{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 1.0, "eval_steps": 500, "global_step": 441, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0022695035460992908, "grad_norm": 202.86715698242188, "learning_rate": 0.0, "loss": 33.6177, "step": 1 }, { "epoch": 0.0045390070921985815, "grad_norm": 170.63381958007812, "learning_rate": 2.0000000000000003e-06, "loss": 29.9103, "step": 2 }, { "epoch": 0.006808510638297872, "grad_norm": 191.40802001953125, "learning_rate": 4.000000000000001e-06, "loss": 32.6244, "step": 3 }, { "epoch": 0.009078014184397163, "grad_norm": 176.60902404785156, "learning_rate": 6e-06, "loss": 28.8876, "step": 4 }, { "epoch": 0.011347517730496455, "grad_norm": 199.67886352539062, "learning_rate": 8.000000000000001e-06, "loss": 27.2283, "step": 5 }, { "epoch": 0.013617021276595745, "grad_norm": 93.18831634521484, "learning_rate": 1e-05, "loss": 24.5405, "step": 6 }, { "epoch": 0.015886524822695036, "grad_norm": 77.14661407470703, "learning_rate": 9.977064220183487e-06, "loss": 22.2702, "step": 7 }, { "epoch": 0.018156028368794326, "grad_norm": 77.71808624267578, "learning_rate": 9.954128440366973e-06, "loss": 21.3282, "step": 8 }, { "epoch": 0.020425531914893616, "grad_norm": 55.18010330200195, "learning_rate": 9.931192660550459e-06, "loss": 18.0126, "step": 9 }, { "epoch": 0.02269503546099291, "grad_norm": 40.912784576416016, "learning_rate": 9.908256880733946e-06, "loss": 16.8396, "step": 10 }, { "epoch": 0.0249645390070922, "grad_norm": 30.7188720703125, "learning_rate": 9.885321100917432e-06, "loss": 16.3323, "step": 11 }, { "epoch": 0.02723404255319149, "grad_norm": 31.02227210998535, "learning_rate": 9.862385321100918e-06, "loss": 16.8634, "step": 12 }, { "epoch": 0.02950354609929078, "grad_norm": 28.18900489807129, "learning_rate": 9.839449541284404e-06, "loss": 16.856, "step": 13 }, { "epoch": 0.03177304964539007, "grad_norm": 33.24095153808594, "learning_rate": 9.81651376146789e-06, "loss": 15.8536, "step": 14 }, { "epoch": 0.03404255319148936, "grad_norm": 25.615413665771484, "learning_rate": 9.793577981651376e-06, "loss": 14.4513, "step": 15 }, { "epoch": 0.03631205673758865, "grad_norm": 28.316972732543945, "learning_rate": 9.770642201834864e-06, "loss": 14.3348, "step": 16 }, { "epoch": 0.03858156028368794, "grad_norm": 24.958993911743164, "learning_rate": 9.74770642201835e-06, "loss": 14.156, "step": 17 }, { "epoch": 0.04085106382978723, "grad_norm": 24.190105438232422, "learning_rate": 9.724770642201836e-06, "loss": 13.8755, "step": 18 }, { "epoch": 0.04312056737588652, "grad_norm": 23.188518524169922, "learning_rate": 9.701834862385322e-06, "loss": 15.1323, "step": 19 }, { "epoch": 0.04539007092198582, "grad_norm": 24.48980712890625, "learning_rate": 9.678899082568808e-06, "loss": 12.71, "step": 20 }, { "epoch": 0.04765957446808511, "grad_norm": 26.518510818481445, "learning_rate": 9.655963302752295e-06, "loss": 14.4117, "step": 21 }, { "epoch": 0.0499290780141844, "grad_norm": 19.951358795166016, "learning_rate": 9.633027522935781e-06, "loss": 12.1108, "step": 22 }, { "epoch": 0.05219858156028369, "grad_norm": 20.609817504882812, "learning_rate": 9.610091743119267e-06, "loss": 11.7957, "step": 23 }, { "epoch": 0.05446808510638298, "grad_norm": 24.724565505981445, "learning_rate": 9.587155963302753e-06, "loss": 12.9538, "step": 24 }, { "epoch": 0.05673758865248227, "grad_norm": 35.223392486572266, "learning_rate": 9.56422018348624e-06, "loss": 12.3753, "step": 25 }, { "epoch": 0.05900709219858156, "grad_norm": 20.378952026367188, "learning_rate": 9.541284403669727e-06, "loss": 12.2574, "step": 26 }, { "epoch": 0.06127659574468085, "grad_norm": 21.990095138549805, "learning_rate": 9.518348623853211e-06, "loss": 13.1586, "step": 27 }, { "epoch": 0.06354609929078014, "grad_norm": 28.636812210083008, "learning_rate": 9.495412844036697e-06, "loss": 11.704, "step": 28 }, { "epoch": 0.06581560283687943, "grad_norm": 19.62146759033203, "learning_rate": 9.472477064220185e-06, "loss": 12.6258, "step": 29 }, { "epoch": 0.06808510638297872, "grad_norm": 17.72417449951172, "learning_rate": 9.44954128440367e-06, "loss": 12.4697, "step": 30 }, { "epoch": 0.07035460992907801, "grad_norm": 18.73772621154785, "learning_rate": 9.426605504587157e-06, "loss": 12.7649, "step": 31 }, { "epoch": 0.0726241134751773, "grad_norm": 17.881986618041992, "learning_rate": 9.403669724770643e-06, "loss": 12.0931, "step": 32 }, { "epoch": 0.0748936170212766, "grad_norm": 16.948307037353516, "learning_rate": 9.380733944954129e-06, "loss": 12.4736, "step": 33 }, { "epoch": 0.07716312056737588, "grad_norm": 17.225482940673828, "learning_rate": 9.357798165137616e-06, "loss": 10.9303, "step": 34 }, { "epoch": 0.07943262411347518, "grad_norm": 14.972012519836426, "learning_rate": 9.334862385321102e-06, "loss": 11.8592, "step": 35 }, { "epoch": 0.08170212765957446, "grad_norm": 18.720165252685547, "learning_rate": 9.311926605504588e-06, "loss": 11.945, "step": 36 }, { "epoch": 0.08397163120567376, "grad_norm": 18.514286041259766, "learning_rate": 9.288990825688074e-06, "loss": 11.8972, "step": 37 }, { "epoch": 0.08624113475177304, "grad_norm": 19.584877014160156, "learning_rate": 9.26605504587156e-06, "loss": 12.7854, "step": 38 }, { "epoch": 0.08851063829787234, "grad_norm": 16.866212844848633, "learning_rate": 9.243119266055046e-06, "loss": 11.7249, "step": 39 }, { "epoch": 0.09078014184397164, "grad_norm": 22.615249633789062, "learning_rate": 9.220183486238534e-06, "loss": 12.3164, "step": 40 }, { "epoch": 0.09304964539007092, "grad_norm": 20.355974197387695, "learning_rate": 9.19724770642202e-06, "loss": 12.6243, "step": 41 }, { "epoch": 0.09531914893617022, "grad_norm": 20.370384216308594, "learning_rate": 9.174311926605506e-06, "loss": 12.5554, "step": 42 }, { "epoch": 0.0975886524822695, "grad_norm": 23.389673233032227, "learning_rate": 9.151376146788992e-06, "loss": 13.906, "step": 43 }, { "epoch": 0.0998581560283688, "grad_norm": 18.33058738708496, "learning_rate": 9.128440366972477e-06, "loss": 11.9003, "step": 44 }, { "epoch": 0.10212765957446808, "grad_norm": 18.68928337097168, "learning_rate": 9.105504587155965e-06, "loss": 13.2574, "step": 45 }, { "epoch": 0.10439716312056738, "grad_norm": 16.325822830200195, "learning_rate": 9.08256880733945e-06, "loss": 11.3404, "step": 46 }, { "epoch": 0.10666666666666667, "grad_norm": 17.23180389404297, "learning_rate": 9.059633027522935e-06, "loss": 11.6588, "step": 47 }, { "epoch": 0.10893617021276596, "grad_norm": 15.936429977416992, "learning_rate": 9.036697247706423e-06, "loss": 12.3846, "step": 48 }, { "epoch": 0.11120567375886525, "grad_norm": 17.257057189941406, "learning_rate": 9.013761467889909e-06, "loss": 12.4578, "step": 49 }, { "epoch": 0.11347517730496454, "grad_norm": 19.273990631103516, "learning_rate": 8.990825688073395e-06, "loss": 11.3671, "step": 50 }, { "epoch": 0.11574468085106383, "grad_norm": 13.63159465789795, "learning_rate": 8.967889908256881e-06, "loss": 12.124, "step": 51 }, { "epoch": 0.11801418439716312, "grad_norm": 16.037647247314453, "learning_rate": 8.944954128440367e-06, "loss": 13.378, "step": 52 }, { "epoch": 0.12028368794326241, "grad_norm": 16.60262107849121, "learning_rate": 8.922018348623855e-06, "loss": 12.6463, "step": 53 }, { "epoch": 0.1225531914893617, "grad_norm": 15.954838752746582, "learning_rate": 8.89908256880734e-06, "loss": 11.6554, "step": 54 }, { "epoch": 0.12482269503546099, "grad_norm": 17.791372299194336, "learning_rate": 8.876146788990826e-06, "loss": 12.2817, "step": 55 }, { "epoch": 0.1270921985815603, "grad_norm": 14.828863143920898, "learning_rate": 8.853211009174312e-06, "loss": 11.8, "step": 56 }, { "epoch": 0.12936170212765957, "grad_norm": 14.657787322998047, "learning_rate": 8.830275229357798e-06, "loss": 11.9322, "step": 57 }, { "epoch": 0.13163120567375886, "grad_norm": 15.721675872802734, "learning_rate": 8.807339449541286e-06, "loss": 12.7914, "step": 58 }, { "epoch": 0.13390070921985817, "grad_norm": 13.708273887634277, "learning_rate": 8.784403669724772e-06, "loss": 11.748, "step": 59 }, { "epoch": 0.13617021276595745, "grad_norm": 15.303019523620605, "learning_rate": 8.761467889908258e-06, "loss": 12.1366, "step": 60 }, { "epoch": 0.13843971631205673, "grad_norm": 13.865371704101562, "learning_rate": 8.738532110091744e-06, "loss": 12.4178, "step": 61 }, { "epoch": 0.14070921985815601, "grad_norm": 15.449434280395508, "learning_rate": 8.71559633027523e-06, "loss": 12.8315, "step": 62 }, { "epoch": 0.14297872340425533, "grad_norm": 13.890251159667969, "learning_rate": 8.692660550458716e-06, "loss": 11.5508, "step": 63 }, { "epoch": 0.1452482269503546, "grad_norm": 18.71402931213379, "learning_rate": 8.669724770642203e-06, "loss": 11.8914, "step": 64 }, { "epoch": 0.1475177304964539, "grad_norm": 16.312633514404297, "learning_rate": 8.646788990825688e-06, "loss": 12.9031, "step": 65 }, { "epoch": 0.1497872340425532, "grad_norm": 13.330503463745117, "learning_rate": 8.623853211009175e-06, "loss": 11.5223, "step": 66 }, { "epoch": 0.15205673758865249, "grad_norm": 15.116589546203613, "learning_rate": 8.600917431192661e-06, "loss": 11.5126, "step": 67 }, { "epoch": 0.15432624113475177, "grad_norm": 15.47360610961914, "learning_rate": 8.577981651376147e-06, "loss": 11.8877, "step": 68 }, { "epoch": 0.15659574468085105, "grad_norm": 15.934971809387207, "learning_rate": 8.555045871559633e-06, "loss": 12.3198, "step": 69 }, { "epoch": 0.15886524822695036, "grad_norm": 14.018664360046387, "learning_rate": 8.53211009174312e-06, "loss": 11.4015, "step": 70 }, { "epoch": 0.16113475177304964, "grad_norm": 15.006296157836914, "learning_rate": 8.509174311926605e-06, "loss": 11.0345, "step": 71 }, { "epoch": 0.16340425531914893, "grad_norm": 14.383210182189941, "learning_rate": 8.486238532110093e-06, "loss": 12.2185, "step": 72 }, { "epoch": 0.16567375886524824, "grad_norm": 15.7976655960083, "learning_rate": 8.463302752293579e-06, "loss": 13.056, "step": 73 }, { "epoch": 0.16794326241134752, "grad_norm": 16.56097984313965, "learning_rate": 8.440366972477065e-06, "loss": 12.6029, "step": 74 }, { "epoch": 0.1702127659574468, "grad_norm": 13.735828399658203, "learning_rate": 8.41743119266055e-06, "loss": 12.0568, "step": 75 }, { "epoch": 0.1724822695035461, "grad_norm": 13.06482219696045, "learning_rate": 8.394495412844037e-06, "loss": 11.6856, "step": 76 }, { "epoch": 0.1747517730496454, "grad_norm": 14.065268516540527, "learning_rate": 8.371559633027524e-06, "loss": 12.4097, "step": 77 }, { "epoch": 0.17702127659574468, "grad_norm": 13.886503219604492, "learning_rate": 8.34862385321101e-06, "loss": 12.782, "step": 78 }, { "epoch": 0.17929078014184396, "grad_norm": 17.30091667175293, "learning_rate": 8.325688073394496e-06, "loss": 12.0025, "step": 79 }, { "epoch": 0.18156028368794327, "grad_norm": 18.678071975708008, "learning_rate": 8.302752293577982e-06, "loss": 11.7748, "step": 80 }, { "epoch": 0.18382978723404256, "grad_norm": 43.334075927734375, "learning_rate": 8.279816513761468e-06, "loss": 12.6631, "step": 81 }, { "epoch": 0.18609929078014184, "grad_norm": 14.227105140686035, "learning_rate": 8.256880733944956e-06, "loss": 13.7783, "step": 82 }, { "epoch": 0.18836879432624112, "grad_norm": 15.684635162353516, "learning_rate": 8.233944954128442e-06, "loss": 11.4588, "step": 83 }, { "epoch": 0.19063829787234043, "grad_norm": 13.842835426330566, "learning_rate": 8.211009174311926e-06, "loss": 11.4581, "step": 84 }, { "epoch": 0.19290780141843972, "grad_norm": 13.890243530273438, "learning_rate": 8.188073394495414e-06, "loss": 11.5576, "step": 85 }, { "epoch": 0.195177304964539, "grad_norm": 14.160876274108887, "learning_rate": 8.1651376146789e-06, "loss": 11.4323, "step": 86 }, { "epoch": 0.1974468085106383, "grad_norm": 14.202988624572754, "learning_rate": 8.142201834862386e-06, "loss": 11.383, "step": 87 }, { "epoch": 0.1997163120567376, "grad_norm": 13.272241592407227, "learning_rate": 8.119266055045872e-06, "loss": 12.002, "step": 88 }, { "epoch": 0.20198581560283688, "grad_norm": 15.298060417175293, "learning_rate": 8.096330275229358e-06, "loss": 12.2606, "step": 89 }, { "epoch": 0.20425531914893616, "grad_norm": 14.067166328430176, "learning_rate": 8.073394495412845e-06, "loss": 11.589, "step": 90 }, { "epoch": 0.20652482269503547, "grad_norm": 16.92888832092285, "learning_rate": 8.050458715596331e-06, "loss": 10.9252, "step": 91 }, { "epoch": 0.20879432624113475, "grad_norm": 13.396157264709473, "learning_rate": 8.027522935779817e-06, "loss": 12.4441, "step": 92 }, { "epoch": 0.21106382978723404, "grad_norm": 13.916125297546387, "learning_rate": 8.004587155963303e-06, "loss": 12.0022, "step": 93 }, { "epoch": 0.21333333333333335, "grad_norm": 14.401926040649414, "learning_rate": 7.981651376146789e-06, "loss": 12.4955, "step": 94 }, { "epoch": 0.21560283687943263, "grad_norm": 14.948918342590332, "learning_rate": 7.958715596330275e-06, "loss": 12.7405, "step": 95 }, { "epoch": 0.2178723404255319, "grad_norm": 15.125786781311035, "learning_rate": 7.935779816513763e-06, "loss": 12.0782, "step": 96 }, { "epoch": 0.2201418439716312, "grad_norm": 13.766701698303223, "learning_rate": 7.912844036697249e-06, "loss": 12.3362, "step": 97 }, { "epoch": 0.2224113475177305, "grad_norm": 14.7355318069458, "learning_rate": 7.889908256880735e-06, "loss": 12.0648, "step": 98 }, { "epoch": 0.2246808510638298, "grad_norm": 13.118962287902832, "learning_rate": 7.86697247706422e-06, "loss": 12.1885, "step": 99 }, { "epoch": 0.22695035460992907, "grad_norm": 14.126100540161133, "learning_rate": 7.844036697247707e-06, "loss": 11.7644, "step": 100 }, { "epoch": 0.22921985815602836, "grad_norm": 15.864127159118652, "learning_rate": 7.821100917431194e-06, "loss": 12.1231, "step": 101 }, { "epoch": 0.23148936170212767, "grad_norm": 13.636550903320312, "learning_rate": 7.79816513761468e-06, "loss": 12.6287, "step": 102 }, { "epoch": 0.23375886524822695, "grad_norm": 14.88927173614502, "learning_rate": 7.775229357798164e-06, "loss": 11.9769, "step": 103 }, { "epoch": 0.23602836879432623, "grad_norm": 14.104449272155762, "learning_rate": 7.752293577981652e-06, "loss": 11.7774, "step": 104 }, { "epoch": 0.23829787234042554, "grad_norm": 14.955862045288086, "learning_rate": 7.729357798165138e-06, "loss": 11.8245, "step": 105 }, { "epoch": 0.24056737588652483, "grad_norm": 14.346540451049805, "learning_rate": 7.706422018348626e-06, "loss": 11.3192, "step": 106 }, { "epoch": 0.2428368794326241, "grad_norm": 14.618536949157715, "learning_rate": 7.68348623853211e-06, "loss": 11.2318, "step": 107 }, { "epoch": 0.2451063829787234, "grad_norm": 13.591572761535645, "learning_rate": 7.660550458715596e-06, "loss": 11.1416, "step": 108 }, { "epoch": 0.2473758865248227, "grad_norm": 13.371695518493652, "learning_rate": 7.637614678899084e-06, "loss": 11.9025, "step": 109 }, { "epoch": 0.24964539007092199, "grad_norm": 15.152725219726562, "learning_rate": 7.6146788990825695e-06, "loss": 11.9765, "step": 110 }, { "epoch": 0.2519148936170213, "grad_norm": 15.232375144958496, "learning_rate": 7.5917431192660555e-06, "loss": 12.274, "step": 111 }, { "epoch": 0.2541843971631206, "grad_norm": 14.697382926940918, "learning_rate": 7.568807339449542e-06, "loss": 11.6749, "step": 112 }, { "epoch": 0.25645390070921986, "grad_norm": 16.53761863708496, "learning_rate": 7.545871559633028e-06, "loss": 12.2933, "step": 113 }, { "epoch": 0.25872340425531914, "grad_norm": 13.810632705688477, "learning_rate": 7.522935779816515e-06, "loss": 11.0977, "step": 114 }, { "epoch": 0.26099290780141843, "grad_norm": 14.215558052062988, "learning_rate": 7.500000000000001e-06, "loss": 11.2798, "step": 115 }, { "epoch": 0.2632624113475177, "grad_norm": 15.162890434265137, "learning_rate": 7.477064220183486e-06, "loss": 11.374, "step": 116 }, { "epoch": 0.265531914893617, "grad_norm": 15.14799976348877, "learning_rate": 7.454128440366973e-06, "loss": 11.4618, "step": 117 }, { "epoch": 0.26780141843971633, "grad_norm": 15.034318923950195, "learning_rate": 7.431192660550459e-06, "loss": 12.4918, "step": 118 }, { "epoch": 0.2700709219858156, "grad_norm": 15.956082344055176, "learning_rate": 7.408256880733946e-06, "loss": 12.3037, "step": 119 }, { "epoch": 0.2723404255319149, "grad_norm": 13.794715881347656, "learning_rate": 7.385321100917432e-06, "loss": 10.7538, "step": 120 }, { "epoch": 0.2746099290780142, "grad_norm": 13.6895112991333, "learning_rate": 7.362385321100918e-06, "loss": 11.7033, "step": 121 }, { "epoch": 0.27687943262411346, "grad_norm": 12.466599464416504, "learning_rate": 7.3394495412844045e-06, "loss": 12.1034, "step": 122 }, { "epoch": 0.27914893617021275, "grad_norm": 13.514978408813477, "learning_rate": 7.31651376146789e-06, "loss": 11.2616, "step": 123 }, { "epoch": 0.28141843971631203, "grad_norm": 14.302180290222168, "learning_rate": 7.293577981651376e-06, "loss": 11.9236, "step": 124 }, { "epoch": 0.28368794326241137, "grad_norm": 14.133037567138672, "learning_rate": 7.270642201834863e-06, "loss": 12.4384, "step": 125 }, { "epoch": 0.28595744680851065, "grad_norm": 15.331138610839844, "learning_rate": 7.247706422018349e-06, "loss": 12.4898, "step": 126 }, { "epoch": 0.28822695035460993, "grad_norm": 15.515961647033691, "learning_rate": 7.224770642201836e-06, "loss": 11.6139, "step": 127 }, { "epoch": 0.2904964539007092, "grad_norm": 13.879063606262207, "learning_rate": 7.201834862385322e-06, "loss": 12.6219, "step": 128 }, { "epoch": 0.2927659574468085, "grad_norm": 16.28034782409668, "learning_rate": 7.178899082568808e-06, "loss": 13.0712, "step": 129 }, { "epoch": 0.2950354609929078, "grad_norm": 14.33593463897705, "learning_rate": 7.155963302752295e-06, "loss": 12.2348, "step": 130 }, { "epoch": 0.29730496453900707, "grad_norm": 13.941629409790039, "learning_rate": 7.133027522935781e-06, "loss": 11.5137, "step": 131 }, { "epoch": 0.2995744680851064, "grad_norm": 13.800041198730469, "learning_rate": 7.110091743119267e-06, "loss": 12.1184, "step": 132 }, { "epoch": 0.3018439716312057, "grad_norm": 16.21302604675293, "learning_rate": 7.087155963302753e-06, "loss": 12.732, "step": 133 }, { "epoch": 0.30411347517730497, "grad_norm": 13.205683708190918, "learning_rate": 7.0642201834862385e-06, "loss": 11.0697, "step": 134 }, { "epoch": 0.30638297872340425, "grad_norm": 13.36678695678711, "learning_rate": 7.041284403669726e-06, "loss": 10.9164, "step": 135 }, { "epoch": 0.30865248226950354, "grad_norm": 16.62143325805664, "learning_rate": 7.018348623853211e-06, "loss": 12.4772, "step": 136 }, { "epoch": 0.3109219858156028, "grad_norm": 14.7496919631958, "learning_rate": 6.995412844036697e-06, "loss": 11.8932, "step": 137 }, { "epoch": 0.3131914893617021, "grad_norm": 14.824339866638184, "learning_rate": 6.972477064220184e-06, "loss": 12.4117, "step": 138 }, { "epoch": 0.31546099290780144, "grad_norm": 13.883928298950195, "learning_rate": 6.94954128440367e-06, "loss": 11.5765, "step": 139 }, { "epoch": 0.3177304964539007, "grad_norm": 13.717906951904297, "learning_rate": 6.926605504587156e-06, "loss": 11.817, "step": 140 }, { "epoch": 0.32, "grad_norm": 16.145219802856445, "learning_rate": 6.903669724770643e-06, "loss": 11.0924, "step": 141 }, { "epoch": 0.3222695035460993, "grad_norm": 13.830381393432617, "learning_rate": 6.880733944954129e-06, "loss": 11.8047, "step": 142 }, { "epoch": 0.3245390070921986, "grad_norm": 14.504805564880371, "learning_rate": 6.8577981651376156e-06, "loss": 11.0613, "step": 143 }, { "epoch": 0.32680851063829786, "grad_norm": 15.642765998840332, "learning_rate": 6.8348623853211015e-06, "loss": 13.3639, "step": 144 }, { "epoch": 0.32907801418439714, "grad_norm": 13.512704849243164, "learning_rate": 6.8119266055045875e-06, "loss": 11.3268, "step": 145 }, { "epoch": 0.3313475177304965, "grad_norm": 14.516170501708984, "learning_rate": 6.788990825688074e-06, "loss": 11.6778, "step": 146 }, { "epoch": 0.33361702127659576, "grad_norm": 13.835782051086426, "learning_rate": 6.76605504587156e-06, "loss": 11.4476, "step": 147 }, { "epoch": 0.33588652482269504, "grad_norm": 14.642313003540039, "learning_rate": 6.743119266055046e-06, "loss": 12.7736, "step": 148 }, { "epoch": 0.3381560283687943, "grad_norm": 13.762947082519531, "learning_rate": 6.720183486238533e-06, "loss": 11.2634, "step": 149 }, { "epoch": 0.3404255319148936, "grad_norm": 14.404915809631348, "learning_rate": 6.697247706422019e-06, "loss": 12.1008, "step": 150 }, { "epoch": 0.3426950354609929, "grad_norm": 14.161348342895508, "learning_rate": 6.674311926605506e-06, "loss": 11.7743, "step": 151 }, { "epoch": 0.3449645390070922, "grad_norm": 13.629798889160156, "learning_rate": 6.651376146788992e-06, "loss": 11.5642, "step": 152 }, { "epoch": 0.3472340425531915, "grad_norm": 13.561607360839844, "learning_rate": 6.628440366972477e-06, "loss": 11.0025, "step": 153 }, { "epoch": 0.3495035460992908, "grad_norm": 14.583564758300781, "learning_rate": 6.6055045871559645e-06, "loss": 12.608, "step": 154 }, { "epoch": 0.3517730496453901, "grad_norm": 13.7203950881958, "learning_rate": 6.58256880733945e-06, "loss": 11.7677, "step": 155 }, { "epoch": 0.35404255319148936, "grad_norm": 13.406794548034668, "learning_rate": 6.559633027522936e-06, "loss": 10.9646, "step": 156 }, { "epoch": 0.35631205673758864, "grad_norm": 13.596993446350098, "learning_rate": 6.536697247706422e-06, "loss": 12.6444, "step": 157 }, { "epoch": 0.35858156028368793, "grad_norm": 15.246335983276367, "learning_rate": 6.513761467889908e-06, "loss": 11.956, "step": 158 }, { "epoch": 0.3608510638297872, "grad_norm": 13.931480407714844, "learning_rate": 6.490825688073395e-06, "loss": 12.5317, "step": 159 }, { "epoch": 0.36312056737588655, "grad_norm": 14.945709228515625, "learning_rate": 6.467889908256881e-06, "loss": 11.6474, "step": 160 }, { "epoch": 0.36539007092198583, "grad_norm": 15.11447811126709, "learning_rate": 6.444954128440367e-06, "loss": 11.1316, "step": 161 }, { "epoch": 0.3676595744680851, "grad_norm": 14.600578308105469, "learning_rate": 6.422018348623854e-06, "loss": 12.0826, "step": 162 }, { "epoch": 0.3699290780141844, "grad_norm": 14.425873756408691, "learning_rate": 6.39908256880734e-06, "loss": 11.8145, "step": 163 }, { "epoch": 0.3721985815602837, "grad_norm": 14.961342811584473, "learning_rate": 6.376146788990826e-06, "loss": 11.1886, "step": 164 }, { "epoch": 0.37446808510638296, "grad_norm": 14.898956298828125, "learning_rate": 6.353211009174313e-06, "loss": 12.7375, "step": 165 }, { "epoch": 0.37673758865248225, "grad_norm": 15.14245891571045, "learning_rate": 6.330275229357799e-06, "loss": 11.9022, "step": 166 }, { "epoch": 0.3790070921985816, "grad_norm": 14.530350685119629, "learning_rate": 6.307339449541285e-06, "loss": 12.066, "step": 167 }, { "epoch": 0.38127659574468087, "grad_norm": 14.191231727600098, "learning_rate": 6.284403669724771e-06, "loss": 10.8152, "step": 168 }, { "epoch": 0.38354609929078015, "grad_norm": 13.8941068649292, "learning_rate": 6.261467889908257e-06, "loss": 10.6517, "step": 169 }, { "epoch": 0.38581560283687943, "grad_norm": 14.872854232788086, "learning_rate": 6.238532110091744e-06, "loss": 12.3971, "step": 170 }, { "epoch": 0.3880851063829787, "grad_norm": 14.781063079833984, "learning_rate": 6.21559633027523e-06, "loss": 11.8754, "step": 171 }, { "epoch": 0.390354609929078, "grad_norm": 15.683016777038574, "learning_rate": 6.192660550458715e-06, "loss": 11.7812, "step": 172 }, { "epoch": 0.3926241134751773, "grad_norm": 13.613964080810547, "learning_rate": 6.169724770642203e-06, "loss": 10.8705, "step": 173 }, { "epoch": 0.3948936170212766, "grad_norm": 14.443016052246094, "learning_rate": 6.146788990825688e-06, "loss": 12.4083, "step": 174 }, { "epoch": 0.3971631205673759, "grad_norm": 13.905133247375488, "learning_rate": 6.123853211009176e-06, "loss": 11.6548, "step": 175 }, { "epoch": 0.3994326241134752, "grad_norm": 14.36567497253418, "learning_rate": 6.100917431192661e-06, "loss": 10.9077, "step": 176 }, { "epoch": 0.40170212765957447, "grad_norm": 13.09998893737793, "learning_rate": 6.077981651376147e-06, "loss": 11.5184, "step": 177 }, { "epoch": 0.40397163120567375, "grad_norm": 14.80097484588623, "learning_rate": 6.0550458715596335e-06, "loss": 12.6442, "step": 178 }, { "epoch": 0.40624113475177304, "grad_norm": 14.203194618225098, "learning_rate": 6.0321100917431195e-06, "loss": 10.8213, "step": 179 }, { "epoch": 0.4085106382978723, "grad_norm": 13.331576347351074, "learning_rate": 6.0091743119266054e-06, "loss": 10.8401, "step": 180 }, { "epoch": 0.41078014184397166, "grad_norm": 13.110844612121582, "learning_rate": 5.986238532110092e-06, "loss": 11.1464, "step": 181 }, { "epoch": 0.41304964539007094, "grad_norm": 13.590310096740723, "learning_rate": 5.963302752293578e-06, "loss": 11.699, "step": 182 }, { "epoch": 0.4153191489361702, "grad_norm": 14.125923156738281, "learning_rate": 5.940366972477065e-06, "loss": 9.9647, "step": 183 }, { "epoch": 0.4175886524822695, "grad_norm": 13.48251724243164, "learning_rate": 5.917431192660551e-06, "loss": 12.136, "step": 184 }, { "epoch": 0.4198581560283688, "grad_norm": 14.360281944274902, "learning_rate": 5.894495412844037e-06, "loss": 10.7266, "step": 185 }, { "epoch": 0.4221276595744681, "grad_norm": 13.273941993713379, "learning_rate": 5.871559633027524e-06, "loss": 11.7335, "step": 186 }, { "epoch": 0.42439716312056736, "grad_norm": 13.64523983001709, "learning_rate": 5.84862385321101e-06, "loss": 11.3546, "step": 187 }, { "epoch": 0.4266666666666667, "grad_norm": 14.246500968933105, "learning_rate": 5.825688073394496e-06, "loss": 11.5303, "step": 188 }, { "epoch": 0.428936170212766, "grad_norm": 14.505959510803223, "learning_rate": 5.8027522935779825e-06, "loss": 12.3668, "step": 189 }, { "epoch": 0.43120567375886526, "grad_norm": 14.955110549926758, "learning_rate": 5.7798165137614684e-06, "loss": 11.2931, "step": 190 }, { "epoch": 0.43347517730496454, "grad_norm": 14.881681442260742, "learning_rate": 5.756880733944955e-06, "loss": 12.6521, "step": 191 }, { "epoch": 0.4357446808510638, "grad_norm": 14.197546005249023, "learning_rate": 5.733944954128441e-06, "loss": 11.975, "step": 192 }, { "epoch": 0.4380141843971631, "grad_norm": 18.983572006225586, "learning_rate": 5.711009174311926e-06, "loss": 12.0041, "step": 193 }, { "epoch": 0.4402836879432624, "grad_norm": 13.735647201538086, "learning_rate": 5.688073394495414e-06, "loss": 11.0253, "step": 194 }, { "epoch": 0.4425531914893617, "grad_norm": 14.99286937713623, "learning_rate": 5.665137614678899e-06, "loss": 11.8618, "step": 195 }, { "epoch": 0.444822695035461, "grad_norm": 14.699832916259766, "learning_rate": 5.642201834862385e-06, "loss": 12.2299, "step": 196 }, { "epoch": 0.4470921985815603, "grad_norm": 13.775699615478516, "learning_rate": 5.619266055045872e-06, "loss": 11.1839, "step": 197 }, { "epoch": 0.4493617021276596, "grad_norm": 14.55324935913086, "learning_rate": 5.596330275229358e-06, "loss": 11.7091, "step": 198 }, { "epoch": 0.45163120567375886, "grad_norm": 13.776188850402832, "learning_rate": 5.573394495412845e-06, "loss": 11.1202, "step": 199 }, { "epoch": 0.45390070921985815, "grad_norm": 13.882137298583984, "learning_rate": 5.5504587155963306e-06, "loss": 10.8068, "step": 200 }, { "epoch": 0.45617021276595743, "grad_norm": 13.154303550720215, "learning_rate": 5.5275229357798165e-06, "loss": 11.4739, "step": 201 }, { "epoch": 0.4584397163120567, "grad_norm": 14.635552406311035, "learning_rate": 5.504587155963303e-06, "loss": 12.5796, "step": 202 }, { "epoch": 0.46070921985815605, "grad_norm": 14.015669822692871, "learning_rate": 5.481651376146789e-06, "loss": 11.4312, "step": 203 }, { "epoch": 0.46297872340425533, "grad_norm": 13.338607788085938, "learning_rate": 5.458715596330275e-06, "loss": 10.7015, "step": 204 }, { "epoch": 0.4652482269503546, "grad_norm": 13.896073341369629, "learning_rate": 5.435779816513762e-06, "loss": 10.9978, "step": 205 }, { "epoch": 0.4675177304964539, "grad_norm": 13.936399459838867, "learning_rate": 5.412844036697248e-06, "loss": 12.0326, "step": 206 }, { "epoch": 0.4697872340425532, "grad_norm": 14.18737506866455, "learning_rate": 5.389908256880735e-06, "loss": 12.2203, "step": 207 }, { "epoch": 0.47205673758865246, "grad_norm": 13.894092559814453, "learning_rate": 5.366972477064221e-06, "loss": 11.8441, "step": 208 }, { "epoch": 0.47432624113475175, "grad_norm": 14.427918434143066, "learning_rate": 5.344036697247707e-06, "loss": 12.4715, "step": 209 }, { "epoch": 0.4765957446808511, "grad_norm": 15.121187210083008, "learning_rate": 5.3211009174311936e-06, "loss": 12.602, "step": 210 }, { "epoch": 0.47886524822695037, "grad_norm": 14.126570701599121, "learning_rate": 5.2981651376146795e-06, "loss": 12.7936, "step": 211 }, { "epoch": 0.48113475177304965, "grad_norm": 13.481224060058594, "learning_rate": 5.275229357798165e-06, "loss": 11.725, "step": 212 }, { "epoch": 0.48340425531914893, "grad_norm": 14.161888122558594, "learning_rate": 5.252293577981652e-06, "loss": 12.6332, "step": 213 }, { "epoch": 0.4856737588652482, "grad_norm": 14.543578147888184, "learning_rate": 5.229357798165137e-06, "loss": 12.0584, "step": 214 }, { "epoch": 0.4879432624113475, "grad_norm": 16.11267852783203, "learning_rate": 5.206422018348625e-06, "loss": 10.3765, "step": 215 }, { "epoch": 0.4902127659574468, "grad_norm": 13.666749954223633, "learning_rate": 5.18348623853211e-06, "loss": 12.0625, "step": 216 }, { "epoch": 0.4924822695035461, "grad_norm": 14.476999282836914, "learning_rate": 5.160550458715596e-06, "loss": 10.9989, "step": 217 }, { "epoch": 0.4947517730496454, "grad_norm": 13.43332290649414, "learning_rate": 5.137614678899083e-06, "loss": 11.421, "step": 218 }, { "epoch": 0.4970212765957447, "grad_norm": 14.954253196716309, "learning_rate": 5.114678899082569e-06, "loss": 12.0475, "step": 219 }, { "epoch": 0.49929078014184397, "grad_norm": 14.410735130310059, "learning_rate": 5.091743119266055e-06, "loss": 10.5587, "step": 220 }, { "epoch": 0.5015602836879433, "grad_norm": 13.990411758422852, "learning_rate": 5.068807339449542e-06, "loss": 12.5069, "step": 221 }, { "epoch": 0.5038297872340426, "grad_norm": 15.5552339553833, "learning_rate": 5.045871559633028e-06, "loss": 12.3707, "step": 222 }, { "epoch": 0.5060992907801418, "grad_norm": 13.867732048034668, "learning_rate": 5.0229357798165144e-06, "loss": 11.4042, "step": 223 }, { "epoch": 0.5083687943262412, "grad_norm": 16.346933364868164, "learning_rate": 5e-06, "loss": 10.6123, "step": 224 }, { "epoch": 0.5106382978723404, "grad_norm": 13.969047546386719, "learning_rate": 4.977064220183486e-06, "loss": 11.7233, "step": 225 }, { "epoch": 0.5129078014184397, "grad_norm": 14.230488777160645, "learning_rate": 4.954128440366973e-06, "loss": 11.3355, "step": 226 }, { "epoch": 0.5151773049645391, "grad_norm": 13.223283767700195, "learning_rate": 4.931192660550459e-06, "loss": 11.6047, "step": 227 }, { "epoch": 0.5174468085106383, "grad_norm": 14.33090591430664, "learning_rate": 4.908256880733945e-06, "loss": 11.232, "step": 228 }, { "epoch": 0.5197163120567376, "grad_norm": 14.492170333862305, "learning_rate": 4.885321100917432e-06, "loss": 12.7075, "step": 229 }, { "epoch": 0.5219858156028369, "grad_norm": 14.039759635925293, "learning_rate": 4.862385321100918e-06, "loss": 11.3565, "step": 230 }, { "epoch": 0.5242553191489362, "grad_norm": 14.774398803710938, "learning_rate": 4.839449541284404e-06, "loss": 12.4035, "step": 231 }, { "epoch": 0.5265248226950354, "grad_norm": 13.320657730102539, "learning_rate": 4.816513761467891e-06, "loss": 11.6516, "step": 232 }, { "epoch": 0.5287943262411348, "grad_norm": 14.816357612609863, "learning_rate": 4.793577981651377e-06, "loss": 11.2822, "step": 233 }, { "epoch": 0.531063829787234, "grad_norm": 14.402239799499512, "learning_rate": 4.770642201834863e-06, "loss": 11.4736, "step": 234 }, { "epoch": 0.5333333333333333, "grad_norm": 15.77016830444336, "learning_rate": 4.7477064220183485e-06, "loss": 12.0636, "step": 235 }, { "epoch": 0.5356028368794327, "grad_norm": 15.892963409423828, "learning_rate": 4.724770642201835e-06, "loss": 11.431, "step": 236 }, { "epoch": 0.5378723404255319, "grad_norm": 14.42391586303711, "learning_rate": 4.701834862385321e-06, "loss": 11.9115, "step": 237 }, { "epoch": 0.5401418439716312, "grad_norm": 14.028605461120605, "learning_rate": 4.678899082568808e-06, "loss": 12.1099, "step": 238 }, { "epoch": 0.5424113475177305, "grad_norm": 14.253106117248535, "learning_rate": 4.655963302752294e-06, "loss": 11.4375, "step": 239 }, { "epoch": 0.5446808510638298, "grad_norm": 13.479880332946777, "learning_rate": 4.63302752293578e-06, "loss": 12.4073, "step": 240 }, { "epoch": 0.546950354609929, "grad_norm": 14.570878982543945, "learning_rate": 4.610091743119267e-06, "loss": 10.1843, "step": 241 }, { "epoch": 0.5492198581560284, "grad_norm": 19.482206344604492, "learning_rate": 4.587155963302753e-06, "loss": 13.1447, "step": 242 }, { "epoch": 0.5514893617021277, "grad_norm": 13.553899765014648, "learning_rate": 4.564220183486239e-06, "loss": 11.325, "step": 243 }, { "epoch": 0.5537588652482269, "grad_norm": 13.618690490722656, "learning_rate": 4.541284403669725e-06, "loss": 11.7594, "step": 244 }, { "epoch": 0.5560283687943263, "grad_norm": 13.999242782592773, "learning_rate": 4.5183486238532115e-06, "loss": 11.2842, "step": 245 }, { "epoch": 0.5582978723404255, "grad_norm": 15.084493637084961, "learning_rate": 4.4954128440366975e-06, "loss": 11.706, "step": 246 }, { "epoch": 0.5605673758865248, "grad_norm": 13.091890335083008, "learning_rate": 4.4724770642201834e-06, "loss": 10.591, "step": 247 }, { "epoch": 0.5628368794326241, "grad_norm": 14.376734733581543, "learning_rate": 4.44954128440367e-06, "loss": 10.4077, "step": 248 }, { "epoch": 0.5651063829787234, "grad_norm": 14.551433563232422, "learning_rate": 4.426605504587156e-06, "loss": 11.6231, "step": 249 }, { "epoch": 0.5673758865248227, "grad_norm": 14.234875679016113, "learning_rate": 4.403669724770643e-06, "loss": 12.2104, "step": 250 }, { "epoch": 0.569645390070922, "grad_norm": 14.833578109741211, "learning_rate": 4.380733944954129e-06, "loss": 11.8478, "step": 251 }, { "epoch": 0.5719148936170213, "grad_norm": 14.350552558898926, "learning_rate": 4.357798165137615e-06, "loss": 11.3335, "step": 252 }, { "epoch": 0.5741843971631205, "grad_norm": 14.479663848876953, "learning_rate": 4.334862385321102e-06, "loss": 11.4386, "step": 253 }, { "epoch": 0.5764539007092199, "grad_norm": 14.645398139953613, "learning_rate": 4.311926605504588e-06, "loss": 11.4093, "step": 254 }, { "epoch": 0.5787234042553191, "grad_norm": 14.000316619873047, "learning_rate": 4.288990825688074e-06, "loss": 11.4979, "step": 255 }, { "epoch": 0.5809929078014184, "grad_norm": 14.698064804077148, "learning_rate": 4.26605504587156e-06, "loss": 11.3451, "step": 256 }, { "epoch": 0.5832624113475178, "grad_norm": 13.498764991760254, "learning_rate": 4.2431192660550464e-06, "loss": 11.5722, "step": 257 }, { "epoch": 0.585531914893617, "grad_norm": 14.747626304626465, "learning_rate": 4.220183486238532e-06, "loss": 10.8321, "step": 258 }, { "epoch": 0.5878014184397163, "grad_norm": 14.443275451660156, "learning_rate": 4.197247706422018e-06, "loss": 10.9451, "step": 259 }, { "epoch": 0.5900709219858156, "grad_norm": 15.280463218688965, "learning_rate": 4.174311926605505e-06, "loss": 12.5972, "step": 260 }, { "epoch": 0.5923404255319149, "grad_norm": 14.973596572875977, "learning_rate": 4.151376146788991e-06, "loss": 12.0011, "step": 261 }, { "epoch": 0.5946099290780141, "grad_norm": 15.749635696411133, "learning_rate": 4.128440366972478e-06, "loss": 12.665, "step": 262 }, { "epoch": 0.5968794326241135, "grad_norm": 15.125367164611816, "learning_rate": 4.105504587155963e-06, "loss": 12.0481, "step": 263 }, { "epoch": 0.5991489361702128, "grad_norm": 13.775811195373535, "learning_rate": 4.08256880733945e-06, "loss": 10.3127, "step": 264 }, { "epoch": 0.601418439716312, "grad_norm": 14.346508026123047, "learning_rate": 4.059633027522936e-06, "loss": 11.1728, "step": 265 }, { "epoch": 0.6036879432624114, "grad_norm": 14.408853530883789, "learning_rate": 4.036697247706423e-06, "loss": 11.4846, "step": 266 }, { "epoch": 0.6059574468085106, "grad_norm": 16.074113845825195, "learning_rate": 4.013761467889909e-06, "loss": 12.4972, "step": 267 }, { "epoch": 0.6082269503546099, "grad_norm": 15.124378204345703, "learning_rate": 3.9908256880733945e-06, "loss": 13.6839, "step": 268 }, { "epoch": 0.6104964539007092, "grad_norm": 17.83473014831543, "learning_rate": 3.967889908256881e-06, "loss": 11.5129, "step": 269 }, { "epoch": 0.6127659574468085, "grad_norm": 14.985913276672363, "learning_rate": 3.944954128440367e-06, "loss": 12.1707, "step": 270 }, { "epoch": 0.6150354609929078, "grad_norm": 13.082594871520996, "learning_rate": 3.922018348623853e-06, "loss": 11.5381, "step": 271 }, { "epoch": 0.6173049645390071, "grad_norm": 14.00425910949707, "learning_rate": 3.89908256880734e-06, "loss": 11.5322, "step": 272 }, { "epoch": 0.6195744680851064, "grad_norm": 16.796083450317383, "learning_rate": 3.876146788990826e-06, "loss": 10.927, "step": 273 }, { "epoch": 0.6218439716312056, "grad_norm": 14.159046173095703, "learning_rate": 3.853211009174313e-06, "loss": 11.5667, "step": 274 }, { "epoch": 0.624113475177305, "grad_norm": 14.538496971130371, "learning_rate": 3.830275229357798e-06, "loss": 12.3332, "step": 275 }, { "epoch": 0.6263829787234042, "grad_norm": 13.794122695922852, "learning_rate": 3.8073394495412848e-06, "loss": 10.7098, "step": 276 }, { "epoch": 0.6286524822695035, "grad_norm": 13.797811508178711, "learning_rate": 3.784403669724771e-06, "loss": 11.5682, "step": 277 }, { "epoch": 0.6309219858156029, "grad_norm": 15.259299278259277, "learning_rate": 3.7614678899082575e-06, "loss": 12.6547, "step": 278 }, { "epoch": 0.6331914893617021, "grad_norm": 13.827862739562988, "learning_rate": 3.738532110091743e-06, "loss": 11.2268, "step": 279 }, { "epoch": 0.6354609929078014, "grad_norm": 14.54641056060791, "learning_rate": 3.7155963302752295e-06, "loss": 12.3683, "step": 280 }, { "epoch": 0.6377304964539007, "grad_norm": 13.92435073852539, "learning_rate": 3.692660550458716e-06, "loss": 11.8067, "step": 281 }, { "epoch": 0.64, "grad_norm": 15.682398796081543, "learning_rate": 3.6697247706422022e-06, "loss": 11.2324, "step": 282 }, { "epoch": 0.6422695035460992, "grad_norm": 15.381531715393066, "learning_rate": 3.646788990825688e-06, "loss": 11.328, "step": 283 }, { "epoch": 0.6445390070921986, "grad_norm": 16.925100326538086, "learning_rate": 3.6238532110091746e-06, "loss": 12.026, "step": 284 }, { "epoch": 0.6468085106382979, "grad_norm": 15.899694442749023, "learning_rate": 3.600917431192661e-06, "loss": 11.7452, "step": 285 }, { "epoch": 0.6490780141843971, "grad_norm": 13.985481262207031, "learning_rate": 3.5779816513761473e-06, "loss": 10.9308, "step": 286 }, { "epoch": 0.6513475177304965, "grad_norm": 16.22553253173828, "learning_rate": 3.5550458715596333e-06, "loss": 10.0753, "step": 287 }, { "epoch": 0.6536170212765957, "grad_norm": 14.844727516174316, "learning_rate": 3.5321100917431193e-06, "loss": 11.2701, "step": 288 }, { "epoch": 0.655886524822695, "grad_norm": 14.071379661560059, "learning_rate": 3.5091743119266056e-06, "loss": 11.6251, "step": 289 }, { "epoch": 0.6581560283687943, "grad_norm": 15.52385139465332, "learning_rate": 3.486238532110092e-06, "loss": 11.5523, "step": 290 }, { "epoch": 0.6604255319148936, "grad_norm": 16.18393325805664, "learning_rate": 3.463302752293578e-06, "loss": 11.4416, "step": 291 }, { "epoch": 0.662695035460993, "grad_norm": 14.769004821777344, "learning_rate": 3.4403669724770644e-06, "loss": 11.2132, "step": 292 }, { "epoch": 0.6649645390070922, "grad_norm": 15.872430801391602, "learning_rate": 3.4174311926605508e-06, "loss": 12.0556, "step": 293 }, { "epoch": 0.6672340425531915, "grad_norm": 15.028341293334961, "learning_rate": 3.394495412844037e-06, "loss": 12.1023, "step": 294 }, { "epoch": 0.6695035460992907, "grad_norm": 14.808226585388184, "learning_rate": 3.371559633027523e-06, "loss": 12.0263, "step": 295 }, { "epoch": 0.6717730496453901, "grad_norm": 14.952188491821289, "learning_rate": 3.3486238532110095e-06, "loss": 11.5882, "step": 296 }, { "epoch": 0.6740425531914893, "grad_norm": 13.47593879699707, "learning_rate": 3.325688073394496e-06, "loss": 11.8359, "step": 297 }, { "epoch": 0.6763120567375887, "grad_norm": 14.836315155029297, "learning_rate": 3.3027522935779823e-06, "loss": 12.0032, "step": 298 }, { "epoch": 0.678581560283688, "grad_norm": 13.710811614990234, "learning_rate": 3.279816513761468e-06, "loss": 12.0126, "step": 299 }, { "epoch": 0.6808510638297872, "grad_norm": 15.23910903930664, "learning_rate": 3.256880733944954e-06, "loss": 12.3408, "step": 300 }, { "epoch": 0.6831205673758866, "grad_norm": 14.627053260803223, "learning_rate": 3.2339449541284406e-06, "loss": 11.5536, "step": 301 }, { "epoch": 0.6853900709219858, "grad_norm": 15.46848201751709, "learning_rate": 3.211009174311927e-06, "loss": 11.718, "step": 302 }, { "epoch": 0.6876595744680851, "grad_norm": 15.809585571289062, "learning_rate": 3.188073394495413e-06, "loss": 12.1575, "step": 303 }, { "epoch": 0.6899290780141843, "grad_norm": 13.710538864135742, "learning_rate": 3.1651376146788993e-06, "loss": 10.9346, "step": 304 }, { "epoch": 0.6921985815602837, "grad_norm": 13.729572296142578, "learning_rate": 3.1422018348623857e-06, "loss": 11.2859, "step": 305 }, { "epoch": 0.694468085106383, "grad_norm": 14.921198844909668, "learning_rate": 3.119266055045872e-06, "loss": 11.124, "step": 306 }, { "epoch": 0.6967375886524823, "grad_norm": 15.134315490722656, "learning_rate": 3.0963302752293576e-06, "loss": 10.7742, "step": 307 }, { "epoch": 0.6990070921985816, "grad_norm": 15.973776817321777, "learning_rate": 3.073394495412844e-06, "loss": 11.6534, "step": 308 }, { "epoch": 0.7012765957446808, "grad_norm": 14.368341445922852, "learning_rate": 3.0504587155963304e-06, "loss": 11.737, "step": 309 }, { "epoch": 0.7035460992907802, "grad_norm": 13.969265937805176, "learning_rate": 3.0275229357798168e-06, "loss": 12.7694, "step": 310 }, { "epoch": 0.7058156028368794, "grad_norm": 14.643651962280273, "learning_rate": 3.0045871559633027e-06, "loss": 11.3182, "step": 311 }, { "epoch": 0.7080851063829787, "grad_norm": 14.867914199829102, "learning_rate": 2.981651376146789e-06, "loss": 10.7874, "step": 312 }, { "epoch": 0.7103546099290781, "grad_norm": 14.654533386230469, "learning_rate": 2.9587155963302755e-06, "loss": 10.6292, "step": 313 }, { "epoch": 0.7126241134751773, "grad_norm": 15.625255584716797, "learning_rate": 2.935779816513762e-06, "loss": 11.6566, "step": 314 }, { "epoch": 0.7148936170212766, "grad_norm": 14.716096878051758, "learning_rate": 2.912844036697248e-06, "loss": 12.5436, "step": 315 }, { "epoch": 0.7171631205673759, "grad_norm": 14.492424011230469, "learning_rate": 2.8899082568807342e-06, "loss": 12.2842, "step": 316 }, { "epoch": 0.7194326241134752, "grad_norm": 14.774408340454102, "learning_rate": 2.8669724770642206e-06, "loss": 11.3632, "step": 317 }, { "epoch": 0.7217021276595744, "grad_norm": 14.195956230163574, "learning_rate": 2.844036697247707e-06, "loss": 11.5185, "step": 318 }, { "epoch": 0.7239716312056738, "grad_norm": 14.807626724243164, "learning_rate": 2.8211009174311925e-06, "loss": 12.0997, "step": 319 }, { "epoch": 0.7262411347517731, "grad_norm": 14.59691047668457, "learning_rate": 2.798165137614679e-06, "loss": 12.0345, "step": 320 }, { "epoch": 0.7285106382978723, "grad_norm": 13.609304428100586, "learning_rate": 2.7752293577981653e-06, "loss": 10.6789, "step": 321 }, { "epoch": 0.7307801418439717, "grad_norm": 14.703914642333984, "learning_rate": 2.7522935779816517e-06, "loss": 12.2577, "step": 322 }, { "epoch": 0.7330496453900709, "grad_norm": 15.197620391845703, "learning_rate": 2.7293577981651376e-06, "loss": 11.2931, "step": 323 }, { "epoch": 0.7353191489361702, "grad_norm": 14.85765552520752, "learning_rate": 2.706422018348624e-06, "loss": 10.0994, "step": 324 }, { "epoch": 0.7375886524822695, "grad_norm": 15.645622253417969, "learning_rate": 2.6834862385321104e-06, "loss": 11.114, "step": 325 }, { "epoch": 0.7398581560283688, "grad_norm": 17.191579818725586, "learning_rate": 2.6605504587155968e-06, "loss": 11.6119, "step": 326 }, { "epoch": 0.7421276595744681, "grad_norm": 15.106724739074707, "learning_rate": 2.6376146788990823e-06, "loss": 13.2085, "step": 327 }, { "epoch": 0.7443971631205674, "grad_norm": 16.031442642211914, "learning_rate": 2.6146788990825687e-06, "loss": 12.7513, "step": 328 }, { "epoch": 0.7466666666666667, "grad_norm": 14.646224021911621, "learning_rate": 2.591743119266055e-06, "loss": 11.8878, "step": 329 }, { "epoch": 0.7489361702127659, "grad_norm": 13.57841682434082, "learning_rate": 2.5688073394495415e-06, "loss": 11.742, "step": 330 }, { "epoch": 0.7512056737588653, "grad_norm": 16.555238723754883, "learning_rate": 2.5458715596330274e-06, "loss": 10.3593, "step": 331 }, { "epoch": 0.7534751773049645, "grad_norm": 14.708159446716309, "learning_rate": 2.522935779816514e-06, "loss": 11.9517, "step": 332 }, { "epoch": 0.7557446808510638, "grad_norm": 14.185422897338867, "learning_rate": 2.5e-06, "loss": 10.4678, "step": 333 }, { "epoch": 0.7580141843971632, "grad_norm": 14.449628829956055, "learning_rate": 2.4770642201834866e-06, "loss": 11.3252, "step": 334 }, { "epoch": 0.7602836879432624, "grad_norm": 15.00167465209961, "learning_rate": 2.4541284403669725e-06, "loss": 10.6833, "step": 335 }, { "epoch": 0.7625531914893617, "grad_norm": 15.32506275177002, "learning_rate": 2.431192660550459e-06, "loss": 12.312, "step": 336 }, { "epoch": 0.764822695035461, "grad_norm": 14.83922290802002, "learning_rate": 2.4082568807339453e-06, "loss": 11.155, "step": 337 }, { "epoch": 0.7670921985815603, "grad_norm": 15.836081504821777, "learning_rate": 2.3853211009174317e-06, "loss": 11.0223, "step": 338 }, { "epoch": 0.7693617021276595, "grad_norm": 14.72590446472168, "learning_rate": 2.3623853211009177e-06, "loss": 11.2304, "step": 339 }, { "epoch": 0.7716312056737589, "grad_norm": 13.718825340270996, "learning_rate": 2.339449541284404e-06, "loss": 11.2422, "step": 340 }, { "epoch": 0.7739007092198582, "grad_norm": 14.209959030151367, "learning_rate": 2.31651376146789e-06, "loss": 11.617, "step": 341 }, { "epoch": 0.7761702127659574, "grad_norm": 16.02104377746582, "learning_rate": 2.2935779816513764e-06, "loss": 10.9203, "step": 342 }, { "epoch": 0.7784397163120568, "grad_norm": 14.302445411682129, "learning_rate": 2.2706422018348624e-06, "loss": 13.048, "step": 343 }, { "epoch": 0.780709219858156, "grad_norm": 15.031492233276367, "learning_rate": 2.2477064220183487e-06, "loss": 11.6518, "step": 344 }, { "epoch": 0.7829787234042553, "grad_norm": 14.67408561706543, "learning_rate": 2.224770642201835e-06, "loss": 11.5427, "step": 345 }, { "epoch": 0.7852482269503546, "grad_norm": 16.907594680786133, "learning_rate": 2.2018348623853215e-06, "loss": 10.5024, "step": 346 }, { "epoch": 0.7875177304964539, "grad_norm": 15.81796932220459, "learning_rate": 2.1788990825688075e-06, "loss": 11.84, "step": 347 }, { "epoch": 0.7897872340425532, "grad_norm": 15.947940826416016, "learning_rate": 2.155963302752294e-06, "loss": 11.1782, "step": 348 }, { "epoch": 0.7920567375886525, "grad_norm": 14.52432918548584, "learning_rate": 2.13302752293578e-06, "loss": 10.9849, "step": 349 }, { "epoch": 0.7943262411347518, "grad_norm": 15.454471588134766, "learning_rate": 2.110091743119266e-06, "loss": 11.7476, "step": 350 }, { "epoch": 0.796595744680851, "grad_norm": 15.229212760925293, "learning_rate": 2.0871559633027526e-06, "loss": 10.9708, "step": 351 }, { "epoch": 0.7988652482269504, "grad_norm": 13.798996925354004, "learning_rate": 2.064220183486239e-06, "loss": 11.2339, "step": 352 }, { "epoch": 0.8011347517730496, "grad_norm": 15.175180435180664, "learning_rate": 2.041284403669725e-06, "loss": 12.0392, "step": 353 }, { "epoch": 0.8034042553191489, "grad_norm": 14.56845760345459, "learning_rate": 2.0183486238532113e-06, "loss": 11.5783, "step": 354 }, { "epoch": 0.8056737588652483, "grad_norm": 15.708647727966309, "learning_rate": 1.9954128440366973e-06, "loss": 12.5884, "step": 355 }, { "epoch": 0.8079432624113475, "grad_norm": 15.064566612243652, "learning_rate": 1.9724770642201837e-06, "loss": 11.3184, "step": 356 }, { "epoch": 0.8102127659574468, "grad_norm": 15.309610366821289, "learning_rate": 1.94954128440367e-06, "loss": 11.0746, "step": 357 }, { "epoch": 0.8124822695035461, "grad_norm": 14.646039009094238, "learning_rate": 1.9266055045871564e-06, "loss": 11.3354, "step": 358 }, { "epoch": 0.8147517730496454, "grad_norm": 15.404284477233887, "learning_rate": 1.9036697247706424e-06, "loss": 12.3391, "step": 359 }, { "epoch": 0.8170212765957446, "grad_norm": 15.028493881225586, "learning_rate": 1.8807339449541288e-06, "loss": 11.4006, "step": 360 }, { "epoch": 0.819290780141844, "grad_norm": 13.99733829498291, "learning_rate": 1.8577981651376147e-06, "loss": 10.5002, "step": 361 }, { "epoch": 0.8215602836879433, "grad_norm": 14.99713134765625, "learning_rate": 1.8348623853211011e-06, "loss": 11.9022, "step": 362 }, { "epoch": 0.8238297872340425, "grad_norm": 14.806184768676758, "learning_rate": 1.8119266055045873e-06, "loss": 10.8005, "step": 363 }, { "epoch": 0.8260992907801419, "grad_norm": 15.64913558959961, "learning_rate": 1.7889908256880737e-06, "loss": 11.5869, "step": 364 }, { "epoch": 0.8283687943262411, "grad_norm": 14.396153450012207, "learning_rate": 1.7660550458715596e-06, "loss": 11.1426, "step": 365 }, { "epoch": 0.8306382978723404, "grad_norm": 14.17025089263916, "learning_rate": 1.743119266055046e-06, "loss": 10.9515, "step": 366 }, { "epoch": 0.8329078014184397, "grad_norm": 16.30831527709961, "learning_rate": 1.7201834862385322e-06, "loss": 11.2075, "step": 367 }, { "epoch": 0.835177304964539, "grad_norm": 14.669882774353027, "learning_rate": 1.6972477064220186e-06, "loss": 11.1552, "step": 368 }, { "epoch": 0.8374468085106384, "grad_norm": 16.9696044921875, "learning_rate": 1.6743119266055047e-06, "loss": 11.1924, "step": 369 }, { "epoch": 0.8397163120567376, "grad_norm": 15.57226848602295, "learning_rate": 1.6513761467889911e-06, "loss": 13.3372, "step": 370 }, { "epoch": 0.8419858156028369, "grad_norm": 13.730722427368164, "learning_rate": 1.628440366972477e-06, "loss": 10.6736, "step": 371 }, { "epoch": 0.8442553191489361, "grad_norm": 15.612845420837402, "learning_rate": 1.6055045871559635e-06, "loss": 11.4974, "step": 372 }, { "epoch": 0.8465248226950355, "grad_norm": 14.862382888793945, "learning_rate": 1.5825688073394496e-06, "loss": 11.5794, "step": 373 }, { "epoch": 0.8487943262411347, "grad_norm": 15.997152328491211, "learning_rate": 1.559633027522936e-06, "loss": 11.665, "step": 374 }, { "epoch": 0.851063829787234, "grad_norm": 16.392852783203125, "learning_rate": 1.536697247706422e-06, "loss": 11.4402, "step": 375 }, { "epoch": 0.8533333333333334, "grad_norm": 15.594365119934082, "learning_rate": 1.5137614678899084e-06, "loss": 11.9343, "step": 376 }, { "epoch": 0.8556028368794326, "grad_norm": 14.07176685333252, "learning_rate": 1.4908256880733945e-06, "loss": 12.0122, "step": 377 }, { "epoch": 0.857872340425532, "grad_norm": 15.689149856567383, "learning_rate": 1.467889908256881e-06, "loss": 11.3892, "step": 378 }, { "epoch": 0.8601418439716312, "grad_norm": 14.251015663146973, "learning_rate": 1.4449541284403671e-06, "loss": 10.9948, "step": 379 }, { "epoch": 0.8624113475177305, "grad_norm": 15.502103805541992, "learning_rate": 1.4220183486238535e-06, "loss": 11.3999, "step": 380 }, { "epoch": 0.8646808510638297, "grad_norm": 15.18033218383789, "learning_rate": 1.3990825688073395e-06, "loss": 12.4196, "step": 381 }, { "epoch": 0.8669503546099291, "grad_norm": 19.31058120727539, "learning_rate": 1.3761467889908258e-06, "loss": 12.5463, "step": 382 }, { "epoch": 0.8692198581560284, "grad_norm": 14.470500946044922, "learning_rate": 1.353211009174312e-06, "loss": 11.314, "step": 383 }, { "epoch": 0.8714893617021277, "grad_norm": 15.050067901611328, "learning_rate": 1.3302752293577984e-06, "loss": 10.8812, "step": 384 }, { "epoch": 0.873758865248227, "grad_norm": 14.32825756072998, "learning_rate": 1.3073394495412844e-06, "loss": 11.1404, "step": 385 }, { "epoch": 0.8760283687943262, "grad_norm": 14.580878257751465, "learning_rate": 1.2844036697247707e-06, "loss": 11.1658, "step": 386 }, { "epoch": 0.8782978723404256, "grad_norm": 15.502610206604004, "learning_rate": 1.261467889908257e-06, "loss": 10.8975, "step": 387 }, { "epoch": 0.8805673758865248, "grad_norm": 14.879796981811523, "learning_rate": 1.2385321100917433e-06, "loss": 11.8596, "step": 388 }, { "epoch": 0.8828368794326241, "grad_norm": 14.855901718139648, "learning_rate": 1.2155963302752295e-06, "loss": 10.9322, "step": 389 }, { "epoch": 0.8851063829787233, "grad_norm": 14.704005241394043, "learning_rate": 1.1926605504587159e-06, "loss": 11.0192, "step": 390 }, { "epoch": 0.8873758865248227, "grad_norm": 15.715887069702148, "learning_rate": 1.169724770642202e-06, "loss": 10.5179, "step": 391 }, { "epoch": 0.889645390070922, "grad_norm": 14.12143611907959, "learning_rate": 1.1467889908256882e-06, "loss": 11.7263, "step": 392 }, { "epoch": 0.8919148936170213, "grad_norm": 14.398093223571777, "learning_rate": 1.1238532110091744e-06, "loss": 10.0019, "step": 393 }, { "epoch": 0.8941843971631206, "grad_norm": 14.590864181518555, "learning_rate": 1.1009174311926608e-06, "loss": 10.7073, "step": 394 }, { "epoch": 0.8964539007092198, "grad_norm": 15.373684883117676, "learning_rate": 1.077981651376147e-06, "loss": 12.1856, "step": 395 }, { "epoch": 0.8987234042553192, "grad_norm": 15.212281227111816, "learning_rate": 1.055045871559633e-06, "loss": 11.5947, "step": 396 }, { "epoch": 0.9009929078014184, "grad_norm": 15.089335441589355, "learning_rate": 1.0321100917431195e-06, "loss": 11.6402, "step": 397 }, { "epoch": 0.9032624113475177, "grad_norm": 15.367538452148438, "learning_rate": 1.0091743119266057e-06, "loss": 11.8477, "step": 398 }, { "epoch": 0.9055319148936171, "grad_norm": 15.173749923706055, "learning_rate": 9.862385321100918e-07, "loss": 12.0116, "step": 399 }, { "epoch": 0.9078014184397163, "grad_norm": 14.271236419677734, "learning_rate": 9.633027522935782e-07, "loss": 11.2358, "step": 400 }, { "epoch": 0.9100709219858156, "grad_norm": 15.217755317687988, "learning_rate": 9.403669724770644e-07, "loss": 12.391, "step": 401 }, { "epoch": 0.9123404255319149, "grad_norm": 18.121543884277344, "learning_rate": 9.174311926605506e-07, "loss": 10.474, "step": 402 }, { "epoch": 0.9146099290780142, "grad_norm": 14.050172805786133, "learning_rate": 8.944954128440368e-07, "loss": 10.2314, "step": 403 }, { "epoch": 0.9168794326241134, "grad_norm": 14.757338523864746, "learning_rate": 8.71559633027523e-07, "loss": 10.9171, "step": 404 }, { "epoch": 0.9191489361702128, "grad_norm": 14.966742515563965, "learning_rate": 8.486238532110093e-07, "loss": 10.6402, "step": 405 }, { "epoch": 0.9214184397163121, "grad_norm": 16.213253021240234, "learning_rate": 8.256880733944956e-07, "loss": 12.6368, "step": 406 }, { "epoch": 0.9236879432624113, "grad_norm": 14.179901123046875, "learning_rate": 8.027522935779817e-07, "loss": 12.0302, "step": 407 }, { "epoch": 0.9259574468085107, "grad_norm": 14.931614875793457, "learning_rate": 7.79816513761468e-07, "loss": 10.4819, "step": 408 }, { "epoch": 0.9282269503546099, "grad_norm": 17.238327026367188, "learning_rate": 7.568807339449542e-07, "loss": 12.8051, "step": 409 }, { "epoch": 0.9304964539007092, "grad_norm": 16.47130584716797, "learning_rate": 7.339449541284405e-07, "loss": 12.2561, "step": 410 }, { "epoch": 0.9327659574468085, "grad_norm": 14.333356857299805, "learning_rate": 7.110091743119267e-07, "loss": 10.8216, "step": 411 }, { "epoch": 0.9350354609929078, "grad_norm": 14.367188453674316, "learning_rate": 6.880733944954129e-07, "loss": 10.7775, "step": 412 }, { "epoch": 0.9373049645390071, "grad_norm": 14.346342086791992, "learning_rate": 6.651376146788992e-07, "loss": 11.6767, "step": 413 }, { "epoch": 0.9395744680851064, "grad_norm": 13.739248275756836, "learning_rate": 6.422018348623854e-07, "loss": 11.0975, "step": 414 }, { "epoch": 0.9418439716312057, "grad_norm": 14.31313705444336, "learning_rate": 6.192660550458716e-07, "loss": 11.1958, "step": 415 }, { "epoch": 0.9441134751773049, "grad_norm": 14.764827728271484, "learning_rate": 5.963302752293579e-07, "loss": 11.6007, "step": 416 }, { "epoch": 0.9463829787234043, "grad_norm": 14.724400520324707, "learning_rate": 5.733944954128441e-07, "loss": 10.916, "step": 417 }, { "epoch": 0.9486524822695035, "grad_norm": 14.651395797729492, "learning_rate": 5.504587155963304e-07, "loss": 12.0351, "step": 418 }, { "epoch": 0.9509219858156028, "grad_norm": 14.940927505493164, "learning_rate": 5.275229357798165e-07, "loss": 11.6732, "step": 419 }, { "epoch": 0.9531914893617022, "grad_norm": 14.852497100830078, "learning_rate": 5.045871559633028e-07, "loss": 11.5796, "step": 420 }, { "epoch": 0.9554609929078014, "grad_norm": 15.628256797790527, "learning_rate": 4.816513761467891e-07, "loss": 11.3813, "step": 421 }, { "epoch": 0.9577304964539007, "grad_norm": 15.39635181427002, "learning_rate": 4.587155963302753e-07, "loss": 12.3113, "step": 422 }, { "epoch": 0.96, "grad_norm": 14.959100723266602, "learning_rate": 4.357798165137615e-07, "loss": 11.0719, "step": 423 }, { "epoch": 0.9622695035460993, "grad_norm": 14.202091217041016, "learning_rate": 4.128440366972478e-07, "loss": 11.4155, "step": 424 }, { "epoch": 0.9645390070921985, "grad_norm": 16.139972686767578, "learning_rate": 3.89908256880734e-07, "loss": 11.8673, "step": 425 }, { "epoch": 0.9668085106382979, "grad_norm": 15.232097625732422, "learning_rate": 3.6697247706422023e-07, "loss": 12.1347, "step": 426 }, { "epoch": 0.9690780141843972, "grad_norm": 15.608128547668457, "learning_rate": 3.4403669724770646e-07, "loss": 12.2494, "step": 427 }, { "epoch": 0.9713475177304964, "grad_norm": 14.872684478759766, "learning_rate": 3.211009174311927e-07, "loss": 11.0248, "step": 428 }, { "epoch": 0.9736170212765958, "grad_norm": 17.246606826782227, "learning_rate": 2.9816513761467896e-07, "loss": 13.684, "step": 429 }, { "epoch": 0.975886524822695, "grad_norm": 15.021284103393555, "learning_rate": 2.752293577981652e-07, "loss": 12.0976, "step": 430 }, { "epoch": 0.9781560283687943, "grad_norm": 15.2746000289917, "learning_rate": 2.522935779816514e-07, "loss": 12.0998, "step": 431 }, { "epoch": 0.9804255319148936, "grad_norm": 15.034667015075684, "learning_rate": 2.2935779816513764e-07, "loss": 10.9027, "step": 432 }, { "epoch": 0.9826950354609929, "grad_norm": 15.840072631835938, "learning_rate": 2.064220183486239e-07, "loss": 11.9374, "step": 433 }, { "epoch": 0.9849645390070922, "grad_norm": 14.527645111083984, "learning_rate": 1.8348623853211012e-07, "loss": 12.0503, "step": 434 }, { "epoch": 0.9872340425531915, "grad_norm": 16.18238639831543, "learning_rate": 1.6055045871559634e-07, "loss": 11.7978, "step": 435 }, { "epoch": 0.9895035460992908, "grad_norm": 16.0859432220459, "learning_rate": 1.376146788990826e-07, "loss": 11.879, "step": 436 }, { "epoch": 0.99177304964539, "grad_norm": 14.35853099822998, "learning_rate": 1.1467889908256882e-07, "loss": 11.066, "step": 437 }, { "epoch": 0.9940425531914894, "grad_norm": 14.60539436340332, "learning_rate": 9.174311926605506e-08, "loss": 11.9377, "step": 438 }, { "epoch": 0.9963120567375886, "grad_norm": 15.746533393859863, "learning_rate": 6.88073394495413e-08, "loss": 10.6221, "step": 439 }, { "epoch": 0.9985815602836879, "grad_norm": 14.928288459777832, "learning_rate": 4.587155963302753e-08, "loss": 11.2228, "step": 440 }, { "epoch": 1.0, "grad_norm": 14.731184005737305, "learning_rate": 2.2935779816513765e-08, "loss": 8.5075, "step": 441 } ], "logging_steps": 1, "max_steps": 441, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 5000, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 1.9858230313182413e+17, "train_batch_size": 2, "trial_name": null, "trial_params": null }