{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.04712334643166272, "eval_steps": 500, "global_step": 1538, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 3.0639366990677975e-05, "grad_norm": 0.24610228836536407, "learning_rate": 2e-05, "loss": 10.4009, "step": 1 }, { "epoch": 6.127873398135595e-05, "grad_norm": 0.2093752771615982, "learning_rate": 4e-05, "loss": 10.3915, "step": 2 }, { "epoch": 9.191810097203391e-05, "grad_norm": 0.2284351885318756, "learning_rate": 6e-05, "loss": 10.3906, "step": 3 }, { "epoch": 0.0001225574679627119, "grad_norm": 0.2171163409948349, "learning_rate": 8e-05, "loss": 10.3869, "step": 4 }, { "epoch": 0.00015319683495338985, "grad_norm": 0.2038799673318863, "learning_rate": 0.0001, "loss": 10.3949, "step": 5 }, { "epoch": 0.00018383620194406782, "grad_norm": 0.2396441251039505, "learning_rate": 9.999989500822154e-05, "loss": 10.4008, "step": 6 }, { "epoch": 0.0002144755689347458, "grad_norm": 0.26151952147483826, "learning_rate": 9.999958003332706e-05, "loss": 10.4042, "step": 7 }, { "epoch": 0.0002451149359254238, "grad_norm": 0.24929848313331604, "learning_rate": 9.999905507663936e-05, "loss": 10.4017, "step": 8 }, { "epoch": 0.0002757543029161018, "grad_norm": 0.24374260008335114, "learning_rate": 9.999832014036307e-05, "loss": 10.4036, "step": 9 }, { "epoch": 0.0003063936699067797, "grad_norm": 0.24356040358543396, "learning_rate": 9.999737522758472e-05, "loss": 10.4014, "step": 10 }, { "epoch": 0.0003370330368974577, "grad_norm": 0.22188138961791992, "learning_rate": 9.99962203422726e-05, "loss": 10.3966, "step": 11 }, { "epoch": 0.00036767240388813565, "grad_norm": 0.23609934747219086, "learning_rate": 9.999485548927685e-05, "loss": 10.3977, "step": 12 }, { "epoch": 0.0003983117708788136, "grad_norm": 0.24605651199817657, "learning_rate": 9.999328067432943e-05, "loss": 10.3925, "step": 13 }, { "epoch": 0.0004289511378694916, "grad_norm": 0.2491612583398819, "learning_rate": 9.9991495904044e-05, "loss": 10.3905, "step": 14 }, { "epoch": 0.0004595905048601696, "grad_norm": 0.2473774403333664, "learning_rate": 9.998950118591606e-05, "loss": 10.3967, "step": 15 }, { "epoch": 0.0004902298718508476, "grad_norm": 0.24023188650608063, "learning_rate": 9.998729652832273e-05, "loss": 10.3919, "step": 16 }, { "epoch": 0.0005208692388415255, "grad_norm": 0.249563068151474, "learning_rate": 9.998488194052287e-05, "loss": 10.3966, "step": 17 }, { "epoch": 0.0005515086058322036, "grad_norm": 0.2716507911682129, "learning_rate": 9.998225743265693e-05, "loss": 10.3958, "step": 18 }, { "epoch": 0.0005821479728228815, "grad_norm": 0.251860648393631, "learning_rate": 9.997942301574701e-05, "loss": 10.3934, "step": 19 }, { "epoch": 0.0006127873398135594, "grad_norm": 0.2491675615310669, "learning_rate": 9.997637870169672e-05, "loss": 10.3971, "step": 20 }, { "epoch": 0.0006434267068042374, "grad_norm": 0.2549178898334503, "learning_rate": 9.997312450329115e-05, "loss": 10.3912, "step": 21 }, { "epoch": 0.0006740660737949153, "grad_norm": 0.24476251006126404, "learning_rate": 9.99696604341969e-05, "loss": 10.3781, "step": 22 }, { "epoch": 0.0007047054407855934, "grad_norm": 0.24391278624534607, "learning_rate": 9.996598650896192e-05, "loss": 10.3703, "step": 23 }, { "epoch": 0.0007353448077762713, "grad_norm": 0.2502497434616089, "learning_rate": 9.996210274301546e-05, "loss": 10.3699, "step": 24 }, { "epoch": 0.0007659841747669493, "grad_norm": 0.24495452642440796, "learning_rate": 9.995800915266809e-05, "loss": 10.3641, "step": 25 }, { "epoch": 0.0007966235417576273, "grad_norm": 0.24135306477546692, "learning_rate": 9.995370575511151e-05, "loss": 10.3599, "step": 26 }, { "epoch": 0.0008272629087483053, "grad_norm": 0.22803382575511932, "learning_rate": 9.99491925684186e-05, "loss": 10.3602, "step": 27 }, { "epoch": 0.0008579022757389832, "grad_norm": 0.23162369430065155, "learning_rate": 9.994446961154325e-05, "loss": 10.3633, "step": 28 }, { "epoch": 0.0008885416427296612, "grad_norm": 0.2333999127149582, "learning_rate": 9.993953690432031e-05, "loss": 10.3599, "step": 29 }, { "epoch": 0.0009191810097203392, "grad_norm": 0.2367755025625229, "learning_rate": 9.993439446746558e-05, "loss": 10.3586, "step": 30 }, { "epoch": 0.0009498203767110172, "grad_norm": 0.2526112496852875, "learning_rate": 9.992904232257555e-05, "loss": 10.36, "step": 31 }, { "epoch": 0.0009804597437016952, "grad_norm": 0.2687104642391205, "learning_rate": 9.99234804921275e-05, "loss": 10.3609, "step": 32 }, { "epoch": 0.0010110991106923731, "grad_norm": 0.27773356437683105, "learning_rate": 9.991770899947926e-05, "loss": 10.3589, "step": 33 }, { "epoch": 0.001041738477683051, "grad_norm": 0.28705063462257385, "learning_rate": 9.991172786886922e-05, "loss": 10.3587, "step": 34 }, { "epoch": 0.001072377844673729, "grad_norm": 0.296935111284256, "learning_rate": 9.990553712541617e-05, "loss": 10.3589, "step": 35 }, { "epoch": 0.0011030172116644071, "grad_norm": 0.3149632513523102, "learning_rate": 9.989913679511919e-05, "loss": 10.3625, "step": 36 }, { "epoch": 0.001133656578655085, "grad_norm": 0.3028753995895386, "learning_rate": 9.989252690485755e-05, "loss": 10.3755, "step": 37 }, { "epoch": 0.001164295945645763, "grad_norm": 0.3272389769554138, "learning_rate": 9.988570748239062e-05, "loss": 10.3758, "step": 38 }, { "epoch": 0.0011949353126364409, "grad_norm": 0.35342222452163696, "learning_rate": 9.987867855635776e-05, "loss": 10.3697, "step": 39 }, { "epoch": 0.0012255746796271188, "grad_norm": 0.37038740515708923, "learning_rate": 9.987144015627809e-05, "loss": 10.3771, "step": 40 }, { "epoch": 0.001256214046617797, "grad_norm": 0.435486763715744, "learning_rate": 9.986399231255056e-05, "loss": 10.3806, "step": 41 }, { "epoch": 0.0012868534136084749, "grad_norm": 0.43793022632598877, "learning_rate": 9.985633505645364e-05, "loss": 10.3783, "step": 42 }, { "epoch": 0.0013174927805991528, "grad_norm": 0.3990364372730255, "learning_rate": 9.98484684201453e-05, "loss": 10.3722, "step": 43 }, { "epoch": 0.0013481321475898307, "grad_norm": 0.3756003677845001, "learning_rate": 9.984039243666283e-05, "loss": 10.3695, "step": 44 }, { "epoch": 0.0013787715145805088, "grad_norm": 0.38554298877716064, "learning_rate": 9.983210713992268e-05, "loss": 10.3747, "step": 45 }, { "epoch": 0.0014094108815711868, "grad_norm": 0.3810689449310303, "learning_rate": 9.98236125647204e-05, "loss": 10.3769, "step": 46 }, { "epoch": 0.0014400502485618647, "grad_norm": 0.3995368182659149, "learning_rate": 9.981490874673039e-05, "loss": 10.3882, "step": 47 }, { "epoch": 0.0014706896155525426, "grad_norm": 0.3769223690032959, "learning_rate": 9.980599572250584e-05, "loss": 10.3825, "step": 48 }, { "epoch": 0.0015013289825432207, "grad_norm": 0.38782820105552673, "learning_rate": 9.97968735294785e-05, "loss": 10.3838, "step": 49 }, { "epoch": 0.0015319683495338987, "grad_norm": 0.3910014033317566, "learning_rate": 9.978754220595861e-05, "loss": 10.3778, "step": 50 }, { "epoch": 0.0015626077165245766, "grad_norm": 0.41532161831855774, "learning_rate": 9.977800179113463e-05, "loss": 10.3535, "step": 51 }, { "epoch": 0.0015932470835152545, "grad_norm": 0.36595699191093445, "learning_rate": 9.97682523250732e-05, "loss": 10.3524, "step": 52 }, { "epoch": 0.0016238864505059326, "grad_norm": 0.4012646973133087, "learning_rate": 9.975829384871884e-05, "loss": 10.3407, "step": 53 }, { "epoch": 0.0016545258174966106, "grad_norm": 0.3944823443889618, "learning_rate": 9.974812640389388e-05, "loss": 10.3522, "step": 54 }, { "epoch": 0.0016851651844872885, "grad_norm": 0.4177343547344208, "learning_rate": 9.973775003329824e-05, "loss": 10.3444, "step": 55 }, { "epoch": 0.0017158045514779664, "grad_norm": 0.45602279901504517, "learning_rate": 9.97271647805093e-05, "loss": 10.3406, "step": 56 }, { "epoch": 0.0017464439184686445, "grad_norm": 0.48096930980682373, "learning_rate": 9.971637068998159e-05, "loss": 10.3446, "step": 57 }, { "epoch": 0.0017770832854593225, "grad_norm": 0.4903767704963684, "learning_rate": 9.970536780704678e-05, "loss": 10.3438, "step": 58 }, { "epoch": 0.0018077226524500004, "grad_norm": 0.502999484539032, "learning_rate": 9.969415617791336e-05, "loss": 10.3429, "step": 59 }, { "epoch": 0.0018383620194406783, "grad_norm": 0.47343501448631287, "learning_rate": 9.968273584966644e-05, "loss": 10.3432, "step": 60 }, { "epoch": 0.0018690013864313562, "grad_norm": 0.5070235729217529, "learning_rate": 9.96711068702677e-05, "loss": 10.341, "step": 61 }, { "epoch": 0.0018996407534220344, "grad_norm": 0.49711889028549194, "learning_rate": 9.965926928855499e-05, "loss": 10.3328, "step": 62 }, { "epoch": 0.0019302801204127123, "grad_norm": 0.48925232887268066, "learning_rate": 9.964722315424227e-05, "loss": 10.3333, "step": 63 }, { "epoch": 0.0019609194874033904, "grad_norm": 0.48452919721603394, "learning_rate": 9.963496851791935e-05, "loss": 10.3311, "step": 64 }, { "epoch": 0.001991558854394068, "grad_norm": 0.492946982383728, "learning_rate": 9.962250543105167e-05, "loss": 10.3337, "step": 65 }, { "epoch": 0.0020221982213847463, "grad_norm": 0.5217669606208801, "learning_rate": 9.960983394598009e-05, "loss": 10.3336, "step": 66 }, { "epoch": 0.002052837588375424, "grad_norm": 0.5229796767234802, "learning_rate": 9.959695411592068e-05, "loss": 10.3299, "step": 67 }, { "epoch": 0.002083476955366102, "grad_norm": 0.5266199707984924, "learning_rate": 9.95838659949645e-05, "loss": 10.332, "step": 68 }, { "epoch": 0.0021141163223567802, "grad_norm": 0.5694423317909241, "learning_rate": 9.957056963807736e-05, "loss": 10.325, "step": 69 }, { "epoch": 0.002144755689347458, "grad_norm": 0.5378698706626892, "learning_rate": 9.955706510109957e-05, "loss": 10.3161, "step": 70 }, { "epoch": 0.002175395056338136, "grad_norm": 0.4891819655895233, "learning_rate": 9.954335244074574e-05, "loss": 10.3199, "step": 71 }, { "epoch": 0.0022060344233288142, "grad_norm": 0.4915742874145508, "learning_rate": 9.952943171460455e-05, "loss": 10.3132, "step": 72 }, { "epoch": 0.002236673790319492, "grad_norm": 0.4707483649253845, "learning_rate": 9.951530298113847e-05, "loss": 10.3078, "step": 73 }, { "epoch": 0.00226731315731017, "grad_norm": 0.5317016243934631, "learning_rate": 9.950096629968352e-05, "loss": 10.2982, "step": 74 }, { "epoch": 0.0022979525243008478, "grad_norm": 0.5227375626564026, "learning_rate": 9.948642173044905e-05, "loss": 10.2931, "step": 75 }, { "epoch": 0.002328591891291526, "grad_norm": 0.4966718852519989, "learning_rate": 9.94716693345175e-05, "loss": 10.2857, "step": 76 }, { "epoch": 0.002359231258282204, "grad_norm": 0.498467355966568, "learning_rate": 9.945670917384403e-05, "loss": 10.2837, "step": 77 }, { "epoch": 0.0023898706252728818, "grad_norm": 0.5161658525466919, "learning_rate": 9.944154131125642e-05, "loss": 10.2833, "step": 78 }, { "epoch": 0.00242050999226356, "grad_norm": 0.4879140853881836, "learning_rate": 9.942616581045473e-05, "loss": 10.2878, "step": 79 }, { "epoch": 0.0024511493592542376, "grad_norm": 0.503729522228241, "learning_rate": 9.941058273601096e-05, "loss": 10.289, "step": 80 }, { "epoch": 0.0024817887262449157, "grad_norm": 0.48749202489852905, "learning_rate": 9.939479215336893e-05, "loss": 10.2847, "step": 81 }, { "epoch": 0.002512428093235594, "grad_norm": 0.5124345421791077, "learning_rate": 9.93787941288439e-05, "loss": 10.2828, "step": 82 }, { "epoch": 0.0025430674602262716, "grad_norm": 0.5024367570877075, "learning_rate": 9.936258872962228e-05, "loss": 10.2694, "step": 83 }, { "epoch": 0.0025737068272169497, "grad_norm": 0.4918675720691681, "learning_rate": 9.934617602376142e-05, "loss": 10.2753, "step": 84 }, { "epoch": 0.002604346194207628, "grad_norm": 0.4941501021385193, "learning_rate": 9.932955608018933e-05, "loss": 10.2718, "step": 85 }, { "epoch": 0.0026349855611983056, "grad_norm": 0.5033401846885681, "learning_rate": 9.931272896870426e-05, "loss": 10.2693, "step": 86 }, { "epoch": 0.0026656249281889837, "grad_norm": 0.49800774455070496, "learning_rate": 9.929569475997457e-05, "loss": 10.269, "step": 87 }, { "epoch": 0.0026962642951796614, "grad_norm": 0.581160306930542, "learning_rate": 9.927845352553831e-05, "loss": 10.2758, "step": 88 }, { "epoch": 0.0027269036621703395, "grad_norm": 0.6085376143455505, "learning_rate": 9.926100533780303e-05, "loss": 10.2805, "step": 89 }, { "epoch": 0.0027575430291610177, "grad_norm": 0.5927174687385559, "learning_rate": 9.924335027004536e-05, "loss": 10.259, "step": 90 }, { "epoch": 0.0027881823961516954, "grad_norm": 0.6134704351425171, "learning_rate": 9.92254883964108e-05, "loss": 10.2574, "step": 91 }, { "epoch": 0.0028188217631423735, "grad_norm": 0.6188032627105713, "learning_rate": 9.920741979191331e-05, "loss": 10.257, "step": 92 }, { "epoch": 0.0028494611301330517, "grad_norm": 0.6642237901687622, "learning_rate": 9.918914453243508e-05, "loss": 10.2553, "step": 93 }, { "epoch": 0.0028801004971237294, "grad_norm": 0.670950710773468, "learning_rate": 9.917066269472623e-05, "loss": 10.2507, "step": 94 }, { "epoch": 0.0029107398641144075, "grad_norm": 0.6101608276367188, "learning_rate": 9.91519743564044e-05, "loss": 10.2564, "step": 95 }, { "epoch": 0.002941379231105085, "grad_norm": 0.48022058606147766, "learning_rate": 9.913307959595444e-05, "loss": 10.2585, "step": 96 }, { "epoch": 0.0029720185980957633, "grad_norm": 0.6569609045982361, "learning_rate": 9.911397849272813e-05, "loss": 10.2623, "step": 97 }, { "epoch": 0.0030026579650864415, "grad_norm": 0.6302333474159241, "learning_rate": 9.909467112694384e-05, "loss": 10.2634, "step": 98 }, { "epoch": 0.003033297332077119, "grad_norm": 0.6016459465026855, "learning_rate": 9.907515757968613e-05, "loss": 10.2572, "step": 99 }, { "epoch": 0.0030639366990677973, "grad_norm": 0.6104916930198669, "learning_rate": 9.905543793290551e-05, "loss": 10.2613, "step": 100 }, { "epoch": 0.003094576066058475, "grad_norm": 0.4617011845111847, "learning_rate": 9.903551226941801e-05, "loss": 10.2507, "step": 101 }, { "epoch": 0.003125215433049153, "grad_norm": 0.45665284991264343, "learning_rate": 9.901538067290485e-05, "loss": 10.2518, "step": 102 }, { "epoch": 0.0031558548000398313, "grad_norm": 0.4125213623046875, "learning_rate": 9.89950432279121e-05, "loss": 10.243, "step": 103 }, { "epoch": 0.003186494167030509, "grad_norm": 0.4446852207183838, "learning_rate": 9.897450001985039e-05, "loss": 10.253, "step": 104 }, { "epoch": 0.003217133534021187, "grad_norm": 0.4295095205307007, "learning_rate": 9.895375113499439e-05, "loss": 10.2319, "step": 105 }, { "epoch": 0.0032477729010118653, "grad_norm": 0.4166061580181122, "learning_rate": 9.893279666048261e-05, "loss": 10.2316, "step": 106 }, { "epoch": 0.003278412268002543, "grad_norm": 0.4115273654460907, "learning_rate": 9.891163668431695e-05, "loss": 10.2319, "step": 107 }, { "epoch": 0.003309051634993221, "grad_norm": 0.4369446635246277, "learning_rate": 9.889027129536237e-05, "loss": 10.2299, "step": 108 }, { "epoch": 0.003339691001983899, "grad_norm": 0.420180082321167, "learning_rate": 9.886870058334644e-05, "loss": 10.228, "step": 109 }, { "epoch": 0.003370330368974577, "grad_norm": 0.389148473739624, "learning_rate": 9.88469246388591e-05, "loss": 10.2292, "step": 110 }, { "epoch": 0.003400969735965255, "grad_norm": 0.37859535217285156, "learning_rate": 9.882494355335211e-05, "loss": 10.2265, "step": 111 }, { "epoch": 0.003431609102955933, "grad_norm": 0.3675991892814636, "learning_rate": 9.880275741913884e-05, "loss": 10.2227, "step": 112 }, { "epoch": 0.003462248469946611, "grad_norm": 0.3687768876552582, "learning_rate": 9.878036632939374e-05, "loss": 10.2206, "step": 113 }, { "epoch": 0.003492887836937289, "grad_norm": 0.3665653467178345, "learning_rate": 9.875777037815202e-05, "loss": 10.2206, "step": 114 }, { "epoch": 0.003523527203927967, "grad_norm": 0.3494964838027954, "learning_rate": 9.873496966030923e-05, "loss": 10.2228, "step": 115 }, { "epoch": 0.003554166570918645, "grad_norm": 0.372764527797699, "learning_rate": 9.871196427162092e-05, "loss": 10.2236, "step": 116 }, { "epoch": 0.0035848059379093226, "grad_norm": 0.35803404450416565, "learning_rate": 9.868875430870216e-05, "loss": 10.2178, "step": 117 }, { "epoch": 0.0036154453049000008, "grad_norm": 0.3608494699001312, "learning_rate": 9.866533986902713e-05, "loss": 10.2158, "step": 118 }, { "epoch": 0.003646084671890679, "grad_norm": 0.39143475890159607, "learning_rate": 9.86417210509288e-05, "loss": 10.2166, "step": 119 }, { "epoch": 0.0036767240388813566, "grad_norm": 0.3595784604549408, "learning_rate": 9.861789795359842e-05, "loss": 10.2183, "step": 120 }, { "epoch": 0.0037073634058720347, "grad_norm": 0.32507047057151794, "learning_rate": 9.859387067708517e-05, "loss": 10.2171, "step": 121 }, { "epoch": 0.0037380027728627124, "grad_norm": 0.3041350543498993, "learning_rate": 9.85696393222957e-05, "loss": 10.2085, "step": 122 }, { "epoch": 0.0037686421398533906, "grad_norm": 0.3051709830760956, "learning_rate": 9.854520399099377e-05, "loss": 10.2146, "step": 123 }, { "epoch": 0.0037992815068440687, "grad_norm": 0.362964004278183, "learning_rate": 9.85205647857997e-05, "loss": 10.2013, "step": 124 }, { "epoch": 0.0038299208738347464, "grad_norm": 0.3657281994819641, "learning_rate": 9.849572181019007e-05, "loss": 10.1957, "step": 125 }, { "epoch": 0.0038605602408254246, "grad_norm": 0.3641434609889984, "learning_rate": 9.847067516849717e-05, "loss": 10.196, "step": 126 }, { "epoch": 0.0038911996078161027, "grad_norm": 0.3638749420642853, "learning_rate": 9.844542496590872e-05, "loss": 10.194, "step": 127 }, { "epoch": 0.003921838974806781, "grad_norm": 0.35783156752586365, "learning_rate": 9.84199713084672e-05, "loss": 10.193, "step": 128 }, { "epoch": 0.003952478341797458, "grad_norm": 0.329607218503952, "learning_rate": 9.839431430306965e-05, "loss": 10.2009, "step": 129 }, { "epoch": 0.003983117708788136, "grad_norm": 0.41538935899734497, "learning_rate": 9.836845405746704e-05, "loss": 10.1916, "step": 130 }, { "epoch": 0.004013757075778814, "grad_norm": 0.3260403573513031, "learning_rate": 9.834239068026387e-05, "loss": 10.1979, "step": 131 }, { "epoch": 0.0040443964427694925, "grad_norm": 0.3089582026004791, "learning_rate": 9.83161242809178e-05, "loss": 10.2174, "step": 132 }, { "epoch": 0.004075035809760171, "grad_norm": 0.3140828013420105, "learning_rate": 9.828965496973906e-05, "loss": 10.209, "step": 133 }, { "epoch": 0.004105675176750848, "grad_norm": 0.30631038546562195, "learning_rate": 9.826298285789002e-05, "loss": 10.2078, "step": 134 }, { "epoch": 0.004136314543741526, "grad_norm": 0.2800963222980499, "learning_rate": 9.823610805738479e-05, "loss": 10.2003, "step": 135 }, { "epoch": 0.004166953910732204, "grad_norm": 0.25573664903640747, "learning_rate": 9.820903068108871e-05, "loss": 10.1959, "step": 136 }, { "epoch": 0.004197593277722882, "grad_norm": 0.2738712728023529, "learning_rate": 9.818175084271786e-05, "loss": 10.1859, "step": 137 }, { "epoch": 0.0042282326447135605, "grad_norm": 0.3030584156513214, "learning_rate": 9.815426865683857e-05, "loss": 10.1822, "step": 138 }, { "epoch": 0.004258872011704238, "grad_norm": 0.3009280860424042, "learning_rate": 9.812658423886698e-05, "loss": 10.1876, "step": 139 }, { "epoch": 0.004289511378694916, "grad_norm": 0.34544259309768677, "learning_rate": 9.809869770506856e-05, "loss": 10.1817, "step": 140 }, { "epoch": 0.004320150745685594, "grad_norm": 0.3761567175388336, "learning_rate": 9.807060917255757e-05, "loss": 10.183, "step": 141 }, { "epoch": 0.004350790112676272, "grad_norm": 0.33650821447372437, "learning_rate": 9.804231875929661e-05, "loss": 10.1803, "step": 142 }, { "epoch": 0.00438142947966695, "grad_norm": 0.37510374188423157, "learning_rate": 9.80138265840961e-05, "loss": 10.1853, "step": 143 }, { "epoch": 0.0044120688466576284, "grad_norm": 0.2876983880996704, "learning_rate": 9.798513276661386e-05, "loss": 10.1988, "step": 144 }, { "epoch": 0.004442708213648306, "grad_norm": 0.26207780838012695, "learning_rate": 9.79562374273544e-05, "loss": 10.1959, "step": 145 }, { "epoch": 0.004473347580638984, "grad_norm": 0.27307620644569397, "learning_rate": 9.792714068766872e-05, "loss": 10.1919, "step": 146 }, { "epoch": 0.004503986947629662, "grad_norm": 0.479770302772522, "learning_rate": 9.789784266975352e-05, "loss": 10.1815, "step": 147 }, { "epoch": 0.00453462631462034, "grad_norm": 0.4118158519268036, "learning_rate": 9.786834349665083e-05, "loss": 10.1935, "step": 148 }, { "epoch": 0.004565265681611018, "grad_norm": 0.4143422245979309, "learning_rate": 9.783864329224752e-05, "loss": 10.203, "step": 149 }, { "epoch": 0.0045959050486016955, "grad_norm": 0.3514252305030823, "learning_rate": 9.780874218127464e-05, "loss": 10.1834, "step": 150 }, { "epoch": 0.004626544415592374, "grad_norm": 0.3279332220554352, "learning_rate": 9.777864028930705e-05, "loss": 10.186, "step": 151 }, { "epoch": 0.004657183782583052, "grad_norm": 0.2270706295967102, "learning_rate": 9.774833774276278e-05, "loss": 10.1987, "step": 152 }, { "epoch": 0.00468782314957373, "grad_norm": 0.3779345154762268, "learning_rate": 9.771783466890254e-05, "loss": 10.2011, "step": 153 }, { "epoch": 0.004718462516564408, "grad_norm": 0.32367634773254395, "learning_rate": 9.768713119582927e-05, "loss": 10.21, "step": 154 }, { "epoch": 0.004749101883555085, "grad_norm": 0.2722915709018707, "learning_rate": 9.765622745248739e-05, "loss": 10.1845, "step": 155 }, { "epoch": 0.0047797412505457635, "grad_norm": 0.25113949179649353, "learning_rate": 9.762512356866252e-05, "loss": 10.1843, "step": 156 }, { "epoch": 0.004810380617536442, "grad_norm": 0.2509434223175049, "learning_rate": 9.75938196749807e-05, "loss": 10.1794, "step": 157 }, { "epoch": 0.00484101998452712, "grad_norm": 0.2345142364501953, "learning_rate": 9.7562315902908e-05, "loss": 10.1776, "step": 158 }, { "epoch": 0.004871659351517798, "grad_norm": 0.23735208809375763, "learning_rate": 9.753061238474991e-05, "loss": 10.1806, "step": 159 }, { "epoch": 0.004902298718508475, "grad_norm": 0.2244131863117218, "learning_rate": 9.749870925365077e-05, "loss": 10.1812, "step": 160 }, { "epoch": 0.004932938085499153, "grad_norm": 0.24302279949188232, "learning_rate": 9.746660664359326e-05, "loss": 10.184, "step": 161 }, { "epoch": 0.0049635774524898315, "grad_norm": 0.2579200267791748, "learning_rate": 9.743430468939777e-05, "loss": 10.1815, "step": 162 }, { "epoch": 0.00499421681948051, "grad_norm": 0.2534882426261902, "learning_rate": 9.740180352672188e-05, "loss": 10.1845, "step": 163 }, { "epoch": 0.005024856186471188, "grad_norm": 0.24429906904697418, "learning_rate": 9.736910329205978e-05, "loss": 10.1765, "step": 164 }, { "epoch": 0.005055495553461866, "grad_norm": 0.24666520953178406, "learning_rate": 9.733620412274173e-05, "loss": 10.1804, "step": 165 }, { "epoch": 0.005086134920452543, "grad_norm": 0.2347945123910904, "learning_rate": 9.730310615693338e-05, "loss": 10.1822, "step": 166 }, { "epoch": 0.005116774287443221, "grad_norm": 0.22700455784797668, "learning_rate": 9.726980953363536e-05, "loss": 10.1818, "step": 167 }, { "epoch": 0.005147413654433899, "grad_norm": 0.23626674711704254, "learning_rate": 9.723631439268248e-05, "loss": 10.1759, "step": 168 }, { "epoch": 0.0051780530214245776, "grad_norm": 0.257414311170578, "learning_rate": 9.720262087474335e-05, "loss": 10.1768, "step": 169 }, { "epoch": 0.005208692388415256, "grad_norm": 0.3152066171169281, "learning_rate": 9.716872912131964e-05, "loss": 10.1714, "step": 170 }, { "epoch": 0.005239331755405933, "grad_norm": 0.28246307373046875, "learning_rate": 9.713463927474559e-05, "loss": 10.1716, "step": 171 }, { "epoch": 0.005269971122396611, "grad_norm": 0.22445334494113922, "learning_rate": 9.710035147818735e-05, "loss": 10.1757, "step": 172 }, { "epoch": 0.005300610489387289, "grad_norm": 0.30164289474487305, "learning_rate": 9.706586587564237e-05, "loss": 10.175, "step": 173 }, { "epoch": 0.005331249856377967, "grad_norm": 0.3072303235530853, "learning_rate": 9.703118261193885e-05, "loss": 10.1654, "step": 174 }, { "epoch": 0.0053618892233686455, "grad_norm": 0.32241764664649963, "learning_rate": 9.699630183273507e-05, "loss": 10.159, "step": 175 }, { "epoch": 0.005392528590359323, "grad_norm": 0.29490017890930176, "learning_rate": 9.696122368451886e-05, "loss": 10.1653, "step": 176 }, { "epoch": 0.005423167957350001, "grad_norm": 0.3198687434196472, "learning_rate": 9.69259483146069e-05, "loss": 10.1572, "step": 177 }, { "epoch": 0.005453807324340679, "grad_norm": 0.3245239555835724, "learning_rate": 9.689047587114416e-05, "loss": 10.1551, "step": 178 }, { "epoch": 0.005484446691331357, "grad_norm": 0.33736497163772583, "learning_rate": 9.685480650310318e-05, "loss": 10.1626, "step": 179 }, { "epoch": 0.005515086058322035, "grad_norm": 0.378255695104599, "learning_rate": 9.681894036028365e-05, "loss": 10.151, "step": 180 }, { "epoch": 0.005545725425312713, "grad_norm": 0.2807524502277374, "learning_rate": 9.678287759331152e-05, "loss": 10.1632, "step": 181 }, { "epoch": 0.005576364792303391, "grad_norm": 0.29772505164146423, "learning_rate": 9.674661835363858e-05, "loss": 10.193, "step": 182 }, { "epoch": 0.005607004159294069, "grad_norm": 0.2409011572599411, "learning_rate": 9.671016279354171e-05, "loss": 10.1763, "step": 183 }, { "epoch": 0.005637643526284747, "grad_norm": 0.26572665572166443, "learning_rate": 9.667351106612223e-05, "loss": 10.1766, "step": 184 }, { "epoch": 0.005668282893275425, "grad_norm": 0.31308165192604065, "learning_rate": 9.663666332530541e-05, "loss": 10.1814, "step": 185 }, { "epoch": 0.005698922260266103, "grad_norm": 0.21770384907722473, "learning_rate": 9.659961972583959e-05, "loss": 10.1631, "step": 186 }, { "epoch": 0.005729561627256781, "grad_norm": 0.20671813189983368, "learning_rate": 9.656238042329574e-05, "loss": 10.1553, "step": 187 }, { "epoch": 0.005760200994247459, "grad_norm": 0.23726466298103333, "learning_rate": 9.652494557406666e-05, "loss": 10.1508, "step": 188 }, { "epoch": 0.005790840361238137, "grad_norm": 0.23543891310691833, "learning_rate": 9.648731533536643e-05, "loss": 10.1515, "step": 189 }, { "epoch": 0.005821479728228815, "grad_norm": 0.24708674848079681, "learning_rate": 9.644948986522966e-05, "loss": 10.1499, "step": 190 }, { "epoch": 0.005852119095219493, "grad_norm": 0.24789170920848846, "learning_rate": 9.641146932251089e-05, "loss": 10.1515, "step": 191 }, { "epoch": 0.00588275846221017, "grad_norm": 0.3027416467666626, "learning_rate": 9.637325386688389e-05, "loss": 10.1453, "step": 192 }, { "epoch": 0.0059133978292008485, "grad_norm": 0.3192403018474579, "learning_rate": 9.6334843658841e-05, "loss": 10.1505, "step": 193 }, { "epoch": 0.005944037196191527, "grad_norm": 0.25966107845306396, "learning_rate": 9.62962388596925e-05, "loss": 10.1594, "step": 194 }, { "epoch": 0.005974676563182205, "grad_norm": 0.23529139161109924, "learning_rate": 9.625743963156582e-05, "loss": 10.162, "step": 195 }, { "epoch": 0.006005315930172883, "grad_norm": 0.22195586562156677, "learning_rate": 9.621844613740494e-05, "loss": 10.151, "step": 196 }, { "epoch": 0.00603595529716356, "grad_norm": 0.4857119619846344, "learning_rate": 9.617925854096975e-05, "loss": 10.146, "step": 197 }, { "epoch": 0.006066594664154238, "grad_norm": 0.34034472703933716, "learning_rate": 9.613987700683526e-05, "loss": 10.1656, "step": 198 }, { "epoch": 0.0060972340311449165, "grad_norm": 0.36044079065322876, "learning_rate": 9.610030170039094e-05, "loss": 10.1633, "step": 199 }, { "epoch": 0.006127873398135595, "grad_norm": 0.314235657453537, "learning_rate": 9.606053278784009e-05, "loss": 10.1535, "step": 200 }, { "epoch": 0.006158512765126273, "grad_norm": 0.23128853738307953, "learning_rate": 9.602057043619903e-05, "loss": 10.1636, "step": 201 }, { "epoch": 0.00618915213211695, "grad_norm": 0.2757967412471771, "learning_rate": 9.598041481329653e-05, "loss": 10.165, "step": 202 }, { "epoch": 0.006219791499107628, "grad_norm": 0.3894402086734772, "learning_rate": 9.5940066087773e-05, "loss": 10.1658, "step": 203 }, { "epoch": 0.006250430866098306, "grad_norm": 0.2699827253818512, "learning_rate": 9.589952442907979e-05, "loss": 10.1837, "step": 204 }, { "epoch": 0.0062810702330889845, "grad_norm": 0.2653277814388275, "learning_rate": 9.585879000747855e-05, "loss": 10.1644, "step": 205 }, { "epoch": 0.006311709600079663, "grad_norm": 0.2447018176317215, "learning_rate": 9.581786299404045e-05, "loss": 10.1589, "step": 206 }, { "epoch": 0.006342348967070341, "grad_norm": 0.2339245080947876, "learning_rate": 9.57767435606455e-05, "loss": 10.1542, "step": 207 }, { "epoch": 0.006372988334061018, "grad_norm": 0.2381335347890854, "learning_rate": 9.57354318799818e-05, "loss": 10.1471, "step": 208 }, { "epoch": 0.006403627701051696, "grad_norm": 0.2182401418685913, "learning_rate": 9.569392812554478e-05, "loss": 10.1462, "step": 209 }, { "epoch": 0.006434267068042374, "grad_norm": 0.21164676547050476, "learning_rate": 9.565223247163661e-05, "loss": 10.1469, "step": 210 }, { "epoch": 0.006464906435033052, "grad_norm": 0.24600906670093536, "learning_rate": 9.56103450933653e-05, "loss": 10.1559, "step": 211 }, { "epoch": 0.0064955458020237306, "grad_norm": 0.23725466430187225, "learning_rate": 9.556826616664407e-05, "loss": 10.1552, "step": 212 }, { "epoch": 0.006526185169014408, "grad_norm": 0.23444445431232452, "learning_rate": 9.552599586819058e-05, "loss": 10.1545, "step": 213 }, { "epoch": 0.006556824536005086, "grad_norm": 0.21064426004886627, "learning_rate": 9.548353437552618e-05, "loss": 10.1484, "step": 214 }, { "epoch": 0.006587463902995764, "grad_norm": 0.2170412838459015, "learning_rate": 9.544088186697515e-05, "loss": 10.1495, "step": 215 }, { "epoch": 0.006618103269986442, "grad_norm": 0.26441171765327454, "learning_rate": 9.539803852166403e-05, "loss": 10.1564, "step": 216 }, { "epoch": 0.00664874263697712, "grad_norm": 0.22346778213977814, "learning_rate": 9.535500451952077e-05, "loss": 10.1438, "step": 217 }, { "epoch": 0.006679382003967798, "grad_norm": 0.20265920460224152, "learning_rate": 9.531178004127403e-05, "loss": 10.152, "step": 218 }, { "epoch": 0.006710021370958476, "grad_norm": 0.20692609250545502, "learning_rate": 9.52683652684524e-05, "loss": 10.1467, "step": 219 }, { "epoch": 0.006740660737949154, "grad_norm": 0.19775721430778503, "learning_rate": 9.522476038338365e-05, "loss": 10.156, "step": 220 }, { "epoch": 0.006771300104939832, "grad_norm": 0.21164998412132263, "learning_rate": 9.518096556919396e-05, "loss": 10.1525, "step": 221 }, { "epoch": 0.00680193947193051, "grad_norm": 0.22803594172000885, "learning_rate": 9.513698100980715e-05, "loss": 10.1542, "step": 222 }, { "epoch": 0.0068325788389211875, "grad_norm": 0.18837936222553253, "learning_rate": 9.509280688994389e-05, "loss": 10.1421, "step": 223 }, { "epoch": 0.006863218205911866, "grad_norm": 0.24142253398895264, "learning_rate": 9.504844339512095e-05, "loss": 10.1327, "step": 224 }, { "epoch": 0.006893857572902544, "grad_norm": 0.24025557935237885, "learning_rate": 9.500389071165046e-05, "loss": 10.1365, "step": 225 }, { "epoch": 0.006924496939893222, "grad_norm": 0.25372639298439026, "learning_rate": 9.495914902663901e-05, "loss": 10.1389, "step": 226 }, { "epoch": 0.0069551363068839, "grad_norm": 0.26540708541870117, "learning_rate": 9.491421852798696e-05, "loss": 10.1319, "step": 227 }, { "epoch": 0.006985775673874578, "grad_norm": 0.2537267804145813, "learning_rate": 9.486909940438762e-05, "loss": 10.1329, "step": 228 }, { "epoch": 0.007016415040865255, "grad_norm": 0.31383460760116577, "learning_rate": 9.48237918453265e-05, "loss": 10.132, "step": 229 }, { "epoch": 0.007047054407855934, "grad_norm": 0.2152584046125412, "learning_rate": 9.477829604108044e-05, "loss": 10.1469, "step": 230 }, { "epoch": 0.007077693774846612, "grad_norm": 0.19982336461544037, "learning_rate": 9.473261218271685e-05, "loss": 10.1642, "step": 231 }, { "epoch": 0.00710833314183729, "grad_norm": 0.1662013679742813, "learning_rate": 9.46867404620929e-05, "loss": 10.148, "step": 232 }, { "epoch": 0.007138972508827968, "grad_norm": 0.20403601229190826, "learning_rate": 9.464068107185476e-05, "loss": 10.1515, "step": 233 }, { "epoch": 0.007169611875818645, "grad_norm": 0.24628746509552002, "learning_rate": 9.459443420543667e-05, "loss": 10.1535, "step": 234 }, { "epoch": 0.007200251242809323, "grad_norm": 0.16836899518966675, "learning_rate": 9.454800005706033e-05, "loss": 10.157, "step": 235 }, { "epoch": 0.0072308906098000015, "grad_norm": 0.17160779237747192, "learning_rate": 9.450137882173384e-05, "loss": 10.1332, "step": 236 }, { "epoch": 0.00726152997679068, "grad_norm": 0.19151553511619568, "learning_rate": 9.445457069525108e-05, "loss": 10.1318, "step": 237 }, { "epoch": 0.007292169343781358, "grad_norm": 0.21934491395950317, "learning_rate": 9.440757587419077e-05, "loss": 10.13, "step": 238 }, { "epoch": 0.007322808710772035, "grad_norm": 0.16131079196929932, "learning_rate": 9.436039455591573e-05, "loss": 10.1289, "step": 239 }, { "epoch": 0.007353448077762713, "grad_norm": 0.21789006888866425, "learning_rate": 9.431302693857195e-05, "loss": 10.1351, "step": 240 }, { "epoch": 0.007384087444753391, "grad_norm": 0.24290093779563904, "learning_rate": 9.426547322108789e-05, "loss": 10.1265, "step": 241 }, { "epoch": 0.0074147268117440695, "grad_norm": 0.2682904005050659, "learning_rate": 9.421773360317347e-05, "loss": 10.1266, "step": 242 }, { "epoch": 0.007445366178734748, "grad_norm": 0.34069767594337463, "learning_rate": 9.416980828531943e-05, "loss": 10.125, "step": 243 }, { "epoch": 0.007476005545725425, "grad_norm": 0.2901553809642792, "learning_rate": 9.412169746879632e-05, "loss": 10.1281, "step": 244 }, { "epoch": 0.007506644912716103, "grad_norm": 0.18873432278633118, "learning_rate": 9.407340135565374e-05, "loss": 10.1392, "step": 245 }, { "epoch": 0.007537284279706781, "grad_norm": 0.18116723001003265, "learning_rate": 9.402492014871951e-05, "loss": 10.156, "step": 246 }, { "epoch": 0.007567923646697459, "grad_norm": 0.21934951841831207, "learning_rate": 9.397625405159875e-05, "loss": 10.1424, "step": 247 }, { "epoch": 0.0075985630136881374, "grad_norm": 0.30539992451667786, "learning_rate": 9.392740326867304e-05, "loss": 10.1459, "step": 248 }, { "epoch": 0.007629202380678816, "grad_norm": 0.34416231513023376, "learning_rate": 9.387836800509962e-05, "loss": 10.1471, "step": 249 }, { "epoch": 0.007659841747669493, "grad_norm": 0.30565956234931946, "learning_rate": 9.382914846681047e-05, "loss": 10.1363, "step": 250 }, { "epoch": 0.007690481114660171, "grad_norm": 0.1922389566898346, "learning_rate": 9.377974486051147e-05, "loss": 10.1499, "step": 251 }, { "epoch": 0.007721120481650849, "grad_norm": 0.24070623517036438, "learning_rate": 9.373015739368152e-05, "loss": 10.162, "step": 252 }, { "epoch": 0.007751759848641527, "grad_norm": 0.29451125860214233, "learning_rate": 9.368038627457165e-05, "loss": 10.1614, "step": 253 }, { "epoch": 0.007782399215632205, "grad_norm": 0.27838650345802307, "learning_rate": 9.363043171220423e-05, "loss": 10.1661, "step": 254 }, { "epoch": 0.007813038582622884, "grad_norm": 0.20925530791282654, "learning_rate": 9.358029391637195e-05, "loss": 10.1536, "step": 255 }, { "epoch": 0.007843677949613562, "grad_norm": 0.19836044311523438, "learning_rate": 9.35299730976371e-05, "loss": 10.1423, "step": 256 }, { "epoch": 0.00787431731660424, "grad_norm": 0.19826310873031616, "learning_rate": 9.347946946733055e-05, "loss": 10.1335, "step": 257 }, { "epoch": 0.007904956683594916, "grad_norm": 0.1715853065252304, "learning_rate": 9.342878323755095e-05, "loss": 10.1356, "step": 258 }, { "epoch": 0.007935596050585594, "grad_norm": 0.18618403375148773, "learning_rate": 9.337791462116381e-05, "loss": 10.1337, "step": 259 }, { "epoch": 0.007966235417576273, "grad_norm": 0.16666516661643982, "learning_rate": 9.332686383180055e-05, "loss": 10.1348, "step": 260 }, { "epoch": 0.00799687478456695, "grad_norm": 0.20730982720851898, "learning_rate": 9.327563108385773e-05, "loss": 10.1422, "step": 261 }, { "epoch": 0.008027514151557629, "grad_norm": 0.18355782330036163, "learning_rate": 9.322421659249603e-05, "loss": 10.1407, "step": 262 }, { "epoch": 0.008058153518548307, "grad_norm": 0.17472055554389954, "learning_rate": 9.31726205736394e-05, "loss": 10.1408, "step": 263 }, { "epoch": 0.008088792885538985, "grad_norm": 0.16438454389572144, "learning_rate": 9.312084324397416e-05, "loss": 10.1428, "step": 264 }, { "epoch": 0.008119432252529663, "grad_norm": 0.14644020795822144, "learning_rate": 9.306888482094806e-05, "loss": 10.1376, "step": 265 }, { "epoch": 0.008150071619520341, "grad_norm": 0.16809964179992676, "learning_rate": 9.301674552276942e-05, "loss": 10.1384, "step": 266 }, { "epoch": 0.00818071098651102, "grad_norm": 0.15989115834236145, "learning_rate": 9.29644255684061e-05, "loss": 10.1446, "step": 267 }, { "epoch": 0.008211350353501696, "grad_norm": 0.1357845813035965, "learning_rate": 9.291192517758474e-05, "loss": 10.1377, "step": 268 }, { "epoch": 0.008241989720492374, "grad_norm": 0.16372017562389374, "learning_rate": 9.28592445707897e-05, "loss": 10.1385, "step": 269 }, { "epoch": 0.008272629087483052, "grad_norm": 0.16150210797786713, "learning_rate": 9.280638396926218e-05, "loss": 10.148, "step": 270 }, { "epoch": 0.00830326845447373, "grad_norm": 0.17247039079666138, "learning_rate": 9.275334359499936e-05, "loss": 10.1395, "step": 271 }, { "epoch": 0.008333907821464408, "grad_norm": 0.19114305078983307, "learning_rate": 9.270012367075336e-05, "loss": 10.144, "step": 272 }, { "epoch": 0.008364547188455087, "grad_norm": 0.18105651438236237, "learning_rate": 9.264672442003034e-05, "loss": 10.1447, "step": 273 }, { "epoch": 0.008395186555445765, "grad_norm": 0.1573803424835205, "learning_rate": 9.259314606708964e-05, "loss": 10.135, "step": 274 }, { "epoch": 0.008425825922436443, "grad_norm": 0.18148738145828247, "learning_rate": 9.253938883694267e-05, "loss": 10.1308, "step": 275 }, { "epoch": 0.008456465289427121, "grad_norm": 0.20688171684741974, "learning_rate": 9.248545295535213e-05, "loss": 10.1298, "step": 276 }, { "epoch": 0.008487104656417799, "grad_norm": 0.24721446633338928, "learning_rate": 9.2431338648831e-05, "loss": 10.1292, "step": 277 }, { "epoch": 0.008517744023408476, "grad_norm": 0.24435733258724213, "learning_rate": 9.237704614464156e-05, "loss": 10.1251, "step": 278 }, { "epoch": 0.008548383390399154, "grad_norm": 0.2644619047641754, "learning_rate": 9.232257567079448e-05, "loss": 10.1229, "step": 279 }, { "epoch": 0.008579022757389832, "grad_norm": 0.2871146500110626, "learning_rate": 9.226792745604784e-05, "loss": 10.124, "step": 280 }, { "epoch": 0.00860966212438051, "grad_norm": 0.14572951197624207, "learning_rate": 9.221310172990616e-05, "loss": 10.147, "step": 281 }, { "epoch": 0.008640301491371188, "grad_norm": 0.24766798317432404, "learning_rate": 9.215809872261947e-05, "loss": 10.157, "step": 282 }, { "epoch": 0.008670940858361866, "grad_norm": 0.190408855676651, "learning_rate": 9.210291866518229e-05, "loss": 10.1525, "step": 283 }, { "epoch": 0.008701580225352544, "grad_norm": 0.16426639258861542, "learning_rate": 9.204756178933274e-05, "loss": 10.147, "step": 284 }, { "epoch": 0.008732219592343222, "grad_norm": 0.23785221576690674, "learning_rate": 9.19920283275515e-05, "loss": 10.1518, "step": 285 }, { "epoch": 0.0087628589593339, "grad_norm": 0.17590944468975067, "learning_rate": 9.19363185130608e-05, "loss": 10.1443, "step": 286 }, { "epoch": 0.008793498326324579, "grad_norm": 0.10858047753572464, "learning_rate": 9.18804325798236e-05, "loss": 10.1312, "step": 287 }, { "epoch": 0.008824137693315257, "grad_norm": 0.15725189447402954, "learning_rate": 9.18243707625424e-05, "loss": 10.1221, "step": 288 }, { "epoch": 0.008854777060305933, "grad_norm": 0.13659140467643738, "learning_rate": 9.176813329665841e-05, "loss": 10.1299, "step": 289 }, { "epoch": 0.008885416427296611, "grad_norm": 0.2288004457950592, "learning_rate": 9.17117204183505e-05, "loss": 10.1196, "step": 290 }, { "epoch": 0.00891605579428729, "grad_norm": 0.21320736408233643, "learning_rate": 9.165513236453419e-05, "loss": 10.1182, "step": 291 }, { "epoch": 0.008946695161277968, "grad_norm": 0.21424899995326996, "learning_rate": 9.15983693728607e-05, "loss": 10.1193, "step": 292 }, { "epoch": 0.008977334528268646, "grad_norm": 0.2179030030965805, "learning_rate": 9.154143168171592e-05, "loss": 10.1192, "step": 293 }, { "epoch": 0.009007973895259324, "grad_norm": 0.3053359389305115, "learning_rate": 9.148431953021947e-05, "loss": 10.1168, "step": 294 }, { "epoch": 0.009038613262250002, "grad_norm": 0.25327202677726746, "learning_rate": 9.142703315822357e-05, "loss": 10.1252, "step": 295 }, { "epoch": 0.00906925262924068, "grad_norm": 0.13767379522323608, "learning_rate": 9.136957280631212e-05, "loss": 10.138, "step": 296 }, { "epoch": 0.009099891996231358, "grad_norm": 0.25260189175605774, "learning_rate": 9.131193871579975e-05, "loss": 10.1382, "step": 297 }, { "epoch": 0.009130531363222037, "grad_norm": 0.25824061036109924, "learning_rate": 9.125413112873067e-05, "loss": 10.1408, "step": 298 }, { "epoch": 0.009161170730212713, "grad_norm": 0.31405767798423767, "learning_rate": 9.119615028787771e-05, "loss": 10.1411, "step": 299 }, { "epoch": 0.009191810097203391, "grad_norm": 0.28313931822776794, "learning_rate": 9.113799643674136e-05, "loss": 10.1334, "step": 300 }, { "epoch": 0.00922244946419407, "grad_norm": 0.18197022378444672, "learning_rate": 9.107966981954869e-05, "loss": 10.136, "step": 301 }, { "epoch": 0.009253088831184747, "grad_norm": 0.198178231716156, "learning_rate": 9.102117068125226e-05, "loss": 10.1561, "step": 302 }, { "epoch": 0.009283728198175425, "grad_norm": 0.32714104652404785, "learning_rate": 9.096249926752927e-05, "loss": 10.1519, "step": 303 }, { "epoch": 0.009314367565166104, "grad_norm": 0.19037552177906036, "learning_rate": 9.09036558247803e-05, "loss": 10.1544, "step": 304 }, { "epoch": 0.009345006932156782, "grad_norm": 0.16049005091190338, "learning_rate": 9.08446406001285e-05, "loss": 10.145, "step": 305 }, { "epoch": 0.00937564629914746, "grad_norm": 0.17063891887664795, "learning_rate": 9.078545384141839e-05, "loss": 10.1333, "step": 306 }, { "epoch": 0.009406285666138138, "grad_norm": 0.1404566466808319, "learning_rate": 9.072609579721491e-05, "loss": 10.1271, "step": 307 }, { "epoch": 0.009436925033128816, "grad_norm": 0.127190962433815, "learning_rate": 9.06665667168023e-05, "loss": 10.1289, "step": 308 }, { "epoch": 0.009467564400119494, "grad_norm": 0.13612677156925201, "learning_rate": 9.060686685018315e-05, "loss": 10.132, "step": 309 }, { "epoch": 0.00949820376711017, "grad_norm": 0.16601459681987762, "learning_rate": 9.054699644807723e-05, "loss": 10.126, "step": 310 }, { "epoch": 0.009528843134100849, "grad_norm": 0.12142466008663177, "learning_rate": 9.048695576192058e-05, "loss": 10.1321, "step": 311 }, { "epoch": 0.009559482501091527, "grad_norm": 0.19359469413757324, "learning_rate": 9.042674504386431e-05, "loss": 10.1388, "step": 312 }, { "epoch": 0.009590121868082205, "grad_norm": 0.1542837768793106, "learning_rate": 9.036636454677364e-05, "loss": 10.1341, "step": 313 }, { "epoch": 0.009620761235072883, "grad_norm": 0.16852296888828278, "learning_rate": 9.030581452422679e-05, "loss": 10.1315, "step": 314 }, { "epoch": 0.009651400602063561, "grad_norm": 0.15417806804180145, "learning_rate": 9.024509523051399e-05, "loss": 10.134, "step": 315 }, { "epoch": 0.00968203996905424, "grad_norm": 0.15264514088630676, "learning_rate": 9.018420692063624e-05, "loss": 10.135, "step": 316 }, { "epoch": 0.009712679336044918, "grad_norm": 0.1251794546842575, "learning_rate": 9.012314985030445e-05, "loss": 10.1384, "step": 317 }, { "epoch": 0.009743318703035596, "grad_norm": 0.13219048082828522, "learning_rate": 9.006192427593825e-05, "loss": 10.1378, "step": 318 }, { "epoch": 0.009773958070026274, "grad_norm": 0.15922632813453674, "learning_rate": 9.00005304546649e-05, "loss": 10.1374, "step": 319 }, { "epoch": 0.00980459743701695, "grad_norm": 0.14578090608119965, "learning_rate": 8.993896864431826e-05, "loss": 10.14, "step": 320 }, { "epoch": 0.009835236804007629, "grad_norm": 0.11984135210514069, "learning_rate": 8.987723910343769e-05, "loss": 10.1399, "step": 321 }, { "epoch": 0.009865876170998307, "grad_norm": 0.14472252130508423, "learning_rate": 8.981534209126694e-05, "loss": 10.1372, "step": 322 }, { "epoch": 0.009896515537988985, "grad_norm": 0.12021119147539139, "learning_rate": 8.975327786775315e-05, "loss": 10.1348, "step": 323 }, { "epoch": 0.009927154904979663, "grad_norm": 0.12422214448451996, "learning_rate": 8.969104669354562e-05, "loss": 10.1358, "step": 324 }, { "epoch": 0.009957794271970341, "grad_norm": 0.19478030502796173, "learning_rate": 8.962864882999482e-05, "loss": 10.1285, "step": 325 }, { "epoch": 0.00998843363896102, "grad_norm": 0.22339242696762085, "learning_rate": 8.956608453915125e-05, "loss": 10.126, "step": 326 }, { "epoch": 0.010019073005951697, "grad_norm": 0.23529845476150513, "learning_rate": 8.950335408376437e-05, "loss": 10.1268, "step": 327 }, { "epoch": 0.010049712372942375, "grad_norm": 0.21394489705562592, "learning_rate": 8.944045772728146e-05, "loss": 10.1266, "step": 328 }, { "epoch": 0.010080351739933054, "grad_norm": 0.27770131826400757, "learning_rate": 8.937739573384653e-05, "loss": 10.1165, "step": 329 }, { "epoch": 0.010110991106923732, "grad_norm": 0.17290028929710388, "learning_rate": 8.93141683682992e-05, "loss": 10.1316, "step": 330 }, { "epoch": 0.010141630473914408, "grad_norm": 0.22467806935310364, "learning_rate": 8.925077589617365e-05, "loss": 10.1453, "step": 331 }, { "epoch": 0.010172269840905086, "grad_norm": 0.21685166656970978, "learning_rate": 8.918721858369738e-05, "loss": 10.1677, "step": 332 }, { "epoch": 0.010202909207895764, "grad_norm": 0.2303144633769989, "learning_rate": 8.91234966977902e-05, "loss": 10.1491, "step": 333 }, { "epoch": 0.010233548574886443, "grad_norm": 0.17318762838840485, "learning_rate": 8.90596105060631e-05, "loss": 10.1422, "step": 334 }, { "epoch": 0.01026418794187712, "grad_norm": 0.16077402234077454, "learning_rate": 8.899556027681709e-05, "loss": 10.1349, "step": 335 }, { "epoch": 0.010294827308867799, "grad_norm": 0.10533782094717026, "learning_rate": 8.8931346279042e-05, "loss": 10.1316, "step": 336 }, { "epoch": 0.010325466675858477, "grad_norm": 0.13302670419216156, "learning_rate": 8.886696878241556e-05, "loss": 10.1211, "step": 337 }, { "epoch": 0.010356106042849155, "grad_norm": 0.12751758098602295, "learning_rate": 8.880242805730208e-05, "loss": 10.1179, "step": 338 }, { "epoch": 0.010386745409839833, "grad_norm": 0.20965084433555603, "learning_rate": 8.873772437475136e-05, "loss": 10.121, "step": 339 }, { "epoch": 0.010417384776830511, "grad_norm": 0.16965822875499725, "learning_rate": 8.86728580064976e-05, "loss": 10.1193, "step": 340 }, { "epoch": 0.010448024143821188, "grad_norm": 0.17672576010227203, "learning_rate": 8.860782922495822e-05, "loss": 10.1162, "step": 341 }, { "epoch": 0.010478663510811866, "grad_norm": 0.20148865878582, "learning_rate": 8.85426383032327e-05, "loss": 10.1224, "step": 342 }, { "epoch": 0.010509302877802544, "grad_norm": 0.2884007692337036, "learning_rate": 8.84772855151015e-05, "loss": 10.1101, "step": 343 }, { "epoch": 0.010539942244793222, "grad_norm": 0.1849764734506607, "learning_rate": 8.841177113502482e-05, "loss": 10.121, "step": 344 }, { "epoch": 0.0105705816117839, "grad_norm": 0.10992087423801422, "learning_rate": 8.834609543814149e-05, "loss": 10.1371, "step": 345 }, { "epoch": 0.010601220978774578, "grad_norm": 0.18129339814186096, "learning_rate": 8.828025870026789e-05, "loss": 10.1279, "step": 346 }, { "epoch": 0.010631860345765257, "grad_norm": 0.23670345544815063, "learning_rate": 8.821426119789662e-05, "loss": 10.1342, "step": 347 }, { "epoch": 0.010662499712755935, "grad_norm": 0.27441591024398804, "learning_rate": 8.814810320819551e-05, "loss": 10.1379, "step": 348 }, { "epoch": 0.010693139079746613, "grad_norm": 0.2867147922515869, "learning_rate": 8.808178500900635e-05, "loss": 10.1313, "step": 349 }, { "epoch": 0.010723778446737291, "grad_norm": 0.25631478428840637, "learning_rate": 8.801530687884378e-05, "loss": 10.1241, "step": 350 }, { "epoch": 0.01075441781372797, "grad_norm": 0.13319076597690582, "learning_rate": 8.794866909689408e-05, "loss": 10.1408, "step": 351 }, { "epoch": 0.010785057180718646, "grad_norm": 0.21450123190879822, "learning_rate": 8.7881871943014e-05, "loss": 10.1527, "step": 352 }, { "epoch": 0.010815696547709324, "grad_norm": 0.3608259856700897, "learning_rate": 8.781491569772966e-05, "loss": 10.1454, "step": 353 }, { "epoch": 0.010846335914700002, "grad_norm": 0.23542171716690063, "learning_rate": 8.774780064223523e-05, "loss": 10.1558, "step": 354 }, { "epoch": 0.01087697528169068, "grad_norm": 0.11694921553134918, "learning_rate": 8.76805270583919e-05, "loss": 10.1551, "step": 355 }, { "epoch": 0.010907614648681358, "grad_norm": 0.13456478714942932, "learning_rate": 8.761309522872657e-05, "loss": 10.1316, "step": 356 }, { "epoch": 0.010938254015672036, "grad_norm": 0.14492842555046082, "learning_rate": 8.754550543643079e-05, "loss": 10.1285, "step": 357 }, { "epoch": 0.010968893382662714, "grad_norm": 0.14882643520832062, "learning_rate": 8.747775796535941e-05, "loss": 10.1277, "step": 358 }, { "epoch": 0.010999532749653393, "grad_norm": 0.10642393678426743, "learning_rate": 8.740985310002956e-05, "loss": 10.1303, "step": 359 }, { "epoch": 0.01103017211664407, "grad_norm": 0.12168186902999878, "learning_rate": 8.734179112561935e-05, "loss": 10.1224, "step": 360 }, { "epoch": 0.011060811483634749, "grad_norm": 0.1298719346523285, "learning_rate": 8.727357232796667e-05, "loss": 10.1207, "step": 361 }, { "epoch": 0.011091450850625425, "grad_norm": 0.14631900191307068, "learning_rate": 8.720519699356804e-05, "loss": 10.137, "step": 362 }, { "epoch": 0.011122090217616103, "grad_norm": 0.15650637447834015, "learning_rate": 8.713666540957739e-05, "loss": 10.1305, "step": 363 }, { "epoch": 0.011152729584606782, "grad_norm": 0.15470795333385468, "learning_rate": 8.706797786380481e-05, "loss": 10.1333, "step": 364 }, { "epoch": 0.01118336895159746, "grad_norm": 0.12874755263328552, "learning_rate": 8.699913464471543e-05, "loss": 10.1355, "step": 365 }, { "epoch": 0.011214008318588138, "grad_norm": 0.19236956536769867, "learning_rate": 8.693013604142812e-05, "loss": 10.1359, "step": 366 }, { "epoch": 0.011244647685578816, "grad_norm": 0.10384097695350647, "learning_rate": 8.686098234371434e-05, "loss": 10.1301, "step": 367 }, { "epoch": 0.011275287052569494, "grad_norm": 0.10370136052370071, "learning_rate": 8.679167384199684e-05, "loss": 10.1379, "step": 368 }, { "epoch": 0.011305926419560172, "grad_norm": 0.13283184170722961, "learning_rate": 8.672221082734857e-05, "loss": 10.1367, "step": 369 }, { "epoch": 0.01133656578655085, "grad_norm": 0.10607551783323288, "learning_rate": 8.665259359149132e-05, "loss": 10.1376, "step": 370 }, { "epoch": 0.011367205153541528, "grad_norm": 0.09600384533405304, "learning_rate": 8.658282242679461e-05, "loss": 10.135, "step": 371 }, { "epoch": 0.011397844520532207, "grad_norm": 0.12220925837755203, "learning_rate": 8.651289762627436e-05, "loss": 10.1374, "step": 372 }, { "epoch": 0.011428483887522883, "grad_norm": 0.15407343208789825, "learning_rate": 8.644281948359178e-05, "loss": 10.1371, "step": 373 }, { "epoch": 0.011459123254513561, "grad_norm": 0.16631901264190674, "learning_rate": 8.637258829305199e-05, "loss": 10.1323, "step": 374 }, { "epoch": 0.01148976262150424, "grad_norm": 0.21785318851470947, "learning_rate": 8.63022043496029e-05, "loss": 10.1221, "step": 375 }, { "epoch": 0.011520401988494917, "grad_norm": 0.21979299187660217, "learning_rate": 8.623166794883393e-05, "loss": 10.1171, "step": 376 }, { "epoch": 0.011551041355485596, "grad_norm": 0.2309437394142151, "learning_rate": 8.616097938697475e-05, "loss": 10.119, "step": 377 }, { "epoch": 0.011581680722476274, "grad_norm": 0.21765172481536865, "learning_rate": 8.609013896089409e-05, "loss": 10.1197, "step": 378 }, { "epoch": 0.011612320089466952, "grad_norm": 0.201009601354599, "learning_rate": 8.601914696809845e-05, "loss": 10.1192, "step": 379 }, { "epoch": 0.01164295945645763, "grad_norm": 0.24598164856433868, "learning_rate": 8.594800370673083e-05, "loss": 10.1206, "step": 380 }, { "epoch": 0.011673598823448308, "grad_norm": 0.20482785999774933, "learning_rate": 8.587670947556954e-05, "loss": 10.1211, "step": 381 }, { "epoch": 0.011704238190438986, "grad_norm": 0.1774405539035797, "learning_rate": 8.580526457402692e-05, "loss": 10.1507, "step": 382 }, { "epoch": 0.011734877557429663, "grad_norm": 0.18236958980560303, "learning_rate": 8.573366930214806e-05, "loss": 10.1516, "step": 383 }, { "epoch": 0.01176551692442034, "grad_norm": 0.19878503680229187, "learning_rate": 8.566192396060953e-05, "loss": 10.1571, "step": 384 }, { "epoch": 0.011796156291411019, "grad_norm": 0.19371262192726135, "learning_rate": 8.559002885071819e-05, "loss": 10.1471, "step": 385 }, { "epoch": 0.011826795658401697, "grad_norm": 0.15792463719844818, "learning_rate": 8.551798427440986e-05, "loss": 10.1439, "step": 386 }, { "epoch": 0.011857435025392375, "grad_norm": 0.09315336495637894, "learning_rate": 8.544579053424805e-05, "loss": 10.129, "step": 387 }, { "epoch": 0.011888074392383053, "grad_norm": 0.12216667085886002, "learning_rate": 8.537344793342277e-05, "loss": 10.1193, "step": 388 }, { "epoch": 0.011918713759373731, "grad_norm": 0.11320982873439789, "learning_rate": 8.53009567757491e-05, "loss": 10.1168, "step": 389 }, { "epoch": 0.01194935312636441, "grad_norm": 0.22389669716358185, "learning_rate": 8.522831736566607e-05, "loss": 10.1134, "step": 390 }, { "epoch": 0.011979992493355088, "grad_norm": 0.13806383311748505, "learning_rate": 8.515553000823536e-05, "loss": 10.1226, "step": 391 }, { "epoch": 0.012010631860345766, "grad_norm": 0.24930189549922943, "learning_rate": 8.50825950091399e-05, "loss": 10.1135, "step": 392 }, { "epoch": 0.012041271227336444, "grad_norm": 0.2644740343093872, "learning_rate": 8.50095126746827e-05, "loss": 10.1094, "step": 393 }, { "epoch": 0.01207191059432712, "grad_norm": 0.24658453464508057, "learning_rate": 8.493628331178553e-05, "loss": 10.1137, "step": 394 }, { "epoch": 0.012102549961317799, "grad_norm": 0.22454893589019775, "learning_rate": 8.486290722798764e-05, "loss": 10.1226, "step": 395 }, { "epoch": 0.012133189328308477, "grad_norm": 0.11018826812505722, "learning_rate": 8.478938473144445e-05, "loss": 10.1222, "step": 396 }, { "epoch": 0.012163828695299155, "grad_norm": 0.18667452037334442, "learning_rate": 8.471571613092627e-05, "loss": 10.1236, "step": 397 }, { "epoch": 0.012194468062289833, "grad_norm": 0.2513224482536316, "learning_rate": 8.464190173581699e-05, "loss": 10.1295, "step": 398 }, { "epoch": 0.012225107429280511, "grad_norm": 0.265055388212204, "learning_rate": 8.456794185611279e-05, "loss": 10.1363, "step": 399 }, { "epoch": 0.01225574679627119, "grad_norm": 0.318289190530777, "learning_rate": 8.449383680242085e-05, "loss": 10.123, "step": 400 }, { "epoch": 0.012286386163261867, "grad_norm": 0.16676893830299377, "learning_rate": 8.441958688595801e-05, "loss": 10.1333, "step": 401 }, { "epoch": 0.012317025530252546, "grad_norm": 0.1813560128211975, "learning_rate": 8.434519241854952e-05, "loss": 10.1454, "step": 402 }, { "epoch": 0.012347664897243224, "grad_norm": 0.22938397526741028, "learning_rate": 8.427065371262768e-05, "loss": 10.1535, "step": 403 }, { "epoch": 0.0123783042642339, "grad_norm": 0.20669525861740112, "learning_rate": 8.419597108123054e-05, "loss": 10.1616, "step": 404 }, { "epoch": 0.012408943631224578, "grad_norm": 0.1719820648431778, "learning_rate": 8.412114483800058e-05, "loss": 10.1296, "step": 405 }, { "epoch": 0.012439582998215256, "grad_norm": 0.11287829279899597, "learning_rate": 8.404617529718341e-05, "loss": 10.1313, "step": 406 }, { "epoch": 0.012470222365205934, "grad_norm": 0.122462697327137, "learning_rate": 8.397106277362647e-05, "loss": 10.1248, "step": 407 }, { "epoch": 0.012500861732196613, "grad_norm": 0.11437121778726578, "learning_rate": 8.389580758277764e-05, "loss": 10.1215, "step": 408 }, { "epoch": 0.01253150109918729, "grad_norm": 0.11850276589393616, "learning_rate": 8.382041004068398e-05, "loss": 10.1219, "step": 409 }, { "epoch": 0.012562140466177969, "grad_norm": 0.13634802401065826, "learning_rate": 8.374487046399036e-05, "loss": 10.1269, "step": 410 }, { "epoch": 0.012592779833168647, "grad_norm": 0.14483821392059326, "learning_rate": 8.366918916993817e-05, "loss": 10.1356, "step": 411 }, { "epoch": 0.012623419200159325, "grad_norm": 0.1115262508392334, "learning_rate": 8.359336647636396e-05, "loss": 10.1297, "step": 412 }, { "epoch": 0.012654058567150003, "grad_norm": 0.1443779319524765, "learning_rate": 8.35174027016981e-05, "loss": 10.1344, "step": 413 }, { "epoch": 0.012684697934140681, "grad_norm": 0.1575508862733841, "learning_rate": 8.344129816496347e-05, "loss": 10.1293, "step": 414 }, { "epoch": 0.012715337301131358, "grad_norm": 0.1343722939491272, "learning_rate": 8.336505318577408e-05, "loss": 10.1256, "step": 415 }, { "epoch": 0.012745976668122036, "grad_norm": 0.12332583963871002, "learning_rate": 8.328866808433378e-05, "loss": 10.1278, "step": 416 }, { "epoch": 0.012776616035112714, "grad_norm": 0.1606401652097702, "learning_rate": 8.321214318143489e-05, "loss": 10.1376, "step": 417 }, { "epoch": 0.012807255402103392, "grad_norm": 0.12114573270082474, "learning_rate": 8.313547879845681e-05, "loss": 10.1413, "step": 418 }, { "epoch": 0.01283789476909407, "grad_norm": 0.12806592881679535, "learning_rate": 8.305867525736474e-05, "loss": 10.1353, "step": 419 }, { "epoch": 0.012868534136084749, "grad_norm": 0.1280607283115387, "learning_rate": 8.298173288070833e-05, "loss": 10.1339, "step": 420 }, { "epoch": 0.012899173503075427, "grad_norm": 0.11357972025871277, "learning_rate": 8.290465199162022e-05, "loss": 10.1355, "step": 421 }, { "epoch": 0.012929812870066105, "grad_norm": 0.1011158749461174, "learning_rate": 8.282743291381481e-05, "loss": 10.1302, "step": 422 }, { "epoch": 0.012960452237056783, "grad_norm": 0.21433721482753754, "learning_rate": 8.275007597158682e-05, "loss": 10.123, "step": 423 }, { "epoch": 0.012991091604047461, "grad_norm": 0.16154591739177704, "learning_rate": 8.267258148980998e-05, "loss": 10.1264, "step": 424 }, { "epoch": 0.013021730971038138, "grad_norm": 0.20570388436317444, "learning_rate": 8.259494979393563e-05, "loss": 10.1276, "step": 425 }, { "epoch": 0.013052370338028816, "grad_norm": 0.2047077715396881, "learning_rate": 8.251718120999137e-05, "loss": 10.1207, "step": 426 }, { "epoch": 0.013083009705019494, "grad_norm": 0.18785904347896576, "learning_rate": 8.243927606457964e-05, "loss": 10.1194, "step": 427 }, { "epoch": 0.013113649072010172, "grad_norm": 0.23100726306438446, "learning_rate": 8.236123468487648e-05, "loss": 10.1179, "step": 428 }, { "epoch": 0.01314428843900085, "grad_norm": 0.2645021975040436, "learning_rate": 8.228305739862998e-05, "loss": 10.1165, "step": 429 }, { "epoch": 0.013174927805991528, "grad_norm": 0.19040991365909576, "learning_rate": 8.220474453415906e-05, "loss": 10.1415, "step": 430 }, { "epoch": 0.013205567172982206, "grad_norm": 0.23067405819892883, "learning_rate": 8.212629642035199e-05, "loss": 10.1651, "step": 431 }, { "epoch": 0.013236206539972884, "grad_norm": 0.228408545255661, "learning_rate": 8.204771338666503e-05, "loss": 10.1511, "step": 432 }, { "epoch": 0.013266845906963563, "grad_norm": 0.24095289409160614, "learning_rate": 8.196899576312111e-05, "loss": 10.1585, "step": 433 }, { "epoch": 0.01329748527395424, "grad_norm": 0.1531878262758255, "learning_rate": 8.189014388030833e-05, "loss": 10.1361, "step": 434 }, { "epoch": 0.013328124640944919, "grad_norm": 0.08747851103544235, "learning_rate": 8.181115806937869e-05, "loss": 10.1274, "step": 435 }, { "epoch": 0.013358764007935595, "grad_norm": 0.09105852246284485, "learning_rate": 8.173203866204662e-05, "loss": 10.1227, "step": 436 }, { "epoch": 0.013389403374926273, "grad_norm": 0.1290649026632309, "learning_rate": 8.165278599058761e-05, "loss": 10.1128, "step": 437 }, { "epoch": 0.013420042741916952, "grad_norm": 0.12962590157985687, "learning_rate": 8.157340038783679e-05, "loss": 10.1142, "step": 438 }, { "epoch": 0.01345068210890763, "grad_norm": 0.11234567314386368, "learning_rate": 8.149388218718761e-05, "loss": 10.1176, "step": 439 }, { "epoch": 0.013481321475898308, "grad_norm": 0.13823869824409485, "learning_rate": 8.141423172259038e-05, "loss": 10.1149, "step": 440 }, { "epoch": 0.013511960842888986, "grad_norm": 0.21879583597183228, "learning_rate": 8.133444932855082e-05, "loss": 10.1107, "step": 441 }, { "epoch": 0.013542600209879664, "grad_norm": 0.18583448231220245, "learning_rate": 8.125453534012877e-05, "loss": 10.1109, "step": 442 }, { "epoch": 0.013573239576870342, "grad_norm": 0.23556499183177948, "learning_rate": 8.117449009293668e-05, "loss": 10.1155, "step": 443 }, { "epoch": 0.01360387894386102, "grad_norm": 0.2879980802536011, "learning_rate": 8.109431392313829e-05, "loss": 10.1105, "step": 444 }, { "epoch": 0.013634518310851699, "grad_norm": 0.11128576099872589, "learning_rate": 8.101400716744713e-05, "loss": 10.1427, "step": 445 }, { "epoch": 0.013665157677842375, "grad_norm": 0.13726451992988586, "learning_rate": 8.093357016312517e-05, "loss": 10.1332, "step": 446 }, { "epoch": 0.013695797044833053, "grad_norm": 0.3366081416606903, "learning_rate": 8.085300324798139e-05, "loss": 10.1212, "step": 447 }, { "epoch": 0.013726436411823731, "grad_norm": 0.23197676241397858, "learning_rate": 8.077230676037031e-05, "loss": 10.1349, "step": 448 }, { "epoch": 0.01375707577881441, "grad_norm": 0.2975676953792572, "learning_rate": 8.069148103919064e-05, "loss": 10.1338, "step": 449 }, { "epoch": 0.013787715145805087, "grad_norm": 0.2648490071296692, "learning_rate": 8.061052642388387e-05, "loss": 10.1353, "step": 450 }, { "epoch": 0.013818354512795766, "grad_norm": 0.16083590686321259, "learning_rate": 8.052944325443271e-05, "loss": 10.1439, "step": 451 }, { "epoch": 0.013848993879786444, "grad_norm": 0.2702782154083252, "learning_rate": 8.044823187135984e-05, "loss": 10.1321, "step": 452 }, { "epoch": 0.013879633246777122, "grad_norm": 0.2232368290424347, "learning_rate": 8.036689261572635e-05, "loss": 10.1503, "step": 453 }, { "epoch": 0.0139102726137678, "grad_norm": 0.14067383110523224, "learning_rate": 8.028542582913036e-05, "loss": 10.1546, "step": 454 }, { "epoch": 0.013940911980758478, "grad_norm": 0.14455874264240265, "learning_rate": 8.020383185370559e-05, "loss": 10.1321, "step": 455 }, { "epoch": 0.013971551347749156, "grad_norm": 0.09233621507883072, "learning_rate": 8.01221110321199e-05, "loss": 10.1234, "step": 456 }, { "epoch": 0.014002190714739833, "grad_norm": 0.09339062869548798, "learning_rate": 8.004026370757388e-05, "loss": 10.1268, "step": 457 }, { "epoch": 0.01403283008173051, "grad_norm": 0.10474835336208344, "learning_rate": 7.995829022379936e-05, "loss": 10.1216, "step": 458 }, { "epoch": 0.014063469448721189, "grad_norm": 0.10820935666561127, "learning_rate": 7.987619092505801e-05, "loss": 10.1264, "step": 459 }, { "epoch": 0.014094108815711867, "grad_norm": 0.09847433120012283, "learning_rate": 7.97939661561399e-05, "loss": 10.1257, "step": 460 }, { "epoch": 0.014124748182702545, "grad_norm": 0.1573990136384964, "learning_rate": 7.9711616262362e-05, "loss": 10.1301, "step": 461 }, { "epoch": 0.014155387549693223, "grad_norm": 0.13659170269966125, "learning_rate": 7.962914158956682e-05, "loss": 10.1312, "step": 462 }, { "epoch": 0.014186026916683902, "grad_norm": 0.15610255300998688, "learning_rate": 7.954654248412082e-05, "loss": 10.1345, "step": 463 }, { "epoch": 0.01421666628367458, "grad_norm": 0.10239801555871964, "learning_rate": 7.94638192929131e-05, "loss": 10.1295, "step": 464 }, { "epoch": 0.014247305650665258, "grad_norm": 0.1152057871222496, "learning_rate": 7.938097236335386e-05, "loss": 10.1233, "step": 465 }, { "epoch": 0.014277945017655936, "grad_norm": 0.09764479100704193, "learning_rate": 7.929800204337294e-05, "loss": 10.1301, "step": 466 }, { "epoch": 0.014308584384646612, "grad_norm": 0.08168231695890427, "learning_rate": 7.921490868141843e-05, "loss": 10.1342, "step": 467 }, { "epoch": 0.01433922375163729, "grad_norm": 0.08545900136232376, "learning_rate": 7.91316926264551e-05, "loss": 10.1359, "step": 468 }, { "epoch": 0.014369863118627969, "grad_norm": 0.1341230720281601, "learning_rate": 7.904835422796302e-05, "loss": 10.1369, "step": 469 }, { "epoch": 0.014400502485618647, "grad_norm": 0.10103137791156769, "learning_rate": 7.896489383593606e-05, "loss": 10.1386, "step": 470 }, { "epoch": 0.014431141852609325, "grad_norm": 0.15637463331222534, "learning_rate": 7.888131180088042e-05, "loss": 10.1337, "step": 471 }, { "epoch": 0.014461781219600003, "grad_norm": 0.17479972541332245, "learning_rate": 7.879760847381315e-05, "loss": 10.1223, "step": 472 }, { "epoch": 0.014492420586590681, "grad_norm": 0.20918747782707214, "learning_rate": 7.871378420626072e-05, "loss": 10.1171, "step": 473 }, { "epoch": 0.01452305995358136, "grad_norm": 0.19822554290294647, "learning_rate": 7.862983935025745e-05, "loss": 10.1167, "step": 474 }, { "epoch": 0.014553699320572037, "grad_norm": 0.18799549341201782, "learning_rate": 7.854577425834418e-05, "loss": 10.124, "step": 475 }, { "epoch": 0.014584338687562716, "grad_norm": 0.20871472358703613, "learning_rate": 7.84615892835666e-05, "loss": 10.1154, "step": 476 }, { "epoch": 0.014614978054553394, "grad_norm": 0.1775389462709427, "learning_rate": 7.837728477947395e-05, "loss": 10.1157, "step": 477 }, { "epoch": 0.01464561742154407, "grad_norm": 0.20797564089298248, "learning_rate": 7.82928611001174e-05, "loss": 10.1188, "step": 478 }, { "epoch": 0.014676256788534748, "grad_norm": 0.235415518283844, "learning_rate": 7.820831860004867e-05, "loss": 10.1113, "step": 479 }, { "epoch": 0.014706896155525426, "grad_norm": 0.16740404069423676, "learning_rate": 7.812365763431843e-05, "loss": 10.1327, "step": 480 }, { "epoch": 0.014737535522516105, "grad_norm": 0.2017061710357666, "learning_rate": 7.803887855847489e-05, "loss": 10.1502, "step": 481 }, { "epoch": 0.014768174889506783, "grad_norm": 0.17415395379066467, "learning_rate": 7.795398172856233e-05, "loss": 10.1514, "step": 482 }, { "epoch": 0.01479881425649746, "grad_norm": 0.23232023417949677, "learning_rate": 7.786896750111947e-05, "loss": 10.1514, "step": 483 }, { "epoch": 0.014829453623488139, "grad_norm": 0.1606239676475525, "learning_rate": 7.778383623317813e-05, "loss": 10.1359, "step": 484 }, { "epoch": 0.014860092990478817, "grad_norm": 0.1336674839258194, "learning_rate": 7.769858828226164e-05, "loss": 10.1305, "step": 485 }, { "epoch": 0.014890732357469495, "grad_norm": 0.1792258471250534, "learning_rate": 7.761322400638335e-05, "loss": 10.1462, "step": 486 }, { "epoch": 0.014921371724460173, "grad_norm": 0.07546272873878479, "learning_rate": 7.752774376404516e-05, "loss": 10.118, "step": 487 }, { "epoch": 0.01495201109145085, "grad_norm": 0.11468010395765305, "learning_rate": 7.744214791423596e-05, "loss": 10.114, "step": 488 }, { "epoch": 0.014982650458441528, "grad_norm": 0.0878458023071289, "learning_rate": 7.735643681643019e-05, "loss": 10.1134, "step": 489 }, { "epoch": 0.015013289825432206, "grad_norm": 0.13913705945014954, "learning_rate": 7.727061083058624e-05, "loss": 10.1172, "step": 490 }, { "epoch": 0.015043929192422884, "grad_norm": 0.22441591322422028, "learning_rate": 7.718467031714506e-05, "loss": 10.108, "step": 491 }, { "epoch": 0.015074568559413562, "grad_norm": 0.20577554404735565, "learning_rate": 7.709861563702852e-05, "loss": 10.1144, "step": 492 }, { "epoch": 0.01510520792640424, "grad_norm": 0.17924779653549194, "learning_rate": 7.7012447151638e-05, "loss": 10.116, "step": 493 }, { "epoch": 0.015135847293394919, "grad_norm": 0.28341996669769287, "learning_rate": 7.692616522285278e-05, "loss": 10.1066, "step": 494 }, { "epoch": 0.015166486660385597, "grad_norm": 0.2298908233642578, "learning_rate": 7.68397702130286e-05, "loss": 10.1181, "step": 495 }, { "epoch": 0.015197126027376275, "grad_norm": 0.10151035338640213, "learning_rate": 7.675326248499606e-05, "loss": 10.1392, "step": 496 }, { "epoch": 0.015227765394366953, "grad_norm": 0.15986812114715576, "learning_rate": 7.666664240205922e-05, "loss": 10.1231, "step": 497 }, { "epoch": 0.015258404761357631, "grad_norm": 0.21760448813438416, "learning_rate": 7.65799103279939e-05, "loss": 10.122, "step": 498 }, { "epoch": 0.015289044128348308, "grad_norm": 0.27722373604774475, "learning_rate": 7.649306662704632e-05, "loss": 10.1347, "step": 499 }, { "epoch": 0.015319683495338986, "grad_norm": 0.21651680767536163, "learning_rate": 7.640611166393141e-05, "loss": 10.1215, "step": 500 }, { "epoch": 0.015350322862329664, "grad_norm": 0.18693667650222778, "learning_rate": 7.631904580383148e-05, "loss": 10.1581, "step": 501 }, { "epoch": 0.015380962229320342, "grad_norm": 0.19806598126888275, "learning_rate": 7.623186941239449e-05, "loss": 10.1474, "step": 502 }, { "epoch": 0.01541160159631102, "grad_norm": 0.28632038831710815, "learning_rate": 7.614458285573261e-05, "loss": 10.1397, "step": 503 }, { "epoch": 0.015442240963301698, "grad_norm": 0.13502807915210724, "learning_rate": 7.605718650042068e-05, "loss": 10.15, "step": 504 }, { "epoch": 0.015472880330292376, "grad_norm": 0.09862906485795975, "learning_rate": 7.596968071349464e-05, "loss": 10.1293, "step": 505 }, { "epoch": 0.015503519697283055, "grad_norm": 0.13603617250919342, "learning_rate": 7.588206586245002e-05, "loss": 10.1205, "step": 506 }, { "epoch": 0.015534159064273733, "grad_norm": 0.11580099910497665, "learning_rate": 7.579434231524038e-05, "loss": 10.1233, "step": 507 }, { "epoch": 0.01556479843126441, "grad_norm": 0.11220922321081161, "learning_rate": 7.570651044027576e-05, "loss": 10.1261, "step": 508 }, { "epoch": 0.015595437798255087, "grad_norm": 0.10228023678064346, "learning_rate": 7.56185706064212e-05, "loss": 10.1248, "step": 509 }, { "epoch": 0.015626077165245767, "grad_norm": 0.11997954547405243, "learning_rate": 7.5530523182995e-05, "loss": 10.1237, "step": 510 }, { "epoch": 0.015656716532236443, "grad_norm": 0.15541759133338928, "learning_rate": 7.544236853976747e-05, "loss": 10.1293, "step": 511 }, { "epoch": 0.015687355899227123, "grad_norm": 0.13872992992401123, "learning_rate": 7.535410704695906e-05, "loss": 10.1292, "step": 512 }, { "epoch": 0.0157179952662178, "grad_norm": 0.13870684802532196, "learning_rate": 7.526573907523904e-05, "loss": 10.1293, "step": 513 }, { "epoch": 0.01574863463320848, "grad_norm": 0.1145470067858696, "learning_rate": 7.517726499572381e-05, "loss": 10.13, "step": 514 }, { "epoch": 0.015779274000199156, "grad_norm": 0.13753440976142883, "learning_rate": 7.508868517997544e-05, "loss": 10.1263, "step": 515 }, { "epoch": 0.015809913367189832, "grad_norm": 0.10048335790634155, "learning_rate": 7.500000000000001e-05, "loss": 10.1281, "step": 516 }, { "epoch": 0.015840552734180512, "grad_norm": 0.13795413076877594, "learning_rate": 7.49112098282461e-05, "loss": 10.132, "step": 517 }, { "epoch": 0.01587119210117119, "grad_norm": 0.10451384633779526, "learning_rate": 7.482231503760325e-05, "loss": 10.1321, "step": 518 }, { "epoch": 0.01590183146816187, "grad_norm": 0.1328907608985901, "learning_rate": 7.473331600140032e-05, "loss": 10.1306, "step": 519 }, { "epoch": 0.015932470835152545, "grad_norm": 0.09811937063932419, "learning_rate": 7.464421309340402e-05, "loss": 10.1359, "step": 520 }, { "epoch": 0.015963110202143225, "grad_norm": 0.11520616710186005, "learning_rate": 7.455500668781726e-05, "loss": 10.1343, "step": 521 }, { "epoch": 0.0159937495691339, "grad_norm": 0.09560289978981018, "learning_rate": 7.446569715927759e-05, "loss": 10.1313, "step": 522 }, { "epoch": 0.01602438893612458, "grad_norm": 0.1667873114347458, "learning_rate": 7.437628488285568e-05, "loss": 10.1219, "step": 523 }, { "epoch": 0.016055028303115258, "grad_norm": 0.17636094987392426, "learning_rate": 7.428677023405366e-05, "loss": 10.1184, "step": 524 }, { "epoch": 0.016085667670105934, "grad_norm": 0.18078844249248505, "learning_rate": 7.419715358880363e-05, "loss": 10.1257, "step": 525 }, { "epoch": 0.016116307037096614, "grad_norm": 0.20024487376213074, "learning_rate": 7.410743532346605e-05, "loss": 10.1198, "step": 526 }, { "epoch": 0.01614694640408729, "grad_norm": 0.19297507405281067, "learning_rate": 7.40176158148281e-05, "loss": 10.1198, "step": 527 }, { "epoch": 0.01617758577107797, "grad_norm": 0.19732798635959625, "learning_rate": 7.392769544010219e-05, "loss": 10.1106, "step": 528 }, { "epoch": 0.016208225138068647, "grad_norm": 0.18131013214588165, "learning_rate": 7.383767457692433e-05, "loss": 10.1192, "step": 529 }, { "epoch": 0.016238864505059326, "grad_norm": 0.22036214172840118, "learning_rate": 7.374755360335253e-05, "loss": 10.1148, "step": 530 }, { "epoch": 0.016269503872050003, "grad_norm": 0.18976740539073944, "learning_rate": 7.365733289786523e-05, "loss": 10.1164, "step": 531 }, { "epoch": 0.016300143239040683, "grad_norm": 0.1878102421760559, "learning_rate": 7.356701283935975e-05, "loss": 10.1494, "step": 532 }, { "epoch": 0.01633078260603136, "grad_norm": 0.15749435126781464, "learning_rate": 7.347659380715061e-05, "loss": 10.1502, "step": 533 }, { "epoch": 0.01636142197302204, "grad_norm": 0.20585496723651886, "learning_rate": 7.338607618096802e-05, "loss": 10.1556, "step": 534 }, { "epoch": 0.016392061340012715, "grad_norm": 0.21954314410686493, "learning_rate": 7.329546034095624e-05, "loss": 10.1539, "step": 535 }, { "epoch": 0.016422700707003392, "grad_norm": 0.15135525166988373, "learning_rate": 7.320474666767201e-05, "loss": 10.1361, "step": 536 }, { "epoch": 0.01645334007399407, "grad_norm": 0.13717420399188995, "learning_rate": 7.311393554208292e-05, "loss": 10.1371, "step": 537 }, { "epoch": 0.016483979440984748, "grad_norm": 0.07186588644981384, "learning_rate": 7.302302734556582e-05, "loss": 10.1177, "step": 538 }, { "epoch": 0.016514618807975428, "grad_norm": 0.09196039289236069, "learning_rate": 7.293202245990526e-05, "loss": 10.1087, "step": 539 }, { "epoch": 0.016545258174966104, "grad_norm": 0.11627346277236938, "learning_rate": 7.284092126729181e-05, "loss": 10.1176, "step": 540 }, { "epoch": 0.016575897541956784, "grad_norm": 0.20991875231266022, "learning_rate": 7.274972415032054e-05, "loss": 10.1055, "step": 541 }, { "epoch": 0.01660653690894746, "grad_norm": 0.21396653354167938, "learning_rate": 7.265843149198931e-05, "loss": 10.1097, "step": 542 }, { "epoch": 0.01663717627593814, "grad_norm": 0.24687819182872772, "learning_rate": 7.256704367569731e-05, "loss": 10.1089, "step": 543 }, { "epoch": 0.016667815642928817, "grad_norm": 0.2213805615901947, "learning_rate": 7.247556108524329e-05, "loss": 10.1166, "step": 544 }, { "epoch": 0.016698455009919497, "grad_norm": 0.13963258266448975, "learning_rate": 7.238398410482408e-05, "loss": 10.1262, "step": 545 }, { "epoch": 0.016729094376910173, "grad_norm": 0.16775479912757874, "learning_rate": 7.229231311903282e-05, "loss": 10.1376, "step": 546 }, { "epoch": 0.01675973374390085, "grad_norm": 0.21375660598278046, "learning_rate": 7.220054851285755e-05, "loss": 10.122, "step": 547 }, { "epoch": 0.01679037311089153, "grad_norm": 0.22696495056152344, "learning_rate": 7.210869067167942e-05, "loss": 10.1323, "step": 548 }, { "epoch": 0.016821012477882206, "grad_norm": 0.30724745988845825, "learning_rate": 7.201673998127116e-05, "loss": 10.1402, "step": 549 }, { "epoch": 0.016851651844872886, "grad_norm": 0.26181256771087646, "learning_rate": 7.192469682779543e-05, "loss": 10.1185, "step": 550 }, { "epoch": 0.016882291211863562, "grad_norm": 0.191587433218956, "learning_rate": 7.18325615978032e-05, "loss": 10.157, "step": 551 }, { "epoch": 0.016912930578854242, "grad_norm": 0.3233880400657654, "learning_rate": 7.174033467823215e-05, "loss": 10.1395, "step": 552 }, { "epoch": 0.01694356994584492, "grad_norm": 0.15868274867534637, "learning_rate": 7.1648016456405e-05, "loss": 10.1516, "step": 553 }, { "epoch": 0.016974209312835598, "grad_norm": 0.1363263875246048, "learning_rate": 7.155560732002791e-05, "loss": 10.1496, "step": 554 }, { "epoch": 0.017004848679826275, "grad_norm": 0.10522077977657318, "learning_rate": 7.146310765718889e-05, "loss": 10.1379, "step": 555 }, { "epoch": 0.01703548804681695, "grad_norm": 0.10624691843986511, "learning_rate": 7.137051785635611e-05, "loss": 10.1191, "step": 556 }, { "epoch": 0.01706612741380763, "grad_norm": 0.1131395772099495, "learning_rate": 7.127783830637625e-05, "loss": 10.1204, "step": 557 }, { "epoch": 0.017096766780798307, "grad_norm": 0.1090913861989975, "learning_rate": 7.118506939647295e-05, "loss": 10.1257, "step": 558 }, { "epoch": 0.017127406147788987, "grad_norm": 0.08919420093297958, "learning_rate": 7.109221151624513e-05, "loss": 10.1243, "step": 559 }, { "epoch": 0.017158045514779664, "grad_norm": 0.11971846222877502, "learning_rate": 7.099926505566537e-05, "loss": 10.1273, "step": 560 }, { "epoch": 0.017188684881770343, "grad_norm": 0.1392238736152649, "learning_rate": 7.09062304050782e-05, "loss": 10.1341, "step": 561 }, { "epoch": 0.01721932424876102, "grad_norm": 0.13273583352565765, "learning_rate": 7.08131079551986e-05, "loss": 10.1306, "step": 562 }, { "epoch": 0.0172499636157517, "grad_norm": 0.13623562455177307, "learning_rate": 7.071989809711019e-05, "loss": 10.1324, "step": 563 }, { "epoch": 0.017280602982742376, "grad_norm": 0.1381106674671173, "learning_rate": 7.062660122226374e-05, "loss": 10.1268, "step": 564 }, { "epoch": 0.017311242349733056, "grad_norm": 0.18326221406459808, "learning_rate": 7.053321772247545e-05, "loss": 10.1245, "step": 565 }, { "epoch": 0.017341881716723732, "grad_norm": 0.1308203488588333, "learning_rate": 7.043974798992532e-05, "loss": 10.1325, "step": 566 }, { "epoch": 0.01737252108371441, "grad_norm": 0.11202985793352127, "learning_rate": 7.034619241715546e-05, "loss": 10.1327, "step": 567 }, { "epoch": 0.01740316045070509, "grad_norm": 0.13189643621444702, "learning_rate": 7.025255139706851e-05, "loss": 10.132, "step": 568 }, { "epoch": 0.017433799817695765, "grad_norm": 0.11403459310531616, "learning_rate": 7.015882532292598e-05, "loss": 10.1394, "step": 569 }, { "epoch": 0.017464439184686445, "grad_norm": 0.1777195781469345, "learning_rate": 7.006501458834655e-05, "loss": 10.1326, "step": 570 }, { "epoch": 0.01749507855167712, "grad_norm": 0.11264806240797043, "learning_rate": 6.997111958730444e-05, "loss": 10.1324, "step": 571 }, { "epoch": 0.0175257179186678, "grad_norm": 0.10327845811843872, "learning_rate": 6.98771407141278e-05, "loss": 10.1351, "step": 572 }, { "epoch": 0.017556357285658478, "grad_norm": 0.12043571472167969, "learning_rate": 6.978307836349699e-05, "loss": 10.1256, "step": 573 }, { "epoch": 0.017586996652649158, "grad_norm": 0.18653319776058197, "learning_rate": 6.968893293044291e-05, "loss": 10.1148, "step": 574 }, { "epoch": 0.017617636019639834, "grad_norm": 0.1647784560918808, "learning_rate": 6.959470481034547e-05, "loss": 10.116, "step": 575 }, { "epoch": 0.017648275386630514, "grad_norm": 0.18059369921684265, "learning_rate": 6.950039439893176e-05, "loss": 10.1231, "step": 576 }, { "epoch": 0.01767891475362119, "grad_norm": 0.1711346060037613, "learning_rate": 6.940600209227451e-05, "loss": 10.1179, "step": 577 }, { "epoch": 0.017709554120611867, "grad_norm": 0.18898466229438782, "learning_rate": 6.931152828679033e-05, "loss": 10.1191, "step": 578 }, { "epoch": 0.017740193487602546, "grad_norm": 0.19983327388763428, "learning_rate": 6.921697337923817e-05, "loss": 10.1127, "step": 579 }, { "epoch": 0.017770832854593223, "grad_norm": 0.2122073918581009, "learning_rate": 6.912233776671753e-05, "loss": 10.1106, "step": 580 }, { "epoch": 0.017801472221583903, "grad_norm": 0.1584252566099167, "learning_rate": 6.902762184666687e-05, "loss": 10.1206, "step": 581 }, { "epoch": 0.01783211158857458, "grad_norm": 0.10339947789907455, "learning_rate": 6.893282601686188e-05, "loss": 10.1293, "step": 582 }, { "epoch": 0.01786275095556526, "grad_norm": 0.16909275949001312, "learning_rate": 6.883795067541391e-05, "loss": 10.1523, "step": 583 }, { "epoch": 0.017893390322555935, "grad_norm": 0.17495974898338318, "learning_rate": 6.874299622076816e-05, "loss": 10.1458, "step": 584 }, { "epoch": 0.017924029689546615, "grad_norm": 0.202564999461174, "learning_rate": 6.864796305170214e-05, "loss": 10.1414, "step": 585 }, { "epoch": 0.01795466905653729, "grad_norm": 0.17011576890945435, "learning_rate": 6.855285156732389e-05, "loss": 10.1409, "step": 586 }, { "epoch": 0.01798530842352797, "grad_norm": 0.17535312473773956, "learning_rate": 6.845766216707037e-05, "loss": 10.1425, "step": 587 }, { "epoch": 0.018015947790518648, "grad_norm": 0.08041417598724365, "learning_rate": 6.836239525070575e-05, "loss": 10.1233, "step": 588 }, { "epoch": 0.018046587157509324, "grad_norm": 0.0948534905910492, "learning_rate": 6.826705121831976e-05, "loss": 10.1104, "step": 589 }, { "epoch": 0.018077226524500004, "grad_norm": 0.1422649323940277, "learning_rate": 6.817163047032598e-05, "loss": 10.1177, "step": 590 }, { "epoch": 0.01810786589149068, "grad_norm": 0.1527387946844101, "learning_rate": 6.807613340746016e-05, "loss": 10.1201, "step": 591 }, { "epoch": 0.01813850525848136, "grad_norm": 0.12443678081035614, "learning_rate": 6.798056043077858e-05, "loss": 10.1149, "step": 592 }, { "epoch": 0.018169144625472037, "grad_norm": 0.24807152152061462, "learning_rate": 6.78849119416563e-05, "loss": 10.1076, "step": 593 }, { "epoch": 0.018199783992462717, "grad_norm": 0.19028262794017792, "learning_rate": 6.77891883417855e-05, "loss": 10.1152, "step": 594 }, { "epoch": 0.018230423359453393, "grad_norm": 0.12494001537561417, "learning_rate": 6.769339003317383e-05, "loss": 10.129, "step": 595 }, { "epoch": 0.018261062726444073, "grad_norm": 0.10999981313943863, "learning_rate": 6.759751741814271e-05, "loss": 10.1198, "step": 596 }, { "epoch": 0.01829170209343475, "grad_norm": 0.19642069935798645, "learning_rate": 6.750157089932557e-05, "loss": 10.1252, "step": 597 }, { "epoch": 0.018322341460425426, "grad_norm": 0.21322087943553925, "learning_rate": 6.740555087966625e-05, "loss": 10.1335, "step": 598 }, { "epoch": 0.018352980827416106, "grad_norm": 0.26945269107818604, "learning_rate": 6.730945776241722e-05, "loss": 10.1252, "step": 599 }, { "epoch": 0.018383620194406782, "grad_norm": 0.23852071166038513, "learning_rate": 6.721329195113801e-05, "loss": 10.1144, "step": 600 }, { "epoch": 0.018414259561397462, "grad_norm": 0.23546016216278076, "learning_rate": 6.71170538496934e-05, "loss": 10.1514, "step": 601 }, { "epoch": 0.01844489892838814, "grad_norm": 0.1574869006872177, "learning_rate": 6.702074386225175e-05, "loss": 10.1295, "step": 602 }, { "epoch": 0.01847553829537882, "grad_norm": 0.293416827917099, "learning_rate": 6.692436239328332e-05, "loss": 10.14, "step": 603 }, { "epoch": 0.018506177662369495, "grad_norm": 0.18177177011966705, "learning_rate": 6.682790984755862e-05, "loss": 10.1533, "step": 604 }, { "epoch": 0.018536817029360175, "grad_norm": 0.15229305624961853, "learning_rate": 6.67313866301466e-05, "loss": 10.1602, "step": 605 }, { "epoch": 0.01856745639635085, "grad_norm": 0.08645322918891907, "learning_rate": 6.663479314641305e-05, "loss": 10.1257, "step": 606 }, { "epoch": 0.01859809576334153, "grad_norm": 0.13360869884490967, "learning_rate": 6.653812980201882e-05, "loss": 10.117, "step": 607 }, { "epoch": 0.018628735130332207, "grad_norm": 0.12092019617557526, "learning_rate": 6.644139700291817e-05, "loss": 10.1187, "step": 608 }, { "epoch": 0.018659374497322884, "grad_norm": 0.11550693213939667, "learning_rate": 6.634459515535703e-05, "loss": 10.1207, "step": 609 }, { "epoch": 0.018690013864313564, "grad_norm": 0.09900422394275665, "learning_rate": 6.624772466587134e-05, "loss": 10.1238, "step": 610 }, { "epoch": 0.01872065323130424, "grad_norm": 0.13152551651000977, "learning_rate": 6.615078594128531e-05, "loss": 10.1282, "step": 611 }, { "epoch": 0.01875129259829492, "grad_norm": 0.12042973935604095, "learning_rate": 6.605377938870968e-05, "loss": 10.1228, "step": 612 }, { "epoch": 0.018781931965285596, "grad_norm": 0.1463330239057541, "learning_rate": 6.59567054155401e-05, "loss": 10.1281, "step": 613 }, { "epoch": 0.018812571332276276, "grad_norm": 0.10764031112194061, "learning_rate": 6.585956442945532e-05, "loss": 10.1285, "step": 614 }, { "epoch": 0.018843210699266952, "grad_norm": 0.09036918729543686, "learning_rate": 6.57623568384155e-05, "loss": 10.126, "step": 615 }, { "epoch": 0.018873850066257632, "grad_norm": 0.10808084905147552, "learning_rate": 6.566508305066062e-05, "loss": 10.127, "step": 616 }, { "epoch": 0.01890448943324831, "grad_norm": 0.07309266924858093, "learning_rate": 6.556774347470855e-05, "loss": 10.1248, "step": 617 }, { "epoch": 0.01893512880023899, "grad_norm": 0.1577768623828888, "learning_rate": 6.547033851935351e-05, "loss": 10.1275, "step": 618 }, { "epoch": 0.018965768167229665, "grad_norm": 0.14701688289642334, "learning_rate": 6.537286859366429e-05, "loss": 10.1291, "step": 619 }, { "epoch": 0.01899640753422034, "grad_norm": 0.14103521406650543, "learning_rate": 6.52753341069825e-05, "loss": 10.13, "step": 620 }, { "epoch": 0.01902704690121102, "grad_norm": 0.06757157295942307, "learning_rate": 6.517773546892093e-05, "loss": 10.1348, "step": 621 }, { "epoch": 0.019057686268201698, "grad_norm": 0.09920302778482437, "learning_rate": 6.508007308936176e-05, "loss": 10.133, "step": 622 }, { "epoch": 0.019088325635192378, "grad_norm": 0.1432391107082367, "learning_rate": 6.498234737845488e-05, "loss": 10.1251, "step": 623 }, { "epoch": 0.019118965002183054, "grad_norm": 0.16380777955055237, "learning_rate": 6.48845587466161e-05, "loss": 10.115, "step": 624 }, { "epoch": 0.019149604369173734, "grad_norm": 0.16665424406528473, "learning_rate": 6.478670760452555e-05, "loss": 10.1186, "step": 625 }, { "epoch": 0.01918024373616441, "grad_norm": 0.18404386937618256, "learning_rate": 6.468879436312584e-05, "loss": 10.1195, "step": 626 }, { "epoch": 0.01921088310315509, "grad_norm": 0.17072229087352753, "learning_rate": 6.459081943362038e-05, "loss": 10.117, "step": 627 }, { "epoch": 0.019241522470145767, "grad_norm": 0.16598741710186005, "learning_rate": 6.449278322747163e-05, "loss": 10.1161, "step": 628 }, { "epoch": 0.019272161837136446, "grad_norm": 0.19128328561782837, "learning_rate": 6.439468615639946e-05, "loss": 10.1123, "step": 629 }, { "epoch": 0.019302801204127123, "grad_norm": 0.17472326755523682, "learning_rate": 6.429652863237927e-05, "loss": 10.1183, "step": 630 }, { "epoch": 0.0193334405711178, "grad_norm": 0.15719427168369293, "learning_rate": 6.419831106764042e-05, "loss": 10.1233, "step": 631 }, { "epoch": 0.01936407993810848, "grad_norm": 0.16873855888843536, "learning_rate": 6.410003387466433e-05, "loss": 10.1397, "step": 632 }, { "epoch": 0.019394719305099156, "grad_norm": 0.16857346892356873, "learning_rate": 6.400169746618294e-05, "loss": 10.1433, "step": 633 }, { "epoch": 0.019425358672089835, "grad_norm": 0.1567775160074234, "learning_rate": 6.39033022551768e-05, "loss": 10.1364, "step": 634 }, { "epoch": 0.019455998039080512, "grad_norm": 0.20178847014904022, "learning_rate": 6.380484865487347e-05, "loss": 10.1469, "step": 635 }, { "epoch": 0.01948663740607119, "grad_norm": 0.21367569267749786, "learning_rate": 6.370633707874563e-05, "loss": 10.146, "step": 636 }, { "epoch": 0.019517276773061868, "grad_norm": 0.09135627746582031, "learning_rate": 6.360776794050954e-05, "loss": 10.116, "step": 637 }, { "epoch": 0.019547916140052548, "grad_norm": 0.10811010748147964, "learning_rate": 6.35091416541232e-05, "loss": 10.1084, "step": 638 }, { "epoch": 0.019578555507043224, "grad_norm": 0.09787940233945847, "learning_rate": 6.341045863378452e-05, "loss": 10.1119, "step": 639 }, { "epoch": 0.0196091948740339, "grad_norm": 0.09531097859144211, "learning_rate": 6.331171929392976e-05, "loss": 10.113, "step": 640 }, { "epoch": 0.01963983424102458, "grad_norm": 0.17204657196998596, "learning_rate": 6.321292404923167e-05, "loss": 10.1048, "step": 641 }, { "epoch": 0.019670473608015257, "grad_norm": 0.23157557845115662, "learning_rate": 6.311407331459781e-05, "loss": 10.1032, "step": 642 }, { "epoch": 0.019701112975005937, "grad_norm": 0.24910658597946167, "learning_rate": 6.301516750516872e-05, "loss": 10.1013, "step": 643 }, { "epoch": 0.019731752341996613, "grad_norm": 0.24974915385246277, "learning_rate": 6.29162070363163e-05, "loss": 10.104, "step": 644 }, { "epoch": 0.019762391708987293, "grad_norm": 0.14382730424404144, "learning_rate": 6.281719232364196e-05, "loss": 10.1233, "step": 645 }, { "epoch": 0.01979303107597797, "grad_norm": 0.14875264465808868, "learning_rate": 6.271812378297495e-05, "loss": 10.1305, "step": 646 }, { "epoch": 0.01982367044296865, "grad_norm": 0.283819317817688, "learning_rate": 6.261900183037052e-05, "loss": 10.123, "step": 647 }, { "epoch": 0.019854309809959326, "grad_norm": 0.26025286316871643, "learning_rate": 6.251982688210833e-05, "loss": 10.1306, "step": 648 }, { "epoch": 0.019884949176950006, "grad_norm": 0.2539716362953186, "learning_rate": 6.242059935469051e-05, "loss": 10.1251, "step": 649 }, { "epoch": 0.019915588543940682, "grad_norm": 0.20857319235801697, "learning_rate": 6.232131966484006e-05, "loss": 10.1128, "step": 650 }, { "epoch": 0.01994622791093136, "grad_norm": 0.17503008246421814, "learning_rate": 6.222198822949902e-05, "loss": 10.1454, "step": 651 }, { "epoch": 0.01997686727792204, "grad_norm": 0.13125689327716827, "learning_rate": 6.212260546582675e-05, "loss": 10.1487, "step": 652 }, { "epoch": 0.020007506644912715, "grad_norm": 0.20821285247802734, "learning_rate": 6.202317179119817e-05, "loss": 10.1295, "step": 653 }, { "epoch": 0.020038146011903395, "grad_norm": 0.22660121321678162, "learning_rate": 6.192368762320203e-05, "loss": 10.155, "step": 654 }, { "epoch": 0.02006878537889407, "grad_norm": 0.16698142886161804, "learning_rate": 6.18241533796391e-05, "loss": 10.1379, "step": 655 }, { "epoch": 0.02009942474588475, "grad_norm": 0.11128538846969604, "learning_rate": 6.172456947852049e-05, "loss": 10.1265, "step": 656 }, { "epoch": 0.020130064112875427, "grad_norm": 0.11151152849197388, "learning_rate": 6.162493633806583e-05, "loss": 10.1215, "step": 657 }, { "epoch": 0.020160703479866107, "grad_norm": 0.09549431502819061, "learning_rate": 6.152525437670154e-05, "loss": 10.1172, "step": 658 }, { "epoch": 0.020191342846856784, "grad_norm": 0.1264229714870453, "learning_rate": 6.142552401305906e-05, "loss": 10.1208, "step": 659 }, { "epoch": 0.020221982213847463, "grad_norm": 0.11999394744634628, "learning_rate": 6.132574566597314e-05, "loss": 10.1236, "step": 660 }, { "epoch": 0.02025262158083814, "grad_norm": 0.12957274913787842, "learning_rate": 6.122591975448004e-05, "loss": 10.1278, "step": 661 }, { "epoch": 0.020283260947828816, "grad_norm": 0.1250484436750412, "learning_rate": 6.112604669781572e-05, "loss": 10.1298, "step": 662 }, { "epoch": 0.020313900314819496, "grad_norm": 0.12586240470409393, "learning_rate": 6.1026126915414215e-05, "loss": 10.1229, "step": 663 }, { "epoch": 0.020344539681810173, "grad_norm": 0.13281145691871643, "learning_rate": 6.0926160826905706e-05, "loss": 10.126, "step": 664 }, { "epoch": 0.020375179048800852, "grad_norm": 0.1286524087190628, "learning_rate": 6.0826148852114936e-05, "loss": 10.1245, "step": 665 }, { "epoch": 0.02040581841579153, "grad_norm": 0.1314413845539093, "learning_rate": 6.072609141105927e-05, "loss": 10.1218, "step": 666 }, { "epoch": 0.02043645778278221, "grad_norm": 0.09817996621131897, "learning_rate": 6.062598892394709e-05, "loss": 10.1236, "step": 667 }, { "epoch": 0.020467097149772885, "grad_norm": 0.13442109525203705, "learning_rate": 6.052584181117589e-05, "loss": 10.1281, "step": 668 }, { "epoch": 0.020497736516763565, "grad_norm": 0.14548683166503906, "learning_rate": 6.042565049333062e-05, "loss": 10.1346, "step": 669 }, { "epoch": 0.02052837588375424, "grad_norm": 0.10334555059671402, "learning_rate": 6.032541539118187e-05, "loss": 10.1301, "step": 670 }, { "epoch": 0.02055901525074492, "grad_norm": 0.07567421346902847, "learning_rate": 6.022513692568412e-05, "loss": 10.1266, "step": 671 }, { "epoch": 0.020589654617735598, "grad_norm": 0.12235136330127716, "learning_rate": 6.012481551797392e-05, "loss": 10.125, "step": 672 }, { "epoch": 0.020620293984726274, "grad_norm": 0.12901850044727325, "learning_rate": 6.0024451589368215e-05, "loss": 10.1248, "step": 673 }, { "epoch": 0.020650933351716954, "grad_norm": 0.1297163963317871, "learning_rate": 5.9924045561362474e-05, "loss": 10.1186, "step": 674 }, { "epoch": 0.02068157271870763, "grad_norm": 0.18924599885940552, "learning_rate": 5.982359785562902e-05, "loss": 10.1079, "step": 675 }, { "epoch": 0.02071221208569831, "grad_norm": 0.20187756419181824, "learning_rate": 5.9723108894015154e-05, "loss": 10.1154, "step": 676 }, { "epoch": 0.020742851452688987, "grad_norm": 0.18014749884605408, "learning_rate": 5.96225790985415e-05, "loss": 10.1099, "step": 677 }, { "epoch": 0.020773490819679667, "grad_norm": 0.21087810397148132, "learning_rate": 5.9522008891400125e-05, "loss": 10.1043, "step": 678 }, { "epoch": 0.020804130186670343, "grad_norm": 0.1960853487253189, "learning_rate": 5.9421398694952825e-05, "loss": 10.1237, "step": 679 }, { "epoch": 0.020834769553661023, "grad_norm": 0.1748495250940323, "learning_rate": 5.9320748931729344e-05, "loss": 10.1396, "step": 680 }, { "epoch": 0.0208654089206517, "grad_norm": 0.17134584486484528, "learning_rate": 5.922006002442556e-05, "loss": 10.1394, "step": 681 }, { "epoch": 0.020896048287642376, "grad_norm": 0.1944963037967682, "learning_rate": 5.911933239590182e-05, "loss": 10.152, "step": 682 }, { "epoch": 0.020926687654633055, "grad_norm": 0.2292083203792572, "learning_rate": 5.9018566469180994e-05, "loss": 10.1418, "step": 683 }, { "epoch": 0.020957327021623732, "grad_norm": 0.22954972088336945, "learning_rate": 5.891776266744686e-05, "loss": 10.1543, "step": 684 }, { "epoch": 0.020987966388614412, "grad_norm": 0.13839173316955566, "learning_rate": 5.881692141404223e-05, "loss": 10.1262, "step": 685 }, { "epoch": 0.021018605755605088, "grad_norm": 0.09933870285749435, "learning_rate": 5.87160431324672e-05, "loss": 10.1167, "step": 686 }, { "epoch": 0.021049245122595768, "grad_norm": 0.08382540941238403, "learning_rate": 5.8615128246377385e-05, "loss": 10.1112, "step": 687 }, { "epoch": 0.021079884489586444, "grad_norm": 0.08333944529294968, "learning_rate": 5.851417717958212e-05, "loss": 10.1076, "step": 688 }, { "epoch": 0.021110523856577124, "grad_norm": 0.19147875905036926, "learning_rate": 5.841319035604267e-05, "loss": 10.1033, "step": 689 }, { "epoch": 0.0211411632235678, "grad_norm": 0.23126104474067688, "learning_rate": 5.831216819987051e-05, "loss": 10.1026, "step": 690 }, { "epoch": 0.02117180259055848, "grad_norm": 0.21587802469730377, "learning_rate": 5.8211111135325445e-05, "loss": 10.1034, "step": 691 }, { "epoch": 0.021202441957549157, "grad_norm": 0.2145092636346817, "learning_rate": 5.8110019586813946e-05, "loss": 10.1062, "step": 692 }, { "epoch": 0.021233081324539833, "grad_norm": 0.18449415266513824, "learning_rate": 5.800889397888723e-05, "loss": 10.1149, "step": 693 }, { "epoch": 0.021263720691530513, "grad_norm": 0.16176313161849976, "learning_rate": 5.7907734736239636e-05, "loss": 10.1195, "step": 694 }, { "epoch": 0.02129436005852119, "grad_norm": 0.09578119963407516, "learning_rate": 5.780654228370669e-05, "loss": 10.1295, "step": 695 }, { "epoch": 0.02132499942551187, "grad_norm": 0.17082186043262482, "learning_rate": 5.770531704626342e-05, "loss": 10.1218, "step": 696 }, { "epoch": 0.021355638792502546, "grad_norm": 0.20365026593208313, "learning_rate": 5.760405944902253e-05, "loss": 10.1209, "step": 697 }, { "epoch": 0.021386278159493226, "grad_norm": 0.24216489493846893, "learning_rate": 5.7502769917232635e-05, "loss": 10.1271, "step": 698 }, { "epoch": 0.021416917526483902, "grad_norm": 0.23165273666381836, "learning_rate": 5.7401448876276475e-05, "loss": 10.1263, "step": 699 }, { "epoch": 0.021447556893474582, "grad_norm": 0.24220670759677887, "learning_rate": 5.7300096751669065e-05, "loss": 10.1125, "step": 700 }, { "epoch": 0.02147819626046526, "grad_norm": 0.25057968497276306, "learning_rate": 5.7198713969056026e-05, "loss": 10.1382, "step": 701 }, { "epoch": 0.02150883562745594, "grad_norm": 0.15875615179538727, "learning_rate": 5.7097300954211685e-05, "loss": 10.1331, "step": 702 }, { "epoch": 0.021539474994446615, "grad_norm": 0.448302298784256, "learning_rate": 5.699585813303737e-05, "loss": 10.1308, "step": 703 }, { "epoch": 0.02157011436143729, "grad_norm": 0.21265876293182373, "learning_rate": 5.689438593155956e-05, "loss": 10.1572, "step": 704 }, { "epoch": 0.02160075372842797, "grad_norm": 0.13801641762256622, "learning_rate": 5.679288477592815e-05, "loss": 10.1331, "step": 705 }, { "epoch": 0.021631393095418647, "grad_norm": 0.1071368157863617, "learning_rate": 5.669135509241457e-05, "loss": 10.1227, "step": 706 }, { "epoch": 0.021662032462409327, "grad_norm": 0.11840381473302841, "learning_rate": 5.658979730741014e-05, "loss": 10.12, "step": 707 }, { "epoch": 0.021692671829400004, "grad_norm": 0.12939777970314026, "learning_rate": 5.6488211847424143e-05, "loss": 10.1178, "step": 708 }, { "epoch": 0.021723311196390684, "grad_norm": 0.10849299281835556, "learning_rate": 5.6386599139082116e-05, "loss": 10.1154, "step": 709 }, { "epoch": 0.02175395056338136, "grad_norm": 0.13726995885372162, "learning_rate": 5.6284959609124e-05, "loss": 10.1169, "step": 710 }, { "epoch": 0.02178458993037204, "grad_norm": 0.11111027002334595, "learning_rate": 5.6183293684402413e-05, "loss": 10.1194, "step": 711 }, { "epoch": 0.021815229297362716, "grad_norm": 0.13127197325229645, "learning_rate": 5.608160179188079e-05, "loss": 10.1188, "step": 712 }, { "epoch": 0.021845868664353396, "grad_norm": 0.14980146288871765, "learning_rate": 5.597988435863166e-05, "loss": 10.1241, "step": 713 }, { "epoch": 0.021876508031344073, "grad_norm": 0.13704746961593628, "learning_rate": 5.587814181183475e-05, "loss": 10.1247, "step": 714 }, { "epoch": 0.02190714739833475, "grad_norm": 0.1472388654947281, "learning_rate": 5.577637457877535e-05, "loss": 10.1228, "step": 715 }, { "epoch": 0.02193778676532543, "grad_norm": 0.15377099812030792, "learning_rate": 5.567458308684232e-05, "loss": 10.1267, "step": 716 }, { "epoch": 0.021968426132316105, "grad_norm": 0.12637226283550262, "learning_rate": 5.557276776352648e-05, "loss": 10.1221, "step": 717 }, { "epoch": 0.021999065499306785, "grad_norm": 0.11990988999605179, "learning_rate": 5.5470929036418714e-05, "loss": 10.1264, "step": 718 }, { "epoch": 0.02202970486629746, "grad_norm": 0.14948558807373047, "learning_rate": 5.536906733320816e-05, "loss": 10.134, "step": 719 }, { "epoch": 0.02206034423328814, "grad_norm": 0.10016921907663345, "learning_rate": 5.526718308168048e-05, "loss": 10.1292, "step": 720 }, { "epoch": 0.022090983600278818, "grad_norm": 0.11993066221475601, "learning_rate": 5.516527670971604e-05, "loss": 10.1252, "step": 721 }, { "epoch": 0.022121622967269498, "grad_norm": 0.11004377901554108, "learning_rate": 5.506334864528808e-05, "loss": 10.1222, "step": 722 }, { "epoch": 0.022152262334260174, "grad_norm": 0.13959096372127533, "learning_rate": 5.496139931646094e-05, "loss": 10.1143, "step": 723 }, { "epoch": 0.02218290170125085, "grad_norm": 0.15570136904716492, "learning_rate": 5.4859429151388286e-05, "loss": 10.1124, "step": 724 }, { "epoch": 0.02221354106824153, "grad_norm": 0.1735779345035553, "learning_rate": 5.475743857831127e-05, "loss": 10.1102, "step": 725 }, { "epoch": 0.022244180435232207, "grad_norm": 0.20514556765556335, "learning_rate": 5.465542802555677e-05, "loss": 10.1113, "step": 726 }, { "epoch": 0.022274819802222887, "grad_norm": 0.19839249551296234, "learning_rate": 5.455339792153554e-05, "loss": 10.107, "step": 727 }, { "epoch": 0.022305459169213563, "grad_norm": 0.18769687414169312, "learning_rate": 5.445134869474049e-05, "loss": 10.114, "step": 728 }, { "epoch": 0.022336098536204243, "grad_norm": 0.19832435250282288, "learning_rate": 5.434928077374478e-05, "loss": 10.1083, "step": 729 }, { "epoch": 0.02236673790319492, "grad_norm": 0.19306580722332, "learning_rate": 5.4247194587200144e-05, "loss": 10.1014, "step": 730 }, { "epoch": 0.0223973772701856, "grad_norm": 0.12483774870634079, "learning_rate": 5.414509056383498e-05, "loss": 10.1296, "step": 731 }, { "epoch": 0.022428016637176276, "grad_norm": 0.17616842687129974, "learning_rate": 5.40429691324526e-05, "loss": 10.1329, "step": 732 }, { "epoch": 0.022458656004166955, "grad_norm": 0.22525690495967865, "learning_rate": 5.394083072192944e-05, "loss": 10.1578, "step": 733 }, { "epoch": 0.022489295371157632, "grad_norm": 0.2022257298231125, "learning_rate": 5.3838675761213244e-05, "loss": 10.136, "step": 734 }, { "epoch": 0.022519934738148308, "grad_norm": 0.16273309290409088, "learning_rate": 5.373650467932122e-05, "loss": 10.1317, "step": 735 }, { "epoch": 0.022550574105138988, "grad_norm": 0.1938069462776184, "learning_rate": 5.363431790533835e-05, "loss": 10.1394, "step": 736 }, { "epoch": 0.022581213472129665, "grad_norm": 0.0923578217625618, "learning_rate": 5.3532115868415464e-05, "loss": 10.1156, "step": 737 }, { "epoch": 0.022611852839120344, "grad_norm": 0.09481492638587952, "learning_rate": 5.342989899776749e-05, "loss": 10.1016, "step": 738 }, { "epoch": 0.02264249220611102, "grad_norm": 0.0936303362250328, "learning_rate": 5.3327667722671716e-05, "loss": 10.1034, "step": 739 }, { "epoch": 0.0226731315731017, "grad_norm": 0.10988948494195938, "learning_rate": 5.3225422472465824e-05, "loss": 10.1079, "step": 740 }, { "epoch": 0.022703770940092377, "grad_norm": 0.1450163871049881, "learning_rate": 5.3123163676546274e-05, "loss": 10.1089, "step": 741 }, { "epoch": 0.022734410307083057, "grad_norm": 0.21641017496585846, "learning_rate": 5.302089176436637e-05, "loss": 10.097, "step": 742 }, { "epoch": 0.022765049674073733, "grad_norm": 0.2382025420665741, "learning_rate": 5.29186071654345e-05, "loss": 10.1026, "step": 743 }, { "epoch": 0.022795689041064413, "grad_norm": 0.2453005313873291, "learning_rate": 5.2816310309312355e-05, "loss": 10.1046, "step": 744 }, { "epoch": 0.02282632840805509, "grad_norm": 0.14431630074977875, "learning_rate": 5.271400162561309e-05, "loss": 10.1247, "step": 745 }, { "epoch": 0.022856967775045766, "grad_norm": 0.17082853615283966, "learning_rate": 5.261168154399952e-05, "loss": 10.1149, "step": 746 }, { "epoch": 0.022887607142036446, "grad_norm": 0.2016887068748474, "learning_rate": 5.2509350494182365e-05, "loss": 10.125, "step": 747 }, { "epoch": 0.022918246509027122, "grad_norm": 0.27934160828590393, "learning_rate": 5.240700890591834e-05, "loss": 10.1174, "step": 748 }, { "epoch": 0.022948885876017802, "grad_norm": 0.3027397096157074, "learning_rate": 5.23046572090085e-05, "loss": 10.1242, "step": 749 }, { "epoch": 0.02297952524300848, "grad_norm": 0.27279090881347656, "learning_rate": 5.2202295833296275e-05, "loss": 10.126, "step": 750 }, { "epoch": 0.02301016460999916, "grad_norm": 0.11216757446527481, "learning_rate": 5.209992520866582e-05, "loss": 10.1422, "step": 751 }, { "epoch": 0.023040803976989835, "grad_norm": 0.37575918436050415, "learning_rate": 5.199754576504006e-05, "loss": 10.1338, "step": 752 }, { "epoch": 0.023071443343980515, "grad_norm": 0.2121380716562271, "learning_rate": 5.1895157932379004e-05, "loss": 10.1393, "step": 753 }, { "epoch": 0.02310208271097119, "grad_norm": 0.2344789355993271, "learning_rate": 5.1792762140677874e-05, "loss": 10.1611, "step": 754 }, { "epoch": 0.02313272207796187, "grad_norm": 0.11771821975708008, "learning_rate": 5.169035881996533e-05, "loss": 10.1285, "step": 755 }, { "epoch": 0.023163361444952547, "grad_norm": 0.10612226277589798, "learning_rate": 5.1587948400301624e-05, "loss": 10.1247, "step": 756 }, { "epoch": 0.023194000811943224, "grad_norm": 0.10430123656988144, "learning_rate": 5.1485531311776855e-05, "loss": 10.119, "step": 757 }, { "epoch": 0.023224640178933904, "grad_norm": 0.12679187953472137, "learning_rate": 5.138310798450912e-05, "loss": 10.1113, "step": 758 }, { "epoch": 0.02325527954592458, "grad_norm": 0.1273856908082962, "learning_rate": 5.1280678848642694e-05, "loss": 10.12, "step": 759 }, { "epoch": 0.02328591891291526, "grad_norm": 0.1182880625128746, "learning_rate": 5.117824433434627e-05, "loss": 10.1127, "step": 760 }, { "epoch": 0.023316558279905936, "grad_norm": 0.14215397834777832, "learning_rate": 5.1075804871811115e-05, "loss": 10.1222, "step": 761 }, { "epoch": 0.023347197646896616, "grad_norm": 0.12041570246219635, "learning_rate": 5.09733608912493e-05, "loss": 10.1276, "step": 762 }, { "epoch": 0.023377837013887293, "grad_norm": 0.1296558529138565, "learning_rate": 5.0870912822891824e-05, "loss": 10.1226, "step": 763 }, { "epoch": 0.023408476380877973, "grad_norm": 0.13056400418281555, "learning_rate": 5.076846109698693e-05, "loss": 10.1222, "step": 764 }, { "epoch": 0.02343911574786865, "grad_norm": 0.11678817123174667, "learning_rate": 5.0666006143798116e-05, "loss": 10.1212, "step": 765 }, { "epoch": 0.023469755114859325, "grad_norm": 0.14268644154071808, "learning_rate": 5.0563548393602546e-05, "loss": 10.1203, "step": 766 }, { "epoch": 0.023500394481850005, "grad_norm": 0.09883932769298553, "learning_rate": 5.046108827668903e-05, "loss": 10.1251, "step": 767 }, { "epoch": 0.02353103384884068, "grad_norm": 0.14595545828342438, "learning_rate": 5.035862622335641e-05, "loss": 10.1314, "step": 768 }, { "epoch": 0.02356167321583136, "grad_norm": 0.11617717146873474, "learning_rate": 5.0256162663911564e-05, "loss": 10.1291, "step": 769 }, { "epoch": 0.023592312582822038, "grad_norm": 0.14400389790534973, "learning_rate": 5.01536980286678e-05, "loss": 10.1217, "step": 770 }, { "epoch": 0.023622951949812718, "grad_norm": 0.1151750311255455, "learning_rate": 5.005123274794283e-05, "loss": 10.1246, "step": 771 }, { "epoch": 0.023653591316803394, "grad_norm": 0.1078348308801651, "learning_rate": 4.994876725205718e-05, "loss": 10.1153, "step": 772 }, { "epoch": 0.023684230683794074, "grad_norm": 0.14584331214427948, "learning_rate": 4.9846301971332234e-05, "loss": 10.1105, "step": 773 }, { "epoch": 0.02371487005078475, "grad_norm": 0.12614212930202484, "learning_rate": 4.974383733608845e-05, "loss": 10.111, "step": 774 }, { "epoch": 0.02374550941777543, "grad_norm": 0.17295652627944946, "learning_rate": 4.9641373776643616e-05, "loss": 10.1085, "step": 775 }, { "epoch": 0.023776148784766107, "grad_norm": 0.21182629466056824, "learning_rate": 4.9538911723310976e-05, "loss": 10.1099, "step": 776 }, { "epoch": 0.023806788151756783, "grad_norm": 0.18705573678016663, "learning_rate": 4.943645160639748e-05, "loss": 10.112, "step": 777 }, { "epoch": 0.023837427518747463, "grad_norm": 0.18547996878623962, "learning_rate": 4.9333993856201896e-05, "loss": 10.1052, "step": 778 }, { "epoch": 0.02386806688573814, "grad_norm": 0.17741180956363678, "learning_rate": 4.92315389030131e-05, "loss": 10.122, "step": 779 }, { "epoch": 0.02389870625272882, "grad_norm": 0.1806713193655014, "learning_rate": 4.912908717710818e-05, "loss": 10.1019, "step": 780 }, { "epoch": 0.023929345619719496, "grad_norm": 0.13920080661773682, "learning_rate": 4.902663910875072e-05, "loss": 10.1314, "step": 781 }, { "epoch": 0.023959984986710176, "grad_norm": 0.1813124269247055, "learning_rate": 4.892419512818889e-05, "loss": 10.1429, "step": 782 }, { "epoch": 0.023990624353700852, "grad_norm": 0.18634380400180817, "learning_rate": 4.882175566565375e-05, "loss": 10.1495, "step": 783 }, { "epoch": 0.024021263720691532, "grad_norm": 0.2652908265590668, "learning_rate": 4.8719321151357324e-05, "loss": 10.1638, "step": 784 }, { "epoch": 0.024051903087682208, "grad_norm": 0.20820124447345734, "learning_rate": 4.86168920154909e-05, "loss": 10.1403, "step": 785 }, { "epoch": 0.024082542454672888, "grad_norm": 0.1762118935585022, "learning_rate": 4.851446868822315e-05, "loss": 10.1336, "step": 786 }, { "epoch": 0.024113181821663564, "grad_norm": 0.1118907630443573, "learning_rate": 4.8412051599698394e-05, "loss": 10.1145, "step": 787 }, { "epoch": 0.02414382118865424, "grad_norm": 0.10061166435480118, "learning_rate": 4.830964118003468e-05, "loss": 10.1002, "step": 788 }, { "epoch": 0.02417446055564492, "grad_norm": 0.08521238714456558, "learning_rate": 4.8207237859322144e-05, "loss": 10.1044, "step": 789 }, { "epoch": 0.024205099922635597, "grad_norm": 0.19789263606071472, "learning_rate": 4.8104842067621e-05, "loss": 10.1053, "step": 790 }, { "epoch": 0.024235739289626277, "grad_norm": 0.20093722641468048, "learning_rate": 4.800245423495997e-05, "loss": 10.0998, "step": 791 }, { "epoch": 0.024266378656616953, "grad_norm": 0.22859030961990356, "learning_rate": 4.790007479133419e-05, "loss": 10.0985, "step": 792 }, { "epoch": 0.024297018023607633, "grad_norm": 0.21149761974811554, "learning_rate": 4.7797704166703744e-05, "loss": 10.0997, "step": 793 }, { "epoch": 0.02432765739059831, "grad_norm": 0.24846968054771423, "learning_rate": 4.769534279099152e-05, "loss": 10.0994, "step": 794 }, { "epoch": 0.02435829675758899, "grad_norm": 0.20187105238437653, "learning_rate": 4.7592991094081676e-05, "loss": 10.1113, "step": 795 }, { "epoch": 0.024388936124579666, "grad_norm": 0.13730686902999878, "learning_rate": 4.749064950581765e-05, "loss": 10.1258, "step": 796 }, { "epoch": 0.024419575491570346, "grad_norm": 0.23561665415763855, "learning_rate": 4.7388318456000496e-05, "loss": 10.1145, "step": 797 }, { "epoch": 0.024450214858561022, "grad_norm": 0.18721893429756165, "learning_rate": 4.728599837438692e-05, "loss": 10.1323, "step": 798 }, { "epoch": 0.0244808542255517, "grad_norm": 0.3149273991584778, "learning_rate": 4.718368969068766e-05, "loss": 10.1201, "step": 799 }, { "epoch": 0.02451149359254238, "grad_norm": 0.28349021077156067, "learning_rate": 4.708139283456551e-05, "loss": 10.1096, "step": 800 }, { "epoch": 0.024542132959533055, "grad_norm": 0.20028243958950043, "learning_rate": 4.697910823563365e-05, "loss": 10.1352, "step": 801 }, { "epoch": 0.024572772326523735, "grad_norm": 0.35270899534225464, "learning_rate": 4.687683632345374e-05, "loss": 10.1473, "step": 802 }, { "epoch": 0.02460341169351441, "grad_norm": 0.22278332710266113, "learning_rate": 4.6774577527534195e-05, "loss": 10.1484, "step": 803 }, { "epoch": 0.02463405106050509, "grad_norm": 0.15622343122959137, "learning_rate": 4.66723322773283e-05, "loss": 10.1315, "step": 804 }, { "epoch": 0.024664690427495767, "grad_norm": 0.1648048758506775, "learning_rate": 4.6570101002232514e-05, "loss": 10.1436, "step": 805 }, { "epoch": 0.024695329794486447, "grad_norm": 0.1094522550702095, "learning_rate": 4.646788413158455e-05, "loss": 10.1199, "step": 806 }, { "epoch": 0.024725969161477124, "grad_norm": 0.11917233467102051, "learning_rate": 4.6365682094661664e-05, "loss": 10.1107, "step": 807 }, { "epoch": 0.0247566085284678, "grad_norm": 0.12444297224283218, "learning_rate": 4.626349532067879e-05, "loss": 10.1099, "step": 808 }, { "epoch": 0.02478724789545848, "grad_norm": 0.13644307851791382, "learning_rate": 4.616132423878679e-05, "loss": 10.1139, "step": 809 }, { "epoch": 0.024817887262449156, "grad_norm": 0.1131858229637146, "learning_rate": 4.605916927807057e-05, "loss": 10.1118, "step": 810 }, { "epoch": 0.024848526629439836, "grad_norm": 0.11814561486244202, "learning_rate": 4.5957030867547424e-05, "loss": 10.114, "step": 811 }, { "epoch": 0.024879165996430513, "grad_norm": 0.11740537732839584, "learning_rate": 4.585490943616504e-05, "loss": 10.1187, "step": 812 }, { "epoch": 0.024909805363421193, "grad_norm": 0.15036876499652863, "learning_rate": 4.5752805412799874e-05, "loss": 10.1239, "step": 813 }, { "epoch": 0.02494044473041187, "grad_norm": 0.10798177868127823, "learning_rate": 4.565071922625523e-05, "loss": 10.117, "step": 814 }, { "epoch": 0.02497108409740255, "grad_norm": 0.13662971556186676, "learning_rate": 4.554865130525953e-05, "loss": 10.1198, "step": 815 }, { "epoch": 0.025001723464393225, "grad_norm": 0.1336485594511032, "learning_rate": 4.5446602078464475e-05, "loss": 10.1187, "step": 816 }, { "epoch": 0.025032362831383905, "grad_norm": 0.12021537125110626, "learning_rate": 4.534457197444325e-05, "loss": 10.1235, "step": 817 }, { "epoch": 0.02506300219837458, "grad_norm": 0.13009947538375854, "learning_rate": 4.524256142168874e-05, "loss": 10.1228, "step": 818 }, { "epoch": 0.025093641565365258, "grad_norm": 0.2030557543039322, "learning_rate": 4.514057084861173e-05, "loss": 10.1191, "step": 819 }, { "epoch": 0.025124280932355938, "grad_norm": 0.10881420969963074, "learning_rate": 4.5038600683539074e-05, "loss": 10.1299, "step": 820 }, { "epoch": 0.025154920299346614, "grad_norm": 0.1462603062391281, "learning_rate": 4.4936651354711946e-05, "loss": 10.1167, "step": 821 }, { "epoch": 0.025185559666337294, "grad_norm": 0.10107901692390442, "learning_rate": 4.483472329028397e-05, "loss": 10.1123, "step": 822 }, { "epoch": 0.02521619903332797, "grad_norm": 0.13641050457954407, "learning_rate": 4.473281691831953e-05, "loss": 10.1058, "step": 823 }, { "epoch": 0.02524683840031865, "grad_norm": 0.17213523387908936, "learning_rate": 4.463093266679185e-05, "loss": 10.112, "step": 824 }, { "epoch": 0.025277477767309327, "grad_norm": 0.19258227944374084, "learning_rate": 4.452907096358131e-05, "loss": 10.1092, "step": 825 }, { "epoch": 0.025308117134300007, "grad_norm": 0.19735084474086761, "learning_rate": 4.442723223647353e-05, "loss": 10.1009, "step": 826 }, { "epoch": 0.025338756501290683, "grad_norm": 0.19507132470607758, "learning_rate": 4.4325416913157704e-05, "loss": 10.1017, "step": 827 }, { "epoch": 0.025369395868281363, "grad_norm": 0.18662738800048828, "learning_rate": 4.422362542122466e-05, "loss": 10.101, "step": 828 }, { "epoch": 0.02540003523527204, "grad_norm": 0.19229738414287567, "learning_rate": 4.4121858188165266e-05, "loss": 10.106, "step": 829 }, { "epoch": 0.025430674602262716, "grad_norm": 0.19341525435447693, "learning_rate": 4.402011564136836e-05, "loss": 10.1395, "step": 830 }, { "epoch": 0.025461313969253396, "grad_norm": 0.17634877562522888, "learning_rate": 4.3918398208119225e-05, "loss": 10.132, "step": 831 }, { "epoch": 0.025491953336244072, "grad_norm": 0.18567730486392975, "learning_rate": 4.381670631559759e-05, "loss": 10.1347, "step": 832 }, { "epoch": 0.025522592703234752, "grad_norm": 0.14753611385822296, "learning_rate": 4.371504039087602e-05, "loss": 10.1273, "step": 833 }, { "epoch": 0.02555323207022543, "grad_norm": 0.2018500566482544, "learning_rate": 4.361340086091789e-05, "loss": 10.1358, "step": 834 }, { "epoch": 0.025583871437216108, "grad_norm": 0.09290245175361633, "learning_rate": 4.3511788152575875e-05, "loss": 10.1135, "step": 835 }, { "epoch": 0.025614510804206785, "grad_norm": 0.08930160105228424, "learning_rate": 4.341020269258987e-05, "loss": 10.1128, "step": 836 }, { "epoch": 0.025645150171197464, "grad_norm": 0.09823785722255707, "learning_rate": 4.330864490758546e-05, "loss": 10.1001, "step": 837 }, { "epoch": 0.02567578953818814, "grad_norm": 0.09049481898546219, "learning_rate": 4.320711522407187e-05, "loss": 10.101, "step": 838 }, { "epoch": 0.02570642890517882, "grad_norm": 0.1584770828485489, "learning_rate": 4.310561406844045e-05, "loss": 10.1001, "step": 839 }, { "epoch": 0.025737068272169497, "grad_norm": 0.17950108647346497, "learning_rate": 4.300414186696264e-05, "loss": 10.0947, "step": 840 }, { "epoch": 0.025767707639160174, "grad_norm": 0.2538093328475952, "learning_rate": 4.290269904578833e-05, "loss": 10.0954, "step": 841 }, { "epoch": 0.025798347006150853, "grad_norm": 0.21318675577640533, "learning_rate": 4.2801286030943985e-05, "loss": 10.1047, "step": 842 }, { "epoch": 0.02582898637314153, "grad_norm": 0.21681830286979675, "learning_rate": 4.269990324833095e-05, "loss": 10.1013, "step": 843 }, { "epoch": 0.02585962574013221, "grad_norm": 0.11876737326383591, "learning_rate": 4.259855112372354e-05, "loss": 10.1131, "step": 844 }, { "epoch": 0.025890265107122886, "grad_norm": 0.12078375369310379, "learning_rate": 4.249723008276737e-05, "loss": 10.1235, "step": 845 }, { "epoch": 0.025920904474113566, "grad_norm": 0.16376064717769623, "learning_rate": 4.239594055097748e-05, "loss": 10.1173, "step": 846 }, { "epoch": 0.025951543841104242, "grad_norm": 0.18515519797801971, "learning_rate": 4.22946829537366e-05, "loss": 10.1171, "step": 847 }, { "epoch": 0.025982183208094922, "grad_norm": 0.21288609504699707, "learning_rate": 4.219345771629333e-05, "loss": 10.1162, "step": 848 }, { "epoch": 0.0260128225750856, "grad_norm": 0.27389636635780334, "learning_rate": 4.209226526376038e-05, "loss": 10.1087, "step": 849 }, { "epoch": 0.026043461942076275, "grad_norm": 0.24797745048999786, "learning_rate": 4.199110602111278e-05, "loss": 10.1051, "step": 850 }, { "epoch": 0.026074101309066955, "grad_norm": 0.17316637933254242, "learning_rate": 4.188998041318608e-05, "loss": 10.1524, "step": 851 }, { "epoch": 0.02610474067605763, "grad_norm": 0.33595332503318787, "learning_rate": 4.1788888864674566e-05, "loss": 10.1542, "step": 852 }, { "epoch": 0.02613538004304831, "grad_norm": 0.2212853878736496, "learning_rate": 4.168783180012952e-05, "loss": 10.1519, "step": 853 }, { "epoch": 0.026166019410038988, "grad_norm": 0.1778721809387207, "learning_rate": 4.1586809643957345e-05, "loss": 10.1236, "step": 854 }, { "epoch": 0.026196658777029667, "grad_norm": 0.15751956403255463, "learning_rate": 4.148582282041791e-05, "loss": 10.112, "step": 855 }, { "epoch": 0.026227298144020344, "grad_norm": 0.10044300556182861, "learning_rate": 4.138487175362263e-05, "loss": 10.112, "step": 856 }, { "epoch": 0.026257937511011024, "grad_norm": 0.12111388891935349, "learning_rate": 4.128395686753282e-05, "loss": 10.1099, "step": 857 }, { "epoch": 0.0262885768780017, "grad_norm": 0.11351887136697769, "learning_rate": 4.1183078585957784e-05, "loss": 10.1116, "step": 858 }, { "epoch": 0.02631921624499238, "grad_norm": 0.1124858632683754, "learning_rate": 4.108223733255316e-05, "loss": 10.1105, "step": 859 }, { "epoch": 0.026349855611983056, "grad_norm": 0.11475300788879395, "learning_rate": 4.098143353081902e-05, "loss": 10.1191, "step": 860 }, { "epoch": 0.026380494978973733, "grad_norm": 0.11222349852323532, "learning_rate": 4.0880667604098205e-05, "loss": 10.1191, "step": 861 }, { "epoch": 0.026411134345964413, "grad_norm": 0.12875118851661682, "learning_rate": 4.0779939975574445e-05, "loss": 10.1147, "step": 862 }, { "epoch": 0.02644177371295509, "grad_norm": 0.1210048496723175, "learning_rate": 4.067925106827068e-05, "loss": 10.1191, "step": 863 }, { "epoch": 0.02647241307994577, "grad_norm": 0.12404125183820724, "learning_rate": 4.057860130504719e-05, "loss": 10.1146, "step": 864 }, { "epoch": 0.026503052446936445, "grad_norm": 0.09907523542642593, "learning_rate": 4.0477991108599886e-05, "loss": 10.1219, "step": 865 }, { "epoch": 0.026533691813927125, "grad_norm": 0.09885027259588242, "learning_rate": 4.0377420901458506e-05, "loss": 10.1189, "step": 866 }, { "epoch": 0.0265643311809178, "grad_norm": 0.1033157929778099, "learning_rate": 4.027689110598486e-05, "loss": 10.1198, "step": 867 }, { "epoch": 0.02659497054790848, "grad_norm": 0.1452263593673706, "learning_rate": 4.017640214437099e-05, "loss": 10.1182, "step": 868 }, { "epoch": 0.026625609914899158, "grad_norm": 0.16847018897533417, "learning_rate": 4.0075954438637545e-05, "loss": 10.1229, "step": 869 }, { "epoch": 0.026656249281889838, "grad_norm": 0.0920506939291954, "learning_rate": 3.9975548410631796e-05, "loss": 10.1211, "step": 870 }, { "epoch": 0.026686888648880514, "grad_norm": 0.10733752697706223, "learning_rate": 3.98751844820261e-05, "loss": 10.1135, "step": 871 }, { "epoch": 0.02671752801587119, "grad_norm": 0.13539202511310577, "learning_rate": 3.977486307431589e-05, "loss": 10.1204, "step": 872 }, { "epoch": 0.02674816738286187, "grad_norm": 0.15287776291370392, "learning_rate": 3.967458460881814e-05, "loss": 10.11, "step": 873 }, { "epoch": 0.026778806749852547, "grad_norm": 0.1812770813703537, "learning_rate": 3.9574349506669385e-05, "loss": 10.1102, "step": 874 }, { "epoch": 0.026809446116843227, "grad_norm": 0.192267507314682, "learning_rate": 3.947415818882414e-05, "loss": 10.1073, "step": 875 }, { "epoch": 0.026840085483833903, "grad_norm": 0.1803596317768097, "learning_rate": 3.937401107605292e-05, "loss": 10.1091, "step": 876 }, { "epoch": 0.026870724850824583, "grad_norm": 0.16590607166290283, "learning_rate": 3.9273908588940747e-05, "loss": 10.1005, "step": 877 }, { "epoch": 0.02690136421781526, "grad_norm": 0.1811617761850357, "learning_rate": 3.9173851147885075e-05, "loss": 10.1034, "step": 878 }, { "epoch": 0.02693200358480594, "grad_norm": 0.21404416859149933, "learning_rate": 3.90738391730943e-05, "loss": 10.1063, "step": 879 }, { "epoch": 0.026962642951796616, "grad_norm": 0.12020877003669739, "learning_rate": 3.89738730845858e-05, "loss": 10.1235, "step": 880 }, { "epoch": 0.026993282318787296, "grad_norm": 0.1766115128993988, "learning_rate": 3.887395330218429e-05, "loss": 10.1278, "step": 881 }, { "epoch": 0.027023921685777972, "grad_norm": 0.15202757716178894, "learning_rate": 3.8774080245519964e-05, "loss": 10.1325, "step": 882 }, { "epoch": 0.02705456105276865, "grad_norm": 0.1784946620464325, "learning_rate": 3.867425433402686e-05, "loss": 10.1447, "step": 883 }, { "epoch": 0.027085200419759328, "grad_norm": 0.1652417778968811, "learning_rate": 3.857447598694094e-05, "loss": 10.1291, "step": 884 }, { "epoch": 0.027115839786750005, "grad_norm": 0.16154542565345764, "learning_rate": 3.847474562329848e-05, "loss": 10.1267, "step": 885 }, { "epoch": 0.027146479153740685, "grad_norm": 0.12061164528131485, "learning_rate": 3.837506366193418e-05, "loss": 10.1197, "step": 886 }, { "epoch": 0.02717711852073136, "grad_norm": 0.07533275336027145, "learning_rate": 3.827543052147952e-05, "loss": 10.1028, "step": 887 }, { "epoch": 0.02720775788772204, "grad_norm": 0.07370825111865997, "learning_rate": 3.81758466203609e-05, "loss": 10.1021, "step": 888 }, { "epoch": 0.027238397254712717, "grad_norm": 0.19061577320098877, "learning_rate": 3.8076312376797985e-05, "loss": 10.0953, "step": 889 }, { "epoch": 0.027269036621703397, "grad_norm": 0.18746474385261536, "learning_rate": 3.797682820880184e-05, "loss": 10.1041, "step": 890 }, { "epoch": 0.027299675988694073, "grad_norm": 0.16970083117485046, "learning_rate": 3.787739453417327e-05, "loss": 10.1041, "step": 891 }, { "epoch": 0.02733031535568475, "grad_norm": 0.22540439665317535, "learning_rate": 3.7778011770501e-05, "loss": 10.0936, "step": 892 }, { "epoch": 0.02736095472267543, "grad_norm": 0.24792306125164032, "learning_rate": 3.7678680335159954e-05, "loss": 10.0955, "step": 893 }, { "epoch": 0.027391594089666106, "grad_norm": 0.19680410623550415, "learning_rate": 3.75794006453095e-05, "loss": 10.1033, "step": 894 }, { "epoch": 0.027422233456656786, "grad_norm": 0.1112222820520401, "learning_rate": 3.748017311789168e-05, "loss": 10.1145, "step": 895 }, { "epoch": 0.027452872823647462, "grad_norm": 0.2534521222114563, "learning_rate": 3.7380998169629476e-05, "loss": 10.1206, "step": 896 }, { "epoch": 0.027483512190638142, "grad_norm": 0.2571105360984802, "learning_rate": 3.7281876217025075e-05, "loss": 10.1104, "step": 897 }, { "epoch": 0.02751415155762882, "grad_norm": 0.23824389278888702, "learning_rate": 3.718280767635805e-05, "loss": 10.1172, "step": 898 }, { "epoch": 0.0275447909246195, "grad_norm": 0.2788489758968353, "learning_rate": 3.708379296368372e-05, "loss": 10.1093, "step": 899 }, { "epoch": 0.027575430291610175, "grad_norm": 0.2438644915819168, "learning_rate": 3.698483249483129e-05, "loss": 10.1089, "step": 900 }, { "epoch": 0.027606069658600855, "grad_norm": 0.16509242355823517, "learning_rate": 3.688592668540221e-05, "loss": 10.1239, "step": 901 }, { "epoch": 0.02763670902559153, "grad_norm": 0.1801857203245163, "learning_rate": 3.678707595076834e-05, "loss": 10.1627, "step": 902 }, { "epoch": 0.027667348392582208, "grad_norm": 0.2536775469779968, "learning_rate": 3.668828070607026e-05, "loss": 10.125, "step": 903 }, { "epoch": 0.027697987759572888, "grad_norm": 0.2195262312889099, "learning_rate": 3.65895413662155e-05, "loss": 10.1547, "step": 904 }, { "epoch": 0.027728627126563564, "grad_norm": 0.20945961773395538, "learning_rate": 3.649085834587683e-05, "loss": 10.1289, "step": 905 }, { "epoch": 0.027759266493554244, "grad_norm": 0.18177199363708496, "learning_rate": 3.639223205949046e-05, "loss": 10.1148, "step": 906 }, { "epoch": 0.02778990586054492, "grad_norm": 0.10026376694440842, "learning_rate": 3.6293662921254396e-05, "loss": 10.1159, "step": 907 }, { "epoch": 0.0278205452275356, "grad_norm": 0.10826322436332703, "learning_rate": 3.619515134512656e-05, "loss": 10.1051, "step": 908 }, { "epoch": 0.027851184594526276, "grad_norm": 0.09625968337059021, "learning_rate": 3.609669774482322e-05, "loss": 10.1118, "step": 909 }, { "epoch": 0.027881823961516956, "grad_norm": 0.1060018241405487, "learning_rate": 3.5998302533817066e-05, "loss": 10.1114, "step": 910 }, { "epoch": 0.027912463328507633, "grad_norm": 0.09621276706457138, "learning_rate": 3.589996612533568e-05, "loss": 10.1117, "step": 911 }, { "epoch": 0.027943102695498313, "grad_norm": 0.13400667905807495, "learning_rate": 3.58016889323596e-05, "loss": 10.1154, "step": 912 }, { "epoch": 0.02797374206248899, "grad_norm": 0.15629635751247406, "learning_rate": 3.5703471367620744e-05, "loss": 10.1203, "step": 913 }, { "epoch": 0.028004381429479665, "grad_norm": 0.12304730713367462, "learning_rate": 3.560531384360055e-05, "loss": 10.1171, "step": 914 }, { "epoch": 0.028035020796470345, "grad_norm": 0.13428464531898499, "learning_rate": 3.550721677252839e-05, "loss": 10.1194, "step": 915 }, { "epoch": 0.02806566016346102, "grad_norm": 0.12355712056159973, "learning_rate": 3.540918056637964e-05, "loss": 10.1182, "step": 916 }, { "epoch": 0.0280962995304517, "grad_norm": 0.11500285565853119, "learning_rate": 3.531120563687419e-05, "loss": 10.1159, "step": 917 }, { "epoch": 0.028126938897442378, "grad_norm": 0.14029541611671448, "learning_rate": 3.5213292395474454e-05, "loss": 10.1265, "step": 918 }, { "epoch": 0.028157578264433058, "grad_norm": 0.1029583215713501, "learning_rate": 3.511544125338392e-05, "loss": 10.1194, "step": 919 }, { "epoch": 0.028188217631423734, "grad_norm": 0.08695020526647568, "learning_rate": 3.501765262154513e-05, "loss": 10.1222, "step": 920 }, { "epoch": 0.028218856998414414, "grad_norm": 0.0980026125907898, "learning_rate": 3.4919926910638246e-05, "loss": 10.1253, "step": 921 }, { "epoch": 0.02824949636540509, "grad_norm": 0.17090702056884766, "learning_rate": 3.4822264531079075e-05, "loss": 10.1069, "step": 922 }, { "epoch": 0.02828013573239577, "grad_norm": 0.16013272106647491, "learning_rate": 3.472466589301751e-05, "loss": 10.1091, "step": 923 }, { "epoch": 0.028310775099386447, "grad_norm": 0.17640572786331177, "learning_rate": 3.4627131406335736e-05, "loss": 10.1063, "step": 924 }, { "epoch": 0.028341414466377123, "grad_norm": 0.16549858450889587, "learning_rate": 3.452966148064651e-05, "loss": 10.1078, "step": 925 }, { "epoch": 0.028372053833367803, "grad_norm": 0.17138153314590454, "learning_rate": 3.4432256525291465e-05, "loss": 10.1054, "step": 926 }, { "epoch": 0.02840269320035848, "grad_norm": 0.1730426400899887, "learning_rate": 3.43349169493394e-05, "loss": 10.1036, "step": 927 }, { "epoch": 0.02843333256734916, "grad_norm": 0.153038889169693, "learning_rate": 3.42376431615845e-05, "loss": 10.1021, "step": 928 }, { "epoch": 0.028463971934339836, "grad_norm": 0.1873427778482437, "learning_rate": 3.41404355705447e-05, "loss": 10.0996, "step": 929 }, { "epoch": 0.028494611301330516, "grad_norm": 0.16789069771766663, "learning_rate": 3.4043294584459906e-05, "loss": 10.1227, "step": 930 }, { "epoch": 0.028525250668321192, "grad_norm": 0.13221538066864014, "learning_rate": 3.394622061129033e-05, "loss": 10.1343, "step": 931 }, { "epoch": 0.028555890035311872, "grad_norm": 0.17641599476337433, "learning_rate": 3.3849214058714704e-05, "loss": 10.1248, "step": 932 }, { "epoch": 0.02858652940230255, "grad_norm": 0.13553400337696075, "learning_rate": 3.375227533412868e-05, "loss": 10.132, "step": 933 }, { "epoch": 0.028617168769293225, "grad_norm": 0.2523645758628845, "learning_rate": 3.3655404844642994e-05, "loss": 10.146, "step": 934 }, { "epoch": 0.028647808136283905, "grad_norm": 0.18830083310604095, "learning_rate": 3.3558602997081866e-05, "loss": 10.1328, "step": 935 }, { "epoch": 0.02867844750327458, "grad_norm": 0.0748366117477417, "learning_rate": 3.34618701979812e-05, "loss": 10.0998, "step": 936 }, { "epoch": 0.02870908687026526, "grad_norm": 0.08600018173456192, "learning_rate": 3.336520685358697e-05, "loss": 10.1056, "step": 937 }, { "epoch": 0.028739726237255937, "grad_norm": 0.0936102494597435, "learning_rate": 3.326861336985341e-05, "loss": 10.0962, "step": 938 }, { "epoch": 0.028770365604246617, "grad_norm": 0.12793132662773132, "learning_rate": 3.31720901524414e-05, "loss": 10.0968, "step": 939 }, { "epoch": 0.028801004971237294, "grad_norm": 0.20576781034469604, "learning_rate": 3.307563760671669e-05, "loss": 10.1036, "step": 940 }, { "epoch": 0.028831644338227973, "grad_norm": 0.19139207899570465, "learning_rate": 3.297925613774828e-05, "loss": 10.1001, "step": 941 }, { "epoch": 0.02886228370521865, "grad_norm": 0.18637914955615997, "learning_rate": 3.288294615030662e-05, "loss": 10.1, "step": 942 }, { "epoch": 0.02889292307220933, "grad_norm": 0.23087814450263977, "learning_rate": 3.2786708048862e-05, "loss": 10.1024, "step": 943 }, { "epoch": 0.028923562439200006, "grad_norm": 0.21617059409618378, "learning_rate": 3.269054223758279e-05, "loss": 10.1094, "step": 944 }, { "epoch": 0.028954201806190683, "grad_norm": 0.11475612223148346, "learning_rate": 3.259444912033378e-05, "loss": 10.12, "step": 945 }, { "epoch": 0.028984841173181362, "grad_norm": 0.11169708520174026, "learning_rate": 3.2498429100674446e-05, "loss": 10.1168, "step": 946 }, { "epoch": 0.02901548054017204, "grad_norm": 0.2035871148109436, "learning_rate": 3.240248258185731e-05, "loss": 10.1118, "step": 947 }, { "epoch": 0.02904611990716272, "grad_norm": 0.22375606000423431, "learning_rate": 3.230660996682618e-05, "loss": 10.1171, "step": 948 }, { "epoch": 0.029076759274153395, "grad_norm": 0.27501577138900757, "learning_rate": 3.2210811658214535e-05, "loss": 10.1126, "step": 949 }, { "epoch": 0.029107398641144075, "grad_norm": 0.2749876081943512, "learning_rate": 3.2115088058343725e-05, "loss": 10.1118, "step": 950 }, { "epoch": 0.02913803800813475, "grad_norm": 0.12354274839162827, "learning_rate": 3.201943956922145e-05, "loss": 10.1519, "step": 951 }, { "epoch": 0.02916867737512543, "grad_norm": 0.2268901914358139, "learning_rate": 3.1923866592539846e-05, "loss": 10.1592, "step": 952 }, { "epoch": 0.029199316742116108, "grad_norm": 0.4165934920310974, "learning_rate": 3.1828369529674046e-05, "loss": 10.1347, "step": 953 }, { "epoch": 0.029229956109106787, "grad_norm": 0.20095956325531006, "learning_rate": 3.173294878168025e-05, "loss": 10.1293, "step": 954 }, { "epoch": 0.029260595476097464, "grad_norm": 0.18425479531288147, "learning_rate": 3.163760474929427e-05, "loss": 10.147, "step": 955 }, { "epoch": 0.02929123484308814, "grad_norm": 0.14681348204612732, "learning_rate": 3.1542337832929644e-05, "loss": 10.1424, "step": 956 }, { "epoch": 0.02932187421007882, "grad_norm": 0.18200388550758362, "learning_rate": 3.144714843267613e-05, "loss": 10.118, "step": 957 }, { "epoch": 0.029352513577069497, "grad_norm": 0.1149030476808548, "learning_rate": 3.135203694829787e-05, "loss": 10.1085, "step": 958 }, { "epoch": 0.029383152944060176, "grad_norm": 0.10842356830835342, "learning_rate": 3.125700377923186e-05, "loss": 10.1086, "step": 959 }, { "epoch": 0.029413792311050853, "grad_norm": 0.09608888626098633, "learning_rate": 3.116204932458609e-05, "loss": 10.1082, "step": 960 }, { "epoch": 0.029444431678041533, "grad_norm": 0.11213342845439911, "learning_rate": 3.106717398313813e-05, "loss": 10.1062, "step": 961 }, { "epoch": 0.02947507104503221, "grad_norm": 0.11706098914146423, "learning_rate": 3.0972378153333145e-05, "loss": 10.1111, "step": 962 }, { "epoch": 0.02950571041202289, "grad_norm": 0.10250700265169144, "learning_rate": 3.087766223328249e-05, "loss": 10.1133, "step": 963 }, { "epoch": 0.029536349779013565, "grad_norm": 0.13958005607128143, "learning_rate": 3.078302662076185e-05, "loss": 10.1226, "step": 964 }, { "epoch": 0.029566989146004245, "grad_norm": 0.11662806570529938, "learning_rate": 3.068847171320969e-05, "loss": 10.1186, "step": 965 }, { "epoch": 0.02959762851299492, "grad_norm": 0.12979698181152344, "learning_rate": 3.0593997907725505e-05, "loss": 10.116, "step": 966 }, { "epoch": 0.029628267879985598, "grad_norm": 0.09451613575220108, "learning_rate": 3.049960560106825e-05, "loss": 10.1157, "step": 967 }, { "epoch": 0.029658907246976278, "grad_norm": 0.09637225419282913, "learning_rate": 3.0405295189654537e-05, "loss": 10.1183, "step": 968 }, { "epoch": 0.029689546613966954, "grad_norm": 0.13728487491607666, "learning_rate": 3.0311067069557097e-05, "loss": 10.1269, "step": 969 }, { "epoch": 0.029720185980957634, "grad_norm": 0.18248336017131805, "learning_rate": 3.0216921636503026e-05, "loss": 10.1169, "step": 970 }, { "epoch": 0.02975082534794831, "grad_norm": 0.195464625954628, "learning_rate": 3.0122859285872214e-05, "loss": 10.1202, "step": 971 }, { "epoch": 0.02978146471493899, "grad_norm": 0.08600299060344696, "learning_rate": 3.0028880412695572e-05, "loss": 10.1186, "step": 972 }, { "epoch": 0.029812104081929667, "grad_norm": 0.06398029625415802, "learning_rate": 2.9934985411653472e-05, "loss": 10.1119, "step": 973 }, { "epoch": 0.029842743448920347, "grad_norm": 0.10837303847074509, "learning_rate": 2.9841174677074035e-05, "loss": 10.1154, "step": 974 }, { "epoch": 0.029873382815911023, "grad_norm": 0.15401288866996765, "learning_rate": 2.9747448602931503e-05, "loss": 10.1097, "step": 975 }, { "epoch": 0.0299040221829017, "grad_norm": 0.15762187540531158, "learning_rate": 2.965380758284456e-05, "loss": 10.107, "step": 976 }, { "epoch": 0.02993466154989238, "grad_norm": 0.1625382900238037, "learning_rate": 2.9560252010074706e-05, "loss": 10.12, "step": 977 }, { "epoch": 0.029965300916883056, "grad_norm": 0.1795027256011963, "learning_rate": 2.9466782277524553e-05, "loss": 10.1027, "step": 978 }, { "epoch": 0.029995940283873736, "grad_norm": 0.17345786094665527, "learning_rate": 2.937339877773627e-05, "loss": 10.1047, "step": 979 }, { "epoch": 0.030026579650864412, "grad_norm": 0.18275123834609985, "learning_rate": 2.9280101902889824e-05, "loss": 10.1094, "step": 980 }, { "epoch": 0.030057219017855092, "grad_norm": 0.20539209246635437, "learning_rate": 2.9186892044801427e-05, "loss": 10.1005, "step": 981 }, { "epoch": 0.03008785838484577, "grad_norm": 0.19990287721157074, "learning_rate": 2.9093769594921804e-05, "loss": 10.1042, "step": 982 }, { "epoch": 0.03011849775183645, "grad_norm": 0.13013561069965363, "learning_rate": 2.900073494433464e-05, "loss": 10.1225, "step": 983 }, { "epoch": 0.030149137118827125, "grad_norm": 0.1957767903804779, "learning_rate": 2.8907788483754867e-05, "loss": 10.1471, "step": 984 }, { "epoch": 0.030179776485817805, "grad_norm": 0.2135556936264038, "learning_rate": 2.8814930603527068e-05, "loss": 10.1404, "step": 985 }, { "epoch": 0.03021041585280848, "grad_norm": 0.17338012158870697, "learning_rate": 2.8722161693623772e-05, "loss": 10.1376, "step": 986 }, { "epoch": 0.030241055219799157, "grad_norm": 0.1783328354358673, "learning_rate": 2.862948214364391e-05, "loss": 10.1314, "step": 987 }, { "epoch": 0.030271694586789837, "grad_norm": 0.0665055438876152, "learning_rate": 2.8536892342811106e-05, "loss": 10.1024, "step": 988 }, { "epoch": 0.030302333953780514, "grad_norm": 0.09287954121828079, "learning_rate": 2.8444392679972103e-05, "loss": 10.0988, "step": 989 }, { "epoch": 0.030332973320771194, "grad_norm": 0.09973522275686264, "learning_rate": 2.8351983543595018e-05, "loss": 10.098, "step": 990 }, { "epoch": 0.03036361268776187, "grad_norm": 0.12514625489711761, "learning_rate": 2.8259665321767865e-05, "loss": 10.1001, "step": 991 }, { "epoch": 0.03039425205475255, "grad_norm": 0.1986560970544815, "learning_rate": 2.8167438402196805e-05, "loss": 10.1017, "step": 992 }, { "epoch": 0.030424891421743226, "grad_norm": 0.23516826331615448, "learning_rate": 2.8075303172204594e-05, "loss": 10.0951, "step": 993 }, { "epoch": 0.030455530788733906, "grad_norm": 0.2748039662837982, "learning_rate": 2.7983260018728858e-05, "loss": 10.0926, "step": 994 }, { "epoch": 0.030486170155724582, "grad_norm": 0.22984515130519867, "learning_rate": 2.7891309328320592e-05, "loss": 10.1014, "step": 995 }, { "epoch": 0.030516809522715262, "grad_norm": 0.13212114572525024, "learning_rate": 2.7799451487142458e-05, "loss": 10.1136, "step": 996 }, { "epoch": 0.03054744888970594, "grad_norm": 0.14289456605911255, "learning_rate": 2.77076868809672e-05, "loss": 10.1126, "step": 997 }, { "epoch": 0.030578088256696615, "grad_norm": 0.21113772690296173, "learning_rate": 2.761601589517595e-05, "loss": 10.1091, "step": 998 }, { "epoch": 0.030608727623687295, "grad_norm": 0.21117530763149261, "learning_rate": 2.7524438914756712e-05, "loss": 10.1205, "step": 999 }, { "epoch": 0.03063936699067797, "grad_norm": 0.30299702286720276, "learning_rate": 2.7432956324302694e-05, "loss": 10.1118, "step": 1000 }, { "epoch": 0.03067000635766865, "grad_norm": 0.24548493325710297, "learning_rate": 2.7341568508010705e-05, "loss": 10.1528, "step": 1001 }, { "epoch": 0.030700645724659328, "grad_norm": 0.16548895835876465, "learning_rate": 2.7250275849679496e-05, "loss": 10.1302, "step": 1002 }, { "epoch": 0.030731285091650008, "grad_norm": 0.2016974836587906, "learning_rate": 2.715907873270821e-05, "loss": 10.1307, "step": 1003 }, { "epoch": 0.030761924458640684, "grad_norm": 0.18414634466171265, "learning_rate": 2.706797754009476e-05, "loss": 10.1415, "step": 1004 }, { "epoch": 0.030792563825631364, "grad_norm": 0.08420543372631073, "learning_rate": 2.6976972654434195e-05, "loss": 10.1166, "step": 1005 }, { "epoch": 0.03082320319262204, "grad_norm": 0.08905380219221115, "learning_rate": 2.6886064457917092e-05, "loss": 10.1117, "step": 1006 }, { "epoch": 0.03085384255961272, "grad_norm": 0.11246532946825027, "learning_rate": 2.6795253332327995e-05, "loss": 10.1226, "step": 1007 }, { "epoch": 0.030884481926603397, "grad_norm": 0.10327516496181488, "learning_rate": 2.6704539659043758e-05, "loss": 10.1071, "step": 1008 }, { "epoch": 0.030915121293594073, "grad_norm": 0.1161801889538765, "learning_rate": 2.6613923819032e-05, "loss": 10.1037, "step": 1009 }, { "epoch": 0.030945760660584753, "grad_norm": 0.08091892302036285, "learning_rate": 2.6523406192849386e-05, "loss": 10.1098, "step": 1010 }, { "epoch": 0.03097640002757543, "grad_norm": 0.14005930721759796, "learning_rate": 2.643298716064027e-05, "loss": 10.1153, "step": 1011 }, { "epoch": 0.03100703939456611, "grad_norm": 0.12964458763599396, "learning_rate": 2.6342667102134776e-05, "loss": 10.1183, "step": 1012 }, { "epoch": 0.031037678761556785, "grad_norm": 0.12214060127735138, "learning_rate": 2.62524463966475e-05, "loss": 10.1144, "step": 1013 }, { "epoch": 0.031068318128547465, "grad_norm": 0.12053851038217545, "learning_rate": 2.6162325423075675e-05, "loss": 10.1159, "step": 1014 }, { "epoch": 0.031098957495538142, "grad_norm": 0.11970780044794083, "learning_rate": 2.607230455989782e-05, "loss": 10.1114, "step": 1015 }, { "epoch": 0.03112959686252882, "grad_norm": 0.16899481415748596, "learning_rate": 2.5982384185171906e-05, "loss": 10.1209, "step": 1016 }, { "epoch": 0.031160236229519498, "grad_norm": 0.15255743265151978, "learning_rate": 2.589256467653397e-05, "loss": 10.1228, "step": 1017 }, { "epoch": 0.031190875596510174, "grad_norm": 0.10139689594507217, "learning_rate": 2.5802846411196358e-05, "loss": 10.1162, "step": 1018 }, { "epoch": 0.031221514963500854, "grad_norm": 0.18596261739730835, "learning_rate": 2.5713229765946357e-05, "loss": 10.117, "step": 1019 }, { "epoch": 0.031252154330491534, "grad_norm": 0.16415287554264069, "learning_rate": 2.5623715117144336e-05, "loss": 10.1163, "step": 1020 }, { "epoch": 0.03128279369748221, "grad_norm": 0.12325111031532288, "learning_rate": 2.5534302840722436e-05, "loss": 10.1128, "step": 1021 }, { "epoch": 0.03131343306447289, "grad_norm": 0.11430035531520844, "learning_rate": 2.544499331218274e-05, "loss": 10.116, "step": 1022 }, { "epoch": 0.03134407243146357, "grad_norm": 0.11466975510120392, "learning_rate": 2.535578690659599e-05, "loss": 10.1258, "step": 1023 }, { "epoch": 0.03137471179845425, "grad_norm": 0.1389143168926239, "learning_rate": 2.5266683998599688e-05, "loss": 10.109, "step": 1024 }, { "epoch": 0.03140535116544492, "grad_norm": 0.14526794850826263, "learning_rate": 2.5177684962396765e-05, "loss": 10.1053, "step": 1025 }, { "epoch": 0.0314359905324356, "grad_norm": 0.14377383887767792, "learning_rate": 2.5088790171753906e-05, "loss": 10.1047, "step": 1026 }, { "epoch": 0.03146662989942628, "grad_norm": 0.17546626925468445, "learning_rate": 2.500000000000001e-05, "loss": 10.1037, "step": 1027 }, { "epoch": 0.03149726926641696, "grad_norm": 0.16977006196975708, "learning_rate": 2.4911314820024568e-05, "loss": 10.1033, "step": 1028 }, { "epoch": 0.03152790863340763, "grad_norm": 0.16812458634376526, "learning_rate": 2.4822735004276186e-05, "loss": 10.1038, "step": 1029 }, { "epoch": 0.03155854800039831, "grad_norm": 0.22327806055545807, "learning_rate": 2.4734260924760965e-05, "loss": 10.0984, "step": 1030 }, { "epoch": 0.03158918736738899, "grad_norm": 0.168112650513649, "learning_rate": 2.4645892953040962e-05, "loss": 10.1327, "step": 1031 }, { "epoch": 0.031619826734379665, "grad_norm": 0.16199827194213867, "learning_rate": 2.4557631460232548e-05, "loss": 10.1337, "step": 1032 }, { "epoch": 0.031650466101370345, "grad_norm": 0.179671511054039, "learning_rate": 2.4469476817005e-05, "loss": 10.1414, "step": 1033 }, { "epoch": 0.031681105468361025, "grad_norm": 0.1846669614315033, "learning_rate": 2.438142939357882e-05, "loss": 10.1352, "step": 1034 }, { "epoch": 0.031711744835351705, "grad_norm": 0.24265703558921814, "learning_rate": 2.4293489559724254e-05, "loss": 10.1423, "step": 1035 }, { "epoch": 0.03174238420234238, "grad_norm": 0.08625683933496475, "learning_rate": 2.4205657684759646e-05, "loss": 10.1123, "step": 1036 }, { "epoch": 0.03177302356933306, "grad_norm": 0.13342924416065216, "learning_rate": 2.4117934137550003e-05, "loss": 10.1253, "step": 1037 }, { "epoch": 0.03180366293632374, "grad_norm": 0.07075991481542587, "learning_rate": 2.4030319286505375e-05, "loss": 10.104, "step": 1038 }, { "epoch": 0.03183430230331441, "grad_norm": 0.10801225155591965, "learning_rate": 2.3942813499579347e-05, "loss": 10.095, "step": 1039 }, { "epoch": 0.03186494167030509, "grad_norm": 0.1405041217803955, "learning_rate": 2.38554171442674e-05, "loss": 10.0968, "step": 1040 }, { "epoch": 0.03189558103729577, "grad_norm": 0.178863987326622, "learning_rate": 2.3768130587605515e-05, "loss": 10.0968, "step": 1041 }, { "epoch": 0.03192622040428645, "grad_norm": 0.17732129991054535, "learning_rate": 2.3680954196168514e-05, "loss": 10.0989, "step": 1042 }, { "epoch": 0.03195685977127712, "grad_norm": 0.20946566760540009, "learning_rate": 2.3593888336068597e-05, "loss": 10.0965, "step": 1043 }, { "epoch": 0.0319874991382678, "grad_norm": 0.2171870768070221, "learning_rate": 2.350693337295371e-05, "loss": 10.1016, "step": 1044 }, { "epoch": 0.03201813850525848, "grad_norm": 0.17834781110286713, "learning_rate": 2.3420089672006114e-05, "loss": 10.1077, "step": 1045 }, { "epoch": 0.03204877787224916, "grad_norm": 0.1505112498998642, "learning_rate": 2.3333357597940793e-05, "loss": 10.1171, "step": 1046 }, { "epoch": 0.032079417239239835, "grad_norm": 0.16523469984531403, "learning_rate": 2.3246737515003953e-05, "loss": 10.1168, "step": 1047 }, { "epoch": 0.032110056606230515, "grad_norm": 0.2550811171531677, "learning_rate": 2.3160229786971428e-05, "loss": 10.1097, "step": 1048 }, { "epoch": 0.032140695973221195, "grad_norm": 0.2789177894592285, "learning_rate": 2.3073834777147236e-05, "loss": 10.1076, "step": 1049 }, { "epoch": 0.03217133534021187, "grad_norm": 0.2644725739955902, "learning_rate": 2.298755284836201e-05, "loss": 10.1085, "step": 1050 }, { "epoch": 0.03220197470720255, "grad_norm": 0.13590534031391144, "learning_rate": 2.2901384362971494e-05, "loss": 10.1366, "step": 1051 }, { "epoch": 0.03223261407419323, "grad_norm": 0.2357386201620102, "learning_rate": 2.281532968285494e-05, "loss": 10.1449, "step": 1052 }, { "epoch": 0.03226325344118391, "grad_norm": 0.22862204909324646, "learning_rate": 2.272938916941377e-05, "loss": 10.1279, "step": 1053 }, { "epoch": 0.03229389280817458, "grad_norm": 0.21856112778186798, "learning_rate": 2.264356318356982e-05, "loss": 10.1506, "step": 1054 }, { "epoch": 0.03232453217516526, "grad_norm": 0.17030023038387299, "learning_rate": 2.2557852085764053e-05, "loss": 10.1397, "step": 1055 }, { "epoch": 0.03235517154215594, "grad_norm": 0.13435903191566467, "learning_rate": 2.2472256235954835e-05, "loss": 10.1187, "step": 1056 }, { "epoch": 0.03238581090914662, "grad_norm": 0.08894478529691696, "learning_rate": 2.2386775993616653e-05, "loss": 10.1092, "step": 1057 }, { "epoch": 0.03241645027613729, "grad_norm": 0.11842325329780579, "learning_rate": 2.230141171773836e-05, "loss": 10.1075, "step": 1058 }, { "epoch": 0.03244708964312797, "grad_norm": 0.09622557461261749, "learning_rate": 2.2216163766821886e-05, "loss": 10.1063, "step": 1059 }, { "epoch": 0.03247772901011865, "grad_norm": 0.09835969656705856, "learning_rate": 2.213103249888053e-05, "loss": 10.1088, "step": 1060 }, { "epoch": 0.032508368377109326, "grad_norm": 0.11798969656229019, "learning_rate": 2.204601827143769e-05, "loss": 10.1045, "step": 1061 }, { "epoch": 0.032539007744100006, "grad_norm": 0.06969135254621506, "learning_rate": 2.1961121441525112e-05, "loss": 10.1133, "step": 1062 }, { "epoch": 0.032569647111090685, "grad_norm": 0.12312201410531998, "learning_rate": 2.1876342365681583e-05, "loss": 10.1132, "step": 1063 }, { "epoch": 0.032600286478081365, "grad_norm": 0.11798254400491714, "learning_rate": 2.179168139995134e-05, "loss": 10.1153, "step": 1064 }, { "epoch": 0.03263092584507204, "grad_norm": 0.10461415350437164, "learning_rate": 2.1707138899882617e-05, "loss": 10.1106, "step": 1065 }, { "epoch": 0.03266156521206272, "grad_norm": 0.10292448848485947, "learning_rate": 2.1622715220526075e-05, "loss": 10.1176, "step": 1066 }, { "epoch": 0.0326922045790534, "grad_norm": 0.11943846195936203, "learning_rate": 2.1538410716433417e-05, "loss": 10.1141, "step": 1067 }, { "epoch": 0.03272284394604408, "grad_norm": 0.12219364196062088, "learning_rate": 2.1454225741655835e-05, "loss": 10.1275, "step": 1068 }, { "epoch": 0.03275348331303475, "grad_norm": 0.08352815359830856, "learning_rate": 2.137016064974256e-05, "loss": 10.1235, "step": 1069 }, { "epoch": 0.03278412268002543, "grad_norm": 0.15778633952140808, "learning_rate": 2.1286215793739302e-05, "loss": 10.1151, "step": 1070 }, { "epoch": 0.03281476204701611, "grad_norm": 0.09516726434230804, "learning_rate": 2.1202391526186856e-05, "loss": 10.1182, "step": 1071 }, { "epoch": 0.032845401414006783, "grad_norm": 0.09550289064645767, "learning_rate": 2.1118688199119586e-05, "loss": 10.1176, "step": 1072 }, { "epoch": 0.03287604078099746, "grad_norm": 0.14591333270072937, "learning_rate": 2.103510616406396e-05, "loss": 10.1198, "step": 1073 }, { "epoch": 0.03290668014798814, "grad_norm": 0.12670935690402985, "learning_rate": 2.0951645772036993e-05, "loss": 10.1155, "step": 1074 }, { "epoch": 0.03293731951497882, "grad_norm": 0.1703256219625473, "learning_rate": 2.0868307373544908e-05, "loss": 10.1137, "step": 1075 }, { "epoch": 0.032967958881969496, "grad_norm": 0.1567576676607132, "learning_rate": 2.0785091318581577e-05, "loss": 10.1021, "step": 1076 }, { "epoch": 0.032998598248960176, "grad_norm": 0.17374320328235626, "learning_rate": 2.0701997956627072e-05, "loss": 10.1005, "step": 1077 }, { "epoch": 0.033029237615950856, "grad_norm": 0.15354010462760925, "learning_rate": 2.061902763664616e-05, "loss": 10.1082, "step": 1078 }, { "epoch": 0.033059876982941536, "grad_norm": 0.2100084275007248, "learning_rate": 2.053618070708691e-05, "loss": 10.0975, "step": 1079 }, { "epoch": 0.03309051634993221, "grad_norm": 0.13717743754386902, "learning_rate": 2.0453457515879188e-05, "loss": 10.1105, "step": 1080 }, { "epoch": 0.03312115571692289, "grad_norm": 0.15381427109241486, "learning_rate": 2.0370858410433203e-05, "loss": 10.1322, "step": 1081 }, { "epoch": 0.03315179508391357, "grad_norm": 0.1967994123697281, "learning_rate": 2.0288383737638006e-05, "loss": 10.1562, "step": 1082 }, { "epoch": 0.03318243445090424, "grad_norm": 0.18786735832691193, "learning_rate": 2.020603384386011e-05, "loss": 10.1357, "step": 1083 }, { "epoch": 0.03321307381789492, "grad_norm": 0.224569633603096, "learning_rate": 2.0123809074941996e-05, "loss": 10.1366, "step": 1084 }, { "epoch": 0.0332437131848856, "grad_norm": 0.27244406938552856, "learning_rate": 2.0041709776200664e-05, "loss": 10.1447, "step": 1085 }, { "epoch": 0.03327435255187628, "grad_norm": 0.20751173794269562, "learning_rate": 1.9959736292426134e-05, "loss": 10.134, "step": 1086 }, { "epoch": 0.033304991918866954, "grad_norm": 0.11408066004514694, "learning_rate": 1.9877888967880106e-05, "loss": 10.1083, "step": 1087 }, { "epoch": 0.033335631285857634, "grad_norm": 0.07623784244060516, "learning_rate": 1.9796168146294412e-05, "loss": 10.0993, "step": 1088 }, { "epoch": 0.033366270652848314, "grad_norm": 0.08841373771429062, "learning_rate": 1.971457417086966e-05, "loss": 10.096, "step": 1089 }, { "epoch": 0.03339691001983899, "grad_norm": 0.16436199843883514, "learning_rate": 1.963310738427367e-05, "loss": 10.1037, "step": 1090 }, { "epoch": 0.033427549386829666, "grad_norm": 0.19379553198814392, "learning_rate": 1.9551768128640175e-05, "loss": 10.1021, "step": 1091 }, { "epoch": 0.033458188753820346, "grad_norm": 0.12466222047805786, "learning_rate": 1.9470556745567297e-05, "loss": 10.0983, "step": 1092 }, { "epoch": 0.033488828120811026, "grad_norm": 0.2379600703716278, "learning_rate": 1.9389473576116158e-05, "loss": 10.0883, "step": 1093 }, { "epoch": 0.0335194674878017, "grad_norm": 0.2670637369155884, "learning_rate": 1.9308518960809353e-05, "loss": 10.0935, "step": 1094 }, { "epoch": 0.03355010685479238, "grad_norm": 0.23542653024196625, "learning_rate": 1.9227693239629707e-05, "loss": 10.1001, "step": 1095 }, { "epoch": 0.03358074622178306, "grad_norm": 0.19121670722961426, "learning_rate": 1.9146996752018626e-05, "loss": 10.103, "step": 1096 }, { "epoch": 0.03361138558877374, "grad_norm": 0.17938552796840668, "learning_rate": 1.9066429836874844e-05, "loss": 10.1077, "step": 1097 }, { "epoch": 0.03364202495576441, "grad_norm": 0.2245842069387436, "learning_rate": 1.8985992832552867e-05, "loss": 10.1102, "step": 1098 }, { "epoch": 0.03367266432275509, "grad_norm": 0.2961188852787018, "learning_rate": 1.8905686076861724e-05, "loss": 10.1096, "step": 1099 }, { "epoch": 0.03370330368974577, "grad_norm": 0.27628466486930847, "learning_rate": 1.8825509907063327e-05, "loss": 10.1111, "step": 1100 }, { "epoch": 0.03373394305673645, "grad_norm": 0.23118211328983307, "learning_rate": 1.874546465987126e-05, "loss": 10.1381, "step": 1101 }, { "epoch": 0.033764582423727124, "grad_norm": 0.23382118344306946, "learning_rate": 1.8665550671449183e-05, "loss": 10.1342, "step": 1102 }, { "epoch": 0.033795221790717804, "grad_norm": 0.21831664443016052, "learning_rate": 1.8585768277409636e-05, "loss": 10.1471, "step": 1103 }, { "epoch": 0.033825861157708484, "grad_norm": 0.23425525426864624, "learning_rate": 1.850611781281239e-05, "loss": 10.151, "step": 1104 }, { "epoch": 0.03385650052469916, "grad_norm": 0.10696188360452652, "learning_rate": 1.8426599612163215e-05, "loss": 10.1135, "step": 1105 }, { "epoch": 0.03388713989168984, "grad_norm": 0.10022056847810745, "learning_rate": 1.83472140094124e-05, "loss": 10.1112, "step": 1106 }, { "epoch": 0.03391777925868052, "grad_norm": 0.1023062989115715, "learning_rate": 1.826796133795339e-05, "loss": 10.1063, "step": 1107 }, { "epoch": 0.033948418625671196, "grad_norm": 0.1029517725110054, "learning_rate": 1.8188841930621313e-05, "loss": 10.1101, "step": 1108 }, { "epoch": 0.03397905799266187, "grad_norm": 0.09381450712680817, "learning_rate": 1.810985611969167e-05, "loss": 10.112, "step": 1109 }, { "epoch": 0.03400969735965255, "grad_norm": 0.08167195320129395, "learning_rate": 1.80310042368789e-05, "loss": 10.1123, "step": 1110 }, { "epoch": 0.03404033672664323, "grad_norm": 0.14054888486862183, "learning_rate": 1.7952286613334984e-05, "loss": 10.1195, "step": 1111 }, { "epoch": 0.0340709760936339, "grad_norm": 0.11850418895483017, "learning_rate": 1.7873703579648034e-05, "loss": 10.1177, "step": 1112 }, { "epoch": 0.03410161546062458, "grad_norm": 0.1178484559059143, "learning_rate": 1.7795255465840947e-05, "loss": 10.1145, "step": 1113 }, { "epoch": 0.03413225482761526, "grad_norm": 0.1248290091753006, "learning_rate": 1.7716942601370023e-05, "loss": 10.114, "step": 1114 }, { "epoch": 0.03416289419460594, "grad_norm": 0.12896636128425598, "learning_rate": 1.763876531512354e-05, "loss": 10.1175, "step": 1115 }, { "epoch": 0.034193533561596615, "grad_norm": 0.0902765691280365, "learning_rate": 1.756072393542037e-05, "loss": 10.1165, "step": 1116 }, { "epoch": 0.034224172928587294, "grad_norm": 0.14123614132404327, "learning_rate": 1.7482818790008647e-05, "loss": 10.1163, "step": 1117 }, { "epoch": 0.034254812295577974, "grad_norm": 0.13783621788024902, "learning_rate": 1.7405050206064373e-05, "loss": 10.1258, "step": 1118 }, { "epoch": 0.034285451662568654, "grad_norm": 0.11364240199327469, "learning_rate": 1.7327418510190037e-05, "loss": 10.1158, "step": 1119 }, { "epoch": 0.03431609102955933, "grad_norm": 0.07386075705289841, "learning_rate": 1.7249924028413193e-05, "loss": 10.1184, "step": 1120 }, { "epoch": 0.03434673039655001, "grad_norm": 0.10463513433933258, "learning_rate": 1.7172567086185205e-05, "loss": 10.1174, "step": 1121 }, { "epoch": 0.03437736976354069, "grad_norm": 0.12307676672935486, "learning_rate": 1.7095348008379785e-05, "loss": 10.1134, "step": 1122 }, { "epoch": 0.03440800913053136, "grad_norm": 0.163552924990654, "learning_rate": 1.701826711929169e-05, "loss": 10.1174, "step": 1123 }, { "epoch": 0.03443864849752204, "grad_norm": 0.18020309507846832, "learning_rate": 1.694132474263526e-05, "loss": 10.1108, "step": 1124 }, { "epoch": 0.03446928786451272, "grad_norm": 0.17734383046627045, "learning_rate": 1.6864521201543197e-05, "loss": 10.1072, "step": 1125 }, { "epoch": 0.0344999272315034, "grad_norm": 0.161997988820076, "learning_rate": 1.6787856818565124e-05, "loss": 10.1003, "step": 1126 }, { "epoch": 0.03453056659849407, "grad_norm": 0.17986786365509033, "learning_rate": 1.671133191566624e-05, "loss": 10.1, "step": 1127 }, { "epoch": 0.03456120596548475, "grad_norm": 0.20350322127342224, "learning_rate": 1.6634946814225936e-05, "loss": 10.1024, "step": 1128 }, { "epoch": 0.03459184533247543, "grad_norm": 0.21712744235992432, "learning_rate": 1.6558701835036556e-05, "loss": 10.1007, "step": 1129 }, { "epoch": 0.03462248469946611, "grad_norm": 0.11170154064893723, "learning_rate": 1.6482597298301916e-05, "loss": 10.1113, "step": 1130 }, { "epoch": 0.034653124066456785, "grad_norm": 0.15030767023563385, "learning_rate": 1.6406633523636066e-05, "loss": 10.1347, "step": 1131 }, { "epoch": 0.034683763433447465, "grad_norm": 0.20985224843025208, "learning_rate": 1.6330810830061833e-05, "loss": 10.1551, "step": 1132 }, { "epoch": 0.034714402800438145, "grad_norm": 0.20883774757385254, "learning_rate": 1.625512953600966e-05, "loss": 10.1444, "step": 1133 }, { "epoch": 0.03474504216742882, "grad_norm": 0.17070642113685608, "learning_rate": 1.6179589959316038e-05, "loss": 10.1346, "step": 1134 }, { "epoch": 0.0347756815344195, "grad_norm": 0.17150768637657166, "learning_rate": 1.6104192417222384e-05, "loss": 10.1261, "step": 1135 }, { "epoch": 0.03480632090141018, "grad_norm": 0.0848160982131958, "learning_rate": 1.6028937226373536e-05, "loss": 10.1131, "step": 1136 }, { "epoch": 0.03483696026840086, "grad_norm": 0.09589201211929321, "learning_rate": 1.5953824702816605e-05, "loss": 10.0984, "step": 1137 }, { "epoch": 0.03486759963539153, "grad_norm": 0.07823175936937332, "learning_rate": 1.5878855161999434e-05, "loss": 10.0948, "step": 1138 }, { "epoch": 0.03489823900238221, "grad_norm": 0.1483733206987381, "learning_rate": 1.5804028918769485e-05, "loss": 10.0973, "step": 1139 }, { "epoch": 0.03492887836937289, "grad_norm": 0.1801983118057251, "learning_rate": 1.572934628737232e-05, "loss": 10.0972, "step": 1140 }, { "epoch": 0.03495951773636357, "grad_norm": 0.18918706476688385, "learning_rate": 1.5654807581450494e-05, "loss": 10.0955, "step": 1141 }, { "epoch": 0.03499015710335424, "grad_norm": 0.1614406704902649, "learning_rate": 1.5580413114042e-05, "loss": 10.0968, "step": 1142 }, { "epoch": 0.03502079647034492, "grad_norm": 0.2320803701877594, "learning_rate": 1.550616319757919e-05, "loss": 10.0936, "step": 1143 }, { "epoch": 0.0350514358373356, "grad_norm": 0.19652941823005676, "learning_rate": 1.5432058143887224e-05, "loss": 10.1005, "step": 1144 }, { "epoch": 0.035082075204326275, "grad_norm": 0.12692388892173767, "learning_rate": 1.535809826418304e-05, "loss": 10.1083, "step": 1145 }, { "epoch": 0.035112714571316955, "grad_norm": 0.11545553803443909, "learning_rate": 1.528428386907375e-05, "loss": 10.116, "step": 1146 }, { "epoch": 0.035143353938307635, "grad_norm": 0.20581473410129547, "learning_rate": 1.5210615268555561e-05, "loss": 10.1096, "step": 1147 }, { "epoch": 0.035173993305298315, "grad_norm": 0.28854358196258545, "learning_rate": 1.5137092772012368e-05, "loss": 10.1079, "step": 1148 }, { "epoch": 0.03520463267228899, "grad_norm": 0.28620094060897827, "learning_rate": 1.5063716688214491e-05, "loss": 10.1039, "step": 1149 }, { "epoch": 0.03523527203927967, "grad_norm": 0.26140114665031433, "learning_rate": 1.4990487325317321e-05, "loss": 10.0979, "step": 1150 }, { "epoch": 0.03526591140627035, "grad_norm": 0.09969083964824677, "learning_rate": 1.4917404990860112e-05, "loss": 10.1386, "step": 1151 }, { "epoch": 0.03529655077326103, "grad_norm": 0.20002202689647675, "learning_rate": 1.4844469991764642e-05, "loss": 10.1364, "step": 1152 }, { "epoch": 0.0353271901402517, "grad_norm": 0.32509979605674744, "learning_rate": 1.4771682634333933e-05, "loss": 10.1303, "step": 1153 }, { "epoch": 0.03535782950724238, "grad_norm": 0.1816631257534027, "learning_rate": 1.469904322425092e-05, "loss": 10.143, "step": 1154 }, { "epoch": 0.03538846887423306, "grad_norm": 0.14395412802696228, "learning_rate": 1.4626552066577249e-05, "loss": 10.1332, "step": 1155 }, { "epoch": 0.03541910824122373, "grad_norm": 0.09631716459989548, "learning_rate": 1.4554209465751945e-05, "loss": 10.1124, "step": 1156 }, { "epoch": 0.03544974760821441, "grad_norm": 0.0874190628528595, "learning_rate": 1.4482015725590158e-05, "loss": 10.1068, "step": 1157 }, { "epoch": 0.03548038697520509, "grad_norm": 0.10873468220233917, "learning_rate": 1.440997114928182e-05, "loss": 10.1061, "step": 1158 }, { "epoch": 0.03551102634219577, "grad_norm": 0.12148800492286682, "learning_rate": 1.433807603939048e-05, "loss": 10.1088, "step": 1159 }, { "epoch": 0.035541665709186446, "grad_norm": 0.09392701089382172, "learning_rate": 1.4266330697851954e-05, "loss": 10.109, "step": 1160 }, { "epoch": 0.035572305076177126, "grad_norm": 0.11402743309736252, "learning_rate": 1.4194735425973093e-05, "loss": 10.111, "step": 1161 }, { "epoch": 0.035602944443167805, "grad_norm": 0.08266928046941757, "learning_rate": 1.4123290524430466e-05, "loss": 10.1149, "step": 1162 }, { "epoch": 0.035633583810158485, "grad_norm": 0.11606547236442566, "learning_rate": 1.4051996293269182e-05, "loss": 10.1151, "step": 1163 }, { "epoch": 0.03566422317714916, "grad_norm": 0.12777186930179596, "learning_rate": 1.3980853031901565e-05, "loss": 10.1151, "step": 1164 }, { "epoch": 0.03569486254413984, "grad_norm": 0.1112896129488945, "learning_rate": 1.3909861039105926e-05, "loss": 10.1173, "step": 1165 }, { "epoch": 0.03572550191113052, "grad_norm": 0.1159241572022438, "learning_rate": 1.3839020613025266e-05, "loss": 10.1223, "step": 1166 }, { "epoch": 0.03575614127812119, "grad_norm": 0.0990486666560173, "learning_rate": 1.3768332051166088e-05, "loss": 10.1165, "step": 1167 }, { "epoch": 0.03578678064511187, "grad_norm": 0.13988462090492249, "learning_rate": 1.369779565039711e-05, "loss": 10.1147, "step": 1168 }, { "epoch": 0.03581742001210255, "grad_norm": 0.12044680118560791, "learning_rate": 1.3627411706948029e-05, "loss": 10.1153, "step": 1169 }, { "epoch": 0.03584805937909323, "grad_norm": 0.10746123641729355, "learning_rate": 1.355718051640823e-05, "loss": 10.1133, "step": 1170 }, { "epoch": 0.035878698746083904, "grad_norm": 0.12597665190696716, "learning_rate": 1.3487102373725635e-05, "loss": 10.1157, "step": 1171 }, { "epoch": 0.03590933811307458, "grad_norm": 0.11332762241363525, "learning_rate": 1.3417177573205398e-05, "loss": 10.1143, "step": 1172 }, { "epoch": 0.03593997748006526, "grad_norm": 0.1729729175567627, "learning_rate": 1.3347406408508695e-05, "loss": 10.1056, "step": 1173 }, { "epoch": 0.03597061684705594, "grad_norm": 0.1695607751607895, "learning_rate": 1.3277789172651439e-05, "loss": 10.1022, "step": 1174 }, { "epoch": 0.036001256214046616, "grad_norm": 0.1789153665304184, "learning_rate": 1.3208326158003171e-05, "loss": 10.1115, "step": 1175 }, { "epoch": 0.036031895581037296, "grad_norm": 0.17896205186843872, "learning_rate": 1.3139017656285673e-05, "loss": 10.0988, "step": 1176 }, { "epoch": 0.036062534948027976, "grad_norm": 0.16750414669513702, "learning_rate": 1.3069863958571893e-05, "loss": 10.105, "step": 1177 }, { "epoch": 0.03609317431501865, "grad_norm": 0.19682849943637848, "learning_rate": 1.3000865355284563e-05, "loss": 10.1006, "step": 1178 }, { "epoch": 0.03612381368200933, "grad_norm": 0.16912584006786346, "learning_rate": 1.29320221361952e-05, "loss": 10.1186, "step": 1179 }, { "epoch": 0.03615445304900001, "grad_norm": 0.19088511168956757, "learning_rate": 1.2863334590422626e-05, "loss": 10.1417, "step": 1180 }, { "epoch": 0.03618509241599069, "grad_norm": 0.1493995189666748, "learning_rate": 1.2794803006431982e-05, "loss": 10.1371, "step": 1181 }, { "epoch": 0.03621573178298136, "grad_norm": 0.15723629295825958, "learning_rate": 1.2726427672033336e-05, "loss": 10.1295, "step": 1182 }, { "epoch": 0.03624637114997204, "grad_norm": 0.17685341835021973, "learning_rate": 1.2658208874380667e-05, "loss": 10.1278, "step": 1183 }, { "epoch": 0.03627701051696272, "grad_norm": 0.1861661672592163, "learning_rate": 1.2590146899970446e-05, "loss": 10.1327, "step": 1184 }, { "epoch": 0.0363076498839534, "grad_norm": 0.1573401391506195, "learning_rate": 1.2522242034640597e-05, "loss": 10.1332, "step": 1185 }, { "epoch": 0.036338289250944074, "grad_norm": 0.08590015023946762, "learning_rate": 1.2454494563569224e-05, "loss": 10.106, "step": 1186 }, { "epoch": 0.036368928617934754, "grad_norm": 0.08154883235692978, "learning_rate": 1.2386904771273444e-05, "loss": 10.0961, "step": 1187 }, { "epoch": 0.036399567984925434, "grad_norm": 0.08401933312416077, "learning_rate": 1.2319472941608118e-05, "loss": 10.0923, "step": 1188 }, { "epoch": 0.03643020735191611, "grad_norm": 0.14282377064228058, "learning_rate": 1.2252199357764777e-05, "loss": 10.0964, "step": 1189 }, { "epoch": 0.036460846718906786, "grad_norm": 0.17002353072166443, "learning_rate": 1.218508430227035e-05, "loss": 10.0946, "step": 1190 }, { "epoch": 0.036491486085897466, "grad_norm": 0.17281170189380646, "learning_rate": 1.2118128056986005e-05, "loss": 10.0949, "step": 1191 }, { "epoch": 0.036522125452888146, "grad_norm": 0.22034141421318054, "learning_rate": 1.2051330903105933e-05, "loss": 10.093, "step": 1192 }, { "epoch": 0.03655276481987882, "grad_norm": 0.1966477483510971, "learning_rate": 1.1984693121156226e-05, "loss": 10.1021, "step": 1193 }, { "epoch": 0.0365834041868695, "grad_norm": 0.1881091147661209, "learning_rate": 1.1918214990993654e-05, "loss": 10.102, "step": 1194 }, { "epoch": 0.03661404355386018, "grad_norm": 0.1465768814086914, "learning_rate": 1.1851896791804507e-05, "loss": 10.1176, "step": 1195 }, { "epoch": 0.03664468292085085, "grad_norm": 0.2364407479763031, "learning_rate": 1.1785738802103396e-05, "loss": 10.1033, "step": 1196 }, { "epoch": 0.03667532228784153, "grad_norm": 0.18871133029460907, "learning_rate": 1.1719741299732128e-05, "loss": 10.1064, "step": 1197 }, { "epoch": 0.03670596165483221, "grad_norm": 0.23370632529258728, "learning_rate": 1.1653904561858514e-05, "loss": 10.1144, "step": 1198 }, { "epoch": 0.03673660102182289, "grad_norm": 0.28471294045448303, "learning_rate": 1.158822886497521e-05, "loss": 10.1081, "step": 1199 }, { "epoch": 0.036767240388813564, "grad_norm": 0.20553641021251678, "learning_rate": 1.1522714484898518e-05, "loss": 10.0941, "step": 1200 }, { "epoch": 0.036797879755804244, "grad_norm": 0.2253408581018448, "learning_rate": 1.1457361696767305e-05, "loss": 10.1261, "step": 1201 }, { "epoch": 0.036828519122794924, "grad_norm": 0.1578921377658844, "learning_rate": 1.1392170775041788e-05, "loss": 10.1428, "step": 1202 }, { "epoch": 0.036859158489785604, "grad_norm": 0.30666685104370117, "learning_rate": 1.1327141993502416e-05, "loss": 10.1386, "step": 1203 }, { "epoch": 0.03688979785677628, "grad_norm": 0.13852092623710632, "learning_rate": 1.1262275625248658e-05, "loss": 10.139, "step": 1204 }, { "epoch": 0.03692043722376696, "grad_norm": 0.10029091686010361, "learning_rate": 1.1197571942697938e-05, "loss": 10.1198, "step": 1205 }, { "epoch": 0.03695107659075764, "grad_norm": 0.0997614711523056, "learning_rate": 1.1133031217584444e-05, "loss": 10.1153, "step": 1206 }, { "epoch": 0.03698171595774831, "grad_norm": 0.10415483266115189, "learning_rate": 1.1068653720958017e-05, "loss": 10.1056, "step": 1207 }, { "epoch": 0.03701235532473899, "grad_norm": 0.09215877950191498, "learning_rate": 1.1004439723182942e-05, "loss": 10.1061, "step": 1208 }, { "epoch": 0.03704299469172967, "grad_norm": 0.08168381452560425, "learning_rate": 1.0940389493936903e-05, "loss": 10.1077, "step": 1209 }, { "epoch": 0.03707363405872035, "grad_norm": 0.08309797197580338, "learning_rate": 1.08765033022098e-05, "loss": 10.1125, "step": 1210 }, { "epoch": 0.03710427342571102, "grad_norm": 0.10364088416099548, "learning_rate": 1.0812781416302642e-05, "loss": 10.117, "step": 1211 }, { "epoch": 0.0371349127927017, "grad_norm": 0.17210230231285095, "learning_rate": 1.0749224103826372e-05, "loss": 10.1187, "step": 1212 }, { "epoch": 0.03716555215969238, "grad_norm": 0.13127228617668152, "learning_rate": 1.0685831631700804e-05, "loss": 10.1182, "step": 1213 }, { "epoch": 0.03719619152668306, "grad_norm": 0.10922396928071976, "learning_rate": 1.0622604266153485e-05, "loss": 10.1126, "step": 1214 }, { "epoch": 0.037226830893673735, "grad_norm": 0.09752316772937775, "learning_rate": 1.0559542272718559e-05, "loss": 10.1135, "step": 1215 }, { "epoch": 0.037257470260664415, "grad_norm": 0.10396401584148407, "learning_rate": 1.049664591623563e-05, "loss": 10.1156, "step": 1216 }, { "epoch": 0.037288109627655094, "grad_norm": 0.10112003982067108, "learning_rate": 1.0433915460848764e-05, "loss": 10.1153, "step": 1217 }, { "epoch": 0.03731874899464577, "grad_norm": 0.1368326097726822, "learning_rate": 1.0371351170005194e-05, "loss": 10.1086, "step": 1218 }, { "epoch": 0.03734938836163645, "grad_norm": 0.20236307382583618, "learning_rate": 1.0308953306454405e-05, "loss": 10.1107, "step": 1219 }, { "epoch": 0.03738002772862713, "grad_norm": 0.1437736600637436, "learning_rate": 1.0246722132246856e-05, "loss": 10.1163, "step": 1220 }, { "epoch": 0.03741066709561781, "grad_norm": 0.09200498461723328, "learning_rate": 1.018465790873307e-05, "loss": 10.1239, "step": 1221 }, { "epoch": 0.03744130646260848, "grad_norm": 0.10136594623327255, "learning_rate": 1.0122760896562333e-05, "loss": 10.1158, "step": 1222 }, { "epoch": 0.03747194582959916, "grad_norm": 0.11569827795028687, "learning_rate": 1.0061031355681766e-05, "loss": 10.1121, "step": 1223 }, { "epoch": 0.03750258519658984, "grad_norm": 0.10667102038860321, "learning_rate": 9.999469545335105e-06, "loss": 10.1077, "step": 1224 }, { "epoch": 0.03753322456358052, "grad_norm": 0.14272551238536835, "learning_rate": 9.938075724061763e-06, "loss": 10.107, "step": 1225 }, { "epoch": 0.03756386393057119, "grad_norm": 0.1692921221256256, "learning_rate": 9.876850149695555e-06, "loss": 10.1072, "step": 1226 }, { "epoch": 0.03759450329756187, "grad_norm": 0.16613340377807617, "learning_rate": 9.815793079363766e-06, "loss": 10.1068, "step": 1227 }, { "epoch": 0.03762514266455255, "grad_norm": 0.18018753826618195, "learning_rate": 9.754904769486024e-06, "loss": 10.1099, "step": 1228 }, { "epoch": 0.037655782031543225, "grad_norm": 0.15732629597187042, "learning_rate": 9.694185475773216e-06, "loss": 10.1044, "step": 1229 }, { "epoch": 0.037686421398533905, "grad_norm": 0.18973876535892487, "learning_rate": 9.633635453226376e-06, "loss": 10.1032, "step": 1230 }, { "epoch": 0.037717060765524585, "grad_norm": 0.1752985566854477, "learning_rate": 9.573254956135701e-06, "loss": 10.0964, "step": 1231 }, { "epoch": 0.037747700132515265, "grad_norm": 0.14074434340000153, "learning_rate": 9.513044238079427e-06, "loss": 10.1308, "step": 1232 }, { "epoch": 0.03777833949950594, "grad_norm": 0.1437339186668396, "learning_rate": 9.45300355192278e-06, "loss": 10.1379, "step": 1233 }, { "epoch": 0.03780897886649662, "grad_norm": 0.16873401403427124, "learning_rate": 9.393133149816869e-06, "loss": 10.1298, "step": 1234 }, { "epoch": 0.0378396182334873, "grad_norm": 0.17544014751911163, "learning_rate": 9.333433283197702e-06, "loss": 10.1325, "step": 1235 }, { "epoch": 0.03787025760047798, "grad_norm": 0.07959257066249847, "learning_rate": 9.273904202785094e-06, "loss": 10.1037, "step": 1236 }, { "epoch": 0.03790089696746865, "grad_norm": 0.08590155094861984, "learning_rate": 9.214546158581622e-06, "loss": 10.1013, "step": 1237 }, { "epoch": 0.03793153633445933, "grad_norm": 0.09715619683265686, "learning_rate": 9.15535939987151e-06, "loss": 10.0955, "step": 1238 }, { "epoch": 0.03796217570145001, "grad_norm": 0.13711023330688477, "learning_rate": 9.096344175219712e-06, "loss": 10.0928, "step": 1239 }, { "epoch": 0.03799281506844068, "grad_norm": 0.14722134172916412, "learning_rate": 9.03750073247075e-06, "loss": 10.0998, "step": 1240 }, { "epoch": 0.03802345443543136, "grad_norm": 0.18758969008922577, "learning_rate": 8.978829318747745e-06, "loss": 10.0938, "step": 1241 }, { "epoch": 0.03805409380242204, "grad_norm": 0.16689984500408173, "learning_rate": 8.92033018045132e-06, "loss": 10.1011, "step": 1242 }, { "epoch": 0.03808473316941272, "grad_norm": 0.23897868394851685, "learning_rate": 8.86200356325863e-06, "loss": 10.0972, "step": 1243 }, { "epoch": 0.038115372536403395, "grad_norm": 0.16616784036159515, "learning_rate": 8.803849712122292e-06, "loss": 10.0984, "step": 1244 }, { "epoch": 0.038146011903394075, "grad_norm": 0.10096263140439987, "learning_rate": 8.745868871269353e-06, "loss": 10.1126, "step": 1245 }, { "epoch": 0.038176651270384755, "grad_norm": 0.11809328943490982, "learning_rate": 8.688061284200266e-06, "loss": 10.1183, "step": 1246 }, { "epoch": 0.038207290637375435, "grad_norm": 0.1539703607559204, "learning_rate": 8.63042719368789e-06, "loss": 10.1114, "step": 1247 }, { "epoch": 0.03823793000436611, "grad_norm": 0.26192590594291687, "learning_rate": 8.572966841776453e-06, "loss": 10.1109, "step": 1248 }, { "epoch": 0.03826856937135679, "grad_norm": 0.2966693937778473, "learning_rate": 8.515680469780552e-06, "loss": 10.1059, "step": 1249 }, { "epoch": 0.03829920873834747, "grad_norm": 0.26570650935173035, "learning_rate": 8.458568318284088e-06, "loss": 10.1017, "step": 1250 }, { "epoch": 0.03832984810533814, "grad_norm": 0.18900097906589508, "learning_rate": 8.401630627139318e-06, "loss": 10.118, "step": 1251 }, { "epoch": 0.03836048747232882, "grad_norm": 0.18116861581802368, "learning_rate": 8.34486763546583e-06, "loss": 10.1413, "step": 1252 }, { "epoch": 0.0383911268393195, "grad_norm": 0.2669692635536194, "learning_rate": 8.288279581649528e-06, "loss": 10.1333, "step": 1253 }, { "epoch": 0.03842176620631018, "grad_norm": 0.15294544398784637, "learning_rate": 8.231866703341596e-06, "loss": 10.1443, "step": 1254 }, { "epoch": 0.03845240557330085, "grad_norm": 0.11219369620084763, "learning_rate": 8.175629237457616e-06, "loss": 10.1343, "step": 1255 }, { "epoch": 0.03848304494029153, "grad_norm": 0.1142490804195404, "learning_rate": 8.11956742017641e-06, "loss": 10.127, "step": 1256 }, { "epoch": 0.03851368430728221, "grad_norm": 0.07548080384731293, "learning_rate": 8.063681486939213e-06, "loss": 10.1138, "step": 1257 }, { "epoch": 0.03854432367427289, "grad_norm": 0.09492000937461853, "learning_rate": 8.00797167244851e-06, "loss": 10.106, "step": 1258 }, { "epoch": 0.038574963041263566, "grad_norm": 0.10051438957452774, "learning_rate": 7.952438210667268e-06, "loss": 10.1084, "step": 1259 }, { "epoch": 0.038605602408254246, "grad_norm": 0.09662171453237534, "learning_rate": 7.897081334817718e-06, "loss": 10.1085, "step": 1260 }, { "epoch": 0.038636241775244926, "grad_norm": 0.08871396631002426, "learning_rate": 7.841901277380554e-06, "loss": 10.1093, "step": 1261 }, { "epoch": 0.0386668811422356, "grad_norm": 0.10740526765584946, "learning_rate": 7.786898270093846e-06, "loss": 10.112, "step": 1262 }, { "epoch": 0.03869752050922628, "grad_norm": 0.11950792372226715, "learning_rate": 7.732072543952174e-06, "loss": 10.117, "step": 1263 }, { "epoch": 0.03872815987621696, "grad_norm": 0.11587467044591904, "learning_rate": 7.677424329205524e-06, "loss": 10.1146, "step": 1264 }, { "epoch": 0.03875879924320764, "grad_norm": 0.11771164834499359, "learning_rate": 7.6229538553584556e-06, "loss": 10.1147, "step": 1265 }, { "epoch": 0.03878943861019831, "grad_norm": 0.09956104308366776, "learning_rate": 7.568661351169004e-06, "loss": 10.1125, "step": 1266 }, { "epoch": 0.03882007797718899, "grad_norm": 0.12855617702007294, "learning_rate": 7.514547044647885e-06, "loss": 10.1153, "step": 1267 }, { "epoch": 0.03885071734417967, "grad_norm": 0.14286097884178162, "learning_rate": 7.460611163057346e-06, "loss": 10.1248, "step": 1268 }, { "epoch": 0.03888135671117035, "grad_norm": 0.12999552488327026, "learning_rate": 7.406853932910374e-06, "loss": 10.117, "step": 1269 }, { "epoch": 0.038911996078161024, "grad_norm": 0.13841578364372253, "learning_rate": 7.353275579969649e-06, "loss": 10.1211, "step": 1270 }, { "epoch": 0.0389426354451517, "grad_norm": 0.15447473526000977, "learning_rate": 7.299876329246652e-06, "loss": 10.1165, "step": 1271 }, { "epoch": 0.03897327481214238, "grad_norm": 0.10077615082263947, "learning_rate": 7.246656405000646e-06, "loss": 10.1325, "step": 1272 }, { "epoch": 0.039003914179133056, "grad_norm": 0.1108795553445816, "learning_rate": 7.193616030737821e-06, "loss": 10.1157, "step": 1273 }, { "epoch": 0.039034553546123736, "grad_norm": 0.10978998988866806, "learning_rate": 7.140755429210316e-06, "loss": 10.1078, "step": 1274 }, { "epoch": 0.039065192913114416, "grad_norm": 0.11849291622638702, "learning_rate": 7.088074822415275e-06, "loss": 10.1044, "step": 1275 }, { "epoch": 0.039095832280105096, "grad_norm": 0.14952406287193298, "learning_rate": 7.035574431593906e-06, "loss": 10.1028, "step": 1276 }, { "epoch": 0.03912647164709577, "grad_norm": 0.17493416368961334, "learning_rate": 6.983254477230588e-06, "loss": 10.1017, "step": 1277 }, { "epoch": 0.03915711101408645, "grad_norm": 0.1578812152147293, "learning_rate": 6.931115179051934e-06, "loss": 10.0983, "step": 1278 }, { "epoch": 0.03918775038107713, "grad_norm": 0.17391373217105865, "learning_rate": 6.879156756025851e-06, "loss": 10.1091, "step": 1279 }, { "epoch": 0.0392183897480678, "grad_norm": 0.21040014922618866, "learning_rate": 6.827379426360614e-06, "loss": 10.1, "step": 1280 }, { "epoch": 0.03924902911505848, "grad_norm": 0.14727576076984406, "learning_rate": 6.775783407503988e-06, "loss": 10.1171, "step": 1281 }, { "epoch": 0.03927966848204916, "grad_norm": 0.1900489181280136, "learning_rate": 6.724368916142282e-06, "loss": 10.1289, "step": 1282 }, { "epoch": 0.03931030784903984, "grad_norm": 0.1603669375181198, "learning_rate": 6.673136168199467e-06, "loss": 10.1336, "step": 1283 }, { "epoch": 0.039340947216030514, "grad_norm": 0.14702396094799042, "learning_rate": 6.622085378836213e-06, "loss": 10.1318, "step": 1284 }, { "epoch": 0.039371586583021194, "grad_norm": 0.19212625920772552, "learning_rate": 6.571216762449051e-06, "loss": 10.1358, "step": 1285 }, { "epoch": 0.039402225950011874, "grad_norm": 0.17218048870563507, "learning_rate": 6.52053053266945e-06, "loss": 10.126, "step": 1286 }, { "epoch": 0.039432865317002554, "grad_norm": 0.07660984992980957, "learning_rate": 6.470026902362913e-06, "loss": 10.1014, "step": 1287 }, { "epoch": 0.03946350468399323, "grad_norm": 0.09120167046785355, "learning_rate": 6.419706083628063e-06, "loss": 10.1022, "step": 1288 }, { "epoch": 0.039494144050983906, "grad_norm": 0.10542449355125427, "learning_rate": 6.369568287795791e-06, "loss": 10.0989, "step": 1289 }, { "epoch": 0.039524783417974586, "grad_norm": 0.07916504144668579, "learning_rate": 6.319613725428352e-06, "loss": 10.1024, "step": 1290 }, { "epoch": 0.03955542278496526, "grad_norm": 0.1278640478849411, "learning_rate": 6.269842606318499e-06, "loss": 10.0996, "step": 1291 }, { "epoch": 0.03958606215195594, "grad_norm": 0.2218398004770279, "learning_rate": 6.22025513948854e-06, "loss": 10.089, "step": 1292 }, { "epoch": 0.03961670151894662, "grad_norm": 0.19924089312553406, "learning_rate": 6.170851533189537e-06, "loss": 10.0913, "step": 1293 }, { "epoch": 0.0396473408859373, "grad_norm": 0.26216378808021545, "learning_rate": 6.121631994900384e-06, "loss": 10.093, "step": 1294 }, { "epoch": 0.03967798025292797, "grad_norm": 0.1728447824716568, "learning_rate": 6.0725967313269736e-06, "loss": 10.1053, "step": 1295 }, { "epoch": 0.03970861961991865, "grad_norm": 0.10329534113407135, "learning_rate": 6.0237459484012605e-06, "loss": 10.1088, "step": 1296 }, { "epoch": 0.03973925898690933, "grad_norm": 0.15759865939617157, "learning_rate": 5.975079851280496e-06, "loss": 10.1017, "step": 1297 }, { "epoch": 0.03976989835390001, "grad_norm": 0.21580256521701813, "learning_rate": 5.926598644346259e-06, "loss": 10.1064, "step": 1298 }, { "epoch": 0.039800537720890684, "grad_norm": 0.30422547459602356, "learning_rate": 5.8783025312037e-06, "loss": 10.1056, "step": 1299 }, { "epoch": 0.039831177087881364, "grad_norm": 0.2916965186595917, "learning_rate": 5.830191714680577e-06, "loss": 10.0905, "step": 1300 }, { "epoch": 0.039861816454872044, "grad_norm": 0.11551357805728912, "learning_rate": 5.782266396826536e-06, "loss": 10.1425, "step": 1301 }, { "epoch": 0.03989245582186272, "grad_norm": 0.24818098545074463, "learning_rate": 5.734526778912119e-06, "loss": 10.1344, "step": 1302 }, { "epoch": 0.0399230951888534, "grad_norm": 0.22023114562034607, "learning_rate": 5.686973061428053e-06, "loss": 10.1452, "step": 1303 }, { "epoch": 0.03995373455584408, "grad_norm": 0.1549285501241684, "learning_rate": 5.639605444084273e-06, "loss": 10.1389, "step": 1304 }, { "epoch": 0.03998437392283476, "grad_norm": 0.1981198936700821, "learning_rate": 5.592424125809237e-06, "loss": 10.1328, "step": 1305 }, { "epoch": 0.04001501328982543, "grad_norm": 0.08430387079715729, "learning_rate": 5.545429304748934e-06, "loss": 10.1126, "step": 1306 }, { "epoch": 0.04004565265681611, "grad_norm": 0.0871620774269104, "learning_rate": 5.498621178266167e-06, "loss": 10.1063, "step": 1307 }, { "epoch": 0.04007629202380679, "grad_norm": 0.11557551473379135, "learning_rate": 5.4519999429396785e-06, "loss": 10.102, "step": 1308 }, { "epoch": 0.04010693139079747, "grad_norm": 0.09451328963041306, "learning_rate": 5.405565794563333e-06, "loss": 10.1063, "step": 1309 }, { "epoch": 0.04013757075778814, "grad_norm": 0.09066541492938995, "learning_rate": 5.3593189281452625e-06, "loss": 10.1078, "step": 1310 }, { "epoch": 0.04016821012477882, "grad_norm": 0.09137746691703796, "learning_rate": 5.313259537907106e-06, "loss": 10.1093, "step": 1311 }, { "epoch": 0.0401988494917695, "grad_norm": 0.1152050718665123, "learning_rate": 5.26738781728316e-06, "loss": 10.1123, "step": 1312 }, { "epoch": 0.040229488858760175, "grad_norm": 0.12141226977109909, "learning_rate": 5.221703958919572e-06, "loss": 10.1159, "step": 1313 }, { "epoch": 0.040260128225750855, "grad_norm": 0.11767212301492691, "learning_rate": 5.176208154673501e-06, "loss": 10.1148, "step": 1314 }, { "epoch": 0.040290767592741535, "grad_norm": 0.12066911906003952, "learning_rate": 5.130900595612381e-06, "loss": 10.1139, "step": 1315 }, { "epoch": 0.040321406959732214, "grad_norm": 0.09035047143697739, "learning_rate": 5.085781472013051e-06, "loss": 10.1112, "step": 1316 }, { "epoch": 0.04035204632672289, "grad_norm": 0.0878148004412651, "learning_rate": 5.040850973361006e-06, "loss": 10.1193, "step": 1317 }, { "epoch": 0.04038268569371357, "grad_norm": 0.10957963764667511, "learning_rate": 4.996109288349549e-06, "loss": 10.1204, "step": 1318 }, { "epoch": 0.04041332506070425, "grad_norm": 0.17014451324939728, "learning_rate": 4.951556604879048e-06, "loss": 10.1145, "step": 1319 }, { "epoch": 0.04044396442769493, "grad_norm": 0.10729119181632996, "learning_rate": 4.9071931100561185e-06, "loss": 10.112, "step": 1320 }, { "epoch": 0.0404746037946856, "grad_norm": 0.08621664345264435, "learning_rate": 4.863018990192869e-06, "loss": 10.1159, "step": 1321 }, { "epoch": 0.04050524316167628, "grad_norm": 0.14119024574756622, "learning_rate": 4.819034430806046e-06, "loss": 10.1205, "step": 1322 }, { "epoch": 0.04053588252866696, "grad_norm": 0.11444737762212753, "learning_rate": 4.7752396166163505e-06, "loss": 10.1068, "step": 1323 }, { "epoch": 0.04056652189565763, "grad_norm": 0.15885058045387268, "learning_rate": 4.731634731547601e-06, "loss": 10.1111, "step": 1324 }, { "epoch": 0.04059716126264831, "grad_norm": 0.16567274928092957, "learning_rate": 4.688219958725981e-06, "loss": 10.1034, "step": 1325 }, { "epoch": 0.04062780062963899, "grad_norm": 0.17553022503852844, "learning_rate": 4.644995480479236e-06, "loss": 10.1003, "step": 1326 }, { "epoch": 0.04065843999662967, "grad_norm": 0.17346560955047607, "learning_rate": 4.601961478335975e-06, "loss": 10.1025, "step": 1327 }, { "epoch": 0.040689079363620345, "grad_norm": 0.1489420384168625, "learning_rate": 4.559118133024853e-06, "loss": 10.112, "step": 1328 }, { "epoch": 0.040719718730611025, "grad_norm": 0.1875048726797104, "learning_rate": 4.516465624473843e-06, "loss": 10.0966, "step": 1329 }, { "epoch": 0.040750358097601705, "grad_norm": 0.2288949340581894, "learning_rate": 4.474004131809429e-06, "loss": 10.0964, "step": 1330 }, { "epoch": 0.040780997464592385, "grad_norm": 0.1559707224369049, "learning_rate": 4.431733833355933e-06, "loss": 10.1234, "step": 1331 }, { "epoch": 0.04081163683158306, "grad_norm": 0.18989545106887817, "learning_rate": 4.389654906634705e-06, "loss": 10.1329, "step": 1332 }, { "epoch": 0.04084227619857374, "grad_norm": 0.15404652059078217, "learning_rate": 4.3477675283634e-06, "loss": 10.1255, "step": 1333 }, { "epoch": 0.04087291556556442, "grad_norm": 0.20747429132461548, "learning_rate": 4.3060718744552256e-06, "loss": 10.1412, "step": 1334 }, { "epoch": 0.04090355493255509, "grad_norm": 0.18440188467502594, "learning_rate": 4.26456812001822e-06, "loss": 10.1317, "step": 1335 }, { "epoch": 0.04093419429954577, "grad_norm": 0.23921966552734375, "learning_rate": 4.223256439354506e-06, "loss": 10.1369, "step": 1336 }, { "epoch": 0.04096483366653645, "grad_norm": 0.11896178871393204, "learning_rate": 4.1821370059595575e-06, "loss": 10.1148, "step": 1337 }, { "epoch": 0.04099547303352713, "grad_norm": 0.0670604407787323, "learning_rate": 4.14120999252145e-06, "loss": 10.1017, "step": 1338 }, { "epoch": 0.0410261124005178, "grad_norm": 0.07954248040914536, "learning_rate": 4.10047557092022e-06, "loss": 10.1003, "step": 1339 }, { "epoch": 0.04105675176750848, "grad_norm": 0.1168399229645729, "learning_rate": 4.05993391222701e-06, "loss": 10.0963, "step": 1340 }, { "epoch": 0.04108739113449916, "grad_norm": 0.22702127695083618, "learning_rate": 4.0195851867034785e-06, "loss": 10.0913, "step": 1341 }, { "epoch": 0.04111803050148984, "grad_norm": 0.1319252997636795, "learning_rate": 3.979429563800968e-06, "loss": 10.0979, "step": 1342 }, { "epoch": 0.041148669868480515, "grad_norm": 0.24066847562789917, "learning_rate": 3.939467212159925e-06, "loss": 10.0887, "step": 1343 }, { "epoch": 0.041179309235471195, "grad_norm": 0.2199808955192566, "learning_rate": 3.899698299609067e-06, "loss": 10.0929, "step": 1344 }, { "epoch": 0.041209948602461875, "grad_norm": 0.19464479386806488, "learning_rate": 3.860122993164761e-06, "loss": 10.096, "step": 1345 }, { "epoch": 0.04124058796945255, "grad_norm": 0.07961917668581009, "learning_rate": 3.820741459030253e-06, "loss": 10.111, "step": 1346 }, { "epoch": 0.04127122733644323, "grad_norm": 0.1435251384973526, "learning_rate": 3.7815538625950665e-06, "loss": 10.1128, "step": 1347 }, { "epoch": 0.04130186670343391, "grad_norm": 0.1744510978460312, "learning_rate": 3.7425603684342003e-06, "loss": 10.1106, "step": 1348 }, { "epoch": 0.04133250607042459, "grad_norm": 0.2808617353439331, "learning_rate": 3.70376114030751e-06, "loss": 10.1096, "step": 1349 }, { "epoch": 0.04136314543741526, "grad_norm": 0.2482672482728958, "learning_rate": 3.6651563411589927e-06, "loss": 10.0973, "step": 1350 }, { "epoch": 0.04139378480440594, "grad_norm": 0.11324569582939148, "learning_rate": 3.6267461331161213e-06, "loss": 10.1308, "step": 1351 }, { "epoch": 0.04142442417139662, "grad_norm": 0.1877259761095047, "learning_rate": 3.5885306774891215e-06, "loss": 10.1509, "step": 1352 }, { "epoch": 0.0414550635383873, "grad_norm": 0.28266143798828125, "learning_rate": 3.5505101347703462e-06, "loss": 10.1398, "step": 1353 }, { "epoch": 0.04148570290537797, "grad_norm": 0.16005541384220123, "learning_rate": 3.5126846646335753e-06, "loss": 10.1396, "step": 1354 }, { "epoch": 0.04151634227236865, "grad_norm": 0.14857356250286102, "learning_rate": 3.475054425933344e-06, "loss": 10.1264, "step": 1355 }, { "epoch": 0.04154698163935933, "grad_norm": 0.08006827533245087, "learning_rate": 3.437619576704271e-06, "loss": 10.1152, "step": 1356 }, { "epoch": 0.041577621006350006, "grad_norm": 0.08990669995546341, "learning_rate": 3.400380274160414e-06, "loss": 10.1058, "step": 1357 }, { "epoch": 0.041608260373340686, "grad_norm": 0.11583833396434784, "learning_rate": 3.3633366746946004e-06, "loss": 10.1014, "step": 1358 }, { "epoch": 0.041638899740331366, "grad_norm": 0.09854194521903992, "learning_rate": 3.326488933877775e-06, "loss": 10.104, "step": 1359 }, { "epoch": 0.041669539107322046, "grad_norm": 0.0991731733083725, "learning_rate": 3.289837206458313e-06, "loss": 10.1055, "step": 1360 }, { "epoch": 0.04170017847431272, "grad_norm": 0.10558903962373734, "learning_rate": 3.2533816463614253e-06, "loss": 10.1046, "step": 1361 }, { "epoch": 0.0417308178413034, "grad_norm": 0.11268564313650131, "learning_rate": 3.2171224066884775e-06, "loss": 10.1172, "step": 1362 }, { "epoch": 0.04176145720829408, "grad_norm": 0.11147574335336685, "learning_rate": 3.181059639716355e-06, "loss": 10.1179, "step": 1363 }, { "epoch": 0.04179209657528475, "grad_norm": 0.10818634927272797, "learning_rate": 3.145193496896809e-06, "loss": 10.1159, "step": 1364 }, { "epoch": 0.04182273594227543, "grad_norm": 0.14246492087841034, "learning_rate": 3.109524128855851e-06, "loss": 10.1174, "step": 1365 }, { "epoch": 0.04185337530926611, "grad_norm": 0.1124851182103157, "learning_rate": 3.0740516853930977e-06, "loss": 10.1131, "step": 1366 }, { "epoch": 0.04188401467625679, "grad_norm": 0.126473531126976, "learning_rate": 3.0387763154811454e-06, "loss": 10.1197, "step": 1367 }, { "epoch": 0.041914654043247464, "grad_norm": 0.10183607786893845, "learning_rate": 3.00369816726494e-06, "loss": 10.1157, "step": 1368 }, { "epoch": 0.041945293410238144, "grad_norm": 0.15727828443050385, "learning_rate": 2.968817388061174e-06, "loss": 10.1189, "step": 1369 }, { "epoch": 0.041975932777228823, "grad_norm": 0.09076463431119919, "learning_rate": 2.934134124357646e-06, "loss": 10.1211, "step": 1370 }, { "epoch": 0.0420065721442195, "grad_norm": 0.0855158120393753, "learning_rate": 2.89964852181267e-06, "loss": 10.1147, "step": 1371 }, { "epoch": 0.042037211511210176, "grad_norm": 0.14145579934120178, "learning_rate": 2.8653607252544236e-06, "loss": 10.1137, "step": 1372 }, { "epoch": 0.042067850878200856, "grad_norm": 0.09084680676460266, "learning_rate": 2.83127087868037e-06, "loss": 10.1136, "step": 1373 }, { "epoch": 0.042098490245191536, "grad_norm": 0.15182866156101227, "learning_rate": 2.7973791252566663e-06, "loss": 10.1095, "step": 1374 }, { "epoch": 0.04212912961218221, "grad_norm": 0.16544382274150848, "learning_rate": 2.76368560731754e-06, "loss": 10.1055, "step": 1375 }, { "epoch": 0.04215976897917289, "grad_norm": 0.17622704803943634, "learning_rate": 2.7301904663646516e-06, "loss": 10.0998, "step": 1376 }, { "epoch": 0.04219040834616357, "grad_norm": 0.17642687261104584, "learning_rate": 2.6968938430666168e-06, "loss": 10.1013, "step": 1377 }, { "epoch": 0.04222104771315425, "grad_norm": 0.18795837461948395, "learning_rate": 2.6637958772582794e-06, "loss": 10.0968, "step": 1378 }, { "epoch": 0.04225168708014492, "grad_norm": 0.21108628809452057, "learning_rate": 2.630896707940228e-06, "loss": 10.1009, "step": 1379 }, { "epoch": 0.0422823264471356, "grad_norm": 0.2268962413072586, "learning_rate": 2.5981964732781307e-06, "loss": 10.1022, "step": 1380 }, { "epoch": 0.04231296581412628, "grad_norm": 0.15077438950538635, "learning_rate": 2.565695310602245e-06, "loss": 10.1277, "step": 1381 }, { "epoch": 0.04234360518111696, "grad_norm": 0.19621235132217407, "learning_rate": 2.5333933564067492e-06, "loss": 10.1359, "step": 1382 }, { "epoch": 0.042374244548107634, "grad_norm": 0.20292441546916962, "learning_rate": 2.5012907463492387e-06, "loss": 10.1418, "step": 1383 }, { "epoch": 0.042404883915098314, "grad_norm": 0.22173507511615753, "learning_rate": 2.469387615250096e-06, "loss": 10.1399, "step": 1384 }, { "epoch": 0.042435523282088994, "grad_norm": 0.1759355664253235, "learning_rate": 2.4376840970920134e-06, "loss": 10.1346, "step": 1385 }, { "epoch": 0.04246616264907967, "grad_norm": 0.18848684430122375, "learning_rate": 2.406180325019319e-06, "loss": 10.1282, "step": 1386 }, { "epoch": 0.04249680201607035, "grad_norm": 0.06980546563863754, "learning_rate": 2.374876431337503e-06, "loss": 10.0977, "step": 1387 }, { "epoch": 0.042527441383061027, "grad_norm": 0.09858546406030655, "learning_rate": 2.343772547512613e-06, "loss": 10.0956, "step": 1388 }, { "epoch": 0.042558080750051706, "grad_norm": 0.08779535442590714, "learning_rate": 2.3128688041707536e-06, "loss": 10.0945, "step": 1389 }, { "epoch": 0.04258872011704238, "grad_norm": 0.1176782175898552, "learning_rate": 2.2821653310974635e-06, "loss": 10.0964, "step": 1390 }, { "epoch": 0.04261935948403306, "grad_norm": 0.1882256269454956, "learning_rate": 2.2516622572372414e-06, "loss": 10.0937, "step": 1391 }, { "epoch": 0.04264999885102374, "grad_norm": 0.1728634238243103, "learning_rate": 2.221359710692961e-06, "loss": 10.0955, "step": 1392 }, { "epoch": 0.04268063821801442, "grad_norm": 0.22270867228507996, "learning_rate": 2.1912578187253674e-06, "loss": 10.091, "step": 1393 }, { "epoch": 0.04271127758500509, "grad_norm": 0.16380862891674042, "learning_rate": 2.1613567077524875e-06, "loss": 10.0988, "step": 1394 }, { "epoch": 0.04274191695199577, "grad_norm": 0.09706560522317886, "learning_rate": 2.1316565033491666e-06, "loss": 10.1146, "step": 1395 }, { "epoch": 0.04277255631898645, "grad_norm": 0.17141427099704742, "learning_rate": 2.1021573302464904e-06, "loss": 10.1136, "step": 1396 }, { "epoch": 0.042803195685977125, "grad_norm": 0.2118794471025467, "learning_rate": 2.0728593123312935e-06, "loss": 10.1132, "step": 1397 }, { "epoch": 0.042833835052967804, "grad_norm": 0.2561670243740082, "learning_rate": 2.043762572645602e-06, "loss": 10.1038, "step": 1398 }, { "epoch": 0.042864474419958484, "grad_norm": 0.281943142414093, "learning_rate": 2.014867233386164e-06, "loss": 10.1048, "step": 1399 }, { "epoch": 0.042895113786949164, "grad_norm": 0.23076589405536652, "learning_rate": 1.9861734159038968e-06, "loss": 10.0946, "step": 1400 }, { "epoch": 0.04292575315393984, "grad_norm": 0.1402137726545334, "learning_rate": 1.957681240703407e-06, "loss": 10.1329, "step": 1401 }, { "epoch": 0.04295639252093052, "grad_norm": 0.16458432376384735, "learning_rate": 1.9293908274424455e-06, "loss": 10.1374, "step": 1402 }, { "epoch": 0.0429870318879212, "grad_norm": 0.2683012783527374, "learning_rate": 1.9013022949314563e-06, "loss": 10.1425, "step": 1403 }, { "epoch": 0.04301767125491188, "grad_norm": 0.16290165483951569, "learning_rate": 1.8734157611330293e-06, "loss": 10.1444, "step": 1404 }, { "epoch": 0.04304831062190255, "grad_norm": 0.09829044342041016, "learning_rate": 1.8457313431614498e-06, "loss": 10.1215, "step": 1405 }, { "epoch": 0.04307894998889323, "grad_norm": 0.09291593730449677, "learning_rate": 1.8182491572821536e-06, "loss": 10.1108, "step": 1406 }, { "epoch": 0.04310958935588391, "grad_norm": 0.09305530041456223, "learning_rate": 1.7909693189112897e-06, "loss": 10.1068, "step": 1407 }, { "epoch": 0.04314022872287458, "grad_norm": 0.11230731755495071, "learning_rate": 1.7638919426152146e-06, "loss": 10.1078, "step": 1408 }, { "epoch": 0.04317086808986526, "grad_norm": 0.14091169834136963, "learning_rate": 1.7370171421099978e-06, "loss": 10.1065, "step": 1409 }, { "epoch": 0.04320150745685594, "grad_norm": 0.08318392932415009, "learning_rate": 1.710345030260957e-06, "loss": 10.1093, "step": 1410 }, { "epoch": 0.04323214682384662, "grad_norm": 0.16856053471565247, "learning_rate": 1.6838757190822007e-06, "loss": 10.1183, "step": 1411 }, { "epoch": 0.043262786190837295, "grad_norm": 0.11230144649744034, "learning_rate": 1.6576093197361253e-06, "loss": 10.1123, "step": 1412 }, { "epoch": 0.043293425557827975, "grad_norm": 0.10174106061458588, "learning_rate": 1.631545942532975e-06, "loss": 10.1131, "step": 1413 }, { "epoch": 0.043324064924818655, "grad_norm": 0.10370048880577087, "learning_rate": 1.605685696930359e-06, "loss": 10.1117, "step": 1414 }, { "epoch": 0.043354704291809334, "grad_norm": 0.12338165193796158, "learning_rate": 1.5800286915328033e-06, "loss": 10.1083, "step": 1415 }, { "epoch": 0.04338534365880001, "grad_norm": 0.12942077219486237, "learning_rate": 1.5545750340912991e-06, "loss": 10.1172, "step": 1416 }, { "epoch": 0.04341598302579069, "grad_norm": 0.08702339977025986, "learning_rate": 1.5293248315028319e-06, "loss": 10.1129, "step": 1417 }, { "epoch": 0.04344662239278137, "grad_norm": 0.12942220270633698, "learning_rate": 1.5042781898099434e-06, "loss": 10.1111, "step": 1418 }, { "epoch": 0.04347726175977204, "grad_norm": 0.14795805513858795, "learning_rate": 1.4794352142003087e-06, "loss": 10.1236, "step": 1419 }, { "epoch": 0.04350790112676272, "grad_norm": 0.11648901551961899, "learning_rate": 1.4547960090062374e-06, "loss": 10.1192, "step": 1420 }, { "epoch": 0.0435385404937534, "grad_norm": 0.09025874733924866, "learning_rate": 1.430360677704301e-06, "loss": 10.1215, "step": 1421 }, { "epoch": 0.04356917986074408, "grad_norm": 0.1041576936841011, "learning_rate": 1.4061293229148399e-06, "loss": 10.1217, "step": 1422 }, { "epoch": 0.04359981922773475, "grad_norm": 0.12477923929691315, "learning_rate": 1.3821020464015956e-06, "loss": 10.1044, "step": 1423 }, { "epoch": 0.04363045859472543, "grad_norm": 0.16487959027290344, "learning_rate": 1.3582789490712179e-06, "loss": 10.1084, "step": 1424 }, { "epoch": 0.04366109796171611, "grad_norm": 0.15673759579658508, "learning_rate": 1.3346601309728812e-06, "loss": 10.1113, "step": 1425 }, { "epoch": 0.04369173732870679, "grad_norm": 0.17070582509040833, "learning_rate": 1.3112456912978465e-06, "loss": 10.1094, "step": 1426 }, { "epoch": 0.043722376695697465, "grad_norm": 0.14337854087352753, "learning_rate": 1.2880357283790777e-06, "loss": 10.1059, "step": 1427 }, { "epoch": 0.043753016062688145, "grad_norm": 0.1527278870344162, "learning_rate": 1.2650303396907704e-06, "loss": 10.1001, "step": 1428 }, { "epoch": 0.043783655429678825, "grad_norm": 0.19555500149726868, "learning_rate": 1.2422296218479955e-06, "loss": 10.1021, "step": 1429 }, { "epoch": 0.0438142947966695, "grad_norm": 0.22751495242118835, "learning_rate": 1.2196336706062739e-06, "loss": 10.1004, "step": 1430 }, { "epoch": 0.04384493416366018, "grad_norm": 0.12596385180950165, "learning_rate": 1.1972425808611742e-06, "loss": 10.1392, "step": 1431 }, { "epoch": 0.04387557353065086, "grad_norm": 0.17588672041893005, "learning_rate": 1.1750564466478986e-06, "loss": 10.1468, "step": 1432 }, { "epoch": 0.04390621289764154, "grad_norm": 0.1698489636182785, "learning_rate": 1.153075361140915e-06, "loss": 10.1367, "step": 1433 }, { "epoch": 0.04393685226463221, "grad_norm": 0.20583803951740265, "learning_rate": 1.131299416653564e-06, "loss": 10.139, "step": 1434 }, { "epoch": 0.04396749163162289, "grad_norm": 0.22030790150165558, "learning_rate": 1.109728704637647e-06, "loss": 10.1382, "step": 1435 }, { "epoch": 0.04399813099861357, "grad_norm": 0.14688998460769653, "learning_rate": 1.0883633156830553e-06, "loss": 10.1272, "step": 1436 }, { "epoch": 0.04402877036560425, "grad_norm": 0.1031157374382019, "learning_rate": 1.0672033395173974e-06, "loss": 10.1165, "step": 1437 }, { "epoch": 0.04405940973259492, "grad_norm": 0.09834488481283188, "learning_rate": 1.0462488650056168e-06, "loss": 10.1037, "step": 1438 }, { "epoch": 0.0440900490995856, "grad_norm": 0.08310945332050323, "learning_rate": 1.0254999801496247e-06, "loss": 10.0979, "step": 1439 }, { "epoch": 0.04412068846657628, "grad_norm": 0.09247684478759766, "learning_rate": 1.004956772087895e-06, "loss": 10.0946, "step": 1440 }, { "epoch": 0.044151327833566956, "grad_norm": 0.1530849188566208, "learning_rate": 9.8461932709516e-07, "loss": 10.0964, "step": 1441 }, { "epoch": 0.044181967200557636, "grad_norm": 0.169045552611351, "learning_rate": 9.644877305819976e-07, "loss": 10.0942, "step": 1442 }, { "epoch": 0.044212606567548315, "grad_norm": 0.199153333902359, "learning_rate": 9.445620670944899e-07, "loss": 10.0944, "step": 1443 }, { "epoch": 0.044243245934538995, "grad_norm": 0.28431570529937744, "learning_rate": 9.248424203138706e-07, "loss": 10.0892, "step": 1444 }, { "epoch": 0.04427388530152967, "grad_norm": 0.1420593559741974, "learning_rate": 9.053288730561716e-07, "loss": 10.1022, "step": 1445 }, { "epoch": 0.04430452466852035, "grad_norm": 0.13696978986263275, "learning_rate": 8.86021507271878e-07, "loss": 10.1259, "step": 1446 }, { "epoch": 0.04433516403551103, "grad_norm": 0.22393156588077545, "learning_rate": 8.669204040455736e-07, "loss": 10.1148, "step": 1447 }, { "epoch": 0.0443658034025017, "grad_norm": 0.24310295283794403, "learning_rate": 8.480256435956124e-07, "loss": 10.1089, "step": 1448 }, { "epoch": 0.04439644276949238, "grad_norm": 0.27099770307540894, "learning_rate": 8.293373052737641e-07, "loss": 10.1086, "step": 1449 }, { "epoch": 0.04442708213648306, "grad_norm": 0.270480751991272, "learning_rate": 8.108554675649194e-07, "loss": 10.0992, "step": 1450 }, { "epoch": 0.04445772150347374, "grad_norm": 0.1927180141210556, "learning_rate": 7.925802080867128e-07, "loss": 10.1662, "step": 1451 }, { "epoch": 0.04448836087046441, "grad_norm": 0.2981465458869934, "learning_rate": 7.745116035892175e-07, "loss": 10.1244, "step": 1452 }, { "epoch": 0.04451900023745509, "grad_norm": 0.23562270402908325, "learning_rate": 7.566497299546393e-07, "loss": 10.1341, "step": 1453 }, { "epoch": 0.04454963960444577, "grad_norm": 0.12152570486068726, "learning_rate": 7.389946621969679e-07, "loss": 10.1264, "step": 1454 }, { "epoch": 0.04458027897143645, "grad_norm": 0.09911651164293289, "learning_rate": 7.215464744616873e-07, "loss": 10.1217, "step": 1455 }, { "epoch": 0.044610918338427126, "grad_norm": 0.08168809115886688, "learning_rate": 7.043052400254435e-07, "loss": 10.1086, "step": 1456 }, { "epoch": 0.044641557705417806, "grad_norm": 0.09287815541028976, "learning_rate": 6.872710312957497e-07, "loss": 10.1076, "step": 1457 }, { "epoch": 0.044672197072408486, "grad_norm": 0.09810962527990341, "learning_rate": 6.704439198106815e-07, "loss": 10.1061, "step": 1458 }, { "epoch": 0.04470283643939916, "grad_norm": 0.1097896620631218, "learning_rate": 6.538239762385822e-07, "loss": 10.1074, "step": 1459 }, { "epoch": 0.04473347580638984, "grad_norm": 0.09674488008022308, "learning_rate": 6.374112703777301e-07, "loss": 10.1057, "step": 1460 }, { "epoch": 0.04476411517338052, "grad_norm": 0.12541504204273224, "learning_rate": 6.212058711561164e-07, "loss": 10.1166, "step": 1461 }, { "epoch": 0.0447947545403712, "grad_norm": 0.11652905493974686, "learning_rate": 6.052078466310673e-07, "loss": 10.1154, "step": 1462 }, { "epoch": 0.04482539390736187, "grad_norm": 0.10813118517398834, "learning_rate": 5.894172639890394e-07, "loss": 10.1144, "step": 1463 }, { "epoch": 0.04485603327435255, "grad_norm": 0.10338053107261658, "learning_rate": 5.738341895452748e-07, "loss": 10.1143, "step": 1464 }, { "epoch": 0.04488667264134323, "grad_norm": 0.08966199308633804, "learning_rate": 5.584586887435739e-07, "loss": 10.1169, "step": 1465 }, { "epoch": 0.04491731200833391, "grad_norm": 0.09585981070995331, "learning_rate": 5.432908261559733e-07, "loss": 10.1149, "step": 1466 }, { "epoch": 0.044947951375324584, "grad_norm": 0.17574290931224823, "learning_rate": 5.283306654825182e-07, "loss": 10.114, "step": 1467 }, { "epoch": 0.044978590742315264, "grad_norm": 0.16598477959632874, "learning_rate": 5.135782695509461e-07, "loss": 10.1172, "step": 1468 }, { "epoch": 0.045009230109305944, "grad_norm": 0.12351733446121216, "learning_rate": 4.990337003164924e-07, "loss": 10.1171, "step": 1469 }, { "epoch": 0.045039869476296616, "grad_norm": 0.07418365776538849, "learning_rate": 4.846970188615463e-07, "loss": 10.1158, "step": 1470 }, { "epoch": 0.045070508843287296, "grad_norm": 0.106537364423275, "learning_rate": 4.7056828539545627e-07, "loss": 10.1097, "step": 1471 }, { "epoch": 0.045101148210277976, "grad_norm": 0.11017125844955444, "learning_rate": 4.5664755925426403e-07, "loss": 10.1143, "step": 1472 }, { "epoch": 0.045131787577268656, "grad_norm": 0.1293984204530716, "learning_rate": 4.429348989004434e-07, "loss": 10.1067, "step": 1473 }, { "epoch": 0.04516242694425933, "grad_norm": 0.17226406931877136, "learning_rate": 4.294303619226503e-07, "loss": 10.105, "step": 1474 }, { "epoch": 0.04519306631125001, "grad_norm": 0.16253753006458282, "learning_rate": 4.1613400503550114e-07, "loss": 10.1034, "step": 1475 }, { "epoch": 0.04522370567824069, "grad_norm": 0.17170493304729462, "learning_rate": 4.030458840793228e-07, "loss": 10.1061, "step": 1476 }, { "epoch": 0.04525434504523137, "grad_norm": 0.17189715802669525, "learning_rate": 3.9016605401991924e-07, "loss": 10.0998, "step": 1477 }, { "epoch": 0.04528498441222204, "grad_norm": 0.18787235021591187, "learning_rate": 3.7749456894834447e-07, "loss": 10.0986, "step": 1478 }, { "epoch": 0.04531562377921272, "grad_norm": 0.24512790143489838, "learning_rate": 3.650314820806577e-07, "loss": 10.0938, "step": 1479 }, { "epoch": 0.0453462631462034, "grad_norm": 0.13357874751091003, "learning_rate": 3.5277684575774075e-07, "loss": 10.1167, "step": 1480 }, { "epoch": 0.045376902513194074, "grad_norm": 0.16420823335647583, "learning_rate": 3.4073071144502533e-07, "loss": 10.1382, "step": 1481 }, { "epoch": 0.045407541880184754, "grad_norm": 0.18857957422733307, "learning_rate": 3.288931297323161e-07, "loss": 10.1431, "step": 1482 }, { "epoch": 0.045438181247175434, "grad_norm": 0.20397290587425232, "learning_rate": 3.1726415033356273e-07, "loss": 10.1374, "step": 1483 }, { "epoch": 0.045468820614166114, "grad_norm": 0.23923923075199127, "learning_rate": 3.058438220866544e-07, "loss": 10.1457, "step": 1484 }, { "epoch": 0.04549945998115679, "grad_norm": 0.11020679026842117, "learning_rate": 2.9463219295322033e-07, "loss": 10.1164, "step": 1485 }, { "epoch": 0.04553009934814747, "grad_norm": 0.07260143011808395, "learning_rate": 2.836293100184073e-07, "loss": 10.1019, "step": 1486 }, { "epoch": 0.04556073871513815, "grad_norm": 0.09858629107475281, "learning_rate": 2.72835219490708e-07, "loss": 10.097, "step": 1487 }, { "epoch": 0.045591378082128826, "grad_norm": 0.10395541787147522, "learning_rate": 2.622499667017553e-07, "loss": 10.0954, "step": 1488 }, { "epoch": 0.0456220174491195, "grad_norm": 0.1422223597764969, "learning_rate": 2.5187359610612805e-07, "loss": 10.0974, "step": 1489 }, { "epoch": 0.04565265681611018, "grad_norm": 0.1788482517004013, "learning_rate": 2.4170615128117357e-07, "loss": 10.0958, "step": 1490 }, { "epoch": 0.04568329618310086, "grad_norm": 0.22789376974105835, "learning_rate": 2.317476749268077e-07, "loss": 10.0874, "step": 1491 }, { "epoch": 0.04571393555009153, "grad_norm": 0.16569283604621887, "learning_rate": 2.2199820886536492e-07, "loss": 10.1, "step": 1492 }, { "epoch": 0.04574457491708221, "grad_norm": 0.21699610352516174, "learning_rate": 2.12457794041393e-07, "loss": 10.0939, "step": 1493 }, { "epoch": 0.04577521428407289, "grad_norm": 0.23684826493263245, "learning_rate": 2.0312647052149746e-07, "loss": 10.0943, "step": 1494 }, { "epoch": 0.04580585365106357, "grad_norm": 0.13697533309459686, "learning_rate": 1.9400427749416418e-07, "loss": 10.1129, "step": 1495 }, { "epoch": 0.045836493018054245, "grad_norm": 0.1590232253074646, "learning_rate": 1.850912532696092e-07, "loss": 10.1118, "step": 1496 }, { "epoch": 0.045867132385044924, "grad_norm": 0.25585997104644775, "learning_rate": 1.763874352796069e-07, "loss": 10.1034, "step": 1497 }, { "epoch": 0.045897771752035604, "grad_norm": 0.24409626424312592, "learning_rate": 1.6789286007731775e-07, "loss": 10.1054, "step": 1498 }, { "epoch": 0.045928411119026284, "grad_norm": 0.26512911915779114, "learning_rate": 1.596075633371774e-07, "loss": 10.105, "step": 1499 }, { "epoch": 0.04595905048601696, "grad_norm": 0.2774305045604706, "learning_rate": 1.5153157985470235e-07, "loss": 10.0852, "step": 1500 }, { "epoch": 0.04598968985300764, "grad_norm": 0.15741734206676483, "learning_rate": 1.4366494354636218e-07, "loss": 10.1517, "step": 1501 }, { "epoch": 0.04602032921999832, "grad_norm": 0.18782265484333038, "learning_rate": 1.3600768744944647e-07, "loss": 10.1477, "step": 1502 }, { "epoch": 0.04605096858698899, "grad_norm": 0.2590548098087311, "learning_rate": 1.2855984372191487e-07, "loss": 10.138, "step": 1503 }, { "epoch": 0.04608160795397967, "grad_norm": 0.15205822885036469, "learning_rate": 1.2132144364225828e-07, "loss": 10.1409, "step": 1504 }, { "epoch": 0.04611224732097035, "grad_norm": 0.09880797564983368, "learning_rate": 1.1429251760938231e-07, "loss": 10.1195, "step": 1505 }, { "epoch": 0.04614288668796103, "grad_norm": 0.08121177554130554, "learning_rate": 1.074730951424574e-07, "loss": 10.1096, "step": 1506 }, { "epoch": 0.0461735260549517, "grad_norm": 0.09380342811346054, "learning_rate": 1.008632048808189e-07, "loss": 10.1038, "step": 1507 }, { "epoch": 0.04620416542194238, "grad_norm": 0.1085876002907753, "learning_rate": 9.446287458383385e-08, "loss": 10.1068, "step": 1508 }, { "epoch": 0.04623480478893306, "grad_norm": 0.08698976039886475, "learning_rate": 8.827213113077881e-08, "loss": 10.107, "step": 1509 }, { "epoch": 0.04626544415592374, "grad_norm": 0.08379095047712326, "learning_rate": 8.229100052074556e-08, "loss": 10.1078, "step": 1510 }, { "epoch": 0.046296083522914415, "grad_norm": 0.09639976173639297, "learning_rate": 7.651950787251339e-08, "loss": 10.1132, "step": 1511 }, { "epoch": 0.046326722889905095, "grad_norm": 0.11675218492746353, "learning_rate": 7.09576774244547e-08, "loss": 10.113, "step": 1512 }, { "epoch": 0.046357362256895775, "grad_norm": 0.08470741659402847, "learning_rate": 6.560553253442958e-08, "loss": 10.1076, "step": 1513 }, { "epoch": 0.04638800162388645, "grad_norm": 0.11935865879058838, "learning_rate": 6.046309567968588e-08, "loss": 10.1139, "step": 1514 }, { "epoch": 0.04641864099087713, "grad_norm": 0.11623800545930862, "learning_rate": 5.553038845676484e-08, "loss": 10.1122, "step": 1515 }, { "epoch": 0.04644928035786781, "grad_norm": 0.10663556307554245, "learning_rate": 5.080743158141221e-08, "loss": 10.1158, "step": 1516 }, { "epoch": 0.04647991972485849, "grad_norm": 0.1251857578754425, "learning_rate": 4.6294244888500645e-08, "loss": 10.1193, "step": 1517 }, { "epoch": 0.04651055909184916, "grad_norm": 0.1286596953868866, "learning_rate": 4.199084733192416e-08, "loss": 10.1298, "step": 1518 }, { "epoch": 0.04654119845883984, "grad_norm": 0.15580035746097565, "learning_rate": 3.7897256984542606e-08, "loss": 10.1127, "step": 1519 }, { "epoch": 0.04657183782583052, "grad_norm": 0.09604835510253906, "learning_rate": 3.4013491038087375e-08, "loss": 10.1209, "step": 1520 }, { "epoch": 0.0466024771928212, "grad_norm": 0.1219484955072403, "learning_rate": 3.033956580309472e-08, "loss": 10.1117, "step": 1521 }, { "epoch": 0.04663311655981187, "grad_norm": 0.12609413266181946, "learning_rate": 2.6875496708850255e-08, "loss": 10.1022, "step": 1522 }, { "epoch": 0.04666375592680255, "grad_norm": 0.1554422825574875, "learning_rate": 2.3621298303294625e-08, "loss": 10.1067, "step": 1523 }, { "epoch": 0.04669439529379323, "grad_norm": 0.15092980861663818, "learning_rate": 2.0576984252995703e-08, "loss": 10.1014, "step": 1524 }, { "epoch": 0.046725034660783905, "grad_norm": 0.17863760888576508, "learning_rate": 1.7742567343070892e-08, "loss": 10.1007, "step": 1525 }, { "epoch": 0.046755674027774585, "grad_norm": 0.1554519534111023, "learning_rate": 1.511805947714273e-08, "loss": 10.1016, "step": 1526 }, { "epoch": 0.046786313394765265, "grad_norm": 0.17655673623085022, "learning_rate": 1.2703471677277811e-08, "loss": 10.0991, "step": 1527 }, { "epoch": 0.046816952761755945, "grad_norm": 0.1972009688615799, "learning_rate": 1.0498814083953479e-08, "loss": 10.107, "step": 1528 }, { "epoch": 0.04684759212874662, "grad_norm": 0.11920743435621262, "learning_rate": 8.504095956002323e-09, "loss": 10.138, "step": 1529 }, { "epoch": 0.0468782314957373, "grad_norm": 0.15013860166072845, "learning_rate": 6.71932567058442e-09, "loss": 10.1349, "step": 1530 }, { "epoch": 0.04690887086272798, "grad_norm": 0.17592684924602509, "learning_rate": 5.144510723154028e-09, "loss": 10.1391, "step": 1531 }, { "epoch": 0.04693951022971865, "grad_norm": 0.16166475415229797, "learning_rate": 3.7796577274096245e-09, "loss": 10.1352, "step": 1532 }, { "epoch": 0.04697014959670933, "grad_norm": 0.22806517779827118, "learning_rate": 2.6247724152883567e-09, "loss": 10.1454, "step": 1533 }, { "epoch": 0.04700078896370001, "grad_norm": 0.23104527592658997, "learning_rate": 1.6798596369327345e-09, "loss": 10.1395, "step": 1534 }, { "epoch": 0.04703142833069069, "grad_norm": 0.14193491637706757, "learning_rate": 9.449233606573238e-10, "loss": 10.1265, "step": 1535 }, { "epoch": 0.04706206769768136, "grad_norm": 0.13836555182933807, "learning_rate": 4.1996667295429727e-10, "loss": 10.1181, "step": 1536 }, { "epoch": 0.04709270706467204, "grad_norm": 0.0696573406457901, "learning_rate": 1.0499177847123065e-10, "loss": 10.1068, "step": 1537 }, { "epoch": 0.04712334643166272, "grad_norm": 0.09298323839902878, "learning_rate": 0.0, "loss": 10.0964, "step": 1538 } ], "logging_steps": 1, "max_steps": 1538, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 385, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 160266508566528.0, "train_batch_size": 4, "trial_name": null, "trial_params": null }