991e-05, "loss": 0.1773, "step": 838 }, { "epoch": 3.4030379746835444, "grad_norm": 0.3194633164709696, "learning_rate": 1.1100179600611491e-05, "loss": 0.1678, "step": 839 }, { "epoch": 3.407088607594937, "grad_norm": 0.31087274569978324, "learning_rate": 1.1049386126140985e-05, "loss": 0.1583, "step": 840 }, { "epoch": 3.411139240506329, "grad_norm": 0.30481515524634656, "learning_rate": 1.0998664738684128e-05, "loss": 0.1643, "step": 841 }, { "epoch": 3.4151898734177215, "grad_norm": 0.29933425628916516, "learning_rate": 1.0948015846744e-05, "loss": 0.1642, "step": 842 }, { "epoch": 3.419240506329114, "grad_norm": 0.3064753453073419, "learning_rate": 1.0897439858239832e-05, "loss": 0.1597, "step": 843 }, { "epoch": 3.423291139240506, "grad_norm": 0.29546137256208826, "learning_rate": 1.0846937180503652e-05, "loss": 0.1544, "step": 844 }, { "epoch": 3.4273417721518986, "grad_norm": 0.29864872614815174, "learning_rate": 1.0796508220277117e-05, "loss": 0.1553, "step": 845 }, { "epoch": 3.431392405063291, "grad_norm": 0.30264035692549435, "learning_rate": 1.0746153383708107e-05, "loss": 0.1578, "step": 846 }, { "epoch": 3.4354430379746836, "grad_norm": 0.2892756484905138, "learning_rate": 1.0695873076347579e-05, "loss": 0.1523, "step": 847 }, { "epoch": 3.439493670886076, "grad_norm": 0.2897922231496335, "learning_rate": 1.0645667703146205e-05, "loss": 0.1621, "step": 848 }, { "epoch": 3.4435443037974682, "grad_norm": 0.27405387986556334, "learning_rate": 1.0595537668451161e-05, "loss": 0.1685, "step": 849 }, { "epoch": 3.4475949367088607, "grad_norm": 0.3045558701481512, "learning_rate": 1.0545483376002854e-05, "loss": 0.1627, "step": 850 }, { "epoch": 3.4516455696202533, "grad_norm": 0.29910248447101534, "learning_rate": 1.0495505228931676e-05, "loss": 0.1657, "step": 851 }, { "epoch": 3.4556962025316453, "grad_norm": 0.2964773469582491, "learning_rate": 1.044560362975474e-05, "loss": 0.1698, "step": 852 }, { "epoch": 3.459746835443038, "grad_norm": 0.3072818125510571, "learning_rate": 1.0395778980372695e-05, "loss": 0.1552, "step": 853 }, { "epoch": 3.4637974683544304, "grad_norm": 0.3133210810014633, "learning_rate": 1.0346031682066381e-05, "loss": 0.1573, "step": 854 }, { "epoch": 3.467848101265823, "grad_norm": 0.2931943994633051, "learning_rate": 1.0296362135493724e-05, "loss": 0.1548, "step": 855 }, { "epoch": 3.4718987341772154, "grad_norm": 0.2848016720877912, "learning_rate": 1.0246770740686422e-05, "loss": 0.1712, "step": 856 }, { "epoch": 3.4759493670886075, "grad_norm": 0.3212851998940559, "learning_rate": 1.0197257897046743e-05, "loss": 0.1646, "step": 857 }, { "epoch": 3.48, "grad_norm": 0.30970164519437726, "learning_rate": 1.014782400334433e-05, "loss": 0.1615, "step": 858 }, { "epoch": 3.4840506329113925, "grad_norm": 0.3072744896200501, "learning_rate": 1.009846945771296e-05, "loss": 0.1578, "step": 859 }, { "epoch": 3.4881012658227846, "grad_norm": 0.2836419284289585, "learning_rate": 1.0049194657647363e-05, "loss": 0.1584, "step": 860 }, { "epoch": 3.492151898734177, "grad_norm": 0.2795208224154033, "learning_rate": 1.0000000000000006e-05, "loss": 0.1644, "step": 861 }, { "epoch": 3.4962025316455696, "grad_norm": 0.3164525611282084, "learning_rate": 9.950885880977891e-06, "loss": 0.1575, "step": 862 }, { "epoch": 3.500253164556962, "grad_norm": 0.29792383972226005, "learning_rate": 9.901852696139382e-06, "loss": 0.1572, "step": 863 }, { "epoch": 3.5043037974683546, "grad_norm": 0.30353076228382025, "learning_rate": 9.852900840391027e-06, "loss": 0.1515, "step": 864 }, { "epoch": 3.5083544303797467, "grad_norm": 0.3185895200557017, "learning_rate": 9.804030707984313e-06, "loss": 0.1626, "step": 865 }, { "epoch": 3.512405063291139, "grad_norm": 0.30822383486810206, "learning_rate": 9.755242692512599e-06, "loss": 0.1687, "step": 866 }, { "epoch": 3.5164556962025317, "grad_norm": 0.3031771873878252, "learning_rate": 9.70653718690782e-06, "loss": 0.1599, "step": 867 }, { "epoch": 3.520506329113924, "grad_norm": 0.29469968585573125, "learning_rate": 9.657914583437454e-06, "loss": 0.1533, "step": 868 }, { "epoch": 3.5245569620253163, "grad_norm": 0.2934983491270243, "learning_rate": 9.609375273701246e-06, "loss": 0.1505, "step": 869 }, { "epoch": 3.528607594936709, "grad_norm": 0.30231883066013343, "learning_rate": 9.560919648628133e-06, "loss": 0.1565, "step": 870 }, { "epoch": 3.5326582278481014, "grad_norm": 0.3052855036975819, "learning_rate": 9.512548098473047e-06, "loss": 0.1604, "step": 871 }, { "epoch": 3.536708860759494, "grad_norm": 0.2986789340102101, "learning_rate": 9.464261012813825e-06, "loss": 0.1617, "step": 872 }, { "epoch": 3.540759493670886, "grad_norm": 0.29017007565107955, "learning_rate": 9.416058780547987e-06, "loss": 0.153, "step": 873 }, { "epoch": 3.5448101265822785, "grad_norm": 0.3026748540848498, "learning_rate": 9.367941789889714e-06, "loss": 0.1602, "step": 874 }, { "epoch": 3.548860759493671, "grad_norm": 0.2868547252462914, "learning_rate": 9.319910428366607e-06, "loss": 0.1714, "step": 875 }, { "epoch": 3.552911392405063, "grad_norm": 0.29600097093862887, "learning_rate": 9.271965082816667e-06, "loss": 0.1603, "step": 876 }, { "epoch": 3.5569620253164556, "grad_norm": 0.3063450246772812, "learning_rate": 9.224106139385111e-06, "loss": 0.1633, "step": 877 }, { "epoch": 3.561012658227848, "grad_norm": 0.293823163673497, "learning_rate": 9.176333983521291e-06, "loss": 0.1516, "step": 878 }, { "epoch": 3.5650632911392406, "grad_norm": 0.3077495938253195, "learning_rate": 9.12864899997558e-06, "loss": 0.1713, "step": 879 }, { "epoch": 3.569113924050633, "grad_norm": 0.31250374008469367, "learning_rate": 9.08105157279628e-06, "loss": 0.1582, "step": 880 }, { "epoch": 3.573164556962025, "grad_norm": 0.31468022036380217, "learning_rate": 9.03354208532653e-06, "loss": 0.1586, "step": 881 }, { "epoch": 3.5772151898734177, "grad_norm": 0.29735102105827305, "learning_rate": 8.986120920201205e-06, "loss": 0.161, "step": 882 }, { "epoch": 3.58126582278481, "grad_norm": 0.2965216858904962, "learning_rate": 8.938788459343852e-06, "loss": 0.1514, "step": 883 }, { "epoch": 3.5853164556962023, "grad_norm": 0.3134858783781481, "learning_rate": 8.8915450839636e-06, "loss": 0.1695, "step": 884 }, { "epoch": 3.589367088607595, "grad_norm": 0.3103643182304426, "learning_rate": 8.844391174552116e-06, "loss": 0.1659, "step": 885 }, { "epoch": 3.5934177215189873, "grad_norm": 0.2841387717183436, "learning_rate": 8.797327110880479e-06, "loss": 0.1814, "step": 886 }, { "epoch": 3.59746835443038, "grad_norm": 0.29894345807617295, "learning_rate": 8.750353271996206e-06, "loss": 0.1463, "step": 887 }, { "epoch": 3.6015189873417723, "grad_norm": 0.2981530048590563, "learning_rate": 8.703470036220132e-06, "loss": 0.1656, "step": 888 }, { "epoch": 3.6055696202531644, "grad_norm": 0.30938215525563795, "learning_rate": 8.656677781143394e-06, "loss": 0.1606, "step": 889 }, { "epoch": 3.609620253164557, "grad_norm": 0.2982639087909178, "learning_rate": 8.609976883624377e-06, "loss": 0.1592, "step": 890 }, { "epoch": 3.6136708860759494, "grad_norm": 0.28974437723536506, "learning_rate": 8.563367719785698e-06, "loss": 0.1716, "step": 891 }, { "epoch": 3.6177215189873415, "grad_norm": 0.28953817283065025, "learning_rate": 8.516850665011138e-06, "loss": 0.1457, "step": 892 }, { "epoch": 3.621772151898734, "grad_norm": 0.2977859439094693, "learning_rate": 8.47042609394269e-06, "loss": 0.1539, "step": 893 }, { "epoch": 3.6258227848101265, "grad_norm": 0.3015064165309544, "learning_rate": 8.424094380477432e-06, "loss": 0.154, "step": 894 }, { "epoch": 3.629873417721519, "grad_norm": 0.28973770600316423, "learning_rate": 8.37785589776465e-06, "loss": 0.1552, "step": 895 }, { "epoch": 3.6339240506329116, "grad_norm": 0.2781850570540563, "learning_rate": 8.331711018202694e-06, "loss": 0.1554, "step": 896 }, { "epoch": 3.6379746835443036, "grad_norm": 0.2879536475563254, "learning_rate": 8.285660113436104e-06, "loss": 0.1538, "step": 897 }, { "epoch": 3.642025316455696, "grad_norm": 0.2786223941660474, "learning_rate": 8.239703554352527e-06, "loss": 0.1703, "step": 898 }, { "epoch": 3.6460759493670887, "grad_norm": 0.286916785463265, "learning_rate": 8.193841711079775e-06, "loss": 0.1573, "step": 899 }, { "epoch": 3.6501265822784807, "grad_norm": 0.3024136943557636, "learning_rate": 8.148074952982828e-06, "loss": 0.1573, "step": 900 }, { "epoch": 3.6541772151898733, "grad_norm": 0.2997531584974771, "learning_rate": 8.102403648660859e-06, "loss": 0.1567, "step": 901 }, { "epoch": 3.6582278481012658, "grad_norm": 0.2935442909461858, "learning_rate": 8.056828165944282e-06, "loss": 0.155, "step": 902 }, { "epoch": 3.6622784810126583, "grad_norm": 0.28477503071395055, "learning_rate": 8.011348871891762e-06, "loss": 0.1664, "step": 903 }, { "epoch": 3.666329113924051, "grad_norm": 0.28900980058384423, "learning_rate": 7.965966132787287e-06, "loss": 0.1531, "step": 904 }, { "epoch": 3.670379746835443, "grad_norm": 0.30062491639930283, "learning_rate": 7.920680314137189e-06, "loss": 0.1679, "step": 905 }, { "epoch": 3.6744303797468354, "grad_norm": 0.29486205669721977, "learning_rate": 7.875491780667246e-06, "loss": 0.1597, "step": 906 }, { "epoch": 3.678481012658228, "grad_norm": 0.3036530452655445, "learning_rate": 7.830400896319667e-06, "loss": 0.1693, "step": 907 }, { "epoch": 3.68253164556962, "grad_norm": 0.28082605387385345, "learning_rate": 7.785408024250259e-06, "loss": 0.1604, "step": 908 }, { "epoch": 3.6865822784810125, "grad_norm": 0.29594669702573556, "learning_rate": 7.74051352682542e-06, "loss": 0.1593, "step": 909 }, { "epoch": 3.690632911392405, "grad_norm": 0.28715132413485583, "learning_rate": 7.695717765619257e-06, "loss": 0.1664, "step": 910 }, { "epoch": 3.6946835443037975, "grad_norm": 0.3014929322745803, "learning_rate": 7.651021101410673e-06, "loss": 0.1615, "step": 911 }, { "epoch": 3.69873417721519, "grad_norm": 0.28916915083230366, "learning_rate": 7.606423894180464e-06, "loss": 0.1586, "step": 912 }, { "epoch": 3.702784810126582, "grad_norm": 0.3021117767253123, "learning_rate": 7.56192650310839e-06, "loss": 0.1543, "step": 913 }, { "epoch": 3.7068354430379746, "grad_norm": 0.2860175105354357, "learning_rate": 7.517529286570349e-06, "loss": 0.1626, "step": 914 }, { "epoch": 3.710886075949367, "grad_norm": 0.2959077674218109, "learning_rate": 7.473232602135387e-06, "loss": 0.1528, "step": 915 }, { "epoch": 3.714936708860759, "grad_norm": 0.30157687759471585, "learning_rate": 7.429036806562935e-06, "loss": 0.162, "step": 916 }, { "epoch": 3.7189873417721517, "grad_norm": 0.2896243601315491, "learning_rate": 7.3849422557998455e-06, "loss": 0.1517, "step": 917 }, { "epoch": 3.7230379746835442, "grad_norm": 0.2849696577263053, "learning_rate": 7.340949304977567e-06, "loss": 0.1551, "step": 918 }, { "epoch": 3.7270886075949368, "grad_norm": 0.3016039949569298, "learning_rate": 7.297058308409282e-06, "loss": 0.1716, "step": 919 }, { "epoch": 3.7311392405063293, "grad_norm": 0.28888361566973325, "learning_rate": 7.25326961958704e-06, "loss": 0.16, "step": 920 }, { "epoch": 3.7351898734177214, "grad_norm": 0.29173890348971393, "learning_rate": 7.209583591178921e-06, "loss": 0.1515, "step": 921 }, { "epoch": 3.739240506329114, "grad_norm": 0.29657160122145965, "learning_rate": 7.1660005750261925e-06, "loss": 0.1542, "step": 922 }, { "epoch": 3.7432911392405064, "grad_norm": 0.2963241359814139, "learning_rate": 7.1225209221404765e-06, "loss": 0.1701, "step": 923 }, { "epoch": 3.747341772151899, "grad_norm": 0.27855079608287714, "learning_rate": 7.079144982700909e-06, "loss": 0.1569, "step": 924 }, { "epoch": 3.7513924050632914, "grad_norm": 0.29060282858845543, "learning_rate": 7.0358731060513695e-06, "loss": 0.1703, "step": 925 }, { "epoch": 3.7554430379746835, "grad_norm": 0.28632353555554063, "learning_rate": 6.99270564069757e-06, "loss": 0.1572, "step": 926 }, { "epoch": 3.759493670886076, "grad_norm": 0.29210276767218324, "learning_rate": 6.949642934304375e-06, "loss": 0.1625, "step": 927 }, { "epoch": 3.7635443037974685, "grad_norm": 0.2819778034105889, "learning_rate": 6.906685333692871e-06, "loss": 0.1508, "step": 928 }, { "epoch": 3.7675949367088606, "grad_norm": 0.3004141661314038, "learning_rate": 6.86383318483769e-06, "loss": 0.1542, "step": 929 }, { "epoch": 3.771645569620253, "grad_norm": 0.2954436825383948, "learning_rate": 6.821086832864139e-06, "loss": 0.1579, "step": 930 }, { "epoch": 3.7756962025316456, "grad_norm": 0.30026530839001647, "learning_rate": 6.77844662204546e-06, "loss": 0.1531, "step": 931 }, { "epoch": 3.779746835443038, "grad_norm": 0.293268921119697, "learning_rate": 6.7359128958000455e-06, "loss": 0.1535, "step": 932 }, { "epoch": 3.7837974683544306, "grad_norm": 0.28975561388314, "learning_rate": 6.693485996688695e-06, "loss": 0.1521, "step": 933 }, { "epoch": 3.7878481012658227, "grad_norm": 0.283940358092582, "learning_rate": 6.651166266411801e-06, "loss": 0.1517, "step": 934 }, { "epoch": 3.7918987341772152, "grad_norm": 0.28848360905237874, "learning_rate": 6.6089540458066725e-06, "loss": 0.1614, "step": 935 }, { "epoch": 3.7959493670886078, "grad_norm": 0.31359869067940666, "learning_rate": 6.566849674844711e-06, "loss": 0.1651, "step": 936 }, { "epoch": 3.8, "grad_norm": 0.3084311379353421, "learning_rate": 6.524853492628747e-06, "loss": 0.1644, "step": 937 }, { "epoch": 3.8040506329113923, "grad_norm": 0.284424533590349, "learning_rate": 6.4829658373902536e-06, "loss": 0.1471, "step": 938 }, { "epoch": 3.808101265822785, "grad_norm": 0.29756205611636755, "learning_rate": 6.441187046486648e-06, "loss": 0.1631, "step": 939 }, { "epoch": 3.8121518987341774, "grad_norm": 0.3061474774715736, "learning_rate": 6.399517456398567e-06, "loss": 0.161, "step": 940 }, { "epoch": 3.81620253164557, "grad_norm": 0.2915616032315793, "learning_rate": 6.357957402727164e-06, "loss": 0.1506, "step": 941 }, { "epoch": 3.820253164556962, "grad_norm": 0.2877032654798346, "learning_rate": 6.316507220191395e-06, "loss": 0.1536, "step": 942 }, { "epoch": 3.8243037974683545, "grad_norm": 0.27838263243907435, "learning_rate": 6.275167242625331e-06, "loss": 0.165, "step": 943 }, { "epoch": 3.828354430379747, "grad_norm": 0.28877761635371446, "learning_rate": 6.233937802975471e-06, "loss": 0.1592, "step": 944 }, { "epoch": 3.832405063291139, "grad_norm": 0.27724951912059576, "learning_rate": 6.192819233298046e-06, "loss": 0.1539, "step": 945 }, { "epoch": 3.8364556962025316, "grad_norm": 0.2975144707675443, "learning_rate": 6.151811864756383e-06, "loss": 0.1474, "step": 946 }, { "epoch": 3.840506329113924, "grad_norm": 0.28752997468267844, "learning_rate": 6.1109160276181655e-06, "loss": 0.1517, "step": 947 }, { "epoch": 3.8445569620253166, "grad_norm": 0.30654257006282376, "learning_rate": 6.070132051252868e-06, "loss": 0.1501, "step": 948 }, { "epoch": 3.848607594936709, "grad_norm": 0.2903047073028669, "learning_rate": 6.0294602641290034e-06, "loss": 0.1615, "step": 949 }, { "epoch": 3.852658227848101, "grad_norm": 0.27405752817644363, "learning_rate": 5.988900993811575e-06, "loss": 0.1511, "step": 950 }, { "epoch": 3.8567088607594937, "grad_norm": 0.29334607815577185, "learning_rate": 5.948454566959363e-06, "loss": 0.1424, "step": 951 }, { "epoch": 3.8607594936708862, "grad_norm": 0.287308140664051, "learning_rate": 5.908121309322328e-06, "loss": 0.153, "step": 952 }, { "epoch": 3.8648101265822783, "grad_norm": 0.2792871988849546, "learning_rate": 5.867901545738976e-06, "loss": 0.146, "step": 953 }, { "epoch": 3.868860759493671, "grad_norm": 0.29133643663801495, "learning_rate": 5.827795600133774e-06, "loss": 0.1473, "step": 954 }, { "epoch": 3.8729113924050633, "grad_norm": 0.27651689043526717, "learning_rate": 5.787803795514466e-06, "loss": 0.1539, "step": 955 }, { "epoch": 3.876962025316456, "grad_norm": 0.2959444557998447, "learning_rate": 5.747926453969576e-06, "loss": 0.1561, "step": 956 }, { "epoch": 3.8810126582278484, "grad_norm": 0.28755744961477775, "learning_rate": 5.708163896665708e-06, "loss": 0.1642, "step": 957 }, { "epoch": 3.8850632911392404, "grad_norm": 0.2784377876173754, "learning_rate": 5.668516443845047e-06, "loss": 0.1641, "step": 958 }, { "epoch": 3.889113924050633, "grad_norm": 0.28765037487320466, "learning_rate": 5.6289844148227225e-06, "loss": 0.1588, "step": 959 }, { "epoch": 3.8931645569620255, "grad_norm": 0.28469164138996966, "learning_rate": 5.5895681279842615e-06, "loss": 0.1622, "step": 960 }, { "epoch": 3.8972151898734175, "grad_norm": 0.26990014186834, "learning_rate": 5.550267900783019e-06, "loss": 0.1612, "step": 961 }, { "epoch": 3.90126582278481, "grad_norm": 0.2803775464090173, "learning_rate": 5.511084049737623e-06, "loss": 0.1511, "step": 962 }, { "epoch": 3.9053164556962026, "grad_norm": 0.28610019664942965, "learning_rate": 5.4720168904294215e-06, "loss": 0.1568, "step": 963 }, { "epoch": 3.909367088607595, "grad_norm": 0.295272209668961, "learning_rate": 5.433066737499948e-06, "loss": 0.1529, "step": 964 }, { "epoch": 3.9134177215189876, "grad_norm": 0.30190868934357984, "learning_rate": 5.394233904648376e-06, "loss": 0.1487, "step": 965 }, { "epoch": 3.9174683544303797, "grad_norm": 0.28418510694638266, "learning_rate": 5.355518704628997e-06, "loss": 0.1545, "step": 966 }, { "epoch": 3.921518987341772, "grad_norm": 0.280324317516332, "learning_rate": 5.316921449248731e-06, "loss": 0.1583, "step": 967 }, { "epoch": 3.9255696202531647, "grad_norm": 0.27611924468259785, "learning_rate": 5.278442449364538e-06, "loss": 0.151, "step": 968 }, { "epoch": 3.9296202531645568, "grad_norm": 0.26668219355894596, "learning_rate": 5.240082014881016e-06, "loss": 0.1533, "step": 969 }, { "epoch": 3.9336708860759493, "grad_norm": 0.2815746460413002, "learning_rate": 5.201840454747822e-06, "loss": 0.1526, "step": 970 }, { "epoch": 3.937721518987342, "grad_norm": 0.269825930174018, "learning_rate": 5.163718076957223e-06, "loss": 0.1571, "step": 971 }, { "epoch": 3.9417721518987343, "grad_norm": 0.2797342321315396, "learning_rate": 5.125715188541609e-06, "loss": 0.1518, "step": 972 }, { "epoch": 3.945822784810127, "grad_norm": 0.2895150248045296, "learning_rate": 5.087832095571021e-06, "loss": 0.156, "step": 973 }, { "epoch": 3.949873417721519, "grad_norm": 0.2822835779361662, "learning_rate": 5.0500691031506766e-06, "loss": 0.1645, "step": 974 }, { "epoch": 3.9539240506329114, "grad_norm": 0.2967046096217083, "learning_rate": 5.01242651541854e-06, "loss": 0.1607, "step": 975 }, { "epoch": 3.957974683544304, "grad_norm": 0.2957788807245544, "learning_rate": 4.974904635542815e-06, "loss": 0.1546, "step": 976 }, { "epoch": 3.962025316455696, "grad_norm": 0.28055932222352714, "learning_rate": 4.937503765719582e-06, "loss": 0.1606, "step": 977 }, { "epoch": 3.9660759493670885, "grad_norm": 0.2806585507293901, "learning_rate": 4.900224207170299e-06, "loss": 0.1497, "step": 978 }, { "epoch": 3.970126582278481, "grad_norm": 0.2789616534048337, "learning_rate": 4.8630662601394065e-06, "loss": 0.1527, "step": 979 }, { "epoch": 3.9741772151898735, "grad_norm": 0.2839837066393894, "learning_rate": 4.8260302238918995e-06, "loss": 0.1581, "step": 980 }, { "epoch": 3.978227848101266, "grad_norm": 0.2760915232778183, "learning_rate": 4.789116396710924e-06, "loss": 0.1639, "step": 981 }, { "epoch": 3.982278481012658, "grad_norm": 0.28056191160068206, "learning_rate": 4.752325075895368e-06, "loss": 0.1619, "step": 982 }, { "epoch": 3.9863291139240506, "grad_norm": 0.28020228165535166, "learning_rate": 4.715656557757473e-06, "loss": 0.1666, "step": 983 }, { "epoch": 3.990379746835443, "grad_norm": 0.27221664686569214, "learning_rate": 4.679111137620442e-06, "loss": 0.1619, "step": 984 }, { "epoch": 3.9944303797468352, "grad_norm": 0.2792838158926976, "learning_rate": 4.6426891098160585e-06, "loss": 0.1667, "step": 985 }, { "epoch": 3.9984810126582278, "grad_norm": 0.2863656730736083, "learning_rate": 4.6063907676823474e-06, "loss": 0.1526, "step": 986 }, { "epoch": 4.004050632911392, "grad_norm": 0.4280927622695084, "learning_rate": 4.570216403561141e-06, "loss": 0.1181, "step": 987 }, { "epoch": 4.008101265822785, "grad_norm": 0.3341477975841459, "learning_rate": 4.534166308795815e-06, "loss": 0.1059, "step": 988 }, { "epoch": 4.012151898734177, "grad_norm": 0.2753008715468381, "learning_rate": 4.498240773728859e-06, "loss": 0.1171, "step": 989 }, { "epoch": 4.01620253164557, "grad_norm": 0.3177475106480987, "learning_rate": 4.462440087699609e-06, "loss": 0.1131, "step": 990 }, { "epoch": 4.020253164556962, "grad_norm": 0.3978004314772558, "learning_rate": 4.426764539041861e-06, "loss": 0.1148, "step": 991 }, { "epoch": 4.024303797468354, "grad_norm": 0.39864692640148264, "learning_rate": 4.391214415081582e-06, "loss": 0.1013, "step": 992 }, { "epoch": 4.028354430379747, "grad_norm": 0.37441219986235186, "learning_rate": 4.355790002134579e-06, "loss": 0.1212, "step": 993 }, { "epoch": 4.032405063291139, "grad_norm": 0.28366972754962066, "learning_rate": 4.320491585504207e-06, "loss": 0.1117, "step": 994 }, { "epoch": 4.036455696202531, "grad_norm": 0.29399618034850833, "learning_rate": 4.2853194494790615e-06, "loss": 0.103, "step": 995 }, { "epoch": 4.040506329113924, "grad_norm": 0.35134915131074446, "learning_rate": 4.250273877330691e-06, "loss": 0.1203, "step": 996 }, { "epoch": 4.044556962025316, "grad_norm": 0.3536751960701333, "learning_rate": 4.215355151311313e-06, "loss": 0.099, "step": 997 }, { "epoch": 4.048607594936709, "grad_norm": 0.30463243799197615, "learning_rate": 4.180563552651542e-06, "loss": 0.1107, "step": 998 }, { "epoch": 4.052658227848101, "grad_norm": 0.3112268325023473, "learning_rate": 4.145899361558147e-06, "loss": 0.1064, "step": 999 }, { "epoch": 4.056708860759493, "grad_norm": 0.3240754574592331, "learning_rate": 4.111362857211738e-06, "loss": 0.1058, "step": 1000 }, { "epoch": 4.060759493670886, "grad_norm": 0.30859366318213965, "learning_rate": 4.076954317764592e-06, "loss": 0.1149, "step": 1001 }, { "epoch": 4.0648101265822785, "grad_norm": 0.32402839717883036, "learning_rate": 4.042674020338335e-06, "loss": 0.1158, "step": 1002 }, { "epoch": 4.0688607594936705, "grad_norm": 0.3116935683882614, "learning_rate": 4.0085222410217835e-06, "loss": 0.1047, "step": 1003 }, { "epoch": 4.0729113924050635, "grad_norm": 0.29933221965249945, "learning_rate": 3.974499254868674e-06, "loss": 0.1186, "step": 1004 }, { "epoch": 4.076962025316456, "grad_norm": 0.2895945100557759, "learning_rate": 3.940605335895451e-06, "loss": 0.1091, "step": 1005 }, { "epoch": 4.0810126582278485, "grad_norm": 0.27589561988061606, "learning_rate": 3.90684075707908e-06, "loss": 0.1215, "step": 1006 }, { "epoch": 4.085063291139241, "grad_norm": 0.2762450931172216, "learning_rate": 3.8732057903548505e-06, "loss": 0.1066, "step": 1007 }, { "epoch": 4.089113924050633, "grad_norm": 0.27367025120129146, "learning_rate": 3.8397007066141375e-06, "loss": 0.1131, "step": 1008 }, { "epoch": 4.093164556962026, "grad_norm": 0.28771681304433994, "learning_rate": 3.806325775702304e-06, "loss": 0.1058, "step": 1009 }, { "epoch": 4.097215189873418, "grad_norm": 0.28743877296347675, "learning_rate": 3.773081266416434e-06, "loss": 0.1012, "step": 1010 }, { "epoch": 4.10126582278481, "grad_norm": 0.2829382470203778, "learning_rate": 3.739967446503245e-06, "loss": 0.1057, "step": 1011 }, { "epoch": 4.105316455696203, "grad_norm": 0.2732633587344594, "learning_rate": 3.706984582656894e-06, "loss": 0.0975, "step": 1012 }, { "epoch": 4.109367088607595, "grad_norm": 0.2834847736772136, "learning_rate": 3.6741329405168237e-06, "loss": 0.0997, "step": 1013 }, { "epoch": 4.113417721518988, "grad_norm": 0.30201370627031854, "learning_rate": 3.641412784665648e-06, "loss": 0.0955, "step": 1014 }, { "epoch": 4.11746835443038, "grad_norm": 0.2959058482291896, "learning_rate": 3.608824378627005e-06, "loss": 0.1047, "step": 1015 }, { "epoch": 4.121518987341772, "grad_norm": 0.2829014566142804, "learning_rate": 3.5763679848634337e-06, "loss": 0.105, "step": 1016 }, { "epoch": 4.125569620253165, "grad_norm": 0.2960513218653522, "learning_rate": 3.544043864774269e-06, "loss": 0.1122, "step": 1017 }, { "epoch": 4.129620253164557, "grad_norm": 0.2727241760977046, "learning_rate": 3.5118522786935282e-06, "loss": 0.1068, "step": 1018 }, { "epoch": 4.133670886075949, "grad_norm": 0.267818085927461, "learning_rate": 3.479793485887819e-06, "loss": 0.1048, "step": 1019 }, { "epoch": 4.137721518987342, "grad_norm": 0.2749259945962392, "learning_rate": 3.4478677445542653e-06, "loss": 0.111, "step": 1020 }, { "epoch": 4.141772151898734, "grad_norm": 0.26513784344660135, "learning_rate": 3.4160753118183767e-06, "loss": 0.1079, "step": 1021 }, { "epoch": 4.145822784810127, "grad_norm": 0.29215371719414723, "learning_rate": 3.3844164437320527e-06, "loss": 0.1077, "step": 1022 }, { "epoch": 4.149873417721519, "grad_norm": 0.2681993755782289, "learning_rate": 3.3528913952714558e-06, "loss": 0.1079, "step": 1023 }, { "epoch": 4.153924050632911, "grad_norm": 0.2794047542994287, "learning_rate": 3.321500420335e-06, "loss": 0.1195, "step": 1024 }, { "epoch": 4.157974683544304, "grad_norm": 0.2796635048557669, "learning_rate": 3.290243771741275e-06, "loss": 0.1052, "step": 1025 }, { "epoch": 4.162025316455696, "grad_norm": 0.2709026070328683, "learning_rate": 3.2591217012270325e-06, "loss": 0.1013, "step": 1026 }, { "epoch": 4.166075949367088, "grad_norm": 0.27126006467680763, "learning_rate": 3.228134459445149e-06, "loss": 0.1054, "step": 1027 }, { "epoch": 4.170126582278481, "grad_norm": 0.27896271826894214, "learning_rate": 3.1972822959626205e-06, "loss": 0.11, "step": 1028 }, { "epoch": 4.174177215189873, "grad_norm": 0.2844495727730424, "learning_rate": 3.166565459258513e-06, "loss": 0.1054, "step": 1029 }, { "epoch": 4.178227848101266, "grad_norm": 0.2860379018434228, "learning_rate": 3.1359841967220193e-06, "loss": 0.1134, "step": 1030 }, { "epoch": 4.182278481012658, "grad_norm": 0.2669895975162218, "learning_rate": 3.105538754650419e-06, "loss": 0.1172, "step": 1031 }, { "epoch": 4.18632911392405, "grad_norm": 0.27742272294028847, "learning_rate": 3.07522937824712e-06, "loss": 0.1088, "step": 1032 }, { "epoch": 4.190379746835443, "grad_norm": 0.2674721073883229, "learning_rate": 3.0450563116196697e-06, "loss": 0.1068, "step": 1033 }, { "epoch": 4.194430379746835, "grad_norm": 0.2731525269137438, "learning_rate": 3.0150197977778008e-06, "loss": 0.1084, "step": 1034 }, { "epoch": 4.1984810126582275, "grad_norm": 0.26997363632727533, "learning_rate": 2.985120078631465e-06, "loss": 0.0978, "step": 1035 }, { "epoch": 4.2025316455696204, "grad_norm": 0.26865533079636195, "learning_rate": 2.9553573949888893e-06, "loss": 0.1048, "step": 1036 }, { "epoch": 4.2065822784810125, "grad_norm": 0.27418126794779746, "learning_rate": 2.9257319865546384e-06, "loss": 0.1106, "step": 1037 }, { "epoch": 4.2106329113924055, "grad_norm": 0.27793206271821885, "learning_rate": 2.896244091927678e-06, "loss": 0.0995, "step": 1038 }, { "epoch": 4.2146835443037975, "grad_norm": 0.2766553662280719, "learning_rate": 2.8668939485994584e-06, "loss": 0.1031, "step": 1039 }, { "epoch": 4.21873417721519, "grad_norm": 0.2709002648147598, "learning_rate": 2.837681792951994e-06, "loss": 0.1098, "step": 1040 }, { "epoch": 4.222784810126583, "grad_norm": 0.2596409210078495, "learning_rate": 2.808607860255981e-06, "loss": 0.1084, "step": 1041 }, { "epoch": 4.226835443037975, "grad_norm": 0.2739962693663791, "learning_rate": 2.7796723846688634e-06, "loss": 0.1029, "step": 1042 }, { "epoch": 4.230886075949367, "grad_norm": 0.27117219696467343, "learning_rate": 2.7508755992329937e-06, "loss": 0.1054, "step": 1043 }, { "epoch": 4.23493670886076, "grad_norm": 0.2598198963972207, "learning_rate": 2.722217735873718e-06, "loss": 0.1039, "step": 1044 }, { "epoch": 4.238987341772152, "grad_norm": 0.2719671175877822, "learning_rate": 2.6936990253975315e-06, "loss": 0.1159, "step": 1045 }, { "epoch": 4.243037974683545, "grad_norm": 0.27207594214571346, "learning_rate": 2.665319697490205e-06, "loss": 0.1118, "step": 1046 }, { "epoch": 4.247088607594937, "grad_norm": 0.26851995923675953, "learning_rate": 2.637079980714945e-06, "loss": 0.1022, "step": 1047 }, { "epoch": 4.251139240506329, "grad_norm": 0.2834382271733648, "learning_rate": 2.6089801025105453e-06, "loss": 0.1084, "step": 1048 }, { "epoch": 4.255189873417722, "grad_norm": 0.263957313169379, "learning_rate": 2.581020289189571e-06, "loss": 0.1052, "step": 1049 }, { "epoch": 4.259240506329114, "grad_norm": 0.27167589570299766, "learning_rate": 2.553200765936501e-06, "loss": 0.099, "step": 1050 }, { "epoch": 4.263291139240506, "grad_norm": 0.2687237042727429, "learning_rate": 2.525521756805962e-06, "loss": 0.1007, "step": 1051 }, { "epoch": 4.267341772151899, "grad_norm": 0.276612859077791, "learning_rate": 2.497983484720885e-06, "loss": 0.0893, "step": 1052 }, { "epoch": 4.271392405063291, "grad_norm": 0.26054348162759217, "learning_rate": 2.470586171470728e-06, "loss": 0.1207, "step": 1053 }, { "epoch": 4.275443037974684, "grad_norm": 0.26224448384968924, "learning_rate": 2.4433300377096836e-06, "loss": 0.1087, "step": 1054 }, { "epoch": 4.279493670886076, "grad_norm": 0.27544627144185674, "learning_rate": 2.4162153029549073e-06, "loss": 0.1033, "step": 1055 }, { "epoch": 4.283544303797468, "grad_norm": 0.2725256772667477, "learning_rate": 2.3892421855847458e-06, "loss": 0.1036, "step": 1056 }, { "epoch": 4.287594936708861, "grad_norm": 0.26134641158370536, "learning_rate": 2.362410902836978e-06, "loss": 0.106, "step": 1057 }, { "epoch": 4.291645569620253, "grad_norm": 0.27302677301048933, "learning_rate": 2.3357216708070653e-06, "loss": 0.1094, "step": 1058 }, { "epoch": 4.295696202531645, "grad_norm": 0.26557358927517305, "learning_rate": 2.309174704446411e-06, "loss": 0.1046, "step": 1059 }, { "epoch": 4.299746835443038, "grad_norm": 0.2691156553827838, "learning_rate": 2.2827702175606437e-06, "loss": 0.1036, "step": 1060 }, { "epoch": 4.30379746835443, "grad_norm": 0.2807050822084683, "learning_rate": 2.256508422807855e-06, "loss": 0.103, "step": 1061 }, { "epoch": 4.307848101265823, "grad_norm": 0.26670204540650067, "learning_rate": 2.230389531696946e-06, "loss": 0.1072, "step": 1062 }, { "epoch": 4.311898734177215, "grad_norm": 0.2665585297924223, "learning_rate": 2.204413754585857e-06, "loss": 0.1031, "step": 1063 }, { "epoch": 4.315949367088607, "grad_norm": 0.25925709492868765, "learning_rate": 2.1785813006799406e-06, "loss": 0.1029, "step": 1064 }, { "epoch": 4.32, "grad_norm": 0.2710653261628063, "learning_rate": 2.1528923780302224e-06, "loss": 0.0983, "step": 1065 }, { "epoch": 4.324050632911392, "grad_norm": 0.2663387553518349, "learning_rate": 2.127347193531757e-06, "loss": 0.111, "step": 1066 }, { "epoch": 4.328101265822784, "grad_norm": 0.2705766645559629, "learning_rate": 2.101945952921942e-06, "loss": 0.1006, "step": 1067 }, { "epoch": 4.332151898734177, "grad_norm": 0.26720650728674117, "learning_rate": 2.0766888607788906e-06, "loss": 0.1071, "step": 1068 }, { "epoch": 4.3362025316455695, "grad_norm": 0.2611698340214045, "learning_rate": 2.0515761205197337e-06, "loss": 0.1103, "step": 1069 }, { "epoch": 4.340253164556962, "grad_norm": 0.26579077021120684, "learning_rate": 2.0266079343990453e-06, "loss": 0.0988, "step": 1070 }, { "epoch": 4.3443037974683545, "grad_norm": 0.26447810802154914, "learning_rate": 2.0017845035071494e-06, "loss": 0.1068, "step": 1071 }, { "epoch": 4.348354430379747, "grad_norm": 0.2766398554853194, "learning_rate": 1.9771060277685537e-06, "loss": 0.0988, "step": 1072 }, { "epoch": 4.3524050632911395, "grad_norm": 0.2756796311093678, "learning_rate": 1.95257270594031e-06, "loss": 0.0992, "step": 1073 }, { "epoch": 4.356455696202532, "grad_norm": 0.26267539322263883, "learning_rate": 1.9281847356104188e-06, "loss": 0.1031, "step": 1074 }, { "epoch": 4.360506329113924, "grad_norm": 0.2722950401779898, "learning_rate": 1.9039423131962365e-06, "loss": 0.1002, "step": 1075 }, { "epoch": 4.364556962025317, "grad_norm": 0.26051923107454, "learning_rate": 1.8798456339429027e-06, "loss": 0.1026, "step": 1076 }, { "epoch": 4.368607594936709, "grad_norm": 0.2754571942171403, "learning_rate": 1.8558948919217612e-06, "loss": 0.1002, "step": 1077 }, { "epoch": 4.372658227848102, "grad_norm": 0.27636627880190734, "learning_rate": 1.8320902800287954e-06, "loss": 0.1035, "step": 1078 }, { "epoch": 4.376708860759494, "grad_norm": 0.27917316003651454, "learning_rate": 1.8084319899830726e-06, "loss": 0.1191, "step": 1079 }, { "epoch": 4.380759493670886, "grad_norm": 0.2763451066647508, "learning_rate": 1.7849202123252097e-06, "loss": 0.0996, "step": 1080 }, { "epoch": 4.384810126582279, "grad_norm": 0.2699808717171086, "learning_rate": 1.7615551364158401e-06, "loss": 0.1099, "step": 1081 }, { "epoch": 4.388860759493671, "grad_norm": 0.2643097242152519, "learning_rate": 1.738336950434061e-06, "loss": 0.1105, "step": 1082 }, { "epoch": 4.392911392405063, "grad_norm": 0.2749157150822863, "learning_rate": 1.715265841375957e-06, "loss": 0.102, "step": 1083 }, { "epoch": 4.396962025316456, "grad_norm": 0.27087048142261566, "learning_rate": 1.6923419950530684e-06, "loss": 0.1061, "step": 1084 }, { "epoch": 4.401012658227848, "grad_norm": 0.27496750660237634, "learning_rate": 1.6695655960909008e-06, "loss": 0.1046, "step": 1085 }, { "epoch": 4.405063291139241, "grad_norm": 0.27687491830462324, "learning_rate": 1.646936827927441e-06, "loss": 0.1082, "step": 1086 }, { "epoch": 4.409113924050633, "grad_norm": 0.277610137841649, "learning_rate": 1.6244558728116766e-06, "loss": 0.111, "step": 1087 }, { "epoch": 4.413164556962025, "grad_norm": 0.2596558911309905, "learning_rate": 1.6021229118021265e-06, "loss": 0.1102, "step": 1088 }, { "epoch": 4.417215189873418, "grad_norm": 0.26632515603860096, "learning_rate": 1.5799381247653967e-06, "loss": 0.096, "step": 1089 }, { "epoch": 4.42126582278481, "grad_norm": 0.27586242744459577, "learning_rate": 1.5579016903747013e-06, "loss": 0.1095, "step": 1090 }, { "epoch": 4.425316455696202, "grad_norm": 0.2672396452093738, "learning_rate": 1.5360137861084656e-06, "loss": 0.1007, "step": 1091 }, { "epoch": 4.429367088607595, "grad_norm": 0.27160028620628823, "learning_rate": 1.5142745882488475e-06, "loss": 0.1056, "step": 1092 }, { "epoch": 4.433417721518987, "grad_norm": 0.2735904288753394, "learning_rate": 1.4926842718803691e-06, "loss": 0.1142, "step": 1093 }, { "epoch": 4.43746835443038, "grad_norm": 0.26321158406590084, "learning_rate": 1.4712430108884657e-06, "loss": 0.1052, "step": 1094 }, { "epoch": 4.441518987341772, "grad_norm": 0.2641753313810358, "learning_rate": 1.4499509779581078e-06, "loss": 0.1141, "step": 1095 }, { "epoch": 4.445569620253164, "grad_norm": 0.25750476172418646, "learning_rate": 1.4288083445723988e-06, "loss": 0.0995, "step": 1096 }, { "epoch": 4.449620253164557, "grad_norm": 0.25928959523375883, "learning_rate": 1.4078152810112045e-06, "loss": 0.1049, "step": 1097 }, { "epoch": 4.453670886075949, "grad_norm": 0.27053675827786205, "learning_rate": 1.3869719563497697e-06, "loss": 0.1033, "step": 1098 }, { "epoch": 4.457721518987341, "grad_norm": 0.2730361237458759, "learning_rate": 1.3662785384573663e-06, "loss": 0.1059, "step": 1099 }, { "epoch": 4.461772151898734, "grad_norm": 0.26720373180478174, "learning_rate": 1.3457351939959383e-06, "loss": 0.0991, "step": 1100 }, { "epoch": 4.465822784810126, "grad_norm": 0.26398983861591324, "learning_rate": 1.3253420884187551e-06, "loss": 0.108, "step": 1101 }, { "epoch": 4.469873417721519, "grad_norm": 0.2561414838857037, "learning_rate": 1.3050993859690953e-06, "loss": 0.112, "step": 1102 }, { "epoch": 4.473924050632911, "grad_norm": 0.27332111030684275, "learning_rate": 1.2850072496788869e-06, "loss": 0.1052, "step": 1103 }, { "epoch": 4.4779746835443035, "grad_norm": 0.2751866331799648, "learning_rate": 1.2650658413674434e-06, "loss": 0.1123, "step": 1104 }, { "epoch": 4.4820253164556965, "grad_norm": 0.2715338808379876, "learning_rate": 1.2452753216401226e-06, "loss": 0.1077, "step": 1105 }, { "epoch": 4.4860759493670885, "grad_norm": 0.2675310731768381, "learning_rate": 1.2256358498870503e-06, "loss": 0.1118, "step": 1106 }, { "epoch": 4.490126582278481, "grad_norm": 0.27031151693242, "learning_rate": 1.2061475842818337e-06, "loss": 0.0955, "step": 1107 }, { "epoch": 4.494177215189874, "grad_norm": 0.26554715179630073, "learning_rate": 1.1868106817802816e-06, "loss": 0.1077, "step": 1108 }, { "epoch": 4.498227848101266, "grad_norm": 0.2698632464449907, "learning_rate": 1.1676252981191482e-06, "loss": 0.1033, "step": 1109 }, { "epoch": 4.502278481012659, "grad_norm": 0.2494450096797627, "learning_rate": 1.1485915878148823e-06, "loss": 0.0968, "step": 1110 }, { "epoch": 4.506329113924051, "grad_norm": 0.2560612980596174, "learning_rate": 1.1297097041623584e-06, "loss": 0.106, "step": 1111 }, { "epoch": 4.510379746835443, "grad_norm": 0.2554047928156256, "learning_rate": 1.1109797992336847e-06, "loss": 0.1058, "step": 1112 }, { "epoch": 4.514430379746836, "grad_norm": 0.27424813658944364, "learning_rate": 1.092402023876933e-06, "loss": 0.107, "step": 1113 }, { "epoch": 4.518481012658228, "grad_norm": 0.2773376370322004, "learning_rate": 1.0739765277149527e-06, "loss": 0.1013, "step": 1114 }, { "epoch": 4.52253164556962, "grad_norm": 0.2592857270852379, "learning_rate": 1.0557034591441596e-06, "loss": 0.1026, "step": 1115 }, { "epoch": 4.526582278481013, "grad_norm": 0.2660644317175103, "learning_rate": 1.0375829653333324e-06, "loss": 0.0968, "step": 1116 }, { "epoch": 4.530632911392405, "grad_norm": 0.2697286851671116, "learning_rate": 1.0196151922224385e-06, "loss": 0.1078, "step": 1117 }, { "epoch": 4.534683544303798, "grad_norm": 0.28380324511027366, "learning_rate": 1.0018002845214526e-06, "loss": 0.1032, "step": 1118 }, { "epoch": 4.53873417721519, "grad_norm": 0.26586955477510826, "learning_rate": 9.841383857091947e-07, "loss": 0.1105, "step": 1119 }, { "epoch": 4.542784810126582, "grad_norm": 0.26451642323603825, "learning_rate": 9.666296380321616e-07, "loss": 0.1058, "step": 1120 }, { "epoch": 4.546835443037975, "grad_norm": 0.26101524350144345, "learning_rate": 9.492741825034124e-07, "loss": 0.0977, "step": 1121 }, { "epoch": 4.550886075949367, "grad_norm": 0.26854891927237745, "learning_rate": 9.320721589013892e-07, "loss": 0.1102, "step": 1122 }, { "epoch": 4.55493670886076, "grad_norm": 0.2592977627025496, "learning_rate": 9.150237057688339e-07, "loss": 0.1041, "step": 1123 }, { "epoch": 4.558987341772152, "grad_norm": 0.27126896193815103, "learning_rate": 8.981289604116328e-07, "loss": 0.1145, "step": 1124 }, { "epoch": 4.563037974683544, "grad_norm": 0.26215940592921616, "learning_rate": 8.813880588977542e-07, "loss": 0.1045, "step": 1125 }, { "epoch": 4.567088607594937, "grad_norm": 0.27609375682430476, "learning_rate": 8.648011360561126e-07, "loss": 0.1068, "step": 1126 }, { "epoch": 4.571139240506329, "grad_norm": 0.2656684445603004, "learning_rate": 8.483683254755037e-07, "loss": 0.1087, "step": 1127 }, { "epoch": 4.575189873417721, "grad_norm": 0.2594600175618137, "learning_rate": 8.320897595035227e-07, "loss": 0.1054, "step": 1128 }, { "epoch": 4.579240506329114, "grad_norm": 0.2524010346309865, "learning_rate": 8.159655692455093e-07, "loss": 0.1121, "step": 1129 }, { "epoch": 4.583291139240506, "grad_norm": 0.27906710500824916, "learning_rate": 7.999958845634648e-07, "loss": 0.1065, "step": 1130 }, { "epoch": 4.587341772151898, "grad_norm": 0.2584216230908451, "learning_rate": 7.841808340750478e-07, "loss": 0.1056, "step": 1131 }, { "epoch": 4.591392405063291, "grad_norm": 0.26825855989092934, "learning_rate": 7.685205451524869e-07, "loss": 0.1054, "step": 1132 }, { "epoch": 4.595443037974683, "grad_norm": 0.26547905974256863, "learning_rate": 7.530151439216027e-07, "loss": 0.0952, "step": 1133 }, { "epoch": 4.599493670886076, "grad_norm": 0.260834103903429, "learning_rate": 7.376647552607675e-07, "loss": 0.1017, "step": 1134 }, { "epoch": 4.603544303797468, "grad_norm": 0.27047716955543527, "learning_rate": 7.224695027998963e-07, "loss": 0.1052, "step": 1135 }, { "epoch": 4.6075949367088604, "grad_norm": 0.266761997407663, "learning_rate": 7.07429508919466e-07, "loss": 0.1082, "step": 1136 }, { "epoch": 4.611645569620253, "grad_norm": 0.2718339887092056, "learning_rate": 6.925448947495206e-07, "loss": 0.1038, "step": 1137 }, { "epoch": 4.6156962025316455, "grad_norm": 0.2670134218061989, "learning_rate": 6.778157801686936e-07, "loss": 0.1156, "step": 1138 }, { "epoch": 4.619746835443038, "grad_norm": 0.2632716127897459, "learning_rate": 6.632422838032515e-07, "loss": 0.1096, "step": 1139 }, { "epoch": 4.6237974683544305, "grad_norm": 0.25194506355382745, "learning_rate": 6.488245230261281e-07, "loss": 0.1014, "step": 1140 }, { "epoch": 4.627848101265823, "grad_norm": 0.2702159084290614, "learning_rate": 6.345626139559868e-07, "loss": 0.1071, "step": 1141 }, { "epoch": 4.6318987341772155, "grad_norm": 0.28149297109181126, "learning_rate": 6.204566714562866e-07, "loss": 0.0951, "step": 1142 }, { "epoch": 4.635949367088608, "grad_norm": 0.2559412297874004, "learning_rate": 6.06506809134344e-07, "loss": 0.1071, "step": 1143 }, { "epoch": 4.64, "grad_norm": 0.2588419803260574, "learning_rate": 5.927131393404373e-07, "loss": 0.1034, "step": 1144 }, { "epoch": 4.644050632911393, "grad_norm": 0.2669037133792349, "learning_rate": 5.790757731668817e-07, "loss": 0.1093, "step": 1145 }, { "epoch": 4.648101265822785, "grad_norm": 0.2538967574817087, "learning_rate": 5.655948204471507e-07, "loss": 0.1044, "step": 1146 }, { "epoch": 4.652151898734177, "grad_norm": 0.2591087984701281, "learning_rate": 5.522703897549875e-07, "loss": 0.1047, "step": 1147 }, { "epoch": 4.65620253164557, "grad_norm": 0.271216432749416, "learning_rate": 5.391025884035239e-07, "loss": 0.1047, "step": 1148 }, { "epoch": 4.660253164556962, "grad_norm": 0.2791835955604378, "learning_rate": 5.260915224444207e-07, "loss": 0.1048, "step": 1149 }, { "epoch": 4.664303797468355, "grad_norm": 0.26605630984932627, "learning_rate": 5.132372966670129e-07, "loss": 0.1033, "step": 1150 }, { "epoch": 4.668354430379747, "grad_norm": 0.26143460744835373, "learning_rate": 5.005400145974704e-07, "loss": 0.0985, "step": 1151 }, { "epoch": 4.672405063291139, "grad_norm": 0.27525864337198475, "learning_rate": 4.879997784979562e-07, "loss": 0.1048, "step": 1152 }, { "epoch": 4.676455696202532, "grad_norm": 0.26543716327972083, "learning_rate": 4.7561668936580984e-07, "loss": 0.1169, "step": 1153 }, { "epoch": 4.680506329113924, "grad_norm": 0.25191776317911035, "learning_rate": 4.6339084693272306e-07, "loss": 0.0944, "step": 1154 }, { "epoch": 4.684556962025317, "grad_norm": 0.26165918506393165, "learning_rate": 4.5132234966395847e-07, "loss": 0.1087, "step": 1155 }, { "epoch": 4.688607594936709, "grad_norm": 0.2669688710902123, "learning_rate": 4.3941129475752795e-07, "loss": 0.0987, "step": 1156 }, { "epoch": 4.692658227848101, "grad_norm": 0.27382001653287014, "learning_rate": 4.27657778143431e-07, "loss": 0.1021, "step": 1157 }, { "epoch": 4.696708860759494, "grad_norm": 0.27684606225496095, "learning_rate": 4.1606189448287757e-07, "loss": 0.1123, "step": 1158 }, { "epoch": 4.700759493670886, "grad_norm": 0.265370271170092, "learning_rate": 4.046237371675177e-07, "loss": 0.1102, "step": 1159 }, { "epoch": 4.704810126582278, "grad_norm": 0.27259441064652135, "learning_rate": 3.9334339831869963e-07, "loss": 0.1015, "step": 1160 }, { "epoch": 4.708860759493671, "grad_norm": 0.2612625782230943, "learning_rate": 3.8222096878671955e-07, "loss": 0.1094, "step": 1161 }, { "epoch": 4.712911392405063, "grad_norm": 0.26432016604373737, "learning_rate": 3.7125653815009545e-07, "loss": 0.1106, "step": 1162 }, { "epoch": 4.716962025316455, "grad_norm": 0.270851695485006, "learning_rate": 3.6045019471484974e-07, "loss": 0.1039, "step": 1163 }, { "epoch": 4.721012658227848, "grad_norm": 0.25979594489071434, "learning_rate": 3.498020255137813e-07, "loss": 0.102, "step": 1164 }, { "epoch": 4.72506329113924, "grad_norm": 0.2626565104167224, "learning_rate": 3.393121163057811e-07, "loss": 0.1069, "step": 1165 }, { "epoch": 4.729113924050633, "grad_norm": 0.2658661046229716, "learning_rate": 3.289805515751399e-07, "loss": 0.1096, "step": 1166 }, { "epoch": 4.733164556962025, "grad_norm": 0.2581234818197009, "learning_rate": 3.188074145308573e-07, "loss": 0.096, "step": 1167 }, { "epoch": 4.737215189873417, "grad_norm": 0.25467636601414695, "learning_rate": 3.087927871059804e-07, "loss": 0.1053, "step": 1168 }, { "epoch": 4.74126582278481, "grad_norm": 0.2666905122444818, "learning_rate": 2.989367499569418e-07, "loss": 0.0988, "step": 1169 }, { "epoch": 4.745316455696202, "grad_norm": 0.25308375506458053, "learning_rate": 2.8923938246290917e-07, "loss": 0.1049, "step": 1170 }, { "epoch": 4.749367088607595, "grad_norm": 0.26260708384553655, "learning_rate": 2.7970076272514804e-07, "loss": 0.111, "step": 1171 }, { "epoch": 4.7534177215189874, "grad_norm": 0.2623421171902755, "learning_rate": 2.703209675663887e-07, "loss": 0.1106, "step": 1172 }, { "epoch": 4.7574683544303795, "grad_norm": 0.2663686894172937, "learning_rate": 2.6110007253021374e-07, "loss": 0.1039, "step": 1173 }, { "epoch": 4.7615189873417725, "grad_norm": 0.28231271975295724, "learning_rate": 2.520381518804471e-07, "loss": 0.0979, "step": 1174 }, { "epoch": 4.7655696202531646, "grad_norm": 0.2576326806142396, "learning_rate": 2.4313527860054585e-07, "loss": 0.1034, "step": 1175 }, { "epoch": 4.769620253164557, "grad_norm": 0.2573650184069184, "learning_rate": 2.343915243930317e-07, "loss": 0.1097, "step": 1176 }, { "epoch": 4.77367088607595, "grad_norm": 0.2616252423246205, "learning_rate": 2.2580695967889367e-07, "loss": 0.1059, "step": 1177 }, { "epoch": 4.777721518987342, "grad_norm": 0.2741665075974677, "learning_rate": 2.1738165359704189e-07, "loss": 0.1068, "step": 1178 }, { "epoch": 4.781772151898734, "grad_norm": 0.25938181009162387, "learning_rate": 2.0911567400373257e-07, "loss": 0.1046, "step": 1179 }, { "epoch": 4.785822784810127, "grad_norm": 0.2768629638346095, "learning_rate": 2.0100908747202607e-07, "loss": 0.1106, "step": 1180 }, { "epoch": 4.789873417721519, "grad_norm": 0.26381235954436133, "learning_rate": 1.9306195929125638e-07, "loss": 0.1067, "step": 1181 }, { "epoch": 4.793924050632912, "grad_norm": 0.2608054310683676, "learning_rate": 1.8527435346650247e-07, "loss": 0.0939, "step": 1182 }, { "epoch": 4.797974683544304, "grad_norm": 0.26813249553767876, "learning_rate": 1.7764633271807108e-07, "loss": 0.112, "step": 1183 }, { "epoch": 4.802025316455696, "grad_norm": 0.2577643256382701, "learning_rate": 1.7017795848099262e-07, "loss": 0.1161, "step": 1184 }, { "epoch": 4.806075949367089, "grad_norm": 0.2626061158442528, "learning_rate": 1.6286929090452596e-07, "loss": 0.0998, "step": 1185 }, { "epoch": 4.810126582278481, "grad_norm": 0.26626056731272435, "learning_rate": 1.557203888516745e-07, "loss": 0.1058, "step": 1186 }, { "epoch": 4.814177215189874, "grad_norm": 0.2754860325071909, "learning_rate": 1.487313098987131e-07, "loss": 0.0949, "step": 1187 }, { "epoch": 4.818227848101266, "grad_norm": 0.2660421356679764, "learning_rate": 1.4190211033472402e-07, "loss": 0.1107, "step": 1188 }, { "epoch": 4.822278481012658, "grad_norm": 0.27088167929852214, "learning_rate": 1.3523284516113955e-07, "loss": 0.0957, "step": 1189 }, { "epoch": 4.826329113924051, "grad_norm": 0.2800528149259873, "learning_rate": 1.2872356809130682e-07, "loss": 0.1011, "step": 1190 }, { "epoch": 4.830379746835443, "grad_norm": 0.2699830980536786, "learning_rate": 1.2237433155004807e-07, "loss": 0.1043, "step": 1191 }, { "epoch": 4.834430379746835, "grad_norm": 0.2695915883337478, "learning_rate": 1.1618518667323886e-07, "loss": 0.1118, "step": 1192 }, { "epoch": 4.838481012658228, "grad_norm": 0.2611098061895777, "learning_rate": 1.1015618330740385e-07, "loss": 0.1187, "step": 1193 }, { "epoch": 4.84253164556962, "grad_norm": 0.25218859493339296, "learning_rate": 1.042873700093061e-07, "loss": 0.1012, "step": 1194 }, { "epoch": 4.846582278481012, "grad_norm": 0.271549511667465, "learning_rate": 9.857879404556291e-08, "loss": 0.1074, "step": 1195 }, { "epoch": 4.850632911392405, "grad_norm": 0.25823624128644546, "learning_rate": 9.303050139225722e-08, "loss": 0.1036, "step": 1196 }, { "epoch": 4.854683544303797, "grad_norm": 0.2634391170184233, "learning_rate": 8.76425367345779e-08, "loss": 0.11, "step": 1197 }, { "epoch": 4.85873417721519, "grad_norm": 0.24730850022767073, "learning_rate": 8.241494346644897e-08, "loss": 0.1033, "step": 1198 }, { "epoch": 4.862784810126582, "grad_norm": 0.2524378698040851, "learning_rate": 7.734776369019204e-08, "loss": 0.1046, "step": 1199 }, { "epoch": 4.866835443037974, "grad_norm": 0.25559583485514087, "learning_rate": 7.244103821617332e-08, "loss": 0.0991, "step": 1200 }, { "epoch": 4.870886075949367, "grad_norm": 0.26915823786497667, "learning_rate": 6.769480656248606e-08, "loss": 0.1128, "step": 1201 }, { "epoch": 4.874936708860759, "grad_norm": 0.2589281033091417, "learning_rate": 6.310910695462635e-08, "loss": 0.1, "step": 1202 }, { "epoch": 4.878987341772152, "grad_norm": 0.26375802062301557, "learning_rate": 5.8683976325191185e-08, "loss": 0.1045, "step": 1203 }, { "epoch": 4.883037974683544, "grad_norm": 0.26937629159157234, "learning_rate": 5.4419450313571984e-08, "loss": 0.1029, "step": 1204 }, { "epoch": 4.8870886075949365, "grad_norm": 0.25588201106857716, "learning_rate": 5.031556326567488e-08, "loss": 0.0953, "step": 1205 }, { "epoch": 4.891139240506329, "grad_norm": 0.28280716069777206, "learning_rate": 4.637234823364312e-08, "loss": 0.0972, "step": 1206 }, { "epoch": 4.8951898734177215, "grad_norm": 0.25976326628964164, "learning_rate": 4.258983697558838e-08, "loss": 0.0987, "step": 1207 }, { "epoch": 4.899240506329114, "grad_norm": 0.2621322478382903, "learning_rate": 3.896805995533548e-08, "loss": 0.1081, "step": 1208 }, { "epoch": 4.9032911392405065, "grad_norm": 0.2552173789923443, "learning_rate": 3.550704634218028e-08, "loss": 0.1067, "step": 1209 }, { "epoch": 4.907341772151899, "grad_norm": 0.2683889071916882, "learning_rate": 3.2206824010647676e-08, "loss": 0.1079, "step": 1210 }, { "epoch": 4.911392405063291, "grad_norm": 0.2551316267086611, "learning_rate": 2.9067419540278476e-08, "loss": 0.1088, "step": 1211 }, { "epoch": 4.915443037974684, "grad_norm": 0.2550031006460478, "learning_rate": 2.6088858215400638e-08, "loss": 0.0962, "step": 1212 }, { "epoch": 4.919493670886076, "grad_norm": 0.2569360796955214, "learning_rate": 2.3271164024940564e-08, "loss": 0.1104, "step": 1213 }, { "epoch": 4.923544303797469, "grad_norm": 0.2558391625192528, "learning_rate": 2.061435966221881e-08, "loss": 0.0961, "step": 1214 }, { "epoch": 4.927594936708861, "grad_norm": 0.25702419732147974, "learning_rate": 1.811846652477245e-08, "loss": 0.1067, "step": 1215 }, { "epoch": 4.931645569620253, "grad_norm": 0.25761492165232797, "learning_rate": 1.5783504714184106e-08, "loss": 0.1033, "step": 1216 }, { "epoch": 4.935696202531646, "grad_norm": 0.26041469930038114, "learning_rate": 1.360949303591097e-08, "loss": 0.1112, "step": 1217 }, { "epoch": 4.939746835443038, "grad_norm": 0.25587902509360677, "learning_rate": 1.1596448999144916e-08, "loss": 0.0997, "step": 1218 }, { "epoch": 4.943797468354431, "grad_norm": 0.270037884264655, "learning_rate": 9.744388816668172e-09, "loss": 0.1006, "step": 1219 }, { "epoch": 4.947848101265823, "grad_norm": 0.26845344558712936, "learning_rate": 8.05332740472009e-09, "loss": 0.1082, "step": 1220 }, { "epoch": 4.951898734177215, "grad_norm": 0.2605311112285889, "learning_rate": 6.523278382872811e-09, "loss": 0.1049, "step": 1221 }, { "epoch": 4.955949367088608, "grad_norm": 0.2569174250567159, "learning_rate": 5.15425407393133e-09, "loss": 0.0992, "step": 1222 }, { "epoch": 4.96, "grad_norm": 0.2556280997424808, "learning_rate": 3.94626550383137e-09, "loss": 0.0979, "step": 1223 }, { "epoch": 4.964050632911392, "grad_norm": 0.2632406675338473, "learning_rate": 2.899322401546112e-09, "loss": 0.11, "step": 1224 }, { "epoch": 4.968101265822785, "grad_norm": 0.2553459212610176, "learning_rate": 2.013433199010706e-09, "loss": 0.0944, "step": 1225 }, { "epoch": 4.972151898734177, "grad_norm": 0.2652074804061254, "learning_rate": 1.2886050310556563e-09, "loss": 0.1065, "step": 1226 }, { "epoch": 4.976202531645569, "grad_norm": 0.25838123564491444, "learning_rate": 7.248437353468695e-10, "loss": 0.1047, "step": 1227 }, { "epoch": 4.980253164556962, "grad_norm": 0.257478156393974, "learning_rate": 3.221538523412449e-10, "loss": 0.1088, "step": 1228 }, { "epoch": 4.984303797468354, "grad_norm": 0.2489465983280526, "learning_rate": 8.053862524670663e-11, "loss": 0.111, "step": 1229 }, { "epoch": 4.988354430379747, "grad_norm": 0.24906429250903517, "learning_rate": 0.0, "loss": 0.099, "step": 1230 }, { "epoch": 4.988354430379747, "step": 1230, "total_flos": 1.424052118385328e+18, "train_loss": 0.23391443721768332, "train_runtime": 42513.0625, "train_samples_per_second": 3.717, "train_steps_per_second": 0.029 } ], "logging_steps": 1, "max_steps": 1230, "num_input_tokens_seen": 0, "num_train_epochs": 5, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 1.424052118385328e+18, "train_batch_size": 1, "trial_name": null, "trial_params": null }