{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 2.0, "eval_steps": 500, "global_step": 1106, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0018083182640144665, "grad_norm": 955.802978515625, "learning_rate": 1.7857142857142858e-07, "loss": 1.9875, "step": 1 }, { "epoch": 0.003616636528028933, "grad_norm": 1658.4447021484375, "learning_rate": 3.5714285714285716e-07, "loss": 2.1509, "step": 2 }, { "epoch": 0.0054249547920434, "grad_norm": 655.71484375, "learning_rate": 5.357142857142857e-07, "loss": 2.215, "step": 3 }, { "epoch": 0.007233273056057866, "grad_norm": 461.0606689453125, "learning_rate": 7.142857142857143e-07, "loss": 2.2237, "step": 4 }, { "epoch": 0.009041591320072333, "grad_norm": 559.2396850585938, "learning_rate": 8.928571428571429e-07, "loss": 2.1465, "step": 5 }, { "epoch": 0.0108499095840868, "grad_norm": 988.4732666015625, "learning_rate": 1.0714285714285714e-06, "loss": 2.1822, "step": 6 }, { "epoch": 0.012658227848101266, "grad_norm": 1084.386962890625, "learning_rate": 1.25e-06, "loss": 2.1443, "step": 7 }, { "epoch": 0.014466546112115732, "grad_norm": 1068.6846923828125, "learning_rate": 1.4285714285714286e-06, "loss": 2.1245, "step": 8 }, { "epoch": 0.0162748643761302, "grad_norm": 1074.8746337890625, "learning_rate": 1.6071428571428574e-06, "loss": 2.1432, "step": 9 }, { "epoch": 0.018083182640144666, "grad_norm": 569.0439453125, "learning_rate": 1.7857142857142859e-06, "loss": 2.1648, "step": 10 }, { "epoch": 0.019891500904159132, "grad_norm": 1904.287109375, "learning_rate": 1.9642857142857144e-06, "loss": 2.2865, "step": 11 }, { "epoch": 0.0216998191681736, "grad_norm": 1574.3634033203125, "learning_rate": 2.1428571428571427e-06, "loss": 2.4159, "step": 12 }, { "epoch": 0.023508137432188065, "grad_norm": 616.3699951171875, "learning_rate": 2.321428571428572e-06, "loss": 2.1203, "step": 13 }, { "epoch": 0.02531645569620253, "grad_norm": 247.9285430908203, "learning_rate": 2.5e-06, "loss": 1.758, "step": 14 }, { "epoch": 0.027124773960216998, "grad_norm": 150.1542510986328, "learning_rate": 2.6785714285714285e-06, "loss": 1.8833, "step": 15 }, { "epoch": 0.028933092224231464, "grad_norm": 128.3291778564453, "learning_rate": 2.8571428571428573e-06, "loss": 1.753, "step": 16 }, { "epoch": 0.03074141048824593, "grad_norm": 81.46281433105469, "learning_rate": 3.0357142857142856e-06, "loss": 1.7433, "step": 17 }, { "epoch": 0.0325497287522604, "grad_norm": 54.90946578979492, "learning_rate": 3.2142857142857147e-06, "loss": 1.6662, "step": 18 }, { "epoch": 0.034358047016274866, "grad_norm": 91.00289916992188, "learning_rate": 3.3928571428571435e-06, "loss": 1.5335, "step": 19 }, { "epoch": 0.03616636528028933, "grad_norm": 97.76078033447266, "learning_rate": 3.5714285714285718e-06, "loss": 1.4818, "step": 20 }, { "epoch": 0.0379746835443038, "grad_norm": 161.85130310058594, "learning_rate": 3.7500000000000005e-06, "loss": 1.4877, "step": 21 }, { "epoch": 0.039783001808318265, "grad_norm": 74.29920959472656, "learning_rate": 3.928571428571429e-06, "loss": 1.543, "step": 22 }, { "epoch": 0.04159132007233273, "grad_norm": 64.86253356933594, "learning_rate": 4.107142857142857e-06, "loss": 1.4513, "step": 23 }, { "epoch": 0.0433996383363472, "grad_norm": 29.356834411621094, "learning_rate": 4.2857142857142855e-06, "loss": 1.6001, "step": 24 }, { "epoch": 0.045207956600361664, "grad_norm": 72.11982727050781, "learning_rate": 4.464285714285715e-06, "loss": 1.6224, "step": 25 }, { "epoch": 0.04701627486437613, "grad_norm": 62.90475845336914, "learning_rate": 4.642857142857144e-06, "loss": 1.2117, "step": 26 }, { "epoch": 0.048824593128390596, "grad_norm": 43.70161819458008, "learning_rate": 4.821428571428572e-06, "loss": 1.3333, "step": 27 }, { "epoch": 0.05063291139240506, "grad_norm": 49.87014389038086, "learning_rate": 5e-06, "loss": 1.301, "step": 28 }, { "epoch": 0.05244122965641953, "grad_norm": 55.53972625732422, "learning_rate": 5.1785714285714296e-06, "loss": 1.2089, "step": 29 }, { "epoch": 0.054249547920433995, "grad_norm": 38.77712631225586, "learning_rate": 5.357142857142857e-06, "loss": 1.201, "step": 30 }, { "epoch": 0.05605786618444846, "grad_norm": 7.504881381988525, "learning_rate": 5.535714285714286e-06, "loss": 1.1594, "step": 31 }, { "epoch": 0.05786618444846293, "grad_norm": 9.592388153076172, "learning_rate": 5.7142857142857145e-06, "loss": 1.1372, "step": 32 }, { "epoch": 0.059674502712477394, "grad_norm": 11.970796585083008, "learning_rate": 5.892857142857144e-06, "loss": 1.1472, "step": 33 }, { "epoch": 0.06148282097649186, "grad_norm": 35.65814208984375, "learning_rate": 6.071428571428571e-06, "loss": 1.1523, "step": 34 }, { "epoch": 0.06329113924050633, "grad_norm": 22.04935646057129, "learning_rate": 6.25e-06, "loss": 1.1485, "step": 35 }, { "epoch": 0.0650994575045208, "grad_norm": 29.375736236572266, "learning_rate": 6.4285714285714295e-06, "loss": 1.2127, "step": 36 }, { "epoch": 0.06690777576853527, "grad_norm": 12.474059104919434, "learning_rate": 6.607142857142858e-06, "loss": 1.1836, "step": 37 }, { "epoch": 0.06871609403254973, "grad_norm": 23.542701721191406, "learning_rate": 6.785714285714287e-06, "loss": 1.0997, "step": 38 }, { "epoch": 0.0705244122965642, "grad_norm": 4.241347789764404, "learning_rate": 6.964285714285714e-06, "loss": 1.0194, "step": 39 }, { "epoch": 0.07233273056057866, "grad_norm": 6.472638130187988, "learning_rate": 7.1428571428571436e-06, "loss": 1.156, "step": 40 }, { "epoch": 0.07414104882459313, "grad_norm": 6.310609340667725, "learning_rate": 7.321428571428572e-06, "loss": 1.0258, "step": 41 }, { "epoch": 0.0759493670886076, "grad_norm": 70.7113037109375, "learning_rate": 7.500000000000001e-06, "loss": 1.0681, "step": 42 }, { "epoch": 0.07775768535262206, "grad_norm": 35.99663543701172, "learning_rate": 7.67857142857143e-06, "loss": 1.0636, "step": 43 }, { "epoch": 0.07956600361663653, "grad_norm": 6.671940326690674, "learning_rate": 7.857142857142858e-06, "loss": 1.0424, "step": 44 }, { "epoch": 0.081374321880651, "grad_norm": 4.112735748291016, "learning_rate": 8.035714285714286e-06, "loss": 1.126, "step": 45 }, { "epoch": 0.08318264014466546, "grad_norm": 22.005268096923828, "learning_rate": 8.214285714285714e-06, "loss": 1.1, "step": 46 }, { "epoch": 0.08499095840867993, "grad_norm": 15.775781631469727, "learning_rate": 8.392857142857144e-06, "loss": 1.1077, "step": 47 }, { "epoch": 0.0867992766726944, "grad_norm": 4.671652793884277, "learning_rate": 8.571428571428571e-06, "loss": 1.1422, "step": 48 }, { "epoch": 0.08860759493670886, "grad_norm": 7.300853252410889, "learning_rate": 8.750000000000001e-06, "loss": 1.1567, "step": 49 }, { "epoch": 0.09041591320072333, "grad_norm": 4.276039123535156, "learning_rate": 8.92857142857143e-06, "loss": 1.1319, "step": 50 }, { "epoch": 0.0922242314647378, "grad_norm": 3.374176263809204, "learning_rate": 9.107142857142858e-06, "loss": 1.0241, "step": 51 }, { "epoch": 0.09403254972875226, "grad_norm": 5.397779941558838, "learning_rate": 9.285714285714288e-06, "loss": 1.0002, "step": 52 }, { "epoch": 0.09584086799276673, "grad_norm": 3.306974411010742, "learning_rate": 9.464285714285714e-06, "loss": 1.0143, "step": 53 }, { "epoch": 0.09764918625678119, "grad_norm": 3.2510509490966797, "learning_rate": 9.642857142857144e-06, "loss": 1.0481, "step": 54 }, { "epoch": 0.09945750452079566, "grad_norm": 3.4914193153381348, "learning_rate": 9.821428571428573e-06, "loss": 1.0573, "step": 55 }, { "epoch": 0.10126582278481013, "grad_norm": 3.341156244277954, "learning_rate": 1e-05, "loss": 1.0949, "step": 56 }, { "epoch": 0.10307414104882459, "grad_norm": 3.0584967136383057, "learning_rate": 9.999977619961366e-06, "loss": 0.9912, "step": 57 }, { "epoch": 0.10488245931283906, "grad_norm": 3.5706567764282227, "learning_rate": 9.999910480045805e-06, "loss": 1.0079, "step": 58 }, { "epoch": 0.10669077757685352, "grad_norm": 8.911609649658203, "learning_rate": 9.999798580854356e-06, "loss": 1.0254, "step": 59 }, { "epoch": 0.10849909584086799, "grad_norm": 4.2039337158203125, "learning_rate": 9.999641923388745e-06, "loss": 1.0342, "step": 60 }, { "epoch": 0.11030741410488246, "grad_norm": 4.725396633148193, "learning_rate": 9.999440509051367e-06, "loss": 1.0969, "step": 61 }, { "epoch": 0.11211573236889692, "grad_norm": 3.846874952316284, "learning_rate": 9.999194339645292e-06, "loss": 1.0285, "step": 62 }, { "epoch": 0.11392405063291139, "grad_norm": 13.786543846130371, "learning_rate": 9.998903417374228e-06, "loss": 0.9999, "step": 63 }, { "epoch": 0.11573236889692586, "grad_norm": 4.326488971710205, "learning_rate": 9.998567744842518e-06, "loss": 0.9069, "step": 64 }, { "epoch": 0.11754068716094032, "grad_norm": 4.657455921173096, "learning_rate": 9.998187325055107e-06, "loss": 1.0412, "step": 65 }, { "epoch": 0.11934900542495479, "grad_norm": 5.258742809295654, "learning_rate": 9.997762161417517e-06, "loss": 0.9796, "step": 66 }, { "epoch": 0.12115732368896925, "grad_norm": 4.375807762145996, "learning_rate": 9.997292257735822e-06, "loss": 1.0077, "step": 67 }, { "epoch": 0.12296564195298372, "grad_norm": 3.8544225692749023, "learning_rate": 9.996777618216608e-06, "loss": 0.9353, "step": 68 }, { "epoch": 0.12477396021699819, "grad_norm": 3.908520221710205, "learning_rate": 9.996218247466932e-06, "loss": 1.0263, "step": 69 }, { "epoch": 0.12658227848101267, "grad_norm": 4.030512809753418, "learning_rate": 9.995614150494293e-06, "loss": 0.8691, "step": 70 }, { "epoch": 0.12839059674502712, "grad_norm": 3.8508689403533936, "learning_rate": 9.994965332706574e-06, "loss": 0.8811, "step": 71 }, { "epoch": 0.1301989150090416, "grad_norm": 4.332608699798584, "learning_rate": 9.994271799912004e-06, "loss": 0.9502, "step": 72 }, { "epoch": 0.13200723327305605, "grad_norm": 4.848439693450928, "learning_rate": 9.993533558319098e-06, "loss": 0.9743, "step": 73 }, { "epoch": 0.13381555153707053, "grad_norm": 5.04752779006958, "learning_rate": 9.992750614536606e-06, "loss": 0.9736, "step": 74 }, { "epoch": 0.13562386980108498, "grad_norm": 5.179821491241455, "learning_rate": 9.991922975573453e-06, "loss": 1.1478, "step": 75 }, { "epoch": 0.13743218806509946, "grad_norm": 4.519721984863281, "learning_rate": 9.991050648838676e-06, "loss": 0.8618, "step": 76 }, { "epoch": 0.13924050632911392, "grad_norm": 4.399446487426758, "learning_rate": 9.990133642141359e-06, "loss": 0.8647, "step": 77 }, { "epoch": 0.1410488245931284, "grad_norm": 4.706704139709473, "learning_rate": 9.989171963690556e-06, "loss": 0.9119, "step": 78 }, { "epoch": 0.14285714285714285, "grad_norm": 4.476073741912842, "learning_rate": 9.988165622095233e-06, "loss": 0.9022, "step": 79 }, { "epoch": 0.14466546112115733, "grad_norm": 5.258116245269775, "learning_rate": 9.987114626364172e-06, "loss": 0.9127, "step": 80 }, { "epoch": 0.14647377938517178, "grad_norm": 5.020689964294434, "learning_rate": 9.986018985905901e-06, "loss": 0.8311, "step": 81 }, { "epoch": 0.14828209764918626, "grad_norm": 5.608833312988281, "learning_rate": 9.984878710528615e-06, "loss": 0.8064, "step": 82 }, { "epoch": 0.15009041591320071, "grad_norm": 10.480090141296387, "learning_rate": 9.983693810440073e-06, "loss": 0.8369, "step": 83 }, { "epoch": 0.1518987341772152, "grad_norm": 10.647453308105469, "learning_rate": 9.982464296247523e-06, "loss": 0.8526, "step": 84 }, { "epoch": 0.15370705244122965, "grad_norm": 6.658600330352783, "learning_rate": 9.98119017895759e-06, "loss": 0.8619, "step": 85 }, { "epoch": 0.15551537070524413, "grad_norm": 7.7756171226501465, "learning_rate": 9.979871469976197e-06, "loss": 0.8356, "step": 86 }, { "epoch": 0.15732368896925858, "grad_norm": 6.902933120727539, "learning_rate": 9.978508181108442e-06, "loss": 0.8544, "step": 87 }, { "epoch": 0.15913200723327306, "grad_norm": 6.575014591217041, "learning_rate": 9.97710032455851e-06, "loss": 0.7825, "step": 88 }, { "epoch": 0.1609403254972875, "grad_norm": 5.8472442626953125, "learning_rate": 9.975647912929558e-06, "loss": 0.7282, "step": 89 }, { "epoch": 0.162748643761302, "grad_norm": 6.694021701812744, "learning_rate": 9.974150959223591e-06, "loss": 0.8255, "step": 90 }, { "epoch": 0.16455696202531644, "grad_norm": 6.769155979156494, "learning_rate": 9.972609476841368e-06, "loss": 0.7658, "step": 91 }, { "epoch": 0.16636528028933092, "grad_norm": 6.8951826095581055, "learning_rate": 9.971023479582258e-06, "loss": 0.755, "step": 92 }, { "epoch": 0.16817359855334538, "grad_norm": 6.742767810821533, "learning_rate": 9.969392981644138e-06, "loss": 0.8451, "step": 93 }, { "epoch": 0.16998191681735986, "grad_norm": 6.182243347167969, "learning_rate": 9.967717997623245e-06, "loss": 0.7149, "step": 94 }, { "epoch": 0.1717902350813743, "grad_norm": 6.797354221343994, "learning_rate": 9.965998542514066e-06, "loss": 0.6718, "step": 95 }, { "epoch": 0.1735985533453888, "grad_norm": 6.560754299163818, "learning_rate": 9.964234631709188e-06, "loss": 0.7059, "step": 96 }, { "epoch": 0.17540687160940324, "grad_norm": 6.439713954925537, "learning_rate": 9.962426280999168e-06, "loss": 0.6795, "step": 97 }, { "epoch": 0.17721518987341772, "grad_norm": 6.930069923400879, "learning_rate": 9.960573506572391e-06, "loss": 0.6911, "step": 98 }, { "epoch": 0.17902350813743217, "grad_norm": 6.315411567687988, "learning_rate": 9.95867632501492e-06, "loss": 0.6717, "step": 99 }, { "epoch": 0.18083182640144665, "grad_norm": 6.522010326385498, "learning_rate": 9.956734753310355e-06, "loss": 0.7603, "step": 100 }, { "epoch": 0.18264014466546113, "grad_norm": 5.4353556632995605, "learning_rate": 9.954748808839675e-06, "loss": 0.6319, "step": 101 }, { "epoch": 0.1844484629294756, "grad_norm": 5.75354528427124, "learning_rate": 9.952718509381086e-06, "loss": 0.7399, "step": 102 }, { "epoch": 0.18625678119349007, "grad_norm": 5.351419925689697, "learning_rate": 9.950643873109861e-06, "loss": 0.6617, "step": 103 }, { "epoch": 0.18806509945750452, "grad_norm": 5.965552806854248, "learning_rate": 9.948524918598175e-06, "loss": 0.6314, "step": 104 }, { "epoch": 0.189873417721519, "grad_norm": 5.747123718261719, "learning_rate": 9.946361664814942e-06, "loss": 0.6604, "step": 105 }, { "epoch": 0.19168173598553345, "grad_norm": 5.316325664520264, "learning_rate": 9.944154131125643e-06, "loss": 0.5935, "step": 106 }, { "epoch": 0.19349005424954793, "grad_norm": 5.224924564361572, "learning_rate": 9.941902337292156e-06, "loss": 0.5308, "step": 107 }, { "epoch": 0.19529837251356238, "grad_norm": 5.287252902984619, "learning_rate": 9.93960630347257e-06, "loss": 0.6041, "step": 108 }, { "epoch": 0.19710669077757687, "grad_norm": 5.332649230957031, "learning_rate": 9.937266050221015e-06, "loss": 0.5528, "step": 109 }, { "epoch": 0.19891500904159132, "grad_norm": 5.89270544052124, "learning_rate": 9.934881598487478e-06, "loss": 0.6338, "step": 110 }, { "epoch": 0.2007233273056058, "grad_norm": 5.446334362030029, "learning_rate": 9.932452969617607e-06, "loss": 0.5772, "step": 111 }, { "epoch": 0.20253164556962025, "grad_norm": 6.122445106506348, "learning_rate": 9.929980185352525e-06, "loss": 0.5932, "step": 112 }, { "epoch": 0.20433996383363473, "grad_norm": 4.830559253692627, "learning_rate": 9.927463267828635e-06, "loss": 0.528, "step": 113 }, { "epoch": 0.20614828209764918, "grad_norm": 4.59034538269043, "learning_rate": 9.924902239577419e-06, "loss": 0.4988, "step": 114 }, { "epoch": 0.20795660036166366, "grad_norm": 4.778143405914307, "learning_rate": 9.922297123525244e-06, "loss": 0.6061, "step": 115 }, { "epoch": 0.20976491862567812, "grad_norm": 5.2140398025512695, "learning_rate": 9.91964794299315e-06, "loss": 0.514, "step": 116 }, { "epoch": 0.2115732368896926, "grad_norm": 6.282818794250488, "learning_rate": 9.91695472169664e-06, "loss": 0.4593, "step": 117 }, { "epoch": 0.21338155515370705, "grad_norm": 4.06541633605957, "learning_rate": 9.914217483745472e-06, "loss": 0.5351, "step": 118 }, { "epoch": 0.21518987341772153, "grad_norm": 4.0099616050720215, "learning_rate": 9.911436253643445e-06, "loss": 0.5179, "step": 119 }, { "epoch": 0.21699819168173598, "grad_norm": 4.021240711212158, "learning_rate": 9.90861105628817e-06, "loss": 0.4713, "step": 120 }, { "epoch": 0.21880650994575046, "grad_norm": 4.073612689971924, "learning_rate": 9.905741916970863e-06, "loss": 0.5243, "step": 121 }, { "epoch": 0.2206148282097649, "grad_norm": 3.9512710571289062, "learning_rate": 9.902828861376101e-06, "loss": 0.4355, "step": 122 }, { "epoch": 0.2224231464737794, "grad_norm": 3.7133541107177734, "learning_rate": 9.8998719155816e-06, "loss": 0.518, "step": 123 }, { "epoch": 0.22423146473779385, "grad_norm": 3.616624593734741, "learning_rate": 9.896871106057989e-06, "loss": 0.4757, "step": 124 }, { "epoch": 0.22603978300180833, "grad_norm": 3.143645763397217, "learning_rate": 9.89382645966856e-06, "loss": 0.4475, "step": 125 }, { "epoch": 0.22784810126582278, "grad_norm": 2.712369918823242, "learning_rate": 9.890738003669029e-06, "loss": 0.4767, "step": 126 }, { "epoch": 0.22965641952983726, "grad_norm": 2.7018110752105713, "learning_rate": 9.887605765707309e-06, "loss": 0.3942, "step": 127 }, { "epoch": 0.2314647377938517, "grad_norm": 2.356400966644287, "learning_rate": 9.884429773823238e-06, "loss": 0.463, "step": 128 }, { "epoch": 0.2332730560578662, "grad_norm": 2.938870429992676, "learning_rate": 9.88121005644835e-06, "loss": 0.4635, "step": 129 }, { "epoch": 0.23508137432188064, "grad_norm": 2.4205424785614014, "learning_rate": 9.877946642405598e-06, "loss": 0.5153, "step": 130 }, { "epoch": 0.23688969258589512, "grad_norm": 2.6452150344848633, "learning_rate": 9.874639560909118e-06, "loss": 0.4108, "step": 131 }, { "epoch": 0.23869801084990958, "grad_norm": 3.627526044845581, "learning_rate": 9.871288841563956e-06, "loss": 0.398, "step": 132 }, { "epoch": 0.24050632911392406, "grad_norm": 2.3740315437316895, "learning_rate": 9.867894514365802e-06, "loss": 0.4232, "step": 133 }, { "epoch": 0.2423146473779385, "grad_norm": 2.1132237911224365, "learning_rate": 9.864456609700726e-06, "loss": 0.3985, "step": 134 }, { "epoch": 0.244122965641953, "grad_norm": 2.9136316776275635, "learning_rate": 9.860975158344902e-06, "loss": 0.3669, "step": 135 }, { "epoch": 0.24593128390596744, "grad_norm": 2.635727882385254, "learning_rate": 9.857450191464337e-06, "loss": 0.4524, "step": 136 }, { "epoch": 0.24773960216998192, "grad_norm": 2.391969919204712, "learning_rate": 9.853881740614591e-06, "loss": 0.478, "step": 137 }, { "epoch": 0.24954792043399637, "grad_norm": 12.022067070007324, "learning_rate": 9.85026983774049e-06, "loss": 0.5529, "step": 138 }, { "epoch": 0.2513562386980108, "grad_norm": 2.6351187229156494, "learning_rate": 9.846614515175843e-06, "loss": 0.4002, "step": 139 }, { "epoch": 0.25316455696202533, "grad_norm": 2.0587735176086426, "learning_rate": 9.842915805643156e-06, "loss": 0.3588, "step": 140 }, { "epoch": 0.2549728752260398, "grad_norm": 2.7483675479888916, "learning_rate": 9.839173742253334e-06, "loss": 0.5578, "step": 141 }, { "epoch": 0.25678119349005424, "grad_norm": 2.096440315246582, "learning_rate": 9.835388358505383e-06, "loss": 0.4697, "step": 142 }, { "epoch": 0.2585895117540687, "grad_norm": 2.126437187194824, "learning_rate": 9.83155968828612e-06, "loss": 0.3993, "step": 143 }, { "epoch": 0.2603978300180832, "grad_norm": 105.704833984375, "learning_rate": 9.827687765869859e-06, "loss": 0.6438, "step": 144 }, { "epoch": 0.26220614828209765, "grad_norm": 2.530317783355713, "learning_rate": 9.823772625918111e-06, "loss": 0.434, "step": 145 }, { "epoch": 0.2640144665461121, "grad_norm": 23.468416213989258, "learning_rate": 9.819814303479268e-06, "loss": 0.4721, "step": 146 }, { "epoch": 0.26582278481012656, "grad_norm": 2.1566429138183594, "learning_rate": 9.815812833988292e-06, "loss": 0.3847, "step": 147 }, { "epoch": 0.26763110307414106, "grad_norm": 2.447932720184326, "learning_rate": 9.811768253266401e-06, "loss": 0.4256, "step": 148 }, { "epoch": 0.2694394213381555, "grad_norm": 2.5068366527557373, "learning_rate": 9.807680597520746e-06, "loss": 0.5136, "step": 149 }, { "epoch": 0.27124773960216997, "grad_norm": 2.336026430130005, "learning_rate": 9.803549903344081e-06, "loss": 0.4813, "step": 150 }, { "epoch": 0.2730560578661845, "grad_norm": 2.0370335578918457, "learning_rate": 9.799376207714446e-06, "loss": 0.4437, "step": 151 }, { "epoch": 0.27486437613019893, "grad_norm": 2.27744197845459, "learning_rate": 9.79515954799483e-06, "loss": 0.4052, "step": 152 }, { "epoch": 0.2766726943942134, "grad_norm": 2.5218756198883057, "learning_rate": 9.790899961932833e-06, "loss": 0.5247, "step": 153 }, { "epoch": 0.27848101265822783, "grad_norm": 2.2429721355438232, "learning_rate": 9.786597487660336e-06, "loss": 0.4919, "step": 154 }, { "epoch": 0.28028933092224234, "grad_norm": 2.2865939140319824, "learning_rate": 9.782252163693159e-06, "loss": 0.4167, "step": 155 }, { "epoch": 0.2820976491862568, "grad_norm": 2.2159383296966553, "learning_rate": 9.777864028930705e-06, "loss": 0.4275, "step": 156 }, { "epoch": 0.28390596745027125, "grad_norm": 2.2138760089874268, "learning_rate": 9.773433122655625e-06, "loss": 0.4375, "step": 157 }, { "epoch": 0.2857142857142857, "grad_norm": 2.4858455657958984, "learning_rate": 9.768959484533461e-06, "loss": 0.4533, "step": 158 }, { "epoch": 0.2875226039783002, "grad_norm": 2.290297031402588, "learning_rate": 9.76444315461229e-06, "loss": 0.4355, "step": 159 }, { "epoch": 0.28933092224231466, "grad_norm": 2.6848325729370117, "learning_rate": 9.75988417332237e-06, "loss": 0.4024, "step": 160 }, { "epoch": 0.2911392405063291, "grad_norm": 6.118619918823242, "learning_rate": 9.755282581475769e-06, "loss": 0.4562, "step": 161 }, { "epoch": 0.29294755877034356, "grad_norm": 2.517714500427246, "learning_rate": 9.750638420266008e-06, "loss": 0.3763, "step": 162 }, { "epoch": 0.29475587703435807, "grad_norm": 2.7288458347320557, "learning_rate": 9.745951731267693e-06, "loss": 0.4858, "step": 163 }, { "epoch": 0.2965641952983725, "grad_norm": 3.0551955699920654, "learning_rate": 9.741222556436132e-06, "loss": 0.3559, "step": 164 }, { "epoch": 0.298372513562387, "grad_norm": 2.6702234745025635, "learning_rate": 9.736450938106976e-06, "loss": 0.495, "step": 165 }, { "epoch": 0.30018083182640143, "grad_norm": 2.422048807144165, "learning_rate": 9.731636918995821e-06, "loss": 0.4032, "step": 166 }, { "epoch": 0.30198915009041594, "grad_norm": 2.3798282146453857, "learning_rate": 9.726780542197845e-06, "loss": 0.3831, "step": 167 }, { "epoch": 0.3037974683544304, "grad_norm": 2.419506311416626, "learning_rate": 9.721881851187406e-06, "loss": 0.4436, "step": 168 }, { "epoch": 0.30560578661844484, "grad_norm": 2.362715005874634, "learning_rate": 9.716940889817662e-06, "loss": 0.4295, "step": 169 }, { "epoch": 0.3074141048824593, "grad_norm": 2.658930778503418, "learning_rate": 9.711957702320176e-06, "loss": 0.4541, "step": 170 }, { "epoch": 0.3092224231464738, "grad_norm": 2.9544925689697266, "learning_rate": 9.706932333304518e-06, "loss": 0.3866, "step": 171 }, { "epoch": 0.31103074141048825, "grad_norm": 2.8166117668151855, "learning_rate": 9.701864827757868e-06, "loss": 0.4661, "step": 172 }, { "epoch": 0.3128390596745027, "grad_norm": 2.546520948410034, "learning_rate": 9.696755231044618e-06, "loss": 0.3491, "step": 173 }, { "epoch": 0.31464737793851716, "grad_norm": 2.6299493312835693, "learning_rate": 9.691603588905956e-06, "loss": 0.3883, "step": 174 }, { "epoch": 0.31645569620253167, "grad_norm": 2.7625033855438232, "learning_rate": 9.68640994745946e-06, "loss": 0.4513, "step": 175 }, { "epoch": 0.3182640144665461, "grad_norm": 2.306105852127075, "learning_rate": 9.681174353198687e-06, "loss": 0.3926, "step": 176 }, { "epoch": 0.32007233273056057, "grad_norm": 2.4626052379608154, "learning_rate": 9.675896852992762e-06, "loss": 0.5025, "step": 177 }, { "epoch": 0.321880650994575, "grad_norm": 2.6227428913116455, "learning_rate": 9.670577494085945e-06, "loss": 0.4626, "step": 178 }, { "epoch": 0.32368896925858953, "grad_norm": 2.3932721614837646, "learning_rate": 9.665216324097222e-06, "loss": 0.4049, "step": 179 }, { "epoch": 0.325497287522604, "grad_norm": 2.31270432472229, "learning_rate": 9.659813391019867e-06, "loss": 0.3982, "step": 180 }, { "epoch": 0.32730560578661844, "grad_norm": 2.2742583751678467, "learning_rate": 9.654368743221022e-06, "loss": 0.3381, "step": 181 }, { "epoch": 0.3291139240506329, "grad_norm": 2.404975414276123, "learning_rate": 9.648882429441258e-06, "loss": 0.3764, "step": 182 }, { "epoch": 0.3309222423146474, "grad_norm": 2.1588802337646484, "learning_rate": 9.643354498794139e-06, "loss": 0.3426, "step": 183 }, { "epoch": 0.33273056057866185, "grad_norm": 2.2824642658233643, "learning_rate": 9.637785000765789e-06, "loss": 0.3449, "step": 184 }, { "epoch": 0.3345388788426763, "grad_norm": 2.289621114730835, "learning_rate": 9.632173985214438e-06, "loss": 0.3949, "step": 185 }, { "epoch": 0.33634719710669075, "grad_norm": 2.445563793182373, "learning_rate": 9.626521502369984e-06, "loss": 0.3246, "step": 186 }, { "epoch": 0.33815551537070526, "grad_norm": 2.5454514026641846, "learning_rate": 9.620827602833542e-06, "loss": 0.4199, "step": 187 }, { "epoch": 0.3399638336347197, "grad_norm": 2.2944490909576416, "learning_rate": 9.615092337576987e-06, "loss": 0.4358, "step": 188 }, { "epoch": 0.34177215189873417, "grad_norm": 2.3894712924957275, "learning_rate": 9.609315757942504e-06, "loss": 0.3726, "step": 189 }, { "epoch": 0.3435804701627486, "grad_norm": 2.187955856323242, "learning_rate": 9.603497915642122e-06, "loss": 0.3597, "step": 190 }, { "epoch": 0.3453887884267631, "grad_norm": 2.08091139793396, "learning_rate": 9.597638862757255e-06, "loss": 0.3248, "step": 191 }, { "epoch": 0.3471971066907776, "grad_norm": 1.8873190879821777, "learning_rate": 9.591738651738235e-06, "loss": 0.3302, "step": 192 }, { "epoch": 0.34900542495479203, "grad_norm": 2.0776877403259277, "learning_rate": 9.585797335403843e-06, "loss": 0.2583, "step": 193 }, { "epoch": 0.3508137432188065, "grad_norm": 2.0342366695404053, "learning_rate": 9.579814966940833e-06, "loss": 0.3653, "step": 194 }, { "epoch": 0.352622061482821, "grad_norm": 2.3085451126098633, "learning_rate": 9.573791599903463e-06, "loss": 0.4005, "step": 195 }, { "epoch": 0.35443037974683544, "grad_norm": 1.8330180644989014, "learning_rate": 9.567727288213005e-06, "loss": 0.348, "step": 196 }, { "epoch": 0.3562386980108499, "grad_norm": 1.9830125570297241, "learning_rate": 9.561622086157273e-06, "loss": 0.3469, "step": 197 }, { "epoch": 0.35804701627486435, "grad_norm": 1.9019001722335815, "learning_rate": 9.55547604839013e-06, "loss": 0.2971, "step": 198 }, { "epoch": 0.35985533453887886, "grad_norm": 1.9900113344192505, "learning_rate": 9.549289229930997e-06, "loss": 0.3369, "step": 199 }, { "epoch": 0.3616636528028933, "grad_norm": 2.334914207458496, "learning_rate": 9.543061686164374e-06, "loss": 0.4592, "step": 200 }, { "epoch": 0.36347197106690776, "grad_norm": 1.9617918729782104, "learning_rate": 9.536793472839325e-06, "loss": 0.3805, "step": 201 }, { "epoch": 0.36528028933092227, "grad_norm": 2.2394866943359375, "learning_rate": 9.530484646068996e-06, "loss": 0.4631, "step": 202 }, { "epoch": 0.3670886075949367, "grad_norm": 2.1650757789611816, "learning_rate": 9.524135262330098e-06, "loss": 0.3214, "step": 203 }, { "epoch": 0.3688969258589512, "grad_norm": 1.7542517185211182, "learning_rate": 9.517745378462417e-06, "loss": 0.3377, "step": 204 }, { "epoch": 0.3707052441229656, "grad_norm": 2.038898229598999, "learning_rate": 9.511315051668287e-06, "loss": 0.3241, "step": 205 }, { "epoch": 0.37251356238698013, "grad_norm": 2.1404659748077393, "learning_rate": 9.504844339512096e-06, "loss": 0.3588, "step": 206 }, { "epoch": 0.3743218806509946, "grad_norm": 1.9045383930206299, "learning_rate": 9.498333299919759e-06, "loss": 0.3453, "step": 207 }, { "epoch": 0.37613019891500904, "grad_norm": 1.7687993049621582, "learning_rate": 9.491781991178203e-06, "loss": 0.2912, "step": 208 }, { "epoch": 0.3779385171790235, "grad_norm": 1.7945553064346313, "learning_rate": 9.485190471934845e-06, "loss": 0.2909, "step": 209 }, { "epoch": 0.379746835443038, "grad_norm": 1.8400776386260986, "learning_rate": 9.478558801197065e-06, "loss": 0.2858, "step": 210 }, { "epoch": 0.38155515370705245, "grad_norm": 2.0392038822174072, "learning_rate": 9.471887038331686e-06, "loss": 0.3374, "step": 211 }, { "epoch": 0.3833634719710669, "grad_norm": 1.998852014541626, "learning_rate": 9.465175243064428e-06, "loss": 0.335, "step": 212 }, { "epoch": 0.38517179023508136, "grad_norm": 1.998155117034912, "learning_rate": 9.458423475479387e-06, "loss": 0.4355, "step": 213 }, { "epoch": 0.38698010849909587, "grad_norm": 1.7829229831695557, "learning_rate": 9.451631796018495e-06, "loss": 0.3174, "step": 214 }, { "epoch": 0.3887884267631103, "grad_norm": 2.1638948917388916, "learning_rate": 9.444800265480968e-06, "loss": 0.4655, "step": 215 }, { "epoch": 0.39059674502712477, "grad_norm": 1.9596186876296997, "learning_rate": 9.437928945022772e-06, "loss": 0.3391, "step": 216 }, { "epoch": 0.3924050632911392, "grad_norm": 1.8147703409194946, "learning_rate": 9.431017896156074e-06, "loss": 0.3406, "step": 217 }, { "epoch": 0.39421338155515373, "grad_norm": 1.830321192741394, "learning_rate": 9.424067180748692e-06, "loss": 0.3328, "step": 218 }, { "epoch": 0.3960216998191682, "grad_norm": 1.6805546283721924, "learning_rate": 9.417076861023539e-06, "loss": 0.2877, "step": 219 }, { "epoch": 0.39783001808318263, "grad_norm": 1.7954466342926025, "learning_rate": 9.410046999558062e-06, "loss": 0.3762, "step": 220 }, { "epoch": 0.3996383363471971, "grad_norm": 1.7240300178527832, "learning_rate": 9.40297765928369e-06, "loss": 0.3243, "step": 221 }, { "epoch": 0.4014466546112116, "grad_norm": 1.9495491981506348, "learning_rate": 9.395868903485269e-06, "loss": 0.3366, "step": 222 }, { "epoch": 0.40325497287522605, "grad_norm": 1.8657008409500122, "learning_rate": 9.388720795800488e-06, "loss": 0.3141, "step": 223 }, { "epoch": 0.4050632911392405, "grad_norm": 1.8704279661178589, "learning_rate": 9.381533400219319e-06, "loss": 0.3311, "step": 224 }, { "epoch": 0.40687160940325495, "grad_norm": 2.168368101119995, "learning_rate": 9.374306781083437e-06, "loss": 0.4232, "step": 225 }, { "epoch": 0.40867992766726946, "grad_norm": 1.6063079833984375, "learning_rate": 9.36704100308565e-06, "loss": 0.3139, "step": 226 }, { "epoch": 0.4104882459312839, "grad_norm": 1.6788493394851685, "learning_rate": 9.359736131269312e-06, "loss": 0.2915, "step": 227 }, { "epoch": 0.41229656419529837, "grad_norm": 1.9857615232467651, "learning_rate": 9.352392231027752e-06, "loss": 0.3561, "step": 228 }, { "epoch": 0.4141048824593128, "grad_norm": 2.068676233291626, "learning_rate": 9.345009368103677e-06, "loss": 0.3974, "step": 229 }, { "epoch": 0.4159132007233273, "grad_norm": 1.414207935333252, "learning_rate": 9.337587608588588e-06, "loss": 0.2463, "step": 230 }, { "epoch": 0.4177215189873418, "grad_norm": 1.5942479372024536, "learning_rate": 9.330127018922195e-06, "loss": 0.2795, "step": 231 }, { "epoch": 0.41952983725135623, "grad_norm": 1.6321314573287964, "learning_rate": 9.322627665891807e-06, "loss": 0.3053, "step": 232 }, { "epoch": 0.4213381555153707, "grad_norm": 1.723650574684143, "learning_rate": 9.315089616631752e-06, "loss": 0.2646, "step": 233 }, { "epoch": 0.4231464737793852, "grad_norm": 1.726138949394226, "learning_rate": 9.307512938622762e-06, "loss": 0.2903, "step": 234 }, { "epoch": 0.42495479204339964, "grad_norm": 1.563706398010254, "learning_rate": 9.299897699691377e-06, "loss": 0.2632, "step": 235 }, { "epoch": 0.4267631103074141, "grad_norm": 1.7615293264389038, "learning_rate": 9.292243968009332e-06, "loss": 0.2807, "step": 236 }, { "epoch": 0.42857142857142855, "grad_norm": 1.8792922496795654, "learning_rate": 9.28455181209295e-06, "loss": 0.3195, "step": 237 }, { "epoch": 0.43037974683544306, "grad_norm": 1.8193873167037964, "learning_rate": 9.276821300802535e-06, "loss": 0.4057, "step": 238 }, { "epoch": 0.4321880650994575, "grad_norm": 1.4362438917160034, "learning_rate": 9.269052503341737e-06, "loss": 0.2753, "step": 239 }, { "epoch": 0.43399638336347196, "grad_norm": 1.7373498678207397, "learning_rate": 9.261245489256956e-06, "loss": 0.3094, "step": 240 }, { "epoch": 0.4358047016274864, "grad_norm": 1.7984397411346436, "learning_rate": 9.253400328436699e-06, "loss": 0.394, "step": 241 }, { "epoch": 0.4376130198915009, "grad_norm": 1.6938806772232056, "learning_rate": 9.24551709111097e-06, "loss": 0.3308, "step": 242 }, { "epoch": 0.4394213381555154, "grad_norm": 1.8981354236602783, "learning_rate": 9.237595847850628e-06, "loss": 0.3902, "step": 243 }, { "epoch": 0.4412296564195298, "grad_norm": 1.7526423931121826, "learning_rate": 9.229636669566769e-06, "loss": 0.3555, "step": 244 }, { "epoch": 0.4430379746835443, "grad_norm": 1.7828216552734375, "learning_rate": 9.221639627510076e-06, "loss": 0.4273, "step": 245 }, { "epoch": 0.4448462929475588, "grad_norm": 1.8212733268737793, "learning_rate": 9.213604793270196e-06, "loss": 0.3265, "step": 246 }, { "epoch": 0.44665461121157324, "grad_norm": 1.6839758157730103, "learning_rate": 9.205532238775089e-06, "loss": 0.3025, "step": 247 }, { "epoch": 0.4484629294755877, "grad_norm": 1.746161699295044, "learning_rate": 9.197422036290386e-06, "loss": 0.2731, "step": 248 }, { "epoch": 0.45027124773960214, "grad_norm": 1.7517246007919312, "learning_rate": 9.189274258418748e-06, "loss": 0.3217, "step": 249 }, { "epoch": 0.45207956600361665, "grad_norm": 1.8492624759674072, "learning_rate": 9.181088978099203e-06, "loss": 0.3233, "step": 250 }, { "epoch": 0.4538878842676311, "grad_norm": 1.850122094154358, "learning_rate": 9.172866268606514e-06, "loss": 0.3065, "step": 251 }, { "epoch": 0.45569620253164556, "grad_norm": 1.95866858959198, "learning_rate": 9.164606203550498e-06, "loss": 0.3341, "step": 252 }, { "epoch": 0.45750452079566006, "grad_norm": 1.8152821063995361, "learning_rate": 9.156308856875386e-06, "loss": 0.3774, "step": 253 }, { "epoch": 0.4593128390596745, "grad_norm": 1.6366527080535889, "learning_rate": 9.147974302859158e-06, "loss": 0.3274, "step": 254 }, { "epoch": 0.46112115732368897, "grad_norm": 1.8053789138793945, "learning_rate": 9.139602616112864e-06, "loss": 0.3294, "step": 255 }, { "epoch": 0.4629294755877034, "grad_norm": 1.6944776773452759, "learning_rate": 9.131193871579975e-06, "loss": 0.3195, "step": 256 }, { "epoch": 0.46473779385171793, "grad_norm": 1.737259030342102, "learning_rate": 9.122748144535704e-06, "loss": 0.3326, "step": 257 }, { "epoch": 0.4665461121157324, "grad_norm": 1.5524746179580688, "learning_rate": 9.114265510586329e-06, "loss": 0.3188, "step": 258 }, { "epoch": 0.46835443037974683, "grad_norm": 1.8886528015136719, "learning_rate": 9.10574604566852e-06, "loss": 0.3479, "step": 259 }, { "epoch": 0.4701627486437613, "grad_norm": 1.5851829051971436, "learning_rate": 9.09718982604866e-06, "loss": 0.2575, "step": 260 }, { "epoch": 0.4719710669077758, "grad_norm": 1.5194969177246094, "learning_rate": 9.088596928322158e-06, "loss": 0.2377, "step": 261 }, { "epoch": 0.47377938517179025, "grad_norm": 1.8121997117996216, "learning_rate": 9.079967429412766e-06, "loss": 0.3533, "step": 262 }, { "epoch": 0.4755877034358047, "grad_norm": 1.7991399765014648, "learning_rate": 9.071301406571893e-06, "loss": 0.3671, "step": 263 }, { "epoch": 0.47739602169981915, "grad_norm": 1.7022171020507812, "learning_rate": 9.062598937377911e-06, "loss": 0.2538, "step": 264 }, { "epoch": 0.47920433996383366, "grad_norm": 1.830853819847107, "learning_rate": 9.053860099735455e-06, "loss": 0.3475, "step": 265 }, { "epoch": 0.4810126582278481, "grad_norm": 2.049315929412842, "learning_rate": 9.045084971874738e-06, "loss": 0.3937, "step": 266 }, { "epoch": 0.48282097649186256, "grad_norm": 1.5634286403656006, "learning_rate": 9.036273632350839e-06, "loss": 0.2534, "step": 267 }, { "epoch": 0.484629294755877, "grad_norm": 1.5801969766616821, "learning_rate": 9.027426160043005e-06, "loss": 0.3189, "step": 268 }, { "epoch": 0.4864376130198915, "grad_norm": 1.77995765209198, "learning_rate": 9.018542634153944e-06, "loss": 0.3218, "step": 269 }, { "epoch": 0.488245931283906, "grad_norm": 1.689652681350708, "learning_rate": 9.00962313420912e-06, "loss": 0.3307, "step": 270 }, { "epoch": 0.49005424954792043, "grad_norm": 1.6479848623275757, "learning_rate": 9.000667740056033e-06, "loss": 0.2612, "step": 271 }, { "epoch": 0.4918625678119349, "grad_norm": 1.7668133974075317, "learning_rate": 8.991676531863507e-06, "loss": 0.3546, "step": 272 }, { "epoch": 0.4936708860759494, "grad_norm": 1.6082919836044312, "learning_rate": 8.982649590120982e-06, "loss": 0.2608, "step": 273 }, { "epoch": 0.49547920433996384, "grad_norm": 1.7007689476013184, "learning_rate": 8.973586995637778e-06, "loss": 0.3361, "step": 274 }, { "epoch": 0.4972875226039783, "grad_norm": 1.728756070137024, "learning_rate": 8.964488829542377e-06, "loss": 0.3332, "step": 275 }, { "epoch": 0.49909584086799275, "grad_norm": 1.613638997077942, "learning_rate": 8.955355173281709e-06, "loss": 0.3329, "step": 276 }, { "epoch": 0.5009041591320073, "grad_norm": 1.4530051946640015, "learning_rate": 8.946186108620397e-06, "loss": 0.244, "step": 277 }, { "epoch": 0.5027124773960217, "grad_norm": 1.6607911586761475, "learning_rate": 8.936981717640061e-06, "loss": 0.3939, "step": 278 }, { "epoch": 0.5045207956600362, "grad_norm": 1.551262378692627, "learning_rate": 8.927742082738542e-06, "loss": 0.3625, "step": 279 }, { "epoch": 0.5063291139240507, "grad_norm": 1.4750007390975952, "learning_rate": 8.9184672866292e-06, "loss": 0.2887, "step": 280 }, { "epoch": 0.5081374321880651, "grad_norm": 1.9051368236541748, "learning_rate": 8.90915741234015e-06, "loss": 0.4483, "step": 281 }, { "epoch": 0.5099457504520796, "grad_norm": 1.584503173828125, "learning_rate": 8.899812543213532e-06, "loss": 0.2518, "step": 282 }, { "epoch": 0.5117540687160941, "grad_norm": 1.6811857223510742, "learning_rate": 8.890432762904757e-06, "loss": 0.3258, "step": 283 }, { "epoch": 0.5135623869801085, "grad_norm": 1.9532098770141602, "learning_rate": 8.881018155381766e-06, "loss": 0.3416, "step": 284 }, { "epoch": 0.515370705244123, "grad_norm": 1.6393986940383911, "learning_rate": 8.871568804924269e-06, "loss": 0.3252, "step": 285 }, { "epoch": 0.5171790235081374, "grad_norm": 1.6037964820861816, "learning_rate": 8.862084796122998e-06, "loss": 0.2987, "step": 286 }, { "epoch": 0.5189873417721519, "grad_norm": 1.8487404584884644, "learning_rate": 8.852566213878947e-06, "loss": 0.3692, "step": 287 }, { "epoch": 0.5207956600361664, "grad_norm": 1.5231586694717407, "learning_rate": 8.84301314340261e-06, "loss": 0.3115, "step": 288 }, { "epoch": 0.5226039783001808, "grad_norm": 1.4328174591064453, "learning_rate": 8.833425670213223e-06, "loss": 0.3164, "step": 289 }, { "epoch": 0.5244122965641953, "grad_norm": 1.7806422710418701, "learning_rate": 8.823803880137993e-06, "loss": 0.3446, "step": 290 }, { "epoch": 0.5262206148282098, "grad_norm": 1.7460269927978516, "learning_rate": 8.814147859311333e-06, "loss": 0.3346, "step": 291 }, { "epoch": 0.5280289330922242, "grad_norm": 1.7192416191101074, "learning_rate": 8.804457694174093e-06, "loss": 0.394, "step": 292 }, { "epoch": 0.5298372513562387, "grad_norm": 1.9701991081237793, "learning_rate": 8.794733471472778e-06, "loss": 0.4043, "step": 293 }, { "epoch": 0.5316455696202531, "grad_norm": 1.5719064474105835, "learning_rate": 8.784975278258783e-06, "loss": 0.259, "step": 294 }, { "epoch": 0.5334538878842676, "grad_norm": 1.4571279287338257, "learning_rate": 8.775183201887603e-06, "loss": 0.2644, "step": 295 }, { "epoch": 0.5352622061482821, "grad_norm": 1.783927083015442, "learning_rate": 8.765357330018056e-06, "loss": 0.4448, "step": 296 }, { "epoch": 0.5370705244122965, "grad_norm": 1.5831583738327026, "learning_rate": 8.755497750611498e-06, "loss": 0.3055, "step": 297 }, { "epoch": 0.538878842676311, "grad_norm": 1.712937355041504, "learning_rate": 8.745604551931042e-06, "loss": 0.3184, "step": 298 }, { "epoch": 0.5406871609403255, "grad_norm": 1.8718096017837524, "learning_rate": 8.73567782254075e-06, "loss": 0.3562, "step": 299 }, { "epoch": 0.5424954792043399, "grad_norm": 2.016859769821167, "learning_rate": 8.725717651304856e-06, "loss": 0.313, "step": 300 }, { "epoch": 0.5443037974683544, "grad_norm": 1.5516358613967896, "learning_rate": 8.715724127386971e-06, "loss": 0.2861, "step": 301 }, { "epoch": 0.546112115732369, "grad_norm": 1.645348072052002, "learning_rate": 8.705697340249275e-06, "loss": 0.2603, "step": 302 }, { "epoch": 0.5479204339963833, "grad_norm": 1.6812154054641724, "learning_rate": 8.695637379651719e-06, "loss": 0.3474, "step": 303 }, { "epoch": 0.5497287522603979, "grad_norm": 1.6335675716400146, "learning_rate": 8.685544335651226e-06, "loss": 0.3567, "step": 304 }, { "epoch": 0.5515370705244123, "grad_norm": 1.5500508546829224, "learning_rate": 8.675418298600884e-06, "loss": 0.3301, "step": 305 }, { "epoch": 0.5533453887884268, "grad_norm": 1.6419695615768433, "learning_rate": 8.665259359149132e-06, "loss": 0.3612, "step": 306 }, { "epoch": 0.5551537070524413, "grad_norm": 6.115174293518066, "learning_rate": 8.655067608238953e-06, "loss": 0.3092, "step": 307 }, { "epoch": 0.5569620253164557, "grad_norm": 1.5488377809524536, "learning_rate": 8.644843137107058e-06, "loss": 0.2923, "step": 308 }, { "epoch": 0.5587703435804702, "grad_norm": 1.5162806510925293, "learning_rate": 8.634586037283072e-06, "loss": 0.307, "step": 309 }, { "epoch": 0.5605786618444847, "grad_norm": 1.5004791021347046, "learning_rate": 8.62429640058871e-06, "loss": 0.287, "step": 310 }, { "epoch": 0.5623869801084991, "grad_norm": 1.5346438884735107, "learning_rate": 8.613974319136959e-06, "loss": 0.2756, "step": 311 }, { "epoch": 0.5641952983725136, "grad_norm": 1.800788402557373, "learning_rate": 8.603619885331251e-06, "loss": 0.3648, "step": 312 }, { "epoch": 0.566003616636528, "grad_norm": 1.9229762554168701, "learning_rate": 8.593233191864638e-06, "loss": 0.3672, "step": 313 }, { "epoch": 0.5678119349005425, "grad_norm": 1.5572224855422974, "learning_rate": 8.582814331718961e-06, "loss": 0.3193, "step": 314 }, { "epoch": 0.569620253164557, "grad_norm": 1.556885838508606, "learning_rate": 8.572363398164017e-06, "loss": 0.286, "step": 315 }, { "epoch": 0.5714285714285714, "grad_norm": 1.6812305450439453, "learning_rate": 8.561880484756726e-06, "loss": 0.3438, "step": 316 }, { "epoch": 0.5732368896925859, "grad_norm": 1.6463974714279175, "learning_rate": 8.551365685340285e-06, "loss": 0.3809, "step": 317 }, { "epoch": 0.5750452079566004, "grad_norm": 1.5008747577667236, "learning_rate": 8.540819094043349e-06, "loss": 0.2663, "step": 318 }, { "epoch": 0.5768535262206148, "grad_norm": 1.7042824029922485, "learning_rate": 8.530240805279159e-06, "loss": 0.3515, "step": 319 }, { "epoch": 0.5786618444846293, "grad_norm": 1.494800090789795, "learning_rate": 8.519630913744726e-06, "loss": 0.2733, "step": 320 }, { "epoch": 0.5804701627486437, "grad_norm": 1.6093062162399292, "learning_rate": 8.508989514419959e-06, "loss": 0.3481, "step": 321 }, { "epoch": 0.5822784810126582, "grad_norm": 1.5477339029312134, "learning_rate": 8.498316702566828e-06, "loss": 0.2806, "step": 322 }, { "epoch": 0.5840867992766727, "grad_norm": 1.532044768333435, "learning_rate": 8.487612573728513e-06, "loss": 0.26, "step": 323 }, { "epoch": 0.5858951175406871, "grad_norm": 1.576225996017456, "learning_rate": 8.476877223728539e-06, "loss": 0.2301, "step": 324 }, { "epoch": 0.5877034358047016, "grad_norm": 1.9125258922576904, "learning_rate": 8.466110748669926e-06, "loss": 0.359, "step": 325 }, { "epoch": 0.5895117540687161, "grad_norm": 1.6308892965316772, "learning_rate": 8.455313244934324e-06, "loss": 0.3655, "step": 326 }, { "epoch": 0.5913200723327305, "grad_norm": 1.5946282148361206, "learning_rate": 8.444484809181155e-06, "loss": 0.2706, "step": 327 }, { "epoch": 0.593128390596745, "grad_norm": 1.604309320449829, "learning_rate": 8.433625538346742e-06, "loss": 0.3268, "step": 328 }, { "epoch": 0.5949367088607594, "grad_norm": 1.743274450302124, "learning_rate": 8.422735529643445e-06, "loss": 0.3061, "step": 329 }, { "epoch": 0.596745027124774, "grad_norm": 1.7052639722824097, "learning_rate": 8.41181488055879e-06, "loss": 0.3507, "step": 330 }, { "epoch": 0.5985533453887885, "grad_norm": 1.6907163858413696, "learning_rate": 8.400863688854598e-06, "loss": 0.3571, "step": 331 }, { "epoch": 0.6003616636528029, "grad_norm": 1.6159577369689941, "learning_rate": 8.389882052566106e-06, "loss": 0.3009, "step": 332 }, { "epoch": 0.6021699819168174, "grad_norm": 1.6263846158981323, "learning_rate": 8.37887007000109e-06, "loss": 0.3542, "step": 333 }, { "epoch": 0.6039783001808319, "grad_norm": 1.4161427021026611, "learning_rate": 8.36782783973899e-06, "loss": 0.2426, "step": 334 }, { "epoch": 0.6057866184448463, "grad_norm": 1.620248556137085, "learning_rate": 8.35675546063002e-06, "loss": 0.2695, "step": 335 }, { "epoch": 0.6075949367088608, "grad_norm": 1.5782829523086548, "learning_rate": 8.345653031794292e-06, "loss": 0.2893, "step": 336 }, { "epoch": 0.6094032549728752, "grad_norm": 1.6616706848144531, "learning_rate": 8.334520652620918e-06, "loss": 0.2904, "step": 337 }, { "epoch": 0.6112115732368897, "grad_norm": 1.6135728359222412, "learning_rate": 8.32335842276713e-06, "loss": 0.3037, "step": 338 }, { "epoch": 0.6130198915009042, "grad_norm": 1.6073436737060547, "learning_rate": 8.31216644215738e-06, "loss": 0.3236, "step": 339 }, { "epoch": 0.6148282097649186, "grad_norm": 1.7613461017608643, "learning_rate": 8.300944810982452e-06, "loss": 0.368, "step": 340 }, { "epoch": 0.6166365280289331, "grad_norm": 1.6920862197875977, "learning_rate": 8.289693629698564e-06, "loss": 0.3126, "step": 341 }, { "epoch": 0.6184448462929476, "grad_norm": 1.6565982103347778, "learning_rate": 8.278412999026462e-06, "loss": 0.3057, "step": 342 }, { "epoch": 0.620253164556962, "grad_norm": 1.40024995803833, "learning_rate": 8.267103019950529e-06, "loss": 0.2406, "step": 343 }, { "epoch": 0.6220614828209765, "grad_norm": 1.607602834701538, "learning_rate": 8.255763793717868e-06, "loss": 0.3192, "step": 344 }, { "epoch": 0.6238698010849909, "grad_norm": 1.5471099615097046, "learning_rate": 8.244395421837412e-06, "loss": 0.2998, "step": 345 }, { "epoch": 0.6256781193490054, "grad_norm": 1.4507505893707275, "learning_rate": 8.232998006078998e-06, "loss": 0.2421, "step": 346 }, { "epoch": 0.6274864376130199, "grad_norm": 1.6553953886032104, "learning_rate": 8.221571648472473e-06, "loss": 0.2817, "step": 347 }, { "epoch": 0.6292947558770343, "grad_norm": 2.6195178031921387, "learning_rate": 8.210116451306762e-06, "loss": 0.2494, "step": 348 }, { "epoch": 0.6311030741410488, "grad_norm": 3.892993450164795, "learning_rate": 8.198632517128968e-06, "loss": 0.259, "step": 349 }, { "epoch": 0.6329113924050633, "grad_norm": 2.0920164585113525, "learning_rate": 8.18711994874345e-06, "loss": 0.4005, "step": 350 }, { "epoch": 0.6347197106690777, "grad_norm": 1.4655321836471558, "learning_rate": 8.175578849210894e-06, "loss": 0.2812, "step": 351 }, { "epoch": 0.6365280289330922, "grad_norm": 1.6014291048049927, "learning_rate": 8.164009321847405e-06, "loss": 0.2729, "step": 352 }, { "epoch": 0.6383363471971067, "grad_norm": 1.4081932306289673, "learning_rate": 8.15241147022357e-06, "loss": 0.2545, "step": 353 }, { "epoch": 0.6401446654611211, "grad_norm": 1.40230393409729, "learning_rate": 8.140785398163535e-06, "loss": 0.2611, "step": 354 }, { "epoch": 0.6419529837251357, "grad_norm": 1.532150387763977, "learning_rate": 8.129131209744075e-06, "loss": 0.3109, "step": 355 }, { "epoch": 0.64376130198915, "grad_norm": 3.1065354347229004, "learning_rate": 8.117449009293668e-06, "loss": 0.3437, "step": 356 }, { "epoch": 0.6455696202531646, "grad_norm": 1.5476206541061401, "learning_rate": 8.105738901391553e-06, "loss": 0.3024, "step": 357 }, { "epoch": 0.6473779385171791, "grad_norm": 1.5530200004577637, "learning_rate": 8.094000990866795e-06, "loss": 0.2784, "step": 358 }, { "epoch": 0.6491862567811935, "grad_norm": 1.4467393159866333, "learning_rate": 8.08223538279735e-06, "loss": 0.2364, "step": 359 }, { "epoch": 0.650994575045208, "grad_norm": 1.4614650011062622, "learning_rate": 8.070442182509127e-06, "loss": 0.2489, "step": 360 }, { "epoch": 0.6528028933092225, "grad_norm": 1.6396328210830688, "learning_rate": 8.058621495575032e-06, "loss": 0.3024, "step": 361 }, { "epoch": 0.6546112115732369, "grad_norm": 1.722334623336792, "learning_rate": 8.046773427814043e-06, "loss": 0.3437, "step": 362 }, { "epoch": 0.6564195298372514, "grad_norm": 1.594954490661621, "learning_rate": 8.034898085290239e-06, "loss": 0.3015, "step": 363 }, { "epoch": 0.6582278481012658, "grad_norm": 1.649190068244934, "learning_rate": 8.022995574311876e-06, "loss": 0.3486, "step": 364 }, { "epoch": 0.6600361663652803, "grad_norm": 1.625191330909729, "learning_rate": 8.011066001430412e-06, "loss": 0.366, "step": 365 }, { "epoch": 0.6618444846292948, "grad_norm": 1.7174073457717896, "learning_rate": 7.99910947343957e-06, "loss": 0.3796, "step": 366 }, { "epoch": 0.6636528028933092, "grad_norm": 1.6358258724212646, "learning_rate": 7.987126097374372e-06, "loss": 0.3043, "step": 367 }, { "epoch": 0.6654611211573237, "grad_norm": 1.5151185989379883, "learning_rate": 7.975115980510187e-06, "loss": 0.2802, "step": 368 }, { "epoch": 0.6672694394213382, "grad_norm": 1.5926612615585327, "learning_rate": 7.963079230361765e-06, "loss": 0.3151, "step": 369 }, { "epoch": 0.6690777576853526, "grad_norm": 1.5765351057052612, "learning_rate": 7.951015954682281e-06, "loss": 0.2712, "step": 370 }, { "epoch": 0.6708860759493671, "grad_norm": 1.4893732070922852, "learning_rate": 7.938926261462366e-06, "loss": 0.2982, "step": 371 }, { "epoch": 0.6726943942133815, "grad_norm": 1.5673125982284546, "learning_rate": 7.926810258929138e-06, "loss": 0.2757, "step": 372 }, { "epoch": 0.674502712477396, "grad_norm": 1.6124296188354492, "learning_rate": 7.914668055545242e-06, "loss": 0.3, "step": 373 }, { "epoch": 0.6763110307414105, "grad_norm": 1.6891038417816162, "learning_rate": 7.902499760007867e-06, "loss": 0.2685, "step": 374 }, { "epoch": 0.6781193490054249, "grad_norm": 2.056053400039673, "learning_rate": 7.890305481247786e-06, "loss": 0.3942, "step": 375 }, { "epoch": 0.6799276672694394, "grad_norm": 1.683259129524231, "learning_rate": 7.87808532842837e-06, "loss": 0.3449, "step": 376 }, { "epoch": 0.6817359855334539, "grad_norm": 1.5315132141113281, "learning_rate": 7.865839410944613e-06, "loss": 0.2818, "step": 377 }, { "epoch": 0.6835443037974683, "grad_norm": 1.7870246171951294, "learning_rate": 7.85356783842216e-06, "loss": 0.3616, "step": 378 }, { "epoch": 0.6853526220614828, "grad_norm": 1.5734965801239014, "learning_rate": 7.841270720716318e-06, "loss": 0.3464, "step": 379 }, { "epoch": 0.6871609403254972, "grad_norm": 1.4913307428359985, "learning_rate": 7.828948167911073e-06, "loss": 0.2739, "step": 380 }, { "epoch": 0.6889692585895117, "grad_norm": 1.5796701908111572, "learning_rate": 7.81660029031811e-06, "loss": 0.268, "step": 381 }, { "epoch": 0.6907775768535263, "grad_norm": 1.658936858177185, "learning_rate": 7.804227198475823e-06, "loss": 0.3112, "step": 382 }, { "epoch": 0.6925858951175407, "grad_norm": 1.7184288501739502, "learning_rate": 7.791829003148313e-06, "loss": 0.2819, "step": 383 }, { "epoch": 0.6943942133815552, "grad_norm": 1.6557133197784424, "learning_rate": 7.779405815324424e-06, "loss": 0.3064, "step": 384 }, { "epoch": 0.6962025316455697, "grad_norm": 1.429786205291748, "learning_rate": 7.76695774621672e-06, "loss": 0.2453, "step": 385 }, { "epoch": 0.6980108499095841, "grad_norm": 1.829107403755188, "learning_rate": 7.754484907260513e-06, "loss": 0.3686, "step": 386 }, { "epoch": 0.6998191681735986, "grad_norm": 1.8477472066879272, "learning_rate": 7.741987410112847e-06, "loss": 0.3286, "step": 387 }, { "epoch": 0.701627486437613, "grad_norm": 1.6070722341537476, "learning_rate": 7.72946536665151e-06, "loss": 0.2745, "step": 388 }, { "epoch": 0.7034358047016275, "grad_norm": 1.611884355545044, "learning_rate": 7.716918888974029e-06, "loss": 0.2631, "step": 389 }, { "epoch": 0.705244122965642, "grad_norm": 1.5838125944137573, "learning_rate": 7.704348089396667e-06, "loss": 0.2963, "step": 390 }, { "epoch": 0.7070524412296564, "grad_norm": 1.4414722919464111, "learning_rate": 7.691753080453413e-06, "loss": 0.248, "step": 391 }, { "epoch": 0.7088607594936709, "grad_norm": 1.5219839811325073, "learning_rate": 7.679133974894984e-06, "loss": 0.3012, "step": 392 }, { "epoch": 0.7106690777576854, "grad_norm": 1.4778845310211182, "learning_rate": 7.666490885687807e-06, "loss": 0.252, "step": 393 }, { "epoch": 0.7124773960216998, "grad_norm": 1.345934271812439, "learning_rate": 7.653823926013016e-06, "loss": 0.2337, "step": 394 }, { "epoch": 0.7142857142857143, "grad_norm": 1.3904049396514893, "learning_rate": 7.641133209265423e-06, "loss": 0.2087, "step": 395 }, { "epoch": 0.7160940325497287, "grad_norm": 1.4897830486297607, "learning_rate": 7.628418849052523e-06, "loss": 0.2468, "step": 396 }, { "epoch": 0.7179023508137432, "grad_norm": 1.4456837177276611, "learning_rate": 7.615680959193469e-06, "loss": 0.2481, "step": 397 }, { "epoch": 0.7197106690777577, "grad_norm": 1.371477484703064, "learning_rate": 7.602919653718044e-06, "loss": 0.2405, "step": 398 }, { "epoch": 0.7215189873417721, "grad_norm": 1.5080976486206055, "learning_rate": 7.590135046865652e-06, "loss": 0.2438, "step": 399 }, { "epoch": 0.7233273056057866, "grad_norm": 1.793002724647522, "learning_rate": 7.577327253084292e-06, "loss": 0.3363, "step": 400 }, { "epoch": 0.7251356238698011, "grad_norm": 1.3960074186325073, "learning_rate": 7.564496387029532e-06, "loss": 0.287, "step": 401 }, { "epoch": 0.7269439421338155, "grad_norm": 1.6666656732559204, "learning_rate": 7.551642563563481e-06, "loss": 0.3034, "step": 402 }, { "epoch": 0.72875226039783, "grad_norm": 1.7052055597305298, "learning_rate": 7.5387658977537695e-06, "loss": 0.2659, "step": 403 }, { "epoch": 0.7305605786618445, "grad_norm": 1.4854893684387207, "learning_rate": 7.5258665048725065e-06, "loss": 0.3265, "step": 404 }, { "epoch": 0.7323688969258589, "grad_norm": 1.4770845174789429, "learning_rate": 7.512944500395255e-06, "loss": 0.2789, "step": 405 }, { "epoch": 0.7341772151898734, "grad_norm": 1.5038588047027588, "learning_rate": 7.500000000000001e-06, "loss": 0.2705, "step": 406 }, { "epoch": 0.7359855334538878, "grad_norm": 1.4147945642471313, "learning_rate": 7.48703311956611e-06, "loss": 0.2608, "step": 407 }, { "epoch": 0.7377938517179023, "grad_norm": 1.4600619077682495, "learning_rate": 7.4740439751732994e-06, "loss": 0.2859, "step": 408 }, { "epoch": 0.7396021699819169, "grad_norm": 1.5855250358581543, "learning_rate": 7.461032683100587e-06, "loss": 0.2736, "step": 409 }, { "epoch": 0.7414104882459313, "grad_norm": 1.6915584802627563, "learning_rate": 7.447999359825263e-06, "loss": 0.3294, "step": 410 }, { "epoch": 0.7432188065099458, "grad_norm": 1.5373306274414062, "learning_rate": 7.434944122021837e-06, "loss": 0.2819, "step": 411 }, { "epoch": 0.7450271247739603, "grad_norm": 1.543886423110962, "learning_rate": 7.421867086561001e-06, "loss": 0.2878, "step": 412 }, { "epoch": 0.7468354430379747, "grad_norm": 1.7228806018829346, "learning_rate": 7.408768370508577e-06, "loss": 0.377, "step": 413 }, { "epoch": 0.7486437613019892, "grad_norm": 1.3493674993515015, "learning_rate": 7.395648091124476e-06, "loss": 0.2406, "step": 414 }, { "epoch": 0.7504520795660036, "grad_norm": 1.550105333328247, "learning_rate": 7.382506365861639e-06, "loss": 0.3265, "step": 415 }, { "epoch": 0.7522603978300181, "grad_norm": 1.6086556911468506, "learning_rate": 7.369343312364994e-06, "loss": 0.2909, "step": 416 }, { "epoch": 0.7540687160940326, "grad_norm": 1.5198277235031128, "learning_rate": 7.356159048470402e-06, "loss": 0.3023, "step": 417 }, { "epoch": 0.755877034358047, "grad_norm": 1.3519054651260376, "learning_rate": 7.342953692203594e-06, "loss": 0.2737, "step": 418 }, { "epoch": 0.7576853526220615, "grad_norm": 1.411717176437378, "learning_rate": 7.3297273617791246e-06, "loss": 0.2598, "step": 419 }, { "epoch": 0.759493670886076, "grad_norm": 1.4423329830169678, "learning_rate": 7.31648017559931e-06, "loss": 0.27, "step": 420 }, { "epoch": 0.7613019891500904, "grad_norm": 1.5203039646148682, "learning_rate": 7.303212252253163e-06, "loss": 0.286, "step": 421 }, { "epoch": 0.7631103074141049, "grad_norm": 1.5155948400497437, "learning_rate": 7.289923710515338e-06, "loss": 0.2402, "step": 422 }, { "epoch": 0.7649186256781193, "grad_norm": 1.4997700452804565, "learning_rate": 7.276614669345069e-06, "loss": 0.2628, "step": 423 }, { "epoch": 0.7667269439421338, "grad_norm": 1.6832001209259033, "learning_rate": 7.263285247885097e-06, "loss": 0.337, "step": 424 }, { "epoch": 0.7685352622061483, "grad_norm": 1.7529714107513428, "learning_rate": 7.249935565460606e-06, "loss": 0.2991, "step": 425 }, { "epoch": 0.7703435804701627, "grad_norm": 1.3480780124664307, "learning_rate": 7.236565741578163e-06, "loss": 0.2364, "step": 426 }, { "epoch": 0.7721518987341772, "grad_norm": 1.4550195932388306, "learning_rate": 7.223175895924638e-06, "loss": 0.3674, "step": 427 }, { "epoch": 0.7739602169981917, "grad_norm": 1.7452478408813477, "learning_rate": 7.2097661483661355e-06, "loss": 0.386, "step": 428 }, { "epoch": 0.7757685352622061, "grad_norm": 1.4702410697937012, "learning_rate": 7.19633661894692e-06, "loss": 0.2623, "step": 429 }, { "epoch": 0.7775768535262206, "grad_norm": 1.5951834917068481, "learning_rate": 7.182887427888351e-06, "loss": 0.2645, "step": 430 }, { "epoch": 0.779385171790235, "grad_norm": 1.6657053232192993, "learning_rate": 7.169418695587791e-06, "loss": 0.3352, "step": 431 }, { "epoch": 0.7811934900542495, "grad_norm": 1.565721035003662, "learning_rate": 7.155930542617543e-06, "loss": 0.2862, "step": 432 }, { "epoch": 0.783001808318264, "grad_norm": 1.3390620946884155, "learning_rate": 7.142423089723758e-06, "loss": 0.2072, "step": 433 }, { "epoch": 0.7848101265822784, "grad_norm": 1.5327821969985962, "learning_rate": 7.128896457825364e-06, "loss": 0.2595, "step": 434 }, { "epoch": 0.786618444846293, "grad_norm": 1.4681278467178345, "learning_rate": 7.11535076801298e-06, "loss": 0.2244, "step": 435 }, { "epoch": 0.7884267631103075, "grad_norm": 1.9192992448806763, "learning_rate": 7.101786141547829e-06, "loss": 0.2909, "step": 436 }, { "epoch": 0.7902350813743219, "grad_norm": 1.759655237197876, "learning_rate": 7.088202699860656e-06, "loss": 0.3486, "step": 437 }, { "epoch": 0.7920433996383364, "grad_norm": 1.5253937244415283, "learning_rate": 7.074600564550643e-06, "loss": 0.341, "step": 438 }, { "epoch": 0.7938517179023508, "grad_norm": 1.4235355854034424, "learning_rate": 7.060979857384316e-06, "loss": 0.2729, "step": 439 }, { "epoch": 0.7956600361663653, "grad_norm": 1.6356101036071777, "learning_rate": 7.047340700294454e-06, "loss": 0.3009, "step": 440 }, { "epoch": 0.7974683544303798, "grad_norm": 1.7109578847885132, "learning_rate": 7.033683215379002e-06, "loss": 0.3417, "step": 441 }, { "epoch": 0.7992766726943942, "grad_norm": 1.3749796152114868, "learning_rate": 7.020007524899976e-06, "loss": 0.2922, "step": 442 }, { "epoch": 0.8010849909584087, "grad_norm": 1.4327658414840698, "learning_rate": 7.006313751282372e-06, "loss": 0.2927, "step": 443 }, { "epoch": 0.8028933092224232, "grad_norm": 1.6591452360153198, "learning_rate": 6.992602017113058e-06, "loss": 0.309, "step": 444 }, { "epoch": 0.8047016274864376, "grad_norm": 1.4170383214950562, "learning_rate": 6.978872445139695e-06, "loss": 0.2631, "step": 445 }, { "epoch": 0.8065099457504521, "grad_norm": 1.4618746042251587, "learning_rate": 6.965125158269619e-06, "loss": 0.2784, "step": 446 }, { "epoch": 0.8083182640144665, "grad_norm": 1.5405513048171997, "learning_rate": 6.951360279568758e-06, "loss": 0.2584, "step": 447 }, { "epoch": 0.810126582278481, "grad_norm": 1.462765097618103, "learning_rate": 6.9375779322605154e-06, "loss": 0.2366, "step": 448 }, { "epoch": 0.8119349005424955, "grad_norm": 1.471453309059143, "learning_rate": 6.923778239724681e-06, "loss": 0.2473, "step": 449 }, { "epoch": 0.8137432188065099, "grad_norm": 1.6243383884429932, "learning_rate": 6.909961325496312e-06, "loss": 0.2752, "step": 450 }, { "epoch": 0.8155515370705244, "grad_norm": 1.4661831855773926, "learning_rate": 6.896127313264643e-06, "loss": 0.2678, "step": 451 }, { "epoch": 0.8173598553345389, "grad_norm": 1.4200160503387451, "learning_rate": 6.88227632687196e-06, "loss": 0.2289, "step": 452 }, { "epoch": 0.8191681735985533, "grad_norm": 1.7850226163864136, "learning_rate": 6.868408490312511e-06, "loss": 0.2898, "step": 453 }, { "epoch": 0.8209764918625678, "grad_norm": 1.9734511375427246, "learning_rate": 6.854523927731383e-06, "loss": 0.403, "step": 454 }, { "epoch": 0.8227848101265823, "grad_norm": 1.5414447784423828, "learning_rate": 6.840622763423391e-06, "loss": 0.286, "step": 455 }, { "epoch": 0.8245931283905967, "grad_norm": 1.5268001556396484, "learning_rate": 6.8267051218319766e-06, "loss": 0.2316, "step": 456 }, { "epoch": 0.8264014466546112, "grad_norm": 1.4395512342453003, "learning_rate": 6.8127711275480805e-06, "loss": 0.2675, "step": 457 }, { "epoch": 0.8282097649186256, "grad_norm": 1.5637903213500977, "learning_rate": 6.798820905309036e-06, "loss": 0.3123, "step": 458 }, { "epoch": 0.8300180831826401, "grad_norm": 1.4868463277816772, "learning_rate": 6.784854579997446e-06, "loss": 0.2896, "step": 459 }, { "epoch": 0.8318264014466547, "grad_norm": 1.580917239189148, "learning_rate": 6.7708722766400745e-06, "loss": 0.3, "step": 460 }, { "epoch": 0.833634719710669, "grad_norm": 1.734419584274292, "learning_rate": 6.7568741204067145e-06, "loss": 0.3063, "step": 461 }, { "epoch": 0.8354430379746836, "grad_norm": 1.691807508468628, "learning_rate": 6.7428602366090764e-06, "loss": 0.3314, "step": 462 }, { "epoch": 0.8372513562386981, "grad_norm": 1.5647021532058716, "learning_rate": 6.728830750699667e-06, "loss": 0.3069, "step": 463 }, { "epoch": 0.8390596745027125, "grad_norm": 1.4804058074951172, "learning_rate": 6.714785788270658e-06, "loss": 0.2435, "step": 464 }, { "epoch": 0.840867992766727, "grad_norm": 1.6172109842300415, "learning_rate": 6.700725475052773e-06, "loss": 0.2863, "step": 465 }, { "epoch": 0.8426763110307414, "grad_norm": 1.6913933753967285, "learning_rate": 6.686649936914151e-06, "loss": 0.3529, "step": 466 }, { "epoch": 0.8444846292947559, "grad_norm": 1.769062876701355, "learning_rate": 6.672559299859228e-06, "loss": 0.3541, "step": 467 }, { "epoch": 0.8462929475587704, "grad_norm": 1.3293713331222534, "learning_rate": 6.658453690027604e-06, "loss": 0.2439, "step": 468 }, { "epoch": 0.8481012658227848, "grad_norm": 1.4551689624786377, "learning_rate": 6.644333233692917e-06, "loss": 0.2667, "step": 469 }, { "epoch": 0.8499095840867993, "grad_norm": 1.489614486694336, "learning_rate": 6.63019805726171e-06, "loss": 0.3174, "step": 470 }, { "epoch": 0.8517179023508138, "grad_norm": 1.582616925239563, "learning_rate": 6.616048287272301e-06, "loss": 0.2627, "step": 471 }, { "epoch": 0.8535262206148282, "grad_norm": 1.4557245969772339, "learning_rate": 6.601884050393649e-06, "loss": 0.2392, "step": 472 }, { "epoch": 0.8553345388788427, "grad_norm": 1.7610139846801758, "learning_rate": 6.587705473424223e-06, "loss": 0.3064, "step": 473 }, { "epoch": 0.8571428571428571, "grad_norm": 1.6895467042922974, "learning_rate": 6.57351268329086e-06, "loss": 0.3047, "step": 474 }, { "epoch": 0.8589511754068716, "grad_norm": 1.8085143566131592, "learning_rate": 6.55930580704764e-06, "loss": 0.3301, "step": 475 }, { "epoch": 0.8607594936708861, "grad_norm": 1.451945424079895, "learning_rate": 6.545084971874738e-06, "loss": 0.2785, "step": 476 }, { "epoch": 0.8625678119349005, "grad_norm": 1.516924262046814, "learning_rate": 6.5308503050772884e-06, "loss": 0.2396, "step": 477 }, { "epoch": 0.864376130198915, "grad_norm": 1.5330302715301514, "learning_rate": 6.51660193408425e-06, "loss": 0.3104, "step": 478 }, { "epoch": 0.8661844484629295, "grad_norm": 1.407259225845337, "learning_rate": 6.50233998644726e-06, "loss": 0.282, "step": 479 }, { "epoch": 0.8679927667269439, "grad_norm": 1.3526206016540527, "learning_rate": 6.4880645898394935e-06, "loss": 0.2353, "step": 480 }, { "epoch": 0.8698010849909584, "grad_norm": 1.5331631898880005, "learning_rate": 6.473775872054522e-06, "loss": 0.3307, "step": 481 }, { "epoch": 0.8716094032549728, "grad_norm": 1.4473603963851929, "learning_rate": 6.459473961005168e-06, "loss": 0.2642, "step": 482 }, { "epoch": 0.8734177215189873, "grad_norm": 1.4895997047424316, "learning_rate": 6.445158984722358e-06, "loss": 0.2385, "step": 483 }, { "epoch": 0.8752260397830018, "grad_norm": 1.3760124444961548, "learning_rate": 6.4308310713539845e-06, "loss": 0.2091, "step": 484 }, { "epoch": 0.8770343580470162, "grad_norm": 1.3591597080230713, "learning_rate": 6.4164903491637475e-06, "loss": 0.2246, "step": 485 }, { "epoch": 0.8788426763110307, "grad_norm": 1.5298205614089966, "learning_rate": 6.402136946530014e-06, "loss": 0.2328, "step": 486 }, { "epoch": 0.8806509945750453, "grad_norm": 1.9018235206604004, "learning_rate": 6.387770991944667e-06, "loss": 0.3431, "step": 487 }, { "epoch": 0.8824593128390597, "grad_norm": 1.551403522491455, "learning_rate": 6.373392614011952e-06, "loss": 0.2984, "step": 488 }, { "epoch": 0.8842676311030742, "grad_norm": 1.2497919797897339, "learning_rate": 6.359001941447331e-06, "loss": 0.1935, "step": 489 }, { "epoch": 0.8860759493670886, "grad_norm": 1.5711236000061035, "learning_rate": 6.344599103076329e-06, "loss": 0.272, "step": 490 }, { "epoch": 0.8878842676311031, "grad_norm": 1.634844183921814, "learning_rate": 6.330184227833376e-06, "loss": 0.2706, "step": 491 }, { "epoch": 0.8896925858951176, "grad_norm": 1.7166848182678223, "learning_rate": 6.315757444760659e-06, "loss": 0.3833, "step": 492 }, { "epoch": 0.891500904159132, "grad_norm": 1.5800580978393555, "learning_rate": 6.301318883006962e-06, "loss": 0.2419, "step": 493 }, { "epoch": 0.8933092224231465, "grad_norm": 1.4986897706985474, "learning_rate": 6.286868671826513e-06, "loss": 0.3292, "step": 494 }, { "epoch": 0.895117540687161, "grad_norm": 1.404306411743164, "learning_rate": 6.272406940577827e-06, "loss": 0.2745, "step": 495 }, { "epoch": 0.8969258589511754, "grad_norm": 1.4220858812332153, "learning_rate": 6.257933818722544e-06, "loss": 0.2482, "step": 496 }, { "epoch": 0.8987341772151899, "grad_norm": 1.5265475511550903, "learning_rate": 6.243449435824276e-06, "loss": 0.2867, "step": 497 }, { "epoch": 0.9005424954792043, "grad_norm": 1.661338210105896, "learning_rate": 6.228953921547441e-06, "loss": 0.3504, "step": 498 }, { "epoch": 0.9023508137432188, "grad_norm": 1.6318782567977905, "learning_rate": 6.2144474056561076e-06, "loss": 0.2575, "step": 499 }, { "epoch": 0.9041591320072333, "grad_norm": 1.8093661069869995, "learning_rate": 6.19993001801283e-06, "loss": 0.3547, "step": 500 }, { "epoch": 0.9059674502712477, "grad_norm": 1.5127339363098145, "learning_rate": 6.185401888577488e-06, "loss": 0.3163, "step": 501 }, { "epoch": 0.9077757685352622, "grad_norm": 1.630306363105774, "learning_rate": 6.17086314740612e-06, "loss": 0.3332, "step": 502 }, { "epoch": 0.9095840867992767, "grad_norm": 1.5948196649551392, "learning_rate": 6.1563139246497615e-06, "loss": 0.3157, "step": 503 }, { "epoch": 0.9113924050632911, "grad_norm": 1.519537091255188, "learning_rate": 6.141754350553279e-06, "loss": 0.2735, "step": 504 }, { "epoch": 0.9132007233273056, "grad_norm": 1.3500949144363403, "learning_rate": 6.1271845554542065e-06, "loss": 0.2519, "step": 505 }, { "epoch": 0.9150090415913201, "grad_norm": 1.3746148347854614, "learning_rate": 6.112604669781572e-06, "loss": 0.242, "step": 506 }, { "epoch": 0.9168173598553345, "grad_norm": 1.646591067314148, "learning_rate": 6.098014824054741e-06, "loss": 0.3417, "step": 507 }, { "epoch": 0.918625678119349, "grad_norm": 1.4279340505599976, "learning_rate": 6.083415148882236e-06, "loss": 0.2381, "step": 508 }, { "epoch": 0.9204339963833634, "grad_norm": 1.5878561735153198, "learning_rate": 6.068805774960574e-06, "loss": 0.2918, "step": 509 }, { "epoch": 0.9222423146473779, "grad_norm": 1.5567982196807861, "learning_rate": 6.054186833073096e-06, "loss": 0.2865, "step": 510 }, { "epoch": 0.9240506329113924, "grad_norm": 1.5154428482055664, "learning_rate": 6.039558454088796e-06, "loss": 0.2303, "step": 511 }, { "epoch": 0.9258589511754068, "grad_norm": 1.6575994491577148, "learning_rate": 6.024920768961153e-06, "loss": 0.239, "step": 512 }, { "epoch": 0.9276672694394213, "grad_norm": 1.5598336458206177, "learning_rate": 6.010273908726944e-06, "loss": 0.2932, "step": 513 }, { "epoch": 0.9294755877034359, "grad_norm": 1.4096535444259644, "learning_rate": 5.995618004505091e-06, "loss": 0.2694, "step": 514 }, { "epoch": 0.9312839059674503, "grad_norm": 1.4656530618667603, "learning_rate": 5.980953187495476e-06, "loss": 0.2529, "step": 515 }, { "epoch": 0.9330922242314648, "grad_norm": 1.4469208717346191, "learning_rate": 5.9662795889777666e-06, "loss": 0.2792, "step": 516 }, { "epoch": 0.9349005424954792, "grad_norm": 1.554093360900879, "learning_rate": 5.951597340310244e-06, "loss": 0.3278, "step": 517 }, { "epoch": 0.9367088607594937, "grad_norm": 1.4311602115631104, "learning_rate": 5.936906572928625e-06, "loss": 0.2748, "step": 518 }, { "epoch": 0.9385171790235082, "grad_norm": 1.6438734531402588, "learning_rate": 5.922207418344884e-06, "loss": 0.2362, "step": 519 }, { "epoch": 0.9403254972875226, "grad_norm": 1.4718252420425415, "learning_rate": 5.907500008146082e-06, "loss": 0.243, "step": 520 }, { "epoch": 0.9421338155515371, "grad_norm": 1.4284759759902954, "learning_rate": 5.892784473993184e-06, "loss": 0.2618, "step": 521 }, { "epoch": 0.9439421338155516, "grad_norm": 1.5094213485717773, "learning_rate": 5.878060947619877e-06, "loss": 0.3067, "step": 522 }, { "epoch": 0.945750452079566, "grad_norm": 1.6129846572875977, "learning_rate": 5.863329560831397e-06, "loss": 0.2617, "step": 523 }, { "epoch": 0.9475587703435805, "grad_norm": 1.5523322820663452, "learning_rate": 5.848590445503345e-06, "loss": 0.2711, "step": 524 }, { "epoch": 0.9493670886075949, "grad_norm": 1.687393307685852, "learning_rate": 5.8338437335805124e-06, "loss": 0.3135, "step": 525 }, { "epoch": 0.9511754068716094, "grad_norm": 1.4182137250900269, "learning_rate": 5.819089557075689e-06, "loss": 0.2825, "step": 526 }, { "epoch": 0.9529837251356239, "grad_norm": 1.6424469947814941, "learning_rate": 5.8043280480684925e-06, "loss": 0.2711, "step": 527 }, { "epoch": 0.9547920433996383, "grad_norm": 1.5802582502365112, "learning_rate": 5.78955933870418e-06, "loss": 0.3098, "step": 528 }, { "epoch": 0.9566003616636528, "grad_norm": 1.607804775238037, "learning_rate": 5.7747835611924655e-06, "loss": 0.3643, "step": 529 }, { "epoch": 0.9584086799276673, "grad_norm": 1.508002758026123, "learning_rate": 5.760000847806337e-06, "loss": 0.2897, "step": 530 }, { "epoch": 0.9602169981916817, "grad_norm": 1.50300133228302, "learning_rate": 5.745211330880872e-06, "loss": 0.2692, "step": 531 }, { "epoch": 0.9620253164556962, "grad_norm": 1.3220748901367188, "learning_rate": 5.730415142812059e-06, "loss": 0.2167, "step": 532 }, { "epoch": 0.9638336347197106, "grad_norm": 1.8082095384597778, "learning_rate": 5.7156124160555985e-06, "loss": 0.2805, "step": 533 }, { "epoch": 0.9656419529837251, "grad_norm": 1.355387806892395, "learning_rate": 5.70080328312573e-06, "loss": 0.2532, "step": 534 }, { "epoch": 0.9674502712477396, "grad_norm": 1.4044346809387207, "learning_rate": 5.68598787659404e-06, "loss": 0.2409, "step": 535 }, { "epoch": 0.969258589511754, "grad_norm": 1.614842176437378, "learning_rate": 5.671166329088278e-06, "loss": 0.2684, "step": 536 }, { "epoch": 0.9710669077757685, "grad_norm": 1.4982759952545166, "learning_rate": 5.656338773291165e-06, "loss": 0.282, "step": 537 }, { "epoch": 0.972875226039783, "grad_norm": 1.536207675933838, "learning_rate": 5.641505341939212e-06, "loss": 0.3339, "step": 538 }, { "epoch": 0.9746835443037974, "grad_norm": 1.4055485725402832, "learning_rate": 5.626666167821522e-06, "loss": 0.2304, "step": 539 }, { "epoch": 0.976491862567812, "grad_norm": 1.4788035154342651, "learning_rate": 5.611821383778614e-06, "loss": 0.2989, "step": 540 }, { "epoch": 0.9783001808318263, "grad_norm": 1.4801082611083984, "learning_rate": 5.596971122701221e-06, "loss": 0.2837, "step": 541 }, { "epoch": 0.9801084990958409, "grad_norm": 1.4849605560302734, "learning_rate": 5.582115517529114e-06, "loss": 0.245, "step": 542 }, { "epoch": 0.9819168173598554, "grad_norm": 1.3338375091552734, "learning_rate": 5.5672547012499e-06, "loss": 0.2098, "step": 543 }, { "epoch": 0.9837251356238698, "grad_norm": 1.3355313539505005, "learning_rate": 5.55238880689783e-06, "loss": 0.2625, "step": 544 }, { "epoch": 0.9855334538878843, "grad_norm": 1.4552525281906128, "learning_rate": 5.537517967552626e-06, "loss": 0.2899, "step": 545 }, { "epoch": 0.9873417721518988, "grad_norm": 1.4461898803710938, "learning_rate": 5.522642316338268e-06, "loss": 0.3198, "step": 546 }, { "epoch": 0.9891500904159132, "grad_norm": 1.5855600833892822, "learning_rate": 5.507761986421818e-06, "loss": 0.3379, "step": 547 }, { "epoch": 0.9909584086799277, "grad_norm": 1.460728406906128, "learning_rate": 5.4928771110122185e-06, "loss": 0.2576, "step": 548 }, { "epoch": 0.9927667269439421, "grad_norm": 1.5250566005706787, "learning_rate": 5.477987823359104e-06, "loss": 0.2946, "step": 549 }, { "epoch": 0.9945750452079566, "grad_norm": 1.5951241254806519, "learning_rate": 5.463094256751608e-06, "loss": 0.296, "step": 550 }, { "epoch": 0.9963833634719711, "grad_norm": 1.583813190460205, "learning_rate": 5.448196544517168e-06, "loss": 0.2926, "step": 551 }, { "epoch": 0.9981916817359855, "grad_norm": 1.6294541358947754, "learning_rate": 5.433294820020335e-06, "loss": 0.318, "step": 552 }, { "epoch": 1.0, "grad_norm": 1.5628619194030762, "learning_rate": 5.41838921666158e-06, "loss": 0.2985, "step": 553 }, { "epoch": 1.0018083182640145, "grad_norm": 1.288798451423645, "learning_rate": 5.403479867876087e-06, "loss": 0.1865, "step": 554 }, { "epoch": 1.003616636528029, "grad_norm": 1.3543511629104614, "learning_rate": 5.388566907132583e-06, "loss": 0.2104, "step": 555 }, { "epoch": 1.0054249547920433, "grad_norm": 1.5060940980911255, "learning_rate": 5.373650467932122e-06, "loss": 0.2433, "step": 556 }, { "epoch": 1.0072332730560578, "grad_norm": 1.311565637588501, "learning_rate": 5.358730683806897e-06, "loss": 0.1904, "step": 557 }, { "epoch": 1.0090415913200723, "grad_norm": 1.3539799451828003, "learning_rate": 5.343807688319047e-06, "loss": 0.18, "step": 558 }, { "epoch": 1.0108499095840868, "grad_norm": 1.288733720779419, "learning_rate": 5.328881615059458e-06, "loss": 0.1911, "step": 559 }, { "epoch": 1.0126582278481013, "grad_norm": 1.2615751028060913, "learning_rate": 5.3139525976465675e-06, "loss": 0.1927, "step": 560 }, { "epoch": 1.0144665461121158, "grad_norm": 1.2770920991897583, "learning_rate": 5.299020769725172e-06, "loss": 0.1889, "step": 561 }, { "epoch": 1.0162748643761301, "grad_norm": 1.265012502670288, "learning_rate": 5.284086264965224e-06, "loss": 0.1695, "step": 562 }, { "epoch": 1.0180831826401446, "grad_norm": 1.4698776006698608, "learning_rate": 5.269149217060642e-06, "loss": 0.2295, "step": 563 }, { "epoch": 1.0198915009041591, "grad_norm": 1.3412383794784546, "learning_rate": 5.2542097597281095e-06, "loss": 0.1802, "step": 564 }, { "epoch": 1.0216998191681737, "grad_norm": 1.6153024435043335, "learning_rate": 5.239268026705878e-06, "loss": 0.2364, "step": 565 }, { "epoch": 1.0235081374321882, "grad_norm": 1.5337324142456055, "learning_rate": 5.224324151752575e-06, "loss": 0.2286, "step": 566 }, { "epoch": 1.0253164556962024, "grad_norm": 1.5997281074523926, "learning_rate": 5.209378268645998e-06, "loss": 0.2103, "step": 567 }, { "epoch": 1.027124773960217, "grad_norm": 1.6632851362228394, "learning_rate": 5.194430511181925e-06, "loss": 0.243, "step": 568 }, { "epoch": 1.0289330922242315, "grad_norm": 1.7955586910247803, "learning_rate": 5.179481013172912e-06, "loss": 0.2487, "step": 569 }, { "epoch": 1.030741410488246, "grad_norm": 1.322706937789917, "learning_rate": 5.1645299084470936e-06, "loss": 0.1406, "step": 570 }, { "epoch": 1.0325497287522605, "grad_norm": 1.3085888624191284, "learning_rate": 5.1495773308469935e-06, "loss": 0.1515, "step": 571 }, { "epoch": 1.0343580470162748, "grad_norm": 1.3752695322036743, "learning_rate": 5.134623414228315e-06, "loss": 0.1758, "step": 572 }, { "epoch": 1.0361663652802893, "grad_norm": 1.3909094333648682, "learning_rate": 5.119668292458751e-06, "loss": 0.1809, "step": 573 }, { "epoch": 1.0379746835443038, "grad_norm": 1.6259689331054688, "learning_rate": 5.1047120994167855e-06, "loss": 0.2162, "step": 574 }, { "epoch": 1.0397830018083183, "grad_norm": 1.3644503355026245, "learning_rate": 5.0897549689904865e-06, "loss": 0.1827, "step": 575 }, { "epoch": 1.0415913200723328, "grad_norm": 1.5412620306015015, "learning_rate": 5.074797035076319e-06, "loss": 0.2085, "step": 576 }, { "epoch": 1.0433996383363473, "grad_norm": 1.4829899072647095, "learning_rate": 5.059838431577937e-06, "loss": 0.1852, "step": 577 }, { "epoch": 1.0452079566003616, "grad_norm": 1.7785180807113647, "learning_rate": 5.04487929240499e-06, "loss": 0.2667, "step": 578 }, { "epoch": 1.047016274864376, "grad_norm": 1.3702012300491333, "learning_rate": 5.029919751471925e-06, "loss": 0.2123, "step": 579 }, { "epoch": 1.0488245931283906, "grad_norm": 1.2965071201324463, "learning_rate": 5.014959942696782e-06, "loss": 0.1702, "step": 580 }, { "epoch": 1.0506329113924051, "grad_norm": 1.4994701147079468, "learning_rate": 5e-06, "loss": 0.1804, "step": 581 }, { "epoch": 1.0524412296564196, "grad_norm": 1.5292582511901855, "learning_rate": 4.98504005730322e-06, "loss": 0.2564, "step": 582 }, { "epoch": 1.054249547920434, "grad_norm": 1.5940722227096558, "learning_rate": 4.970080248528077e-06, "loss": 0.2782, "step": 583 }, { "epoch": 1.0560578661844484, "grad_norm": 1.4146605730056763, "learning_rate": 4.955120707595011e-06, "loss": 0.1607, "step": 584 }, { "epoch": 1.057866184448463, "grad_norm": 1.4707739353179932, "learning_rate": 4.940161568422065e-06, "loss": 0.2052, "step": 585 }, { "epoch": 1.0596745027124774, "grad_norm": 1.5129636526107788, "learning_rate": 4.9252029649236835e-06, "loss": 0.2395, "step": 586 }, { "epoch": 1.061482820976492, "grad_norm": 1.3441998958587646, "learning_rate": 4.910245031009515e-06, "loss": 0.1619, "step": 587 }, { "epoch": 1.0632911392405062, "grad_norm": 1.3049641847610474, "learning_rate": 4.895287900583216e-06, "loss": 0.1703, "step": 588 }, { "epoch": 1.0650994575045207, "grad_norm": 1.4299386739730835, "learning_rate": 4.88033170754125e-06, "loss": 0.2155, "step": 589 }, { "epoch": 1.0669077757685352, "grad_norm": 1.5841361284255981, "learning_rate": 4.865376585771687e-06, "loss": 0.2355, "step": 590 }, { "epoch": 1.0687160940325497, "grad_norm": 1.569944977760315, "learning_rate": 4.850422669153009e-06, "loss": 0.2132, "step": 591 }, { "epoch": 1.0705244122965643, "grad_norm": 1.3636471033096313, "learning_rate": 4.835470091552906e-06, "loss": 0.19, "step": 592 }, { "epoch": 1.0723327305605788, "grad_norm": 1.4102762937545776, "learning_rate": 4.8205189868270894e-06, "loss": 0.1957, "step": 593 }, { "epoch": 1.074141048824593, "grad_norm": 1.485796332359314, "learning_rate": 4.805569488818077e-06, "loss": 0.2053, "step": 594 }, { "epoch": 1.0759493670886076, "grad_norm": 1.3742706775665283, "learning_rate": 4.7906217313540035e-06, "loss": 0.1945, "step": 595 }, { "epoch": 1.077757685352622, "grad_norm": 1.372023105621338, "learning_rate": 4.775675848247427e-06, "loss": 0.1508, "step": 596 }, { "epoch": 1.0795660036166366, "grad_norm": 1.3647346496582031, "learning_rate": 4.760731973294122e-06, "loss": 0.1703, "step": 597 }, { "epoch": 1.081374321880651, "grad_norm": 1.4168416261672974, "learning_rate": 4.745790240271892e-06, "loss": 0.203, "step": 598 }, { "epoch": 1.0831826401446654, "grad_norm": 1.3828188180923462, "learning_rate": 4.73085078293936e-06, "loss": 0.1736, "step": 599 }, { "epoch": 1.0849909584086799, "grad_norm": 1.4786967039108276, "learning_rate": 4.715913735034779e-06, "loss": 0.1753, "step": 600 }, { "epoch": 1.0867992766726944, "grad_norm": 1.7085444927215576, "learning_rate": 4.700979230274829e-06, "loss": 0.1833, "step": 601 }, { "epoch": 1.0886075949367089, "grad_norm": 1.6073724031448364, "learning_rate": 4.686047402353433e-06, "loss": 0.2471, "step": 602 }, { "epoch": 1.0904159132007234, "grad_norm": 1.4836734533309937, "learning_rate": 4.6711183849405435e-06, "loss": 0.2139, "step": 603 }, { "epoch": 1.092224231464738, "grad_norm": 1.4820582866668701, "learning_rate": 4.6561923116809545e-06, "loss": 0.1897, "step": 604 }, { "epoch": 1.0940325497287522, "grad_norm": 1.4775195121765137, "learning_rate": 4.641269316193104e-06, "loss": 0.2223, "step": 605 }, { "epoch": 1.0958408679927667, "grad_norm": 1.3953652381896973, "learning_rate": 4.626349532067879e-06, "loss": 0.2057, "step": 606 }, { "epoch": 1.0976491862567812, "grad_norm": 1.3379745483398438, "learning_rate": 4.611433092867417e-06, "loss": 0.1685, "step": 607 }, { "epoch": 1.0994575045207957, "grad_norm": 1.5075714588165283, "learning_rate": 4.596520132123915e-06, "loss": 0.238, "step": 608 }, { "epoch": 1.1012658227848102, "grad_norm": 1.5365735292434692, "learning_rate": 4.581610783338424e-06, "loss": 0.2399, "step": 609 }, { "epoch": 1.1030741410488245, "grad_norm": 1.2758504152297974, "learning_rate": 4.566705179979665e-06, "loss": 0.1774, "step": 610 }, { "epoch": 1.104882459312839, "grad_norm": 1.272873044013977, "learning_rate": 4.551803455482833e-06, "loss": 0.1701, "step": 611 }, { "epoch": 1.1066907775768535, "grad_norm": 1.5903825759887695, "learning_rate": 4.536905743248394e-06, "loss": 0.2408, "step": 612 }, { "epoch": 1.108499095840868, "grad_norm": 1.262425422668457, "learning_rate": 4.522012176640898e-06, "loss": 0.1584, "step": 613 }, { "epoch": 1.1103074141048825, "grad_norm": 1.2817269563674927, "learning_rate": 4.507122888987782e-06, "loss": 0.1411, "step": 614 }, { "epoch": 1.1121157323688968, "grad_norm": 1.4184229373931885, "learning_rate": 4.4922380135781835e-06, "loss": 0.1892, "step": 615 }, { "epoch": 1.1139240506329113, "grad_norm": 1.408778429031372, "learning_rate": 4.477357683661734e-06, "loss": 0.1921, "step": 616 }, { "epoch": 1.1157323688969258, "grad_norm": 1.4096134901046753, "learning_rate": 4.462482032447377e-06, "loss": 0.1833, "step": 617 }, { "epoch": 1.1175406871609403, "grad_norm": 1.546582579612732, "learning_rate": 4.447611193102171e-06, "loss": 0.2424, "step": 618 }, { "epoch": 1.1193490054249549, "grad_norm": 1.3519054651260376, "learning_rate": 4.432745298750102e-06, "loss": 0.1856, "step": 619 }, { "epoch": 1.1211573236889691, "grad_norm": 1.5110186338424683, "learning_rate": 4.417884482470887e-06, "loss": 0.2059, "step": 620 }, { "epoch": 1.1229656419529837, "grad_norm": 1.5506789684295654, "learning_rate": 4.4030288772987795e-06, "loss": 0.1998, "step": 621 }, { "epoch": 1.1247739602169982, "grad_norm": 1.5391626358032227, "learning_rate": 4.388178616221389e-06, "loss": 0.2146, "step": 622 }, { "epoch": 1.1265822784810127, "grad_norm": 1.4599207639694214, "learning_rate": 4.373333832178478e-06, "loss": 0.1889, "step": 623 }, { "epoch": 1.1283905967450272, "grad_norm": 1.6507724523544312, "learning_rate": 4.35849465806079e-06, "loss": 0.2617, "step": 624 }, { "epoch": 1.1301989150090417, "grad_norm": 1.4002302885055542, "learning_rate": 4.3436612267088355e-06, "loss": 0.1588, "step": 625 }, { "epoch": 1.132007233273056, "grad_norm": 1.4234485626220703, "learning_rate": 4.3288336709117246e-06, "loss": 0.1777, "step": 626 }, { "epoch": 1.1338155515370705, "grad_norm": 1.4206223487854004, "learning_rate": 4.314012123405961e-06, "loss": 0.1479, "step": 627 }, { "epoch": 1.135623869801085, "grad_norm": 1.699669361114502, "learning_rate": 4.299196716874271e-06, "loss": 0.2543, "step": 628 }, { "epoch": 1.1374321880650995, "grad_norm": 1.4417308568954468, "learning_rate": 4.284387583944403e-06, "loss": 0.1863, "step": 629 }, { "epoch": 1.139240506329114, "grad_norm": 1.4756022691726685, "learning_rate": 4.269584857187942e-06, "loss": 0.1957, "step": 630 }, { "epoch": 1.1410488245931285, "grad_norm": 1.5260920524597168, "learning_rate": 4.254788669119127e-06, "loss": 0.2506, "step": 631 }, { "epoch": 1.1428571428571428, "grad_norm": 1.3204761743545532, "learning_rate": 4.239999152193664e-06, "loss": 0.1685, "step": 632 }, { "epoch": 1.1446654611211573, "grad_norm": 1.4023820161819458, "learning_rate": 4.225216438807536e-06, "loss": 0.1826, "step": 633 }, { "epoch": 1.1464737793851718, "grad_norm": 1.3649920225143433, "learning_rate": 4.2104406612958216e-06, "loss": 0.184, "step": 634 }, { "epoch": 1.1482820976491863, "grad_norm": 1.4958913326263428, "learning_rate": 4.195671951931509e-06, "loss": 0.2063, "step": 635 }, { "epoch": 1.1500904159132008, "grad_norm": 1.4916859865188599, "learning_rate": 4.180910442924312e-06, "loss": 0.2357, "step": 636 }, { "epoch": 1.1518987341772151, "grad_norm": 1.4113558530807495, "learning_rate": 4.166156266419489e-06, "loss": 0.2031, "step": 637 }, { "epoch": 1.1537070524412296, "grad_norm": 1.4064443111419678, "learning_rate": 4.1514095544966556e-06, "loss": 0.1805, "step": 638 }, { "epoch": 1.1555153707052441, "grad_norm": 1.7487319707870483, "learning_rate": 4.136670439168605e-06, "loss": 0.2385, "step": 639 }, { "epoch": 1.1573236889692586, "grad_norm": 1.470876693725586, "learning_rate": 4.121939052380125e-06, "loss": 0.1843, "step": 640 }, { "epoch": 1.1591320072332731, "grad_norm": 1.432257890701294, "learning_rate": 4.107215526006818e-06, "loss": 0.1962, "step": 641 }, { "epoch": 1.1609403254972874, "grad_norm": 1.3049852848052979, "learning_rate": 4.092499991853919e-06, "loss": 0.1524, "step": 642 }, { "epoch": 1.162748643761302, "grad_norm": 1.6097644567489624, "learning_rate": 4.0777925816551175e-06, "loss": 0.2284, "step": 643 }, { "epoch": 1.1645569620253164, "grad_norm": 1.5653713941574097, "learning_rate": 4.063093427071376e-06, "loss": 0.2529, "step": 644 }, { "epoch": 1.166365280289331, "grad_norm": 1.3673524856567383, "learning_rate": 4.048402659689757e-06, "loss": 0.1827, "step": 645 }, { "epoch": 1.1681735985533455, "grad_norm": 1.1965135335922241, "learning_rate": 4.033720411022235e-06, "loss": 0.1805, "step": 646 }, { "epoch": 1.1699819168173597, "grad_norm": 1.3401261568069458, "learning_rate": 4.019046812504526e-06, "loss": 0.2014, "step": 647 }, { "epoch": 1.1717902350813743, "grad_norm": 1.480340600013733, "learning_rate": 4.0043819954949105e-06, "loss": 0.1971, "step": 648 }, { "epoch": 1.1735985533453888, "grad_norm": 1.4571661949157715, "learning_rate": 3.989726091273056e-06, "loss": 0.1972, "step": 649 }, { "epoch": 1.1754068716094033, "grad_norm": 1.4018959999084473, "learning_rate": 3.975079231038848e-06, "loss": 0.1669, "step": 650 }, { "epoch": 1.1772151898734178, "grad_norm": 1.4926209449768066, "learning_rate": 3.960441545911205e-06, "loss": 0.2012, "step": 651 }, { "epoch": 1.179023508137432, "grad_norm": 1.5835425853729248, "learning_rate": 3.9458131669269066e-06, "loss": 0.1727, "step": 652 }, { "epoch": 1.1808318264014466, "grad_norm": 1.6140756607055664, "learning_rate": 3.931194225039427e-06, "loss": 0.2129, "step": 653 }, { "epoch": 1.182640144665461, "grad_norm": 1.4102574586868286, "learning_rate": 3.916584851117766e-06, "loss": 0.1861, "step": 654 }, { "epoch": 1.1844484629294756, "grad_norm": 1.3546948432922363, "learning_rate": 3.90198517594526e-06, "loss": 0.1585, "step": 655 }, { "epoch": 1.18625678119349, "grad_norm": 1.4348087310791016, "learning_rate": 3.887395330218429e-06, "loss": 0.1853, "step": 656 }, { "epoch": 1.1880650994575046, "grad_norm": 1.522248387336731, "learning_rate": 3.872815444545794e-06, "loss": 0.2177, "step": 657 }, { "epoch": 1.189873417721519, "grad_norm": 1.2331684827804565, "learning_rate": 3.8582456494467214e-06, "loss": 0.1467, "step": 658 }, { "epoch": 1.1916817359855334, "grad_norm": 1.3185243606567383, "learning_rate": 3.843686075350239e-06, "loss": 0.1828, "step": 659 }, { "epoch": 1.193490054249548, "grad_norm": 1.4795818328857422, "learning_rate": 3.829136852593881e-06, "loss": 0.2041, "step": 660 }, { "epoch": 1.1952983725135624, "grad_norm": 1.5679435729980469, "learning_rate": 3.8145981114225135e-06, "loss": 0.2063, "step": 661 }, { "epoch": 1.197106690777577, "grad_norm": 1.3789476156234741, "learning_rate": 3.8000699819871704e-06, "loss": 0.1525, "step": 662 }, { "epoch": 1.1989150090415914, "grad_norm": 1.5000629425048828, "learning_rate": 3.785552594343894e-06, "loss": 0.174, "step": 663 }, { "epoch": 1.2007233273056057, "grad_norm": 1.415205478668213, "learning_rate": 3.7710460784525617e-06, "loss": 0.1635, "step": 664 }, { "epoch": 1.2025316455696202, "grad_norm": 1.4001487493515015, "learning_rate": 3.756550564175727e-06, "loss": 0.1922, "step": 665 }, { "epoch": 1.2043399638336347, "grad_norm": 1.6880931854248047, "learning_rate": 3.7420661812774577e-06, "loss": 0.231, "step": 666 }, { "epoch": 1.2061482820976492, "grad_norm": 1.350974202156067, "learning_rate": 3.7275930594221752e-06, "loss": 0.1778, "step": 667 }, { "epoch": 1.2079566003616637, "grad_norm": 1.636757254600525, "learning_rate": 3.7131313281734895e-06, "loss": 0.2303, "step": 668 }, { "epoch": 1.209764918625678, "grad_norm": 1.5623453855514526, "learning_rate": 3.69868111699304e-06, "loss": 0.226, "step": 669 }, { "epoch": 1.2115732368896925, "grad_norm": 1.3637696504592896, "learning_rate": 3.6842425552393424e-06, "loss": 0.1791, "step": 670 }, { "epoch": 1.213381555153707, "grad_norm": 1.37736177444458, "learning_rate": 3.669815772166625e-06, "loss": 0.1475, "step": 671 }, { "epoch": 1.2151898734177216, "grad_norm": 1.3118550777435303, "learning_rate": 3.655400896923672e-06, "loss": 0.1695, "step": 672 }, { "epoch": 1.216998191681736, "grad_norm": 1.3771377801895142, "learning_rate": 3.6409980585526707e-06, "loss": 0.1681, "step": 673 }, { "epoch": 1.2188065099457503, "grad_norm": 1.6271418333053589, "learning_rate": 3.62660738598805e-06, "loss": 0.2083, "step": 674 }, { "epoch": 1.2206148282097649, "grad_norm": 1.3113658428192139, "learning_rate": 3.6122290080553334e-06, "loss": 0.1649, "step": 675 }, { "epoch": 1.2224231464737794, "grad_norm": 1.4772794246673584, "learning_rate": 3.5978630534699873e-06, "loss": 0.204, "step": 676 }, { "epoch": 1.2242314647377939, "grad_norm": 1.4688736200332642, "learning_rate": 3.583509650836254e-06, "loss": 0.1917, "step": 677 }, { "epoch": 1.2260397830018084, "grad_norm": 1.5840643644332886, "learning_rate": 3.5691689286460172e-06, "loss": 0.2115, "step": 678 }, { "epoch": 1.2278481012658227, "grad_norm": 1.2356911897659302, "learning_rate": 3.5548410152776414e-06, "loss": 0.148, "step": 679 }, { "epoch": 1.2296564195298372, "grad_norm": 1.4228116273880005, "learning_rate": 3.540526038994834e-06, "loss": 0.1925, "step": 680 }, { "epoch": 1.2314647377938517, "grad_norm": 1.6336411237716675, "learning_rate": 3.526224127945479e-06, "loss": 0.2096, "step": 681 }, { "epoch": 1.2332730560578662, "grad_norm": 1.459225058555603, "learning_rate": 3.5119354101605086e-06, "loss": 0.219, "step": 682 }, { "epoch": 1.2350813743218807, "grad_norm": 1.5233231782913208, "learning_rate": 3.4976600135527403e-06, "loss": 0.2047, "step": 683 }, { "epoch": 1.2368896925858952, "grad_norm": 1.67374849319458, "learning_rate": 3.4833980659157507e-06, "loss": 0.2019, "step": 684 }, { "epoch": 1.2386980108499095, "grad_norm": 1.4992425441741943, "learning_rate": 3.469149694922712e-06, "loss": 0.194, "step": 685 }, { "epoch": 1.240506329113924, "grad_norm": 1.3291999101638794, "learning_rate": 3.4549150281252635e-06, "loss": 0.1763, "step": 686 }, { "epoch": 1.2423146473779385, "grad_norm": 1.4153790473937988, "learning_rate": 3.4406941929523607e-06, "loss": 0.1764, "step": 687 }, { "epoch": 1.244122965641953, "grad_norm": 1.474101185798645, "learning_rate": 3.4264873167091405e-06, "loss": 0.2023, "step": 688 }, { "epoch": 1.2459312839059675, "grad_norm": 1.4104926586151123, "learning_rate": 3.412294526575779e-06, "loss": 0.182, "step": 689 }, { "epoch": 1.247739602169982, "grad_norm": 1.5934327840805054, "learning_rate": 3.398115949606352e-06, "loss": 0.2415, "step": 690 }, { "epoch": 1.2495479204339963, "grad_norm": 1.464013934135437, "learning_rate": 3.383951712727701e-06, "loss": 0.1953, "step": 691 }, { "epoch": 1.2513562386980108, "grad_norm": 1.277265191078186, "learning_rate": 3.3698019427382912e-06, "loss": 0.1425, "step": 692 }, { "epoch": 1.2531645569620253, "grad_norm": 1.6223770380020142, "learning_rate": 3.355666766307084e-06, "loss": 0.2527, "step": 693 }, { "epoch": 1.2549728752260398, "grad_norm": 1.5549708604812622, "learning_rate": 3.341546309972398e-06, "loss": 0.1909, "step": 694 }, { "epoch": 1.2567811934900543, "grad_norm": 1.5393190383911133, "learning_rate": 3.327440700140774e-06, "loss": 0.2212, "step": 695 }, { "epoch": 1.2585895117540686, "grad_norm": 1.2974177598953247, "learning_rate": 3.3133500630858507e-06, "loss": 0.16, "step": 696 }, { "epoch": 1.2603978300180831, "grad_norm": 1.473394513130188, "learning_rate": 3.299274524947229e-06, "loss": 0.2186, "step": 697 }, { "epoch": 1.2622061482820977, "grad_norm": 1.5463542938232422, "learning_rate": 3.2852142117293435e-06, "loss": 0.2018, "step": 698 }, { "epoch": 1.2640144665461122, "grad_norm": 1.3791486024856567, "learning_rate": 3.2711692493003357e-06, "loss": 0.1811, "step": 699 }, { "epoch": 1.2658227848101267, "grad_norm": 1.3562315702438354, "learning_rate": 3.2571397633909252e-06, "loss": 0.1681, "step": 700 }, { "epoch": 1.267631103074141, "grad_norm": 1.4410741329193115, "learning_rate": 3.2431258795932863e-06, "loss": 0.1581, "step": 701 }, { "epoch": 1.2694394213381555, "grad_norm": 1.5001894235610962, "learning_rate": 3.229127723359927e-06, "loss": 0.2031, "step": 702 }, { "epoch": 1.27124773960217, "grad_norm": 1.7136058807373047, "learning_rate": 3.215145420002555e-06, "loss": 0.227, "step": 703 }, { "epoch": 1.2730560578661845, "grad_norm": 1.444724202156067, "learning_rate": 3.2011790946909673e-06, "loss": 0.218, "step": 704 }, { "epoch": 1.274864376130199, "grad_norm": 1.2470664978027344, "learning_rate": 3.1872288724519207e-06, "loss": 0.1459, "step": 705 }, { "epoch": 1.2766726943942133, "grad_norm": 1.601298213005066, "learning_rate": 3.173294878168025e-06, "loss": 0.2433, "step": 706 }, { "epoch": 1.2784810126582278, "grad_norm": 1.6532466411590576, "learning_rate": 3.1593772365766107e-06, "loss": 0.2537, "step": 707 }, { "epoch": 1.2802893309222423, "grad_norm": 1.263442873954773, "learning_rate": 3.1454760722686206e-06, "loss": 0.1649, "step": 708 }, { "epoch": 1.2820976491862568, "grad_norm": 1.5168344974517822, "learning_rate": 3.1315915096874894e-06, "loss": 0.1891, "step": 709 }, { "epoch": 1.2839059674502713, "grad_norm": 1.40994131565094, "learning_rate": 3.11772367312804e-06, "loss": 0.1835, "step": 710 }, { "epoch": 1.2857142857142856, "grad_norm": 1.3709584474563599, "learning_rate": 3.1038726867353587e-06, "loss": 0.1642, "step": 711 }, { "epoch": 1.2875226039783003, "grad_norm": 1.2538282871246338, "learning_rate": 3.090038674503688e-06, "loss": 0.147, "step": 712 }, { "epoch": 1.2893309222423146, "grad_norm": 1.4287935495376587, "learning_rate": 3.076221760275321e-06, "loss": 0.1811, "step": 713 }, { "epoch": 1.2911392405063291, "grad_norm": 1.3382304906845093, "learning_rate": 3.0624220677394854e-06, "loss": 0.152, "step": 714 }, { "epoch": 1.2929475587703436, "grad_norm": 1.5919476747512817, "learning_rate": 3.048639720431244e-06, "loss": 0.1989, "step": 715 }, { "epoch": 1.2947558770343581, "grad_norm": 1.452908992767334, "learning_rate": 3.0348748417303826e-06, "loss": 0.2012, "step": 716 }, { "epoch": 1.2965641952983726, "grad_norm": 1.3485349416732788, "learning_rate": 3.0211275548603076e-06, "loss": 0.1667, "step": 717 }, { "epoch": 1.298372513562387, "grad_norm": 1.3571429252624512, "learning_rate": 3.007397982886942e-06, "loss": 0.1937, "step": 718 }, { "epoch": 1.3001808318264014, "grad_norm": 1.554996371269226, "learning_rate": 2.9936862487176295e-06, "loss": 0.1983, "step": 719 }, { "epoch": 1.301989150090416, "grad_norm": 1.5363129377365112, "learning_rate": 2.979992475100024e-06, "loss": 0.2064, "step": 720 }, { "epoch": 1.3037974683544304, "grad_norm": 1.491005539894104, "learning_rate": 2.966316784621e-06, "loss": 0.1952, "step": 721 }, { "epoch": 1.305605786618445, "grad_norm": 1.4383454322814941, "learning_rate": 2.9526592997055488e-06, "loss": 0.1703, "step": 722 }, { "epoch": 1.3074141048824592, "grad_norm": 1.2506189346313477, "learning_rate": 2.9390201426156855e-06, "loss": 0.1376, "step": 723 }, { "epoch": 1.3092224231464737, "grad_norm": 1.4490293264389038, "learning_rate": 2.9253994354493575e-06, "loss": 0.184, "step": 724 }, { "epoch": 1.3110307414104883, "grad_norm": 1.474991798400879, "learning_rate": 2.911797300139345e-06, "loss": 0.1932, "step": 725 }, { "epoch": 1.3128390596745028, "grad_norm": 1.295271873474121, "learning_rate": 2.8982138584521734e-06, "loss": 0.1402, "step": 726 }, { "epoch": 1.3146473779385173, "grad_norm": 1.706601858139038, "learning_rate": 2.884649231987021e-06, "loss": 0.2696, "step": 727 }, { "epoch": 1.3164556962025316, "grad_norm": 1.5334216356277466, "learning_rate": 2.871103542174637e-06, "loss": 0.2192, "step": 728 }, { "epoch": 1.318264014466546, "grad_norm": 1.4288280010223389, "learning_rate": 2.857576910276243e-06, "loss": 0.2015, "step": 729 }, { "epoch": 1.3200723327305606, "grad_norm": 1.4637763500213623, "learning_rate": 2.844069457382459e-06, "loss": 0.1809, "step": 730 }, { "epoch": 1.321880650994575, "grad_norm": 1.720653772354126, "learning_rate": 2.83058130441221e-06, "loss": 0.2008, "step": 731 }, { "epoch": 1.3236889692585896, "grad_norm": 1.4206902980804443, "learning_rate": 2.817112572111651e-06, "loss": 0.1653, "step": 732 }, { "epoch": 1.3254972875226039, "grad_norm": 1.5712977647781372, "learning_rate": 2.803663381053081e-06, "loss": 0.2031, "step": 733 }, { "epoch": 1.3273056057866184, "grad_norm": 1.3399608135223389, "learning_rate": 2.790233851633868e-06, "loss": 0.1902, "step": 734 }, { "epoch": 1.3291139240506329, "grad_norm": 1.6704126596450806, "learning_rate": 2.776824104075364e-06, "loss": 0.2311, "step": 735 }, { "epoch": 1.3309222423146474, "grad_norm": 1.3174846172332764, "learning_rate": 2.7634342584218364e-06, "loss": 0.1528, "step": 736 }, { "epoch": 1.332730560578662, "grad_norm": 1.3168045282363892, "learning_rate": 2.7500644345393945e-06, "loss": 0.1538, "step": 737 }, { "epoch": 1.3345388788426762, "grad_norm": 1.5989593267440796, "learning_rate": 2.7367147521149052e-06, "loss": 0.1861, "step": 738 }, { "epoch": 1.3363471971066907, "grad_norm": 1.5324201583862305, "learning_rate": 2.723385330654933e-06, "loss": 0.2057, "step": 739 }, { "epoch": 1.3381555153707052, "grad_norm": 1.3872687816619873, "learning_rate": 2.7100762894846633e-06, "loss": 0.1736, "step": 740 }, { "epoch": 1.3399638336347197, "grad_norm": 1.5545507669448853, "learning_rate": 2.6967877477468394e-06, "loss": 0.1932, "step": 741 }, { "epoch": 1.3417721518987342, "grad_norm": 1.3831270933151245, "learning_rate": 2.683519824400693e-06, "loss": 0.1806, "step": 742 }, { "epoch": 1.3435804701627485, "grad_norm": 1.4221932888031006, "learning_rate": 2.6702726382208775e-06, "loss": 0.1794, "step": 743 }, { "epoch": 1.3453887884267632, "grad_norm": 1.638218879699707, "learning_rate": 2.657046307796407e-06, "loss": 0.2283, "step": 744 }, { "epoch": 1.3471971066907775, "grad_norm": 1.3295620679855347, "learning_rate": 2.6438409515295997e-06, "loss": 0.1616, "step": 745 }, { "epoch": 1.349005424954792, "grad_norm": 1.3417298793792725, "learning_rate": 2.6306566876350072e-06, "loss": 0.1602, "step": 746 }, { "epoch": 1.3508137432188065, "grad_norm": 1.3896750211715698, "learning_rate": 2.617493634138363e-06, "loss": 0.182, "step": 747 }, { "epoch": 1.352622061482821, "grad_norm": 1.7337005138397217, "learning_rate": 2.6043519088755263e-06, "loss": 0.188, "step": 748 }, { "epoch": 1.3544303797468356, "grad_norm": 1.3530741930007935, "learning_rate": 2.5912316294914232e-06, "loss": 0.1652, "step": 749 }, { "epoch": 1.3562386980108498, "grad_norm": 1.4354356527328491, "learning_rate": 2.578132913439e-06, "loss": 0.1757, "step": 750 }, { "epoch": 1.3580470162748643, "grad_norm": 1.6724201440811157, "learning_rate": 2.5650558779781635e-06, "loss": 0.1673, "step": 751 }, { "epoch": 1.3598553345388789, "grad_norm": 1.3326820135116577, "learning_rate": 2.55200064017474e-06, "loss": 0.1483, "step": 752 }, { "epoch": 1.3616636528028934, "grad_norm": 1.5459133386611938, "learning_rate": 2.538967316899414e-06, "loss": 0.2169, "step": 753 }, { "epoch": 1.3634719710669079, "grad_norm": 1.4136031866073608, "learning_rate": 2.5259560248267022e-06, "loss": 0.1792, "step": 754 }, { "epoch": 1.3652802893309222, "grad_norm": 1.3369264602661133, "learning_rate": 2.512966880433891e-06, "loss": 0.1558, "step": 755 }, { "epoch": 1.3670886075949367, "grad_norm": 1.4669493436813354, "learning_rate": 2.5000000000000015e-06, "loss": 0.1574, "step": 756 }, { "epoch": 1.3688969258589512, "grad_norm": 1.6217176914215088, "learning_rate": 2.4870554996047454e-06, "loss": 0.216, "step": 757 }, { "epoch": 1.3707052441229657, "grad_norm": 1.3404053449630737, "learning_rate": 2.4741334951274948e-06, "loss": 0.1457, "step": 758 }, { "epoch": 1.3725135623869802, "grad_norm": 1.3390123844146729, "learning_rate": 2.461234102246231e-06, "loss": 0.1695, "step": 759 }, { "epoch": 1.3743218806509945, "grad_norm": 1.5099008083343506, "learning_rate": 2.448357436436519e-06, "loss": 0.1505, "step": 760 }, { "epoch": 1.376130198915009, "grad_norm": 1.356495976448059, "learning_rate": 2.43550361297047e-06, "loss": 0.1689, "step": 761 }, { "epoch": 1.3779385171790235, "grad_norm": 1.5271865129470825, "learning_rate": 2.4226727469157097e-06, "loss": 0.1876, "step": 762 }, { "epoch": 1.379746835443038, "grad_norm": 1.5067741870880127, "learning_rate": 2.40986495313435e-06, "loss": 0.1856, "step": 763 }, { "epoch": 1.3815551537070525, "grad_norm": 1.31850266456604, "learning_rate": 2.3970803462819586e-06, "loss": 0.134, "step": 764 }, { "epoch": 1.3833634719710668, "grad_norm": 1.7735867500305176, "learning_rate": 2.384319040806533e-06, "loss": 0.2485, "step": 765 }, { "epoch": 1.3851717902350813, "grad_norm": 1.531624674797058, "learning_rate": 2.371581150947476e-06, "loss": 0.1988, "step": 766 }, { "epoch": 1.3869801084990958, "grad_norm": 1.315036416053772, "learning_rate": 2.3588667907345787e-06, "loss": 0.1403, "step": 767 }, { "epoch": 1.3887884267631103, "grad_norm": 1.7370548248291016, "learning_rate": 2.3461760739869865e-06, "loss": 0.2479, "step": 768 }, { "epoch": 1.3905967450271248, "grad_norm": 1.576979398727417, "learning_rate": 2.3335091143121935e-06, "loss": 0.2055, "step": 769 }, { "epoch": 1.3924050632911391, "grad_norm": 1.4256597757339478, "learning_rate": 2.320866025105016e-06, "loss": 0.1679, "step": 770 }, { "epoch": 1.3942133815551538, "grad_norm": 1.4176342487335205, "learning_rate": 2.3082469195465893e-06, "loss": 0.165, "step": 771 }, { "epoch": 1.3960216998191681, "grad_norm": 1.5547435283660889, "learning_rate": 2.2956519106033366e-06, "loss": 0.1974, "step": 772 }, { "epoch": 1.3978300180831826, "grad_norm": 1.3791308403015137, "learning_rate": 2.283081111025973e-06, "loss": 0.1489, "step": 773 }, { "epoch": 1.3996383363471971, "grad_norm": 1.3772070407867432, "learning_rate": 2.2705346333484925e-06, "loss": 0.1665, "step": 774 }, { "epoch": 1.4014466546112117, "grad_norm": 1.322318196296692, "learning_rate": 2.258012589887154e-06, "loss": 0.1371, "step": 775 }, { "epoch": 1.4032549728752262, "grad_norm": 1.4020181894302368, "learning_rate": 2.245515092739488e-06, "loss": 0.1701, "step": 776 }, { "epoch": 1.4050632911392404, "grad_norm": 1.5914230346679688, "learning_rate": 2.23304225378328e-06, "loss": 0.1869, "step": 777 }, { "epoch": 1.406871609403255, "grad_norm": 1.5742111206054688, "learning_rate": 2.2205941846755787e-06, "loss": 0.2102, "step": 778 }, { "epoch": 1.4086799276672695, "grad_norm": 1.445941686630249, "learning_rate": 2.2081709968516867e-06, "loss": 0.1638, "step": 779 }, { "epoch": 1.410488245931284, "grad_norm": 1.4306185245513916, "learning_rate": 2.1957728015241793e-06, "loss": 0.147, "step": 780 }, { "epoch": 1.4122965641952985, "grad_norm": 1.585424780845642, "learning_rate": 2.1833997096818897e-06, "loss": 0.179, "step": 781 }, { "epoch": 1.4141048824593128, "grad_norm": 1.445631980895996, "learning_rate": 2.171051832088928e-06, "loss": 0.1945, "step": 782 }, { "epoch": 1.4159132007233273, "grad_norm": 1.4252804517745972, "learning_rate": 2.158729279283684e-06, "loss": 0.1686, "step": 783 }, { "epoch": 1.4177215189873418, "grad_norm": 1.3047935962677002, "learning_rate": 2.146432161577842e-06, "loss": 0.1557, "step": 784 }, { "epoch": 1.4195298372513563, "grad_norm": 1.4402592182159424, "learning_rate": 2.1341605890553895e-06, "loss": 0.1846, "step": 785 }, { "epoch": 1.4213381555153708, "grad_norm": 1.4303795099258423, "learning_rate": 2.1219146715716332e-06, "loss": 0.166, "step": 786 }, { "epoch": 1.423146473779385, "grad_norm": 1.3623348474502563, "learning_rate": 2.109694518752216e-06, "loss": 0.1406, "step": 787 }, { "epoch": 1.4249547920433996, "grad_norm": 1.4112073183059692, "learning_rate": 2.097500239992132e-06, "loss": 0.1538, "step": 788 }, { "epoch": 1.426763110307414, "grad_norm": 1.3982943296432495, "learning_rate": 2.085331944454759e-06, "loss": 0.1461, "step": 789 }, { "epoch": 1.4285714285714286, "grad_norm": 1.7053756713867188, "learning_rate": 2.0731897410708618e-06, "loss": 0.2159, "step": 790 }, { "epoch": 1.4303797468354431, "grad_norm": 1.752418041229248, "learning_rate": 2.061073738537635e-06, "loss": 0.2657, "step": 791 }, { "epoch": 1.4321880650994574, "grad_norm": 1.3400688171386719, "learning_rate": 2.0489840453177198e-06, "loss": 0.1735, "step": 792 }, { "epoch": 1.433996383363472, "grad_norm": 1.6205812692642212, "learning_rate": 2.0369207696382366e-06, "loss": 0.2268, "step": 793 }, { "epoch": 1.4358047016274864, "grad_norm": 1.382676601409912, "learning_rate": 2.0248840194898155e-06, "loss": 0.1782, "step": 794 }, { "epoch": 1.437613019891501, "grad_norm": 1.4933558702468872, "learning_rate": 2.0128739026256306e-06, "loss": 0.2093, "step": 795 }, { "epoch": 1.4394213381555154, "grad_norm": 1.6756647825241089, "learning_rate": 2.0008905265604316e-06, "loss": 0.2046, "step": 796 }, { "epoch": 1.4412296564195297, "grad_norm": 1.5282819271087646, "learning_rate": 1.9889339985695894e-06, "loss": 0.1927, "step": 797 }, { "epoch": 1.4430379746835442, "grad_norm": 1.4078805446624756, "learning_rate": 1.977004425688126e-06, "loss": 0.1852, "step": 798 }, { "epoch": 1.4448462929475587, "grad_norm": 1.441102147102356, "learning_rate": 1.9651019147097624e-06, "loss": 0.1776, "step": 799 }, { "epoch": 1.4466546112115732, "grad_norm": 1.246789813041687, "learning_rate": 1.95322657218596e-06, "loss": 0.1574, "step": 800 }, { "epoch": 1.4484629294755877, "grad_norm": 1.537737250328064, "learning_rate": 1.941378504424968e-06, "loss": 0.2084, "step": 801 }, { "epoch": 1.450271247739602, "grad_norm": 1.4707449674606323, "learning_rate": 1.929557817490874e-06, "loss": 0.1287, "step": 802 }, { "epoch": 1.4520795660036168, "grad_norm": 1.667445182800293, "learning_rate": 1.9177646172026513e-06, "loss": 0.2415, "step": 803 }, { "epoch": 1.453887884267631, "grad_norm": 1.4681103229522705, "learning_rate": 1.9059990091332082e-06, "loss": 0.2176, "step": 804 }, { "epoch": 1.4556962025316456, "grad_norm": 1.515844702720642, "learning_rate": 1.8942610986084487e-06, "loss": 0.2129, "step": 805 }, { "epoch": 1.45750452079566, "grad_norm": 1.5487630367279053, "learning_rate": 1.8825509907063328e-06, "loss": 0.2393, "step": 806 }, { "epoch": 1.4593128390596746, "grad_norm": 1.683606743812561, "learning_rate": 1.8708687902559264e-06, "loss": 0.1609, "step": 807 }, { "epoch": 1.461121157323689, "grad_norm": 1.5615615844726562, "learning_rate": 1.8592146018364682e-06, "loss": 0.191, "step": 808 }, { "epoch": 1.4629294755877034, "grad_norm": 3.3206162452697754, "learning_rate": 1.8475885297764307e-06, "loss": 0.1926, "step": 809 }, { "epoch": 1.4647377938517179, "grad_norm": 1.4970349073410034, "learning_rate": 1.8359906781525955e-06, "loss": 0.2171, "step": 810 }, { "epoch": 1.4665461121157324, "grad_norm": 1.6930969953536987, "learning_rate": 1.8244211507891064e-06, "loss": 0.1672, "step": 811 }, { "epoch": 1.4683544303797469, "grad_norm": 1.5726300477981567, "learning_rate": 1.8128800512565514e-06, "loss": 0.1906, "step": 812 }, { "epoch": 1.4701627486437614, "grad_norm": 1.4316885471343994, "learning_rate": 1.8013674828710326e-06, "loss": 0.1589, "step": 813 }, { "epoch": 1.4719710669077757, "grad_norm": 1.4346808195114136, "learning_rate": 1.7898835486932398e-06, "loss": 0.1649, "step": 814 }, { "epoch": 1.4737793851717902, "grad_norm": 1.508784294128418, "learning_rate": 1.7784283515275292e-06, "loss": 0.2037, "step": 815 }, { "epoch": 1.4755877034358047, "grad_norm": 1.4229631423950195, "learning_rate": 1.7670019939210025e-06, "loss": 0.1767, "step": 816 }, { "epoch": 1.4773960216998192, "grad_norm": 1.2219524383544922, "learning_rate": 1.7556045781625902e-06, "loss": 0.1503, "step": 817 }, { "epoch": 1.4792043399638337, "grad_norm": 1.5036314725875854, "learning_rate": 1.7442362062821323e-06, "loss": 0.1606, "step": 818 }, { "epoch": 1.481012658227848, "grad_norm": 1.5157402753829956, "learning_rate": 1.7328969800494727e-06, "loss": 0.2075, "step": 819 }, { "epoch": 1.4828209764918625, "grad_norm": 1.293325424194336, "learning_rate": 1.7215870009735386e-06, "loss": 0.1747, "step": 820 }, { "epoch": 1.484629294755877, "grad_norm": 1.3456655740737915, "learning_rate": 1.7103063703014372e-06, "loss": 0.1703, "step": 821 }, { "epoch": 1.4864376130198915, "grad_norm": 1.332581639289856, "learning_rate": 1.6990551890175488e-06, "loss": 0.1417, "step": 822 }, { "epoch": 1.488245931283906, "grad_norm": 1.267886757850647, "learning_rate": 1.6878335578426225e-06, "loss": 0.1848, "step": 823 }, { "epoch": 1.4900542495479203, "grad_norm": 1.4757543802261353, "learning_rate": 1.6766415772328732e-06, "loss": 0.1634, "step": 824 }, { "epoch": 1.4918625678119348, "grad_norm": 1.3498923778533936, "learning_rate": 1.6654793473790842e-06, "loss": 0.1697, "step": 825 }, { "epoch": 1.4936708860759493, "grad_norm": 1.3948800563812256, "learning_rate": 1.6543469682057105e-06, "loss": 0.1721, "step": 826 }, { "epoch": 1.4954792043399638, "grad_norm": 1.415420413017273, "learning_rate": 1.6432445393699803e-06, "loss": 0.1543, "step": 827 }, { "epoch": 1.4972875226039783, "grad_norm": 1.6577571630477905, "learning_rate": 1.632172160261012e-06, "loss": 0.2465, "step": 828 }, { "epoch": 1.4990958408679926, "grad_norm": 1.3747472763061523, "learning_rate": 1.621129929998912e-06, "loss": 0.1782, "step": 829 }, { "epoch": 1.5009041591320074, "grad_norm": 1.3993545770645142, "learning_rate": 1.610117947433897e-06, "loss": 0.1469, "step": 830 }, { "epoch": 1.5027124773960217, "grad_norm": 1.642367959022522, "learning_rate": 1.5991363111454023e-06, "loss": 0.2557, "step": 831 }, { "epoch": 1.5045207956600362, "grad_norm": 1.3355597257614136, "learning_rate": 1.5881851194412106e-06, "loss": 0.1548, "step": 832 }, { "epoch": 1.5063291139240507, "grad_norm": 1.5234614610671997, "learning_rate": 1.5772644703565564e-06, "loss": 0.1994, "step": 833 }, { "epoch": 1.508137432188065, "grad_norm": 1.504475474357605, "learning_rate": 1.5663744616532612e-06, "loss": 0.2028, "step": 834 }, { "epoch": 1.5099457504520797, "grad_norm": 1.3635886907577515, "learning_rate": 1.5555151908188465e-06, "loss": 0.1889, "step": 835 }, { "epoch": 1.511754068716094, "grad_norm": 1.4009240865707397, "learning_rate": 1.544686755065677e-06, "loss": 0.1539, "step": 836 }, { "epoch": 1.5135623869801085, "grad_norm": 1.4138375520706177, "learning_rate": 1.5338892513300757e-06, "loss": 0.1778, "step": 837 }, { "epoch": 1.515370705244123, "grad_norm": 1.4289062023162842, "learning_rate": 1.523122776271463e-06, "loss": 0.1509, "step": 838 }, { "epoch": 1.5171790235081373, "grad_norm": 1.6109567880630493, "learning_rate": 1.5123874262714893e-06, "loss": 0.2201, "step": 839 }, { "epoch": 1.518987341772152, "grad_norm": 1.574204683303833, "learning_rate": 1.5016832974331725e-06, "loss": 0.2282, "step": 840 }, { "epoch": 1.5207956600361663, "grad_norm": 1.427335500717163, "learning_rate": 1.4910104855800429e-06, "loss": 0.2001, "step": 841 }, { "epoch": 1.5226039783001808, "grad_norm": 1.6017565727233887, "learning_rate": 1.4803690862552755e-06, "loss": 0.213, "step": 842 }, { "epoch": 1.5244122965641953, "grad_norm": 1.4459260702133179, "learning_rate": 1.4697591947208412e-06, "loss": 0.1833, "step": 843 }, { "epoch": 1.5262206148282098, "grad_norm": 1.4301433563232422, "learning_rate": 1.459180905956653e-06, "loss": 0.1637, "step": 844 }, { "epoch": 1.5280289330922243, "grad_norm": 1.345879316329956, "learning_rate": 1.4486343146597154e-06, "loss": 0.1901, "step": 845 }, { "epoch": 1.5298372513562386, "grad_norm": 1.4471890926361084, "learning_rate": 1.438119515243277e-06, "loss": 0.1925, "step": 846 }, { "epoch": 1.5316455696202531, "grad_norm": 1.2805246114730835, "learning_rate": 1.4276366018359845e-06, "loss": 0.1494, "step": 847 }, { "epoch": 1.5334538878842676, "grad_norm": 1.271423578262329, "learning_rate": 1.4171856682810386e-06, "loss": 0.1422, "step": 848 }, { "epoch": 1.5352622061482821, "grad_norm": 1.4614052772521973, "learning_rate": 1.4067668081353625e-06, "loss": 0.195, "step": 849 }, { "epoch": 1.5370705244122966, "grad_norm": 1.3629380464553833, "learning_rate": 1.39638011466875e-06, "loss": 0.154, "step": 850 }, { "epoch": 1.538878842676311, "grad_norm": 1.4218387603759766, "learning_rate": 1.3860256808630429e-06, "loss": 0.1593, "step": 851 }, { "epoch": 1.5406871609403257, "grad_norm": 1.469496726989746, "learning_rate": 1.3757035994112915e-06, "loss": 0.1432, "step": 852 }, { "epoch": 1.54249547920434, "grad_norm": 1.614713430404663, "learning_rate": 1.3654139627169282e-06, "loss": 0.2015, "step": 853 }, { "epoch": 1.5443037974683544, "grad_norm": 1.3606630563735962, "learning_rate": 1.3551568628929434e-06, "loss": 0.1811, "step": 854 }, { "epoch": 1.546112115732369, "grad_norm": 1.4007984399795532, "learning_rate": 1.344932391761049e-06, "loss": 0.1593, "step": 855 }, { "epoch": 1.5479204339963832, "grad_norm": 1.5159410238265991, "learning_rate": 1.3347406408508695e-06, "loss": 0.2105, "step": 856 }, { "epoch": 1.549728752260398, "grad_norm": 1.4720289707183838, "learning_rate": 1.3245817013991164e-06, "loss": 0.1895, "step": 857 }, { "epoch": 1.5515370705244123, "grad_norm": 1.3945072889328003, "learning_rate": 1.3144556643487743e-06, "loss": 0.1643, "step": 858 }, { "epoch": 1.5533453887884268, "grad_norm": 1.573025107383728, "learning_rate": 1.3043626203482823e-06, "loss": 0.2169, "step": 859 }, { "epoch": 1.5551537070524413, "grad_norm": 1.4449193477630615, "learning_rate": 1.2943026597507268e-06, "loss": 0.1939, "step": 860 }, { "epoch": 1.5569620253164556, "grad_norm": 1.486480712890625, "learning_rate": 1.2842758726130283e-06, "loss": 0.1818, "step": 861 }, { "epoch": 1.5587703435804703, "grad_norm": 1.635010838508606, "learning_rate": 1.2742823486951434e-06, "loss": 0.2323, "step": 862 }, { "epoch": 1.5605786618444846, "grad_norm": 1.5351861715316772, "learning_rate": 1.2643221774592517e-06, "loss": 0.1972, "step": 863 }, { "epoch": 1.562386980108499, "grad_norm": 1.5097938776016235, "learning_rate": 1.254395448068959e-06, "loss": 0.1936, "step": 864 }, { "epoch": 1.5641952983725136, "grad_norm": 1.584326148033142, "learning_rate": 1.2445022493885017e-06, "loss": 0.2023, "step": 865 }, { "epoch": 1.5660036166365279, "grad_norm": 1.4544150829315186, "learning_rate": 1.234642669981946e-06, "loss": 0.1828, "step": 866 }, { "epoch": 1.5678119349005426, "grad_norm": 1.460277795791626, "learning_rate": 1.2248167981123992e-06, "loss": 0.1834, "step": 867 }, { "epoch": 1.5696202531645569, "grad_norm": 1.5682498216629028, "learning_rate": 1.2150247217412186e-06, "loss": 0.2042, "step": 868 }, { "epoch": 1.5714285714285714, "grad_norm": 1.3950685262680054, "learning_rate": 1.205266528527223e-06, "loss": 0.1947, "step": 869 }, { "epoch": 1.573236889692586, "grad_norm": 1.5041773319244385, "learning_rate": 1.195542305825908e-06, "loss": 0.1967, "step": 870 }, { "epoch": 1.5750452079566004, "grad_norm": 1.3620222806930542, "learning_rate": 1.1858521406886674e-06, "loss": 0.175, "step": 871 }, { "epoch": 1.576853526220615, "grad_norm": 1.398863673210144, "learning_rate": 1.1761961198620081e-06, "loss": 0.1732, "step": 872 }, { "epoch": 1.5786618444846292, "grad_norm": 1.4025603532791138, "learning_rate": 1.1665743297867781e-06, "loss": 0.1514, "step": 873 }, { "epoch": 1.5804701627486437, "grad_norm": 1.3119568824768066, "learning_rate": 1.1569868565973912e-06, "loss": 0.1501, "step": 874 }, { "epoch": 1.5822784810126582, "grad_norm": 1.411069393157959, "learning_rate": 1.1474337861210543e-06, "loss": 0.1653, "step": 875 }, { "epoch": 1.5840867992766727, "grad_norm": 1.8041685819625854, "learning_rate": 1.137915203877003e-06, "loss": 0.2351, "step": 876 }, { "epoch": 1.5858951175406872, "grad_norm": 1.5084284543991089, "learning_rate": 1.1284311950757326e-06, "loss": 0.1853, "step": 877 }, { "epoch": 1.5877034358047015, "grad_norm": 1.696347713470459, "learning_rate": 1.118981844618236e-06, "loss": 0.2093, "step": 878 }, { "epoch": 1.5895117540687163, "grad_norm": 1.3641921281814575, "learning_rate": 1.1095672370952431e-06, "loss": 0.1911, "step": 879 }, { "epoch": 1.5913200723327305, "grad_norm": 1.5706814527511597, "learning_rate": 1.1001874567864696e-06, "loss": 0.1461, "step": 880 }, { "epoch": 1.593128390596745, "grad_norm": 1.5438495874404907, "learning_rate": 1.0908425876598512e-06, "loss": 0.2105, "step": 881 }, { "epoch": 1.5949367088607596, "grad_norm": 1.3843843936920166, "learning_rate": 1.0815327133708015e-06, "loss": 0.1804, "step": 882 }, { "epoch": 1.5967450271247738, "grad_norm": 1.3429632186889648, "learning_rate": 1.0722579172614577e-06, "loss": 0.1767, "step": 883 }, { "epoch": 1.5985533453887886, "grad_norm": 1.5504016876220703, "learning_rate": 1.06301828235994e-06, "loss": 0.2058, "step": 884 }, { "epoch": 1.6003616636528029, "grad_norm": 1.3073272705078125, "learning_rate": 1.0538138913796032e-06, "loss": 0.1554, "step": 885 }, { "epoch": 1.6021699819168174, "grad_norm": 1.3386409282684326, "learning_rate": 1.044644826718295e-06, "loss": 0.1768, "step": 886 }, { "epoch": 1.6039783001808319, "grad_norm": 1.410357117652893, "learning_rate": 1.0355111704576237e-06, "loss": 0.1828, "step": 887 }, { "epoch": 1.6057866184448462, "grad_norm": 1.4223674535751343, "learning_rate": 1.0264130043622245e-06, "loss": 0.1635, "step": 888 }, { "epoch": 1.6075949367088609, "grad_norm": 1.4922338724136353, "learning_rate": 1.0173504098790188e-06, "loss": 0.2087, "step": 889 }, { "epoch": 1.6094032549728752, "grad_norm": 1.5573688745498657, "learning_rate": 1.0083234681364934e-06, "loss": 0.1907, "step": 890 }, { "epoch": 1.6112115732368897, "grad_norm": 1.4887069463729858, "learning_rate": 9.993322599439692e-07, "loss": 0.1827, "step": 891 }, { "epoch": 1.6130198915009042, "grad_norm": 1.3548970222473145, "learning_rate": 9.903768657908803e-07, "loss": 0.1454, "step": 892 }, { "epoch": 1.6148282097649185, "grad_norm": 1.465614676475525, "learning_rate": 9.814573658460564e-07, "loss": 0.1708, "step": 893 }, { "epoch": 1.6166365280289332, "grad_norm": 1.3208645582199097, "learning_rate": 9.725738399569968e-07, "loss": 0.1566, "step": 894 }, { "epoch": 1.6184448462929475, "grad_norm": 1.360666036605835, "learning_rate": 9.637263676491627e-07, "loss": 0.1772, "step": 895 }, { "epoch": 1.620253164556962, "grad_norm": 1.4041972160339355, "learning_rate": 9.549150281252633e-07, "loss": 0.1498, "step": 896 }, { "epoch": 1.6220614828209765, "grad_norm": 1.4478718042373657, "learning_rate": 9.46139900264546e-07, "loss": 0.1717, "step": 897 }, { "epoch": 1.6238698010849908, "grad_norm": 1.4047507047653198, "learning_rate": 9.374010626220908e-07, "loss": 0.177, "step": 898 }, { "epoch": 1.6256781193490055, "grad_norm": 1.3035439252853394, "learning_rate": 9.286985934281079e-07, "loss": 0.1491, "step": 899 }, { "epoch": 1.6274864376130198, "grad_norm": 1.4029420614242554, "learning_rate": 9.200325705872342e-07, "loss": 0.1796, "step": 900 }, { "epoch": 1.6292947558770343, "grad_norm": 1.3811177015304565, "learning_rate": 9.114030716778433e-07, "loss": 0.1598, "step": 901 }, { "epoch": 1.6311030741410488, "grad_norm": 1.5565098524093628, "learning_rate": 9.028101739513406e-07, "loss": 0.1774, "step": 902 }, { "epoch": 1.6329113924050633, "grad_norm": 1.3216103315353394, "learning_rate": 8.942539543314799e-07, "loss": 0.1611, "step": 903 }, { "epoch": 1.6347197106690778, "grad_norm": 1.264941692352295, "learning_rate": 8.857344894136715e-07, "loss": 0.1426, "step": 904 }, { "epoch": 1.6365280289330921, "grad_norm": 1.5673799514770508, "learning_rate": 8.772518554642973e-07, "loss": 0.2009, "step": 905 }, { "epoch": 1.6383363471971069, "grad_norm": 1.6467387676239014, "learning_rate": 8.688061284200266e-07, "loss": 0.1927, "step": 906 }, { "epoch": 1.6401446654611211, "grad_norm": 1.4807838201522827, "learning_rate": 8.603973838871388e-07, "loss": 0.1927, "step": 907 }, { "epoch": 1.6419529837251357, "grad_norm": 1.4467524290084839, "learning_rate": 8.520256971408453e-07, "loss": 0.1934, "step": 908 }, { "epoch": 1.6437613019891502, "grad_norm": 1.4074771404266357, "learning_rate": 8.436911431246136e-07, "loss": 0.1988, "step": 909 }, { "epoch": 1.6455696202531644, "grad_norm": 1.5251373052597046, "learning_rate": 8.353937964495029e-07, "loss": 0.1958, "step": 910 }, { "epoch": 1.6473779385171792, "grad_norm": 1.4521328210830688, "learning_rate": 8.271337313934869e-07, "loss": 0.158, "step": 911 }, { "epoch": 1.6491862567811935, "grad_norm": 1.4754406213760376, "learning_rate": 8.189110219007967e-07, "loss": 0.1993, "step": 912 }, { "epoch": 1.650994575045208, "grad_norm": 1.4505196809768677, "learning_rate": 8.107257415812526e-07, "loss": 0.168, "step": 913 }, { "epoch": 1.6528028933092225, "grad_norm": 1.3877017498016357, "learning_rate": 8.025779637096138e-07, "loss": 0.1539, "step": 914 }, { "epoch": 1.6546112115732368, "grad_norm": 1.783137559890747, "learning_rate": 7.944677612249113e-07, "loss": 0.2342, "step": 915 }, { "epoch": 1.6564195298372515, "grad_norm": 1.587096095085144, "learning_rate": 7.863952067298042e-07, "loss": 0.2629, "step": 916 }, { "epoch": 1.6582278481012658, "grad_norm": 1.2927180528640747, "learning_rate": 7.783603724899258e-07, "loss": 0.1496, "step": 917 }, { "epoch": 1.6600361663652803, "grad_norm": 1.3756784200668335, "learning_rate": 7.70363330433233e-07, "loss": 0.1575, "step": 918 }, { "epoch": 1.6618444846292948, "grad_norm": 1.4591854810714722, "learning_rate": 7.624041521493735e-07, "loss": 0.1647, "step": 919 }, { "epoch": 1.663652802893309, "grad_norm": 1.3824682235717773, "learning_rate": 7.544829088890326e-07, "loss": 0.1639, "step": 920 }, { "epoch": 1.6654611211573238, "grad_norm": 1.3037139177322388, "learning_rate": 7.465996715633028e-07, "loss": 0.1693, "step": 921 }, { "epoch": 1.667269439421338, "grad_norm": 1.5770865678787231, "learning_rate": 7.387545107430455e-07, "loss": 0.2302, "step": 922 }, { "epoch": 1.6690777576853526, "grad_norm": 1.5596235990524292, "learning_rate": 7.309474966582636e-07, "loss": 0.1686, "step": 923 }, { "epoch": 1.6708860759493671, "grad_norm": 1.3297088146209717, "learning_rate": 7.23178699197467e-07, "loss": 0.1696, "step": 924 }, { "epoch": 1.6726943942133814, "grad_norm": 1.5276892185211182, "learning_rate": 7.154481879070502e-07, "loss": 0.2435, "step": 925 }, { "epoch": 1.6745027124773961, "grad_norm": 1.5488836765289307, "learning_rate": 7.077560319906696e-07, "loss": 0.1872, "step": 926 }, { "epoch": 1.6763110307414104, "grad_norm": 1.6117419004440308, "learning_rate": 7.001023003086243e-07, "loss": 0.1831, "step": 927 }, { "epoch": 1.678119349005425, "grad_norm": 1.5337069034576416, "learning_rate": 6.924870613772388e-07, "loss": 0.1888, "step": 928 }, { "epoch": 1.6799276672694394, "grad_norm": 1.2280519008636475, "learning_rate": 6.849103833682491e-07, "loss": 0.1399, "step": 929 }, { "epoch": 1.681735985533454, "grad_norm": 1.4914060831069946, "learning_rate": 6.773723341081945e-07, "loss": 0.1909, "step": 930 }, { "epoch": 1.6835443037974684, "grad_norm": 1.356615662574768, "learning_rate": 6.698729810778065e-07, "loss": 0.1839, "step": 931 }, { "epoch": 1.6853526220614827, "grad_norm": 1.279007077217102, "learning_rate": 6.624123914114122e-07, "loss": 0.1404, "step": 932 }, { "epoch": 1.6871609403254972, "grad_norm": 1.234628438949585, "learning_rate": 6.549906318963245e-07, "loss": 0.1394, "step": 933 }, { "epoch": 1.6889692585895117, "grad_norm": 1.5829991102218628, "learning_rate": 6.476077689722487e-07, "loss": 0.1889, "step": 934 }, { "epoch": 1.6907775768535263, "grad_norm": 1.292048692703247, "learning_rate": 6.402638687306872e-07, "loss": 0.1429, "step": 935 }, { "epoch": 1.6925858951175408, "grad_norm": 1.3141627311706543, "learning_rate": 6.329589969143518e-07, "loss": 0.1724, "step": 936 }, { "epoch": 1.694394213381555, "grad_norm": 1.4548964500427246, "learning_rate": 6.256932189165644e-07, "loss": 0.1491, "step": 937 }, { "epoch": 1.6962025316455698, "grad_norm": 1.4217482805252075, "learning_rate": 6.184665997806832e-07, "loss": 0.1566, "step": 938 }, { "epoch": 1.698010849909584, "grad_norm": 1.4867550134658813, "learning_rate": 6.112792041995125e-07, "loss": 0.1769, "step": 939 }, { "epoch": 1.6998191681735986, "grad_norm": 1.4310846328735352, "learning_rate": 6.041310965147318e-07, "loss": 0.1558, "step": 940 }, { "epoch": 1.701627486437613, "grad_norm": 1.6445306539535522, "learning_rate": 5.9702234071631e-07, "loss": 0.2454, "step": 941 }, { "epoch": 1.7034358047016274, "grad_norm": 1.3807169198989868, "learning_rate": 5.899530004419396e-07, "loss": 0.1664, "step": 942 }, { "epoch": 1.705244122965642, "grad_norm": 1.3569984436035156, "learning_rate": 5.829231389764628e-07, "loss": 0.1446, "step": 943 }, { "epoch": 1.7070524412296564, "grad_norm": 1.5462021827697754, "learning_rate": 5.759328192513075e-07, "loss": 0.1853, "step": 944 }, { "epoch": 1.7088607594936709, "grad_norm": 1.387600302696228, "learning_rate": 5.689821038439264e-07, "loss": 0.1944, "step": 945 }, { "epoch": 1.7106690777576854, "grad_norm": 1.4269497394561768, "learning_rate": 5.620710549772295e-07, "loss": 0.1543, "step": 946 }, { "epoch": 1.7124773960216997, "grad_norm": 1.4337564706802368, "learning_rate": 5.55199734519034e-07, "loss": 0.1778, "step": 947 }, { "epoch": 1.7142857142857144, "grad_norm": 1.5276905298233032, "learning_rate": 5.483682039815059e-07, "loss": 0.1845, "step": 948 }, { "epoch": 1.7160940325497287, "grad_norm": 1.6974987983703613, "learning_rate": 5.415765245206128e-07, "loss": 0.2359, "step": 949 }, { "epoch": 1.7179023508137432, "grad_norm": 1.4583032131195068, "learning_rate": 5.348247569355736e-07, "loss": 0.1879, "step": 950 }, { "epoch": 1.7197106690777577, "grad_norm": 1.2315136194229126, "learning_rate": 5.281129616683167e-07, "loss": 0.131, "step": 951 }, { "epoch": 1.721518987341772, "grad_norm": 1.4944851398468018, "learning_rate": 5.214411988029355e-07, "loss": 0.1806, "step": 952 }, { "epoch": 1.7233273056057867, "grad_norm": 1.56333327293396, "learning_rate": 5.148095280651566e-07, "loss": 0.1883, "step": 953 }, { "epoch": 1.725135623869801, "grad_norm": 1.4044638872146606, "learning_rate": 5.082180088217981e-07, "loss": 0.1771, "step": 954 }, { "epoch": 1.7269439421338155, "grad_norm": 1.4745898246765137, "learning_rate": 5.016667000802417e-07, "loss": 0.1609, "step": 955 }, { "epoch": 1.72875226039783, "grad_norm": 1.469342827796936, "learning_rate": 4.951556604879049e-07, "loss": 0.1877, "step": 956 }, { "epoch": 1.7305605786618445, "grad_norm": 1.534229040145874, "learning_rate": 4.886849483317141e-07, "loss": 0.1958, "step": 957 }, { "epoch": 1.732368896925859, "grad_norm": 1.5850822925567627, "learning_rate": 4.822546215375851e-07, "loss": 0.2493, "step": 958 }, { "epoch": 1.7341772151898733, "grad_norm": 1.4331377744674683, "learning_rate": 4.758647376699033e-07, "loss": 0.1423, "step": 959 }, { "epoch": 1.7359855334538878, "grad_norm": 1.3268859386444092, "learning_rate": 4.6951535393100654e-07, "loss": 0.1734, "step": 960 }, { "epoch": 1.7377938517179023, "grad_norm": 1.552573800086975, "learning_rate": 4.632065271606756e-07, "loss": 0.2068, "step": 961 }, { "epoch": 1.7396021699819169, "grad_norm": 1.247005820274353, "learning_rate": 4.569383138356276e-07, "loss": 0.1224, "step": 962 }, { "epoch": 1.7414104882459314, "grad_norm": 1.4744571447372437, "learning_rate": 4.507107700690044e-07, "loss": 0.1702, "step": 963 }, { "epoch": 1.7432188065099457, "grad_norm": 1.324377179145813, "learning_rate": 4.4452395160987314e-07, "loss": 0.1366, "step": 964 }, { "epoch": 1.7450271247739604, "grad_norm": 1.4414422512054443, "learning_rate": 4.383779138427274e-07, "loss": 0.1604, "step": 965 }, { "epoch": 1.7468354430379747, "grad_norm": 1.311666488647461, "learning_rate": 4.322727117869951e-07, "loss": 0.1538, "step": 966 }, { "epoch": 1.7486437613019892, "grad_norm": 1.3424110412597656, "learning_rate": 4.2620840009653827e-07, "loss": 0.1454, "step": 967 }, { "epoch": 1.7504520795660037, "grad_norm": 1.605882167816162, "learning_rate": 4.201850330591678e-07, "loss": 0.1994, "step": 968 }, { "epoch": 1.752260397830018, "grad_norm": 1.7594163417816162, "learning_rate": 4.1420266459615944e-07, "loss": 0.2694, "step": 969 }, { "epoch": 1.7540687160940327, "grad_norm": 1.5380682945251465, "learning_rate": 4.082613482617664e-07, "loss": 0.1976, "step": 970 }, { "epoch": 1.755877034358047, "grad_norm": 1.353868007659912, "learning_rate": 4.0236113724274716e-07, "loss": 0.1774, "step": 971 }, { "epoch": 1.7576853526220615, "grad_norm": 1.4633132219314575, "learning_rate": 3.965020843578804e-07, "loss": 0.1771, "step": 972 }, { "epoch": 1.759493670886076, "grad_norm": 1.588869333267212, "learning_rate": 3.90684242057498e-07, "loss": 0.2269, "step": 973 }, { "epoch": 1.7613019891500903, "grad_norm": 1.4125856161117554, "learning_rate": 3.8490766242301356e-07, "loss": 0.1671, "step": 974 }, { "epoch": 1.763110307414105, "grad_norm": 1.401391863822937, "learning_rate": 3.7917239716645906e-07, "loss": 0.1646, "step": 975 }, { "epoch": 1.7649186256781193, "grad_norm": 1.3753687143325806, "learning_rate": 3.734784976300165e-07, "loss": 0.1448, "step": 976 }, { "epoch": 1.7667269439421338, "grad_norm": 1.3209081888198853, "learning_rate": 3.678260147855628e-07, "loss": 0.1573, "step": 977 }, { "epoch": 1.7685352622061483, "grad_norm": 1.7541275024414062, "learning_rate": 3.6221499923421164e-07, "loss": 0.2607, "step": 978 }, { "epoch": 1.7703435804701626, "grad_norm": 1.29871666431427, "learning_rate": 3.566455012058612e-07, "loss": 0.1573, "step": 979 }, { "epoch": 1.7721518987341773, "grad_norm": 1.418175458908081, "learning_rate": 3.511175705587433e-07, "loss": 0.1718, "step": 980 }, { "epoch": 1.7739602169981916, "grad_norm": 1.4867905378341675, "learning_rate": 3.4563125677897936e-07, "loss": 0.1875, "step": 981 }, { "epoch": 1.7757685352622061, "grad_norm": 1.5604780912399292, "learning_rate": 3.4018660898013423e-07, "loss": 0.2334, "step": 982 }, { "epoch": 1.7775768535262206, "grad_norm": 1.4401788711547852, "learning_rate": 3.347836759027789e-07, "loss": 0.1841, "step": 983 }, { "epoch": 1.779385171790235, "grad_norm": 1.474273920059204, "learning_rate": 3.2942250591405546e-07, "loss": 0.1896, "step": 984 }, { "epoch": 1.7811934900542497, "grad_norm": 1.3961596488952637, "learning_rate": 3.241031470072398e-07, "loss": 0.1883, "step": 985 }, { "epoch": 1.783001808318264, "grad_norm": 1.2985126972198486, "learning_rate": 3.18825646801314e-07, "loss": 0.1453, "step": 986 }, { "epoch": 1.7848101265822784, "grad_norm": 1.3792794942855835, "learning_rate": 3.135900525405428e-07, "loss": 0.1485, "step": 987 }, { "epoch": 1.786618444846293, "grad_norm": 1.2826642990112305, "learning_rate": 3.0839641109404627e-07, "loss": 0.1234, "step": 988 }, { "epoch": 1.7884267631103075, "grad_norm": 1.5358680486679077, "learning_rate": 3.03244768955383e-07, "loss": 0.1581, "step": 989 }, { "epoch": 1.790235081374322, "grad_norm": 1.507939338684082, "learning_rate": 2.9813517224213274e-07, "loss": 0.1806, "step": 990 }, { "epoch": 1.7920433996383363, "grad_norm": 1.5270705223083496, "learning_rate": 2.930676666954846e-07, "loss": 0.1901, "step": 991 }, { "epoch": 1.7938517179023508, "grad_norm": 1.3921293020248413, "learning_rate": 2.8804229767982637e-07, "loss": 0.1822, "step": 992 }, { "epoch": 1.7956600361663653, "grad_norm": 1.7586761713027954, "learning_rate": 2.8305911018233935e-07, "loss": 0.2805, "step": 993 }, { "epoch": 1.7974683544303798, "grad_norm": 1.3629529476165771, "learning_rate": 2.7811814881259503e-07, "loss": 0.177, "step": 994 }, { "epoch": 1.7992766726943943, "grad_norm": 1.4581550359725952, "learning_rate": 2.7321945780215576e-07, "loss": 0.1863, "step": 995 }, { "epoch": 1.8010849909584086, "grad_norm": 1.3623037338256836, "learning_rate": 2.6836308100417874e-07, "loss": 0.1825, "step": 996 }, { "epoch": 1.8028933092224233, "grad_norm": 1.3838571310043335, "learning_rate": 2.6354906189302534e-07, "loss": 0.1754, "step": 997 }, { "epoch": 1.8047016274864376, "grad_norm": 1.593772053718567, "learning_rate": 2.587774435638679e-07, "loss": 0.1985, "step": 998 }, { "epoch": 1.806509945750452, "grad_norm": 1.416452169418335, "learning_rate": 2.5404826873230926e-07, "loss": 0.1624, "step": 999 }, { "epoch": 1.8083182640144666, "grad_norm": 1.4714127779006958, "learning_rate": 2.4936157973399266e-07, "loss": 0.1602, "step": 1000 }, { "epoch": 1.810126582278481, "grad_norm": 1.572771668434143, "learning_rate": 2.447174185242324e-07, "loss": 0.1953, "step": 1001 }, { "epoch": 1.8119349005424956, "grad_norm": 1.6987907886505127, "learning_rate": 2.40115826677631e-07, "loss": 0.2066, "step": 1002 }, { "epoch": 1.81374321880651, "grad_norm": 1.5862913131713867, "learning_rate": 2.3555684538770995e-07, "loss": 0.2132, "step": 1003 }, { "epoch": 1.8155515370705244, "grad_norm": 1.3430746793746948, "learning_rate": 2.3104051546654016e-07, "loss": 0.1714, "step": 1004 }, { "epoch": 1.817359855334539, "grad_norm": 1.5095547437667847, "learning_rate": 2.2656687734437577e-07, "loss": 0.1894, "step": 1005 }, { "epoch": 1.8191681735985532, "grad_norm": 1.4941962957382202, "learning_rate": 2.2213597106929608e-07, "loss": 0.1987, "step": 1006 }, { "epoch": 1.820976491862568, "grad_norm": 1.2490885257720947, "learning_rate": 2.177478363068425e-07, "loss": 0.1584, "step": 1007 }, { "epoch": 1.8227848101265822, "grad_norm": 1.520779013633728, "learning_rate": 2.134025123396638e-07, "loss": 0.2157, "step": 1008 }, { "epoch": 1.8245931283905967, "grad_norm": 1.5588268041610718, "learning_rate": 2.0910003806716817e-07, "loss": 0.2177, "step": 1009 }, { "epoch": 1.8264014466546112, "grad_norm": 1.3247624635696411, "learning_rate": 2.0484045200517222e-07, "loss": 0.1582, "step": 1010 }, { "epoch": 1.8282097649186255, "grad_norm": 1.4235435724258423, "learning_rate": 2.006237922855553e-07, "loss": 0.1918, "step": 1011 }, { "epoch": 1.8300180831826403, "grad_norm": 1.3423272371292114, "learning_rate": 1.9645009665592073e-07, "loss": 0.1516, "step": 1012 }, { "epoch": 1.8318264014466545, "grad_norm": 1.319929599761963, "learning_rate": 1.9231940247925573e-07, "loss": 0.1488, "step": 1013 }, { "epoch": 1.833634719710669, "grad_norm": 1.4853554964065552, "learning_rate": 1.882317467335998e-07, "loss": 0.1685, "step": 1014 }, { "epoch": 1.8354430379746836, "grad_norm": 1.673097848892212, "learning_rate": 1.841871660117095e-07, "loss": 0.224, "step": 1015 }, { "epoch": 1.837251356238698, "grad_norm": 1.5810422897338867, "learning_rate": 1.801856965207338e-07, "loss": 0.2309, "step": 1016 }, { "epoch": 1.8390596745027126, "grad_norm": 1.4019553661346436, "learning_rate": 1.7622737408188984e-07, "loss": 0.1796, "step": 1017 }, { "epoch": 1.8408679927667269, "grad_norm": 1.6758962869644165, "learning_rate": 1.7231223413014086e-07, "loss": 0.2212, "step": 1018 }, { "epoch": 1.8426763110307414, "grad_norm": 1.5785558223724365, "learning_rate": 1.6844031171388054e-07, "loss": 0.2135, "step": 1019 }, { "epoch": 1.8444846292947559, "grad_norm": 1.6636614799499512, "learning_rate": 1.6461164149461805e-07, "loss": 0.2525, "step": 1020 }, { "epoch": 1.8462929475587704, "grad_norm": 1.6070526838302612, "learning_rate": 1.6082625774666793e-07, "loss": 0.2128, "step": 1021 }, { "epoch": 1.8481012658227849, "grad_norm": 1.4531391859054565, "learning_rate": 1.5708419435684463e-07, "loss": 0.1908, "step": 1022 }, { "epoch": 1.8499095840867992, "grad_norm": 1.4320067167282104, "learning_rate": 1.5338548482415726e-07, "loss": 0.1932, "step": 1023 }, { "epoch": 1.851717902350814, "grad_norm": 1.4349814653396606, "learning_rate": 1.4973016225951097e-07, "loss": 0.1858, "step": 1024 }, { "epoch": 1.8535262206148282, "grad_norm": 1.355491280555725, "learning_rate": 1.4611825938540936e-07, "loss": 0.1593, "step": 1025 }, { "epoch": 1.8553345388788427, "grad_norm": 1.3993618488311768, "learning_rate": 1.4254980853566248e-07, "loss": 0.1558, "step": 1026 }, { "epoch": 1.8571428571428572, "grad_norm": 1.3245823383331299, "learning_rate": 1.3902484165509877e-07, "loss": 0.1403, "step": 1027 }, { "epoch": 1.8589511754068715, "grad_norm": 1.6627517938613892, "learning_rate": 1.3554339029927532e-07, "loss": 0.249, "step": 1028 }, { "epoch": 1.8607594936708862, "grad_norm": 1.3459573984146118, "learning_rate": 1.3210548563419857e-07, "loss": 0.1503, "step": 1029 }, { "epoch": 1.8625678119349005, "grad_norm": 1.3954676389694214, "learning_rate": 1.2871115843604508e-07, "loss": 0.1466, "step": 1030 }, { "epoch": 1.864376130198915, "grad_norm": 1.487899899482727, "learning_rate": 1.253604390908819e-07, "loss": 0.1821, "step": 1031 }, { "epoch": 1.8661844484629295, "grad_norm": 1.3367693424224854, "learning_rate": 1.220533575944033e-07, "loss": 0.1379, "step": 1032 }, { "epoch": 1.8679927667269438, "grad_norm": 1.4436026811599731, "learning_rate": 1.1878994355165207e-07, "loss": 0.189, "step": 1033 }, { "epoch": 1.8698010849909585, "grad_norm": 1.4232622385025024, "learning_rate": 1.1557022617676217e-07, "loss": 0.1775, "step": 1034 }, { "epoch": 1.8716094032549728, "grad_norm": 1.465479850769043, "learning_rate": 1.1239423429269203e-07, "loss": 0.2127, "step": 1035 }, { "epoch": 1.8734177215189873, "grad_norm": 1.4854105710983276, "learning_rate": 1.0926199633097156e-07, "loss": 0.1947, "step": 1036 }, { "epoch": 1.8752260397830018, "grad_norm": 1.382188081741333, "learning_rate": 1.0617354033144289e-07, "loss": 0.1678, "step": 1037 }, { "epoch": 1.8770343580470161, "grad_norm": 1.4120211601257324, "learning_rate": 1.031288939420122e-07, "loss": 0.1446, "step": 1038 }, { "epoch": 1.8788426763110309, "grad_norm": 1.4153492450714111, "learning_rate": 1.0012808441839994e-07, "loss": 0.1529, "step": 1039 }, { "epoch": 1.8806509945750451, "grad_norm": 1.6111195087432861, "learning_rate": 9.717113862389993e-08, "loss": 0.1994, "step": 1040 }, { "epoch": 1.8824593128390597, "grad_norm": 1.3485233783721924, "learning_rate": 9.42580830291373e-08, "loss": 0.1672, "step": 1041 }, { "epoch": 1.8842676311030742, "grad_norm": 1.3682034015655518, "learning_rate": 9.138894371182983e-08, "loss": 0.1272, "step": 1042 }, { "epoch": 1.8860759493670884, "grad_norm": 1.4585204124450684, "learning_rate": 8.856374635655696e-08, "loss": 0.1904, "step": 1043 }, { "epoch": 1.8878842676311032, "grad_norm": 1.6006243228912354, "learning_rate": 8.57825162545295e-08, "loss": 0.2224, "step": 1044 }, { "epoch": 1.8896925858951175, "grad_norm": 1.550670862197876, "learning_rate": 8.304527830336251e-08, "loss": 0.213, "step": 1045 }, { "epoch": 1.891500904159132, "grad_norm": 1.268154501914978, "learning_rate": 8.035205700685167e-08, "loss": 0.148, "step": 1046 }, { "epoch": 1.8933092224231465, "grad_norm": 1.4060418605804443, "learning_rate": 7.770287647475672e-08, "loss": 0.1949, "step": 1047 }, { "epoch": 1.895117540687161, "grad_norm": 1.3881064653396606, "learning_rate": 7.509776042258166e-08, "loss": 0.181, "step": 1048 }, { "epoch": 1.8969258589511755, "grad_norm": 1.4185147285461426, "learning_rate": 7.253673217136659e-08, "loss": 0.1799, "step": 1049 }, { "epoch": 1.8987341772151898, "grad_norm": 1.3678489923477173, "learning_rate": 7.001981464747565e-08, "loss": 0.1587, "step": 1050 }, { "epoch": 1.9005424954792043, "grad_norm": 1.4927364587783813, "learning_rate": 6.75470303823933e-08, "loss": 0.1773, "step": 1051 }, { "epoch": 1.9023508137432188, "grad_norm": 1.5047712326049805, "learning_rate": 6.511840151252169e-08, "loss": 0.1723, "step": 1052 }, { "epoch": 1.9041591320072333, "grad_norm": 1.801727294921875, "learning_rate": 6.273394977898528e-08, "loss": 0.2423, "step": 1053 }, { "epoch": 1.9059674502712478, "grad_norm": 1.3307334184646606, "learning_rate": 6.039369652743266e-08, "loss": 0.1741, "step": 1054 }, { "epoch": 1.907775768535262, "grad_norm": 1.405661940574646, "learning_rate": 5.809766270784667e-08, "loss": 0.1786, "step": 1055 }, { "epoch": 1.9095840867992768, "grad_norm": 1.3668214082717896, "learning_rate": 5.584586887435739e-08, "loss": 0.1598, "step": 1056 }, { "epoch": 1.9113924050632911, "grad_norm": 1.452925682067871, "learning_rate": 5.363833518505834e-08, "loss": 0.2291, "step": 1057 }, { "epoch": 1.9132007233273056, "grad_norm": 1.3178629875183105, "learning_rate": 5.1475081401825553e-08, "loss": 0.1551, "step": 1058 }, { "epoch": 1.9150090415913201, "grad_norm": 1.6016581058502197, "learning_rate": 4.9356126890139356e-08, "loss": 0.207, "step": 1059 }, { "epoch": 1.9168173598553344, "grad_norm": 1.428049921989441, "learning_rate": 4.7281490618914516e-08, "loss": 0.1826, "step": 1060 }, { "epoch": 1.9186256781193491, "grad_norm": 1.462370753288269, "learning_rate": 4.52511911603265e-08, "loss": 0.1823, "step": 1061 }, { "epoch": 1.9204339963833634, "grad_norm": 1.329318642616272, "learning_rate": 4.32652466896466e-08, "loss": 0.1445, "step": 1062 }, { "epoch": 1.922242314647378, "grad_norm": 1.368668556213379, "learning_rate": 4.13236749850815e-08, "loss": 0.1303, "step": 1063 }, { "epoch": 1.9240506329113924, "grad_norm": 1.4341305494308472, "learning_rate": 3.9426493427611177e-08, "loss": 0.1688, "step": 1064 }, { "epoch": 1.9258589511754067, "grad_norm": 1.5449689626693726, "learning_rate": 3.7573719000832954e-08, "loss": 0.172, "step": 1065 }, { "epoch": 1.9276672694394215, "grad_norm": 1.3612035512924194, "learning_rate": 3.576536829081323e-08, "loss": 0.1767, "step": 1066 }, { "epoch": 1.9294755877034357, "grad_norm": 1.4490336179733276, "learning_rate": 3.400145748593542e-08, "loss": 0.1834, "step": 1067 }, { "epoch": 1.9312839059674503, "grad_norm": 1.6164692640304565, "learning_rate": 3.2282002376756163e-08, "loss": 0.2068, "step": 1068 }, { "epoch": 1.9330922242314648, "grad_norm": 1.4480701684951782, "learning_rate": 3.0607018355864326e-08, "loss": 0.2062, "step": 1069 }, { "epoch": 1.934900542495479, "grad_norm": 1.337966799736023, "learning_rate": 2.8976520417742794e-08, "loss": 0.1475, "step": 1070 }, { "epoch": 1.9367088607594938, "grad_norm": 1.525605320930481, "learning_rate": 2.7390523158633552e-08, "loss": 0.2038, "step": 1071 }, { "epoch": 1.938517179023508, "grad_norm": 1.418442726135254, "learning_rate": 2.584904077640893e-08, "loss": 0.1643, "step": 1072 }, { "epoch": 1.9403254972875226, "grad_norm": 1.4032057523727417, "learning_rate": 2.43520870704439e-08, "loss": 0.1692, "step": 1073 }, { "epoch": 1.942133815551537, "grad_norm": 1.4892172813415527, "learning_rate": 2.2899675441490078e-08, "loss": 0.1626, "step": 1074 }, { "epoch": 1.9439421338155516, "grad_norm": 1.5173064470291138, "learning_rate": 2.1491818891559156e-08, "loss": 0.1748, "step": 1075 }, { "epoch": 1.945750452079566, "grad_norm": 1.5170865058898926, "learning_rate": 2.012853002380466e-08, "loss": 0.212, "step": 1076 }, { "epoch": 1.9475587703435804, "grad_norm": 1.4932132959365845, "learning_rate": 1.8809821042410358e-08, "loss": 0.1774, "step": 1077 }, { "epoch": 1.9493670886075949, "grad_norm": 1.6137913465499878, "learning_rate": 1.753570375247815e-08, "loss": 0.2019, "step": 1078 }, { "epoch": 1.9511754068716094, "grad_norm": 1.3536970615386963, "learning_rate": 1.630618955992702e-08, "loss": 0.1611, "step": 1079 }, { "epoch": 1.952983725135624, "grad_norm": 1.5503106117248535, "learning_rate": 1.5121289471385915e-08, "loss": 0.2254, "step": 1080 }, { "epoch": 1.9547920433996384, "grad_norm": 1.4560229778289795, "learning_rate": 1.3981014094099354e-08, "loss": 0.1706, "step": 1081 }, { "epoch": 1.9566003616636527, "grad_norm": 1.6546319723129272, "learning_rate": 1.2885373635829756e-08, "loss": 0.2459, "step": 1082 }, { "epoch": 1.9584086799276674, "grad_norm": 1.4596152305603027, "learning_rate": 1.1834377904768046e-08, "loss": 0.1917, "step": 1083 }, { "epoch": 1.9602169981916817, "grad_norm": 1.4562087059020996, "learning_rate": 1.0828036309443735e-08, "loss": 0.1973, "step": 1084 }, { "epoch": 1.9620253164556962, "grad_norm": 1.6077297925949097, "learning_rate": 9.866357858642206e-09, "loss": 0.2338, "step": 1085 }, { "epoch": 1.9638336347197107, "grad_norm": 1.5160093307495117, "learning_rate": 8.949351161324227e-09, "loss": 0.1648, "step": 1086 }, { "epoch": 1.965641952983725, "grad_norm": 1.5699567794799805, "learning_rate": 8.077024426547675e-09, "loss": 0.2017, "step": 1087 }, { "epoch": 1.9674502712477397, "grad_norm": 1.7581249475479126, "learning_rate": 7.249385463395375e-09, "loss": 0.144, "step": 1088 }, { "epoch": 1.969258589511754, "grad_norm": 1.5871422290802002, "learning_rate": 6.46644168090349e-09, "loss": 0.2035, "step": 1089 }, { "epoch": 1.9710669077757685, "grad_norm": 1.484626293182373, "learning_rate": 5.728200087997126e-09, "loss": 0.1929, "step": 1090 }, { "epoch": 1.972875226039783, "grad_norm": 1.5120055675506592, "learning_rate": 5.034667293427053e-09, "loss": 0.2145, "step": 1091 }, { "epoch": 1.9746835443037973, "grad_norm": 1.4649606943130493, "learning_rate": 4.385849505708084e-09, "loss": 0.1756, "step": 1092 }, { "epoch": 1.976491862567812, "grad_norm": 1.8743977546691895, "learning_rate": 3.781752533068561e-09, "loss": 0.2438, "step": 1093 }, { "epoch": 1.9783001808318263, "grad_norm": 1.474522352218628, "learning_rate": 3.2223817833931803e-09, "loss": 0.2034, "step": 1094 }, { "epoch": 1.9801084990958409, "grad_norm": 1.6017460823059082, "learning_rate": 2.707742264178026e-09, "loss": 0.2172, "step": 1095 }, { "epoch": 1.9819168173598554, "grad_norm": 1.3220065832138062, "learning_rate": 2.237838582483387e-09, "loss": 0.1572, "step": 1096 }, { "epoch": 1.9837251356238697, "grad_norm": 1.4205492734909058, "learning_rate": 1.8126749448943437e-09, "loss": 0.1725, "step": 1097 }, { "epoch": 1.9855334538878844, "grad_norm": 1.4909166097640991, "learning_rate": 1.4322551574830202e-09, "loss": 0.2007, "step": 1098 }, { "epoch": 1.9873417721518987, "grad_norm": 1.4982306957244873, "learning_rate": 1.096582625772502e-09, "loss": 0.1965, "step": 1099 }, { "epoch": 1.9891500904159132, "grad_norm": 1.5286743640899658, "learning_rate": 8.056603547090813e-10, "loss": 0.1972, "step": 1100 }, { "epoch": 1.9909584086799277, "grad_norm": 1.5510579347610474, "learning_rate": 5.594909486328348e-10, "loss": 0.1793, "step": 1101 }, { "epoch": 1.992766726943942, "grad_norm": 1.2177929878234863, "learning_rate": 3.580766112565304e-10, "loss": 0.1099, "step": 1102 }, { "epoch": 1.9945750452079567, "grad_norm": 1.3810474872589111, "learning_rate": 2.0141914564453247e-10, "loss": 0.1598, "step": 1103 }, { "epoch": 1.996383363471971, "grad_norm": 1.2665152549743652, "learning_rate": 8.951995419614889e-11, "loss": 0.1546, "step": 1104 }, { "epoch": 1.9981916817359855, "grad_norm": 1.5448002815246582, "learning_rate": 2.2380038635638758e-11, "loss": 0.1903, "step": 1105 }, { "epoch": 2.0, "grad_norm": 1.2623151540756226, "learning_rate": 0.0, "loss": 0.1488, "step": 1106 }, { "epoch": 2.0, "step": 1106, "total_flos": 328114776080384.0, "train_loss": 0.340545193654288, "train_runtime": 5685.0486, "train_samples_per_second": 3.11, "train_steps_per_second": 0.195 } ], "logging_steps": 1.0, "max_steps": 1106, "num_input_tokens_seen": 0, "num_train_epochs": 2, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": false, "should_training_stop": false }, "attributes": {} } }, "total_flos": 328114776080384.0, "train_batch_size": 4, "trial_name": null, "trial_params": null }