{ "best_metric": null, "best_model_checkpoint": null, "epoch": 4.982278481012658, "eval_steps": 500, "global_step": 1230, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.004050632911392405, "grad_norm": 7.732524899337994, "learning_rate": 3.2520325203252037e-07, "loss": 1.0956, "step": 1 }, { "epoch": 0.00810126582278481, "grad_norm": 7.717390132184792, "learning_rate": 6.504065040650407e-07, "loss": 1.0992, "step": 2 }, { "epoch": 0.012151898734177215, "grad_norm": 7.56754549472902, "learning_rate": 9.75609756097561e-07, "loss": 1.0949, "step": 3 }, { "epoch": 0.01620253164556962, "grad_norm": 7.4813532657487585, "learning_rate": 1.3008130081300815e-06, "loss": 1.088, "step": 4 }, { "epoch": 0.020253164556962026, "grad_norm": 6.992686811319286, "learning_rate": 1.6260162601626018e-06, "loss": 1.0774, "step": 5 }, { "epoch": 0.02430379746835443, "grad_norm": 6.856876213320309, "learning_rate": 1.951219512195122e-06, "loss": 1.074, "step": 6 }, { "epoch": 0.028354430379746835, "grad_norm": 5.17666644394414, "learning_rate": 2.2764227642276426e-06, "loss": 1.0366, "step": 7 }, { "epoch": 0.03240506329113924, "grad_norm": 4.76898945175685, "learning_rate": 2.601626016260163e-06, "loss": 1.04, "step": 8 }, { "epoch": 0.03645569620253165, "grad_norm": 3.0680394913226965, "learning_rate": 2.926829268292683e-06, "loss": 0.9914, "step": 9 }, { "epoch": 0.04050632911392405, "grad_norm": 2.9611689037768865, "learning_rate": 3.2520325203252037e-06, "loss": 0.9908, "step": 10 }, { "epoch": 0.044556962025316456, "grad_norm": 2.9379219103968697, "learning_rate": 3.577235772357724e-06, "loss": 0.9965, "step": 11 }, { "epoch": 0.04860759493670886, "grad_norm": 4.097340019994171, "learning_rate": 3.902439024390244e-06, "loss": 0.9575, "step": 12 }, { "epoch": 0.052658227848101265, "grad_norm": 4.286185749809645, "learning_rate": 4.227642276422765e-06, "loss": 0.9716, "step": 13 }, { "epoch": 0.05670886075949367, "grad_norm": 4.006831125007636, "learning_rate": 4.552845528455285e-06, "loss": 0.9406, "step": 14 }, { "epoch": 0.060759493670886074, "grad_norm": 3.447620763776701, "learning_rate": 4.8780487804878055e-06, "loss": 0.9259, "step": 15 }, { "epoch": 0.06481012658227848, "grad_norm": 2.5413779961162146, "learning_rate": 5.203252032520326e-06, "loss": 0.89, "step": 16 }, { "epoch": 0.06886075949367089, "grad_norm": 2.587855999200275, "learning_rate": 5.528455284552846e-06, "loss": 0.8718, "step": 17 }, { "epoch": 0.0729113924050633, "grad_norm": 2.200131030244883, "learning_rate": 5.853658536585366e-06, "loss": 0.86, "step": 18 }, { "epoch": 0.0769620253164557, "grad_norm": 1.528504373687041, "learning_rate": 6.178861788617887e-06, "loss": 0.8468, "step": 19 }, { "epoch": 0.0810126582278481, "grad_norm": 1.1203359707651883, "learning_rate": 6.504065040650407e-06, "loss": 0.8247, "step": 20 }, { "epoch": 0.08506329113924051, "grad_norm": 1.258841039777198, "learning_rate": 6.829268292682928e-06, "loss": 0.8192, "step": 21 }, { "epoch": 0.08911392405063291, "grad_norm": 1.3719356008758194, "learning_rate": 7.154471544715448e-06, "loss": 0.8051, "step": 22 }, { "epoch": 0.09316455696202532, "grad_norm": 1.1693658341477549, "learning_rate": 7.4796747967479676e-06, "loss": 0.7803, "step": 23 }, { "epoch": 0.09721518987341772, "grad_norm": 0.9654979658710224, "learning_rate": 7.804878048780489e-06, "loss": 0.7768, "step": 24 }, { "epoch": 0.10126582278481013, "grad_norm": 0.9835089189469621, "learning_rate": 8.130081300813009e-06, "loss": 0.7799, "step": 25 }, { "epoch": 0.10531645569620253, "grad_norm": 0.9310958007052378, "learning_rate": 8.45528455284553e-06, "loss": 0.7762, "step": 26 }, { "epoch": 0.10936708860759493, "grad_norm": 0.9254984628146359, "learning_rate": 8.78048780487805e-06, "loss": 0.768, "step": 27 }, { "epoch": 0.11341772151898734, "grad_norm": 0.8121660320123946, "learning_rate": 9.10569105691057e-06, "loss": 0.7518, "step": 28 }, { "epoch": 0.11746835443037974, "grad_norm": 0.8217277652698322, "learning_rate": 9.43089430894309e-06, "loss": 0.7537, "step": 29 }, { "epoch": 0.12151898734177215, "grad_norm": 0.8156314883550289, "learning_rate": 9.756097560975611e-06, "loss": 0.753, "step": 30 }, { "epoch": 0.12556962025316457, "grad_norm": 0.7725540413516938, "learning_rate": 1.008130081300813e-05, "loss": 0.7413, "step": 31 }, { "epoch": 0.12962025316455697, "grad_norm": 0.6377870339430359, "learning_rate": 1.0406504065040652e-05, "loss": 0.7351, "step": 32 }, { "epoch": 0.13367088607594937, "grad_norm": 0.6390902108847236, "learning_rate": 1.0731707317073172e-05, "loss": 0.7339, "step": 33 }, { "epoch": 0.13772151898734178, "grad_norm": 0.7189896780326551, "learning_rate": 1.1056910569105692e-05, "loss": 0.7323, "step": 34 }, { "epoch": 0.14177215189873418, "grad_norm": 0.7052322018493971, "learning_rate": 1.1382113821138213e-05, "loss": 0.7115, "step": 35 }, { "epoch": 0.1458227848101266, "grad_norm": 0.5885057583860994, "learning_rate": 1.1707317073170731e-05, "loss": 0.7115, "step": 36 }, { "epoch": 0.149873417721519, "grad_norm": 0.7104010838108131, "learning_rate": 1.2032520325203254e-05, "loss": 0.7183, "step": 37 }, { "epoch": 0.1539240506329114, "grad_norm": 0.6336332317547739, "learning_rate": 1.2357723577235774e-05, "loss": 0.7052, "step": 38 }, { "epoch": 0.1579746835443038, "grad_norm": 0.7677597072289932, "learning_rate": 1.2682926829268294e-05, "loss": 0.7092, "step": 39 }, { "epoch": 0.1620253164556962, "grad_norm": 0.6666030178896452, "learning_rate": 1.3008130081300815e-05, "loss": 0.7034, "step": 40 }, { "epoch": 0.1660759493670886, "grad_norm": 0.6928366472976552, "learning_rate": 1.3333333333333333e-05, "loss": 0.7067, "step": 41 }, { "epoch": 0.17012658227848101, "grad_norm": 0.6384175522992862, "learning_rate": 1.3658536585365855e-05, "loss": 0.7088, "step": 42 }, { "epoch": 0.17417721518987342, "grad_norm": 0.6673658016540963, "learning_rate": 1.3983739837398376e-05, "loss": 0.6966, "step": 43 }, { "epoch": 0.17822784810126582, "grad_norm": 0.524277043529056, "learning_rate": 1.4308943089430896e-05, "loss": 0.6975, "step": 44 }, { "epoch": 0.18227848101265823, "grad_norm": 0.7091907919268892, "learning_rate": 1.4634146341463415e-05, "loss": 0.6806, "step": 45 }, { "epoch": 0.18632911392405063, "grad_norm": 0.5798618683803232, "learning_rate": 1.4959349593495935e-05, "loss": 0.6845, "step": 46 }, { "epoch": 0.19037974683544304, "grad_norm": 0.6454205483722738, "learning_rate": 1.528455284552846e-05, "loss": 0.6955, "step": 47 }, { "epoch": 0.19443037974683544, "grad_norm": 0.6341780749233981, "learning_rate": 1.5609756097560978e-05, "loss": 0.7005, "step": 48 }, { "epoch": 0.19848101265822785, "grad_norm": 0.8160633497771463, "learning_rate": 1.5934959349593496e-05, "loss": 0.6848, "step": 49 }, { "epoch": 0.20253164556962025, "grad_norm": 0.7047934874041232, "learning_rate": 1.6260162601626018e-05, "loss": 0.6727, "step": 50 }, { "epoch": 0.20658227848101265, "grad_norm": 0.5784070633397905, "learning_rate": 1.6585365853658537e-05, "loss": 0.6828, "step": 51 }, { "epoch": 0.21063291139240506, "grad_norm": 0.6532652367569824, "learning_rate": 1.691056910569106e-05, "loss": 0.6801, "step": 52 }, { "epoch": 0.21468354430379746, "grad_norm": 0.6696662814596274, "learning_rate": 1.7235772357723578e-05, "loss": 0.672, "step": 53 }, { "epoch": 0.21873417721518987, "grad_norm": 0.7719383775275271, "learning_rate": 1.75609756097561e-05, "loss": 0.6785, "step": 54 }, { "epoch": 0.22278481012658227, "grad_norm": 0.6849218610288049, "learning_rate": 1.788617886178862e-05, "loss": 0.6777, "step": 55 }, { "epoch": 0.22683544303797468, "grad_norm": 0.8692101784259096, "learning_rate": 1.821138211382114e-05, "loss": 0.6711, "step": 56 }, { "epoch": 0.23088607594936708, "grad_norm": 0.9301475147444148, "learning_rate": 1.8536585365853663e-05, "loss": 0.6695, "step": 57 }, { "epoch": 0.23493670886075949, "grad_norm": 0.9872021648774384, "learning_rate": 1.886178861788618e-05, "loss": 0.6626, "step": 58 }, { "epoch": 0.2389873417721519, "grad_norm": 1.0577948881863648, "learning_rate": 1.91869918699187e-05, "loss": 0.6557, "step": 59 }, { "epoch": 0.2430379746835443, "grad_norm": 1.0172322249304329, "learning_rate": 1.9512195121951222e-05, "loss": 0.6718, "step": 60 }, { "epoch": 0.2470886075949367, "grad_norm": 0.702780309671675, "learning_rate": 1.983739837398374e-05, "loss": 0.665, "step": 61 }, { "epoch": 0.25113924050632913, "grad_norm": 0.7577405777385738, "learning_rate": 2.016260162601626e-05, "loss": 0.6561, "step": 62 }, { "epoch": 0.25518987341772154, "grad_norm": 0.9660715505847182, "learning_rate": 2.048780487804878e-05, "loss": 0.663, "step": 63 }, { "epoch": 0.25924050632911394, "grad_norm": 1.1062485831870004, "learning_rate": 2.0813008130081303e-05, "loss": 0.6734, "step": 64 }, { "epoch": 0.26329113924050634, "grad_norm": 0.6485031185990456, "learning_rate": 2.1138211382113822e-05, "loss": 0.6535, "step": 65 }, { "epoch": 0.26734177215189875, "grad_norm": 1.2414697932694325, "learning_rate": 2.1463414634146344e-05, "loss": 0.665, "step": 66 }, { "epoch": 0.27139240506329115, "grad_norm": 1.2054066145470201, "learning_rate": 2.1788617886178863e-05, "loss": 0.6617, "step": 67 }, { "epoch": 0.27544303797468356, "grad_norm": 0.8234046248894216, "learning_rate": 2.2113821138211385e-05, "loss": 0.6657, "step": 68 }, { "epoch": 0.27949367088607596, "grad_norm": 0.9917864631678054, "learning_rate": 2.2439024390243907e-05, "loss": 0.6563, "step": 69 }, { "epoch": 0.28354430379746837, "grad_norm": 1.0460631403670668, "learning_rate": 2.2764227642276426e-05, "loss": 0.6594, "step": 70 }, { "epoch": 0.28759493670886077, "grad_norm": 1.3176609738908147, "learning_rate": 2.3089430894308948e-05, "loss": 0.6619, "step": 71 }, { "epoch": 0.2916455696202532, "grad_norm": 0.9197537492069436, "learning_rate": 2.3414634146341463e-05, "loss": 0.6481, "step": 72 }, { "epoch": 0.2956962025316456, "grad_norm": 1.3481014307501056, "learning_rate": 2.3739837398373985e-05, "loss": 0.6451, "step": 73 }, { "epoch": 0.299746835443038, "grad_norm": 1.1327785481363317, "learning_rate": 2.4065040650406507e-05, "loss": 0.6487, "step": 74 }, { "epoch": 0.3037974683544304, "grad_norm": 0.9582667137292215, "learning_rate": 2.4390243902439026e-05, "loss": 0.6517, "step": 75 }, { "epoch": 0.3078481012658228, "grad_norm": 1.312487669743203, "learning_rate": 2.4715447154471548e-05, "loss": 0.6592, "step": 76 }, { "epoch": 0.3118987341772152, "grad_norm": 0.8631007962696733, "learning_rate": 2.5040650406504066e-05, "loss": 0.668, "step": 77 }, { "epoch": 0.3159493670886076, "grad_norm": 1.5479192206477592, "learning_rate": 2.536585365853659e-05, "loss": 0.6652, "step": 78 }, { "epoch": 0.32, "grad_norm": 1.221015335297266, "learning_rate": 2.569105691056911e-05, "loss": 0.6545, "step": 79 }, { "epoch": 0.3240506329113924, "grad_norm": 1.28130597344399, "learning_rate": 2.601626016260163e-05, "loss": 0.6427, "step": 80 }, { "epoch": 0.3281012658227848, "grad_norm": 1.403008285624315, "learning_rate": 2.634146341463415e-05, "loss": 0.6525, "step": 81 }, { "epoch": 0.3321518987341772, "grad_norm": 1.2740202940042333, "learning_rate": 2.6666666666666667e-05, "loss": 0.6602, "step": 82 }, { "epoch": 0.3362025316455696, "grad_norm": 1.5441259906107292, "learning_rate": 2.699186991869919e-05, "loss": 0.6527, "step": 83 }, { "epoch": 0.34025316455696203, "grad_norm": 1.305333306744245, "learning_rate": 2.731707317073171e-05, "loss": 0.6436, "step": 84 }, { "epoch": 0.34430379746835443, "grad_norm": 1.3353909858301807, "learning_rate": 2.764227642276423e-05, "loss": 0.643, "step": 85 }, { "epoch": 0.34835443037974684, "grad_norm": 1.3577970599008697, "learning_rate": 2.796747967479675e-05, "loss": 0.642, "step": 86 }, { "epoch": 0.35240506329113924, "grad_norm": 0.9493769252821821, "learning_rate": 2.829268292682927e-05, "loss": 0.6586, "step": 87 }, { "epoch": 0.35645569620253165, "grad_norm": 1.7116959007031043, "learning_rate": 2.8617886178861792e-05, "loss": 0.6495, "step": 88 }, { "epoch": 0.36050632911392405, "grad_norm": 1.1009444431142437, "learning_rate": 2.8943089430894314e-05, "loss": 0.6314, "step": 89 }, { "epoch": 0.36455696202531646, "grad_norm": 2.1243653119526735, "learning_rate": 2.926829268292683e-05, "loss": 0.6497, "step": 90 }, { "epoch": 0.36860759493670886, "grad_norm": 1.9200895370178837, "learning_rate": 2.959349593495935e-05, "loss": 0.6409, "step": 91 }, { "epoch": 0.37265822784810126, "grad_norm": 1.5639357707861403, "learning_rate": 2.991869918699187e-05, "loss": 0.6496, "step": 92 }, { "epoch": 0.37670886075949367, "grad_norm": 1.6405647742552176, "learning_rate": 3.0243902439024392e-05, "loss": 0.657, "step": 93 }, { "epoch": 0.3807594936708861, "grad_norm": 1.5298584096387633, "learning_rate": 3.056910569105692e-05, "loss": 0.6344, "step": 94 }, { "epoch": 0.3848101265822785, "grad_norm": 1.360779504825709, "learning_rate": 3.089430894308943e-05, "loss": 0.6454, "step": 95 }, { "epoch": 0.3888607594936709, "grad_norm": 1.6681305606560415, "learning_rate": 3.1219512195121955e-05, "loss": 0.6548, "step": 96 }, { "epoch": 0.3929113924050633, "grad_norm": 1.233716588664374, "learning_rate": 3.154471544715447e-05, "loss": 0.6448, "step": 97 }, { "epoch": 0.3969620253164557, "grad_norm": 1.3271906637476578, "learning_rate": 3.186991869918699e-05, "loss": 0.633, "step": 98 }, { "epoch": 0.4010126582278481, "grad_norm": 1.0958427379157614, "learning_rate": 3.2195121951219514e-05, "loss": 0.6425, "step": 99 }, { "epoch": 0.4050632911392405, "grad_norm": 1.3021564041002447, "learning_rate": 3.2520325203252037e-05, "loss": 0.6417, "step": 100 }, { "epoch": 0.4091139240506329, "grad_norm": 0.9861966558986908, "learning_rate": 3.284552845528456e-05, "loss": 0.6353, "step": 101 }, { "epoch": 0.4131645569620253, "grad_norm": 1.9915105149674939, "learning_rate": 3.3170731707317074e-05, "loss": 0.6477, "step": 102 }, { "epoch": 0.4172151898734177, "grad_norm": 1.2544090272296686, "learning_rate": 3.3495934959349596e-05, "loss": 0.6404, "step": 103 }, { "epoch": 0.4212658227848101, "grad_norm": 1.868263886020954, "learning_rate": 3.382113821138212e-05, "loss": 0.6459, "step": 104 }, { "epoch": 0.4253164556962025, "grad_norm": 1.6352747641542345, "learning_rate": 3.414634146341463e-05, "loss": 0.6377, "step": 105 }, { "epoch": 0.4293670886075949, "grad_norm": 1.2944790386735956, "learning_rate": 3.4471544715447155e-05, "loss": 0.6466, "step": 106 }, { "epoch": 0.43341772151898733, "grad_norm": 1.2196904057485163, "learning_rate": 3.479674796747968e-05, "loss": 0.6356, "step": 107 }, { "epoch": 0.43746835443037974, "grad_norm": 1.0050719919755935, "learning_rate": 3.51219512195122e-05, "loss": 0.6329, "step": 108 }, { "epoch": 0.44151898734177214, "grad_norm": 1.4012823511826276, "learning_rate": 3.544715447154472e-05, "loss": 0.6293, "step": 109 }, { "epoch": 0.44556962025316454, "grad_norm": 1.2134650373369753, "learning_rate": 3.577235772357724e-05, "loss": 0.6371, "step": 110 }, { "epoch": 0.44962025316455695, "grad_norm": 0.9161306299972071, "learning_rate": 3.609756097560976e-05, "loss": 0.6271, "step": 111 }, { "epoch": 0.45367088607594935, "grad_norm": 1.3277377837312232, "learning_rate": 3.642276422764228e-05, "loss": 0.6231, "step": 112 }, { "epoch": 0.45772151898734176, "grad_norm": 1.9880695027064155, "learning_rate": 3.67479674796748e-05, "loss": 0.6325, "step": 113 }, { "epoch": 0.46177215189873416, "grad_norm": 1.099881613541119, "learning_rate": 3.7073170731707325e-05, "loss": 0.627, "step": 114 }, { "epoch": 0.46582278481012657, "grad_norm": 2.7128036550600165, "learning_rate": 3.739837398373984e-05, "loss": 0.6424, "step": 115 }, { "epoch": 0.46987341772151897, "grad_norm": 2.1578696236807793, "learning_rate": 3.772357723577236e-05, "loss": 0.6384, "step": 116 }, { "epoch": 0.4739240506329114, "grad_norm": 1.7522593046814712, "learning_rate": 3.804878048780488e-05, "loss": 0.6394, "step": 117 }, { "epoch": 0.4779746835443038, "grad_norm": 1.5111368727828536, "learning_rate": 3.83739837398374e-05, "loss": 0.6248, "step": 118 }, { "epoch": 0.4820253164556962, "grad_norm": 1.7809993403452324, "learning_rate": 3.869918699186992e-05, "loss": 0.6375, "step": 119 }, { "epoch": 0.4860759493670886, "grad_norm": 1.249435158041367, "learning_rate": 3.9024390243902444e-05, "loss": 0.641, "step": 120 }, { "epoch": 0.490126582278481, "grad_norm": 1.4550756106504188, "learning_rate": 3.9349593495934966e-05, "loss": 0.6455, "step": 121 }, { "epoch": 0.4941772151898734, "grad_norm": 1.5319269721500643, "learning_rate": 3.967479674796748e-05, "loss": 0.6405, "step": 122 }, { "epoch": 0.4982278481012658, "grad_norm": 1.1470942655017025, "learning_rate": 4e-05, "loss": 0.6345, "step": 123 }, { "epoch": 0.5022784810126583, "grad_norm": 1.6367530558072505, "learning_rate": 3.999991946137476e-05, "loss": 0.6233, "step": 124 }, { "epoch": 0.5063291139240507, "grad_norm": 1.1634473590869547, "learning_rate": 3.999967784614766e-05, "loss": 0.6445, "step": 125 }, { "epoch": 0.5103797468354431, "grad_norm": 1.4156414178315002, "learning_rate": 3.9999275156264656e-05, "loss": 0.6293, "step": 126 }, { "epoch": 0.5144303797468355, "grad_norm": 1.2753256327353748, "learning_rate": 3.999871139496895e-05, "loss": 0.6346, "step": 127 }, { "epoch": 0.5184810126582279, "grad_norm": 1.2063943886755502, "learning_rate": 3.9997986566800995e-05, "loss": 0.6312, "step": 128 }, { "epoch": 0.5225316455696203, "grad_norm": 1.4821240093496588, "learning_rate": 3.999710067759846e-05, "loss": 0.6399, "step": 129 }, { "epoch": 0.5265822784810127, "grad_norm": 1.105987652158323, "learning_rate": 3.999605373449617e-05, "loss": 0.6409, "step": 130 }, { "epoch": 0.5306329113924051, "grad_norm": 1.5266765845642067, "learning_rate": 3.9994845745926075e-05, "loss": 0.6317, "step": 131 }, { "epoch": 0.5346835443037975, "grad_norm": 1.0040263901026576, "learning_rate": 3.999347672161713e-05, "loss": 0.6397, "step": 132 }, { "epoch": 0.5387341772151899, "grad_norm": 1.6505044503423818, "learning_rate": 3.999194667259528e-05, "loss": 0.6218, "step": 133 }, { "epoch": 0.5427848101265823, "grad_norm": 1.3230499957500885, "learning_rate": 3.999025561118334e-05, "loss": 0.6384, "step": 134 }, { "epoch": 0.5468354430379747, "grad_norm": 1.5709750077353462, "learning_rate": 3.998840355100086e-05, "loss": 0.6327, "step": 135 }, { "epoch": 0.5508860759493671, "grad_norm": 1.3938502125886867, "learning_rate": 3.998639050696409e-05, "loss": 0.6453, "step": 136 }, { "epoch": 0.5549367088607595, "grad_norm": 1.198258041291447, "learning_rate": 3.998421649528582e-05, "loss": 0.6372, "step": 137 }, { "epoch": 0.5589873417721519, "grad_norm": 1.0797154967318512, "learning_rate": 3.9981881533475234e-05, "loss": 0.6217, "step": 138 }, { "epoch": 0.5630379746835443, "grad_norm": 1.0993741502093517, "learning_rate": 3.997938564033779e-05, "loss": 0.6258, "step": 139 }, { "epoch": 0.5670886075949367, "grad_norm": 0.8495462621025772, "learning_rate": 3.9976728835975064e-05, "loss": 0.6115, "step": 140 }, { "epoch": 0.5711392405063291, "grad_norm": 1.2666208645732493, "learning_rate": 3.9973911141784605e-05, "loss": 0.6193, "step": 141 }, { "epoch": 0.5751898734177215, "grad_norm": 0.8265864674934269, "learning_rate": 3.997093258045973e-05, "loss": 0.6236, "step": 142 }, { "epoch": 0.579240506329114, "grad_norm": 1.0700132302784573, "learning_rate": 3.996779317598936e-05, "loss": 0.626, "step": 143 }, { "epoch": 0.5832911392405064, "grad_norm": 0.7483094696946129, "learning_rate": 3.996449295365782e-05, "loss": 0.625, "step": 144 }, { "epoch": 0.5873417721518988, "grad_norm": 1.0571743339059352, "learning_rate": 3.996103194004467e-05, "loss": 0.6326, "step": 145 }, { "epoch": 0.5913924050632912, "grad_norm": 0.7812728757384583, "learning_rate": 3.995741016302441e-05, "loss": 0.636, "step": 146 }, { "epoch": 0.5954430379746836, "grad_norm": 0.939673038560442, "learning_rate": 3.9953627651766364e-05, "loss": 0.6151, "step": 147 }, { "epoch": 0.599493670886076, "grad_norm": 0.9894969249661532, "learning_rate": 3.9949684436734325e-05, "loss": 0.6203, "step": 148 }, { "epoch": 0.6035443037974684, "grad_norm": 1.001886362847681, "learning_rate": 3.994558054968643e-05, "loss": 0.6331, "step": 149 }, { "epoch": 0.6075949367088608, "grad_norm": 0.9642683145397989, "learning_rate": 3.994131602367481e-05, "loss": 0.6361, "step": 150 }, { "epoch": 0.6116455696202532, "grad_norm": 0.9770510420594829, "learning_rate": 3.9936890893045376e-05, "loss": 0.6111, "step": 151 }, { "epoch": 0.6156962025316456, "grad_norm": 0.714718229371181, "learning_rate": 3.993230519343752e-05, "loss": 0.6241, "step": 152 }, { "epoch": 0.619746835443038, "grad_norm": 0.8480657975232424, "learning_rate": 3.992755896178383e-05, "loss": 0.6291, "step": 153 }, { "epoch": 0.6237974683544304, "grad_norm": 0.866293409749637, "learning_rate": 3.992265223630981e-05, "loss": 0.6378, "step": 154 }, { "epoch": 0.6278481012658228, "grad_norm": 1.0047063840884083, "learning_rate": 3.991758505653355e-05, "loss": 0.6269, "step": 155 }, { "epoch": 0.6318987341772152, "grad_norm": 1.0229108560166338, "learning_rate": 3.991235746326543e-05, "loss": 0.6287, "step": 156 }, { "epoch": 0.6359493670886076, "grad_norm": 0.7248781456942647, "learning_rate": 3.9906969498607745e-05, "loss": 0.6112, "step": 157 }, { "epoch": 0.64, "grad_norm": 0.7866368951744799, "learning_rate": 3.990142120595444e-05, "loss": 0.6331, "step": 158 }, { "epoch": 0.6440506329113924, "grad_norm": 1.0623261291404862, "learning_rate": 3.98957126299907e-05, "loss": 0.6129, "step": 159 }, { "epoch": 0.6481012658227848, "grad_norm": 0.7075774909491774, "learning_rate": 3.9889843816692596e-05, "loss": 0.6283, "step": 160 }, { "epoch": 0.6521518987341772, "grad_norm": 1.04006620864673, "learning_rate": 3.9883814813326766e-05, "loss": 0.6152, "step": 161 }, { "epoch": 0.6562025316455696, "grad_norm": 0.8347378679317734, "learning_rate": 3.9877625668449956e-05, "loss": 0.6358, "step": 162 }, { "epoch": 0.660253164556962, "grad_norm": 0.7409276424518496, "learning_rate": 3.98712764319087e-05, "loss": 0.6362, "step": 163 }, { "epoch": 0.6643037974683544, "grad_norm": 0.8070712432365799, "learning_rate": 3.9864767154838864e-05, "loss": 0.6267, "step": 164 }, { "epoch": 0.6683544303797468, "grad_norm": 0.7536238756064942, "learning_rate": 3.9858097889665277e-05, "loss": 0.6266, "step": 165 }, { "epoch": 0.6724050632911392, "grad_norm": 0.9523482986953387, "learning_rate": 3.985126869010129e-05, "loss": 0.6357, "step": 166 }, { "epoch": 0.6764556962025317, "grad_norm": 0.6055952704593108, "learning_rate": 3.984427961114833e-05, "loss": 0.6105, "step": 167 }, { "epoch": 0.6805063291139241, "grad_norm": 0.802616244052181, "learning_rate": 3.9837130709095475e-05, "loss": 0.6171, "step": 168 }, { "epoch": 0.6845569620253165, "grad_norm": 0.7039691772045646, "learning_rate": 3.982982204151901e-05, "loss": 0.6301, "step": 169 }, { "epoch": 0.6886075949367089, "grad_norm": 0.6443115520005089, "learning_rate": 3.982235366728193e-05, "loss": 0.6247, "step": 170 }, { "epoch": 0.6926582278481013, "grad_norm": 0.5768058395941336, "learning_rate": 3.9814725646533505e-05, "loss": 0.6234, "step": 171 }, { "epoch": 0.6967088607594937, "grad_norm": 0.7959047029357879, "learning_rate": 3.9806938040708746e-05, "loss": 0.6084, "step": 172 }, { "epoch": 0.7007594936708861, "grad_norm": 0.9973523781312673, "learning_rate": 3.9798990912527976e-05, "loss": 0.6015, "step": 173 }, { "epoch": 0.7048101265822785, "grad_norm": 0.606389382605842, "learning_rate": 3.979088432599627e-05, "loss": 0.6241, "step": 174 }, { "epoch": 0.7088607594936709, "grad_norm": 1.0239322202657364, "learning_rate": 3.9782618346402964e-05, "loss": 0.6149, "step": 175 }, { "epoch": 0.7129113924050633, "grad_norm": 0.8985260431868708, "learning_rate": 3.977419304032111e-05, "loss": 0.621, "step": 176 }, { "epoch": 0.7169620253164557, "grad_norm": 0.8046389533424279, "learning_rate": 3.976560847560697e-05, "loss": 0.624, "step": 177 }, { "epoch": 0.7210126582278481, "grad_norm": 1.3108615100000611, "learning_rate": 3.9756864721399456e-05, "loss": 0.6174, "step": 178 }, { "epoch": 0.7250632911392405, "grad_norm": 0.6266703795134254, "learning_rate": 3.974796184811956e-05, "loss": 0.6151, "step": 179 }, { "epoch": 0.7291139240506329, "grad_norm": 1.1968703352815118, "learning_rate": 3.973889992746979e-05, "loss": 0.6197, "step": 180 }, { "epoch": 0.7331645569620253, "grad_norm": 0.6681459489699814, "learning_rate": 3.972967903243361e-05, "loss": 0.615, "step": 181 }, { "epoch": 0.7372151898734177, "grad_norm": 0.7978974933861913, "learning_rate": 3.972029923727486e-05, "loss": 0.6196, "step": 182 }, { "epoch": 0.7412658227848101, "grad_norm": 0.7442788954760837, "learning_rate": 3.971076061753709e-05, "loss": 0.6171, "step": 183 }, { "epoch": 0.7453164556962025, "grad_norm": 0.7997708337454055, "learning_rate": 3.9701063250043066e-05, "loss": 0.6327, "step": 184 }, { "epoch": 0.7493670886075949, "grad_norm": 0.6267689290572701, "learning_rate": 3.969120721289402e-05, "loss": 0.6232, "step": 185 }, { "epoch": 0.7534177215189873, "grad_norm": 0.911267265579453, "learning_rate": 3.9681192585469146e-05, "loss": 0.599, "step": 186 }, { "epoch": 0.7574683544303797, "grad_norm": 0.9816241858836346, "learning_rate": 3.9671019448424865e-05, "loss": 0.6213, "step": 187 }, { "epoch": 0.7615189873417721, "grad_norm": 0.5947329255484376, "learning_rate": 3.966068788369422e-05, "loss": 0.6064, "step": 188 }, { "epoch": 0.7655696202531646, "grad_norm": 0.7871417651272268, "learning_rate": 3.965019797448622e-05, "loss": 0.5956, "step": 189 }, { "epoch": 0.769620253164557, "grad_norm": 0.6193028918365722, "learning_rate": 3.963954980528515e-05, "loss": 0.6158, "step": 190 }, { "epoch": 0.7736708860759494, "grad_norm": 0.7356758881431426, "learning_rate": 3.9628743461849905e-05, "loss": 0.6224, "step": 191 }, { "epoch": 0.7777215189873418, "grad_norm": 0.7104339821332911, "learning_rate": 3.961777903121329e-05, "loss": 0.6179, "step": 192 }, { "epoch": 0.7817721518987342, "grad_norm": 0.5088471892939366, "learning_rate": 3.960665660168131e-05, "loss": 0.6077, "step": 193 }, { "epoch": 0.7858227848101266, "grad_norm": 0.5909154700344365, "learning_rate": 3.9595376262832485e-05, "loss": 0.6071, "step": 194 }, { "epoch": 0.789873417721519, "grad_norm": 0.5694736176100695, "learning_rate": 3.9583938105517127e-05, "loss": 0.6034, "step": 195 }, { "epoch": 0.7939240506329114, "grad_norm": 0.6585729806740599, "learning_rate": 3.957234222185657e-05, "loss": 0.6094, "step": 196 }, { "epoch": 0.7979746835443038, "grad_norm": 0.656809429168001, "learning_rate": 3.9560588705242474e-05, "loss": 0.6172, "step": 197 }, { "epoch": 0.8020253164556962, "grad_norm": 0.5806265839185347, "learning_rate": 3.954867765033605e-05, "loss": 0.613, "step": 198 }, { "epoch": 0.8060759493670886, "grad_norm": 0.6302907895505472, "learning_rate": 3.953660915306728e-05, "loss": 0.6106, "step": 199 }, { "epoch": 0.810126582278481, "grad_norm": 0.6806718914249638, "learning_rate": 3.952438331063419e-05, "loss": 0.6059, "step": 200 }, { "epoch": 0.8141772151898734, "grad_norm": 0.5760758484347329, "learning_rate": 3.951200022150205e-05, "loss": 0.617, "step": 201 }, { "epoch": 0.8182278481012658, "grad_norm": 0.6404621386199326, "learning_rate": 3.949945998540253e-05, "loss": 0.611, "step": 202 }, { "epoch": 0.8222784810126582, "grad_norm": 0.7536634204020715, "learning_rate": 3.9486762703332993e-05, "loss": 0.6107, "step": 203 }, { "epoch": 0.8263291139240506, "grad_norm": 0.7093486788897463, "learning_rate": 3.947390847755559e-05, "loss": 0.6158, "step": 204 }, { "epoch": 0.830379746835443, "grad_norm": 0.5984326991253901, "learning_rate": 3.946089741159648e-05, "loss": 0.6112, "step": 205 }, { "epoch": 0.8344303797468354, "grad_norm": 0.6339939518828068, "learning_rate": 3.944772961024501e-05, "loss": 0.594, "step": 206 }, { "epoch": 0.8384810126582278, "grad_norm": 0.6120473840299494, "learning_rate": 3.943440517955285e-05, "loss": 0.6042, "step": 207 }, { "epoch": 0.8425316455696202, "grad_norm": 0.655308007083571, "learning_rate": 3.9420924226833126e-05, "loss": 0.6143, "step": 208 }, { "epoch": 0.8465822784810126, "grad_norm": 0.550049123690399, "learning_rate": 3.9407286860659566e-05, "loss": 0.6023, "step": 209 }, { "epoch": 0.850632911392405, "grad_norm": 0.5696659812506536, "learning_rate": 3.9393493190865657e-05, "loss": 0.6173, "step": 210 }, { "epoch": 0.8546835443037974, "grad_norm": 0.5921134721997223, "learning_rate": 3.937954332854371e-05, "loss": 0.6129, "step": 211 }, { "epoch": 0.8587341772151899, "grad_norm": 0.5802806287932405, "learning_rate": 3.9365437386044016e-05, "loss": 0.6105, "step": 212 }, { "epoch": 0.8627848101265823, "grad_norm": 0.7328355036344966, "learning_rate": 3.935117547697387e-05, "loss": 0.6081, "step": 213 }, { "epoch": 0.8668354430379747, "grad_norm": 0.7917619142325161, "learning_rate": 3.933675771619675e-05, "loss": 0.6208, "step": 214 }, { "epoch": 0.8708860759493671, "grad_norm": 0.7121788829311407, "learning_rate": 3.932218421983131e-05, "loss": 0.6094, "step": 215 }, { "epoch": 0.8749367088607595, "grad_norm": 0.688271222419086, "learning_rate": 3.9307455105250484e-05, "loss": 0.5995, "step": 216 }, { "epoch": 0.8789873417721519, "grad_norm": 0.667488259806073, "learning_rate": 3.929257049108054e-05, "loss": 0.6097, "step": 217 }, { "epoch": 0.8830379746835443, "grad_norm": 0.6743497586555637, "learning_rate": 3.927753049720011e-05, "loss": 0.5945, "step": 218 }, { "epoch": 0.8870886075949367, "grad_norm": 0.6051666990873316, "learning_rate": 3.9262335244739234e-05, "loss": 0.6197, "step": 219 }, { "epoch": 0.8911392405063291, "grad_norm": 0.45765325900690407, "learning_rate": 3.92469848560784e-05, "loss": 0.5904, "step": 220 }, { "epoch": 0.8951898734177215, "grad_norm": 0.6424228162140317, "learning_rate": 3.923147945484751e-05, "loss": 0.5958, "step": 221 }, { "epoch": 0.8992405063291139, "grad_norm": 0.5942668534008888, "learning_rate": 3.9215819165924956e-05, "loss": 0.6145, "step": 222 }, { "epoch": 0.9032911392405063, "grad_norm": 0.728038901623283, "learning_rate": 3.920000411543654e-05, "loss": 0.6059, "step": 223 }, { "epoch": 0.9073417721518987, "grad_norm": 0.6211491761993221, "learning_rate": 3.9184034430754495e-05, "loss": 0.5993, "step": 224 }, { "epoch": 0.9113924050632911, "grad_norm": 0.591282433317295, "learning_rate": 3.916791024049648e-05, "loss": 0.602, "step": 225 }, { "epoch": 0.9154430379746835, "grad_norm": 0.6102458112891519, "learning_rate": 3.91516316745245e-05, "loss": 0.5933, "step": 226 }, { "epoch": 0.9194936708860759, "grad_norm": 0.639706727217608, "learning_rate": 3.913519886394389e-05, "loss": 0.6082, "step": 227 }, { "epoch": 0.9235443037974683, "grad_norm": 0.5997536311963827, "learning_rate": 3.911861194110225e-05, "loss": 0.5981, "step": 228 }, { "epoch": 0.9275949367088607, "grad_norm": 0.49752264065888957, "learning_rate": 3.910187103958837e-05, "loss": 0.599, "step": 229 }, { "epoch": 0.9316455696202531, "grad_norm": 0.6258323917603847, "learning_rate": 3.908497629423117e-05, "loss": 0.6084, "step": 230 }, { "epoch": 0.9356962025316455, "grad_norm": 0.6662575937935632, "learning_rate": 3.9067927841098614e-05, "loss": 0.6102, "step": 231 }, { "epoch": 0.9397468354430379, "grad_norm": 0.5560174796493339, "learning_rate": 3.9050725817496594e-05, "loss": 0.6096, "step": 232 }, { "epoch": 0.9437974683544303, "grad_norm": 0.5146867436335085, "learning_rate": 3.9033370361967844e-05, "loss": 0.6027, "step": 233 }, { "epoch": 0.9478481012658228, "grad_norm": 0.746617839727397, "learning_rate": 3.901586161429081e-05, "loss": 0.6174, "step": 234 }, { "epoch": 0.9518987341772152, "grad_norm": 0.8801260438707954, "learning_rate": 3.8998199715478545e-05, "loss": 0.588, "step": 235 }, { "epoch": 0.9559493670886076, "grad_norm": 0.5944682719459576, "learning_rate": 3.8980384807777564e-05, "loss": 0.6065, "step": 236 }, { "epoch": 0.96, "grad_norm": 1.12472783801954, "learning_rate": 3.896241703466667e-05, "loss": 0.6148, "step": 237 }, { "epoch": 0.9640506329113924, "grad_norm": 0.8394606190191818, "learning_rate": 3.894429654085585e-05, "loss": 0.6171, "step": 238 }, { "epoch": 0.9681012658227848, "grad_norm": 0.5822010494784494, "learning_rate": 3.892602347228505e-05, "loss": 0.5944, "step": 239 }, { "epoch": 0.9721518987341772, "grad_norm": 0.8542905673340957, "learning_rate": 3.890759797612307e-05, "loss": 0.6073, "step": 240 }, { "epoch": 0.9762025316455696, "grad_norm": 0.8520489585181831, "learning_rate": 3.888902020076632e-05, "loss": 0.6077, "step": 241 }, { "epoch": 0.980253164556962, "grad_norm": 0.5848550441248854, "learning_rate": 3.887029029583764e-05, "loss": 0.6006, "step": 242 }, { "epoch": 0.9843037974683544, "grad_norm": 0.7526640033188469, "learning_rate": 3.8851408412185125e-05, "loss": 0.5986, "step": 243 }, { "epoch": 0.9883544303797468, "grad_norm": 0.8748709459892107, "learning_rate": 3.8832374701880855e-05, "loss": 0.5999, "step": 244 }, { "epoch": 0.9924050632911392, "grad_norm": 0.8226376044782282, "learning_rate": 3.881318931821972e-05, "loss": 0.6039, "step": 245 }, { "epoch": 0.9964556962025316, "grad_norm": 0.5630090630092439, "learning_rate": 3.879385241571817e-05, "loss": 0.6028, "step": 246 }, { "epoch": 1.000506329113924, "grad_norm": 0.7507201212353878, "learning_rate": 3.8774364150112955e-05, "loss": 0.6719, "step": 247 }, { "epoch": 1.0045569620253165, "grad_norm": 0.8076952550791776, "learning_rate": 3.8754724678359884e-05, "loss": 0.543, "step": 248 }, { "epoch": 1.0086075949367088, "grad_norm": 0.6607387744183136, "learning_rate": 3.873493415863256e-05, "loss": 0.5819, "step": 249 }, { "epoch": 1.0126582278481013, "grad_norm": 0.7416537868041101, "learning_rate": 3.871499275032111e-05, "loss": 0.5481, "step": 250 }, { "epoch": 1.0167088607594936, "grad_norm": 0.7015540709937512, "learning_rate": 3.869490061403091e-05, "loss": 0.5537, "step": 251 }, { "epoch": 1.0207594936708861, "grad_norm": 0.7519729582328205, "learning_rate": 3.867465791158124e-05, "loss": 0.5379, "step": 252 }, { "epoch": 1.0248101265822784, "grad_norm": 0.7998797935772037, "learning_rate": 3.865426480600407e-05, "loss": 0.5646, "step": 253 }, { "epoch": 1.028860759493671, "grad_norm": 0.6579076874771392, "learning_rate": 3.863372146154264e-05, "loss": 0.5462, "step": 254 }, { "epoch": 1.0329113924050632, "grad_norm": 0.5422077162891843, "learning_rate": 3.861302804365024e-05, "loss": 0.5699, "step": 255 }, { "epoch": 1.0369620253164558, "grad_norm": 0.7388471665931728, "learning_rate": 3.85921847189888e-05, "loss": 0.5341, "step": 256 }, { "epoch": 1.041012658227848, "grad_norm": 0.5877147726699852, "learning_rate": 3.85711916554276e-05, "loss": 0.5614, "step": 257 }, { "epoch": 1.0450632911392406, "grad_norm": 0.6185993731443774, "learning_rate": 3.85500490220419e-05, "loss": 0.5358, "step": 258 }, { "epoch": 1.0491139240506329, "grad_norm": 0.6992525471995376, "learning_rate": 3.852875698911154e-05, "loss": 0.557, "step": 259 }, { "epoch": 1.0531645569620254, "grad_norm": 0.7353239683059807, "learning_rate": 3.850731572811963e-05, "loss": 0.5514, "step": 260 }, { "epoch": 1.0572151898734177, "grad_norm": 0.6143855347125572, "learning_rate": 3.848572541175116e-05, "loss": 0.5299, "step": 261 }, { "epoch": 1.0612658227848102, "grad_norm": 0.6749194786601802, "learning_rate": 3.846398621389154e-05, "loss": 0.5625, "step": 262 }, { "epoch": 1.0653164556962025, "grad_norm": 0.5407449487318072, "learning_rate": 3.84420983096253e-05, "loss": 0.5505, "step": 263 }, { "epoch": 1.069367088607595, "grad_norm": 0.5218461233216785, "learning_rate": 3.8420061875234606e-05, "loss": 0.5632, "step": 264 }, { "epoch": 1.0734177215189873, "grad_norm": 0.5540673442589057, "learning_rate": 3.839787708819787e-05, "loss": 0.5423, "step": 265 }, { "epoch": 1.0774683544303798, "grad_norm": 0.4386538181398556, "learning_rate": 3.8375544127188325e-05, "loss": 0.5498, "step": 266 }, { "epoch": 1.081518987341772, "grad_norm": 0.49271040755197154, "learning_rate": 3.8353063172072564e-05, "loss": 0.554, "step": 267 }, { "epoch": 1.0855696202531646, "grad_norm": 0.48242381213842417, "learning_rate": 3.8330434403909105e-05, "loss": 0.5732, "step": 268 }, { "epoch": 1.089620253164557, "grad_norm": 0.5290958751875288, "learning_rate": 3.8307658004946934e-05, "loss": 0.5535, "step": 269 }, { "epoch": 1.0936708860759494, "grad_norm": 0.47687358443819056, "learning_rate": 3.8284734158624046e-05, "loss": 0.538, "step": 270 }, { "epoch": 1.0977215189873417, "grad_norm": 0.5721486671151396, "learning_rate": 3.826166304956594e-05, "loss": 0.5499, "step": 271 }, { "epoch": 1.1017721518987342, "grad_norm": 0.5068034980752262, "learning_rate": 3.8238444863584164e-05, "loss": 0.5543, "step": 272 }, { "epoch": 1.1058227848101265, "grad_norm": 0.6118741356510613, "learning_rate": 3.821507978767479e-05, "loss": 0.5484, "step": 273 }, { "epoch": 1.109873417721519, "grad_norm": 0.6237397016069653, "learning_rate": 3.819156801001693e-05, "loss": 0.5365, "step": 274 }, { "epoch": 1.1139240506329113, "grad_norm": 0.5938944993967848, "learning_rate": 3.816790971997121e-05, "loss": 0.56, "step": 275 }, { "epoch": 1.1179746835443038, "grad_norm": 0.5441646471762, "learning_rate": 3.8144105108078246e-05, "loss": 0.5599, "step": 276 }, { "epoch": 1.1220253164556961, "grad_norm": 0.5153543279477772, "learning_rate": 3.81201543660571e-05, "loss": 0.5439, "step": 277 }, { "epoch": 1.1260759493670887, "grad_norm": 0.48096122915005923, "learning_rate": 3.809605768680377e-05, "loss": 0.5543, "step": 278 }, { "epoch": 1.130126582278481, "grad_norm": 0.5378062857838541, "learning_rate": 3.807181526438958e-05, "loss": 0.5642, "step": 279 }, { "epoch": 1.1341772151898735, "grad_norm": 0.4634022252089541, "learning_rate": 3.8047427294059697e-05, "loss": 0.545, "step": 280 }, { "epoch": 1.1382278481012658, "grad_norm": 0.5045638013164182, "learning_rate": 3.802289397223145e-05, "loss": 0.5606, "step": 281 }, { "epoch": 1.1422784810126583, "grad_norm": 0.43419656722493705, "learning_rate": 3.7998215496492854e-05, "loss": 0.5542, "step": 282 }, { "epoch": 1.1463291139240506, "grad_norm": 0.45762230419615296, "learning_rate": 3.797339206560096e-05, "loss": 0.5521, "step": 283 }, { "epoch": 1.150379746835443, "grad_norm": 0.4546188882345411, "learning_rate": 3.794842387948027e-05, "loss": 0.5508, "step": 284 }, { "epoch": 1.1544303797468354, "grad_norm": 0.5769354330618904, "learning_rate": 3.7923311139221114e-05, "loss": 0.5522, "step": 285 }, { "epoch": 1.158481012658228, "grad_norm": 0.46923054139455933, "learning_rate": 3.7898054047078054e-05, "loss": 0.5342, "step": 286 }, { "epoch": 1.1625316455696202, "grad_norm": 0.5811728098884562, "learning_rate": 3.787265280646825e-05, "loss": 0.5768, "step": 287 }, { "epoch": 1.1665822784810127, "grad_norm": 0.6427012142691877, "learning_rate": 3.7847107621969786e-05, "loss": 0.5342, "step": 288 }, { "epoch": 1.170632911392405, "grad_norm": 0.5360130315567895, "learning_rate": 3.7821418699320064e-05, "loss": 0.5809, "step": 289 }, { "epoch": 1.1746835443037975, "grad_norm": 0.5822903002705316, "learning_rate": 3.7795586245414145e-05, "loss": 0.5301, "step": 290 }, { "epoch": 1.1787341772151898, "grad_norm": 0.5470314504779057, "learning_rate": 3.776961046830306e-05, "loss": 0.5368, "step": 291 }, { "epoch": 1.1827848101265823, "grad_norm": 0.5584789553075055, "learning_rate": 3.774349157719215e-05, "loss": 0.561, "step": 292 }, { "epoch": 1.1868354430379746, "grad_norm": 0.5642772271703588, "learning_rate": 3.7717229782439365e-05, "loss": 0.5436, "step": 293 }, { "epoch": 1.1908860759493671, "grad_norm": 0.5885254788668897, "learning_rate": 3.769082529555359e-05, "loss": 0.5665, "step": 294 }, { "epoch": 1.1949367088607594, "grad_norm": 0.6350035320999246, "learning_rate": 3.766427832919294e-05, "loss": 0.5196, "step": 295 }, { "epoch": 1.198987341772152, "grad_norm": 0.595273039609602, "learning_rate": 3.7637589097163024e-05, "loss": 0.5687, "step": 296 }, { "epoch": 1.2030379746835442, "grad_norm": 0.6051297671216856, "learning_rate": 3.761075781441526e-05, "loss": 0.5464, "step": 297 }, { "epoch": 1.2070886075949367, "grad_norm": 0.5226841615960941, "learning_rate": 3.75837846970451e-05, "loss": 0.5403, "step": 298 }, { "epoch": 1.211139240506329, "grad_norm": 0.5267293463238256, "learning_rate": 3.755666996229032e-05, "loss": 0.5515, "step": 299 }, { "epoch": 1.2151898734177216, "grad_norm": 0.645441321087611, "learning_rate": 3.752941382852927e-05, "loss": 0.5719, "step": 300 }, { "epoch": 1.2192405063291138, "grad_norm": 0.4442199189999075, "learning_rate": 3.7502016515279115e-05, "loss": 0.531, "step": 301 }, { "epoch": 1.2232911392405064, "grad_norm": 0.5277495250330881, "learning_rate": 3.7474478243194043e-05, "loss": 0.5492, "step": 302 }, { "epoch": 1.2273417721518987, "grad_norm": 0.5529168970606974, "learning_rate": 3.744679923406351e-05, "loss": 0.5645, "step": 303 }, { "epoch": 1.2313924050632912, "grad_norm": 0.5244981220717256, "learning_rate": 3.741897971081043e-05, "loss": 0.5739, "step": 304 }, { "epoch": 1.2354430379746835, "grad_norm": 0.418898980227361, "learning_rate": 3.739101989748946e-05, "loss": 0.5334, "step": 305 }, { "epoch": 1.239493670886076, "grad_norm": 0.5403963751571289, "learning_rate": 3.7362920019285066e-05, "loss": 0.5654, "step": 306 }, { "epoch": 1.2435443037974683, "grad_norm": 0.5342824611710978, "learning_rate": 3.73346803025098e-05, "loss": 0.5569, "step": 307 }, { "epoch": 1.2475949367088608, "grad_norm": 0.43849146586202414, "learning_rate": 3.730630097460247e-05, "loss": 0.5483, "step": 308 }, { "epoch": 1.251645569620253, "grad_norm": 0.466324232143768, "learning_rate": 3.727778226412628e-05, "loss": 0.5432, "step": 309 }, { "epoch": 1.2556962025316456, "grad_norm": 0.46632589282876263, "learning_rate": 3.7249124400767006e-05, "loss": 0.5581, "step": 310 }, { "epoch": 1.259746835443038, "grad_norm": 0.46940600017738043, "learning_rate": 3.722032761533114e-05, "loss": 0.547, "step": 311 }, { "epoch": 1.2637974683544304, "grad_norm": 0.4324786371438734, "learning_rate": 3.719139213974403e-05, "loss": 0.5252, "step": 312 }, { "epoch": 1.2678481012658227, "grad_norm": 0.5038443924984649, "learning_rate": 3.7162318207048006e-05, "loss": 0.571, "step": 313 }, { "epoch": 1.2718987341772152, "grad_norm": 0.567076495461743, "learning_rate": 3.713310605140055e-05, "loss": 0.5493, "step": 314 }, { "epoch": 1.2759493670886077, "grad_norm": 0.47707983455484726, "learning_rate": 3.710375590807233e-05, "loss": 0.5318, "step": 315 }, { "epoch": 1.28, "grad_norm": 0.4209198839753279, "learning_rate": 3.7074268013445365e-05, "loss": 0.5382, "step": 316 }, { "epoch": 1.2840506329113923, "grad_norm": 0.48601910277926214, "learning_rate": 3.7044642605011114e-05, "loss": 0.5602, "step": 317 }, { "epoch": 1.2881012658227848, "grad_norm": 0.4827520861412068, "learning_rate": 3.701487992136854e-05, "loss": 0.5263, "step": 318 }, { "epoch": 1.2921518987341774, "grad_norm": 0.506816960061014, "learning_rate": 3.69849802022222e-05, "loss": 0.57, "step": 319 }, { "epoch": 1.2962025316455696, "grad_norm": 0.46681069240507084, "learning_rate": 3.6954943688380334e-05, "loss": 0.5452, "step": 320 }, { "epoch": 1.300253164556962, "grad_norm": 0.44066682716751926, "learning_rate": 3.692477062175289e-05, "loss": 0.5347, "step": 321 }, { "epoch": 1.3043037974683545, "grad_norm": 0.5112706642171039, "learning_rate": 3.689446124534958e-05, "loss": 0.5433, "step": 322 }, { "epoch": 1.308354430379747, "grad_norm": 0.5108541342362822, "learning_rate": 3.686401580327799e-05, "loss": 0.5357, "step": 323 }, { "epoch": 1.3124050632911393, "grad_norm": 0.4526701543516962, "learning_rate": 3.683343454074149e-05, "loss": 0.5586, "step": 324 }, { "epoch": 1.3164556962025316, "grad_norm": 0.516140515112787, "learning_rate": 3.6802717704037386e-05, "loss": 0.5725, "step": 325 }, { "epoch": 1.320506329113924, "grad_norm": 0.4343600266580703, "learning_rate": 3.6771865540554855e-05, "loss": 0.5151, "step": 326 }, { "epoch": 1.3245569620253166, "grad_norm": 0.44819011371750267, "learning_rate": 3.674087829877297e-05, "loss": 0.5598, "step": 327 }, { "epoch": 1.3286075949367089, "grad_norm": 0.4496737634656963, "learning_rate": 3.6709756228258735e-05, "loss": 0.5238, "step": 328 }, { "epoch": 1.3326582278481012, "grad_norm": 0.45042926420179913, "learning_rate": 3.667849957966501e-05, "loss": 0.5215, "step": 329 }, { "epoch": 1.3367088607594937, "grad_norm": 0.5702182659503398, "learning_rate": 3.6647108604728546e-05, "loss": 0.5631, "step": 330 }, { "epoch": 1.3407594936708862, "grad_norm": 0.5174936579753079, "learning_rate": 3.661558355626795e-05, "loss": 0.5409, "step": 331 }, { "epoch": 1.3448101265822785, "grad_norm": 0.48220389831587496, "learning_rate": 3.658392468818163e-05, "loss": 0.5529, "step": 332 }, { "epoch": 1.3488607594936708, "grad_norm": 0.46675158088653734, "learning_rate": 3.655213225544574e-05, "loss": 0.5211, "step": 333 }, { "epoch": 1.3529113924050633, "grad_norm": 0.4958185777913933, "learning_rate": 3.652020651411218e-05, "loss": 0.5746, "step": 334 }, { "epoch": 1.3569620253164558, "grad_norm": 0.44784523526994646, "learning_rate": 3.6488147721306474e-05, "loss": 0.5416, "step": 335 }, { "epoch": 1.3610126582278481, "grad_norm": 0.5220132699992405, "learning_rate": 3.645595613522574e-05, "loss": 0.563, "step": 336 }, { "epoch": 1.3650632911392404, "grad_norm": 0.5664829058876377, "learning_rate": 3.642363201513657e-05, "loss": 0.5407, "step": 337 }, { "epoch": 1.369113924050633, "grad_norm": 0.5326145723933363, "learning_rate": 3.6391175621373006e-05, "loss": 0.5495, "step": 338 }, { "epoch": 1.3731645569620254, "grad_norm": 0.4601257349502685, "learning_rate": 3.6358587215334355e-05, "loss": 0.5382, "step": 339 }, { "epoch": 1.3772151898734177, "grad_norm": 0.634368547788164, "learning_rate": 3.632586705948318e-05, "loss": 0.5731, "step": 340 }, { "epoch": 1.38126582278481, "grad_norm": 0.45365468677512766, "learning_rate": 3.629301541734311e-05, "loss": 0.5233, "step": 341 }, { "epoch": 1.3853164556962025, "grad_norm": 0.5242430553310445, "learning_rate": 3.626003255349676e-05, "loss": 0.5591, "step": 342 }, { "epoch": 1.389367088607595, "grad_norm": 0.48605234734488567, "learning_rate": 3.622691873358357e-05, "loss": 0.536, "step": 343 }, { "epoch": 1.3934177215189874, "grad_norm": 0.5026509866847212, "learning_rate": 3.61936742242977e-05, "loss": 0.5469, "step": 344 }, { "epoch": 1.3974683544303796, "grad_norm": 0.5445222787011536, "learning_rate": 3.6160299293385864e-05, "loss": 0.5726, "step": 345 }, { "epoch": 1.4015189873417722, "grad_norm": 0.5428310046941834, "learning_rate": 3.612679420964516e-05, "loss": 0.5507, "step": 346 }, { "epoch": 1.4055696202531647, "grad_norm": 0.5976299318296099, "learning_rate": 3.609315924292092e-05, "loss": 0.5653, "step": 347 }, { "epoch": 1.409620253164557, "grad_norm": 0.4626055383515896, "learning_rate": 3.6059394664104554e-05, "loss": 0.5259, "step": 348 }, { "epoch": 1.4136708860759493, "grad_norm": 0.6138136356971757, "learning_rate": 3.602550074513133e-05, "loss": 0.5734, "step": 349 }, { "epoch": 1.4177215189873418, "grad_norm": 0.56420545521681, "learning_rate": 3.599147775897822e-05, "loss": 0.5602, "step": 350 }, { "epoch": 1.4217721518987343, "grad_norm": 0.5682925677491585, "learning_rate": 3.595732597966167e-05, "loss": 0.5627, "step": 351 }, { "epoch": 1.4258227848101266, "grad_norm": 0.6562744482414496, "learning_rate": 3.592304568223542e-05, "loss": 0.5461, "step": 352 }, { "epoch": 1.4298734177215189, "grad_norm": 0.8488304110002913, "learning_rate": 3.588863714278826e-05, "loss": 0.5408, "step": 353 }, { "epoch": 1.4339240506329114, "grad_norm": 0.4692327769293613, "learning_rate": 3.585410063844186e-05, "loss": 0.5315, "step": 354 }, { "epoch": 1.437974683544304, "grad_norm": 0.6876000395672665, "learning_rate": 3.581943644734846e-05, "loss": 0.5684, "step": 355 }, { "epoch": 1.4420253164556962, "grad_norm": 0.6227338015869643, "learning_rate": 3.578464484868869e-05, "loss": 0.5218, "step": 356 }, { "epoch": 1.4460759493670885, "grad_norm": 0.42997231971850586, "learning_rate": 3.5749726122669316e-05, "loss": 0.533, "step": 357 }, { "epoch": 1.450126582278481, "grad_norm": 0.5059111895170803, "learning_rate": 3.5714680550520943e-05, "loss": 0.5501, "step": 358 }, { "epoch": 1.4541772151898735, "grad_norm": 0.4741396778891267, "learning_rate": 3.5679508414495794e-05, "loss": 0.578, "step": 359 }, { "epoch": 1.4582278481012658, "grad_norm": 0.5444276110490243, "learning_rate": 3.564420999786543e-05, "loss": 0.5547, "step": 360 }, { "epoch": 1.4622784810126581, "grad_norm": 0.5041558841653334, "learning_rate": 3.560878558491842e-05, "loss": 0.5227, "step": 361 }, { "epoch": 1.4663291139240506, "grad_norm": 0.5099306838285624, "learning_rate": 3.5573235460958145e-05, "loss": 0.5413, "step": 362 }, { "epoch": 1.4703797468354431, "grad_norm": 0.4896172233641162, "learning_rate": 3.553755991230039e-05, "loss": 0.5467, "step": 363 }, { "epoch": 1.4744303797468354, "grad_norm": 0.5474829743112887, "learning_rate": 3.5501759226271144e-05, "loss": 0.5696, "step": 364 }, { "epoch": 1.4784810126582277, "grad_norm": 0.5531466328985911, "learning_rate": 3.546583369120419e-05, "loss": 0.5446, "step": 365 }, { "epoch": 1.4825316455696202, "grad_norm": 0.44905089019031746, "learning_rate": 3.5429783596438864e-05, "loss": 0.5266, "step": 366 }, { "epoch": 1.4865822784810128, "grad_norm": 0.5452388884528362, "learning_rate": 3.539360923231766e-05, "loss": 0.5477, "step": 367 }, { "epoch": 1.490632911392405, "grad_norm": 0.4632070397704927, "learning_rate": 3.535731089018394e-05, "loss": 0.5404, "step": 368 }, { "epoch": 1.4946835443037974, "grad_norm": 0.4744149118136965, "learning_rate": 3.532088886237956e-05, "loss": 0.55, "step": 369 }, { "epoch": 1.4987341772151899, "grad_norm": 0.43631432646212337, "learning_rate": 3.528434344224253e-05, "loss": 0.5517, "step": 370 }, { "epoch": 1.5027848101265824, "grad_norm": 0.46843866500333403, "learning_rate": 3.524767492410464e-05, "loss": 0.5262, "step": 371 }, { "epoch": 1.5068354430379747, "grad_norm": 0.5839358202156036, "learning_rate": 3.521088360328908e-05, "loss": 0.5718, "step": 372 }, { "epoch": 1.510886075949367, "grad_norm": 0.6394003872480466, "learning_rate": 3.517396977610811e-05, "loss": 0.527, "step": 373 }, { "epoch": 1.5149367088607595, "grad_norm": 0.4279677289890143, "learning_rate": 3.5136933739860595e-05, "loss": 0.5545, "step": 374 }, { "epoch": 1.518987341772152, "grad_norm": 0.5201377183960041, "learning_rate": 3.509977579282971e-05, "loss": 0.5512, "step": 375 }, { "epoch": 1.5230379746835443, "grad_norm": 0.41642185201080384, "learning_rate": 3.5062496234280424e-05, "loss": 0.5195, "step": 376 }, { "epoch": 1.5270886075949366, "grad_norm": 0.4726108600264769, "learning_rate": 3.502509536445719e-05, "loss": 0.5627, "step": 377 }, { "epoch": 1.531139240506329, "grad_norm": 0.46593370738469814, "learning_rate": 3.498757348458147e-05, "loss": 0.5232, "step": 378 }, { "epoch": 1.5351898734177216, "grad_norm": 0.48580388963759863, "learning_rate": 3.4949930896849324e-05, "loss": 0.5484, "step": 379 }, { "epoch": 1.539240506329114, "grad_norm": 0.44455158978705855, "learning_rate": 3.491216790442899e-05, "loss": 0.5402, "step": 380 }, { "epoch": 1.5432911392405062, "grad_norm": 0.544520663382051, "learning_rate": 3.487428481145839e-05, "loss": 0.5546, "step": 381 }, { "epoch": 1.5473417721518987, "grad_norm": 0.48549629911208686, "learning_rate": 3.483628192304278e-05, "loss": 0.5197, "step": 382 }, { "epoch": 1.5513924050632912, "grad_norm": 0.44881385665741375, "learning_rate": 3.479815954525219e-05, "loss": 0.5847, "step": 383 }, { "epoch": 1.5554430379746835, "grad_norm": 0.5344725667197828, "learning_rate": 3.475991798511899e-05, "loss": 0.5594, "step": 384 }, { "epoch": 1.5594936708860758, "grad_norm": 0.46260134782966766, "learning_rate": 3.4721557550635464e-05, "loss": 0.5445, "step": 385 }, { "epoch": 1.5635443037974683, "grad_norm": 0.5494658120500395, "learning_rate": 3.468307855075128e-05, "loss": 0.5513, "step": 386 }, { "epoch": 1.5675949367088609, "grad_norm": 0.5761663150481504, "learning_rate": 3.4644481295371005e-05, "loss": 0.5233, "step": 387 }, { "epoch": 1.5716455696202531, "grad_norm": 0.47722315223613915, "learning_rate": 3.460576609535163e-05, "loss": 0.5472, "step": 388 }, { "epoch": 1.5756962025316454, "grad_norm": 0.49469378183419743, "learning_rate": 3.456693326250006e-05, "loss": 0.5627, "step": 389 }, { "epoch": 1.579746835443038, "grad_norm": 0.4804363267109439, "learning_rate": 3.452798310957058e-05, "loss": 0.5727, "step": 390 }, { "epoch": 1.5837974683544305, "grad_norm": 0.4979140548696786, "learning_rate": 3.4488915950262386e-05, "loss": 0.5416, "step": 391 }, { "epoch": 1.5878481012658228, "grad_norm": 0.4336731311486208, "learning_rate": 3.4449732099216985e-05, "loss": 0.528, "step": 392 }, { "epoch": 1.591898734177215, "grad_norm": 0.407323809203771, "learning_rate": 3.441043187201574e-05, "loss": 0.5487, "step": 393 }, { "epoch": 1.5959493670886076, "grad_norm": 0.4611254301889277, "learning_rate": 3.437101558517728e-05, "loss": 0.5564, "step": 394 }, { "epoch": 1.6, "grad_norm": 0.4195367272671082, "learning_rate": 3.433148355615496e-05, "loss": 0.5575, "step": 395 }, { "epoch": 1.6040506329113924, "grad_norm": 0.5132598054034244, "learning_rate": 3.4291836103334294e-05, "loss": 0.5558, "step": 396 }, { "epoch": 1.6081012658227847, "grad_norm": 0.46124747934801624, "learning_rate": 3.425207354603043e-05, "loss": 0.5273, "step": 397 }, { "epoch": 1.6121518987341772, "grad_norm": 0.5817146715271955, "learning_rate": 3.421219620448553e-05, "loss": 0.5608, "step": 398 }, { "epoch": 1.6162025316455697, "grad_norm": 0.45981130976278506, "learning_rate": 3.417220439986623e-05, "loss": 0.5524, "step": 399 }, { "epoch": 1.620253164556962, "grad_norm": 0.5824369014210701, "learning_rate": 3.4132098454261024e-05, "loss": 0.5212, "step": 400 }, { "epoch": 1.6243037974683543, "grad_norm": 0.5075646757529213, "learning_rate": 3.4091878690677676e-05, "loss": 0.5579, "step": 401 }, { "epoch": 1.6283544303797468, "grad_norm": 0.5218940003224086, "learning_rate": 3.405154543304065e-05, "loss": 0.5432, "step": 402 }, { "epoch": 1.6324050632911393, "grad_norm": 0.4662977917247075, "learning_rate": 3.401109900618843e-05, "loss": 0.5724, "step": 403 }, { "epoch": 1.6364556962025316, "grad_norm": 0.49975737258562924, "learning_rate": 3.3970539735870996e-05, "loss": 0.5232, "step": 404 }, { "epoch": 1.640506329113924, "grad_norm": 0.45158909858136687, "learning_rate": 3.392986794874714e-05, "loss": 0.5764, "step": 405 }, { "epoch": 1.6445569620253164, "grad_norm": 0.558486602061321, "learning_rate": 3.388908397238184e-05, "loss": 0.5607, "step": 406 }, { "epoch": 1.648607594936709, "grad_norm": 0.4647348480875382, "learning_rate": 3.384818813524362e-05, "loss": 0.5269, "step": 407 }, { "epoch": 1.6526582278481012, "grad_norm": 0.5038653717390965, "learning_rate": 3.380718076670195e-05, "loss": 0.5617, "step": 408 }, { "epoch": 1.6567088607594935, "grad_norm": 0.4642447356028076, "learning_rate": 3.376606219702454e-05, "loss": 0.5146, "step": 409 }, { "epoch": 1.660759493670886, "grad_norm": 0.41139673422427625, "learning_rate": 3.372483275737468e-05, "loss": 0.5447, "step": 410 }, { "epoch": 1.6648101265822786, "grad_norm": 0.46740099826654935, "learning_rate": 3.368349277980861e-05, "loss": 0.5565, "step": 411 }, { "epoch": 1.6688607594936709, "grad_norm": 0.41955365008241835, "learning_rate": 3.3642042597272844e-05, "loss": 0.5415, "step": 412 }, { "epoch": 1.6729113924050631, "grad_norm": 0.479864495599026, "learning_rate": 3.360048254360144e-05, "loss": 0.5217, "step": 413 }, { "epoch": 1.6769620253164557, "grad_norm": 0.5044477989708716, "learning_rate": 3.355881295351336e-05, "loss": 0.5588, "step": 414 }, { "epoch": 1.6810126582278482, "grad_norm": 0.42777394297110216, "learning_rate": 3.351703416260975e-05, "loss": 0.5633, "step": 415 }, { "epoch": 1.6850632911392405, "grad_norm": 0.46947207221884907, "learning_rate": 3.347514650737126e-05, "loss": 0.5331, "step": 416 }, { "epoch": 1.6891139240506328, "grad_norm": 0.41451545861143063, "learning_rate": 3.3433150325155295e-05, "loss": 0.5532, "step": 417 }, { "epoch": 1.6931645569620253, "grad_norm": 0.4261622798697416, "learning_rate": 3.339104595419334e-05, "loss": 0.5369, "step": 418 }, { "epoch": 1.6972151898734178, "grad_norm": 0.4561883646248756, "learning_rate": 3.3348833733588204e-05, "loss": 0.5529, "step": 419 }, { "epoch": 1.70126582278481, "grad_norm": 0.4232529325762018, "learning_rate": 3.3306514003311305e-05, "loss": 0.5305, "step": 420 }, { "epoch": 1.7053164556962024, "grad_norm": 0.41101546613211337, "learning_rate": 3.326408710419996e-05, "loss": 0.5408, "step": 421 }, { "epoch": 1.709367088607595, "grad_norm": 0.4570932882313613, "learning_rate": 3.322155337795454e-05, "loss": 0.547, "step": 422 }, { "epoch": 1.7134177215189874, "grad_norm": 0.3631754035599048, "learning_rate": 3.317891316713587e-05, "loss": 0.5499, "step": 423 }, { "epoch": 1.7174683544303797, "grad_norm": 0.47245613969569006, "learning_rate": 3.313616681516231e-05, "loss": 0.5566, "step": 424 }, { "epoch": 1.721518987341772, "grad_norm": 0.39022544937308934, "learning_rate": 3.309331466630713e-05, "loss": 0.5385, "step": 425 }, { "epoch": 1.7255696202531645, "grad_norm": 0.4515271336917904, "learning_rate": 3.305035706569563e-05, "loss": 0.58, "step": 426 }, { "epoch": 1.729620253164557, "grad_norm": 0.477039448422297, "learning_rate": 3.3007294359302433e-05, "loss": 0.5353, "step": 427 }, { "epoch": 1.7336708860759493, "grad_norm": 0.38850979945395886, "learning_rate": 3.296412689394864e-05, "loss": 0.5226, "step": 428 }, { "epoch": 1.7377215189873416, "grad_norm": 0.5443900003137979, "learning_rate": 3.292085501729909e-05, "loss": 0.5479, "step": 429 }, { "epoch": 1.7417721518987341, "grad_norm": 0.3929374814431518, "learning_rate": 3.2877479077859534e-05, "loss": 0.542, "step": 430 }, { "epoch": 1.7458227848101266, "grad_norm": 0.47525348408990464, "learning_rate": 3.283399942497381e-05, "loss": 0.5395, "step": 431 }, { "epoch": 1.749873417721519, "grad_norm": 0.4307157883387603, "learning_rate": 3.279041640882108e-05, "loss": 0.543, "step": 432 }, { "epoch": 1.7539240506329112, "grad_norm": 0.4660400480510728, "learning_rate": 3.2746730380412964e-05, "loss": 0.5446, "step": 433 }, { "epoch": 1.7579746835443038, "grad_norm": 0.42253223824858854, "learning_rate": 3.2702941691590726e-05, "loss": 0.5372, "step": 434 }, { "epoch": 1.7620253164556963, "grad_norm": 0.5201961784369417, "learning_rate": 3.265905069502244e-05, "loss": 0.5529, "step": 435 }, { "epoch": 1.7660759493670886, "grad_norm": 0.39118211638882755, "learning_rate": 3.261505774420016e-05, "loss": 0.5293, "step": 436 }, { "epoch": 1.7701265822784809, "grad_norm": 0.5933094970339051, "learning_rate": 3.257096319343707e-05, "loss": 0.5473, "step": 437 }, { "epoch": 1.7741772151898734, "grad_norm": 0.5194964666017517, "learning_rate": 3.2526767397864614e-05, "loss": 0.5565, "step": 438 }, { "epoch": 1.7782278481012659, "grad_norm": 0.4510151585635111, "learning_rate": 3.248247071342966e-05, "loss": 0.5371, "step": 439 }, { "epoch": 1.7822784810126582, "grad_norm": 0.48206994249486246, "learning_rate": 3.243807349689161e-05, "loss": 0.5265, "step": 440 }, { "epoch": 1.7863291139240505, "grad_norm": 0.4177820461632051, "learning_rate": 3.2393576105819544e-05, "loss": 0.568, "step": 441 }, { "epoch": 1.790379746835443, "grad_norm": 0.4531545503973841, "learning_rate": 3.2348978898589333e-05, "loss": 0.5556, "step": 442 }, { "epoch": 1.7944303797468355, "grad_norm": 0.4010089134074396, "learning_rate": 3.230428223438075e-05, "loss": 0.5288, "step": 443 }, { "epoch": 1.7984810126582278, "grad_norm": 0.39616149319428634, "learning_rate": 3.225948647317459e-05, "loss": 0.5474, "step": 444 }, { "epoch": 1.80253164556962, "grad_norm": 0.4494826821322049, "learning_rate": 3.2214591975749745e-05, "loss": 0.5369, "step": 445 }, { "epoch": 1.8065822784810126, "grad_norm": 0.3847527331158778, "learning_rate": 3.216959910368034e-05, "loss": 0.5445, "step": 446 }, { "epoch": 1.8106329113924051, "grad_norm": 0.42530257326971665, "learning_rate": 3.212450821933277e-05, "loss": 0.5776, "step": 447 }, { "epoch": 1.8146835443037974, "grad_norm": 0.41598597353457756, "learning_rate": 3.207931968586281e-05, "loss": 0.5427, "step": 448 }, { "epoch": 1.81873417721519, "grad_norm": 0.3649781248513926, "learning_rate": 3.203403386721272e-05, "loss": 0.5286, "step": 449 }, { "epoch": 1.8227848101265822, "grad_norm": 0.4251156342334173, "learning_rate": 3.1988651128108245e-05, "loss": 0.5347, "step": 450 }, { "epoch": 1.8268354430379747, "grad_norm": 0.35100696144932025, "learning_rate": 3.194317183405573e-05, "loss": 0.559, "step": 451 }, { "epoch": 1.8308860759493673, "grad_norm": 0.43694106744531364, "learning_rate": 3.189759635133914e-05, "loss": 0.553, "step": 452 }, { "epoch": 1.8349367088607595, "grad_norm": 0.396830319295389, "learning_rate": 3.185192504701718e-05, "loss": 0.5455, "step": 453 }, { "epoch": 1.8389873417721518, "grad_norm": 0.4174333125416691, "learning_rate": 3.1806158288920234e-05, "loss": 0.5484, "step": 454 }, { "epoch": 1.8430379746835444, "grad_norm": 0.44021555581410865, "learning_rate": 3.1760296445647477e-05, "loss": 0.5394, "step": 455 }, { "epoch": 1.8470886075949369, "grad_norm": 0.39305699764657676, "learning_rate": 3.1714339886563896e-05, "loss": 0.5256, "step": 456 }, { "epoch": 1.8511392405063292, "grad_norm": 0.4029957911624852, "learning_rate": 3.166828898179731e-05, "loss": 0.5505, "step": 457 }, { "epoch": 1.8551898734177215, "grad_norm": 0.380336525230525, "learning_rate": 3.162214410223536e-05, "loss": 0.5404, "step": 458 }, { "epoch": 1.859240506329114, "grad_norm": 0.385530307109811, "learning_rate": 3.157590561952257e-05, "loss": 0.534, "step": 459 }, { "epoch": 1.8632911392405065, "grad_norm": 0.3983364315288058, "learning_rate": 3.152957390605732e-05, "loss": 0.5331, "step": 460 }, { "epoch": 1.8673417721518988, "grad_norm": 0.41335446595291314, "learning_rate": 3.148314933498886e-05, "loss": 0.549, "step": 461 }, { "epoch": 1.871392405063291, "grad_norm": 0.40509984396493487, "learning_rate": 3.143663228021431e-05, "loss": 0.5516, "step": 462 }, { "epoch": 1.8754430379746836, "grad_norm": 0.3628343102813581, "learning_rate": 3.1390023116375624e-05, "loss": 0.5311, "step": 463 }, { "epoch": 1.879493670886076, "grad_norm": 0.4168763003977813, "learning_rate": 3.134332221885661e-05, "loss": 0.5389, "step": 464 }, { "epoch": 1.8835443037974684, "grad_norm": 0.4199027711577741, "learning_rate": 3.129652996377987e-05, "loss": 0.5693, "step": 465 }, { "epoch": 1.8875949367088607, "grad_norm": 0.4065358407873812, "learning_rate": 3.12496467280038e-05, "loss": 0.5289, "step": 466 }, { "epoch": 1.8916455696202532, "grad_norm": 0.40556601218037125, "learning_rate": 3.120267288911952e-05, "loss": 0.543, "step": 467 }, { "epoch": 1.8956962025316457, "grad_norm": 0.3826284574743239, "learning_rate": 3.11556088254479e-05, "loss": 0.5238, "step": 468 }, { "epoch": 1.899746835443038, "grad_norm": 0.418890743417976, "learning_rate": 3.11084549160364e-05, "loss": 0.5263, "step": 469 }, { "epoch": 1.9037974683544303, "grad_norm": 0.42978709374323343, "learning_rate": 3.106121154065615e-05, "loss": 0.5478, "step": 470 }, { "epoch": 1.9078481012658228, "grad_norm": 0.3806037233487916, "learning_rate": 3.1013879079798805e-05, "loss": 0.509, "step": 471 }, { "epoch": 1.9118987341772153, "grad_norm": 0.4827585168594669, "learning_rate": 3.096645791467348e-05, "loss": 0.5663, "step": 472 }, { "epoch": 1.9159493670886076, "grad_norm": 0.48977759546010335, "learning_rate": 3.091894842720373e-05, "loss": 0.5349, "step": 473 }, { "epoch": 1.92, "grad_norm": 0.44183376924632267, "learning_rate": 3.0871351000024425e-05, "loss": 0.5532, "step": 474 }, { "epoch": 1.9240506329113924, "grad_norm": 0.45587137641782194, "learning_rate": 3.0823666016478716e-05, "loss": 0.5207, "step": 475 }, { "epoch": 1.928101265822785, "grad_norm": 0.4317506057631582, "learning_rate": 3.0775893860614896e-05, "loss": 0.544, "step": 476 }, { "epoch": 1.9321518987341773, "grad_norm": 0.5233653295953754, "learning_rate": 3.0728034917183336e-05, "loss": 0.5581, "step": 477 }, { "epoch": 1.9362025316455695, "grad_norm": 0.5939359070660547, "learning_rate": 3.06800895716334e-05, "loss": 0.5664, "step": 478 }, { "epoch": 1.940253164556962, "grad_norm": 0.4028200239765329, "learning_rate": 3.063205821011029e-05, "loss": 0.5256, "step": 479 }, { "epoch": 1.9443037974683546, "grad_norm": 0.6835248230838051, "learning_rate": 3.0583941219452016e-05, "loss": 0.5333, "step": 480 }, { "epoch": 1.9483544303797469, "grad_norm": 0.4132061563110443, "learning_rate": 3.053573898718618e-05, "loss": 0.5434, "step": 481 }, { "epoch": 1.9524050632911392, "grad_norm": 0.5102066389759208, "learning_rate": 3.0487451901526956e-05, "loss": 0.5477, "step": 482 }, { "epoch": 1.9564556962025317, "grad_norm": 0.43366832994097454, "learning_rate": 3.0439080351371875e-05, "loss": 0.5304, "step": 483 }, { "epoch": 1.9605063291139242, "grad_norm": 0.39876598278239883, "learning_rate": 3.0390624726298764e-05, "loss": 0.5603, "step": 484 }, { "epoch": 1.9645569620253165, "grad_norm": 0.44578069429200257, "learning_rate": 3.034208541656255e-05, "loss": 0.5685, "step": 485 }, { "epoch": 1.9686075949367088, "grad_norm": 0.3881407643886869, "learning_rate": 3.029346281309218e-05, "loss": 0.5213, "step": 486 }, { "epoch": 1.9726582278481013, "grad_norm": 0.46606073610187476, "learning_rate": 3.0244757307487415e-05, "loss": 0.5694, "step": 487 }, { "epoch": 1.9767088607594938, "grad_norm": 0.42759342152787483, "learning_rate": 3.019596929201569e-05, "loss": 0.5291, "step": 488 }, { "epoch": 1.980759493670886, "grad_norm": 0.4397345225603689, "learning_rate": 3.0147099159608985e-05, "loss": 0.5276, "step": 489 }, { "epoch": 1.9848101265822784, "grad_norm": 0.4292705843935787, "learning_rate": 3.0098147303860616e-05, "loss": 0.5336, "step": 490 }, { "epoch": 1.988860759493671, "grad_norm": 0.4594653447999785, "learning_rate": 3.0049114119022117e-05, "loss": 0.5514, "step": 491 }, { "epoch": 1.9929113924050634, "grad_norm": 0.4142985284016258, "learning_rate": 3.0000000000000004e-05, "loss": 0.5377, "step": 492 }, { "epoch": 1.9969620253164557, "grad_norm": 0.5097371149508293, "learning_rate": 2.995080534235264e-05, "loss": 0.5702, "step": 493 }, { "epoch": 2.001012658227848, "grad_norm": 0.5633833260832208, "learning_rate": 2.9901530542287044e-05, "loss": 0.5766, "step": 494 }, { "epoch": 2.0050632911392405, "grad_norm": 0.5145581903130819, "learning_rate": 2.9852175996655676e-05, "loss": 0.4761, "step": 495 }, { "epoch": 2.009113924050633, "grad_norm": 0.4707880621930016, "learning_rate": 2.980274210295326e-05, "loss": 0.4376, "step": 496 }, { "epoch": 2.013164556962025, "grad_norm": 0.7006859035565186, "learning_rate": 2.9753229259313578e-05, "loss": 0.4903, "step": 497 }, { "epoch": 2.0172151898734176, "grad_norm": 0.535983124865509, "learning_rate": 2.9703637864506274e-05, "loss": 0.4382, "step": 498 }, { "epoch": 2.02126582278481, "grad_norm": 0.6216911721819752, "learning_rate": 2.965396831793362e-05, "loss": 0.5052, "step": 499 }, { "epoch": 2.0253164556962027, "grad_norm": 0.5598066523781318, "learning_rate": 2.9604221019627316e-05, "loss": 0.4556, "step": 500 }, { "epoch": 2.0293670886075947, "grad_norm": 0.5363745686184743, "learning_rate": 2.955439637024526e-05, "loss": 0.4652, "step": 501 }, { "epoch": 2.0334177215189873, "grad_norm": 0.5797838163111377, "learning_rate": 2.9504494771068334e-05, "loss": 0.4657, "step": 502 }, { "epoch": 2.0374683544303798, "grad_norm": 0.5116407068241654, "learning_rate": 2.9454516623997156e-05, "loss": 0.4653, "step": 503 }, { "epoch": 2.0415189873417723, "grad_norm": 0.5749717014996107, "learning_rate": 2.9404462331548847e-05, "loss": 0.4709, "step": 504 }, { "epoch": 2.0455696202531644, "grad_norm": 0.48164326355432047, "learning_rate": 2.93543322968538e-05, "loss": 0.4686, "step": 505 }, { "epoch": 2.049620253164557, "grad_norm": 0.3997410277960586, "learning_rate": 2.9304126923652428e-05, "loss": 0.4401, "step": 506 }, { "epoch": 2.0536708860759494, "grad_norm": 0.5497777303247265, "learning_rate": 2.9253846616291896e-05, "loss": 0.4949, "step": 507 }, { "epoch": 2.057721518987342, "grad_norm": 0.40826669805499055, "learning_rate": 2.9203491779722896e-05, "loss": 0.429, "step": 508 }, { "epoch": 2.061772151898734, "grad_norm": 0.5953157462272335, "learning_rate": 2.9153062819496357e-05, "loss": 0.4816, "step": 509 }, { "epoch": 2.0658227848101265, "grad_norm": 0.6140264855321809, "learning_rate": 2.9102560141760178e-05, "loss": 0.4697, "step": 510 }, { "epoch": 2.069873417721519, "grad_norm": 0.4023883756243701, "learning_rate": 2.9051984153256004e-05, "loss": 0.4676, "step": 511 }, { "epoch": 2.0739240506329115, "grad_norm": 0.614128633144076, "learning_rate": 2.900133526131588e-05, "loss": 0.5015, "step": 512 }, { "epoch": 2.0779746835443036, "grad_norm": 0.37759668846306915, "learning_rate": 2.8950613873859025e-05, "loss": 0.4453, "step": 513 }, { "epoch": 2.082025316455696, "grad_norm": 0.5227908823087246, "learning_rate": 2.8899820399388515e-05, "loss": 0.4901, "step": 514 }, { "epoch": 2.0860759493670886, "grad_norm": 0.7019725042298394, "learning_rate": 2.8848955246988012e-05, "loss": 0.4545, "step": 515 }, { "epoch": 2.090126582278481, "grad_norm": 0.3693950327366212, "learning_rate": 2.879801882631847e-05, "loss": 0.4549, "step": 516 }, { "epoch": 2.094177215189873, "grad_norm": 0.7692127550775153, "learning_rate": 2.8747011547614808e-05, "loss": 0.4722, "step": 517 }, { "epoch": 2.0982278481012657, "grad_norm": 0.5061235177078995, "learning_rate": 2.8695933821682635e-05, "loss": 0.4708, "step": 518 }, { "epoch": 2.1022784810126582, "grad_norm": 0.4327914858638204, "learning_rate": 2.864478605989494e-05, "loss": 0.4594, "step": 519 }, { "epoch": 2.1063291139240508, "grad_norm": 0.45784242767589517, "learning_rate": 2.8593568674188765e-05, "loss": 0.4782, "step": 520 }, { "epoch": 2.110379746835443, "grad_norm": 0.41314548580213645, "learning_rate": 2.8542282077061892e-05, "loss": 0.4655, "step": 521 }, { "epoch": 2.1144303797468353, "grad_norm": 0.4016280761481268, "learning_rate": 2.8490926681569523e-05, "loss": 0.4493, "step": 522 }, { "epoch": 2.118481012658228, "grad_norm": 0.47759151471401623, "learning_rate": 2.8439502901320956e-05, "loss": 0.4755, "step": 523 }, { "epoch": 2.1225316455696204, "grad_norm": 0.40902923032982147, "learning_rate": 2.8388011150476237e-05, "loss": 0.4692, "step": 524 }, { "epoch": 2.1265822784810124, "grad_norm": 0.42977714755319213, "learning_rate": 2.8336451843742866e-05, "loss": 0.4569, "step": 525 }, { "epoch": 2.130632911392405, "grad_norm": 0.3980309448445065, "learning_rate": 2.8284825396372387e-05, "loss": 0.4527, "step": 526 }, { "epoch": 2.1346835443037975, "grad_norm": 0.5037796883669882, "learning_rate": 2.8233132224157132e-05, "loss": 0.4909, "step": 527 }, { "epoch": 2.13873417721519, "grad_norm": 0.43297289689453244, "learning_rate": 2.8181372743426805e-05, "loss": 0.4698, "step": 528 }, { "epoch": 2.1427848101265825, "grad_norm": 0.42416645484815557, "learning_rate": 2.8129547371045128e-05, "loss": 0.4349, "step": 529 }, { "epoch": 2.1468354430379746, "grad_norm": 0.4253254864490533, "learning_rate": 2.8077656524406534e-05, "loss": 0.4527, "step": 530 }, { "epoch": 2.150886075949367, "grad_norm": 0.4102438660471352, "learning_rate": 2.802570062143278e-05, "loss": 0.476, "step": 531 }, { "epoch": 2.1549367088607596, "grad_norm": 0.4122818577968311, "learning_rate": 2.7973680080569555e-05, "loss": 0.4753, "step": 532 }, { "epoch": 2.1589873417721517, "grad_norm": 0.44253629861359345, "learning_rate": 2.792159532078314e-05, "loss": 0.4706, "step": 533 }, { "epoch": 2.163037974683544, "grad_norm": 0.3868934133804731, "learning_rate": 2.7869446761557033e-05, "loss": 0.4754, "step": 534 }, { "epoch": 2.1670886075949367, "grad_norm": 0.5106175276164745, "learning_rate": 2.781723482288857e-05, "loss": 0.456, "step": 535 }, { "epoch": 2.1711392405063292, "grad_norm": 0.4126833293166233, "learning_rate": 2.7764959925285517e-05, "loss": 0.4601, "step": 536 }, { "epoch": 2.1751898734177217, "grad_norm": 0.5285036087546393, "learning_rate": 2.771262248976272e-05, "loss": 0.4614, "step": 537 }, { "epoch": 2.179240506329114, "grad_norm": 0.3930001010670523, "learning_rate": 2.7660222937838677e-05, "loss": 0.4747, "step": 538 }, { "epoch": 2.1832911392405063, "grad_norm": 0.5313195626130051, "learning_rate": 2.7607761691532186e-05, "loss": 0.4483, "step": 539 }, { "epoch": 2.187341772151899, "grad_norm": 0.41056596292213277, "learning_rate": 2.7555239173358916e-05, "loss": 0.4629, "step": 540 }, { "epoch": 2.191392405063291, "grad_norm": 0.46915884792906964, "learning_rate": 2.7502655806328e-05, "loss": 0.4702, "step": 541 }, { "epoch": 2.1954430379746834, "grad_norm": 0.4587723201835012, "learning_rate": 2.7450012013938648e-05, "loss": 0.4772, "step": 542 }, { "epoch": 2.199493670886076, "grad_norm": 0.35994480342316537, "learning_rate": 2.739730822017673e-05, "loss": 0.4392, "step": 543 }, { "epoch": 2.2035443037974685, "grad_norm": 0.4753506324894439, "learning_rate": 2.7344544849511355e-05, "loss": 0.4845, "step": 544 }, { "epoch": 2.207594936708861, "grad_norm": 0.43040639184272866, "learning_rate": 2.7291722326891456e-05, "loss": 0.4583, "step": 545 }, { "epoch": 2.211645569620253, "grad_norm": 0.4497733309188554, "learning_rate": 2.723884107774236e-05, "loss": 0.4563, "step": 546 }, { "epoch": 2.2156962025316456, "grad_norm": 0.4381825502483391, "learning_rate": 2.718590152796239e-05, "loss": 0.4723, "step": 547 }, { "epoch": 2.219746835443038, "grad_norm": 0.4147915717702344, "learning_rate": 2.71329041039194e-05, "loss": 0.4414, "step": 548 }, { "epoch": 2.22379746835443, "grad_norm": 0.4542479560947888, "learning_rate": 2.7079849232447357e-05, "loss": 0.4935, "step": 549 }, { "epoch": 2.2278481012658227, "grad_norm": 0.3658189168595364, "learning_rate": 2.7026737340842895e-05, "loss": 0.4501, "step": 550 }, { "epoch": 2.231898734177215, "grad_norm": 0.4384863218489249, "learning_rate": 2.697356885686189e-05, "loss": 0.4699, "step": 551 }, { "epoch": 2.2359493670886077, "grad_norm": 0.38805902823061494, "learning_rate": 2.6920344208716014e-05, "loss": 0.4753, "step": 552 }, { "epoch": 2.24, "grad_norm": 0.4324829464010064, "learning_rate": 2.6867063825069252e-05, "loss": 0.4465, "step": 553 }, { "epoch": 2.2440506329113923, "grad_norm": 0.35531656084424335, "learning_rate": 2.6813728135034494e-05, "loss": 0.4642, "step": 554 }, { "epoch": 2.248101265822785, "grad_norm": 0.47477436134951095, "learning_rate": 2.6760337568170056e-05, "loss": 0.4861, "step": 555 }, { "epoch": 2.2521518987341773, "grad_norm": 0.3785464242444033, "learning_rate": 2.6706892554476226e-05, "loss": 0.4629, "step": 556 }, { "epoch": 2.2562025316455694, "grad_norm": 0.3967150976806621, "learning_rate": 2.6653393524391795e-05, "loss": 0.4449, "step": 557 }, { "epoch": 2.260253164556962, "grad_norm": 0.4078308926288044, "learning_rate": 2.6599840908790592e-05, "loss": 0.4687, "step": 558 }, { "epoch": 2.2643037974683544, "grad_norm": 0.44933021649672367, "learning_rate": 2.6546235138978028e-05, "loss": 0.4697, "step": 559 }, { "epoch": 2.268354430379747, "grad_norm": 0.37364930978536637, "learning_rate": 2.6492576646687597e-05, "loss": 0.4727, "step": 560 }, { "epoch": 2.2724050632911394, "grad_norm": 0.4962246480153093, "learning_rate": 2.6438865864077425e-05, "loss": 0.4666, "step": 561 }, { "epoch": 2.2764556962025315, "grad_norm": 0.35362753039203737, "learning_rate": 2.6385103223726766e-05, "loss": 0.4599, "step": 562 }, { "epoch": 2.280506329113924, "grad_norm": 0.4861932841842465, "learning_rate": 2.6331289158632537e-05, "loss": 0.4628, "step": 563 }, { "epoch": 2.2845569620253166, "grad_norm": 0.36944605760822924, "learning_rate": 2.6277424102205817e-05, "loss": 0.4787, "step": 564 }, { "epoch": 2.2886075949367086, "grad_norm": 0.46807386512275184, "learning_rate": 2.6223508488268374e-05, "loss": 0.4755, "step": 565 }, { "epoch": 2.292658227848101, "grad_norm": 0.366994337489342, "learning_rate": 2.6169542751049148e-05, "loss": 0.4575, "step": 566 }, { "epoch": 2.2967088607594937, "grad_norm": 0.4072969427911742, "learning_rate": 2.6115527325180754e-05, "loss": 0.4865, "step": 567 }, { "epoch": 2.300759493670886, "grad_norm": 0.40893964218867407, "learning_rate": 2.606146264569603e-05, "loss": 0.4744, "step": 568 }, { "epoch": 2.3048101265822787, "grad_norm": 0.41179015012716513, "learning_rate": 2.6007349148024447e-05, "loss": 0.4759, "step": 569 }, { "epoch": 2.3088607594936708, "grad_norm": 0.42480492949648785, "learning_rate": 2.5953187267988694e-05, "loss": 0.4488, "step": 570 }, { "epoch": 2.3129113924050633, "grad_norm": 0.4225403693915914, "learning_rate": 2.5898977441801097e-05, "loss": 0.4871, "step": 571 }, { "epoch": 2.316962025316456, "grad_norm": 0.4436360186033238, "learning_rate": 2.584472010606015e-05, "loss": 0.4563, "step": 572 }, { "epoch": 2.321012658227848, "grad_norm": 0.4070606165827539, "learning_rate": 2.5790415697746976e-05, "loss": 0.4706, "step": 573 }, { "epoch": 2.3250632911392404, "grad_norm": 0.40539632232186906, "learning_rate": 2.5736064654221808e-05, "loss": 0.4828, "step": 574 }, { "epoch": 2.329113924050633, "grad_norm": 0.4785803549200606, "learning_rate": 2.568166741322048e-05, "loss": 0.4807, "step": 575 }, { "epoch": 2.3331645569620254, "grad_norm": 0.3827463495600536, "learning_rate": 2.56272244128509e-05, "loss": 0.4538, "step": 576 }, { "epoch": 2.337215189873418, "grad_norm": 0.3842096046591822, "learning_rate": 2.55727360915895e-05, "loss": 0.4598, "step": 577 }, { "epoch": 2.34126582278481, "grad_norm": 0.3642878770221747, "learning_rate": 2.5518202888277734e-05, "loss": 0.4422, "step": 578 }, { "epoch": 2.3453164556962025, "grad_norm": 0.39798664614286783, "learning_rate": 2.5463625242118523e-05, "loss": 0.4978, "step": 579 }, { "epoch": 2.349367088607595, "grad_norm": 0.3860680507462137, "learning_rate": 2.5409003592672723e-05, "loss": 0.4654, "step": 580 }, { "epoch": 2.353417721518987, "grad_norm": 0.36627622057741366, "learning_rate": 2.535433837985559e-05, "loss": 0.4609, "step": 581 }, { "epoch": 2.3574683544303796, "grad_norm": 0.3759582718655425, "learning_rate": 2.529963004393324e-05, "loss": 0.4653, "step": 582 }, { "epoch": 2.361518987341772, "grad_norm": 0.3582844784974076, "learning_rate": 2.524487902551908e-05, "loss": 0.465, "step": 583 }, { "epoch": 2.3655696202531646, "grad_norm": 0.3708809846033201, "learning_rate": 2.519008576557029e-05, "loss": 0.4613, "step": 584 }, { "epoch": 2.369620253164557, "grad_norm": 0.3622000527017929, "learning_rate": 2.5135250705384254e-05, "loss": 0.4892, "step": 585 }, { "epoch": 2.3736708860759492, "grad_norm": 0.38065856955815164, "learning_rate": 2.5080374286595007e-05, "loss": 0.4448, "step": 586 }, { "epoch": 2.3777215189873417, "grad_norm": 0.3857322121286496, "learning_rate": 2.5025456951169677e-05, "loss": 0.4985, "step": 587 }, { "epoch": 2.3817721518987343, "grad_norm": 0.40396353873520385, "learning_rate": 2.4970499141404942e-05, "loss": 0.4496, "step": 588 }, { "epoch": 2.3858227848101268, "grad_norm": 0.3798840603615128, "learning_rate": 2.491550129992345e-05, "loss": 0.4723, "step": 589 }, { "epoch": 2.389873417721519, "grad_norm": 0.4068124910720994, "learning_rate": 2.486046386967024e-05, "loss": 0.4678, "step": 590 }, { "epoch": 2.3939240506329114, "grad_norm": 0.3977737178853907, "learning_rate": 2.4805387293909214e-05, "loss": 0.4668, "step": 591 }, { "epoch": 2.397974683544304, "grad_norm": 0.32890465079071907, "learning_rate": 2.4750272016219552e-05, "loss": 0.4446, "step": 592 }, { "epoch": 2.4020253164556964, "grad_norm": 0.3918867303724685, "learning_rate": 2.4695118480492114e-05, "loss": 0.479, "step": 593 }, { "epoch": 2.4060759493670885, "grad_norm": 0.3586649988072146, "learning_rate": 2.4639927130925898e-05, "loss": 0.4875, "step": 594 }, { "epoch": 2.410126582278481, "grad_norm": 0.3799516124671789, "learning_rate": 2.458469841202444e-05, "loss": 0.4306, "step": 595 }, { "epoch": 2.4141772151898735, "grad_norm": 0.3780254663156502, "learning_rate": 2.452943276859226e-05, "loss": 0.4812, "step": 596 }, { "epoch": 2.418227848101266, "grad_norm": 0.38712655768105503, "learning_rate": 2.447413064573125e-05, "loss": 0.4525, "step": 597 }, { "epoch": 2.422278481012658, "grad_norm": 0.3698605597106699, "learning_rate": 2.4418792488837095e-05, "loss": 0.4884, "step": 598 }, { "epoch": 2.4263291139240506, "grad_norm": 0.3725643990174631, "learning_rate": 2.4363418743595713e-05, "loss": 0.4592, "step": 599 }, { "epoch": 2.430379746835443, "grad_norm": 0.3858989411930491, "learning_rate": 2.430800985597963e-05, "loss": 0.4662, "step": 600 }, { "epoch": 2.4344303797468356, "grad_norm": 0.4667572888962148, "learning_rate": 2.4252566272244415e-05, "loss": 0.454, "step": 601 }, { "epoch": 2.4384810126582277, "grad_norm": 0.3337461722847208, "learning_rate": 2.4197088438925063e-05, "loss": 0.4774, "step": 602 }, { "epoch": 2.44253164556962, "grad_norm": 0.40691110694219407, "learning_rate": 2.4141576802832417e-05, "loss": 0.4654, "step": 603 }, { "epoch": 2.4465822784810127, "grad_norm": 0.3612995579279913, "learning_rate": 2.408603181104957e-05, "loss": 0.4776, "step": 604 }, { "epoch": 2.4506329113924052, "grad_norm": 0.4192356878661848, "learning_rate": 2.4030453910928245e-05, "loss": 0.4672, "step": 605 }, { "epoch": 2.4546835443037973, "grad_norm": 0.37884096109328325, "learning_rate": 2.397484355008521e-05, "loss": 0.4925, "step": 606 }, { "epoch": 2.45873417721519, "grad_norm": 0.38984299403674333, "learning_rate": 2.3919201176398662e-05, "loss": 0.4604, "step": 607 }, { "epoch": 2.4627848101265823, "grad_norm": 0.3154547271241589, "learning_rate": 2.3863527238004633e-05, "loss": 0.4402, "step": 608 }, { "epoch": 2.466835443037975, "grad_norm": 0.3668744862509012, "learning_rate": 2.380782218329337e-05, "loss": 0.4828, "step": 609 }, { "epoch": 2.470886075949367, "grad_norm": 0.323465023936168, "learning_rate": 2.3752086460905725e-05, "loss": 0.4423, "step": 610 }, { "epoch": 2.4749367088607594, "grad_norm": 0.35888331265685797, "learning_rate": 2.3696320519729544e-05, "loss": 0.483, "step": 611 }, { "epoch": 2.478987341772152, "grad_norm": 0.3564671300044005, "learning_rate": 2.3640524808896045e-05, "loss": 0.4699, "step": 612 }, { "epoch": 2.4830379746835445, "grad_norm": 0.3353579131338718, "learning_rate": 2.3584699777776222e-05, "loss": 0.4741, "step": 613 }, { "epoch": 2.4870886075949366, "grad_norm": 0.3243083367371577, "learning_rate": 2.3528845875977195e-05, "loss": 0.4636, "step": 614 }, { "epoch": 2.491139240506329, "grad_norm": 0.3166802925348444, "learning_rate": 2.3472963553338614e-05, "loss": 0.4453, "step": 615 }, { "epoch": 2.4951898734177216, "grad_norm": 0.3651837933714487, "learning_rate": 2.341705325992901e-05, "loss": 0.5131, "step": 616 }, { "epoch": 2.499240506329114, "grad_norm": 0.339666179554698, "learning_rate": 2.336111544604222e-05, "loss": 0.4397, "step": 617 }, { "epoch": 2.503291139240506, "grad_norm": 0.4112512635058932, "learning_rate": 2.33051505621937e-05, "loss": 0.514, "step": 618 }, { "epoch": 2.5073417721518987, "grad_norm": 0.38005244969635044, "learning_rate": 2.324915905911693e-05, "loss": 0.4465, "step": 619 }, { "epoch": 2.511392405063291, "grad_norm": 0.3763192884493274, "learning_rate": 2.319314138775977e-05, "loss": 0.4802, "step": 620 }, { "epoch": 2.5154430379746833, "grad_norm": 0.31066327400314003, "learning_rate": 2.3137097999280856e-05, "loss": 0.4528, "step": 621 }, { "epoch": 2.519493670886076, "grad_norm": 0.37722167204065576, "learning_rate": 2.308102934504593e-05, "loss": 0.4772, "step": 622 }, { "epoch": 2.5235443037974683, "grad_norm": 0.3808778432882257, "learning_rate": 2.3024935876624222e-05, "loss": 0.465, "step": 623 }, { "epoch": 2.527594936708861, "grad_norm": 0.34432939955418385, "learning_rate": 2.2968818045784813e-05, "loss": 0.4795, "step": 624 }, { "epoch": 2.5316455696202533, "grad_norm": 0.3432663995387939, "learning_rate": 2.2912676304493006e-05, "loss": 0.4493, "step": 625 }, { "epoch": 2.5356962025316454, "grad_norm": 0.38455751785641124, "learning_rate": 2.2856511104906668e-05, "loss": 0.4748, "step": 626 }, { "epoch": 2.539746835443038, "grad_norm": 0.34266421916537415, "learning_rate": 2.2800322899372586e-05, "loss": 0.4809, "step": 627 }, { "epoch": 2.5437974683544304, "grad_norm": 0.36493537611098087, "learning_rate": 2.2744112140422844e-05, "loss": 0.448, "step": 628 }, { "epoch": 2.547848101265823, "grad_norm": 0.37099277184266083, "learning_rate": 2.2687879280771177e-05, "loss": 0.5033, "step": 629 }, { "epoch": 2.5518987341772155, "grad_norm": 0.3201588606757426, "learning_rate": 2.26316247733093e-05, "loss": 0.4438, "step": 630 }, { "epoch": 2.5559493670886075, "grad_norm": 0.3700947619921916, "learning_rate": 2.257534907110328e-05, "loss": 0.4409, "step": 631 }, { "epoch": 2.56, "grad_norm": 0.35349301140392436, "learning_rate": 2.2519052627389882e-05, "loss": 0.478, "step": 632 }, { "epoch": 2.5640506329113926, "grad_norm": 0.34149921635709496, "learning_rate": 2.246273589557294e-05, "loss": 0.4622, "step": 633 }, { "epoch": 2.5681012658227846, "grad_norm": 0.3553911101845489, "learning_rate": 2.240639932921966e-05, "loss": 0.4788, "step": 634 }, { "epoch": 2.572151898734177, "grad_norm": 0.3912589788795399, "learning_rate": 2.2350043382056995e-05, "loss": 0.4579, "step": 635 }, { "epoch": 2.5762025316455697, "grad_norm": 0.3466454658559497, "learning_rate": 2.2293668507968015e-05, "loss": 0.4786, "step": 636 }, { "epoch": 2.580253164556962, "grad_norm": 0.4493715583184417, "learning_rate": 2.2237275160988186e-05, "loss": 0.4605, "step": 637 }, { "epoch": 2.5843037974683547, "grad_norm": 0.3768414797190866, "learning_rate": 2.2180863795301787e-05, "loss": 0.4912, "step": 638 }, { "epoch": 2.5883544303797468, "grad_norm": 0.3769729828667998, "learning_rate": 2.212443486523819e-05, "loss": 0.4819, "step": 639 }, { "epoch": 2.5924050632911393, "grad_norm": 0.3514355328809295, "learning_rate": 2.2067988825268243e-05, "loss": 0.4661, "step": 640 }, { "epoch": 2.596455696202532, "grad_norm": 0.32387427135087893, "learning_rate": 2.2011526130000596e-05, "loss": 0.4698, "step": 641 }, { "epoch": 2.600506329113924, "grad_norm": 0.3646621660418733, "learning_rate": 2.1955047234178038e-05, "loss": 0.4707, "step": 642 }, { "epoch": 2.6045569620253164, "grad_norm": 0.3275723054019375, "learning_rate": 2.1898552592673825e-05, "loss": 0.4803, "step": 643 }, { "epoch": 2.608607594936709, "grad_norm": 0.33920167685216984, "learning_rate": 2.184204266048803e-05, "loss": 0.4648, "step": 644 }, { "epoch": 2.6126582278481014, "grad_norm": 0.3460954763862244, "learning_rate": 2.1785517892743887e-05, "loss": 0.4401, "step": 645 }, { "epoch": 2.616708860759494, "grad_norm": 0.3358026587942254, "learning_rate": 2.17289787446841e-05, "loss": 0.5051, "step": 646 }, { "epoch": 2.620759493670886, "grad_norm": 0.3289377978816245, "learning_rate": 2.1672425671667198e-05, "loss": 0.4566, "step": 647 }, { "epoch": 2.6248101265822785, "grad_norm": 0.364980374261778, "learning_rate": 2.161585912916385e-05, "loss": 0.4698, "step": 648 }, { "epoch": 2.628860759493671, "grad_norm": 0.3146074026549989, "learning_rate": 2.1559279572753214e-05, "loss": 0.4453, "step": 649 }, { "epoch": 2.632911392405063, "grad_norm": 0.3523778629169849, "learning_rate": 2.1502687458119268e-05, "loss": 0.4867, "step": 650 }, { "epoch": 2.6369620253164556, "grad_norm": 0.438070132577322, "learning_rate": 2.1446083241047116e-05, "loss": 0.4661, "step": 651 }, { "epoch": 2.641012658227848, "grad_norm": 0.3634525473511234, "learning_rate": 2.1389467377419333e-05, "loss": 0.4952, "step": 652 }, { "epoch": 2.6450632911392407, "grad_norm": 0.3980323492559783, "learning_rate": 2.133284032321232e-05, "loss": 0.4491, "step": 653 }, { "epoch": 2.649113924050633, "grad_norm": 0.357836008887165, "learning_rate": 2.1276202534492566e-05, "loss": 0.4672, "step": 654 }, { "epoch": 2.6531645569620252, "grad_norm": 0.40537459184733315, "learning_rate": 2.121955446741306e-05, "loss": 0.4881, "step": 655 }, { "epoch": 2.6572151898734178, "grad_norm": 0.3679640513208277, "learning_rate": 2.1162896578209517e-05, "loss": 0.4699, "step": 656 }, { "epoch": 2.6612658227848103, "grad_norm": 0.3947148015130508, "learning_rate": 2.1106229323196813e-05, "loss": 0.4404, "step": 657 }, { "epoch": 2.6653164556962023, "grad_norm": 0.39110853659964434, "learning_rate": 2.1049553158765214e-05, "loss": 0.4865, "step": 658 }, { "epoch": 2.669367088607595, "grad_norm": 0.37915017985636407, "learning_rate": 2.0992868541376764e-05, "loss": 0.465, "step": 659 }, { "epoch": 2.6734177215189874, "grad_norm": 0.3536384423086592, "learning_rate": 2.093617592756158e-05, "loss": 0.451, "step": 660 }, { "epoch": 2.67746835443038, "grad_norm": 0.34621786871593596, "learning_rate": 2.0879475773914167e-05, "loss": 0.4726, "step": 661 }, { "epoch": 2.6815189873417724, "grad_norm": 0.33882595648710095, "learning_rate": 2.082276853708978e-05, "loss": 0.4802, "step": 662 }, { "epoch": 2.6855696202531645, "grad_norm": 0.3358544303230221, "learning_rate": 2.076605467380071e-05, "loss": 0.4739, "step": 663 }, { "epoch": 2.689620253164557, "grad_norm": 0.35067883318227816, "learning_rate": 2.0709334640812613e-05, "loss": 0.4399, "step": 664 }, { "epoch": 2.6936708860759495, "grad_norm": 0.3629944754830274, "learning_rate": 2.0652608894940824e-05, "loss": 0.4872, "step": 665 }, { "epoch": 2.6977215189873416, "grad_norm": 0.3798000617190403, "learning_rate": 2.0595877893046722e-05, "loss": 0.4528, "step": 666 }, { "epoch": 2.701772151898734, "grad_norm": 0.36960614645336926, "learning_rate": 2.0539142092033985e-05, "loss": 0.5045, "step": 667 }, { "epoch": 2.7058227848101266, "grad_norm": 0.4054886622103652, "learning_rate": 2.048240194884496e-05, "loss": 0.4463, "step": 668 }, { "epoch": 2.709873417721519, "grad_norm": 0.4025232400976603, "learning_rate": 2.042565792045695e-05, "loss": 0.4861, "step": 669 }, { "epoch": 2.7139240506329116, "grad_norm": 0.4261191709671934, "learning_rate": 2.036891046387857e-05, "loss": 0.4748, "step": 670 }, { "epoch": 2.7179746835443037, "grad_norm": 0.39414387028771963, "learning_rate": 2.0312160036146036e-05, "loss": 0.4695, "step": 671 }, { "epoch": 2.7220253164556962, "grad_norm": 0.350397701345335, "learning_rate": 2.025540709431948e-05, "loss": 0.449, "step": 672 }, { "epoch": 2.7260759493670887, "grad_norm": 0.3705071367541822, "learning_rate": 2.0198652095479298e-05, "loss": 0.4694, "step": 673 }, { "epoch": 2.730126582278481, "grad_norm": 0.36186251820591914, "learning_rate": 2.014189549672245e-05, "loss": 0.4666, "step": 674 }, { "epoch": 2.7341772151898733, "grad_norm": 0.33116591785596783, "learning_rate": 2.0085137755158776e-05, "loss": 0.4584, "step": 675 }, { "epoch": 2.738227848101266, "grad_norm": 0.3483608232118701, "learning_rate": 2.0028379327907327e-05, "loss": 0.4485, "step": 676 }, { "epoch": 2.7422784810126584, "grad_norm": 0.36552510375916275, "learning_rate": 1.9971620672092676e-05, "loss": 0.4811, "step": 677 }, { "epoch": 2.746329113924051, "grad_norm": 0.3461946206063941, "learning_rate": 1.991486224484123e-05, "loss": 0.4676, "step": 678 }, { "epoch": 2.750379746835443, "grad_norm": 0.37617932578672264, "learning_rate": 1.985810450327756e-05, "loss": 0.445, "step": 679 }, { "epoch": 2.7544303797468355, "grad_norm": 0.3112956029466544, "learning_rate": 1.9801347904520706e-05, "loss": 0.4571, "step": 680 }, { "epoch": 2.758481012658228, "grad_norm": 0.35436067408789085, "learning_rate": 1.974459290568053e-05, "loss": 0.4861, "step": 681 }, { "epoch": 2.76253164556962, "grad_norm": 0.32610112991572066, "learning_rate": 1.968783996385397e-05, "loss": 0.4526, "step": 682 }, { "epoch": 2.7665822784810126, "grad_norm": 0.30300874288496343, "learning_rate": 1.963108953612143e-05, "loss": 0.454, "step": 683 }, { "epoch": 2.770632911392405, "grad_norm": 0.33033682996833474, "learning_rate": 1.9574342079543056e-05, "loss": 0.4943, "step": 684 }, { "epoch": 2.7746835443037976, "grad_norm": 0.32697418239425924, "learning_rate": 1.9517598051155046e-05, "loss": 0.46, "step": 685 }, { "epoch": 2.77873417721519, "grad_norm": 0.32144535026277565, "learning_rate": 1.9460857907966025e-05, "loss": 0.4534, "step": 686 }, { "epoch": 2.782784810126582, "grad_norm": 0.36166639490816843, "learning_rate": 1.9404122106953285e-05, "loss": 0.4772, "step": 687 }, { "epoch": 2.7868354430379747, "grad_norm": 0.31420364390619265, "learning_rate": 1.9347391105059176e-05, "loss": 0.4594, "step": 688 }, { "epoch": 2.790886075949367, "grad_norm": 0.348484589816806, "learning_rate": 1.92906653591874e-05, "loss": 0.4708, "step": 689 }, { "epoch": 2.7949367088607593, "grad_norm": 0.32007765997324344, "learning_rate": 1.9233945326199295e-05, "loss": 0.4725, "step": 690 }, { "epoch": 2.798987341772152, "grad_norm": 0.2872866437588627, "learning_rate": 1.917723146291022e-05, "loss": 0.4535, "step": 691 }, { "epoch": 2.8030379746835443, "grad_norm": 0.3091625670796399, "learning_rate": 1.912052422608584e-05, "loss": 0.472, "step": 692 }, { "epoch": 2.807088607594937, "grad_norm": 0.3273225864982373, "learning_rate": 1.9063824072438428e-05, "loss": 0.4808, "step": 693 }, { "epoch": 2.8111392405063294, "grad_norm": 0.293937642926387, "learning_rate": 1.9007131458623246e-05, "loss": 0.4444, "step": 694 }, { "epoch": 2.8151898734177214, "grad_norm": 0.3281401816759164, "learning_rate": 1.895044684123479e-05, "loss": 0.4587, "step": 695 }, { "epoch": 2.819240506329114, "grad_norm": 0.3279985409750009, "learning_rate": 1.8893770676803194e-05, "loss": 0.4625, "step": 696 }, { "epoch": 2.8232911392405065, "grad_norm": 0.3088755592754909, "learning_rate": 1.8837103421790486e-05, "loss": 0.4576, "step": 697 }, { "epoch": 2.8273417721518985, "grad_norm": 0.33632734559983785, "learning_rate": 1.8780445532586952e-05, "loss": 0.4822, "step": 698 }, { "epoch": 2.831392405063291, "grad_norm": 0.38357777106049473, "learning_rate": 1.872379746550743e-05, "loss": 0.4744, "step": 699 }, { "epoch": 2.8354430379746836, "grad_norm": 0.34512057405645274, "learning_rate": 1.866715967678769e-05, "loss": 0.4448, "step": 700 }, { "epoch": 2.839493670886076, "grad_norm": 0.3522279486036707, "learning_rate": 1.861053262258067e-05, "loss": 0.4791, "step": 701 }, { "epoch": 2.8435443037974686, "grad_norm": 0.34286887702241114, "learning_rate": 1.8553916758952897e-05, "loss": 0.479, "step": 702 }, { "epoch": 2.8475949367088607, "grad_norm": 0.3454030860458736, "learning_rate": 1.8497312541880735e-05, "loss": 0.468, "step": 703 }, { "epoch": 2.851645569620253, "grad_norm": 0.31423110251029207, "learning_rate": 1.8440720427246786e-05, "loss": 0.4615, "step": 704 }, { "epoch": 2.8556962025316457, "grad_norm": 0.35758465653491195, "learning_rate": 1.8384140870836157e-05, "loss": 0.4606, "step": 705 }, { "epoch": 2.8597468354430378, "grad_norm": 0.3514569381412306, "learning_rate": 1.8327574328332806e-05, "loss": 0.4815, "step": 706 }, { "epoch": 2.8637974683544303, "grad_norm": 0.34866307005146785, "learning_rate": 1.8271021255315906e-05, "loss": 0.4488, "step": 707 }, { "epoch": 2.867848101265823, "grad_norm": 0.38791095789683494, "learning_rate": 1.8214482107256117e-05, "loss": 0.4776, "step": 708 }, { "epoch": 2.8718987341772153, "grad_norm": 0.37025633769908367, "learning_rate": 1.8157957339511968e-05, "loss": 0.4655, "step": 709 }, { "epoch": 2.875949367088608, "grad_norm": 0.3649906681083972, "learning_rate": 1.8101447407326182e-05, "loss": 0.4733, "step": 710 }, { "epoch": 2.88, "grad_norm": 0.30425415494332314, "learning_rate": 1.8044952765821966e-05, "loss": 0.4454, "step": 711 }, { "epoch": 2.8840506329113924, "grad_norm": 0.36380734463040304, "learning_rate": 1.7988473869999407e-05, "loss": 0.4649, "step": 712 }, { "epoch": 2.888101265822785, "grad_norm": 0.32361803546157897, "learning_rate": 1.7932011174731764e-05, "loss": 0.472, "step": 713 }, { "epoch": 2.892151898734177, "grad_norm": 0.336879767657441, "learning_rate": 1.7875565134761817e-05, "loss": 0.458, "step": 714 }, { "epoch": 2.8962025316455695, "grad_norm": 0.3130828808641832, "learning_rate": 1.7819136204698226e-05, "loss": 0.4852, "step": 715 }, { "epoch": 2.900253164556962, "grad_norm": 0.3211488533939851, "learning_rate": 1.776272483901182e-05, "loss": 0.4741, "step": 716 }, { "epoch": 2.9043037974683545, "grad_norm": 0.32962641729090975, "learning_rate": 1.7706331492031995e-05, "loss": 0.4578, "step": 717 }, { "epoch": 2.908354430379747, "grad_norm": 0.31739784907442287, "learning_rate": 1.764995661794301e-05, "loss": 0.4814, "step": 718 }, { "epoch": 2.912405063291139, "grad_norm": 0.3186701252329526, "learning_rate": 1.759360067078035e-05, "loss": 0.4521, "step": 719 }, { "epoch": 2.9164556962025316, "grad_norm": 0.40686535318896466, "learning_rate": 1.7537264104427064e-05, "loss": 0.4915, "step": 720 }, { "epoch": 2.920506329113924, "grad_norm": 0.29581497408651913, "learning_rate": 1.748094737261012e-05, "loss": 0.4627, "step": 721 }, { "epoch": 2.9245569620253162, "grad_norm": 0.31033594908153755, "learning_rate": 1.7424650928896726e-05, "loss": 0.4628, "step": 722 }, { "epoch": 2.9286075949367087, "grad_norm": 0.34621117801558643, "learning_rate": 1.7368375226690712e-05, "loss": 0.4714, "step": 723 }, { "epoch": 2.9326582278481013, "grad_norm": 0.29140259736809837, "learning_rate": 1.731212071922883e-05, "loss": 0.4363, "step": 724 }, { "epoch": 2.9367088607594938, "grad_norm": 0.3726154115340492, "learning_rate": 1.7255887859577156e-05, "loss": 0.5039, "step": 725 }, { "epoch": 2.9407594936708863, "grad_norm": 0.3122615000153575, "learning_rate": 1.7199677100627427e-05, "loss": 0.4744, "step": 726 }, { "epoch": 2.9448101265822784, "grad_norm": 0.3453509142889604, "learning_rate": 1.7143488895093343e-05, "loss": 0.4629, "step": 727 }, { "epoch": 2.948860759493671, "grad_norm": 0.3427576131715334, "learning_rate": 1.7087323695506994e-05, "loss": 0.4574, "step": 728 }, { "epoch": 2.9529113924050634, "grad_norm": 0.3197935485181645, "learning_rate": 1.7031181954215194e-05, "loss": 0.4809, "step": 729 }, { "epoch": 2.9569620253164555, "grad_norm": 0.314667600115691, "learning_rate": 1.6975064123375788e-05, "loss": 0.4502, "step": 730 }, { "epoch": 2.961012658227848, "grad_norm": 0.3385589231003756, "learning_rate": 1.6918970654954084e-05, "loss": 0.4757, "step": 731 }, { "epoch": 2.9650632911392405, "grad_norm": 0.30321516677222393, "learning_rate": 1.686290200071915e-05, "loss": 0.4838, "step": 732 }, { "epoch": 2.969113924050633, "grad_norm": 0.3086328392929045, "learning_rate": 1.6806858612240234e-05, "loss": 0.4512, "step": 733 }, { "epoch": 2.9731645569620255, "grad_norm": 0.3311091069886148, "learning_rate": 1.6750840940883078e-05, "loss": 0.4715, "step": 734 }, { "epoch": 2.9772151898734176, "grad_norm": 0.3017700055208927, "learning_rate": 1.6694849437806305e-05, "loss": 0.4913, "step": 735 }, { "epoch": 2.98126582278481, "grad_norm": 0.32760103326186873, "learning_rate": 1.663888455395778e-05, "loss": 0.4465, "step": 736 }, { "epoch": 2.9853164556962026, "grad_norm": 0.3436186768099805, "learning_rate": 1.6582946740070995e-05, "loss": 0.4927, "step": 737 }, { "epoch": 2.9893670886075947, "grad_norm": 0.3120995550688494, "learning_rate": 1.6527036446661396e-05, "loss": 0.4286, "step": 738 }, { "epoch": 2.993417721518987, "grad_norm": 0.33217063872309444, "learning_rate": 1.6471154124022818e-05, "loss": 0.5026, "step": 739 }, { "epoch": 2.9974683544303797, "grad_norm": 0.3186289431336098, "learning_rate": 1.6415300222223788e-05, "loss": 0.4846, "step": 740 }, { "epoch": 3.0015189873417722, "grad_norm": 0.40994460173688885, "learning_rate": 1.6359475191103958e-05, "loss": 0.4987, "step": 741 }, { "epoch": 3.0055696202531648, "grad_norm": 0.42944936858931076, "learning_rate": 1.6303679480270466e-05, "loss": 0.3614, "step": 742 }, { "epoch": 3.009620253164557, "grad_norm": 0.3937751898141698, "learning_rate": 1.624791353909428e-05, "loss": 0.404, "step": 743 }, { "epoch": 3.0136708860759494, "grad_norm": 0.6171195416424777, "learning_rate": 1.619217781670663e-05, "loss": 0.3814, "step": 744 }, { "epoch": 3.017721518987342, "grad_norm": 0.5203782628658555, "learning_rate": 1.6136472761995373e-05, "loss": 0.3781, "step": 745 }, { "epoch": 3.0217721518987344, "grad_norm": 0.42654926959651857, "learning_rate": 1.608079882360134e-05, "loss": 0.3856, "step": 746 }, { "epoch": 3.0258227848101265, "grad_norm": 0.5047981648545924, "learning_rate": 1.60251564499148e-05, "loss": 0.3783, "step": 747 }, { "epoch": 3.029873417721519, "grad_norm": 0.42847934154942247, "learning_rate": 1.596954608907176e-05, "loss": 0.3751, "step": 748 }, { "epoch": 3.0339240506329115, "grad_norm": 0.4416583280732185, "learning_rate": 1.591396818895043e-05, "loss": 0.3984, "step": 749 }, { "epoch": 3.037974683544304, "grad_norm": 0.39747903396915096, "learning_rate": 1.585842319716759e-05, "loss": 0.3703, "step": 750 }, { "epoch": 3.042025316455696, "grad_norm": 0.45307910587490535, "learning_rate": 1.5802911561074944e-05, "loss": 0.4016, "step": 751 }, { "epoch": 3.0460759493670886, "grad_norm": 0.38564316210518723, "learning_rate": 1.5747433727755595e-05, "loss": 0.3648, "step": 752 }, { "epoch": 3.050126582278481, "grad_norm": 0.3829170808943174, "learning_rate": 1.5691990144020376e-05, "loss": 0.394, "step": 753 }, { "epoch": 3.0541772151898736, "grad_norm": 0.41691635312062114, "learning_rate": 1.5636581256404297e-05, "loss": 0.3848, "step": 754 }, { "epoch": 3.0582278481012657, "grad_norm": 0.369837431002592, "learning_rate": 1.558120751116291e-05, "loss": 0.366, "step": 755 }, { "epoch": 3.062278481012658, "grad_norm": 0.3692185530020885, "learning_rate": 1.552586935426876e-05, "loss": 0.3812, "step": 756 }, { "epoch": 3.0663291139240507, "grad_norm": 0.41101600931600474, "learning_rate": 1.547056723140774e-05, "loss": 0.3788, "step": 757 }, { "epoch": 3.0703797468354432, "grad_norm": 0.41005643775572703, "learning_rate": 1.5415301587975565e-05, "loss": 0.3819, "step": 758 }, { "epoch": 3.0744303797468353, "grad_norm": 0.33891914882592317, "learning_rate": 1.536007286907411e-05, "loss": 0.3902, "step": 759 }, { "epoch": 3.078481012658228, "grad_norm": 0.40278304534729037, "learning_rate": 1.5304881519507896e-05, "loss": 0.3688, "step": 760 }, { "epoch": 3.0825316455696203, "grad_norm": 0.3627253681835091, "learning_rate": 1.5249727983780453e-05, "loss": 0.3982, "step": 761 }, { "epoch": 3.086582278481013, "grad_norm": 0.3345078188189313, "learning_rate": 1.5194612706090786e-05, "loss": 0.372, "step": 762 }, { "epoch": 3.090632911392405, "grad_norm": 0.36760662076086037, "learning_rate": 1.5139536130329771e-05, "loss": 0.3906, "step": 763 }, { "epoch": 3.0946835443037974, "grad_norm": 0.3238771504697011, "learning_rate": 1.508449870007656e-05, "loss": 0.3595, "step": 764 }, { "epoch": 3.09873417721519, "grad_norm": 0.38909449893116016, "learning_rate": 1.5029500858595056e-05, "loss": 0.3861, "step": 765 }, { "epoch": 3.1027848101265825, "grad_norm": 0.36547130972592545, "learning_rate": 1.4974543048830328e-05, "loss": 0.4194, "step": 766 }, { "epoch": 3.1068354430379745, "grad_norm": 0.33072174812379174, "learning_rate": 1.4919625713405e-05, "loss": 0.3705, "step": 767 }, { "epoch": 3.110886075949367, "grad_norm": 0.34116320208479145, "learning_rate": 1.4864749294615756e-05, "loss": 0.3816, "step": 768 }, { "epoch": 3.1149367088607596, "grad_norm": 0.3426647434527568, "learning_rate": 1.4809914234429716e-05, "loss": 0.3813, "step": 769 }, { "epoch": 3.118987341772152, "grad_norm": 0.3179643247918671, "learning_rate": 1.4755120974480923e-05, "loss": 0.3595, "step": 770 }, { "epoch": 3.123037974683544, "grad_norm": 0.3200926827021234, "learning_rate": 1.4700369956066771e-05, "loss": 0.3893, "step": 771 }, { "epoch": 3.1270886075949367, "grad_norm": 0.3494778949467551, "learning_rate": 1.4645661620144413e-05, "loss": 0.381, "step": 772 }, { "epoch": 3.131139240506329, "grad_norm": 0.3596071169815533, "learning_rate": 1.4590996407327284e-05, "loss": 0.3802, "step": 773 }, { "epoch": 3.1351898734177217, "grad_norm": 0.3439110846444239, "learning_rate": 1.4536374757881487e-05, "loss": 0.4071, "step": 774 }, { "epoch": 3.1392405063291138, "grad_norm": 0.3176773042094243, "learning_rate": 1.4481797111722271e-05, "loss": 0.3473, "step": 775 }, { "epoch": 3.1432911392405063, "grad_norm": 0.3499093266961346, "learning_rate": 1.4427263908410507e-05, "loss": 0.4102, "step": 776 }, { "epoch": 3.147341772151899, "grad_norm": 0.3251686461444994, "learning_rate": 1.4372775587149108e-05, "loss": 0.3815, "step": 777 }, { "epoch": 3.1513924050632913, "grad_norm": 0.3274476967572929, "learning_rate": 1.4318332586779522e-05, "loss": 0.3624, "step": 778 }, { "epoch": 3.1554430379746834, "grad_norm": 0.34347742433290246, "learning_rate": 1.4263935345778202e-05, "loss": 0.3808, "step": 779 }, { "epoch": 3.159493670886076, "grad_norm": 0.3606234631171453, "learning_rate": 1.420958430225303e-05, "loss": 0.3959, "step": 780 }, { "epoch": 3.1635443037974684, "grad_norm": 0.3001188318952908, "learning_rate": 1.415527989393985e-05, "loss": 0.3693, "step": 781 }, { "epoch": 3.167594936708861, "grad_norm": 0.33023703391803383, "learning_rate": 1.410102255819891e-05, "loss": 0.3561, "step": 782 }, { "epoch": 3.171645569620253, "grad_norm": 0.33364565538570645, "learning_rate": 1.404681273201131e-05, "loss": 0.3821, "step": 783 }, { "epoch": 3.1756962025316455, "grad_norm": 0.32023147710515387, "learning_rate": 1.399265085197556e-05, "loss": 0.4021, "step": 784 }, { "epoch": 3.179746835443038, "grad_norm": 0.3229396282893938, "learning_rate": 1.393853735430398e-05, "loss": 0.3907, "step": 785 }, { "epoch": 3.1837974683544306, "grad_norm": 0.34279628554203295, "learning_rate": 1.3884472674819246e-05, "loss": 0.3604, "step": 786 }, { "epoch": 3.1878481012658226, "grad_norm": 0.3660381556593123, "learning_rate": 1.3830457248950864e-05, "loss": 0.4088, "step": 787 }, { "epoch": 3.191898734177215, "grad_norm": 0.31553017364493824, "learning_rate": 1.377649151173163e-05, "loss": 0.3786, "step": 788 }, { "epoch": 3.1959493670886077, "grad_norm": 0.33541640730229527, "learning_rate": 1.3722575897794181e-05, "loss": 0.3836, "step": 789 }, { "epoch": 3.2, "grad_norm": 0.29229700770018086, "learning_rate": 1.3668710841367472e-05, "loss": 0.3589, "step": 790 }, { "epoch": 3.2040506329113922, "grad_norm": 0.3382268044904535, "learning_rate": 1.361489677627324e-05, "loss": 0.3996, "step": 791 }, { "epoch": 3.2081012658227848, "grad_norm": 0.342731224402649, "learning_rate": 1.3561134135922585e-05, "loss": 0.3812, "step": 792 }, { "epoch": 3.2121518987341773, "grad_norm": 0.2923382705667686, "learning_rate": 1.350742335331241e-05, "loss": 0.362, "step": 793 }, { "epoch": 3.21620253164557, "grad_norm": 0.3344498019735593, "learning_rate": 1.345376486102198e-05, "loss": 0.3803, "step": 794 }, { "epoch": 3.220253164556962, "grad_norm": 0.3172074260558831, "learning_rate": 1.3400159091209414e-05, "loss": 0.3778, "step": 795 }, { "epoch": 3.2243037974683544, "grad_norm": 0.31279153930671505, "learning_rate": 1.3346606475608216e-05, "loss": 0.3885, "step": 796 }, { "epoch": 3.228354430379747, "grad_norm": 0.35572434021101823, "learning_rate": 1.3293107445523781e-05, "loss": 0.3868, "step": 797 }, { "epoch": 3.2324050632911394, "grad_norm": 0.32878080777539753, "learning_rate": 1.3239662431829949e-05, "loss": 0.3859, "step": 798 }, { "epoch": 3.2364556962025315, "grad_norm": 0.3475095770180374, "learning_rate": 1.3186271864965509e-05, "loss": 0.375, "step": 799 }, { "epoch": 3.240506329113924, "grad_norm": 0.32082015441492445, "learning_rate": 1.3132936174930756e-05, "loss": 0.36, "step": 800 }, { "epoch": 3.2445569620253165, "grad_norm": 0.32061379174284754, "learning_rate": 1.3079655791283995e-05, "loss": 0.3928, "step": 801 }, { "epoch": 3.248607594936709, "grad_norm": 0.32980416289653064, "learning_rate": 1.3026431143138108e-05, "loss": 0.3989, "step": 802 }, { "epoch": 3.252658227848101, "grad_norm": 0.33501940986383577, "learning_rate": 1.2973262659157114e-05, "loss": 0.3822, "step": 803 }, { "epoch": 3.2567088607594936, "grad_norm": 0.3168964791340219, "learning_rate": 1.2920150767552651e-05, "loss": 0.3813, "step": 804 }, { "epoch": 3.260759493670886, "grad_norm": 0.30243389005885074, "learning_rate": 1.2867095896080607e-05, "loss": 0.3641, "step": 805 }, { "epoch": 3.2648101265822786, "grad_norm": 0.3141077271462181, "learning_rate": 1.2814098472037612e-05, "loss": 0.3914, "step": 806 }, { "epoch": 3.2688607594936707, "grad_norm": 0.3463800807618216, "learning_rate": 1.276115892225764e-05, "loss": 0.4135, "step": 807 }, { "epoch": 3.2729113924050632, "grad_norm": 0.32747552099141775, "learning_rate": 1.2708277673108555e-05, "loss": 0.389, "step": 808 }, { "epoch": 3.2769620253164558, "grad_norm": 0.3079315164324747, "learning_rate": 1.2655455150488649e-05, "loss": 0.3906, "step": 809 }, { "epoch": 3.2810126582278483, "grad_norm": 0.325676373780002, "learning_rate": 1.2602691779823272e-05, "loss": 0.394, "step": 810 }, { "epoch": 3.2850632911392403, "grad_norm": 0.29234129544647575, "learning_rate": 1.2549987986061355e-05, "loss": 0.3429, "step": 811 }, { "epoch": 3.289113924050633, "grad_norm": 0.3323372820144752, "learning_rate": 1.2497344193672005e-05, "loss": 0.3987, "step": 812 }, { "epoch": 3.2931645569620254, "grad_norm": 0.31819505126575326, "learning_rate": 1.2444760826641092e-05, "loss": 0.3808, "step": 813 }, { "epoch": 3.297215189873418, "grad_norm": 0.3268536149017938, "learning_rate": 1.2392238308467817e-05, "loss": 0.3663, "step": 814 }, { "epoch": 3.30126582278481, "grad_norm": 0.32877320570252744, "learning_rate": 1.2339777062161326e-05, "loss": 0.4149, "step": 815 }, { "epoch": 3.3053164556962025, "grad_norm": 0.2834982383975248, "learning_rate": 1.2287377510237293e-05, "loss": 0.3429, "step": 816 }, { "epoch": 3.309367088607595, "grad_norm": 0.35838591958778304, "learning_rate": 1.2235040074714488e-05, "loss": 0.3848, "step": 817 }, { "epoch": 3.3134177215189875, "grad_norm": 0.34357210169099733, "learning_rate": 1.2182765177111434e-05, "loss": 0.4073, "step": 818 }, { "epoch": 3.3174683544303796, "grad_norm": 0.3173378422124111, "learning_rate": 1.213055323844297e-05, "loss": 0.3695, "step": 819 }, { "epoch": 3.321518987341772, "grad_norm": 0.34229798478138634, "learning_rate": 1.2078404679216864e-05, "loss": 0.39, "step": 820 }, { "epoch": 3.3255696202531646, "grad_norm": 0.29216046240814814, "learning_rate": 1.2026319919430458e-05, "loss": 0.3686, "step": 821 }, { "epoch": 3.329620253164557, "grad_norm": 0.30336568813848563, "learning_rate": 1.1974299378567227e-05, "loss": 0.3666, "step": 822 }, { "epoch": 3.333670886075949, "grad_norm": 0.31783243155591484, "learning_rate": 1.1922343475593462e-05, "loss": 0.3851, "step": 823 }, { "epoch": 3.3377215189873417, "grad_norm": 0.31545830750924203, "learning_rate": 1.187045262895488e-05, "loss": 0.365, "step": 824 }, { "epoch": 3.3417721518987342, "grad_norm": 0.30754674564720114, "learning_rate": 1.1818627256573203e-05, "loss": 0.3989, "step": 825 }, { "epoch": 3.3458227848101267, "grad_norm": 0.3093689662698597, "learning_rate": 1.1766867775842864e-05, "loss": 0.3728, "step": 826 }, { "epoch": 3.349873417721519, "grad_norm": 0.3477259610678054, "learning_rate": 1.1715174603627615e-05, "loss": 0.3779, "step": 827 }, { "epoch": 3.3539240506329113, "grad_norm": 0.33645137929370844, "learning_rate": 1.1663548156257147e-05, "loss": 0.4077, "step": 828 }, { "epoch": 3.357974683544304, "grad_norm": 0.3391580797132643, "learning_rate": 1.161198884952377e-05, "loss": 0.3859, "step": 829 }, { "epoch": 3.3620253164556964, "grad_norm": 0.3004918741660032, "learning_rate": 1.1560497098679056e-05, "loss": 0.3657, "step": 830 }, { "epoch": 3.3660759493670884, "grad_norm": 0.32100525074686037, "learning_rate": 1.1509073318430479e-05, "loss": 0.3749, "step": 831 }, { "epoch": 3.370126582278481, "grad_norm": 0.3429571639264182, "learning_rate": 1.1457717922938116e-05, "loss": 0.4042, "step": 832 }, { "epoch": 3.3741772151898735, "grad_norm": 0.2864118805460335, "learning_rate": 1.1406431325811233e-05, "loss": 0.3582, "step": 833 }, { "epoch": 3.378227848101266, "grad_norm": 0.34971387218827665, "learning_rate": 1.135521394010506e-05, "loss": 0.4134, "step": 834 }, { "epoch": 3.382278481012658, "grad_norm": 0.3177449267682754, "learning_rate": 1.1304066178317367e-05, "loss": 0.3462, "step": 835 }, { "epoch": 3.3863291139240506, "grad_norm": 0.32713109848306715, "learning_rate": 1.1252988452385199e-05, "loss": 0.397, "step": 836 }, { "epoch": 3.390379746835443, "grad_norm": 0.339968523368515, "learning_rate": 1.1201981173681536e-05, "loss": 0.3898, "step": 837 }, { "epoch": 3.3944303797468356, "grad_norm": 0.32020276714962437, "learning_rate": 1.1151044753011991e-05, "loss": 0.3807, "step": 838 }, { "epoch": 3.3984810126582277, "grad_norm": 0.35039829805075634, "learning_rate": 1.1100179600611491e-05, "loss": 0.419, "step": 839 }, { "epoch": 3.40253164556962, "grad_norm": 0.32900205401246824, "learning_rate": 1.1049386126140985e-05, "loss": 0.3653, "step": 840 }, { "epoch": 3.4065822784810127, "grad_norm": 0.3235353398054543, "learning_rate": 1.0998664738684128e-05, "loss": 0.3666, "step": 841 }, { "epoch": 3.410632911392405, "grad_norm": 0.346813352756252, "learning_rate": 1.0948015846744e-05, "loss": 0.3963, "step": 842 }, { "epoch": 3.4146835443037973, "grad_norm": 0.31280017528506276, "learning_rate": 1.0897439858239832e-05, "loss": 0.3615, "step": 843 }, { "epoch": 3.41873417721519, "grad_norm": 0.3399225387662564, "learning_rate": 1.0846937180503652e-05, "loss": 0.3897, "step": 844 }, { "epoch": 3.4227848101265823, "grad_norm": 0.32389372086767293, "learning_rate": 1.0796508220277117e-05, "loss": 0.3884, "step": 845 }, { "epoch": 3.426835443037975, "grad_norm": 0.29983217588311123, "learning_rate": 1.0746153383708107e-05, "loss": 0.3804, "step": 846 }, { "epoch": 3.430886075949367, "grad_norm": 0.3053449103989314, "learning_rate": 1.0695873076347579e-05, "loss": 0.389, "step": 847 }, { "epoch": 3.4349367088607594, "grad_norm": 0.3384504447523181, "learning_rate": 1.0645667703146205e-05, "loss": 0.386, "step": 848 }, { "epoch": 3.438987341772152, "grad_norm": 0.31371983696098965, "learning_rate": 1.0595537668451161e-05, "loss": 0.3745, "step": 849 }, { "epoch": 3.4430379746835444, "grad_norm": 0.3146580103322715, "learning_rate": 1.0545483376002854e-05, "loss": 0.3761, "step": 850 }, { "epoch": 3.4470886075949365, "grad_norm": 0.3373459636409347, "learning_rate": 1.0495505228931676e-05, "loss": 0.4056, "step": 851 }, { "epoch": 3.451139240506329, "grad_norm": 0.31702114454227415, "learning_rate": 1.044560362975474e-05, "loss": 0.3713, "step": 852 }, { "epoch": 3.4551898734177215, "grad_norm": 0.31274880326685883, "learning_rate": 1.0395778980372695e-05, "loss": 0.3967, "step": 853 }, { "epoch": 3.459240506329114, "grad_norm": 0.2979640266339792, "learning_rate": 1.0346031682066381e-05, "loss": 0.3477, "step": 854 }, { "epoch": 3.463291139240506, "grad_norm": 0.3337061904099551, "learning_rate": 1.0296362135493724e-05, "loss": 0.417, "step": 855 }, { "epoch": 3.4673417721518986, "grad_norm": 0.2866720679776003, "learning_rate": 1.0246770740686422e-05, "loss": 0.3783, "step": 856 }, { "epoch": 3.471392405063291, "grad_norm": 0.32159565699279885, "learning_rate": 1.0197257897046743e-05, "loss": 0.3992, "step": 857 }, { "epoch": 3.4754430379746837, "grad_norm": 0.32835109610787283, "learning_rate": 1.014782400334433e-05, "loss": 0.3947, "step": 858 }, { "epoch": 3.479493670886076, "grad_norm": 0.2837967279432517, "learning_rate": 1.009846945771296e-05, "loss": 0.3516, "step": 859 }, { "epoch": 3.4835443037974683, "grad_norm": 0.3478498231532301, "learning_rate": 1.0049194657647363e-05, "loss": 0.4114, "step": 860 }, { "epoch": 3.487594936708861, "grad_norm": 0.3026439406099569, "learning_rate": 1.0000000000000006e-05, "loss": 0.3825, "step": 861 }, { "epoch": 3.4916455696202533, "grad_norm": 0.3065597713825451, "learning_rate": 9.950885880977891e-06, "loss": 0.365, "step": 862 }, { "epoch": 3.4956962025316454, "grad_norm": 0.3015621273443233, "learning_rate": 9.901852696139382e-06, "loss": 0.3818, "step": 863 }, { "epoch": 3.499746835443038, "grad_norm": 0.30471749087517297, "learning_rate": 9.852900840391027e-06, "loss": 0.3898, "step": 864 }, { "epoch": 3.5037974683544304, "grad_norm": 0.29841191730681343, "learning_rate": 9.804030707984313e-06, "loss": 0.3688, "step": 865 }, { "epoch": 3.507848101265823, "grad_norm": 0.3355359125109627, "learning_rate": 9.755242692512599e-06, "loss": 0.3941, "step": 866 }, { "epoch": 3.5118987341772154, "grad_norm": 0.33587041093365316, "learning_rate": 9.70653718690782e-06, "loss": 0.3913, "step": 867 }, { "epoch": 3.5159493670886075, "grad_norm": 0.3324518183613984, "learning_rate": 9.657914583437454e-06, "loss": 0.3695, "step": 868 }, { "epoch": 3.52, "grad_norm": 0.29661334409790585, "learning_rate": 9.609375273701246e-06, "loss": 0.3866, "step": 869 }, { "epoch": 3.5240506329113925, "grad_norm": 0.30627413385214736, "learning_rate": 9.560919648628133e-06, "loss": 0.3743, "step": 870 }, { "epoch": 3.5281012658227846, "grad_norm": 0.3150597442069357, "learning_rate": 9.512548098473047e-06, "loss": 0.3833, "step": 871 }, { "epoch": 3.532151898734177, "grad_norm": 0.3015056602971135, "learning_rate": 9.464261012813825e-06, "loss": 0.3915, "step": 872 }, { "epoch": 3.5362025316455696, "grad_norm": 0.3079456005919427, "learning_rate": 9.416058780547987e-06, "loss": 0.408, "step": 873 }, { "epoch": 3.540253164556962, "grad_norm": 0.28763145959479297, "learning_rate": 9.367941789889714e-06, "loss": 0.3653, "step": 874 }, { "epoch": 3.5443037974683547, "grad_norm": 0.3157650550225521, "learning_rate": 9.319910428366607e-06, "loss": 0.3845, "step": 875 }, { "epoch": 3.5483544303797467, "grad_norm": 0.29435554063129976, "learning_rate": 9.271965082816667e-06, "loss": 0.3954, "step": 876 }, { "epoch": 3.5524050632911393, "grad_norm": 0.2851998966332392, "learning_rate": 9.224106139385111e-06, "loss": 0.3748, "step": 877 }, { "epoch": 3.5564556962025318, "grad_norm": 0.28070478322111214, "learning_rate": 9.176333983521291e-06, "loss": 0.362, "step": 878 }, { "epoch": 3.560506329113924, "grad_norm": 0.3146999402103096, "learning_rate": 9.12864899997558e-06, "loss": 0.3955, "step": 879 }, { "epoch": 3.5645569620253164, "grad_norm": 0.2912252161894346, "learning_rate": 9.08105157279628e-06, "loss": 0.3778, "step": 880 }, { "epoch": 3.568607594936709, "grad_norm": 0.2958284576820089, "learning_rate": 9.03354208532653e-06, "loss": 0.3763, "step": 881 }, { "epoch": 3.5726582278481014, "grad_norm": 0.28299515431920763, "learning_rate": 8.986120920201205e-06, "loss": 0.3806, "step": 882 }, { "epoch": 3.576708860759494, "grad_norm": 0.3070384442899086, "learning_rate": 8.938788459343852e-06, "loss": 0.4031, "step": 883 }, { "epoch": 3.580759493670886, "grad_norm": 0.2951450976867777, "learning_rate": 8.8915450839636e-06, "loss": 0.3779, "step": 884 }, { "epoch": 3.5848101265822785, "grad_norm": 0.29024185210681724, "learning_rate": 8.844391174552116e-06, "loss": 0.3813, "step": 885 }, { "epoch": 3.588860759493671, "grad_norm": 0.28588910374148474, "learning_rate": 8.797327110880479e-06, "loss": 0.3717, "step": 886 }, { "epoch": 3.592911392405063, "grad_norm": 0.3129824451487225, "learning_rate": 8.750353271996206e-06, "loss": 0.3941, "step": 887 }, { "epoch": 3.5969620253164556, "grad_norm": 0.29257904492828535, "learning_rate": 8.703470036220132e-06, "loss": 0.3692, "step": 888 }, { "epoch": 3.601012658227848, "grad_norm": 0.3309151433217031, "learning_rate": 8.656677781143394e-06, "loss": 0.4147, "step": 889 }, { "epoch": 3.6050632911392406, "grad_norm": 0.27942171809753985, "learning_rate": 8.609976883624377e-06, "loss": 0.3633, "step": 890 }, { "epoch": 3.609113924050633, "grad_norm": 0.30777588503022874, "learning_rate": 8.563367719785698e-06, "loss": 0.3746, "step": 891 }, { "epoch": 3.613164556962025, "grad_norm": 0.29302163789937863, "learning_rate": 8.516850665011138e-06, "loss": 0.3806, "step": 892 }, { "epoch": 3.6172151898734177, "grad_norm": 0.2812088379286749, "learning_rate": 8.47042609394269e-06, "loss": 0.3764, "step": 893 }, { "epoch": 3.6212658227848102, "grad_norm": 0.29830572312518755, "learning_rate": 8.424094380477432e-06, "loss": 0.3885, "step": 894 }, { "epoch": 3.6253164556962023, "grad_norm": 0.32065684946747597, "learning_rate": 8.37785589776465e-06, "loss": 0.3731, "step": 895 }, { "epoch": 3.629367088607595, "grad_norm": 0.2823300891240847, "learning_rate": 8.331711018202694e-06, "loss": 0.4005, "step": 896 }, { "epoch": 3.6334177215189873, "grad_norm": 0.27997715554337826, "learning_rate": 8.285660113436104e-06, "loss": 0.3692, "step": 897 }, { "epoch": 3.63746835443038, "grad_norm": 0.32693135967255127, "learning_rate": 8.239703554352527e-06, "loss": 0.3989, "step": 898 }, { "epoch": 3.6415189873417724, "grad_norm": 0.2850507014740402, "learning_rate": 8.193841711079775e-06, "loss": 0.3417, "step": 899 }, { "epoch": 3.6455696202531644, "grad_norm": 0.30912742552981465, "learning_rate": 8.148074952982828e-06, "loss": 0.4087, "step": 900 }, { "epoch": 3.649620253164557, "grad_norm": 0.29367159435744544, "learning_rate": 8.102403648660859e-06, "loss": 0.3617, "step": 901 }, { "epoch": 3.6536708860759495, "grad_norm": 0.30952782484312596, "learning_rate": 8.056828165944282e-06, "loss": 0.4173, "step": 902 }, { "epoch": 3.6577215189873415, "grad_norm": 0.28453450622740345, "learning_rate": 8.011348871891762e-06, "loss": 0.359, "step": 903 }, { "epoch": 3.661772151898734, "grad_norm": 0.31299055766450307, "learning_rate": 7.965966132787287e-06, "loss": 0.3886, "step": 904 }, { "epoch": 3.6658227848101266, "grad_norm": 0.27535699697578436, "learning_rate": 7.920680314137189e-06, "loss": 0.3879, "step": 905 }, { "epoch": 3.669873417721519, "grad_norm": 0.30644956672963763, "learning_rate": 7.875491780667246e-06, "loss": 0.3813, "step": 906 }, { "epoch": 3.6739240506329116, "grad_norm": 0.28498857310111086, "learning_rate": 7.830400896319667e-06, "loss": 0.3802, "step": 907 }, { "epoch": 3.6779746835443037, "grad_norm": 0.2763059863546663, "learning_rate": 7.785408024250259e-06, "loss": 0.3784, "step": 908 }, { "epoch": 3.682025316455696, "grad_norm": 0.32197667585087697, "learning_rate": 7.74051352682542e-06, "loss": 0.3992, "step": 909 }, { "epoch": 3.6860759493670887, "grad_norm": 0.2906448091597364, "learning_rate": 7.695717765619257e-06, "loss": 0.3604, "step": 910 }, { "epoch": 3.690126582278481, "grad_norm": 0.2870967936326908, "learning_rate": 7.651021101410673e-06, "loss": 0.3763, "step": 911 }, { "epoch": 3.6941772151898733, "grad_norm": 0.33746570043550644, "learning_rate": 7.606423894180464e-06, "loss": 0.3941, "step": 912 }, { "epoch": 3.698227848101266, "grad_norm": 0.2881614727312123, "learning_rate": 7.56192650310839e-06, "loss": 0.365, "step": 913 }, { "epoch": 3.7022784810126583, "grad_norm": 0.29625423884625385, "learning_rate": 7.517529286570349e-06, "loss": 0.3767, "step": 914 }, { "epoch": 3.706329113924051, "grad_norm": 0.31850605566329576, "learning_rate": 7.473232602135387e-06, "loss": 0.3831, "step": 915 }, { "epoch": 3.710379746835443, "grad_norm": 0.31113421146861875, "learning_rate": 7.429036806562935e-06, "loss": 0.3937, "step": 916 }, { "epoch": 3.7144303797468354, "grad_norm": 0.28172021099601424, "learning_rate": 7.3849422557998455e-06, "loss": 0.3603, "step": 917 }, { "epoch": 3.718481012658228, "grad_norm": 0.30508255753361235, "learning_rate": 7.340949304977567e-06, "loss": 0.3675, "step": 918 }, { "epoch": 3.72253164556962, "grad_norm": 0.2947352848459537, "learning_rate": 7.297058308409282e-06, "loss": 0.3636, "step": 919 }, { "epoch": 3.7265822784810125, "grad_norm": 0.3055065164176725, "learning_rate": 7.25326961958704e-06, "loss": 0.4071, "step": 920 }, { "epoch": 3.730632911392405, "grad_norm": 0.33387570293506036, "learning_rate": 7.209583591178921e-06, "loss": 0.403, "step": 921 }, { "epoch": 3.7346835443037976, "grad_norm": 0.2851924550341593, "learning_rate": 7.1660005750261925e-06, "loss": 0.3618, "step": 922 }, { "epoch": 3.73873417721519, "grad_norm": 0.3053137106941311, "learning_rate": 7.1225209221404765e-06, "loss": 0.4088, "step": 923 }, { "epoch": 3.742784810126582, "grad_norm": 0.29813488476732897, "learning_rate": 7.079144982700909e-06, "loss": 0.3729, "step": 924 }, { "epoch": 3.7468354430379747, "grad_norm": 0.2753381962434218, "learning_rate": 7.0358731060513695e-06, "loss": 0.3646, "step": 925 }, { "epoch": 3.750886075949367, "grad_norm": 0.2955691609027648, "learning_rate": 6.99270564069757e-06, "loss": 0.4033, "step": 926 }, { "epoch": 3.7549367088607593, "grad_norm": 0.2942831317474174, "learning_rate": 6.949642934304375e-06, "loss": 0.3525, "step": 927 }, { "epoch": 3.7589873417721518, "grad_norm": 0.29472494248185294, "learning_rate": 6.906685333692871e-06, "loss": 0.4096, "step": 928 }, { "epoch": 3.7630379746835443, "grad_norm": 0.27504106404871365, "learning_rate": 6.86383318483769e-06, "loss": 0.378, "step": 929 }, { "epoch": 3.767088607594937, "grad_norm": 0.287496523118781, "learning_rate": 6.821086832864139e-06, "loss": 0.3797, "step": 930 }, { "epoch": 3.7711392405063293, "grad_norm": 0.30259687656539214, "learning_rate": 6.77844662204546e-06, "loss": 0.3683, "step": 931 }, { "epoch": 3.7751898734177214, "grad_norm": 0.28547826140204874, "learning_rate": 6.7359128958000455e-06, "loss": 0.3901, "step": 932 }, { "epoch": 3.779240506329114, "grad_norm": 0.3079638493423702, "learning_rate": 6.693485996688695e-06, "loss": 0.3969, "step": 933 }, { "epoch": 3.7832911392405064, "grad_norm": 0.2919778443094413, "learning_rate": 6.651166266411801e-06, "loss": 0.352, "step": 934 }, { "epoch": 3.7873417721518985, "grad_norm": 0.28497820496001836, "learning_rate": 6.6089540458066725e-06, "loss": 0.3638, "step": 935 }, { "epoch": 3.791392405063291, "grad_norm": 0.2896601786490366, "learning_rate": 6.566849674844711e-06, "loss": 0.399, "step": 936 }, { "epoch": 3.7954430379746835, "grad_norm": 0.3059594468885647, "learning_rate": 6.524853492628747e-06, "loss": 0.387, "step": 937 }, { "epoch": 3.799493670886076, "grad_norm": 0.2824532699310055, "learning_rate": 6.4829658373902536e-06, "loss": 0.3644, "step": 938 }, { "epoch": 3.8035443037974686, "grad_norm": 0.2822088249877316, "learning_rate": 6.441187046486648e-06, "loss": 0.3786, "step": 939 }, { "epoch": 3.8075949367088606, "grad_norm": 0.2730203061782244, "learning_rate": 6.399517456398567e-06, "loss": 0.3667, "step": 940 }, { "epoch": 3.811645569620253, "grad_norm": 0.28463973072399873, "learning_rate": 6.357957402727164e-06, "loss": 0.381, "step": 941 }, { "epoch": 3.8156962025316457, "grad_norm": 0.3132692082168306, "learning_rate": 6.316507220191395e-06, "loss": 0.3948, "step": 942 }, { "epoch": 3.8197468354430377, "grad_norm": 0.31586436693461944, "learning_rate": 6.275167242625331e-06, "loss": 0.3839, "step": 943 }, { "epoch": 3.8237974683544302, "grad_norm": 0.2989890996311846, "learning_rate": 6.233937802975471e-06, "loss": 0.3944, "step": 944 }, { "epoch": 3.8278481012658228, "grad_norm": 0.2752419366185577, "learning_rate": 6.192819233298046e-06, "loss": 0.3617, "step": 945 }, { "epoch": 3.8318987341772153, "grad_norm": 0.2939538511247147, "learning_rate": 6.151811864756383e-06, "loss": 0.387, "step": 946 }, { "epoch": 3.835949367088608, "grad_norm": 0.277183355688577, "learning_rate": 6.1109160276181655e-06, "loss": 0.355, "step": 947 }, { "epoch": 3.84, "grad_norm": 0.29168477842468393, "learning_rate": 6.070132051252868e-06, "loss": 0.3887, "step": 948 }, { "epoch": 3.8440506329113924, "grad_norm": 0.27851442782961444, "learning_rate": 6.0294602641290034e-06, "loss": 0.3609, "step": 949 }, { "epoch": 3.848101265822785, "grad_norm": 0.30010613265794334, "learning_rate": 5.988900993811575e-06, "loss": 0.3796, "step": 950 }, { "epoch": 3.852151898734177, "grad_norm": 0.28195132648368454, "learning_rate": 5.948454566959363e-06, "loss": 0.3732, "step": 951 }, { "epoch": 3.8562025316455695, "grad_norm": 0.28125537815020873, "learning_rate": 5.908121309322328e-06, "loss": 0.3943, "step": 952 }, { "epoch": 3.860253164556962, "grad_norm": 0.2882655679133461, "learning_rate": 5.867901545738976e-06, "loss": 0.3789, "step": 953 }, { "epoch": 3.8643037974683545, "grad_norm": 0.2789202545704935, "learning_rate": 5.827795600133774e-06, "loss": 0.3812, "step": 954 }, { "epoch": 3.868354430379747, "grad_norm": 0.27386452755941665, "learning_rate": 5.787803795514466e-06, "loss": 0.3712, "step": 955 }, { "epoch": 3.872405063291139, "grad_norm": 0.29339655803198056, "learning_rate": 5.747926453969576e-06, "loss": 0.4182, "step": 956 }, { "epoch": 3.8764556962025316, "grad_norm": 0.27601728696369837, "learning_rate": 5.708163896665708e-06, "loss": 0.3521, "step": 957 }, { "epoch": 3.880506329113924, "grad_norm": 0.2701977942758217, "learning_rate": 5.668516443845047e-06, "loss": 0.3599, "step": 958 }, { "epoch": 3.884556962025316, "grad_norm": 0.29315725910570817, "learning_rate": 5.6289844148227225e-06, "loss": 0.3856, "step": 959 }, { "epoch": 3.8886075949367087, "grad_norm": 0.2849611187268521, "learning_rate": 5.5895681279842615e-06, "loss": 0.3862, "step": 960 }, { "epoch": 3.8926582278481012, "grad_norm": 0.29097973968445073, "learning_rate": 5.550267900783019e-06, "loss": 0.3806, "step": 961 }, { "epoch": 3.8967088607594937, "grad_norm": 0.2778710956775842, "learning_rate": 5.511084049737623e-06, "loss": 0.386, "step": 962 }, { "epoch": 3.9007594936708863, "grad_norm": 0.29627385678752355, "learning_rate": 5.4720168904294215e-06, "loss": 0.385, "step": 963 }, { "epoch": 3.9048101265822783, "grad_norm": 0.30583488664103853, "learning_rate": 5.433066737499948e-06, "loss": 0.3831, "step": 964 }, { "epoch": 3.908860759493671, "grad_norm": 0.27234082915306085, "learning_rate": 5.394233904648376e-06, "loss": 0.3874, "step": 965 }, { "epoch": 3.9129113924050634, "grad_norm": 0.27590373458574396, "learning_rate": 5.355518704628997e-06, "loss": 0.3714, "step": 966 }, { "epoch": 3.9169620253164554, "grad_norm": 0.2829157921738668, "learning_rate": 5.316921449248731e-06, "loss": 0.3766, "step": 967 }, { "epoch": 3.921012658227848, "grad_norm": 0.3026130337912494, "learning_rate": 5.278442449364538e-06, "loss": 0.4129, "step": 968 }, { "epoch": 3.9250632911392405, "grad_norm": 0.274343868994269, "learning_rate": 5.240082014881016e-06, "loss": 0.3611, "step": 969 }, { "epoch": 3.929113924050633, "grad_norm": 0.2817698351786252, "learning_rate": 5.201840454747822e-06, "loss": 0.3694, "step": 970 }, { "epoch": 3.9331645569620255, "grad_norm": 0.3166382731698574, "learning_rate": 5.163718076957223e-06, "loss": 0.3923, "step": 971 }, { "epoch": 3.9372151898734176, "grad_norm": 0.29281840785395064, "learning_rate": 5.125715188541609e-06, "loss": 0.3593, "step": 972 }, { "epoch": 3.94126582278481, "grad_norm": 0.28254516237053184, "learning_rate": 5.087832095571021e-06, "loss": 0.408, "step": 973 }, { "epoch": 3.9453164556962026, "grad_norm": 0.29531121092563273, "learning_rate": 5.0500691031506766e-06, "loss": 0.3733, "step": 974 }, { "epoch": 3.9493670886075947, "grad_norm": 0.28994979032714047, "learning_rate": 5.01242651541854e-06, "loss": 0.3886, "step": 975 }, { "epoch": 3.953417721518987, "grad_norm": 0.28416390323445484, "learning_rate": 4.974904635542815e-06, "loss": 0.3823, "step": 976 }, { "epoch": 3.9574683544303797, "grad_norm": 0.263736889404555, "learning_rate": 4.937503765719582e-06, "loss": 0.3465, "step": 977 }, { "epoch": 3.961518987341772, "grad_norm": 0.2940985681156503, "learning_rate": 4.900224207170299e-06, "loss": 0.4132, "step": 978 }, { "epoch": 3.9655696202531647, "grad_norm": 0.30685461110297724, "learning_rate": 4.8630662601394065e-06, "loss": 0.3727, "step": 979 }, { "epoch": 3.969620253164557, "grad_norm": 0.27774919670187365, "learning_rate": 4.8260302238918995e-06, "loss": 0.3809, "step": 980 }, { "epoch": 3.9736708860759493, "grad_norm": 0.28245334334101985, "learning_rate": 4.789116396710924e-06, "loss": 0.3941, "step": 981 }, { "epoch": 3.977721518987342, "grad_norm": 0.26483030903882687, "learning_rate": 4.752325075895368e-06, "loss": 0.3445, "step": 982 }, { "epoch": 3.981772151898734, "grad_norm": 0.2985722414990917, "learning_rate": 4.715656557757473e-06, "loss": 0.4081, "step": 983 }, { "epoch": 3.9858227848101264, "grad_norm": 0.2778022928514926, "learning_rate": 4.679111137620442e-06, "loss": 0.3695, "step": 984 }, { "epoch": 3.989873417721519, "grad_norm": 0.28431360241462017, "learning_rate": 4.6426891098160585e-06, "loss": 0.377, "step": 985 }, { "epoch": 3.9939240506329114, "grad_norm": 0.29745746718950045, "learning_rate": 4.6063907676823474e-06, "loss": 0.3849, "step": 986 }, { "epoch": 3.997974683544304, "grad_norm": 0.31400479884751115, "learning_rate": 4.570216403561141e-06, "loss": 0.405, "step": 987 }, { "epoch": 4.002025316455696, "grad_norm": 0.3708129654224815, "learning_rate": 4.534166308795815e-06, "loss": 0.358, "step": 988 }, { "epoch": 4.006075949367089, "grad_norm": 0.47536270726922525, "learning_rate": 4.498240773728859e-06, "loss": 0.3446, "step": 989 }, { "epoch": 4.010126582278481, "grad_norm": 0.3807781576704854, "learning_rate": 4.462440087699609e-06, "loss": 0.2842, "step": 990 }, { "epoch": 4.014177215189873, "grad_norm": 0.31577215810493114, "learning_rate": 4.426764539041861e-06, "loss": 0.3355, "step": 991 }, { "epoch": 4.018227848101266, "grad_norm": 0.37750443311745835, "learning_rate": 4.391214415081582e-06, "loss": 0.3194, "step": 992 }, { "epoch": 4.022278481012658, "grad_norm": 0.5092343941307169, "learning_rate": 4.355790002134579e-06, "loss": 0.3233, "step": 993 }, { "epoch": 4.02632911392405, "grad_norm": 0.476749502230546, "learning_rate": 4.320491585504207e-06, "loss": 0.2902, "step": 994 }, { "epoch": 4.030379746835443, "grad_norm": 0.4189482338030652, "learning_rate": 4.2853194494790615e-06, "loss": 0.3352, "step": 995 }, { "epoch": 4.034430379746835, "grad_norm": 0.33900139633585413, "learning_rate": 4.250273877330691e-06, "loss": 0.3014, "step": 996 }, { "epoch": 4.038481012658228, "grad_norm": 0.37695794807189287, "learning_rate": 4.215355151311313e-06, "loss": 0.3309, "step": 997 }, { "epoch": 4.04253164556962, "grad_norm": 0.38267860147355903, "learning_rate": 4.180563552651542e-06, "loss": 0.3118, "step": 998 }, { "epoch": 4.046582278481012, "grad_norm": 0.40427890552905704, "learning_rate": 4.145899361558147e-06, "loss": 0.3154, "step": 999 }, { "epoch": 4.050632911392405, "grad_norm": 0.33969846620130784, "learning_rate": 4.111362857211738e-06, "loss": 0.2956, "step": 1000 }, { "epoch": 4.054683544303797, "grad_norm": 0.3514658993281177, "learning_rate": 4.076954317764592e-06, "loss": 0.3397, "step": 1001 }, { "epoch": 4.0587341772151895, "grad_norm": 0.35687011568817273, "learning_rate": 4.042674020338335e-06, "loss": 0.3059, "step": 1002 }, { "epoch": 4.062784810126582, "grad_norm": 0.36290086057343274, "learning_rate": 4.0085222410217835e-06, "loss": 0.3045, "step": 1003 }, { "epoch": 4.0668354430379745, "grad_norm": 0.37308593716412486, "learning_rate": 3.974499254868674e-06, "loss": 0.3201, "step": 1004 }, { "epoch": 4.0708860759493675, "grad_norm": 0.33575723554398734, "learning_rate": 3.940605335895451e-06, "loss": 0.3118, "step": 1005 }, { "epoch": 4.0749367088607595, "grad_norm": 0.3500147007928206, "learning_rate": 3.90684075707908e-06, "loss": 0.3291, "step": 1006 }, { "epoch": 4.078987341772152, "grad_norm": 0.3125560851295687, "learning_rate": 3.8732057903548505e-06, "loss": 0.2899, "step": 1007 }, { "epoch": 4.083037974683545, "grad_norm": 0.3442192445312139, "learning_rate": 3.8397007066141375e-06, "loss": 0.3212, "step": 1008 }, { "epoch": 4.087088607594937, "grad_norm": 0.32259652440828457, "learning_rate": 3.806325775702304e-06, "loss": 0.3231, "step": 1009 }, { "epoch": 4.091139240506329, "grad_norm": 0.29856402016597, "learning_rate": 3.773081266416434e-06, "loss": 0.3061, "step": 1010 }, { "epoch": 4.095189873417722, "grad_norm": 0.31950238442999757, "learning_rate": 3.739967446503245e-06, "loss": 0.3117, "step": 1011 }, { "epoch": 4.099240506329114, "grad_norm": 0.3200780552248714, "learning_rate": 3.706984582656894e-06, "loss": 0.3279, "step": 1012 }, { "epoch": 4.103291139240507, "grad_norm": 0.30584108646456815, "learning_rate": 3.6741329405168237e-06, "loss": 0.3005, "step": 1013 }, { "epoch": 4.107341772151899, "grad_norm": 0.3101099194903966, "learning_rate": 3.641412784665648e-06, "loss": 0.3036, "step": 1014 }, { "epoch": 4.111392405063291, "grad_norm": 0.3226725771628949, "learning_rate": 3.608824378627005e-06, "loss": 0.343, "step": 1015 }, { "epoch": 4.115443037974684, "grad_norm": 0.3337086578270224, "learning_rate": 3.5763679848634337e-06, "loss": 0.321, "step": 1016 }, { "epoch": 4.119493670886076, "grad_norm": 0.29450557859657295, "learning_rate": 3.544043864774269e-06, "loss": 0.2959, "step": 1017 }, { "epoch": 4.123544303797468, "grad_norm": 0.28595405279753966, "learning_rate": 3.5118522786935282e-06, "loss": 0.3001, "step": 1018 }, { "epoch": 4.127594936708861, "grad_norm": 0.3139989432883553, "learning_rate": 3.479793485887819e-06, "loss": 0.3167, "step": 1019 }, { "epoch": 4.131645569620253, "grad_norm": 0.3232352182788352, "learning_rate": 3.4478677445542653e-06, "loss": 0.3052, "step": 1020 }, { "epoch": 4.135696202531646, "grad_norm": 0.3138908185846246, "learning_rate": 3.4160753118183767e-06, "loss": 0.3335, "step": 1021 }, { "epoch": 4.139746835443038, "grad_norm": 0.2927445913383231, "learning_rate": 3.3844164437320527e-06, "loss": 0.2914, "step": 1022 }, { "epoch": 4.14379746835443, "grad_norm": 0.31920440193796434, "learning_rate": 3.3528913952714558e-06, "loss": 0.3248, "step": 1023 }, { "epoch": 4.147848101265823, "grad_norm": 0.30657640202998776, "learning_rate": 3.321500420335e-06, "loss": 0.2956, "step": 1024 }, { "epoch": 4.151898734177215, "grad_norm": 0.3390017968161179, "learning_rate": 3.290243771741275e-06, "loss": 0.3398, "step": 1025 }, { "epoch": 4.155949367088607, "grad_norm": 0.302746946714378, "learning_rate": 3.2591217012270325e-06, "loss": 0.2972, "step": 1026 }, { "epoch": 4.16, "grad_norm": 0.29763931101375607, "learning_rate": 3.228134459445149e-06, "loss": 0.3058, "step": 1027 }, { "epoch": 4.164050632911392, "grad_norm": 0.2910135392008009, "learning_rate": 3.1972822959626205e-06, "loss": 0.3117, "step": 1028 }, { "epoch": 4.168101265822785, "grad_norm": 0.28983630777477376, "learning_rate": 3.166565459258513e-06, "loss": 0.3124, "step": 1029 }, { "epoch": 4.172151898734177, "grad_norm": 0.28271917235822325, "learning_rate": 3.1359841967220193e-06, "loss": 0.3009, "step": 1030 }, { "epoch": 4.176202531645569, "grad_norm": 0.28687123426775535, "learning_rate": 3.105538754650419e-06, "loss": 0.3141, "step": 1031 }, { "epoch": 4.180253164556962, "grad_norm": 0.29802788407639685, "learning_rate": 3.07522937824712e-06, "loss": 0.317, "step": 1032 }, { "epoch": 4.184303797468354, "grad_norm": 0.280792216418672, "learning_rate": 3.0450563116196697e-06, "loss": 0.3039, "step": 1033 }, { "epoch": 4.188354430379746, "grad_norm": 0.2965709957605698, "learning_rate": 3.0150197977778008e-06, "loss": 0.33, "step": 1034 }, { "epoch": 4.192405063291139, "grad_norm": 0.31522096560199026, "learning_rate": 2.985120078631465e-06, "loss": 0.3169, "step": 1035 }, { "epoch": 4.1964556962025314, "grad_norm": 0.3134455428750743, "learning_rate": 2.9553573949888893e-06, "loss": 0.3121, "step": 1036 }, { "epoch": 4.200506329113924, "grad_norm": 0.290326779592756, "learning_rate": 2.9257319865546384e-06, "loss": 0.3059, "step": 1037 }, { "epoch": 4.2045569620253165, "grad_norm": 0.29929060744658986, "learning_rate": 2.896244091927678e-06, "loss": 0.2998, "step": 1038 }, { "epoch": 4.2086075949367086, "grad_norm": 0.31356746530664414, "learning_rate": 2.8668939485994584e-06, "loss": 0.3335, "step": 1039 }, { "epoch": 4.2126582278481015, "grad_norm": 0.2952440661348538, "learning_rate": 2.837681792951994e-06, "loss": 0.3041, "step": 1040 }, { "epoch": 4.216708860759494, "grad_norm": 0.30051505402517853, "learning_rate": 2.808607860255981e-06, "loss": 0.3206, "step": 1041 }, { "epoch": 4.220759493670886, "grad_norm": 0.28104775860606557, "learning_rate": 2.7796723846688634e-06, "loss": 0.3058, "step": 1042 }, { "epoch": 4.224810126582279, "grad_norm": 0.2804541625198444, "learning_rate": 2.7508755992329937e-06, "loss": 0.3207, "step": 1043 }, { "epoch": 4.228860759493671, "grad_norm": 0.28918561129262155, "learning_rate": 2.722217735873718e-06, "loss": 0.3005, "step": 1044 }, { "epoch": 4.232911392405064, "grad_norm": 0.2938260145970656, "learning_rate": 2.6936990253975315e-06, "loss": 0.3247, "step": 1045 }, { "epoch": 4.236962025316456, "grad_norm": 0.28353948287662917, "learning_rate": 2.665319697490205e-06, "loss": 0.3121, "step": 1046 }, { "epoch": 4.241012658227848, "grad_norm": 0.28238127851398803, "learning_rate": 2.637079980714945e-06, "loss": 0.3138, "step": 1047 }, { "epoch": 4.245063291139241, "grad_norm": 0.2772178377698874, "learning_rate": 2.6089801025105453e-06, "loss": 0.3023, "step": 1048 }, { "epoch": 4.249113924050633, "grad_norm": 0.2834097690212246, "learning_rate": 2.581020289189571e-06, "loss": 0.3179, "step": 1049 }, { "epoch": 4.253164556962025, "grad_norm": 0.3057411435619533, "learning_rate": 2.553200765936501e-06, "loss": 0.3142, "step": 1050 }, { "epoch": 4.257215189873418, "grad_norm": 0.273382220271728, "learning_rate": 2.525521756805962e-06, "loss": 0.2953, "step": 1051 }, { "epoch": 4.26126582278481, "grad_norm": 0.3071591083907643, "learning_rate": 2.497983484720885e-06, "loss": 0.3452, "step": 1052 }, { "epoch": 4.265316455696203, "grad_norm": 0.2882748325110727, "learning_rate": 2.470586171470728e-06, "loss": 0.3186, "step": 1053 }, { "epoch": 4.269367088607595, "grad_norm": 0.27781894864985446, "learning_rate": 2.4433300377096836e-06, "loss": 0.3018, "step": 1054 }, { "epoch": 4.273417721518987, "grad_norm": 0.28724836587937147, "learning_rate": 2.4162153029549073e-06, "loss": 0.3149, "step": 1055 }, { "epoch": 4.27746835443038, "grad_norm": 0.28408316947785334, "learning_rate": 2.3892421855847458e-06, "loss": 0.2988, "step": 1056 }, { "epoch": 4.281518987341772, "grad_norm": 0.2893088234676635, "learning_rate": 2.362410902836978e-06, "loss": 0.296, "step": 1057 }, { "epoch": 4.285569620253165, "grad_norm": 0.29981125208906256, "learning_rate": 2.3357216708070653e-06, "loss": 0.3279, "step": 1058 }, { "epoch": 4.289620253164557, "grad_norm": 0.2974910230813767, "learning_rate": 2.309174704446411e-06, "loss": 0.3166, "step": 1059 }, { "epoch": 4.293670886075949, "grad_norm": 0.27926540795756677, "learning_rate": 2.2827702175606437e-06, "loss": 0.2891, "step": 1060 }, { "epoch": 4.297721518987342, "grad_norm": 0.28883495693660216, "learning_rate": 2.256508422807855e-06, "loss": 0.3158, "step": 1061 }, { "epoch": 4.301772151898734, "grad_norm": 0.2825915273169645, "learning_rate": 2.230389531696946e-06, "loss": 0.3006, "step": 1062 }, { "epoch": 4.305822784810126, "grad_norm": 0.2950564395689144, "learning_rate": 2.204413754585857e-06, "loss": 0.3431, "step": 1063 }, { "epoch": 4.309873417721519, "grad_norm": 0.2607151260102671, "learning_rate": 2.1785813006799406e-06, "loss": 0.2693, "step": 1064 }, { "epoch": 4.313924050632911, "grad_norm": 0.2971964795361232, "learning_rate": 2.1528923780302224e-06, "loss": 0.3288, "step": 1065 }, { "epoch": 4.317974683544303, "grad_norm": 0.28625527680294277, "learning_rate": 2.127347193531757e-06, "loss": 0.3194, "step": 1066 }, { "epoch": 4.322025316455696, "grad_norm": 0.28566209981818047, "learning_rate": 2.101945952921942e-06, "loss": 0.3238, "step": 1067 }, { "epoch": 4.326075949367088, "grad_norm": 0.2953087623879323, "learning_rate": 2.0766888607788906e-06, "loss": 0.3192, "step": 1068 }, { "epoch": 4.330126582278481, "grad_norm": 0.2783105306501893, "learning_rate": 2.0515761205197337e-06, "loss": 0.297, "step": 1069 }, { "epoch": 4.334177215189873, "grad_norm": 0.2794889548320566, "learning_rate": 2.0266079343990453e-06, "loss": 0.3086, "step": 1070 }, { "epoch": 4.3382278481012655, "grad_norm": 0.28078117691037024, "learning_rate": 2.0017845035071494e-06, "loss": 0.3099, "step": 1071 }, { "epoch": 4.3422784810126585, "grad_norm": 0.2833689465450994, "learning_rate": 1.9771060277685537e-06, "loss": 0.2984, "step": 1072 }, { "epoch": 4.3463291139240505, "grad_norm": 0.2980063448004615, "learning_rate": 1.95257270594031e-06, "loss": 0.3157, "step": 1073 }, { "epoch": 4.3503797468354435, "grad_norm": 0.284132878652653, "learning_rate": 1.9281847356104188e-06, "loss": 0.3297, "step": 1074 }, { "epoch": 4.3544303797468356, "grad_norm": 0.2621330050148234, "learning_rate": 1.9039423131962365e-06, "loss": 0.2877, "step": 1075 }, { "epoch": 4.358481012658228, "grad_norm": 0.277680310234056, "learning_rate": 1.8798456339429027e-06, "loss": 0.3072, "step": 1076 }, { "epoch": 4.362531645569621, "grad_norm": 0.2806127229552841, "learning_rate": 1.8558948919217612e-06, "loss": 0.3136, "step": 1077 }, { "epoch": 4.366582278481013, "grad_norm": 0.28259160212629203, "learning_rate": 1.8320902800287954e-06, "loss": 0.307, "step": 1078 }, { "epoch": 4.370632911392405, "grad_norm": 0.2908547702010183, "learning_rate": 1.8084319899830726e-06, "loss": 0.3085, "step": 1079 }, { "epoch": 4.374683544303798, "grad_norm": 0.2829875464023137, "learning_rate": 1.7849202123252097e-06, "loss": 0.3107, "step": 1080 }, { "epoch": 4.37873417721519, "grad_norm": 0.28247123051927236, "learning_rate": 1.7615551364158401e-06, "loss": 0.3143, "step": 1081 }, { "epoch": 4.382784810126582, "grad_norm": 0.2798599314776953, "learning_rate": 1.738336950434061e-06, "loss": 0.3051, "step": 1082 }, { "epoch": 4.386835443037975, "grad_norm": 0.291053443901299, "learning_rate": 1.715265841375957e-06, "loss": 0.3216, "step": 1083 }, { "epoch": 4.390886075949367, "grad_norm": 0.2768409697605248, "learning_rate": 1.6923419950530684e-06, "loss": 0.3025, "step": 1084 }, { "epoch": 4.39493670886076, "grad_norm": 0.29511195510726357, "learning_rate": 1.6695655960909008e-06, "loss": 0.3222, "step": 1085 }, { "epoch": 4.398987341772152, "grad_norm": 0.277058822737526, "learning_rate": 1.646936827927441e-06, "loss": 0.3066, "step": 1086 }, { "epoch": 4.403037974683544, "grad_norm": 0.2829117195070929, "learning_rate": 1.6244558728116766e-06, "loss": 0.3141, "step": 1087 }, { "epoch": 4.407088607594937, "grad_norm": 0.2626424463072873, "learning_rate": 1.6021229118021265e-06, "loss": 0.302, "step": 1088 }, { "epoch": 4.411139240506329, "grad_norm": 0.28880786169745415, "learning_rate": 1.5799381247653967e-06, "loss": 0.3158, "step": 1089 }, { "epoch": 4.415189873417722, "grad_norm": 0.2886721797825902, "learning_rate": 1.5579016903747013e-06, "loss": 0.3192, "step": 1090 }, { "epoch": 4.419240506329114, "grad_norm": 0.2942592641818175, "learning_rate": 1.5360137861084656e-06, "loss": 0.3188, "step": 1091 }, { "epoch": 4.423291139240506, "grad_norm": 0.2661127231946344, "learning_rate": 1.5142745882488475e-06, "loss": 0.2835, "step": 1092 }, { "epoch": 4.427341772151899, "grad_norm": 0.2827234824493419, "learning_rate": 1.4926842718803691e-06, "loss": 0.3333, "step": 1093 }, { "epoch": 4.431392405063291, "grad_norm": 0.2835080076726211, "learning_rate": 1.4712430108884657e-06, "loss": 0.2951, "step": 1094 }, { "epoch": 4.435443037974683, "grad_norm": 0.2919156893136523, "learning_rate": 1.4499509779581078e-06, "loss": 0.3204, "step": 1095 }, { "epoch": 4.439493670886076, "grad_norm": 0.29141994406101507, "learning_rate": 1.4288083445723988e-06, "loss": 0.3248, "step": 1096 }, { "epoch": 4.443544303797468, "grad_norm": 0.2641038580329077, "learning_rate": 1.4078152810112045e-06, "loss": 0.286, "step": 1097 }, { "epoch": 4.44759493670886, "grad_norm": 0.28483223559952325, "learning_rate": 1.3869719563497697e-06, "loss": 0.3363, "step": 1098 }, { "epoch": 4.451645569620253, "grad_norm": 0.287028987604184, "learning_rate": 1.3662785384573663e-06, "loss": 0.3283, "step": 1099 }, { "epoch": 4.455696202531645, "grad_norm": 0.28353805311680397, "learning_rate": 1.3457351939959383e-06, "loss": 0.2888, "step": 1100 }, { "epoch": 4.459746835443038, "grad_norm": 0.29366835913742934, "learning_rate": 1.3253420884187551e-06, "loss": 0.3178, "step": 1101 }, { "epoch": 4.46379746835443, "grad_norm": 0.28531633843976567, "learning_rate": 1.3050993859690953e-06, "loss": 0.3345, "step": 1102 }, { "epoch": 4.467848101265822, "grad_norm": 0.27351097689531395, "learning_rate": 1.2850072496788869e-06, "loss": 0.3099, "step": 1103 }, { "epoch": 4.471898734177215, "grad_norm": 0.27786782771027085, "learning_rate": 1.2650658413674434e-06, "loss": 0.32, "step": 1104 }, { "epoch": 4.4759493670886075, "grad_norm": 0.2714512551923189, "learning_rate": 1.2452753216401226e-06, "loss": 0.3252, "step": 1105 }, { "epoch": 4.48, "grad_norm": 0.2610507151013288, "learning_rate": 1.2256358498870503e-06, "loss": 0.2763, "step": 1106 }, { "epoch": 4.4840506329113925, "grad_norm": 0.2814294594034428, "learning_rate": 1.2061475842818337e-06, "loss": 0.3149, "step": 1107 }, { "epoch": 4.488101265822785, "grad_norm": 0.2868090244238883, "learning_rate": 1.1868106817802816e-06, "loss": 0.3164, "step": 1108 }, { "epoch": 4.4921518987341775, "grad_norm": 0.26284469738306504, "learning_rate": 1.1676252981191482e-06, "loss": 0.2956, "step": 1109 }, { "epoch": 4.49620253164557, "grad_norm": 0.29417223949851545, "learning_rate": 1.1485915878148823e-06, "loss": 0.339, "step": 1110 }, { "epoch": 4.500253164556962, "grad_norm": 0.268981429103765, "learning_rate": 1.1297097041623584e-06, "loss": 0.3103, "step": 1111 }, { "epoch": 4.504303797468355, "grad_norm": 0.26744947260382557, "learning_rate": 1.1109797992336847e-06, "loss": 0.3139, "step": 1112 }, { "epoch": 4.508354430379747, "grad_norm": 0.2859512125388351, "learning_rate": 1.092402023876933e-06, "loss": 0.3252, "step": 1113 }, { "epoch": 4.512405063291139, "grad_norm": 0.29708205557439343, "learning_rate": 1.0739765277149527e-06, "loss": 0.3254, "step": 1114 }, { "epoch": 4.516455696202532, "grad_norm": 0.28956388016975915, "learning_rate": 1.0557034591441596e-06, "loss": 0.3189, "step": 1115 }, { "epoch": 4.520506329113924, "grad_norm": 0.2768341151451826, "learning_rate": 1.0375829653333324e-06, "loss": 0.3028, "step": 1116 }, { "epoch": 4.524556962025317, "grad_norm": 0.28884484071835537, "learning_rate": 1.0196151922224385e-06, "loss": 0.3304, "step": 1117 }, { "epoch": 4.528607594936709, "grad_norm": 0.27155237919305475, "learning_rate": 1.0018002845214526e-06, "loss": 0.3119, "step": 1118 }, { "epoch": 4.532658227848101, "grad_norm": 0.2870985186788924, "learning_rate": 9.841383857091947e-07, "loss": 0.319, "step": 1119 }, { "epoch": 4.536708860759494, "grad_norm": 0.272600094831932, "learning_rate": 9.666296380321616e-07, "loss": 0.2898, "step": 1120 }, { "epoch": 4.540759493670886, "grad_norm": 0.28786860885695104, "learning_rate": 9.492741825034124e-07, "loss": 0.3311, "step": 1121 }, { "epoch": 4.544810126582279, "grad_norm": 0.298033277175779, "learning_rate": 9.320721589013892e-07, "loss": 0.3301, "step": 1122 }, { "epoch": 4.548860759493671, "grad_norm": 0.27598399571344995, "learning_rate": 9.150237057688339e-07, "loss": 0.3037, "step": 1123 }, { "epoch": 4.552911392405063, "grad_norm": 0.2832589946898227, "learning_rate": 8.981289604116328e-07, "loss": 0.3088, "step": 1124 }, { "epoch": 4.556962025316456, "grad_norm": 0.2764257467071167, "learning_rate": 8.813880588977542e-07, "loss": 0.308, "step": 1125 }, { "epoch": 4.561012658227848, "grad_norm": 0.2908132420462898, "learning_rate": 8.648011360561126e-07, "loss": 0.3241, "step": 1126 }, { "epoch": 4.56506329113924, "grad_norm": 0.2920647076087745, "learning_rate": 8.483683254755037e-07, "loss": 0.3169, "step": 1127 }, { "epoch": 4.569113924050633, "grad_norm": 0.2767801628308843, "learning_rate": 8.320897595035227e-07, "loss": 0.3046, "step": 1128 }, { "epoch": 4.573164556962025, "grad_norm": 0.27492807321494733, "learning_rate": 8.159655692455093e-07, "loss": 0.3016, "step": 1129 }, { "epoch": 4.577215189873417, "grad_norm": 0.28840284862424875, "learning_rate": 7.999958845634648e-07, "loss": 0.339, "step": 1130 }, { "epoch": 4.58126582278481, "grad_norm": 0.28804639414963124, "learning_rate": 7.841808340750478e-07, "loss": 0.3131, "step": 1131 }, { "epoch": 4.585316455696202, "grad_norm": 0.2786998320807008, "learning_rate": 7.685205451524869e-07, "loss": 0.3143, "step": 1132 }, { "epoch": 4.589367088607595, "grad_norm": 0.2851534984626819, "learning_rate": 7.530151439216027e-07, "loss": 0.3021, "step": 1133 }, { "epoch": 4.593417721518987, "grad_norm": 0.27661533148737755, "learning_rate": 7.376647552607675e-07, "loss": 0.3083, "step": 1134 }, { "epoch": 4.597468354430379, "grad_norm": 0.2810375015116644, "learning_rate": 7.224695027998963e-07, "loss": 0.3266, "step": 1135 }, { "epoch": 4.601518987341772, "grad_norm": 0.27395643395164593, "learning_rate": 7.07429508919466e-07, "loss": 0.2997, "step": 1136 }, { "epoch": 4.605569620253164, "grad_norm": 0.2858795542360859, "learning_rate": 6.925448947495206e-07, "loss": 0.2901, "step": 1137 }, { "epoch": 4.609620253164557, "grad_norm": 0.29804269339980377, "learning_rate": 6.778157801686936e-07, "loss": 0.3231, "step": 1138 }, { "epoch": 4.613670886075949, "grad_norm": 0.28454366056320096, "learning_rate": 6.632422838032515e-07, "loss": 0.3062, "step": 1139 }, { "epoch": 4.6177215189873415, "grad_norm": 0.2761522061350989, "learning_rate": 6.488245230261281e-07, "loss": 0.3229, "step": 1140 }, { "epoch": 4.6217721518987345, "grad_norm": 0.282219125265452, "learning_rate": 6.345626139559868e-07, "loss": 0.3159, "step": 1141 }, { "epoch": 4.6258227848101265, "grad_norm": 0.2853030525000241, "learning_rate": 6.204566714562866e-07, "loss": 0.3215, "step": 1142 }, { "epoch": 4.629873417721519, "grad_norm": 0.27035305396063747, "learning_rate": 6.06506809134344e-07, "loss": 0.2936, "step": 1143 }, { "epoch": 4.633924050632912, "grad_norm": 0.28153645204185374, "learning_rate": 5.927131393404373e-07, "loss": 0.3222, "step": 1144 }, { "epoch": 4.637974683544304, "grad_norm": 0.27164856204121157, "learning_rate": 5.790757731668817e-07, "loss": 0.3129, "step": 1145 }, { "epoch": 4.642025316455696, "grad_norm": 0.27975969526643396, "learning_rate": 5.655948204471507e-07, "loss": 0.3205, "step": 1146 }, { "epoch": 4.646075949367089, "grad_norm": 0.27146703042484166, "learning_rate": 5.522703897549875e-07, "loss": 0.2982, "step": 1147 }, { "epoch": 4.650126582278481, "grad_norm": 0.2752604568166583, "learning_rate": 5.391025884035239e-07, "loss": 0.3091, "step": 1148 }, { "epoch": 4.654177215189874, "grad_norm": 0.2842593143859214, "learning_rate": 5.260915224444207e-07, "loss": 0.3299, "step": 1149 }, { "epoch": 4.658227848101266, "grad_norm": 0.27914189453242966, "learning_rate": 5.132372966670129e-07, "loss": 0.3227, "step": 1150 }, { "epoch": 4.662278481012658, "grad_norm": 0.26981159473005956, "learning_rate": 5.005400145974704e-07, "loss": 0.2997, "step": 1151 }, { "epoch": 4.666329113924051, "grad_norm": 0.27066060456834623, "learning_rate": 4.879997784979562e-07, "loss": 0.3236, "step": 1152 }, { "epoch": 4.670379746835443, "grad_norm": 0.26226176353584096, "learning_rate": 4.7561668936580984e-07, "loss": 0.3045, "step": 1153 }, { "epoch": 4.674430379746836, "grad_norm": 0.2817120838351469, "learning_rate": 4.6339084693272306e-07, "loss": 0.3269, "step": 1154 }, { "epoch": 4.678481012658228, "grad_norm": 0.27220877238191815, "learning_rate": 4.5132234966395847e-07, "loss": 0.3051, "step": 1155 }, { "epoch": 4.68253164556962, "grad_norm": 0.27205256544022965, "learning_rate": 4.3941129475752795e-07, "loss": 0.3058, "step": 1156 }, { "epoch": 4.686582278481013, "grad_norm": 0.2712482078186113, "learning_rate": 4.27657778143431e-07, "loss": 0.3136, "step": 1157 }, { "epoch": 4.690632911392405, "grad_norm": 0.2657113720336847, "learning_rate": 4.1606189448287757e-07, "loss": 0.2934, "step": 1158 }, { "epoch": 4.694683544303797, "grad_norm": 0.28292180823807733, "learning_rate": 4.046237371675177e-07, "loss": 0.3338, "step": 1159 }, { "epoch": 4.69873417721519, "grad_norm": 0.26769688037338846, "learning_rate": 3.9334339831869963e-07, "loss": 0.2991, "step": 1160 }, { "epoch": 4.702784810126582, "grad_norm": 0.2802998354763574, "learning_rate": 3.8222096878671955e-07, "loss": 0.316, "step": 1161 }, { "epoch": 4.706835443037974, "grad_norm": 0.2831201309122744, "learning_rate": 3.7125653815009545e-07, "loss": 0.3039, "step": 1162 }, { "epoch": 4.710886075949367, "grad_norm": 0.28596826531346553, "learning_rate": 3.6045019471484974e-07, "loss": 0.3297, "step": 1163 }, { "epoch": 4.714936708860759, "grad_norm": 0.2808594567240539, "learning_rate": 3.498020255137813e-07, "loss": 0.3171, "step": 1164 }, { "epoch": 4.718987341772152, "grad_norm": 0.2717271449380879, "learning_rate": 3.393121163057811e-07, "loss": 0.3165, "step": 1165 }, { "epoch": 4.723037974683544, "grad_norm": 0.27663634813061366, "learning_rate": 3.289805515751399e-07, "loss": 0.312, "step": 1166 }, { "epoch": 4.727088607594936, "grad_norm": 0.28461487581397854, "learning_rate": 3.188074145308573e-07, "loss": 0.3294, "step": 1167 }, { "epoch": 4.731139240506329, "grad_norm": 0.2749212325432172, "learning_rate": 3.087927871059804e-07, "loss": 0.2979, "step": 1168 }, { "epoch": 4.735189873417721, "grad_norm": 0.28866454001631453, "learning_rate": 2.989367499569418e-07, "loss": 0.3283, "step": 1169 }, { "epoch": 4.739240506329114, "grad_norm": 0.2776534388680019, "learning_rate": 2.8923938246290917e-07, "loss": 0.2912, "step": 1170 }, { "epoch": 4.743291139240506, "grad_norm": 0.2750829358732585, "learning_rate": 2.7970076272514804e-07, "loss": 0.2962, "step": 1171 }, { "epoch": 4.7473417721518985, "grad_norm": 0.2796313924935612, "learning_rate": 2.703209675663887e-07, "loss": 0.3271, "step": 1172 }, { "epoch": 4.751392405063291, "grad_norm": 0.25743950175723385, "learning_rate": 2.6110007253021374e-07, "loss": 0.2795, "step": 1173 }, { "epoch": 4.7554430379746835, "grad_norm": 0.291883504804354, "learning_rate": 2.520381518804471e-07, "loss": 0.3278, "step": 1174 }, { "epoch": 4.759493670886076, "grad_norm": 0.29571997972124203, "learning_rate": 2.4313527860054585e-07, "loss": 0.3235, "step": 1175 }, { "epoch": 4.7635443037974685, "grad_norm": 0.26520163017411735, "learning_rate": 2.343915243930317e-07, "loss": 0.3002, "step": 1176 }, { "epoch": 4.767594936708861, "grad_norm": 0.2690323061383751, "learning_rate": 2.2580695967889367e-07, "loss": 0.3099, "step": 1177 }, { "epoch": 4.7716455696202535, "grad_norm": 0.2634375119905879, "learning_rate": 2.1738165359704189e-07, "loss": 0.291, "step": 1178 }, { "epoch": 4.775696202531646, "grad_norm": 0.296918773085543, "learning_rate": 2.0911567400373257e-07, "loss": 0.3484, "step": 1179 }, { "epoch": 4.779746835443038, "grad_norm": 0.26581085952918765, "learning_rate": 2.0100908747202607e-07, "loss": 0.2865, "step": 1180 }, { "epoch": 4.783797468354431, "grad_norm": 0.2879925711642636, "learning_rate": 1.9306195929125638e-07, "loss": 0.3462, "step": 1181 }, { "epoch": 4.787848101265823, "grad_norm": 0.2607977689391529, "learning_rate": 1.8527435346650247e-07, "loss": 0.2817, "step": 1182 }, { "epoch": 4.791898734177215, "grad_norm": 0.2827106148379982, "learning_rate": 1.7764633271807108e-07, "loss": 0.3315, "step": 1183 }, { "epoch": 4.795949367088608, "grad_norm": 0.27036971691252515, "learning_rate": 1.7017795848099262e-07, "loss": 0.3271, "step": 1184 }, { "epoch": 4.8, "grad_norm": 0.26211802148651553, "learning_rate": 1.6286929090452596e-07, "loss": 0.2911, "step": 1185 }, { "epoch": 4.804050632911393, "grad_norm": 0.27611969689986066, "learning_rate": 1.557203888516745e-07, "loss": 0.3314, "step": 1186 }, { "epoch": 4.808101265822785, "grad_norm": 0.2670746821536963, "learning_rate": 1.487313098987131e-07, "loss": 0.3086, "step": 1187 }, { "epoch": 4.812151898734177, "grad_norm": 0.28080405399884417, "learning_rate": 1.4190211033472402e-07, "loss": 0.3255, "step": 1188 }, { "epoch": 4.81620253164557, "grad_norm": 0.2678085301322021, "learning_rate": 1.3523284516113955e-07, "loss": 0.2986, "step": 1189 }, { "epoch": 4.820253164556962, "grad_norm": 0.26917772731282424, "learning_rate": 1.2872356809130682e-07, "loss": 0.3098, "step": 1190 }, { "epoch": 4.824303797468355, "grad_norm": 0.27869536265393247, "learning_rate": 1.2237433155004807e-07, "loss": 0.3049, "step": 1191 }, { "epoch": 4.828354430379747, "grad_norm": 0.271992185232331, "learning_rate": 1.1618518667323886e-07, "loss": 0.3065, "step": 1192 }, { "epoch": 4.832405063291139, "grad_norm": 0.2798607930059501, "learning_rate": 1.1015618330740385e-07, "loss": 0.3177, "step": 1193 }, { "epoch": 4.836455696202532, "grad_norm": 0.26768688909089977, "learning_rate": 1.042873700093061e-07, "loss": 0.3167, "step": 1194 }, { "epoch": 4.840506329113924, "grad_norm": 0.2665238393627066, "learning_rate": 9.857879404556291e-08, "loss": 0.2928, "step": 1195 }, { "epoch": 4.844556962025316, "grad_norm": 0.2874318740117917, "learning_rate": 9.303050139225722e-08, "loss": 0.3328, "step": 1196 }, { "epoch": 4.848607594936709, "grad_norm": 0.2770207508011934, "learning_rate": 8.76425367345779e-08, "loss": 0.3115, "step": 1197 }, { "epoch": 4.852658227848101, "grad_norm": 0.2860285801152122, "learning_rate": 8.241494346644897e-08, "loss": 0.3007, "step": 1198 }, { "epoch": 4.856708860759493, "grad_norm": 0.27579968281128503, "learning_rate": 7.734776369019204e-08, "loss": 0.3079, "step": 1199 }, { "epoch": 4.860759493670886, "grad_norm": 0.2858936532670639, "learning_rate": 7.244103821617332e-08, "loss": 0.3542, "step": 1200 }, { "epoch": 4.864810126582278, "grad_norm": 0.2763698981113065, "learning_rate": 6.769480656248606e-08, "loss": 0.318, "step": 1201 }, { "epoch": 4.868860759493671, "grad_norm": 0.2869940611829118, "learning_rate": 6.310910695462635e-08, "loss": 0.3023, "step": 1202 }, { "epoch": 4.872911392405063, "grad_norm": 0.27338857309000153, "learning_rate": 5.8683976325191185e-08, "loss": 0.301, "step": 1203 }, { "epoch": 4.876962025316455, "grad_norm": 0.28181459422651217, "learning_rate": 5.4419450313571984e-08, "loss": 0.3225, "step": 1204 }, { "epoch": 4.881012658227848, "grad_norm": 0.27109528577305114, "learning_rate": 5.031556326567488e-08, "loss": 0.2965, "step": 1205 }, { "epoch": 4.88506329113924, "grad_norm": 0.2790939359203373, "learning_rate": 4.637234823364312e-08, "loss": 0.3142, "step": 1206 }, { "epoch": 4.889113924050633, "grad_norm": 0.2882365094571139, "learning_rate": 4.258983697558838e-08, "loss": 0.327, "step": 1207 }, { "epoch": 4.8931645569620255, "grad_norm": 0.2694485265932956, "learning_rate": 3.896805995533548e-08, "loss": 0.3038, "step": 1208 }, { "epoch": 4.8972151898734175, "grad_norm": 0.2651124103881976, "learning_rate": 3.550704634218028e-08, "loss": 0.2847, "step": 1209 }, { "epoch": 4.9012658227848105, "grad_norm": 0.2816482105523644, "learning_rate": 3.2206824010647676e-08, "loss": 0.3342, "step": 1210 }, { "epoch": 4.905316455696203, "grad_norm": 0.27543658232355084, "learning_rate": 2.9067419540278476e-08, "loss": 0.2947, "step": 1211 }, { "epoch": 4.909367088607595, "grad_norm": 0.27707882138896645, "learning_rate": 2.6088858215400638e-08, "loss": 0.3077, "step": 1212 }, { "epoch": 4.913417721518988, "grad_norm": 0.2810061367950438, "learning_rate": 2.3271164024940564e-08, "loss": 0.3177, "step": 1213 }, { "epoch": 4.91746835443038, "grad_norm": 0.2724309234797965, "learning_rate": 2.061435966221881e-08, "loss": 0.3117, "step": 1214 }, { "epoch": 4.921518987341772, "grad_norm": 0.2733909269402092, "learning_rate": 1.811846652477245e-08, "loss": 0.2928, "step": 1215 }, { "epoch": 4.925569620253165, "grad_norm": 0.28938468504202847, "learning_rate": 1.5783504714184106e-08, "loss": 0.3157, "step": 1216 }, { "epoch": 4.929620253164557, "grad_norm": 0.2869591096693559, "learning_rate": 1.360949303591097e-08, "loss": 0.3166, "step": 1217 }, { "epoch": 4.93367088607595, "grad_norm": 0.26399935702099886, "learning_rate": 1.1596448999144916e-08, "loss": 0.2971, "step": 1218 }, { "epoch": 4.937721518987342, "grad_norm": 0.26941941132756125, "learning_rate": 9.744388816668172e-09, "loss": 0.327, "step": 1219 }, { "epoch": 4.941772151898734, "grad_norm": 0.27386190140072625, "learning_rate": 8.05332740472009e-09, "loss": 0.3139, "step": 1220 }, { "epoch": 4.945822784810127, "grad_norm": 0.24925843498682793, "learning_rate": 6.523278382872811e-09, "loss": 0.2791, "step": 1221 }, { "epoch": 4.949873417721519, "grad_norm": 0.27573941109064964, "learning_rate": 5.15425407393133e-09, "loss": 0.3121, "step": 1222 }, { "epoch": 4.953924050632912, "grad_norm": 0.29107201945087036, "learning_rate": 3.94626550383137e-09, "loss": 0.3366, "step": 1223 }, { "epoch": 4.957974683544304, "grad_norm": 0.27142467149431815, "learning_rate": 2.899322401546112e-09, "loss": 0.2959, "step": 1224 }, { "epoch": 4.962025316455696, "grad_norm": 0.28929578071908024, "learning_rate": 2.013433199010706e-09, "loss": 0.3265, "step": 1225 }, { "epoch": 4.966075949367089, "grad_norm": 0.27330366263937084, "learning_rate": 1.2886050310556563e-09, "loss": 0.309, "step": 1226 }, { "epoch": 4.970126582278481, "grad_norm": 0.282714168529177, "learning_rate": 7.248437353468695e-10, "loss": 0.3131, "step": 1227 }, { "epoch": 4.974177215189873, "grad_norm": 0.2703626917857017, "learning_rate": 3.221538523412449e-10, "loss": 0.293, "step": 1228 }, { "epoch": 4.978227848101266, "grad_norm": 0.2830591308521438, "learning_rate": 8.053862524670663e-11, "loss": 0.3192, "step": 1229 }, { "epoch": 4.982278481012658, "grad_norm": 0.28282033236012344, "learning_rate": 0.0, "loss": 0.3252, "step": 1230 }, { "epoch": 4.982278481012658, "step": 1230, "total_flos": 3.172179213725729e+18, "train_loss": 0.47651251888856655, "train_runtime": 80247.9852, "train_samples_per_second": 1.969, "train_steps_per_second": 0.015 } ], "logging_steps": 1.0, "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": 3.172179213725729e+18, "train_batch_size": 1, "trial_name": null, "trial_params": null }